<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD Journal Publishing DTD v2.3 20070202//EN" "journalpublishing.dtd">
<article article-type="review-article" dtd-version="2.3" xml:lang="EN" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">
<front>
<journal-meta>
<journal-id journal-id-type="publisher-id">Front. Genet.</journal-id>
<journal-title>Frontiers in Genetics</journal-title>
<abbrev-journal-title abbrev-type="pubmed">Front. Genet.</abbrev-journal-title>
<issn pub-type="epub">1664-8021</issn>
<publisher>
<publisher-name>Frontiers Media S.A.</publisher-name>
</publisher>
</journal-meta>
<article-meta>
<article-id pub-id-type="publisher-id">981005</article-id>
<article-id pub-id-type="doi">10.3389/fgene.2022.981005</article-id>
<article-categories>
<subj-group subj-group-type="heading">
<subject>Genetics</subject>
<subj-group>
<subject>Review</subject>
</subj-group>
</subj-group>
</article-categories>
<title-group>
<article-title>Computational approaches for predicting variant impact: An overview from resources, principles to applications</article-title>
<alt-title alt-title-type="left-running-head">Liu et al.</alt-title>
<alt-title alt-title-type="right-running-head">
<ext-link ext-link-type="uri" xlink:href="https://doi.org/10.3389/fgene.2022.981005">10.3389/fgene.2022.981005</ext-link>
</alt-title>
</title-group>
<contrib-group>
<contrib contrib-type="author">
<name>
<surname>Liu</surname>
<given-names>Ye</given-names>
</name>
<xref ref-type="aff" rid="aff1">
<sup>1</sup>
</xref>
<uri xlink:href="https://loop.frontiersin.org/people/1889635/overview"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname>Yeung</surname>
<given-names>William S. B.</given-names>
</name>
<xref ref-type="aff" rid="aff1">
<sup>1</sup>
</xref>
<xref ref-type="aff" rid="aff2">
<sup>2</sup>
</xref>
<uri xlink:href="https://loop.frontiersin.org/people/1022625/overview"/>
</contrib>
<contrib contrib-type="author" corresp="yes">
<name>
<surname>Chiu</surname>
<given-names>Philip C. N.</given-names>
</name>
<xref ref-type="aff" rid="aff1">
<sup>1</sup>
</xref>
<xref ref-type="aff" rid="aff2">
<sup>2</sup>
</xref>
<xref ref-type="corresp" rid="c001">&#x2a;</xref>
<uri xlink:href="https://loop.frontiersin.org/people/644882/overview"/>
</contrib>
<contrib contrib-type="author" corresp="yes">
<name>
<surname>Cao</surname>
<given-names>Dandan</given-names>
</name>
<xref ref-type="aff" rid="aff1">
<sup>1</sup>
</xref>
<xref ref-type="corresp" rid="c001">&#x2a;</xref>
<uri xlink:href="https://loop.frontiersin.org/people/1815332/overview"/>
</contrib>
</contrib-group>
<aff id="aff1">
<sup>1</sup>
<institution>Shenzhen Key Laboratory of Fertility Regulation</institution>, <institution>Reproductive Medicine Center</institution>, <institution>The University of Hong Kong-Shenzhen Hospital</institution>, <addr-line>Shenzhen</addr-line>, <country>China</country>
</aff>
<aff id="aff2">
<sup>2</sup>
<institution>Department of Obstetrics and Gynaecology</institution>, <institution>Li Ka Shing Faculty of Medicine</institution>, <institution>The University of Hong Kong</institution>, <addr-line>Hong Kong SAR</addr-line>, <country>China</country>
</aff>
<author-notes>
<fn fn-type="edited-by">
<p>
<bold>Edited by:</bold> <ext-link ext-link-type="uri" xlink:href="https://loop.frontiersin.org/people/32091/overview">Shoba Ranganathan</ext-link>, Macquarie University, Australia</p>
</fn>
<fn fn-type="edited-by">
<p>
<bold>Reviewed by:</bold> <ext-link ext-link-type="uri" xlink:href="https://loop.frontiersin.org/people/338019/overview">Simone Furini</ext-link>, University of Siena, Italy</p>
<p>
<ext-link ext-link-type="uri" xlink:href="https://loop.frontiersin.org/people/554338/overview">Piotr K. Janicki</ext-link>, College of Medicine, Pennsylvania State University, United States</p>
</fn>
<corresp id="c001">&#x2a;Correspondence: Philip C. N. Chiu, <email>pchiucn@hku.hk</email>; Dandan Cao, <email>caodd@hku-szh.org</email>
</corresp>
<fn fn-type="other">
<p>This article was submitted to Computational Genomics, a section of the journal Frontiers in Genetics</p>
</fn>
</author-notes>
<pub-date pub-type="epub">
<day>29</day>
<month>09</month>
<year>2022</year>
</pub-date>
<pub-date pub-type="collection">
<year>2022</year>
</pub-date>
<volume>13</volume>
<elocation-id>981005</elocation-id>
<history>
<date date-type="received">
<day>29</day>
<month>06</month>
<year>2022</year>
</date>
<date date-type="accepted">
<day>08</day>
<month>08</month>
<year>2022</year>
</date>
</history>
<permissions>
<copyright-statement>Copyright &#xa9; 2022 Liu, Yeung, Chiu and Cao.</copyright-statement>
<copyright-year>2022</copyright-year>
<copyright-holder>Liu, Yeung, Chiu and Cao</copyright-holder>
<license xlink:href="http://creativecommons.org/licenses/by/4.0/">
<p>This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.</p>
</license>
</permissions>
<abstract>
<p>One objective of human genetics is to unveil the variants that contribute to human diseases. With the rapid development and wide use of next-generation sequencing (NGS), massive genomic sequence data have been created, making personal genetic information available. Conventional experimental evidence is critical in establishing the relationship between sequence variants and phenotype but with low efficiency. Due to the lack of comprehensive databases and resources which present clinical and experimental evidence on genotype-phenotype relationship, as well as accumulating variants found from NGS, different computational tools that can predict the impact of the variants on phenotype have been greatly developed to bridge the gap. In this review, we present a brief introduction and discussion about the computational approaches for variant impact prediction. Following an innovative manner, we mainly focus on approaches for non-synonymous variants (nsSNVs) impact prediction and categorize them into six classes. Their underlying rationale and constraints, together with the concerns and remedies raised from comparative studies are discussed. We also present how the predictive approaches employed in different research. Although diverse constraints exist, the computational predictive approaches are indispensable in exploring genotype-phenotype relationship.</p>
</abstract>
<kwd-group>
<kwd>
<italic>in silico</italic> prediction</kwd>
<kwd>human genetics</kwd>
<kwd>genotype-phenotype relationship</kwd>
<kwd>nonsynonymous variants</kwd>
<kwd>variant impact</kwd>
</kwd-group>
</article-meta>
</front>
<body>
<sec id="s1">
<title>1 Introduction</title>
<p>One of the primary goals of human genetics is to discover the genetic variants associated with the onset and progression of human disease. The challenge is a &#x201c;a needle in haystack&#x201d; problem: how to pinpoint the potential causative ones from millions of individual variants (<xref ref-type="bibr" rid="B85">Genomes Project et al., 2015</xref>) spreading over the newly assembled, non-gap 3.055 billion&#x2013;base pair human genome sequence (<xref ref-type="bibr" rid="B167">Nurk et al., 2022</xref>). Efforts to achieve this goal, such as linkage analysis and genome-wide association studies, were inadequately effective in identifying causative candidates and had poor clinical predictive value (<xref ref-type="bibr" rid="B225">Tam et al., 2019</xref>).</p>
<p>Over the last decade, the next generation sequencing (NGS) has been extensively utilized in biomedical research as consequences of its substantially reduced cost and generation of large volume of data. According to the fact sheets on genomic cost provided by the National Human Genome Research Institute (NHGRI) (KA., 2021), NGS technology achieved one hundred-fold cost reduction compared to Sanger sequencing, and the price is currently less than $1,000 per human genome. Nowadays, NGS platforms can finish one run within 2&#xa0;days producing billions of reads for up to 48 samples (<xref ref-type="bibr" rid="B101">Hu et al., 2021</xref>). With the raw NGS data, standard and well-recognized variant format files can be generated using upstream analysis pipeline (<xref ref-type="bibr" rid="B116">Kanzi et al., 2020</xref>). Whereas the downstream disease-causing variant fishing step among &#x223c;50,000 variants from WES, or even millions of variants from WGS is the most challenge part (<xref ref-type="bibr" rid="B66">Eberle et al., 2017</xref>; <xref ref-type="bibr" rid="B125">Koboldt, 2020</xref>).</p>
<p>There are plenty of data resources storing evidenced genotype-phenotype relationship information. To a certain extent, clinicians and researchers are able to utilize these records to interpret the formation, progress, diagnosis and treatment of diseases from a genetic perspective. However, even the most well-recognized databases, such as ClinVar (<xref ref-type="bibr" rid="B132">Landrum et al., 2020</xref>), only contain around 14,000 of highly confident variants with evidence evaluated by genetic experts, which is a small fraction compared to the huge number of variants identified from NGS. This situation dramatically reduces clinical utility from genetics. In addition, it also poses great challenges for understanding differential actions of genes between/among individuals, populations and species, as well as deciphering the genotype-phenotype relationship (<xref ref-type="bibr" rid="B170">Orgogozo et al., 2015</xref>). To address these issues, computational tools for predicting variant impact have emerged which can help bridge the gap between vast amount of genomic data generated and limited known genetic evidence, and finally build up the potential genotype-phenotype relationship for the newly identified variants.</p>
<p>Variant call format (VCF) files store identified variants providing variant genomic position, nucleotide substitution, assessed quality score, genotype and other relevant information according to alignment and variant calling information (<xref ref-type="bibr" rid="B53">Danecek et al., 2011</xref>). Based on the specified information, variant annotation can locate them to specific genes or transcripts, classify them into different types and conclude on their impactable consequences (<xref ref-type="bibr" rid="B241">Wang et al., 2010</xref>; <xref ref-type="bibr" rid="B43">Cingolani et al., 2012</xref>; <xref ref-type="bibr" rid="B153">McLaren et al., 2016</xref>). Variants causing sequence alteration are mainly categorized into four types: insertion, deletion, single nucleotide variant (SNV) and other substitution, including multiple nucleotide variant (MNV) (<xref ref-type="bibr" rid="B68">Eilbeck et al., 2005</xref>). Among them, SNVs are the most frequently identified (<xref ref-type="bibr" rid="B85">Genomes Project et al., 2015</xref>; <xref ref-type="bibr" rid="B134">Lek et al., 2016</xref>) and annotated (<xref ref-type="bibr" rid="B51">Cunningham et al., 2015</xref>). SNVs are composed of non-synonymous SNVs (nsSNVs) and synonymous SNVs (sSNVs). Comparing to sSNVs, nsSNVs, which will cause amino acid change based on the protein translation codons, are estimated at higher frequency in individuals with excess deleteriousness (<xref ref-type="bibr" rid="B84">Genomes Project et al., 2012</xref>). Therefore, in this review, we focus on the computational approaches which are developed to infer the impact of nsSNVs in coding regions. The database resources that are utilized by majority of the predictive methods (we name them as predictors throughout this review) are firstly introduced. Following that, we discuss the underlying motivation and constraints of those predictors with which we group them into six categories in an innovative manner. We also present their corresponding predictive performance and concerns from assessment studies. Finally, we demonstrate the application performance of the predictors in large-scale studies, as well as their ability to reveal the genotype-phenotype associations.</p>
</sec>
<sec id="s2">
<title>2 Database resources for variant predictors</title>
<p>Models are not created out of thin air; rather, they are designed to identify hidden correlations in massive volumes of real data, allowing data to be interpreted and used to generate predictions. Since the deployment of the Human Genome Project in the 1990s, various relevant databases and knowledgebases have been established and maintained by academic institutions, organizations, consortia, and communities to collect, store, and retrieve records pertaining to genetic, clinical, and phenotypic information. They provide sufficient accessible evidences and facts to reliably demonstrate the genotype-phenotype association, which explains the functional and pathogenic importance of genetic variations (<xref ref-type="bibr" rid="B110">Johnston and Biesecker, 2013</xref>).</p>
<p>Databases can be categorized according to their scope, purpose, and scale. Several reviews (<xref ref-type="bibr" rid="B231">Thorisson et al., 2009</xref>; <xref ref-type="bibr" rid="B29">Brookes and Robinson, 2015</xref>; <xref ref-type="bibr" rid="B253">Zhang et al., 2019</xref>; <xref ref-type="bibr" rid="B16">Banck et al., 2021</xref>; <xref ref-type="bibr" rid="B120">Katsonis et al., 2022</xref>) provided comprehensive details of the content, usage, comparisons, and limitations for those databases. In this section, we briefly review the most frequently used databases (<xref ref-type="table" rid="T1">Table 1</xref>) containing sequence information, population-scale data, phenotype ontology, clinical and experimental evidence.</p>
<table-wrap id="T1" position="float">
<label>TABLE 1</label>
<caption>
<p>Summary of resources for human genotypes and phenotypes relationships.</p>
</caption>
<table>
<thead valign="top">
<tr>
<th align="left">Type of data</th>
<th align="left">Name</th>
<th align="left">Full name</th>
<th align="left">Techniques</th>
<th align="left">Type of variants</th>
<th align="left">Targeted diseases</th>
<th align="left">Website</th>
<th align="left">Containing entries (until writtern in June 2022)</th>
<th align="left">Composition</th>
<th align="left">First publication year</th>
<th align="left">Last update (until writtern in June 2022)</th>
<th align="left">Accessible</th>
<th align="left">Publications</th>
</tr>
</thead>
<tbody valign="top">
<tr>
<td align="left">Protein data</td>
<td align="left">Uniprot</td>
<td align="left">Universal protein resource</td>
<td align="left">Curated</td>
<td align="left">&#x2014;</td>
<td align="left">General</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://www.uniprot.org/">https://www.uniprot.org/</ext-link>
</td>
<td align="left">567,483 entries in Swiss-Prot and 231,354,261 entries in TrEMBL</td>
<td align="left">UniProt Knowledgebase, UniProt Reference Clusters, and UniProt Archive</td>
<td align="char" char=".">1997</td>
<td align="left">2 February 2021</td>
<td align="left">Free</td>
<td align="left">
<xref ref-type="bibr" rid="B235">UniProt, (2021)</xref>
</td>
</tr>
<tr>
<td align="left">Protein information</td>
<td align="left">UniProtKB</td>
<td align="left">Uniprot Knowledgebase</td>
<td align="left">Curated</td>
<td align="left">&#x2014;</td>
<td align="left">General</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://www.uniprot.org/uniprot/">https://www.uniprot.org/uniprot/</ext-link>
</td>
<td align="left">&#x2014;</td>
<td align="left">Swiss-Prot and TrEMBL</td>
<td align="left">&#x2014;</td>
<td align="left">22 November 2021</td>
<td align="left">Free</td>
<td align="left">
<xref ref-type="bibr" rid="B235">UniProt, (2021)</xref>
</td>
</tr>
<tr>
<td align="left">Protein sequences</td>
<td align="left">UniRef</td>
<td align="left">Uniprot Reference Clusters</td>
<td align="left">Curated</td>
<td align="left">&#x2014;</td>
<td align="left">General</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://www.uniprot.org/uniref/">https://www.uniprot.org/uniref/</ext-link>
</td>
<td align="left">&#x2014;</td>
<td align="left">UniRef100, 90, 50</td>
<td align="left">&#x2014;</td>
<td align="left">29 November 2021</td>
<td align="left">Free</td>
<td align="left">
<xref ref-type="bibr" rid="B235">UniProt, (2021)</xref>
</td>
</tr>
<tr>
<td align="left">Protein sequences</td>
<td align="left">UniParc</td>
<td align="left">Uniprot Archive</td>
<td align="left">Curated</td>
<td align="left">&#x2014;</td>
<td align="left">General</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://www.uniprot.org/uniparc/">https://www.uniprot.org/uniparc/</ext-link>
</td>
<td align="left">&#x2014;</td>
<td align="left">&#x2014;</td>
<td align="left">&#x2014;</td>
<td align="left">24 March 2022</td>
<td align="left">Free</td>
<td align="left">
<xref ref-type="bibr" rid="B235">UniProt, (2021)</xref>
</td>
</tr>
<tr>
<td align="left">Protein, DNA and RNA structural data</td>
<td align="left">PDB</td>
<td align="left">Protein data bank</td>
<td align="left">Structural data from X-ray, NMR, electron microscopy</td>
<td align="left">&#x2014;</td>
<td align="left">General</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://www.rcsb.org/">https://www.rcsb.org/</ext-link>
</td>
<td align="left">191,565 Biological Macromolecular Structures</td>
<td align="left">&#x2014;</td>
<td align="char" char=".">1971</td>
<td align="left">14 June 2022</td>
<td align="left">Free</td>
<td align="left">
<xref ref-type="bibr" rid="B21">Berman et al. (2000)</xref>
</td>
</tr>
<tr>
<td align="left">Protein data with themodynamic parameters</td>
<td align="left">ProThermDB</td>
<td align="left">Thermodynamic Database for Proteins and Mutants</td>
<td align="left">Curated</td>
<td align="left">&#x2014;</td>
<td align="left">General</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://web.iitm.ac.in/bioinfo2/prothermdb/index.html">https://web.iitm.ac.in/bioinfo2/prothermdb/index.html</ext-link>
</td>
<td align="left">&#x223c;0.12 million thermodynamic data obtained for different organisms and cell lines, &#x3e;32,000 entries, &#x223c;20,000 mutations</td>
<td align="left">&#x2014;</td>
<td align="char" char=".">1999</td>
<td align="left">22 September 2021</td>
<td align="left">Free</td>
<td align="left">
<xref ref-type="bibr" rid="B163">Nikam et al. (2021)</xref>
</td>
</tr>
<tr>
<td align="left">Protein data</td>
<td align="left">ONGene</td>
<td align="left">&#x2014;</td>
<td align="left">Curated</td>
<td align="left">&#x2014;</td>
<td align="left">Cancer</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://ongene.bioinfo-minzhao.org/index.html">https://ongene.bioinfo-minzhao.org/index.html</ext-link>
</td>
<td align="left">803 oncogenes</td>
<td align="left">&#x2014;</td>
<td align="char" char=".">2016</td>
<td align="left">&#x2014;</td>
<td align="left">Free</td>
<td align="left">
<xref ref-type="bibr" rid="B146">Liu et al. (2017)</xref>
</td>
</tr>
<tr>
<td align="left">Protein data</td>
<td align="left">TSGene2.0</td>
<td align="left">Tumor suppressor gene database</td>
<td align="left">Curated</td>
<td align="left">&#x2014;</td>
<td align="left">Cancer</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://bioinfo.uth.edu/TSGene/">https://bioinfo.uth.edu/TSGene/</ext-link>
</td>
<td align="left">1217 human tumor suppressor genes</td>
<td align="left">&#x2014;</td>
<td align="char" char=".">2012</td>
<td align="left">4 January 2016</td>
<td align="left">Free</td>
<td align="left">
<xref ref-type="bibr" rid="B256">Zhao et al. (2016)</xref>
</td>
</tr>
<tr>
<td align="left">Population data</td>
<td align="left">1000 Genome Project</td>
<td align="left">&#x2014;</td>
<td align="left">WGS</td>
<td align="left">SNVs, indels</td>
<td align="left">General</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://www.internationalgenome.org/">https://www.internationalgenome.org/</ext-link>
</td>
<td align="left">Genotypes for 2,504 healthy donor samples from 26 populations</td>
<td align="left">&#x2014;</td>
<td align="char" char=".">2008</td>
<td align="left">1 October 2015</td>
<td align="left">Free</td>
<td align="left">
<xref ref-type="bibr" rid="B221">Sudmant et al. (2015)</xref>
</td>
</tr>
<tr>
<td align="left">Population data</td>
<td align="left">GnomAD (previously ExAC)</td>
<td align="left">Genome aggregation database</td>
<td align="left">WGS, WES</td>
<td align="left">SNVs, indels</td>
<td align="left">General</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://gnomad.broadinstitute.org/">https://gnomad.broadinstitute.org/</ext-link>
</td>
<td align="left">76,156 genomes data of diverse ancestries in v3.1 and 141,456 individuals exomes or genomes data in v2</td>
<td align="left">&#x2014;</td>
<td align="char" char=".">2014</td>
<td align="left">21 January 2022</td>
<td align="left">Free</td>
<td align="left">
<xref ref-type="bibr" rid="B117">Karczewski et al. (2020)</xref>
</td>
</tr>
<tr>
<td align="left">Population data</td>
<td align="left">ESP</td>
<td align="left">The NHLBI exome sequencing project</td>
<td align="left">WES</td>
<td align="left">SNVs, indels</td>
<td align="left">Disease-, phenotype-related</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://evs.gs.washington.edu/EVS/">https://evs.gs.washington.edu/EVS/</ext-link>
</td>
<td align="left">6,503 unrelated individual exom data</td>
<td align="left">&#x2014;</td>
<td align="char" char=".">2011</td>
<td align="left">23 April 2019</td>
<td align="left">Free</td>
<td align="left">
<xref ref-type="bibr" rid="B80">Fu et al. (2013)</xref>
</td>
</tr>
<tr>
<td align="left">Population data</td>
<td align="left">UK Biobank</td>
<td align="left">&#x2014;</td>
<td align="left">&#x2014;</td>
<td align="left">&#x2014;</td>
<td align="left">Disease-, phenotype-related</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://www.ukbiobank.ac.uk/">https://www.ukbiobank.ac.uk/</ext-link>
</td>
<td align="left">49,960 exome data</td>
<td align="left">&#x2014;</td>
<td align="char" char=".">2006</td>
<td align="left">19 March 2019</td>
<td align="left">Registration fee needed</td>
<td align="left">&#x2014;</td>
</tr>
<tr>
<td align="left">Population data</td>
<td align="left">UK10K</td>
<td align="left">&#x2014;</td>
<td align="left">WGS, WES</td>
<td align="left">&#x2014;</td>
<td align="left">Healthy and disease-related cohorts</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://www.uk10k.org/">https://www.uk10k.org/</ext-link>
</td>
<td align="left">Nearly 10,000 individuals in UK population</td>
<td align="left">Whole genome, Neurodevelopment, Obesity, Rare Diseases Sample Sets</td>
<td align="char" char=".">2010</td>
<td align="left">1 October 2015</td>
<td align="left">Access control</td>
<td align="left">
<xref ref-type="bibr" rid="B45">Consortium et al. (2015)</xref>
</td>
</tr>
<tr>
<td align="left">Phenotype and genotype data</td>
<td align="left">OMIM</td>
<td align="left">Online Mendelian Inheritance in Man</td>
<td align="left">Classification</td>
<td align="left">&#x2014;</td>
<td align="left">Disease-, phenotype-, gene-related</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://www.omim.org/">https://www.omim.org/</ext-link>
</td>
<td align="left">26,446 entries, including all known mendelian disorders and over 16,000 genes</td>
<td align="left">&#x2014;</td>
<td align="char" char=".">1960</td>
<td align="left">27 May 2022</td>
<td align="left">Free</td>
<td align="left">
<xref ref-type="bibr" rid="B9">Amberger et al. (2019)</xref>
</td>
</tr>
<tr>
<td align="left">Phenotype and genotype data</td>
<td align="left">Orphanet</td>
<td align="left">The portal for rare diseases and orphan drugs</td>
<td align="left">Classification</td>
<td align="left">&#x2014;</td>
<td align="left">Disease-, phenotype-related</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://www.orpha.net/">https://www.orpha.net/</ext-link>
</td>
<td align="left">6,172 disease, 5835 genes</td>
<td align="left">&#x2014;</td>
<td align="char" char=".">1997</td>
<td align="left">31 May 2022</td>
<td align="left">Free</td>
<td align="left">&#x2014;</td>
</tr>
<tr>
<td align="left">Ontology</td>
<td align="left">HPO</td>
<td align="left">Human phenotype ontology</td>
<td align="left">Classification</td>
<td align="left">&#x2014;</td>
<td align="left">Disease-, phenotype-, gene-related</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://hpo.jax.org/">https://hpo.jax.org/</ext-link>
</td>
<td align="left">&#x3e;13,000 terms, &#x3e; 156,000 annotations</td>
<td align="left">&#x2014;</td>
<td align="char" char=".">2008</td>
<td align="left">14 April 2022</td>
<td align="left">Free</td>
<td align="left">
<xref ref-type="bibr" rid="B126">Kohler et al. (2021)</xref>
</td>
</tr>
<tr>
<td align="left">Ontology</td>
<td align="left">GO</td>
<td align="left">Gene ontology</td>
<td align="left">Classification</td>
<td align="left">&#x2014;</td>
<td align="left">Gene-specific</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="http://geneontology.org/">http://geneontology.org/</ext-link>
</td>
<td align="left">7,510,543 annotations</td>
<td align="left">Molecular Function, Cellular Component, and Biological Process</td>
<td align="char" char=".">2000</td>
<td align="left">16 May 2022</td>
<td align="left">Free</td>
<td align="left">(<xref ref-type="bibr" rid="B12">Ashburner et al., 2000</xref>; <xref ref-type="bibr" rid="B83">Gene Ontology, 2021</xref>)</td>
</tr>
<tr>
<td align="left">Ontology</td>
<td align="left">Mammalian Phenotype Ontology</td>
<td align="left">&#x2014;</td>
<td align="left">Classification</td>
<td align="left">&#x2014;</td>
<td align="left">Phenotype-related</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://bioportal.bioontology.org/ontologies/MP/?p=summary">https://bioportal.bioontology.org/ontologies/MP/?p&#x3d;summary</ext-link>
</td>
<td align="left">14,716 classes</td>
<td align="left">&#x2014;</td>
<td align="char" char=".">2005</td>
<td align="left">14 June 2022</td>
<td align="left">Free</td>
<td align="left">
<xref ref-type="bibr" rid="B217">Smith et al. (2005)</xref>
</td>
</tr>
<tr>
<td align="left">Genomic data</td>
<td align="left">HGMD</td>
<td align="left">Human gene mutation database</td>
<td align="left">Curated</td>
<td align="left">SNVs, indels</td>
<td align="left">Disease-, phenotype-related</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="http://www.hgmd.cf.ac.uk/ac/index.php">http://www.hgmd.cf.ac.uk/ac/index.php</ext-link>
</td>
<td align="left">352,731 mutation entries</td>
<td align="left">352,731 mutation entries</td>
<td align="char" char=".">1996</td>
<td align="left">31 May 2022</td>
<td align="left">Registration needed</td>
<td align="left">
<xref ref-type="bibr" rid="B150">Maffucci et al. (2019)</xref>
</td>
</tr>
<tr>
<td align="left">Genomic data</td>
<td align="left">VariBench</td>
<td align="left">A benchmark database for variations</td>
<td align="left">Curated</td>
<td align="left">SNVs, indels</td>
<td align="left">&#x2014;</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="http://structure.bmc.lu.se/VariBench/index.php">http://structure.bmc.lu.se/VariBench/index.php</ext-link>
</td>
<td align="left">&#x2014;</td>
<td align="left">VariBench datasets include disease-causing missense variations, neutral high frequency SNPs, protein stability affecting missense variations, variations affecting transcription factor binding sites, variations affecting splice sites</td>
<td align="char" char=".">2012</td>
<td align="left">&#x2014;</td>
<td align="left">Free</td>
<td align="left">
<xref ref-type="bibr" rid="B199">Sasidharan Nair and Vihinen, (2013)</xref>
</td>
</tr>
<tr>
<td align="left">Genomic data</td>
<td align="left">VariSNP</td>
<td align="left">&#x2014;</td>
<td align="left">Curated</td>
<td align="left">SNVs, indels</td>
<td align="left">&#x2014;</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="http://structure.bmc.lu.se/VariSNP/index.php">http://structure.bmc.lu.se/VariSNP/index.php</ext-link>
</td>
<td align="left">145,435,955 variants</td>
<td align="left">Datasets selected from dbSNP which were filtered for disease-related variants found in ClinVar, Swiss-Prot and PhenCode</td>
<td align="char" char=".">2014</td>
<td align="left">16 February 2017</td>
<td align="left">Free</td>
<td align="left">
<xref ref-type="bibr" rid="B202">Schaafsma and Vihinen, (2015)</xref>
</td>
</tr>
<tr>
<td align="left">Genomic data</td>
<td align="left">dbSNP</td>
<td align="left">Single nucleotide polymorphism database</td>
<td align="left">Curated</td>
<td align="left">SNVs, indels, retroposable element insertions and microsatellite repeat variations</td>
<td align="left">General</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://www.ncbi.nlm.nih.gov/snp/">https://www.ncbi.nlm.nih.gov/snp/</ext-link>
</td>
<td align="left">1,085,850,277 refSNP</td>
<td align="left">&#x2014;</td>
<td align="char" char=".">1999</td>
<td align="left">26 May 2020</td>
<td align="left">Free</td>
<td align="left">
<xref ref-type="bibr" rid="B206">Sherry et al. (2001)</xref>
</td>
</tr>
<tr>
<td align="left">Genomic data</td>
<td align="left">ClinVar</td>
<td align="left">&#x2014;</td>
<td align="left">Curated</td>
<td align="left">SNVs, indels</td>
<td align="left">Disease-, phenotype-, gene-related</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://www.ncbi.nlm.nih.gov/clinvar/">https://www.ncbi.nlm.nih.gov/clinvar/</ext-link>
</td>
<td align="left">1,540,318 unique variation records</td>
<td align="left">&#x2014;</td>
<td align="char" char=".">2013</td>
<td align="left">5 May 2022</td>
<td align="left">Free</td>
<td align="left">
<xref ref-type="bibr" rid="B132">Landrum et al. (2020)</xref>
</td>
</tr>
<tr>
<td align="left">Genomic data</td>
<td align="left">ClinGen</td>
<td align="left">&#x2014;</td>
<td align="left">Curated</td>
<td align="left">SNVs, indels</td>
<td align="left">Disease-, phenotype-related</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://clinicalgenome.org/">https://clinicalgenome.org/</ext-link>
</td>
<td align="left">Unique 3692 variants in unique 2278 genes</td>
<td align="left">&#x2014;</td>
<td align="char" char=".">2013</td>
<td align="left">1 April 2022</td>
<td align="left">Free</td>
<td align="left">
<xref ref-type="bibr" rid="B186">Rehm et al. (2015)</xref>
</td>
</tr>
<tr>
<td align="left">Genomic data</td>
<td align="left">DoCM</td>
<td align="left">Database of Curated Mutations</td>
<td align="left">Curated</td>
<td align="left">SNVs, indels</td>
<td align="left">Cancer</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="http://www.docm.info/">http://www.docm.info/</ext-link>
</td>
<td align="left">1,364 variants among 122 disease type</td>
<td align="left">&#x2014;</td>
<td align="char" char=".">2014</td>
<td align="left">&#x2014;</td>
<td align="left">Free</td>
<td align="left">
<xref ref-type="bibr" rid="B5">Ainscough et al. (2016)</xref>
</td>
</tr>
<tr>
<td align="left">Genomic data</td>
<td align="left">VKGL</td>
<td align="left">Vereniging klinisch genetische</td>
<td align="left">Curated</td>
<td align="left">SNVs, indels</td>
<td align="left">Disease-, phenotype-related</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://vkgl.molgeniscloud.org/">https://vkgl.molgeniscloud.org/</ext-link>
</td>
<td align="left">188,502 variants</td>
<td align="left">&#x2014;</td>
<td align="char" char=".">2018</td>
<td align="left">December 2021</td>
<td align="left">Free</td>
<td align="left">
<xref ref-type="bibr" rid="B75">Fokkema et al. (2019)</xref>
</td>
</tr>
<tr>
<td align="left">Genomic data</td>
<td align="left">CIViC</td>
<td align="left">Clinical interpretation of variants in cancer</td>
<td align="left">Curated</td>
<td align="left">SNVs, indels, SVs</td>
<td align="left">Cancer</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://civicdb.org/welcome">https://civicdb.org/welcome</ext-link>
</td>
<td align="left">3165 variants, 470 genes with clinical interpretation</td>
<td align="left">&#x2014;</td>
<td align="char" char=".">2015</td>
<td align="left">1 May 2022</td>
<td align="left">Free</td>
<td align="left">
<xref ref-type="bibr" rid="B90">Griffith et al. (2017)</xref>
</td>
</tr>
<tr>
<td align="left">Genomic data</td>
<td align="left">COSMIC</td>
<td align="left">Catalogue of somatic mutations in cancer</td>
<td align="left">Curated</td>
<td align="left">SNVs, indels</td>
<td align="left">Cancer</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://cancer.sanger.ac.uk/cosmic">https://cancer.sanger.ac.uk/cosmic</ext-link>
</td>
<td align="left">29,399,170 variants, 1,207,190 CNVs, 19,422 fusions</td>
<td align="left">&#x2014;</td>
<td align="char" char=".">2004</td>
<td align="left">31 May 2022</td>
<td align="left">Free</td>
<td align="left">
<xref ref-type="bibr" rid="B226">Tate et al. (2019)</xref>
</td>
</tr>
<tr>
<td align="left">Genomic data</td>
<td align="left">LOVD3.0</td>
<td align="left">Leiden open variation database 3.0</td>
<td align="left">Curated</td>
<td align="left">SNVs, indels</td>
<td align="left">Disease-, phenotype-related</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://www.lovd.nl/3.0/home">https://www.lovd.nl/3.0/home</ext-link>
</td>
<td align="left">800,780 variants</td>
<td align="left">&#x2014;</td>
<td align="char" char=".">2002</td>
<td align="left">17 August 2021</td>
<td align="left">Free</td>
<td align="left">
<xref ref-type="bibr" rid="B74">Fokkema et al. (2021)</xref>
</td>
</tr>
<tr>
<td align="left">Genomic data</td>
<td align="left">InSight</td>
<td align="left">The International Society for Gastrointestinal Hereditary Tumours</td>
<td align="left">Curated</td>
<td align="left">SNVs, indels</td>
<td align="left">Gene-specific</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="http://insight-database.org/">http://insight-database.org/</ext-link>
</td>
<td align="left">35,644 variant entries from 9 genes related to gastrointestinal tumours</td>
<td align="left">Variants are automatically sourced from LOVD3</td>
<td align="char" char=".">2005</td>
<td align="left">&#x2014;</td>
<td align="left">Free</td>
<td align="left">
<xref ref-type="bibr" rid="B74">Fokkema et al. (2021)</xref>
</td>
</tr>
<tr>
<td align="left">Genomic data</td>
<td align="left">HuVarBase</td>
<td align="left">Human variants database</td>
<td align="left">Curated</td>
<td align="left">Missense, nonsense, insertion, deletion</td>
<td align="left">Disease-, phenotype-related</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://www.iitm.ac.in/bioinfo/huvarbase/index.php">https://www.iitm.ac.in/bioinfo/huvarbase/index.php</ext-link>
</td>
<td align="left">774,863 variants from 18,318 proteins, including 702,048 disease-causing and 72,815 neutral variants</td>
<td align="left">Sources from 1000 Genomes, ClinVar, COSMIC, Humsavar, SwissVar, MutHTP, PROXiMATE</td>
<td align="char" char=".">2018</td>
<td align="left">15 October 2018</td>
<td align="left">Free</td>
<td align="left">
<xref ref-type="bibr" rid="B81">Ganesan et al. (2019)</xref>
</td>
</tr>
<tr>
<td align="left">Genomic data</td>
<td align="left">DVD</td>
<td align="left">Deafness variation database</td>
<td align="left">Curated</td>
<td align="left">SNVs, indels</td>
<td align="left">Deafness-related</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://deafnessvariationdatabase.org/">https://deafnessvariationdatabase.org/</ext-link>
</td>
<td align="left">223 genes</td>
<td align="left">Sources from ClinVar, dbNSFP, gnomAD, VEP, CADD, dbSNP, Population Analysis and others</td>
<td align="char" char=".">2018</td>
<td align="left">4 January 2021</td>
<td align="left">Free</td>
<td align="left">
<xref ref-type="bibr" rid="B14">Azaiez et al. (2018)</xref>
</td>
</tr>
<tr>
<td align="left">Genomic data</td>
<td align="left">METABRIC</td>
<td align="left">Molecular Taxonomy of Breast Cancer International Consortium</td>
<td align="left">Targeted NGS</td>
<td align="left">SNVs, indels</td>
<td align="left">Breast cancer</td>
<td align="left">Mutation details can be retrived from <ext-link ext-link-type="uri" xlink:href="https://www.cbioportal.org/study/summary?id=brca_metabric">https://www.cbioportal.org/study/summary?id&#x3d;brca_metabric</ext-link>
</td>
<td align="left">Mutation data in 173 genes from 2433 primary breast tumor samples and 650 normal controls</td>
<td align="left">Genomic mutation data, copy number aberration (CNA), gene expression and long-term clinical follow-up data</td>
<td align="char" char=".">2012</td>
<td align="left">&#x2014;</td>
<td align="left">Free</td>
<td align="left">(<xref ref-type="bibr" rid="B52">Curtis et al., 2012</xref>; <xref ref-type="bibr" rid="B176">Pereira et al., 2016</xref>)</td>
</tr>
<tr>
<td align="left">Genomic data</td>
<td align="left">TCGA-BRCA</td>
<td align="left">&#x2014;</td>
<td align="left">WES</td>
<td align="left">SNVs, indels</td>
<td align="left">Breast cancer</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://portal.gdc.cancer.gov/projects/TCGA-BRCA">https://portal.gdc.cancer.gov/projects/TCGA-BRCA</ext-link>
</td>
<td align="left">Mutation data from WES of 817 Breast Invasive Carcinoma tumor/normal pairs</td>
<td align="left">Genomic mutation data, copy number aberration (CNA), gene expression and long-term clinical follow-up data</td>
<td align="char" char=".">2012</td>
<td align="left">8 October 2015</td>
<td align="left">Free</td>
<td align="left">
<xref ref-type="bibr" rid="B44">Ciriello et al. (2015)</xref>
</td>
</tr>
<tr>
<td align="left">Genomic data</td>
<td align="left">
<italic>BRCA1</italic> dataset</td>
<td align="left">&#x2014;</td>
<td align="left">Saturation genome editing assays</td>
<td align="left">SNVs</td>
<td align="left">
<italic>BRCA1</italic> gene</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://sge.gs.washington.edu/BRCA1/">https://sge.gs.washington.edu/BRCA1/</ext-link>
</td>
<td align="left">3,893 SNVs located within or near 13 exons that encode for the RING and BRCT domains of BRCA1 (exons 2&#x2013;5 and 15&#x2013;23, respectively)</td>
<td align="left">&#x2014;</td>
<td align="char" char=".">2018</td>
<td align="left">&#x2014;</td>
<td align="left">Free</td>
<td align="left">
<xref ref-type="bibr" rid="B73">Findlay et al. (2018)</xref>
</td>
</tr>
<tr>
<td align="left">Genomic data</td>
<td align="left">VarCards</td>
<td align="left">&#x2014;</td>
<td align="left">Curated</td>
<td align="left">SNVs, indels</td>
<td align="left">General</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="http://varcards.biols.ac.cn/">http://varcards.biols.ac.cn/</ext-link>
</td>
<td align="left">110,154,363 SNVs, and 1,223,370 indels in coding regions or splicing sites</td>
<td align="left">Variant-level and gene-level resources</td>
<td align="char" char=".">2016</td>
<td align="left">28 June 2020</td>
<td align="left">Free</td>
<td align="left">
<xref ref-type="bibr" rid="B138">Li et al. (2018)</xref>
</td>
</tr>
</tbody>
</table>
</table-wrap>
<sec id="s2-1">
<title>2.1 Sequence resources</title>
<p>GenBank (<xref ref-type="bibr" rid="B201">Sayers et al., 2022</xref>), hosted by National Institutes of Health (NIH), European Nucleotide Archive (ENA) (<xref ref-type="bibr" rid="B15">Baker et al., 2000</xref>), hosted by European Molecular Biology Laboratory&#x2019;s European Bioinformatics Institute (EMBL-EBI), as well as the DNA Data Bank of Japan (DDBJ) (<xref ref-type="bibr" rid="B169">Okido et al., 2022</xref>) are the most widely used sequence databases, storing over 2.5 billion nucleotide sequences for over 504,000 formally described species. They serve as a basis for genetic analysis since aligning clean reads to the reference genome is an indispensable step in NGS analysis. As sequences of plethora species become accessible, protein sequences with 100%, 95%, and 50% identity are assembled to create clusters that are stored in informative databases such as UniProt Reference Clusters (UniRef) (<xref ref-type="bibr" rid="B224">Suzek et al., 2007</xref>), a branch of Universal Protein Resource (UniProt) (<xref ref-type="bibr" rid="B235">UniProt, 2021</xref>). These clusters are utilized to build multiple sequence alignment (MSA) sets, which form the basis of homology sequence-based approach.</p>
</sec>
<sec id="s2-2">
<title>2.2 Population resources</title>
<p>Several worldwide population projects exist, including the NCBI dbSNP (<xref ref-type="bibr" rid="B216">Smigielski et al., 2000</xref>), 1000 genome project (1KGP) (<xref ref-type="bibr" rid="B221">Sudmant et al., 2015</xref>), HapMap (<xref ref-type="bibr" rid="B103">International HapMap, 2003</xref>), UK10K (<xref ref-type="bibr" rid="B45">Consortium et al., 2015</xref>), Genome Aggregation Database (gnomAD) (<xref ref-type="bibr" rid="B118">Karczewski et al., 2020</xref>), and NHLBI GO Exome Sequencing Project (ESP) (<xref ref-type="bibr" rid="B80">Fu et al., 2013</xref>). With their progress and completion, their reports are now public and offer an exquisite view of the landscape of human genetic variants ranging from common to extremely rare ones. They also provide valuable information allowing the examination of variants between and within subpopulations with different ethnicities or disease status like heart, lung and blood disorders. Furthermore, minor allele frequency (MAF) from these databases is usually a useful indicator for prioritization or pertain as important feature for building prediction models.</p>
</sec>
<sec id="s2-3">
<title>2.3 Phenotype resources</title>
<p>Phenotype databases describe phenotypes and illnesses in conjunction with genetic information. The most widely known are OMIM (Online Mendelian Inheritance in Man) (<xref ref-type="bibr" rid="B9">Amberger et al., 2019</xref>) and Orphanet (<xref ref-type="bibr" rid="B13">Ayme et al., 1998</xref>). Their goal is to offer high-quality information on common and rare diseases or phenotypes in order to comprehensively review the genotype-phenotype association. To assist the investigation on connections between phenotypes and genes and to describe diseases in an algorithm-friendly data structure, ontology databases such as Human Phenotype Ontology (HPO) (<xref ref-type="bibr" rid="B191">Robinson et al., 2008</xref>), Mammalian Phenotype Ontology (<xref ref-type="bibr" rid="B217">Smith et al., 2005</xref>), and Gene Ontology (GO) (<xref ref-type="bibr" rid="B12">Ashburner et al., 2000</xref>) were developed. They are designed to annotate clinical phenotypes and genes with well-structured, computational-friendly, precise, and accurate terminology. Overall, these databases provide valuable insights for prioritization and interpretation of genetic data.</p>
</sec>
<sec id="s2-4">
<title>2.4 Clinical genetic resources</title>
<p>Several databases curated genetic data with clinical significance information. These databases are also known as Locus-Specific Databases (LSDB). Data and entries are often curated from literature and clinical trials. LSDBs range in scale from a single gene with roughly 4000 variants (<xref ref-type="bibr" rid="B73">Findlay et al., 2018</xref>) to hundreds of millions of variants (<xref ref-type="bibr" rid="B202">Schaafsma and Vihinen, 2015</xref>). The goal of LSDBs is to unambiguously and accurately define and categorize genotype-phenotype correlation, to understand gene functions and effects, to provide a map of genetic distribution across populations and diseases, and to assist clinicians/diagnostic laboratories in conducting further validation assays by providing detail molecule, pathogenicity, and effects of variants (<xref ref-type="bibr" rid="B88">Greenblatt et al., 2008</xref>). A well-curated and annotated LSDB is a valuable resource for constructing and evaluating prediction models. But note in mind that there would be overlapped variants in different LSDBs, even with contradictory classification of clinical impact due to inconsistent rules and subjective opinion of different curators. Phenotype-/disease- specific LSDBs are established, such as DVD (Deafness Variation Database) (<xref ref-type="bibr" rid="B14">Azaiez et al., 2018</xref>) for deafness, RAPID (Resource of Asian Primary Immunodeficiency Diseases) (<xref ref-type="bibr" rid="B121">Keerthikumar et al., 2009</xref>) for primary immunodeficiency disease, InSiGHT (The International Society for Gastrointestinal Hereditary Tumors) (<xref ref-type="bibr" rid="B74">Fokkema et al., 2021</xref>) for gastrointestinal tumors, <ext-link ext-link-type="uri" xlink:href="http://fabry-database.org">fabry-database.org</ext-link> (<xref ref-type="bibr" rid="B194">Saito et al., 2011</xref>) for Fabry disease. Thanks to the effort of the Leiden Open source Variation Database (LOVD) (<xref ref-type="bibr" rid="B74">Fokkema et al., 2021</xref>) platform, a comprehensive list of public LSDBs are presented with details for researchers and clinicians to retrieve gene and mutation information from different resources.</p>
</sec>
</sec>
<sec id="s3">
<title>3 Various variant predictors</title>
<p>Each predictor has a unique biochemical or biological basis. It is important to remember that the outcome of the predictor on different bases has different implications. The terms &#x201c;dangerous,&#x201d; &#x201c;pathogenic,&#x201d; &#x201c;conservative,&#x201d; and &#x201c;damaging&#x201d; do not necessarily denote causal of a specific phenotype or condition. Knowing the principles and drawbacks of each type of predictor aids in correctly interpreting the variants.</p>
<p>Variant impact predictors can be categorized in different ways: machine-learning (ML) and non-ML models based on the used algorithms; homology sequence-based and structural-based models regarding the features they used in prediction; supervised and unsupervised ML-models. Unlike the category of sequence-, structure- and meta-methodologies in other reviews (<xref ref-type="bibr" rid="B94">Hassan et al., 2019b</xref>; <xref ref-type="bibr" rid="B248">Yazar and Ozbek, 2021</xref>), we introduced an innovative category here based on the characteristics and included features of each type (<xref ref-type="fig" rid="F1">Figure 1</xref>). We discuss these categories by outlining the rational reasoning behind the predictors and provide an overview of the constraints. Later, we discuss predictor performance evaluation and underline current concerns and remedies. Details for each tool are present in <xref ref-type="sec" rid="s10">Supplementary Table S1</xref> and <xref ref-type="table" rid="T2">Table 2</xref>.</p>
<fig id="F1" position="float">
<label>FIGURE 1</label>
<caption>
<p>Summarized workflow of variants impact predictors. Protein structure and protein features of BRCA1 BRCT mutant M1775K are retrived from studies. (<xref ref-type="bibr" rid="B259">Birrane, 2006</xref>: <xref ref-type="bibr" rid="B260">Tischkowitz et al., 2008</xref>). The minor allele frequency (MAF) information of variant rs41293463 (chr17-43051071-A-C(GRCh38)) was retrived from gnomAD (Genome Aggregation Database).</p>
</caption>
<graphic xlink:href="fgene-13-981005-g001.tif"/>
</fig>
<table-wrap id="T2" position="float">
<label>TABLE 2</label>
<caption>
<p>Representative diseases-, phenotypes-, genes-specific variants impact predictors.</p>
</caption>
<table>
<thead valign="top">
<tr>
<th align="left">Characteristic category</th>
<th align="left">Name</th>
<th align="left">Type of variants</th>
<th align="left">Targeted disease/phenotype/gene</th>
<th align="left">&#x23; of genes</th>
<th align="left">Website</th>
<th align="left">Distribution (web-server/stand-alone)</th>
<th align="left">First publication</th>
<th align="left">Programming language</th>
<th align="left">Algorithm/model</th>
<th align="left">Features</th>
<th align="left">Dataset for modeling</th>
<th align="left">Classification index</th>
<th align="left">Classification</th>
<th align="left">Additional data</th>
<th align="left">Publication</th>
</tr>
</thead>
<tbody valign="top">
<tr>
<td align="left">Meta-predictor</td>
<td align="left">VIPPID (Variant Impact Predictor for PIDs)</td>
<td align="left">Missense</td>
<td align="left">Primary immunodeficiency (PID) diseases</td>
<td align="char" char=".">146</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://mylab.shinyapps.io/VIPPID/">https://mylab.shinyapps.io/VIPPID/</ext-link>
</td>
<td align="left">Web and stand-alone</td>
<td align="left">April 2022</td>
<td align="left">Perl, R</td>
<td align="left">Conditional Inference Forest</td>
<td align="left">85 features including AA, exonic, protein structural, conservation, and 20 pre-existing prediction tools</td>
<td align="left">4,865 disease-associated variants from Asian Primary Immunodeficiency Diseases (RAPID) database, HGMD and ClinVar; 4,237 neutral variants from gnomAD</td>
<td align="left">Classifier</td>
<td align="left">Pathogenic/non-pathogenic</td>
<td align="left">26 reviewed P/LP variants of known PID pathogenic genes from 1318 patients cohort and 39 validated in-house variants</td>
<td align="left">
<xref ref-type="bibr" rid="B70">Fang et al. (2022)</xref>
</td>
</tr>
<tr>
<td align="left">Meta-predictor</td>
<td align="left">CanPredict</td>
<td align="left">Missense</td>
<td align="left">Cancer</td>
<td align="left">&#x2014;</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="http://www.canpredict.org/">http://www.canpredict.org/</ext-link>or <ext-link ext-link-type="uri" xlink:href="http://www.cgl.ucsf.edu/Research/genentech/canpredict/">http://www.cgl.ucsf.edu/Research/genentech/canpredict/</ext-link>, both are not accessible</td>
<td align="left">&#x2014;</td>
<td align="left">May 2007</td>
<td align="left">R</td>
<td align="left">RF</td>
<td align="left">SIFT, Pfam-based LogR.E-value and GO Similarity Score (GOSS) metrics</td>
<td align="left">&#x2014;</td>
<td align="left">Classifier</td>
<td align="left">Likely cancer/likely non-cancer/not determined</td>
<td align="left">&#x2014;</td>
<td align="left">
<xref ref-type="bibr" rid="B115">Kaminker et al. (2007)</xref>
</td>
</tr>
<tr>
<td align="left">Meta-predictor</td>
<td align="left">PolyPhen-HCM</td>
<td align="left">Missense</td>
<td align="left">Hypertrophic cardiomyopathy</td>
<td align="char" char=".">6</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="http://genetics.bwh.harvard.edu/hcm/">http://genetics.bwh.harvard.edu/hcm/</ext-link>
</td>
<td align="left">Pre-computed results</td>
<td align="left">February 2011</td>
<td align="left">&#x2014;</td>
<td align="left">Na&#xef;ve bayes classifier</td>
<td align="left">Prediction scores, protein structure comparison score</td>
<td align="left">74 curated variants from literitures and manually classified by Laboratory for Molecular Medicine standard variant-assessment pipeline (41 pathogenic, 26 benign)</td>
<td align="left">Classifier</td>
<td align="left">Pathogenic/benign/no call</td>
<td align="left">&#x2014;</td>
<td align="left">
<xref ref-type="bibr" rid="B112">Jordan et al. (2011)</xref>
</td>
</tr>
<tr>
<td align="left">Meta-predictor</td>
<td align="left">Cadioboost</td>
<td align="left">Missense</td>
<td align="left">Cardiomyopathies and arrhythmias</td>
<td align="char" char=".">22</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://www.cardiodb.org/cardioboost/">https://www.cardiodb.org/cardioboost/</ext-link>
</td>
<td align="left">Pre-computed results</td>
<td align="left">October. 2020</td>
<td align="left">R</td>
<td align="left">2 Adaptive Boosting (Adaboost) classifiers</td>
<td align="left">76 functional features</td>
<td align="left">CM datasets: 356 rare P/LP variants from 9,007 clinical CM patients, 302 rare missense variants in CM genes from 2,090 healthy controls. Inherited arrhythmia dataset: 252&#xa0;P/LP in arrhythmia-associated genes from ClinVar, 237 rare missense variants in arrhythmia genes from 2,090 healthy controls</td>
<td align="left">Pathogenicity score</td>
<td align="left">Disease-causing/VUS/Benign</td>
<td align="left">4 datasets from ClinVar, HGMD, Oxford Medical Genetics Laboratory (OMGL), a large registry of HCM patients, SHaRe</td>
<td align="left">
<xref ref-type="bibr" rid="B254">Zhang et al. (2021)</xref>
</td>
</tr>
<tr>
<td align="left">Multiple features</td>
<td align="left">GENESIS (GENe-specific EnSemble grId Search)</td>
<td align="left">Variants of uncertain clinical significance</td>
<td align="left">Catecholaminergic polymorphic ventricular tachycardia and long QT syndrome (LQTS)</td>
<td align="char" char=".">4</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://github.com/rachellea/medgenetics">https://github.com/rachellea/medgenetics</ext-link>
</td>
<td align="left">Stand-alone and pre-computed results</td>
<td align="left">March 2022</td>
<td align="left">Python</td>
<td align="left">Logistic regression and multilayer perceptron model</td>
<td align="left">8 kinds of features including AA features, domain, conservation, rate of evolution, signal-to-noise ratio, and a position-specific scoring matrix (PSSM) score</td>
<td align="left">717 pathogenic variants and 3,164 benign variants curated from literiture</td>
<td align="left">Probabilities of pathogenicity</td>
<td align="left">Pathogenic/VUS/benign</td>
<td align="left">925 VUS classified according to ACMG</td>
<td align="left">
<xref ref-type="bibr" rid="B65">Draelos et al. (2022)</xref>
</td>
</tr>
<tr>
<td align="left">Multiple features</td>
<td align="left">CACNA1F-vp</td>
<td align="left">Missense</td>
<td align="left">X-linked incomplete Congenital Stationary Night Blindness (iCSNB)</td>
<td align="char" char=".">1</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://github.com/shalawsallah/CACNA1F-variants-analysis">https://github.com/shalawsallah/CACNA1F-variants-analysis</ext-link>
</td>
<td align="left">Stand-alone</td>
<td align="left">April 2020</td>
<td align="left">Python</td>
<td align="left">Logistic regression model</td>
<td align="left">Variant-level features and structural features</td>
<td align="left">72 disease-implicated from HGMD or MGDL database, 322 benign variants from gnomAD</td>
<td align="left">Probabilities of pathogenicity</td>
<td align="left">Pathogenic/benign</td>
<td align="left">-</td>
<td align="left">
<xref ref-type="bibr" rid="B196">Sallah et al. (2020)</xref>
</td>
</tr>
<tr>
<td align="left">Optimized PON-P2</td>
<td align="left">PON-MMR2</td>
<td align="left">AA substitution</td>
<td align="left">Mismatch repair (MMR)</td>
<td align="char" char=".">4</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="http://structure.bmc.lu.se/PON-MMR2/">http://structure.bmc.lu.se/PON-MMR2/</ext-link>
</td>
<td align="left">Web and stand-alone</td>
<td align="left">September 2015</td>
<td align="left">R</td>
<td align="left">RF</td>
<td align="left">5 features: sequence conservation, physical and biochemical properties of AA</td>
<td align="left">109 pathogenic, 99 neutral, 354 VUS from InSiGHT database and VariBench</td>
<td align="left">Probabilities of pathogenicity</td>
<td align="left">Pathogenic/VUS/benign</td>
<td align="left">354 VUS dataset</td>
<td align="left">
<xref ref-type="bibr" rid="B165">Niroula and Vihinen, (2015)</xref>
</td>
</tr>
<tr>
<td align="left">Optimized MAPP</td>
<td align="left">CoDP (Combination of Different Properties of MSH6 protein)</td>
<td align="left">Missense</td>
<td align="left">Lynch syndrome (LS)</td>
<td align="char" char=".">1</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="http://cib.cf.ocha.ac.jp/CoDP/">http://cib.cf.ocha.ac.jp/CoDP/</ext-link>
</td>
<td align="left">Web</td>
<td align="left">April 2013</td>
<td align="left">&#x2014;</td>
<td align="left">Logistic regression model</td>
<td align="left">MSA, phylogenetic tree, structral properties, MAPP, SIFT, PolyPhen2</td>
<td align="left">294 missense variants from InSiGHT, MMRUV, UniProt, dbSNP, ESP, HapMap Project, 1KGP and literature</td>
<td align="left">Probabilities of pathogenicity</td>
<td align="left">Likely LS/Unlikely LS</td>
<td align="left">260 unclassified variants dataset</td>
<td align="left">
<xref ref-type="bibr" rid="B227">Terui et al. (2013)</xref>
</td>
</tr>
<tr>
<td align="left">Meta-predictor with MAF as features</td>
<td align="left">DvPred</td>
<td align="left">nsSNVs</td>
<td align="left">Genetic hearing loss (HL)</td>
<td align="char" char=".">157</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://github.com/WCH-IRD/DVPred/tree/main/DVPred_score">https://github.com/WCH-IRD/DVPred/tree/main/DVPred_score</ext-link>
</td>
<td align="left">Stand-alone and pre-computed results</td>
<td align="left">February 2022</td>
<td align="left">Python</td>
<td align="left">Gradient boosting decision tree (GBDT)</td>
<td align="left">65 features include conservation scores, prediction scores, MAF, gene intolerance scores and other features</td>
<td align="left">1,318&#xa0;P/LP and 4,628&#xa0;B/LB from China Deafness Genetics Consortium (CDGC), Deafness Variation Database (DVD), ClinVar, HGMD</td>
<td align="left">DvPred score</td>
<td align="left">Deleterious/neutral</td>
<td align="left">463 pathogenic and 454 benign variants from new version of CDGC and ClinVar</td>
<td align="left">
<xref ref-type="bibr" rid="B30">Bu et al. (2022)</xref>
</td>
</tr>
<tr>
<td align="left">Meta-predictor</td>
<td align="left">NBDriver</td>
<td align="left">Missense</td>
<td align="left">Cancer</td>
<td align="char" char=".">58</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://github.com/RamanLab/NBDriver">https://github.com/RamanLab/NBDriver</ext-link>
</td>
<td align="left">Stand-alone</td>
<td align="left">May 2021</td>
<td align="left">Python</td>
<td align="left">RF, extra tress (ET) classifier, generative KDE classifier</td>
<td align="left">3 types of features: one-hot encoding, overlapping k-mers, 27 genomic features</td>
<td align="left">5,265 disease-associated variants from five literatures</td>
<td align="left">Classifier</td>
<td align="left">&#x2014;</td>
<td align="left">&#x2014;</td>
<td align="left">
<xref ref-type="bibr" rid="B17">Banerjee et al. (2021)</xref>
</td>
</tr>
<tr>
<td align="left">Combination of rule-based and meta-predictor</td>
<td align="left">CancerVar</td>
<td align="left">Exon variants, CNVs, indels</td>
<td align="left">Cancer</td>
<td align="char" char=".">1911</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://cancervar.wglab.org/index.php">https://cancervar.wglab.org/index.php</ext-link>
</td>
<td align="left">Web, stand-alone and pre-computed results</td>
<td align="left">May 2022</td>
<td align="left">Python</td>
<td align="left">Semi-supervised generative adversarial network used in scoring method OPAI</td>
<td align="left">12 clinical evidence prediction scores and 23 precomputed scores by other computational tools</td>
<td align="left">13 million variants from 7 cancer knowledgebases</td>
<td align="left">OPAI score</td>
<td align="left">Oncogenic/benign</td>
<td align="left">4 datasets from OncoKB and CIViC, IARC and literatures</td>
<td align="left">
<xref ref-type="bibr" rid="B141">Li et al. (2022)</xref>
</td>
</tr>
</tbody>
</table>
<table-wrap-foot>
<fn>
<p>&#x2a;VUS, variant of uncertain significance.</p>
</fn>
</table-wrap-foot>
</table-wrap>
<sec id="s3-1">
<title>3.1 Types of tools and their principles</title>
<sec id="s3-1-1">
<title>3.1.1 Homologous sequence-based predictors</title>
<p>This class of predictors are derived from comparative genomics. The assumption is straightforward: under natural selection, amino acid changes in conservative sequences are more &#x201c;deleterious&#x201d; determined by homologous sequence searching across species, than that happened in other non-homologous positions which would be deemed as &#x201c;tolerant&#x201d; (<xref ref-type="bibr" rid="B46">Cooper and Shendure, 2011</xref>). Methodologically, these predictors firstly construct the multiple sequence alignment (MSA) either by grouping multiple protein sequences with a given similarity from BLAST alignment (<xref ref-type="bibr" rid="B8">Altschul et al., 1990</xref>), or just retrieval customed selective sequences from afroed-mentioned genomic databases (<xref ref-type="sec" rid="s2-1">Section 2.1</xref>) for multiple alignment using MULTIZ (<xref ref-type="bibr" rid="B23">Blanchette et al., 2004</xref>), or MUSCLE (<xref ref-type="bibr" rid="B67">Edgar, 2004</xref>). Based on MSA, a position-specific scoring matrix (PSSM) (<xref ref-type="bibr" rid="B89">Gribskov et al., 1987</xref>) is computed to generate the prediction outcome with probability score (<xref ref-type="bibr" rid="B161">Ng and Henikoff, 2001</xref>), likelihood ratio (<xref ref-type="bibr" rid="B42">Chun and Fay, 2009</xref>), the average distance between targeted species and others in subfamilies (<xref ref-type="bibr" rid="B41">Choi et al., 2012</xref>), or the entropy difference (<xref ref-type="bibr" rid="B187">Reva et al., 2007</xref>; <xref ref-type="bibr" rid="B100">Hopf et al., 2017</xref>). The predictive outcomes are normally continuous values with the designer&#x2019;s recommended threshold validated in mutation datasets.</p>
<p>Apart from computing scores using empirically rational equations, ML algorithms were commonly utilized as classifiers. Classical models include random forest (RF) (<xref ref-type="bibr" rid="B36">Capriotti et al., 2006</xref>), and hidden Markov Model (HMM) (<xref ref-type="bibr" rid="B228">Thomas et al., 2003</xref>; <xref ref-type="bibr" rid="B211">Siepel et al., 2005</xref>; <xref ref-type="bibr" rid="B82">Garber et al., 2009</xref>; <xref ref-type="bibr" rid="B180">Pollard et al., 2010</xref>; <xref ref-type="bibr" rid="B209">Shihab et al., 2013</xref>). Although they are both ML techniques, the attributes they employ are distinct. For example, PhD-SNP (<xref ref-type="bibr" rid="B36">Capriotti et al., 2006</xref>) converted MSA and mutation to a 40-feature variables in support vector machine (SVM). The 40 features are composed of two parts: the first 20 vectors explicitly define the mutation residues, with -1 for the wild-type residue, 1 for the mutation, and 0 for the others. The second set of 20 vectors represents the mutation sequence environment, which is the frequency of each 20 amino acid residue in a 20 amino acid length window centered on the targeted site. Unlike unweighted and balanced MSA, HMM is a probabilistic profile of MSA that captures position-specific information (<xref ref-type="bibr" rid="B128">Krogh et al., 1994</xref>). Two different configurations of HMM were observed. One assumed three hidden states: &#x201c;match,&#x201d; &#x201c;insertion,&#x201d; and &#x201c;deletion&#x201d; to build a profile-HMM MSA (<xref ref-type="bibr" rid="B228">Thomas et al., 2003</xref>; <xref ref-type="bibr" rid="B209">Shihab et al., 2013</xref>), while the other considered a two-hidden state as &#x201c;conserved&#x201d; and &#x201c;non-conserved&#x201d; according to the phylogenetic information from tree topologies (<xref ref-type="bibr" rid="B211">Siepel et al., 2005</xref>; <xref ref-type="bibr" rid="B82">Garber et al., 2009</xref>; <xref ref-type="bibr" rid="B180">Pollard et al., 2010</xref>).</p>
<p>More recently, a novel unsupervised ML model is utilized to discover patterns and correlations between absolute locations in the MSA, allowing direct observation of both conservation and coevolution (<xref ref-type="bibr" rid="B190">Riesselman et al., 2018</xref>; <xref ref-type="bibr" rid="B78">Frazer et al., 2021</xref>). This deep generative model captured the latent structure from MSA using Variational Autoencoders (VAEs), which was proved to be an outstanding model for separation of &#x3b2;-lactamase protein family, at the phyla level (<xref ref-type="bibr" rid="B60">Detlefsen et al., 2022</xref>). By assuming the observed data <italic>s</italic> are generated from latent variable <italic>z</italic>, the decode part of VAE consists of modeling the conditional probability. Hence, the encode part is the neural network modeling of approximate posterior distribution (<xref ref-type="bibr" rid="B190">Riesselman et al., 2018</xref>; <xref ref-type="bibr" rid="B78">Frazer et al., 2021</xref>).</p>
<p>ML models&#x2019; predictions were normally given as log odds ratio scores between the probabilities of &#x201c;substitution&#x201d; and &#x201c;wild-type&#x201d; or &#x201c;conserved&#x201d; and &#x201c;non-conserved&#x201d;. In other words, under wild-type or neutral model, higher scores represent higher probability of unexpected substitution, thus are more evolutionary constraint.</p>
<p>There are two considerations regarding homologous sequence-based predictions (<xref ref-type="bibr" rid="B69">Eilbeck et al., 2017</xref>). Firstly, many known disease-causing alleles reside in poorly or non-conserved regions will be false-negatively classified as neutral by predictors. Secondly, the tools are inadequate for predicting stop-gain and frameshift variations since they are not included in other organisms in the MSA (<xref ref-type="bibr" rid="B69">Eilbeck et al., 2017</xref>). The stop-gain and frameshift variants are rated as &#x201c;HIGH&#x201d; impact on biological sequence in annotation tools, e.g., VEP (<xref ref-type="bibr" rid="B154">McLaren et al., 2010</xref>) and SnpEff (<xref ref-type="bibr" rid="B43">Cingolani et al., 2012</xref>). But the impact on protein is not always concordant. The amino acid changes seem to be tolerant especially the ones located near C-terminal of protein (<xref ref-type="bibr" rid="B149">MacArthur et al., 2012</xref>). Some frameshift variants, even in homozygous state, were frequently observed among population suggesting limited impact on human health (<xref ref-type="bibr" rid="B69">Eilbeck et al., 2017</xref>). Thus, additional information such as protein structure might help improve the predictive power and efficiency of the predictors, which will be discussed in the following subsections in more detail.</p>
</sec>
<sec id="s3-1-2">
<title>3.1.2 Structure-based predictors</title>
<p>Apart from the primary structure of protein, the folding and stability are also essential for protein function normally. Early findings of variants that affect protein structure leading to aberrant phenotypes can be dated back to the 1950s, when the amino acid substitution in the half molecule of hemoglobin was discovered to cause sickle cell anemia (<xref ref-type="bibr" rid="B102">Ingram, 1957</xref>). Since then, thousands of mutations (<xref ref-type="bibr" rid="B86">Giardine et al., 2014</xref>) were described to impact on the function (increase (<xref ref-type="bibr" rid="B111">Jones et al., 1979</xref>) or decrease (<xref ref-type="bibr" rid="B25">Bonaventura and Riggs, 1968</xref>) oxygen affinity), stability (<xref ref-type="bibr" rid="B152">Martinez et al., 1977</xref>) and conformation (<xref ref-type="bibr" rid="B158">Moo-Penn et al., 1988</xref>) of hemoglobin. Indeed, missense variants also affect protein expression (<xref ref-type="bibr" rid="B93">Haraksingh and Snyder, 2013</xref>), post-translational modification (<xref ref-type="bibr" rid="B122">Kim et al., 2015</xref>) or binding affinity (<xref ref-type="bibr" rid="B179">Pires et al., 2015</xref>; <xref ref-type="bibr" rid="B159">Morningstar-Kywi et al., 2021</xref>).</p>
<p>An estimation of &#x223c;75% disease-causing variants directly lead to protein destabilization, making protein stability the major contributor to disease pathology (<xref ref-type="bibr" rid="B250">Yue et al., 2005</xref>), whereas &#x223c;7% variants in disease dataset also have functional role (<xref ref-type="bibr" rid="B252">Yue et al., 2014</xref>). The location of the mutation has a preference. In comparison to polymorphisms, disease-causing mutations predominantly impact the core of the protein, whereas &#x223c;70% are found in structural and functionally essential regions (<xref ref-type="bibr" rid="B222">Sunyaev et al., 2000</xref>; <xref ref-type="bibr" rid="B57">de Beer et al., 2013</xref>). Protein-protein interfaces are hot spots for disease-causing nsSNVs (<xref ref-type="bibr" rid="B54">David et al., 2012</xref>; <xref ref-type="bibr" rid="B178">Petukh et al., 2015</xref>). Again, disease-causing variations were 49% more likely (interface core vs interface rim odds ratio (OR) 1.49, 95% CI 1.24&#x2013;1.80, <italic>p</italic> &#x3c; 0.00001) to be found in the interface core than in the rim, possibly due to their differences in energy contribution to protein stability, physicochemical and evolutionary properties (<xref ref-type="bibr" rid="B55">David and Sternberg, 2015</xref>).</p>
<p>Typically, nsSNVs impact on protein stability is estimated by computing the variation of Gibbs free energy change (&#x2206;&#x2206;G<sub>f</sub>) resulting from an amino acid substitution. Physical effective energy function, statistical potential function, and empirical defined potential function are the three types of energy computing methodologies (<xref ref-type="bibr" rid="B92">Guerois et al., 2002</xref>). Because the first function is computationally intensive, the latter two are more frequently utilized. Structure-based predictors of protein stability mainly attribute to empirical potentials that integrate physical and statistical structure-related energy components (<xref ref-type="bibr" rid="B92">Guerois et al., 2002</xref>), and ML techniques (<xref ref-type="bibr" rid="B58">Dehouck et al., 2009</xref>; <xref ref-type="bibr" rid="B131">Laimer et al., 2015</xref>).</p>
<p>In theory, these approaches should potentially give greater insights into the mutation effect than the homologous sequence-based predictors since they are built on the direct impact of mutation on protein structure and function. However, the truth is that protein-based predictors are still limited because of the unbalance and intrinsic variability of the thermodynamic data and their prediction performance (<xref ref-type="bibr" rid="B197">Sanavia et al., 2020</xref>). On one hand, despite that the Protein Data Bank (PDB) (<xref ref-type="bibr" rid="B21">Berman et al., 2000</xref>) contains over 50,000 human protein records, many of them are redundant, covering only 70% of reference human proteome at a sequence identity level higher than 30% (<xref ref-type="bibr" rid="B218">Somody et al., 2017</xref>). The development of AlphaFold2 (<xref ref-type="bibr" rid="B234">Tunyasuvunakool et al., 2021</xref>), to an extent increases the protein structure coverage; but its capability to predict the impact of single mutation is questionable (<xref ref-type="bibr" rid="B171">Pak et al., 2021</xref>; <xref ref-type="bibr" rid="B31">Buel and Walters, 2022</xref>). On the other hand, sequence-based techniques, under certain circumstances, outperform structure-based stability prediction tools (<xref ref-type="bibr" rid="B98">Hoie et al., 2022</xref>). Thus, combining sequence with structural information may aid in improving prediction capacity of variant impact.</p>
</sec>
<sec id="s3-1-3">
<title>3.1.3 Sequence and structure combination-based predictors</title>
<p>The approaches of this category consider both the previously described homologous sequence and protein structure information. Predictions take benefit from the combination of homology sequence information (e.g., conservative scores), and the structure features, such as hydropathy, polarity, backbone angles and electrostatic interactions, supplemented with energy features and biochemical features such as solvent accessible surface area of the interface (<xref ref-type="bibr" rid="B129">Kulshreshtha et al., 2016</xref>). Those features are sometimes transformed or selected for model training to achieve high prediction efficiency. Sometimes hundreds of features might be incorporated into the final model (<xref ref-type="bibr" rid="B164">Niroula et al., 2015</xref>). Algorithmically, supervised ML approaches including SVM (<xref ref-type="bibr" rid="B32">Calabrese et al., 2009</xref>; <xref ref-type="bibr" rid="B136">Li et al., 2009</xref>), na&#xef;ve bayes classifier (<xref ref-type="bibr" rid="B3">Adzhubei et al., 2010</xref>), neural network (NN) (<xref ref-type="bibr" rid="B97">Hecht et al., 2015</xref>), RF (<xref ref-type="bibr" rid="B37">Carter et al., 2013</xref>; <xref ref-type="bibr" rid="B164">Niroula et al., 2015</xref>) and boosted tree regression (<xref ref-type="bibr" rid="B258">Zhou et al., 2016</xref>) are commonly applied in the multiple features predictors.</p>
</sec>
<sec id="s3-1-4">
<title>3.1.4 Meta-predictors</title>
<p>Meta-predictors are tools that make predictions by integrating results of pre-existing predictors. The term &#x201c;meta-&#x201d; sometimes corresponds to the term &#x201c;consensus&#x201d; in other studies (<xref ref-type="bibr" rid="B19">Bendl et al., 2014</xref>). The basic idea behind meta-predictors is to leverage on potential complimentary performance of selected predictors in classifying variants.</p>
<p>There are mainly two improvements regarding meta-predictors comparing to aforementioned counterparts. First of all, meta-predictors give a comprehensive evaluation on the selected pre-existing tools. Each predictor has its own metric and scale making it difficult to compare across multiple predictors hindering the simultaneous usage. Meta-predictors have their own way to interpret scores from selected tools, by transforming to a comparable range as normalized scores (<xref ref-type="bibr" rid="B19">Bendl et al., 2014</xref>) or binary values (<xref ref-type="bibr" rid="B87">Gonzalez-Perez and Lopez-Bigas, 2011</xref>). In addition, meta-predictors are able to improve prediction performance by integrating prediction scores from different predictors, which allows the avoidance of bias and anti-generalization by single predictors (<xref ref-type="bibr" rid="B124">Kircher et al., 2014</xref>).</p>
<p>In terms of missing value, where partly pre-existing tools fail to predict, some meta-predictors impute them using deleterious/neutral threshold (<xref ref-type="bibr" rid="B35">Capriotti et al., 2013</xref>), average score (<xref ref-type="bibr" rid="B124">Kircher et al., 2014</xref>; <xref ref-type="bibr" rid="B184">Quang et al., 2015</xref>), fixed score (<xref ref-type="bibr" rid="B185">Quinodoz et al., 2022</xref>), the maximal pathogenic score (<xref ref-type="bibr" rid="B107">Jagadeesh et al., 2016</xref>), or a flexible imputation using average value of k-nearest neighbors (<xref ref-type="bibr" rid="B104">Ioannidis et al., 2016</xref>) and Bayesian principle component analysis (BPCA) (<xref ref-type="bibr" rid="B63">Dong et al., 2015</xref>). There is currently no gold standard for imputation. Although machine-learning imputation appears to be more accurate (<xref ref-type="bibr" rid="B27">Brock et al., 2008</xref>; <xref ref-type="bibr" rid="B243">Wei et al., 2018</xref>), meta-predictor builders revealed that missing values account for less than 10% of their training and testing datasets (<xref ref-type="bibr" rid="B63">Dong et al., 2015</xref>), making the imputation methods less significant difference.</p>
<p>While prediction performance studies suggested that meta-predictors surpassed other counterparts (<xref ref-type="bibr" rid="B232">Tian et al., 2019</xref>), concerns regarding circularity occurred, which will be discussed in <xref ref-type="sec" rid="s3-3">Section 3.3</xref>.</p>
</sec>
<sec id="s3-1-5">
<title>3.1.5 Combining population data</title>
<p>A polymorphism is defined as an alteration in DNA sequence found in the general population at a MAF greater than 1%. According to The American College of Medical Genetics (ACMG) and the Association for Molecular Pathology (AMP) guidelines for clinical variant interpretation, a variant with &#x3e;5% MAF is considered as a stand-alone support for benign interpretation for a rare Mendelian disorder (<xref ref-type="bibr" rid="B189">Richards et al., 2015</xref>). This is supported by the &#x201c;neutral theory&#x201d;, which defines neutral variants as the ones settled in the population through random genetic drift causing neither harmful nor beneficial effect to the survival of individual organisms (<xref ref-type="bibr" rid="B123">Kimura, 1979</xref>). When training and validating predictors, variants with higher than specified allele frequency (e.g., 5% or 1%) from population-scale databases were usually denoted as benign or neutral. However, predictors in predicting neutral variants differ greatly in capacity and specificity. For example, PON-P2 (<xref ref-type="bibr" rid="B164">Niroula et al., 2015</xref>) had a 95% specificity, while the poorest predictor incorrectly categorized more than one-third of polymorphisms as disease-causing (<xref ref-type="bibr" rid="B166">Niroula and Vihinen, 2019</xref>). Classifying the impact of variants according to their MAF were further argued by different hypothesis including &#x201c;rare variant for Mendelian disease&#x201d; (<xref ref-type="bibr" rid="B183">Pritchard and Cox, 2002</xref>), &#x201c;Common disease, common variant&#x201d; (CDCV) and &#x201c;Common disease/rare variant&#x201d; (CDRV).</p>
<p>Researchers now have access to an exquisitely detailed view of the landscape of common and rare human genetic variants. Another issue that predictors should be careful with when utilizing MAF is that MAF is largely dependent on the population size and varies among subpopulations leading to population stratification (<xref ref-type="bibr" rid="B69">Eilbeck et al., 2017</xref>). For example, rs79444516, which is common in African population (13%), exhibited its extreme rareness in European and Asian population, with MAF &#x3c;0.05%. When estimated in the mixture population, the MAF is 1.2% which will cause confounding classification. Varied MAF for the same variant because of different scales of sample size could be largely mitigated with the completion of the huge population-scale projects.</p>
<p>To better utilize MAF in prediction, ClinPred (<xref ref-type="bibr" rid="B7">Alirezaie et al., 2018</xref>), a meta-predictor using ML approach, employs MAFs from diverse populations as part of their features, instead of classifying variants based on single arbitrary MAF cutoffs. Together with feature scores from 16 pre-existing tools, ClinPred trains on clinically curated pathogenic and benign datasets and outperforms other meta-predictors when applied to datasets of rare diseases and cancer (<xref ref-type="bibr" rid="B7">Alirezaie et al., 2018</xref>). Therefore, MAFs from population data is capable to enhance the prediction. Similarly, more and more tools (<xref ref-type="bibr" rid="B39">Chennen et al., 2020</xref>; <xref ref-type="bibr" rid="B62">do Nascimento et al., 2020</xref>; <xref ref-type="bibr" rid="B130">Lai et al., 2020</xref>; <xref ref-type="bibr" rid="B143">Li et al., 2020</xref>) integrated MAFs as predicting features and achieved competitive performance on pathogenicity prediction.</p>
</sec>
<sec id="s3-1-6">
<title>3.1.6 Disease-, phenotype-, gene-specific predictors</title>
<p>The ultimate goal of the variant prediction tools is to accelerate the development of precision medicine. Majority of the strategies discussed above aim to estimate disease occurrence based on the assumption that changes in protein function leads to a decrease in organismal fitness (<xref ref-type="bibr" rid="B26">Boucher et al., 2016</xref>). They are trained in a large-scale datasets in a genome-wide and pan-disease manner neglecting the complexity among different diseases and making the prediction results suboptimal (<xref ref-type="bibr" rid="B64">Dorfman et al., 2010</xref>). Therefore, with the necessity to precisely estimate the impact of variants on specific disease/phenotype, a class of disease-, gene-, phenotype-specific prediction has emerged.</p>
<p>The phenotype-targeting predictors range widely from common cardiac (<xref ref-type="bibr" rid="B254">Zhang et al., 2021</xref>), cancer (<xref ref-type="bibr" rid="B115">Kaminker et al., 2007</xref>), and neurodegenerative disease (<xref ref-type="bibr" rid="B4">Ahmed et al., 2015</xref>), to rare diseases, such as methylmalonic acidemia (<xref ref-type="bibr" rid="B175">Peng et al., 2019</xref>), X-linked incomplete Congenital Stationary Night Blindness (<xref ref-type="bibr" rid="B196">Sallah et al., 2020</xref>) and Pompe disease (<xref ref-type="bibr" rid="B2">Adhikari, 2019</xref>). More details are presented in <xref ref-type="table" rid="T2">Table 2</xref>. There are over 13,000 terms defined in HPO. While LSDBs provide benchmarked variant datasets, such as COSMIC, CIViC and OncoKB for cancer, which can be utilized for disease-specific predictors construction, limited datasets are available for majority of phenotypes. For a particular disease/phenotype, the training and validation datasets can be prepared by curation of variants and genes from literatures, or re-analysis of unpublished sequencing data of case-control cohorts, followed by manually classification using recognized guidelines such as ACMG/AMP. The scale of the curated databases for different diseases/phenotypes varies in gene (from one to hundreds) and variant number (from thousands to millions) which is largely dependent on the number of relevant publications.</p>
<p>With the curated databases, most of this category of predictors utilize ML methodology. They can be grouped into three classes. The first class overlaps with previous mentioned categories but has distinct characteristic. It includes sequence and structure combination-based (<xref ref-type="bibr" rid="B196">Sallah et al., 2020</xref>; <xref ref-type="bibr" rid="B65">Draelos et al., 2022</xref>), sharing the same strategy with previously mention predictors in <xref ref-type="sec" rid="s3-1-3">Section 3.1.3</xref>, and meta-predictors (<xref ref-type="bibr" rid="B112">Jordan et al., 2011</xref>; <xref ref-type="bibr" rid="B30">Bu et al., 2022</xref>) similar to the ones discussed in <xref ref-type="sec" rid="s3-1-4">Section 3.1.4</xref>. The distinct characteristic is the difference in training and validation datasets selection. Also, disease-related genes are known, making predictors capable of constructing sub-model for each gene, resulting in better prediction performance (<xref ref-type="bibr" rid="B70">Fang et al., 2022</xref>). The second class aims to optimize pre-existing predictor, usually sequence-based model, by re-constructing MSAs and phylogenetic tree of targeted gene(s) (<xref ref-type="bibr" rid="B165">Niroula and Vihinen, 2015</xref>; <xref ref-type="bibr" rid="B77">Fortuno et al., 2018</xref>). These predictors share the same strategy as their precursors, with distinct features selection. The third class predicts variants in a comprehensive and robust way, utilizing additional rule-based classification system. For example, CancerVar (<xref ref-type="bibr" rid="B141">Li et al., 2022</xref>), integrates rule-based categorization with ML-based meta-predictor scores to interpret the predicting clinical significance.</p>
<p>These well-calibrated and sculpted predictors demonstrate their capability in targeted sequencing disease-specific panels to the utmost (<xref ref-type="bibr" rid="B175">Peng et al., 2019</xref>). In contrast, their ability to generalize is then questioned. When utilizing these techniques, note in mind the key target phenotypes and genes.</p>
</sec>
</sec>
<sec id="s3-2">
<title>3.2 Performance assessment of predictors</title>
<p>As dozens of predictors exist, choosing the appropriate one(s) becomes challenging for end users. Several assessment criteria, such as sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy, and Matthews correlation coefficient (MCC), are commonly used to demonstrate model performance (<xref ref-type="bibr" rid="B239">Vihinen, 2012</xref>). The values for sensitivity, specificity, PPV, NPV, and accuracy range from 0 to 1, with higher values indicating better performance. MCC benefits from true and false positives and negatives with values on a scale of -1 to 1, with values closer to 1 indicating perfect prediction. Furthermore, a visualization measurement, receiver operating characteristics (ROC) analysis is frequently used to intuitively compare the area under the ROC curve (AUC) of multiple predictors (<xref ref-type="bibr" rid="B239">Vihinen, 2012</xref>). For non-intersecting curves, the AUC value closer to 1 suggests better overall performance, while a value of 0.5 indicates random and useless classification.</p>
<p>Most predictors, when developed, would be assessed using respective training and validation datasets presenting supreme or acceptable performance. However, evaluation using consensus datasets would be more informative for tool selection.</p>
<p>There are dozens of comparison studies on the performance assessment of different selected tools using different benchmark datasets. When Performance evaluation of pathogenicity-computation methods for missense variants, meta-predictors such as REVEL, Meta-SNP, generally have better performance and stronger evidence in clinical interpretation (<xref ref-type="bibr" rid="B1">Accetturo et al., 2020</xref>; <xref ref-type="bibr" rid="B50">Cubuk et al., 2021</xref>; <xref ref-type="bibr" rid="B10">Anderson and Lassmann, 2022</xref>). In the assessment of 23 predictors, Li et al. (<xref ref-type="bibr" rid="B138">Li et al., 2018</xref>) revealed that meta-predictors achieved higher AUC than others of sequence-based and structure-based predictors using the ClinVar benchmark dataset, indicating better performance of meta-predictors. However, when regarding somatic variants and <italic>PPARG</italic> gene benchmark datasets, meta-predictors and structure-based predictors exhibited comparable performance (AUC&#x3e;0.8) (<xref ref-type="bibr" rid="B138">Li et al., 2018</xref>), and were superior to homology sequence-based predictors (AUC&#x3e;0.7). Hassan et al. (<xref ref-type="bibr" rid="B95">Hassan et al., 2019a</xref>) revealed that meta-predictor which integrated 4 pre-existing prediction scores, outperformed other 8 predictors achieving &#x223c;10%, 20%, 15% improvement in specificity, sensitivity and AUC, respectively.</p>
<p>The performance of different categories are not always consistent, and sometimes are contradictory. Poon&#x2019;s study (<xref ref-type="bibr" rid="B181">Poon, 2021</xref>) on <italic>BRCA1/2</italic> datasets revealed that SIFT and PolyPhen2&#x2019;s performance differed among genes. Mel&#xe9;ndez-Aranda et al. (<xref ref-type="bibr" rid="B155">Melendez-Aranda et al., 2019</xref>) compared the performance of 6 <italic>in silico</italic> tools on 215 missense mutations in hemophilia B causative gene <italic>F9</italic>, and the results showed that the most popular tool, SIFT, was the most accurate. When applying to a somatic dataset containing 4319 somatic missense variants, the performance of SIFT was sub-optimal (<xref ref-type="bibr" rid="B223">Suybeng et al., 2020</xref>). As a result, it is critical to have pre-knowledge of your testing data and predictive goal when selecting appropriate tools.</p>
<p>In order to address the confounding situation and objectively determine the appropriate usage and accuracy of predictors, the Critical Assessment of Genome Interpretation (CAGI) (<xref ref-type="bibr" rid="B11">Andreoletti et al., 2019</xref>) community started their experiments in 2010. Until now, there are six editions with 63 challenges and over 50 articles released. Participants predict the phenotypic impact of unpublished genetic variants collected from experimental and clinical labs provided by CAGI. Later, independent assessors test the predictions against experimental characterized phenotypes, and the results will be presented at the CAGI conference and published in special journal issues. The challenges released include a wide range of topics, from nsSNVs to splicing variants, and from disease panels to databases including curated variants. However, the reality of the outcome is frequently far more complex than the challenges&#x2019; initial objective. Predictors with superior performance in one challenge, would fail to call the pathogenicity of variants in other datasets (<xref ref-type="bibr" rid="B119">Katsonis and Lichtarge, 2019</xref>; <xref ref-type="bibr" rid="B200">Savojardo et al., 2019</xref>). Complex gene datasets caused divergence predictions and confounding outcomes, raising concerns about the possibility of experimental mistakes as the basis of disagreement (<xref ref-type="bibr" rid="B157">Miller et al., 2019</xref>). All the above suggested the caution when interpreting the evaluation results.</p>
</sec>
<sec id="s3-3">
<title>3.3 Concerns of current predictors and remedies</title>
<p>Majority of predictors are trained, validated and tested using benchmarked sets of variants with explicit classification labels. When evaluated 10 predictors across major public databases, <xref ref-type="bibr" rid="B91">Grimm et al. (2015)</xref> raised concerns about &#x201c;circularity&#x201d; involving in the usage of predictors and conduction of comparative studies. The term &#x201c;circularity&#x201d; refers to the situation that same variants are recursively used in both training and evaluating models.</p>
<p>&#x201c;Type 1 circularity&#x201d; refers to the overlap between training and evaluation particularly for supervised ML-based predictors, resulting in poor generalization on new data (<xref ref-type="bibr" rid="B91">Grimm et al., 2015</xref>). Selecting predictions from unsupervised tools as features or filtering overlapping sets during training might assist to minimize the &#x201c;type 1 circularity&#x201d; during model construction (<xref ref-type="bibr" rid="B7">Alirezaie et al., 2018</xref>; <xref ref-type="bibr" rid="B245">Won et al., 2021</xref>). Furthermore, avoiding overuse of individual dataset (<xref ref-type="bibr" rid="B238">Vihinen, 2013</xref>; <xref ref-type="bibr" rid="B242">Weber et al., 2019</xref>) and choosing benchmark database which addressed overlapped issue (<xref ref-type="bibr" rid="B199">Sasidharan Nair and Vihinen, 2013</xref>; <xref ref-type="bibr" rid="B198">Sarkar et al., 2020</xref>) also helps when conducting comparative studies.</p>
<p>
<xref ref-type="bibr" rid="B91">Grimm et al. (2015)</xref> observed that weighted FatHMM (<xref ref-type="bibr" rid="B209">Shihab et al., 2013</xref>) achieved outstanding performance in 2 datasets but severe drop in performance in subset from SwissVar. They found that the ratio of pathogenic and neutral variants in the same protein family was the key element for weighting scheme, leading to higher pathogenic score assigned to both neutral and pathogenic variants in the same gene with higher ratio (<xref ref-type="bibr" rid="B91">Grimm et al., 2015</xref>). This strategy made weighted FatHMM statistically successful in some datasets, but ultimately inappropriate. Therefore, they defined the &#x201c;Type 2 circularity&#x201d; as the circumstance in which all variants from the same gene are jointly labeled as pathogenic or neutral. To address this problem, it was suggested to use datasets with an appropriate pathogenic-to-neutral ratio and avoid genes with exclusive pathogenic or neutral variations when reporting performance (<xref ref-type="bibr" rid="B30">Bu et al., 2022</xref>; <xref ref-type="bibr" rid="B185">Quinodoz et al., 2022</xref>).</p>
<p>Another concern is about &#x201c;collinearity,&#x201d; which generally occurs with the regression models. &#x2018;Collinearity&#x2019; refers to the circumstance in which significant correlation between two or more feature variables resulting in independent regression coefficients estimation problems and leading to redundancy in the set of variables (<xref ref-type="bibr" rid="B18">Bayman and Dexter, 2021</xref>). This situation might be mitigated via feature selection and estimator modification (<xref ref-type="bibr" rid="B257">Zheng et al., 2020</xref>; <xref ref-type="bibr" rid="B38">Chan et al., 2022</xref>). From another perspective, &#x201c;collinearity&#x201d; should not be a problem because more complicated machine learning algorithms including SVM, Random Forest, and Neural Network, can handle large-scale and multi-collinear datasets in a better way (<xref ref-type="bibr" rid="B63">Dong et al., 2015</xref>; <xref ref-type="bibr" rid="B177">Perez-Enciso and Zingaretti, 2019</xref>).</p>
</sec>
</sec>
<sec id="s4">
<title>4 Application</title>
<p>In-silico approaches combined mathematical strategies with expert opinion allows researchers to analyze the biological meaning of genetic data efficiently and economically (<xref ref-type="bibr" rid="B233">Trisilowati and Mallet, 2012</xref>). In-silico predictors on variant effect aids in genome interpretation. The prediction-based categorization provides insight into variant characterization and prioritization.</p>
<p>Regards to large-scale population study, <italic>in silico</italic> predictors aid in variant classification for pattern overview and comparison at subpopulation level. For example, <xref ref-type="bibr" rid="B172">Palmer et al. (2022)</xref> subdivided missense variants by SIFT and PolyPhen2 prediction in research on bipolar disorder (BD) and revealed an obvious enrichment in ultra-rare harmful missense variation outside of confined missense areas, particularly in bipolar II disorder (BD2). This observation contrasted with the findings in schizophrenia cases (<xref ref-type="bibr" rid="B214">Singh et al., 2022</xref>) of enrichment within constrained missense regions. The authors speculated this signal may capture something distinct to mood disorders relative to psychotic disorders (<xref ref-type="bibr" rid="B172">Palmer et al., 2022</xref>).</p>
<p>For large-scale population<italic>, in silico</italic> predictors also facilitate the detection of variant-level signals under natural-selection for those living in extreme environments or with a diverse geographic distribution. <xref ref-type="bibr" rid="B59">Deng et al. (2019)</xref> ranked variants by calculating the functional importance score (FIS) from four <italic>in silico</italic> predictors. Based on the ranking of adaptive genetic variants, they revealed a seldom studied gene, <italic>TMEM247</italic> with a missense variant rs116983452, to be the most-differentiated functional variant identified between Tibetan and non-Tibetan populations (<xref ref-type="bibr" rid="B59">Deng et al., 2019</xref>). When studying non-homogeneous Taiwanese Han population, integrated selection of allele favored by evolution (iSAFE) was incorporated with the CADD functional impact score to identify 16 natural-selection signals by geographic distribution that were unambiguously localized to 5 single genes (<xref ref-type="bibr" rid="B147">Lo et al., 2021</xref>). Meanwhile, in the western Roma population, <xref ref-type="bibr" rid="B76">Font-Porterias et al. (2021)</xref> categorized missense variants based on GERP, PolyPhen2 and CADD, revealing significant difference in common deleterious variant portion between Roma and non-Roma population. Furthermore, runs of homozygozity (ROH), which are continuous homozygous regions of the DNA sequence, exhibit ancestry-specific patterns of accumulation of deleterious homozygotes.</p>
<p>In addition to characterization for population-level study, predictors have also been widely used for prioritization of disease-causing candidates in case-control or pedigree studies, finally leading to the identification of genotype-phenotype association. There are commonly two strategies for variant prioritization in which predictors help. Several frameworks and platforms are listed in <xref ref-type="table" rid="T3">Table 3</xref>.</p>
<table-wrap id="T3" position="float">
<label>TABLE 3</label>
<caption>
<p>Representative prioritization frameworks and tools.</p>
</caption>
<table>
<thead valign="top">
<tr>
<th align="left">Characteristic category</th>
<th align="left">Name</th>
<th align="left">Type of Targeted variants&#x2a;</th>
<th align="left">Website</th>
<th align="left">Distribution (web-server/stand-alone)</th>
<th align="left">First publication</th>
<th align="left">Last update</th>
<th align="left">Programming language</th>
<th align="left">Algorithm/modules</th>
<th align="left">Input type</th>
<th align="left">Dataset for modeling</th>
<th align="left">Publications</th>
</tr>
</thead>
<tbody valign="top">
<tr>
<td align="left">User-defined rule-based</td>
<td align="left">VCF.Filter</td>
<td align="left">SNVs, indels</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://biomedical-sequencing.at/VCFFilter/">https://biomedical-sequencing.at/VCFFilter/</ext-link>
</td>
<td align="left">Web and stand-alone</td>
<td align="left">July 2017</td>
<td align="left">&#x2014;</td>
<td align="left">Java</td>
<td align="left">Filter cohort, prioritize on pedigree and search variant in cohort modules</td>
<td align="left">VCF files, targeted regions, cohort allele frequencies, pedigree information</td>
<td align="left">&#x2014;</td>
<td align="left">
<xref ref-type="bibr" rid="B160">Muller et al. (2017)</xref>
</td>
</tr>
<tr>
<td align="left">User-defined rule-based</td>
<td align="left">BiERapp</td>
<td align="left">SNVs, indels, CNVs, MNVs, SVs</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="http://bioinfo.cipf.es/apps-beta/bierapp/2.0.0/">http://bioinfo.cipf.es/apps-beta/bierapp/2.0.0/&#x23;home</ext-link>
</td>
<td align="left">Web and stand-alone</td>
<td align="left">April 2014</td>
<td align="left">&#x2014;</td>
<td align="left">HTML5 and JS</td>
<td align="left">CellBase annotation, consecutive filtering strategy</td>
<td align="left">Multi-sample VCF files</td>
<td align="left">&#x2014;</td>
<td align="left">
<xref ref-type="bibr" rid="B6">Aleman et al. (2014)</xref>
</td>
</tr>
<tr>
<td align="left">User-defined rule-based</td>
<td align="left">KGGSeq</td>
<td align="left">SNVs, indel, CNVs</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="http://pmglab.top/kggseq/">http://pmglab.top/kggseq/</ext-link>
</td>
<td align="left">Stand-alone</td>
<td align="left">January. 2012</td>
<td align="left">1 January 2022</td>
<td align="left">Java</td>
<td align="left">5 major modules: quality control, filtration, annotation, pathogenic prediction and statistic tests</td>
<td align="left">VCF files, pedigree information</td>
<td align="left">7,296 disease-causing variants from OMIM and 48,089 neutral variants</td>
<td align="left">
<xref ref-type="bibr" rid="B140">Li et al. (2012)</xref>; <xref ref-type="bibr" rid="B139">Li et al. (2017)</xref>
</td>
</tr>
<tr>
<td align="left">User-defined rule-based</td>
<td align="left">VPOT (variant prioritization ordering tool)</td>
<td align="left">SNVs, indel</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://github.com/VCCRI/VPOT/">https://github.com/VCCRI/VPOT/</ext-link>
</td>
<td align="left">Stand-alone</td>
<td align="left">November. 2019</td>
<td align="left">27 October 2021</td>
<td align="left">Python</td>
<td align="left">2 steps: prioritization of variants based on user-defined parameters, post-processing of variant priority ordered list</td>
<td align="left">ANNOVAR annotated VCF or TXT files, inheritance model</td>
<td align="left">&#x2014;</td>
<td align="left">
<xref ref-type="bibr" rid="B105">Ip et al. (2019)</xref>
</td>
</tr>
<tr>
<td align="left">ACMG guideline based</td>
<td align="left">TAPES</td>
<td align="left">SNVs, indel</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://github.com/a-xavier/tapes">https://github.com/a-xavier/tapes</ext-link>
</td>
<td align="left">Stand-alone</td>
<td align="left">October. 2019</td>
<td align="left">&#x2014;</td>
<td align="left">Python</td>
<td align="left">Bayesian classification framework</td>
<td align="left">VCF files</td>
<td align="left">&#x2014;</td>
<td align="left">
<xref ref-type="bibr" rid="B247">Xavier et al. (2019)</xref>
</td>
</tr>
<tr>
<td align="left">ACMG guideline based</td>
<td align="left">InterVar</td>
<td align="left">SNVs, indel</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://github.com/WGLab/InterVar">https://github.com/WGLab/InterVar</ext-link>, <ext-link ext-link-type="uri" xlink:href="http://wintervar.wglab.org/">http://wintervar.wglab.org/</ext-link>
</td>
<td align="left">Web, stand-alone and pre-computed results</td>
<td align="left">February 2017</td>
<td align="left">13 June 2022</td>
<td align="left">Python</td>
<td align="left">Automated or manually scoring system. Manual review and adjustment on specific criteria</td>
<td align="left">Annotated or unannotated VCF files</td>
<td align="left">&#x2014;</td>
<td align="left">
<xref ref-type="bibr" rid="B142">Li and Wang, (2017)</xref>
</td>
</tr>
<tr>
<td align="left">ACMG guideline realted</td>
<td align="left">VarFish</td>
<td align="left">SNVs, indels</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://varfish-kiosk.bihealth.org/">https://varfish-kiosk.bihealth.org/, https://github.com/bihealth/varfish-server</ext-link>
</td>
<td align="left">Web and stand-alone</td>
<td align="left">July 2020</td>
<td align="left">June 2022</td>
<td align="left">Python</td>
<td align="left">Quality control, database- and user-based annotation, filtering interface, joint filtering of multiple cases</td>
<td align="left">VCF files, optional pedigree information</td>
<td align="left">-</td>
<td align="left">
<xref ref-type="bibr" rid="B99">Holtgrewe et al. (2020)</xref>
</td>
</tr>
<tr>
<td align="left">Phenotype-driven</td>
<td align="left">Exomiser</td>
<td align="left">SNVs, indels</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://www.sanger.ac.uk/tool/exomiser/">https://www.sanger.ac.uk/tool/exomiser/</ext-link>
</td>
<td align="left">Stand-alone</td>
<td align="left">November 2015</td>
<td align="left">November 2021</td>
<td align="left">Java</td>
<td align="left">Filtering and Prioritization based on logistical regression model. Four prioritization method include PHIVE, PhenIX, ExomeWalker, hiPHIVE.</td>
<td align="left">VCF files, HPO terms, optional pedigree information</td>
<td align="left">&#x2014;</td>
<td align="left">
<xref ref-type="bibr" rid="B215">Smedley et al. (2015)</xref>
</td>
</tr>
<tr>
<td align="left">Phenotype-driven</td>
<td align="left">eXtasy</td>
<td align="left">nsSNVs</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://extasy.esat.kuleuven.be/">https://extasy.esat.kuleuven.be/</ext-link>
</td>
<td align="left">Web and stand-alone</td>
<td align="left">September 2013</td>
<td align="left">&#x2014;</td>
<td align="left">Ruby</td>
<td align="left">RF</td>
<td align="left">VCF files, HPO terms</td>
<td align="left">24,454 disease-causing nsSNV from HGMD associated with 1,142 HPO terms. Control datasets: common polymophisms and rare variants from 1KGP, rare variants in in-house control samples</td>
<td align="left">
<xref ref-type="bibr" rid="B212">Sifrim et al. (2013)</xref>
</td>
</tr>
<tr>
<td align="left">Phenotype-driven</td>
<td align="left">AMELIE (Automatic Mendelian Literature Evaluation)</td>
<td align="left">Missense, stopgain, splicing, indels, duplication</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://amelie.stanford.edu/">https://amelie.stanford.edu/</ext-link>
</td>
<td align="left">Web and stand-alone</td>
<td align="left">May 2020</td>
<td align="left">May 2021</td>
<td align="left">&#x2014;</td>
<td align="left">Natural language processing (NLP) and logistic regression classifier</td>
<td align="left">VCF files, HPO terms</td>
<td align="left">A set of 681 simulated patients using data from OMIM, ClinVar and 1KGP</td>
<td align="left">
<xref ref-type="bibr" rid="B22">Birgmeier et al. (2020)</xref>
</td>
</tr>
<tr>
<td align="left">Phenotype-driven</td>
<td align="left">Phen-Gen</td>
<td align="left">Missense, nonsense, splice site and indels</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://github.com/pkuerten/phen-gen">https://github.com/pkuerten/phen-gen</ext-link>
</td>
<td align="left">Stand-alone</td>
<td align="left">September 2014</td>
<td align="left">&#x2014;</td>
<td align="left">Perl</td>
<td align="left">Random walk&#x2013;with&#x2013;restart algorithm, Bayesian framework based on genotype and phenotype data</td>
<td align="left">VCF files, HPO terms</td>
<td align="left">HGMD 2011.4 datasets</td>
<td align="left">
<xref ref-type="bibr" rid="B108">Javed et al. (2014)</xref>
</td>
</tr>
<tr>
<td align="left">Phenotype-driven</td>
<td align="left">LIRICAL (LIkelihood Ratio Interpretation of Clinical AbnormaLities)</td>
<td align="left">SNVs, indels</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://github.com/TheJacksonLaboratory/LIRICAL">https://github.com/TheJacksonLaboratory/LIRICAL</ext-link>
</td>
<td align="left">Stand-alone</td>
<td align="left">September 2020</td>
<td align="left">September 2021</td>
<td align="left">Java</td>
<td align="left">Likelihood-ratio</td>
<td align="left">VCF files, HPO terms</td>
<td align="left">&#x2014;</td>
<td align="left">
<xref ref-type="bibr" rid="B192">Robinson et al. (2020)</xref>
</td>
</tr>
<tr>
<td align="left">Phenotype only</td>
<td align="left">Phrank (phenotype ranking)</td>
<td align="left">&#x2014;</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://bitbucket.org/bejerano/phrank/src/master/">https://bitbucket.org/bejerano/phrank/src/master/</ext-link>
</td>
<td align="left">Stand-alone</td>
<td align="left">February 2019</td>
<td align="left">&#x2014;</td>
<td align="left">Python</td>
<td align="left">Boolean Bayesian network</td>
<td align="left">HPO terms</td>
<td align="left">Knowledgebase of gene-disease-phenotype relationships, HPO-A</td>
<td align="left">
<xref ref-type="bibr" rid="B106">Jagadeesh et al. (2019)</xref>
</td>
</tr>
<tr>
<td align="left">Phenotype only</td>
<td align="left">PhenoRank</td>
<td align="left">&#x2014;</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://github.com/alexjcornish/PhenoRank">https://github.com/alexjcornish/PhenoRank</ext-link>
</td>
<td align="left">Stand-alone</td>
<td align="left">June 2018</td>
<td align="left">&#x2014;</td>
<td align="left">Python</td>
<td align="left">Phenotypic similarity measured by simGIC, gene scores calculation by random walk with restart (RWR) method</td>
<td align="left">HPO terms</td>
<td align="left">5,685 unique associations between 4,729 diseases and 3,713 genes from ClinVar, OMIM and UniProtKB</td>
<td align="left">
<xref ref-type="bibr" rid="B48">Cornish et al. (2018)</xref>
</td>
</tr>
<tr>
<td align="left">Phenotype only</td>
<td align="left">Phen2Gene</td>
<td align="left">&#x2014;</td>
<td align="left">
<ext-link ext-link-type="uri" xlink:href="https://phen2gene.wglab.org/">https://phen2gene.wglab.org/</ext-link>, <ext-link ext-link-type="uri" xlink:href="https://github.com/WGLab/Phen2Gene">https://github.com/WGLab/Phen2Gene</ext-link>
</td>
<td align="left">Web and stand-alone</td>
<td align="left">June 2020</td>
<td align="left">March 2021</td>
<td align="left">Python</td>
<td align="left">Weighting by skewness</td>
<td align="left">HPO terms</td>
<td align="left">HPO&#x2013;gene annotation files downloaded from the Jackson Laboratory for Genomic Medicine; gene-disease databases OMIM, ClinVar, Orphanet, GeneReviews; gene-gene relationship databases HPRD, HGNC, Biosystem, HTRI</td>
<td align="left">
<xref ref-type="bibr" rid="B255">Zhao et al. (2020)</xref>
</td>
</tr>
</tbody>
</table>
</table-wrap>
<p>First, empirical criteria are used to filter variations. With high quality variants, many studies (<xref ref-type="bibr" rid="B148">Ma et al., 2013</xref>; <xref ref-type="bibr" rid="B24">Blue et al., 2014</xref>) performed prioritization based on <italic>in silico</italic> predictions, MAF in population database and control groups, inheritance pattern, and functional effect. By this method, less than 10 variants are distilled out of hundreds of thousands obtained from WES analysis. Following the validation of orthogonal assays (e.g., Sanger sequencing), true positive causal candidates will be examined for the functional effect on protein <italic>in vitro</italic> and/or <italic>in vivo</italic>. The relationship between variants-phenotype is therefore thoroughly investigated. Several user-friendly rule-based frameworks (<xref ref-type="bibr" rid="B49">Coutant et al., 2012</xref>; <xref ref-type="bibr" rid="B140">Li et al., 2012</xref>; <xref ref-type="bibr" rid="B6">Aleman et al., 2014</xref>; <xref ref-type="bibr" rid="B160">Muller et al., 2017</xref>) have been built to make the filtering procedure easier to implement. Researchers can set their own criteria and get the findings in readable files with detailed annotation information. The prioritization can also be supplemented with adoption of consensus recommendations, such as ACMG/AMP standards and guidelines (<xref ref-type="bibr" rid="B189">Richards et al., 2015</xref>). The guideline includes a comprehensive set of definitions and criteria for variation interpretation, ranging from standardized nomenclature to evidence-based rating yielding a five-tier terminology system outcome. Results from <italic>in silico</italic> predictors are accounted as &#x201c;supporting&#x201d; evidence for benign or pathogenic classification. Some automatic tools (<xref ref-type="bibr" rid="B142">Li and Wang, 2017</xref>; <xref ref-type="bibr" rid="B247">Xavier et al., 2019</xref>) have also been developed for variant classification based on the guidelines, although the manual classification by professional geneticists would be deemed as the golden standard.</p>
<p>The second strategy refers to phenotype-driven frameworks, which combine phenotype and variants data for prioritization and interpretation. Clinical diagnosis would be straightforward when the disease is known. However, before the identification of candidate disease, the procedure to explain a set of clinical features is challenging due to the absence or presence of unrelated features and various degrees of specificity (<xref ref-type="bibr" rid="B127">Kohler et al., 2009</xref>). To extract standardized and normalized phenotypic terminologies from sparse clinical abnormalities in case studies, some tools like Phenomizer (<xref ref-type="bibr" rid="B127">Kohler et al., 2009</xref>) and Doc2HPO (<xref ref-type="bibr" rid="B145">Liu et al., 2019</xref>) are recommended to map the clinical symptoms to the list of known disorders and estimate the significance of each disease match. Prediction scores from <italic>in silico</italic> predictors are integrated in this kind of framework as &#x201c;pathogenicity&#x201d; or &#x201c;deleteriousness&#x201d; features. Most of phenotype-driven tools (<xref ref-type="bibr" rid="B212">Sifrim et al., 2013</xref>; <xref ref-type="bibr" rid="B108">Javed et al., 2014</xref>; <xref ref-type="bibr" rid="B215">Smedley et al., 2015</xref>; <xref ref-type="bibr" rid="B22">Birgmeier et al., 2020</xref>; <xref ref-type="bibr" rid="B192">Robinson et al., 2020</xref>) require variant files and HPO terms as input, while some tools (<xref ref-type="bibr" rid="B48">Cornish et al., 2018</xref>; <xref ref-type="bibr" rid="B106">Jagadeesh et al., 2019</xref>; <xref ref-type="bibr" rid="B255">Zhao et al., 2020</xref>) require only HPO terms. <xref ref-type="bibr" rid="B249">Yuan et al. (2022)</xref> investigated causal-gene prioritizing performance of both types on two benchmark datasets in a recent comparative study and revealed that former ones performed better overall than latter ones. Their results also indicated the complementarity of multiple phenotype-driven tools towards a viable integrated strategy may improve diagnostic efficiency (<xref ref-type="bibr" rid="B249">Yuan et al., 2022</xref>).</p>
</sec>
<sec id="s5">
<title>5 Discussion</title>
<p>In this review, we firstly summarized the database resources frequently used during predictor development. We then discussed the rational, necessity and limitations for the newly categorized predictors: homologous sequence-based, structural-based, combination of sequence and structural, meta-predictors, population-based, and gene-, phenotype-, disease-specific predictors. Predictor performance as well as their limitations and possible remedies were then outlined. The application of the predictors in real studies was finally presented demonstrating their efficient assistance in variant characterization and prioritization, as well as the discovery of genotype-phenotype association.</p>
<p>When building predictors, unambiguous labeled datasets are critical. Avoiding overlapping and contradicting data, as well as balancing the positive-negative ratio in training and validation datasets, will definitely minimize the negative influence of circularity. Further examination on the collinearity between/among feature variables will facilitate the optimization of prediction models, even though some algorithms are literally not affected.</p>
<p>Among the predictors, meta-predictors outperform others in general; however, their prediction performance is considerably discounted in some disease-specific datasets, raising concern about their applications especially in clinical settings (<xref ref-type="bibr" rid="B203">Schiemann and Stowell, 2016</xref>; <xref ref-type="bibr" rid="B151">Mahmood et al., 2017</xref>). Employment of disease-, gene-, phenotype-specific predictors can to an extent solve the above issue. When selecting predictors for a particular study, efforts should be given on screening whether the genes and phenotype predictor calibrated perfectly matching your research, and understanding the scope and predictive performance of each predictor. On the other hand, we look forward to more specialized predictors sculpted for a variety of phenotypes covering both common and rare diseases.</p>
<p>According to Variation Ontology (VariO) (<xref ref-type="bibr" rid="B240">Vihinen, 2014</xref>), variant impacts on protein level can be annotated with effects on function, structure and property. Variants impact on protein functional or property effects can be classified as follows: abundance, which includes gene dosage, expression, degradation and mis-localization; activity, which includes enzymatic, kinetic and regulation; enzymatic specificity, and molecular affinity (<xref ref-type="bibr" rid="B237">Vihinen, 2021</xref>). Most of above-mentioned predictors computed the possibility of pathogenic effect on protein function and structure in a broad range, rather the effects on protein abundance, activity or affinity properties separately. This may indicate a challenging future orientation of variant predictors development.</p>
<p>The correlation between variants pathogenic prediction on protein function or structure and abnormal clinical outcomes are validated by experimental facts at the current stage. For certain phenotypes, an evident enrichment of deleterious variants in a set of disease-related genes, such as the increased mutational burden in essential genes in autism spectrum disorder (<xref ref-type="bibr" rid="B109">Ji et al., 2016</xref>), WNT signaling genes in myelomeningocele (<xref ref-type="bibr" rid="B96">Hebert et al., 2020</xref>), a set of 5 genes in epilepsy (<xref ref-type="bibr" rid="B135">Leu et al., 2015</xref>). The gap between observed higher burden genes and clinical phenotype is then bridged by functional or mechanical experimental studies. For example, meiocytes with pathogenic mutation p.S167L in <italic>HSF2BP</italic> found in premature ovarian insufficiency (POI) patients from a family, showed a reduced number of foci formed by the recombinases RAD51/DMC1, leading to crossover defect, which provided an insight into the molecular mechanism of mutation in POI and subfertility (<xref ref-type="bibr" rid="B71">Felipe-Medina et al., 2020</xref>). Currently, variant impact predictors are insufficient for indicating molecular mechanism of pathogenicity. However, the advancement of protein structure prediction may assist the interpretation of pathogenic variants since structural information gives useful insights in evaluating variant impact on protein or biological systems (<xref ref-type="bibr" rid="B61">Diwan et al., 2021</xref>).</p>
<p>Impacts of mutations on protein synthesis includes transcriptional and translational influences. For SNVs, the impact on transcription involves in changes in transcript sequence and influence in gene regulation (<xref ref-type="bibr" rid="B93">Haraksingh and Snyder, 2013</xref>). Tools for predicting impact on gene regulation have been timely and systematically reviewed by other studies (<xref ref-type="bibr" rid="B144">Li et al., 2015</xref>; <xref ref-type="bibr" rid="B168">Ohno et al., 2018</xref>; <xref ref-type="bibr" rid="B193">Rojano et al., 2019</xref>; <xref ref-type="bibr" rid="B34">Canson et al., 2020</xref>). In terms of translation, SNVs-induced amino acid substitution causes protein structure and function abnormalities, and the prediction methods have been explored in this study. The deeper association between SNVs for protein folding and post-translation modification is still being investigated.</p>
<p>With the development of a cutting-edge structure prediction tool, AlphaFold2, the unstructured human protein narrowed down to less than 30% (<xref ref-type="bibr" rid="B182">Porta-Pardo et al., 2022</xref>). However, examples showed that AlphaFold2 was not capable for predicting protein structure modification caused by pathogenic mutations, particularly those having experimentally proven destabilizing effect (<xref ref-type="bibr" rid="B31">Buel and Walters, 2022</xref>). The reasons for this limitation may relate to the bioinformatics and physical methodologies utilized in modeling, as well as the resources from protein sequence and PDB structure data employed, instead of the fundamental driving forces of protein folding (<xref ref-type="bibr" rid="B113">Jumper et al., 2021</xref>; <xref ref-type="bibr" rid="B31">Buel and Walters, 2022</xref>). The AlphaFold team is presently considering solutions for new mutations, which may give better prediction on unfolding to folding state, based on protein physics instead of sequence evolutionary (<xref ref-type="bibr" rid="B33">Callaway, 2022</xref>). We anticipate that its success will usher in a new age of human genetic research, including the acceleration of <italic>in silico</italic> functional and mechanical genotype-phenotype association investigations.</p>
<p>Finally, although the variant effect predictors greatly help the genomic interpretation, end-users should keep in mind that the predictor&#x2019;s role is only an assistance to clinical diagnosis, and merely a starting point (<xref ref-type="bibr" rid="B69">Eilbeck et al., 2017</xref>). The unequal relationship between predicted damaging effect and pathogenicity warns their usage. In addition, under some circumstances, the predicted scores overstating the effect of uncommon mutations, will cause inflated estimation affecting the specificity and sensitivity (<xref ref-type="bibr" rid="B133">Lanktree et al., 2018</xref>). Therefore, experimental validations, the golden standard in variant impact evaluation, are still indispensable.</p>
</sec>
</body>
<back>
<sec id="s6">
<title>Author contributions</title>
<p>YL and DC designed the structure of the review. YL wrote the draft manuscript, curated data, organized tables and figure. DC supervised the work and revised the manuscript. PC and WY supervised and reviewed the manuscript. All authors contributed to the article and approved the submitted version.</p>
</sec>
<sec id="s7">
<title>Funding</title>
<p>This work was supported by the Shenzhen Fundamental Research Program, China (no. JCYJ20210324114807019).</p>
</sec>
<sec sec-type="COI-statement" id="s8">
<title>Conflict of interest</title>
<p>The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.</p>
</sec>
<sec sec-type="disclaimer" id="s9">
<title>Publisher&#x2019;s note</title>
<p>All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article, or claim that may be made by its manufacturer, is not guaranteed or endorsed by the publisher.</p>
</sec>
<sec id="s10">
<title>Supplementary material</title>
<p>The Supplementary Material for this article can be found online at: <ext-link ext-link-type="uri" xlink:href="https://www.frontiersin.org/articles/10.3389/fgene.2022.981005/full#supplementary-material">https://www.frontiersin.org/articles/10.3389/fgene.2022.981005/full&#x23;supplementary-material</ext-link>
</p>
<supplementary-material xlink:href="Table1.docx" id="SM1" mimetype="application/docx" xmlns:xlink="http://www.w3.org/1999/xlink"/>
</sec>
<ref-list>
<title>References</title>
<ref id="B1">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Accetturo</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Bartolomeo</surname>
<given-names>N.</given-names>
</name>
<name>
<surname>Stella</surname>
<given-names>A.</given-names>
</name>
</person-group> (<year>2020</year>). <article-title>
<italic>In-silico</italic> analysis of NF1 missense variants in ClinVar: Translating variant predictions into variant interpretation and classification</article-title>. <source>Int. J. Mol. Sci.</source> <volume>21</volume> (<issue>3</issue>), <fpage>E721</fpage>. <pub-id pub-id-type="doi">10.3390/ijms21030721</pub-id> </citation>
</ref>
<ref id="B2">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Adhikari</surname>
<given-names>A. N.</given-names>
</name>
</person-group> (<year>2019</year>). <article-title>Gene-specific features enhance interpretation of mutational impact on acid alpha-glucosidase enzyme activity</article-title>. <source>Hum. Mutat.</source> <volume>40</volume> (<issue>9</issue>), <fpage>1507</fpage>&#x2013;<lpage>1518</lpage>. <pub-id pub-id-type="doi">10.1002/humu.23846</pub-id> </citation>
</ref>
<ref id="B3">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Adzhubei</surname>
<given-names>I. A.</given-names>
</name>
<name>
<surname>Schmidt</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Peshkin</surname>
<given-names>L.</given-names>
</name>
<name>
<surname>Ramensky</surname>
<given-names>V. E.</given-names>
</name>
<name>
<surname>Gerasimova</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Bork</surname>
<given-names>P.</given-names>
</name>
<etal/>
</person-group> (<year>2010</year>). <article-title>A method and server for predicting damaging missense mutations</article-title>. <source>Nat. Methods</source> <volume>7</volume> (<issue>4</issue>), <fpage>248</fpage>&#x2013;<lpage>249</lpage>. <pub-id pub-id-type="doi">10.1038/nmeth0410-248</pub-id> </citation>
</ref>
<ref id="B4">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Ahmed</surname>
<given-names>A. B.</given-names>
</name>
<name>
<surname>Znassi</surname>
<given-names>N.</given-names>
</name>
<name>
<surname>Chateau</surname>
<given-names>M. T.</given-names>
</name>
<name>
<surname>Kajava</surname>
<given-names>A. V.</given-names>
</name>
</person-group> (<year>2015</year>). <article-title>A structure-based approach to predict predisposition to amyloidosis</article-title>. <source>Alzheimers Dement.</source> <volume>11</volume> (<issue>6</issue>), <fpage>681</fpage>&#x2013;<lpage>690</lpage>. <pub-id pub-id-type="doi">10.1016/j.jalz.2014.06.007</pub-id> </citation>
</ref>
<ref id="B5">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Ainscough</surname>
<given-names>B. J.</given-names>
</name>
<name>
<surname>Griffith</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Coffman</surname>
<given-names>A. C.</given-names>
</name>
<name>
<surname>Wagner</surname>
<given-names>A. H.</given-names>
</name>
<name>
<surname>Kunisaki</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Choudhary</surname>
<given-names>M. N.</given-names>
</name>
<etal/>
</person-group> (<year>2016</year>). <article-title>DoCM: A database of curated mutations in cancer</article-title>. <source>Nat. Methods</source> <volume>13</volume>(<issue>10</issue>), <fpage>806</fpage>&#x2013;<lpage>807</lpage>. <pub-id pub-id-type="doi">10.1038/nmeth.4000</pub-id> </citation>
</ref>
<ref id="B6">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Aleman</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Garcia-Garcia</surname>
<given-names>F.</given-names>
</name>
<name>
<surname>Salavert</surname>
<given-names>F.</given-names>
</name>
<name>
<surname>Medina</surname>
<given-names>I.</given-names>
</name>
<name>
<surname>Dopazo</surname>
<given-names>J.</given-names>
</name>
</person-group> (<year>2014</year>). <article-title>A web-based interactive framework to assist in the prioritization of disease candidate genes in whole-exome sequencing studies</article-title>. <source>Nucleic Acids Res.</source> <volume>42</volume>, <fpage>W88</fpage>&#x2013;<lpage>W93</lpage>. <comment>Web Server issue)</comment>. <pub-id pub-id-type="doi">10.1093/nar/gku407</pub-id> </citation>
</ref>
<ref id="B7">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Alirezaie</surname>
<given-names>N.</given-names>
</name>
<name>
<surname>Kernohan</surname>
<given-names>K. D.</given-names>
</name>
<name>
<surname>Hartley</surname>
<given-names>T.</given-names>
</name>
<name>
<surname>Majewski</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Hocking</surname>
<given-names>T. D.</given-names>
</name>
</person-group> (<year>2018</year>). <article-title>ClinPred: Prediction tool to identify disease-relevant nonsynonymous single-nucleotide variants</article-title>. <source>Am. J. Hum. Genet.</source> <volume>103</volume> (<issue>4</issue>), <fpage>474</fpage>&#x2013;<lpage>483</lpage>. <pub-id pub-id-type="doi">10.1016/j.ajhg.2018.08.005</pub-id> </citation>
</ref>
<ref id="B8">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Altschul</surname>
<given-names>S. F.</given-names>
</name>
<name>
<surname>Gish</surname>
<given-names>W.</given-names>
</name>
<name>
<surname>Miller</surname>
<given-names>W.</given-names>
</name>
<name>
<surname>Myers</surname>
<given-names>E. W.</given-names>
</name>
<name>
<surname>Lipman</surname>
<given-names>D. J.</given-names>
</name>
</person-group> (<year>1990</year>). <article-title>Basic local alignment search tool</article-title>. <source>J. Mol. Biol.</source> <volume>215</volume> (<issue>3</issue>), <fpage>403</fpage>&#x2013;<lpage>410</lpage>. <pub-id pub-id-type="doi">10.1016/S0022-2836(05)80360-2</pub-id> </citation>
</ref>
<ref id="B9">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Amberger</surname>
<given-names>J. S.</given-names>
</name>
<name>
<surname>Bocchini</surname>
<given-names>C. A.</given-names>
</name>
<name>
<surname>Scott</surname>
<given-names>A. F.</given-names>
</name>
<name>
<surname>Hamosh</surname>
<given-names>A.</given-names>
</name>
</person-group> (<year>2019</year>). <article-title>OMIM.org: Leveraging knowledge across phenotype-gene relationships</article-title>. <source>Nucleic Acids Res.</source> <volume>47</volume> (<issue>D1</issue>), <fpage>D1038-D1043</fpage>&#x2013;<lpage>D1043</lpage>. <pub-id pub-id-type="doi">10.1093/nar/gky1151</pub-id> </citation>
</ref>
<ref id="B10">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Anderson</surname>
<given-names>D.</given-names>
</name>
<name>
<surname>Lassmann</surname>
<given-names>T.</given-names>
</name>
</person-group> (<year>2022</year>). <article-title>An expanded phenotype centric benchmark of variant prioritisation tools</article-title>. <source>Hum. Mutat.</source> <volume>43</volume> (<issue>5</issue>), <fpage>539</fpage>&#x2013;<lpage>546</lpage>. <pub-id pub-id-type="doi">10.1002/humu.24362</pub-id> </citation>
</ref>
<ref id="B11">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Andreoletti</surname>
<given-names>G.</given-names>
</name>
<name>
<surname>Pal</surname>
<given-names>L. R.</given-names>
</name>
<name>
<surname>Moult</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Brenner</surname>
<given-names>S. E.</given-names>
</name>
</person-group> (<year>2019</year>). <article-title>Reports from the fifth edition of CAGI: The critical assessment of genome interpretation</article-title>. <source>Hum. Mutat.</source> <volume>40</volume> (<issue>9</issue>), <fpage>1197</fpage>&#x2013;<lpage>1201</lpage>. <pub-id pub-id-type="doi">10.1002/humu.23876</pub-id> </citation>
</ref>
<ref id="B12">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Ashburner</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Ball</surname>
<given-names>C. A.</given-names>
</name>
<name>
<surname>Blake</surname>
<given-names>J. A.</given-names>
</name>
<name>
<surname>Botstein</surname>
<given-names>D.</given-names>
</name>
<name>
<surname>Butler</surname>
<given-names>H.</given-names>
</name>
<name>
<surname>Cherry</surname>
<given-names>J. M.</given-names>
</name>
<etal/>
</person-group> (<year>2000</year>). <article-title>Gene ontology: Tool for the unification of biology. The gene ontology consortium</article-title>. <source>Nat. Genet.</source> <volume>25</volume> (<issue>1</issue>), <fpage>25</fpage>&#x2013;<lpage>29</lpage>. <pub-id pub-id-type="doi">10.1038/75556</pub-id> </citation>
</ref>
<ref id="B13">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Ayme</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Urbero</surname>
<given-names>B.</given-names>
</name>
<name>
<surname>Oziel</surname>
<given-names>D.</given-names>
</name>
<name>
<surname>Lecouturier</surname>
<given-names>E.</given-names>
</name>
<name>
<surname>Biscarat</surname>
<given-names>A. C.</given-names>
</name>
</person-group> (<year>1998</year>). <article-title>Information on rare diseases: The Orphanet project</article-title>. <source>La Rev. Med. Interne</source> <volume>19</volume> (<issue>3</issue>), <fpage>376S</fpage>&#x2013;<lpage>377S</lpage>. <pub-id pub-id-type="doi">10.1016/s0248-8663(98)90021-2</pub-id> </citation>
</ref>
<ref id="B14">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Azaiez</surname>
<given-names>H.</given-names>
</name>
<name>
<surname>Booth</surname>
<given-names>K. T.</given-names>
</name>
<name>
<surname>Ephraim</surname>
<given-names>S. S.</given-names>
</name>
<name>
<surname>Crone</surname>
<given-names>B.</given-names>
</name>
<name>
<surname>Black-Ziegelbein</surname>
<given-names>E. A.</given-names>
</name>
<name>
<surname>Marini</surname>
<given-names>R. J.</given-names>
</name>
<etal/>
</person-group> (<year>2018</year>). <article-title>Genomic landscape and mutational Signatures of deafness-associated genes</article-title>. <source>Am. J. Hum. Genet.</source> <volume>103</volume> (<issue>4</issue>), <fpage>484</fpage>&#x2013;<lpage>497</lpage>. <pub-id pub-id-type="doi">10.1016/j.ajhg.2018.08.006</pub-id> </citation>
</ref>
<ref id="B15">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Baker</surname>
<given-names>W.</given-names>
</name>
<name>
<surname>van den Broek</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Camon</surname>
<given-names>E.</given-names>
</name>
<name>
<surname>Hingamp</surname>
<given-names>P.</given-names>
</name>
<name>
<surname>Sterk</surname>
<given-names>P.</given-names>
</name>
<name>
<surname>Stoesser</surname>
<given-names>G.</given-names>
</name>
<etal/>
</person-group> (<year>2000</year>). <article-title>The EMBL nucleotide sequence database</article-title>. <source>Nucleic Acids Res.</source> <volume>28</volume> (<issue>1</issue>), <fpage>19</fpage>&#x2013;<lpage>23</lpage>. <pub-id pub-id-type="doi">10.1093/nar/28.1.19</pub-id> </citation>
</ref>
<ref id="B16">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Banck</surname>
<given-names>H.</given-names>
</name>
<name>
<surname>Dugas</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>C</surname>
<given-names>M. U.-T.</given-names>
</name>
<name>
<surname>Sandmann</surname>
<given-names>S.</given-names>
</name>
</person-group> (<year>2021</year>). <article-title>Comparison of open-access databases for clinical variant interpretation in cancer: A case study of MDS/AML</article-title>. <source>Cancer Genomics Proteomics</source> <volume>18</volume> (<issue>2</issue>), <fpage>157</fpage>&#x2013;<lpage>166</lpage>. <pub-id pub-id-type="doi">10.21873/cgp.20250</pub-id> </citation>
</ref>
<ref id="B17">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Banerjee</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Raman</surname>
<given-names>K.</given-names>
</name>
<name>
<surname>Ravindran</surname>
<given-names>B.</given-names>
</name>
</person-group> (<year>2021</year>). <article-title>Sequence neighborhoods enable reliable prediction of pathogenic mutations in cancer genomes</article-title>. <source>Cancers (Basel)</source> <volume>13</volume> (<issue>10</issue>), <fpage>2366</fpage>. <pub-id pub-id-type="doi">10.3390/cancers13102366</pub-id> </citation>
</ref>
<ref id="B18">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Bayman</surname>
<given-names>E. O.</given-names>
</name>
<name>
<surname>Dexter</surname>
<given-names>F.</given-names>
</name>
</person-group> (<year>2021</year>). <article-title>Multicollinearity in logistic regression models</article-title>. <source>Anesth. Analg.</source> <volume>133</volume> (<issue>2</issue>), <fpage>362</fpage>&#x2013;<lpage>365</lpage>. <pub-id pub-id-type="doi">10.1213/ANE.0000000000005593</pub-id> </citation>
</ref>
<ref id="B19">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Bendl</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Stourac</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Salanda</surname>
<given-names>O.</given-names>
</name>
<name>
<surname>Pavelka</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Wieben</surname>
<given-names>E. D.</given-names>
</name>
<name>
<surname>Zendulka</surname>
<given-names>J.</given-names>
</name>
<etal/>
</person-group> (<year>2014</year>). <article-title>PredictSNP: Robust and accurate consensus classifier for prediction of disease-related mutations</article-title>. <source>PLoS Comput. Biol.</source> <volume>10</volume> (<issue>1</issue>), <fpage>e1003440</fpage>. <pub-id pub-id-type="doi">10.1371/journal.pcbi.1003440</pub-id> </citation>
</ref>
<ref id="B20">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Berliner</surname>
<given-names>N.</given-names>
</name>
<name>
<surname>Teyra</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Colak</surname>
<given-names>R.</given-names>
</name>
<name>
<surname>Garcia Lopez</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Kim</surname>
<given-names>P. M.</given-names>
</name>
</person-group> (<year>2014</year>). <article-title>Combining structural modeling with ensemble machine learning to accurately predict protein fold stability and binding affinity effects upon mutation</article-title>. <source>PLoS One</source> <volume>9</volume> (<issue>9</issue>), <fpage>e107353</fpage>. <pub-id pub-id-type="doi">10.1371/journal.pone.0107353</pub-id> </citation>
</ref>
<ref id="B21">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Berman</surname>
<given-names>H. M.</given-names>
</name>
<name>
<surname>Westbrook</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Feng</surname>
<given-names>Z.</given-names>
</name>
<name>
<surname>Gilliland</surname>
<given-names>G.</given-names>
</name>
<name>
<surname>Bhat</surname>
<given-names>T. N.</given-names>
</name>
<name>
<surname>Weissig</surname>
<given-names>H.</given-names>
</name>
<etal/>
</person-group> (<year>2000</year>). <article-title>The protein Data Bank</article-title>. <source>Nucleic Acids Res.</source> <volume>28</volume> (<issue>1</issue>), <fpage>235</fpage>&#x2013;<lpage>242</lpage>. <pub-id pub-id-type="doi">10.1093/nar/28.1.235</pub-id> </citation>
</ref>
<ref id="B22">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Birgmeier</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Haeussler</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Deisseroth</surname>
<given-names>C. A.</given-names>
</name>
<name>
<surname>Steinberg</surname>
<given-names>E. H.</given-names>
</name>
<name>
<surname>Jagadeesh</surname>
<given-names>K. A.</given-names>
</name>
<name>
<surname>Ratner</surname>
<given-names>A. J.</given-names>
</name>
<etal/>
</person-group> (<year>2020</year>). <article-title>AMELIE speeds Mendelian diagnosis by matching patient phenotype and genotype to primary literature</article-title>. <source>Sci. Transl. Med.</source> <volume>12</volume> (<issue>544</issue>), <fpage>eaau9113</fpage>. <pub-id pub-id-type="doi">10.1126/scitranslmed.aau9113</pub-id> </citation>
</ref>
<ref id="B259">
<citation citation-type="web">
<person-group person-group-type="author">
<name>
<surname>Birrane</surname>
<given-names>G.</given-names>
</name>
<name>
<surname>Soni</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Ladias</surname>
<given-names>J. A. A.</given-names>
</name>
</person-group> (<year>2006</year>). <article-title>X-ray Structure of the BRCA1 BRCT mutant M1775K [Online]</article-title>. <comment>Available at: <ext-link ext-link-type="uri" xlink:href="https://gnomad.broadinstitute.org/variant/17-43051071-A-C?dataset=gnomad_r3">https://gnomad.broadinstitute.org/variant/17-43051071-A-C&#x003F;dataset&#x003D;gnomad&#x005F;r3</ext-link>
</comment> (<comment>Accessed September 13 2022</comment>) <comment>[abstract]</comment>. </citation>
</ref>
<ref id="B23">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Blanchette</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Kent</surname>
<given-names>W. J.</given-names>
</name>
<name>
<surname>Riemer</surname>
<given-names>C.</given-names>
</name>
<name>
<surname>Elnitski</surname>
<given-names>L.</given-names>
</name>
<name>
<surname>Smit</surname>
<given-names>A. F.</given-names>
</name>
<name>
<surname>Roskin</surname>
<given-names>K. M.</given-names>
</name>
<etal/>
</person-group> (<year>2004</year>). <article-title>Aligning multiple genomic sequences with the threaded blockset aligner</article-title>. <source>Genome Res.</source> <volume>14</volume> (<issue>4</issue>), <fpage>708</fpage>&#x2013;<lpage>715</lpage>. <pub-id pub-id-type="doi">10.1101/gr.1933104</pub-id> </citation>
</ref>
<ref id="B24">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Blue</surname>
<given-names>G. M.</given-names>
</name>
<name>
<surname>Kirk</surname>
<given-names>E. P.</given-names>
</name>
<name>
<surname>Giannoulatou</surname>
<given-names>E.</given-names>
</name>
<name>
<surname>Dunwoodie</surname>
<given-names>S. L.</given-names>
</name>
<name>
<surname>Ho</surname>
<given-names>J. W.</given-names>
</name>
<name>
<surname>Hilton</surname>
<given-names>D. C.</given-names>
</name>
<etal/>
</person-group> (<year>2014</year>). <article-title>Targeted next-generation sequencing identifies pathogenic variants in familial congenital heart disease</article-title>. <source>J. Am. Coll. Cardiol.</source> <volume>64</volume> (<issue>23</issue>), <fpage>2498</fpage>&#x2013;<lpage>2506</lpage>. <pub-id pub-id-type="doi">10.1016/j.jacc.2014.09.048</pub-id> </citation>
</ref>
<ref id="B25">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Bonaventura</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Riggs</surname>
<given-names>A.</given-names>
</name>
</person-group> (<year>1968</year>). <article-title>Hemoglobin Kansas, a human hemoglobin with a neutral amino acid substitution and an abnormal oxygen equilibrium</article-title>. <source>J. Biol. Chem.</source> <volume>243</volume> (<issue>5</issue>), <fpage>980</fpage>&#x2013;<lpage>991</lpage>. <pub-id pub-id-type="doi">10.1016/s0021-9258(18)93612-4</pub-id> </citation>
</ref>
<ref id="B26">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Boucher</surname>
<given-names>J. I.</given-names>
</name>
<name>
<surname>Bolon</surname>
<given-names>D. N.</given-names>
</name>
<name>
<surname>Tawfik</surname>
<given-names>D. S.</given-names>
</name>
</person-group> (<year>2016</year>). <article-title>Quantifying and understanding the fitness effects of protein mutations: Laboratory versus nature</article-title>. <source>Protein Sci.</source> <volume>25</volume> (<issue>7</issue>), <fpage>1219</fpage>&#x2013;<lpage>1226</lpage>. <pub-id pub-id-type="doi">10.1002/pro.2928</pub-id> </citation>
</ref>
<ref id="B27">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Brock</surname>
<given-names>G. N.</given-names>
</name>
<name>
<surname>Shaffer</surname>
<given-names>J. R.</given-names>
</name>
<name>
<surname>Blakesley</surname>
<given-names>R. E.</given-names>
</name>
<name>
<surname>Lotz</surname>
<given-names>M. J.</given-names>
</name>
<name>
<surname>Tseng</surname>
<given-names>G. C.</given-names>
</name>
</person-group> (<year>2008</year>). <article-title>Which missing value imputation method to use in expression profiles: A comparative study and two selection schemes</article-title>. <source>BMC Bioinforma.</source> <volume>9</volume>, <fpage>12</fpage>. <pub-id pub-id-type="doi">10.1186/1471-2105-9-12</pub-id> </citation>
</ref>
<ref id="B28">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Bromberg</surname>
<given-names>Y.</given-names>
</name>
<name>
<surname>Rost</surname>
<given-names>B.</given-names>
</name>
</person-group> (<year>2007</year>). <article-title>Snap: Predict effect of non-synonymous polymorphisms on function</article-title>. <source>Nucleic Acids Res.</source> <volume>35</volume> (<issue>11</issue>), <fpage>3823</fpage>&#x2013;<lpage>3835</lpage>. <pub-id pub-id-type="doi">10.1093/nar/gkm238</pub-id> </citation>
</ref>
<ref id="B29">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Brookes</surname>
<given-names>A. J.</given-names>
</name>
<name>
<surname>Robinson</surname>
<given-names>P. N.</given-names>
</name>
</person-group> (<year>2015</year>). <article-title>Human genotype-phenotype databases: Aims, challenges and opportunities</article-title>. <source>Nat. Rev. Genet.</source> <volume>16</volume> (<issue>12</issue>), <fpage>702</fpage>&#x2013;<lpage>715</lpage>. <pub-id pub-id-type="doi">10.1038/nrg3932</pub-id> </citation>
</ref>
<ref id="B30">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Bu</surname>
<given-names>F.</given-names>
</name>
<name>
<surname>Zhong</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Chen</surname>
<given-names>Q.</given-names>
</name>
<name>
<surname>Wang</surname>
<given-names>Y.</given-names>
</name>
<name>
<surname>Zhao</surname>
<given-names>X.</given-names>
</name>
<name>
<surname>Zhang</surname>
<given-names>Q.</given-names>
</name>
<etal/>
</person-group> (<year>2022</year>). <article-title>DVPred: A disease-specific prediction tool for variant pathogenicity classification for hearing loss</article-title>. <source>Hum. Genet.</source> <volume>141</volume> (<issue>3-4</issue>), <fpage>401</fpage>&#x2013;<lpage>411</lpage>. <pub-id pub-id-type="doi">10.1007/s00439-022-02440-1</pub-id> </citation>
</ref>
<ref id="B31">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Buel</surname>
<given-names>G. R.</given-names>
</name>
<name>
<surname>Walters</surname>
<given-names>K. J.</given-names>
</name>
</person-group> (<year>2022</year>). <article-title>Can AlphaFold2 predict the impact of missense mutations on structure?</article-title> <source>Nat. Struct. Mol. Biol.</source> <volume>29</volume> (<issue>1</issue>), <fpage>1</fpage>&#x2013;<lpage>2</lpage>. <pub-id pub-id-type="doi">10.1038/s41594-021-00714-2</pub-id> </citation>
</ref>
<ref id="B32">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Calabrese</surname>
<given-names>R.</given-names>
</name>
<name>
<surname>Capriotti</surname>
<given-names>E.</given-names>
</name>
<name>
<surname>Fariselli</surname>
<given-names>P.</given-names>
</name>
<name>
<surname>Martelli</surname>
<given-names>P. L.</given-names>
</name>
<name>
<surname>Casadio</surname>
<given-names>R.</given-names>
</name>
</person-group> (<year>2009</year>). <article-title>Functional annotations improve the predictive score of human disease-related mutations in proteins</article-title>. <source>Hum. Mutat.</source> <volume>30</volume> (<issue>8</issue>), <fpage>1237</fpage>&#x2013;<lpage>1244</lpage>. <pub-id pub-id-type="doi">10.1002/humu.21047</pub-id> </citation>
</ref>
<ref id="B33">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Callaway</surname>
<given-names>E.</given-names>
</name>
</person-group> (<year>2022</year>). <article-title>What&#x27;s next for AlphaFold and the AI protein-folding revolution</article-title>. <source>Nature</source> <volume>604</volume> (<issue>7905</issue>), <fpage>234</fpage>&#x2013;<lpage>238</lpage>. <pub-id pub-id-type="doi">10.1038/d41586-022-00997-5</pub-id> </citation>
</ref>
<ref id="B34">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Canson</surname>
<given-names>D.</given-names>
</name>
<name>
<surname>Glubb</surname>
<given-names>D.</given-names>
</name>
<name>
<surname>Spurdle</surname>
<given-names>A. B.</given-names>
</name>
</person-group> (<year>2020</year>). <article-title>Variant effect on splicing regulatory elements, branchpoint usage, and pseudoexonization: Strategies to enhance bioinformatic prediction using hereditary cancer genes as exemplars</article-title>. <source>Hum. Mutat.</source> <volume>41</volume> (<issue>10</issue>), <fpage>1705</fpage>&#x2013;<lpage>1721</lpage>. <pub-id pub-id-type="doi">10.1002/humu.24074</pub-id> </citation>
</ref>
<ref id="B35">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Capriotti</surname>
<given-names>E.</given-names>
</name>
<name>
<surname>Altman</surname>
<given-names>R. B.</given-names>
</name>
<name>
<surname>Bromberg</surname>
<given-names>Y.</given-names>
</name>
</person-group> (<year>2013</year>). <article-title>Collective judgment predicts disease-associated single nucleotide variants</article-title>. <source>BMC Genomics</source> <volume>14</volume> (<issue>3</issue>), <fpage>S2</fpage>. <pub-id pub-id-type="doi">10.1186/1471-2164-14-S3-S2</pub-id> </citation>
</ref>
<ref id="B36">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Capriotti</surname>
<given-names>E.</given-names>
</name>
<name>
<surname>Calabrese</surname>
<given-names>R.</given-names>
</name>
<name>
<surname>Casadio</surname>
<given-names>R.</given-names>
</name>
</person-group> (<year>2006</year>). <article-title>Predicting the insurgence of human genetic diseases associated to single point protein mutations with support vector machines and evolutionary information</article-title>. <source>Bioinformatics</source> <volume>22</volume> (<issue>22</issue>), <fpage>2729</fpage>&#x2013;<lpage>2734</lpage>. <pub-id pub-id-type="doi">10.1093/bioinformatics/btl423</pub-id> </citation>
</ref>
<ref id="B37">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Carter</surname>
<given-names>H.</given-names>
</name>
<name>
<surname>Douville</surname>
<given-names>C.</given-names>
</name>
<name>
<surname>Stenson</surname>
<given-names>P. D.</given-names>
</name>
<name>
<surname>Cooper</surname>
<given-names>D. N.</given-names>
</name>
<name>
<surname>Karchin</surname>
<given-names>R.</given-names>
</name>
</person-group> (<year>2013</year>). <article-title>Identifying Mendelian disease genes with the variant effect scoring tool</article-title>. <source>BMC Genomics</source> <volume>14</volume>, <fpage>S3</fpage>. <pub-id pub-id-type="doi">10.1186/1471-2164-14-S3-S3</pub-id> </citation>
</ref>
<ref id="B38">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Chan</surname>
<given-names>J. Y.-L.</given-names>
</name>
<name>
<surname>Leow</surname>
<given-names>S. M. H.</given-names>
</name>
<name>
<surname>Bea</surname>
<given-names>K. T.</given-names>
</name>
<name>
<surname>Cheng</surname>
<given-names>W. K.</given-names>
</name>
<name>
<surname>Phoong</surname>
<given-names>S. W.</given-names>
</name>
<name>
<surname>Hong</surname>
<given-names>Z.-W.</given-names>
</name>
<etal/>
</person-group> (<year>2022</year>). <article-title>Mitigating the multicollinearity problem and its machine learning approach: A review</article-title>. <source>Mathematics</source> <volume>10</volume> (<issue>8</issue>), <fpage>1283</fpage>. <pub-id pub-id-type="doi">10.3390/math10081283</pub-id> </citation>
</ref>
<ref id="B39">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Chennen</surname>
<given-names>K.</given-names>
</name>
<name>
<surname>Weber</surname>
<given-names>T.</given-names>
</name>
<name>
<surname>Lornage</surname>
<given-names>X.</given-names>
</name>
<name>
<surname>Kress</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Bohm</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Thompson</surname>
<given-names>J.</given-names>
</name>
<etal/>
</person-group> (<year>2020</year>). <article-title>Mistic: A prediction tool to reveal disease-relevant deleterious missense variants</article-title>. <source>PLoS One</source> <volume>15</volume> (<issue>7</issue>), <fpage>e0236962</fpage>. <pub-id pub-id-type="doi">10.1371/journal.pone.0236962</pub-id> </citation>
</ref>
<ref id="B40">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Choi</surname>
<given-names>Y.</given-names>
</name>
<name>
<surname>Chan</surname>
<given-names>A. P.</given-names>
</name>
</person-group> (<year>2015</year>). <article-title>PROVEAN web server: A tool to predict the functional effect of amino acid substitutions and indels</article-title>. <source>Bioinformatics</source> <volume>31</volume> (<issue>16</issue>), <fpage>2745</fpage>&#x2013;<lpage>2747</lpage>. <pub-id pub-id-type="doi">10.1093/bioinformatics/btv195</pub-id> </citation>
</ref>
<ref id="B41">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Choi</surname>
<given-names>Y.</given-names>
</name>
<name>
<surname>Sims</surname>
<given-names>G. E.</given-names>
</name>
<name>
<surname>Murphy</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Miller</surname>
<given-names>J. R.</given-names>
</name>
<name>
<surname>Chan</surname>
<given-names>A. P.</given-names>
</name>
</person-group> (<year>2012</year>). <article-title>Predicting the functional effect of amino acid substitutions and indels</article-title>. <source>PLoS One</source> <volume>7</volume> (<issue>10</issue>), <fpage>e46688</fpage>. <pub-id pub-id-type="doi">10.1371/journal.pone.0046688</pub-id> </citation>
</ref>
<ref id="B42">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Chun</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Fay</surname>
<given-names>J. C.</given-names>
</name>
</person-group> (<year>2009</year>). <article-title>Identification of deleterious mutations within three human genomes</article-title>. <source>Genome Res.</source> <volume>19</volume> (<issue>9</issue>), <fpage>1553</fpage>&#x2013;<lpage>1561</lpage>. <pub-id pub-id-type="doi">10.1101/gr.092619.109</pub-id> </citation>
</ref>
<ref id="B43">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Cingolani</surname>
<given-names>P.</given-names>
</name>
<name>
<surname>Platts</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Wang le</surname>
<given-names>L.</given-names>
</name>
<name>
<surname>Coon</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Nguyen</surname>
<given-names>T.</given-names>
</name>
<name>
<surname>Wang</surname>
<given-names>L.</given-names>
</name>
<etal/>
</person-group> (<year>2012</year>). <article-title>A program for annotating and predicting the effects of single nucleotide polymorphisms, SnpEff: SNPs in the genome of <italic>Drosophila melanogaster</italic> strain w1118; iso-2; iso-3</article-title>. <source>Fly. (Austin)</source> <volume>6</volume> (<issue>2</issue>), <fpage>80</fpage>&#x2013;<lpage>92</lpage>. <pub-id pub-id-type="doi">10.4161/fly.19695</pub-id> </citation>
</ref>
<ref id="B44">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Ciriello</surname>
<given-names>G.</given-names>
</name>
<name>
<surname>Gatza</surname>
<given-names>M. L.</given-names>
</name>
<name>
<surname>Beck</surname>
<given-names>A. H.</given-names>
</name>
<name>
<surname>Wilkerson</surname>
<given-names>M. D.</given-names>
</name>
<name>
<surname>Rhie</surname>
<given-names>S. K.</given-names>
</name>
<name>
<surname>Pastore</surname>
<given-names>A.</given-names>
</name>
<etal/>
</person-group> (<year>2015</year>). <article-title>Comprehensive molecular portraits of invasive lobular breast cancer</article-title>. <source>Cell.</source> <volume>163</volume> (<issue>2</issue>), <fpage>506</fpage>&#x2013;<lpage>519</lpage>. <pub-id pub-id-type="doi">10.1016/j.cell.2015.09.033</pub-id> </citation>
</ref>
<ref id="B45">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Consortium</surname>
<given-names>U. K.</given-names>
</name>
<name>
<surname>Walter</surname>
<given-names>K.</given-names>
</name>
<name>
<surname>Min</surname>
<given-names>J. L.</given-names>
</name>
<name>
<surname>Huang</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Crooks</surname>
<given-names>L.</given-names>
</name>
<name>
<surname>Memari</surname>
<given-names>Y.</given-names>
</name>
<etal/>
</person-group> (<year>2015</year>). <article-title>The UK10K project identifies rare variants in health and disease</article-title>. <source>Nature</source> <volume>526</volume> (<issue>7571</issue>), <fpage>82</fpage>&#x2013;<lpage>90</lpage>. <pub-id pub-id-type="doi">10.1038/nature14962</pub-id> </citation>
</ref>
<ref id="B46">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Cooper</surname>
<given-names>G. M.</given-names>
</name>
<name>
<surname>Shendure</surname>
<given-names>J.</given-names>
</name>
</person-group> (<year>2011</year>). <article-title>Needles in stacks of needles: Finding disease-causal variants in a wealth of genomic data</article-title>. <source>Nat. Rev. Genet.</source> <volume>12</volume> (<issue>9</issue>), <fpage>628</fpage>&#x2013;<lpage>640</lpage>. <pub-id pub-id-type="doi">10.1038/nrg3046</pub-id> </citation>
</ref>
<ref id="B47">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Cooper</surname>
<given-names>G. M.</given-names>
</name>
<name>
<surname>Stone</surname>
<given-names>E. A.</given-names>
</name>
<name>
<surname>Asimenos</surname>
<given-names>G.</given-names>
</name>
<name>
<surname>Program</surname>
<given-names>N. C. S.</given-names>
</name>
<name>
<surname>Green</surname>
<given-names>E. D.</given-names>
</name>
<name>
<surname>Batzoglou</surname>
<given-names>S.</given-names>
</name>
<etal/>
</person-group> (<year>2005</year>). <article-title>Distribution and intensity of constraint in mammalian genomic sequence</article-title>. <source>Genome Res.</source> <volume>15</volume> (<issue>7</issue>), <fpage>901</fpage>&#x2013;<lpage>913</lpage>. <pub-id pub-id-type="doi">10.1101/gr.3577405</pub-id> </citation>
</ref>
<ref id="B48">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Cornish</surname>
<given-names>A. J.</given-names>
</name>
<name>
<surname>David</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Sternberg</surname>
<given-names>M. J. E.</given-names>
</name>
</person-group> (<year>2018</year>). <article-title>PhenoRank: Reducing study bias in gene prioritization through simulation</article-title>. <source>Bioinformatics</source> <volume>34</volume> (<issue>12</issue>), <fpage>2087</fpage>&#x2013;<lpage>2095</lpage>. <pub-id pub-id-type="doi">10.1093/bioinformatics/bty028</pub-id> </citation>
</ref>
<ref id="B49">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Coutant</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Cabot</surname>
<given-names>C.</given-names>
</name>
<name>
<surname>Lefebvre</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Leonard</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Prieur-Gaston</surname>
<given-names>E.</given-names>
</name>
<name>
<surname>Campion</surname>
<given-names>D.</given-names>
</name>
<etal/>
</person-group> (<year>2012</year>). <article-title>Eva: Exome Variation Analyzer, an efficient and versatile tool for filtering strategies in medical genomics</article-title>. <source>BMC Bioinforma.</source> <volume>13</volume>, <fpage>S9</fpage>. <comment>Suppl 14</comment>. <pub-id pub-id-type="doi">10.1186/1471-2105-13-S14-S9</pub-id> </citation>
</ref>
<ref id="B50">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Cubuk</surname>
<given-names>C.</given-names>
</name>
<name>
<surname>Garrett</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Choi</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>King</surname>
<given-names>L.</given-names>
</name>
<name>
<surname>Loveday</surname>
<given-names>C.</given-names>
</name>
<name>
<surname>Torr</surname>
<given-names>B.</given-names>
</name>
<etal/>
</person-group> (<year>2021</year>). <article-title>Clinical likelihood ratios and balanced accuracy for 44 <italic>in silico</italic> tools against multiple large-scale functional assays of cancer susceptibility genes</article-title>. <source>Genet. Med.</source> <volume>23</volume> (<issue>11</issue>), <fpage>2096</fpage>&#x2013;<lpage>2104</lpage>. <pub-id pub-id-type="doi">10.1038/s41436-021-01265-z</pub-id> </citation>
</ref>
<ref id="B51">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Cunningham</surname>
<given-names>F.</given-names>
</name>
<name>
<surname>Moore</surname>
<given-names>B.</given-names>
</name>
<name>
<surname>Ruiz-Schultz</surname>
<given-names>N.</given-names>
</name>
<name>
<surname>Ritchie</surname>
<given-names>G. R.</given-names>
</name>
<name>
<surname>Eilbeck</surname>
<given-names>K.</given-names>
</name>
</person-group> (<year>2015</year>). <article-title>Improving the Sequence Ontology terminology for genomic variant annotation</article-title>. <source>J. Biomed. Semant.</source> <volume>6</volume>, <fpage>32</fpage>. <pub-id pub-id-type="doi">10.1186/s13326-015-0030-4</pub-id> </citation>
</ref>
<ref id="B52">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Curtis</surname>
<given-names>C.</given-names>
</name>
<name>
<surname>Shah</surname>
<given-names>S. P.</given-names>
</name>
<name>
<surname>Chin</surname>
<given-names>S. F.</given-names>
</name>
<name>
<surname>Turashvili</surname>
<given-names>G.</given-names>
</name>
<name>
<surname>Rueda</surname>
<given-names>O. M.</given-names>
</name>
<name>
<surname>Dunning</surname>
<given-names>M. J.</given-names>
</name>
<etal/>
</person-group> (<year>2012</year>). <article-title>The genomic and transcriptomic architecture of 2, 000 breast tumours reveals novel subgroups</article-title>. <source>Nature</source> <volume>486</volume> (<issue>7403</issue>), <fpage>346</fpage>&#x2013;<lpage>352</lpage>. <pub-id pub-id-type="doi">10.1038/nature10983</pub-id> </citation>
</ref>
<ref id="B53">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Danecek</surname>
<given-names>P.</given-names>
</name>
<name>
<surname>Auton</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Abecasis</surname>
<given-names>G.</given-names>
</name>
<name>
<surname>Albers</surname>
<given-names>C. A.</given-names>
</name>
<name>
<surname>Banks</surname>
<given-names>E.</given-names>
</name>
<name>
<surname>DePristo</surname>
<given-names>M. A.</given-names>
</name>
<etal/>
</person-group> (<year>2011</year>). <article-title>The variant call format and VCFtools</article-title>. <source>Bioinformatics</source> <volume>27</volume> (<issue>15</issue>), <fpage>2156</fpage>&#x2013;<lpage>2158</lpage>. <pub-id pub-id-type="doi">10.1093/bioinformatics/btr330</pub-id> </citation>
</ref>
<ref id="B54">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>David</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Razali</surname>
<given-names>R.</given-names>
</name>
<name>
<surname>Wass</surname>
<given-names>M. N.</given-names>
</name>
<name>
<surname>Sternberg</surname>
<given-names>M. J.</given-names>
</name>
</person-group> (<year>2012</year>). <article-title>Protein-protein interaction sites are hot spots for disease-associated nonsynonymous SNPs</article-title>. <source>Hum. Mutat.</source> <volume>33</volume> (<issue>2</issue>), <fpage>359</fpage>&#x2013;<lpage>363</lpage>. <pub-id pub-id-type="doi">10.1002/humu.21656</pub-id> </citation>
</ref>
<ref id="B55">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>David</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Sternberg</surname>
<given-names>M. J.</given-names>
</name>
</person-group> (<year>2015</year>). <article-title>The contribution of missense mutations in core and rim residues of protein-protein interfaces to human disease</article-title>. <source>J. Mol. Biol.</source> <volume>427</volume> (<issue>17</issue>), <fpage>2886</fpage>&#x2013;<lpage>2898</lpage>. <pub-id pub-id-type="doi">10.1016/j.jmb.2015.07.004</pub-id> </citation>
</ref>
<ref id="B56">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Davydov</surname>
<given-names>E. V.</given-names>
</name>
<name>
<surname>Goode</surname>
<given-names>D. L.</given-names>
</name>
<name>
<surname>Sirota</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Cooper</surname>
<given-names>G. M.</given-names>
</name>
<name>
<surname>Sidow</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Batzoglou</surname>
<given-names>S.</given-names>
</name>
</person-group> (<year>2010</year>). <article-title>Identifying a high fraction of the human genome to be under selective constraint using GERP&#x2b;&#x2b;</article-title>. <source>PLoS Comput. Biol.</source> <volume>6</volume> (<issue>12</issue>), <fpage>e1001025</fpage>. <pub-id pub-id-type="doi">10.1371/journal.pcbi.1001025</pub-id> </citation>
</ref>
<ref id="B57">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>de Beer</surname>
<given-names>T. A.</given-names>
</name>
<name>
<surname>Laskowski</surname>
<given-names>R. A.</given-names>
</name>
<name>
<surname>Parks</surname>
<given-names>S. L.</given-names>
</name>
<name>
<surname>Sipos</surname>
<given-names>B.</given-names>
</name>
<name>
<surname>Goldman</surname>
<given-names>N.</given-names>
</name>
<name>
<surname>Thornton</surname>
<given-names>J. M.</given-names>
</name>
</person-group> (<year>2013</year>). <article-title>Amino acid changes in disease-associated variants differ radically from variants observed in the 1000 genomes project dataset</article-title>. <source>PLoS Comput. Biol.</source> <volume>9</volume> (<issue>12</issue>), <fpage>e1003382</fpage>. <pub-id pub-id-type="doi">10.1371/journal.pcbi.1003382</pub-id> </citation>
</ref>
<ref id="B58">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Dehouck</surname>
<given-names>Y.</given-names>
</name>
<name>
<surname>Grosfils</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Folch</surname>
<given-names>B.</given-names>
</name>
<name>
<surname>Gilis</surname>
<given-names>D.</given-names>
</name>
<name>
<surname>Bogaerts</surname>
<given-names>P.</given-names>
</name>
<name>
<surname>Rooman</surname>
<given-names>M.</given-names>
</name>
</person-group> (<year>2009</year>). <article-title>Fast and accurate predictions of protein stability changes upon mutations using statistical potentials and neural networks: PoPMuSiC-2.0</article-title>. <source>Bioinformatics</source> <volume>25</volume> (<issue>19</issue>), <fpage>2537</fpage>&#x2013;<lpage>2543</lpage>. <pub-id pub-id-type="doi">10.1093/bioinformatics/btp445</pub-id> </citation>
</ref>
<ref id="B59">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Deng</surname>
<given-names>L.</given-names>
</name>
<name>
<surname>Zhang</surname>
<given-names>C.</given-names>
</name>
<name>
<surname>Yuan</surname>
<given-names>K.</given-names>
</name>
<name>
<surname>Gao</surname>
<given-names>Y.</given-names>
</name>
<name>
<surname>Pan</surname>
<given-names>Y.</given-names>
</name>
<name>
<surname>Ge</surname>
<given-names>X.</given-names>
</name>
<etal/>
</person-group> (<year>2019</year>). <article-title>Prioritizing natural-selection signals from the deep-sequencing genomic data suggests multi-variant adaptation in Tibetan highlanders</article-title>. <source>Natl. Sci. Rev.</source> <volume>6</volume> (<issue>6</issue>), <fpage>1201</fpage>&#x2013;<lpage>1222</lpage>. <pub-id pub-id-type="doi">10.1093/nsr/nwz108</pub-id> </citation>
</ref>
<ref id="B60">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Detlefsen</surname>
<given-names>N. S.</given-names>
</name>
<name>
<surname>Hauberg</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Boomsma</surname>
<given-names>W.</given-names>
</name>
</person-group> (<year>2022</year>). <article-title>Learning meaningful representations of protein sequences</article-title>. <source>Nat. Commun.</source> <volume>13</volume> (<issue>1</issue>), <fpage>1914</fpage>. <pub-id pub-id-type="doi">10.1038/s41467-022-29443-w</pub-id> </citation>
</ref>
<ref id="B61">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Diwan</surname>
<given-names>G. D.</given-names>
</name>
<name>
<surname>Gonzalez-Sanchez</surname>
<given-names>J. C.</given-names>
</name>
<name>
<surname>Apic</surname>
<given-names>G.</given-names>
</name>
<name>
<surname>Russell</surname>
<given-names>R. B.</given-names>
</name>
</person-group> (<year>2021</year>). <article-title>Next generation protein structure predictions and genetic variant interpretation</article-title>. <source>J. Mol. Biol.</source> <volume>433</volume> (<issue>20</issue>), <fpage>167180</fpage>. <pub-id pub-id-type="doi">10.1016/j.jmb.2021.167180</pub-id> </citation>
</ref>
<ref id="B62">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>do Nascimento</surname>
<given-names>P. M.</given-names>
</name>
<name>
<surname>Medeiros</surname>
<given-names>I. G.</given-names>
</name>
<name>
<surname>Falcao</surname>
<given-names>R. M.</given-names>
</name>
<name>
<surname>Stransky</surname>
<given-names>B.</given-names>
</name>
<name>
<surname>de Souza</surname>
<given-names>J. E. S.</given-names>
</name>
</person-group> (<year>2020</year>). <article-title>A decision tree to improve identification of pathogenic mutations in clinical practice</article-title>. <source>BMC Med. Inf. Decis. Mak.</source> <volume>20</volume> (<issue>1</issue>), <fpage>52</fpage>. <pub-id pub-id-type="doi">10.1186/s12911-020-1060-0</pub-id> </citation>
</ref>
<ref id="B63">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Dong</surname>
<given-names>C.</given-names>
</name>
<name>
<surname>Wei</surname>
<given-names>P.</given-names>
</name>
<name>
<surname>Jian</surname>
<given-names>X.</given-names>
</name>
<name>
<surname>Gibbs</surname>
<given-names>R.</given-names>
</name>
<name>
<surname>Boerwinkle</surname>
<given-names>E.</given-names>
</name>
<name>
<surname>Wang</surname>
<given-names>K.</given-names>
</name>
<etal/>
</person-group> (<year>2015</year>). <article-title>Comparison and integration of deleteriousness prediction methods for nonsynonymous SNVs in whole exome sequencing studies</article-title>. <source>Hum. Mol. Genet.</source> <volume>24</volume> (<issue>8</issue>), <fpage>2125</fpage>&#x2013;<lpage>2137</lpage>. <pub-id pub-id-type="doi">10.1093/hmg/ddu733</pub-id> </citation>
</ref>
<ref id="B64">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Dorfman</surname>
<given-names>R.</given-names>
</name>
<name>
<surname>Nalpathamkalam</surname>
<given-names>T.</given-names>
</name>
<name>
<surname>Taylor</surname>
<given-names>C.</given-names>
</name>
<name>
<surname>Gonska</surname>
<given-names>T.</given-names>
</name>
<name>
<surname>Keenan</surname>
<given-names>K.</given-names>
</name>
<name>
<surname>Yuan</surname>
<given-names>X. W.</given-names>
</name>
<etal/>
</person-group> (<year>2010</year>). <article-title>Do common <italic>in silico</italic> tools predict the clinical consequences of amino-acid substitutions in the CFTR gene?</article-title> <source>Clin. Genet.</source> <volume>77</volume> (<issue>5</issue>), <fpage>464</fpage>&#x2013;<lpage>473</lpage>. <pub-id pub-id-type="doi">10.1111/j.1399-0004.2009.01351.x</pub-id> </citation>
</ref>
<ref id="B65">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Draelos</surname>
<given-names>R. L.</given-names>
</name>
<name>
<surname>Ezekian</surname>
<given-names>J. E.</given-names>
</name>
<name>
<surname>Zhuang</surname>
<given-names>F.</given-names>
</name>
<name>
<surname>Moya-Mendez</surname>
<given-names>M. E.</given-names>
</name>
<name>
<surname>Zhang</surname>
<given-names>Z.</given-names>
</name>
<name>
<surname>Rosamilia</surname>
<given-names>M. B.</given-names>
</name>
<etal/>
</person-group> (<year>2022</year>). <article-title>Genesis: Gene-specific machine learning models for variants of uncertain significance found in catecholaminergic polymorphic ventricular Tachycardia and Long QT syndrome-associated genes</article-title>. <source>Circ. Arrhythm. Electrophysiol.</source> <volume>15</volume> (<issue>4</issue>), <fpage>e010326</fpage>. <pub-id pub-id-type="doi">10.1161/CIRCEP.121.010326</pub-id> </citation>
</ref>
<ref id="B66">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Eberle</surname>
<given-names>M. A.</given-names>
</name>
<name>
<surname>Fritzilas</surname>
<given-names>E.</given-names>
</name>
<name>
<surname>Krusche</surname>
<given-names>P.</given-names>
</name>
<name>
<surname>Kallberg</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Moore</surname>
<given-names>B. L.</given-names>
</name>
<name>
<surname>Bekritsky</surname>
<given-names>M. A.</given-names>
</name>
<etal/>
</person-group> (<year>2017</year>). <article-title>A reference data set of 5.4 million phased human variants validated by genetic inheritance from sequencing a three-generation 17-member pedigree</article-title>. <source>Genome Res.</source> <volume>27</volume> (<issue>1</issue>), <fpage>157</fpage>&#x2013;<lpage>164</lpage>. <pub-id pub-id-type="doi">10.1101/gr.210500.116</pub-id> </citation>
</ref>
<ref id="B67">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Edgar</surname>
<given-names>R. C.</given-names>
</name>
</person-group> (<year>2004</year>). <article-title>Muscle: Multiple sequence alignment with high accuracy and high throughput</article-title>. <source>Nucleic Acids Res.</source> <volume>32</volume> (<issue>5</issue>), <fpage>1792</fpage>&#x2013;<lpage>1797</lpage>. <pub-id pub-id-type="doi">10.1093/nar/gkh340</pub-id> </citation>
</ref>
<ref id="B68">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Eilbeck</surname>
<given-names>K.</given-names>
</name>
<name>
<surname>Lewis</surname>
<given-names>S. E.</given-names>
</name>
<name>
<surname>Mungall</surname>
<given-names>C. J.</given-names>
</name>
<name>
<surname>Yandell</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Stein</surname>
<given-names>L.</given-names>
</name>
<name>
<surname>Durbin</surname>
<given-names>R.</given-names>
</name>
<etal/>
</person-group> (<year>2005</year>). <article-title>The sequence ontology: A tool for the unification of genome annotations</article-title>. <source>Genome Biol.</source> <volume>6</volume> (<issue>5</issue>), <fpage>R44</fpage>. <pub-id pub-id-type="doi">10.1186/gb-2005-6-5-r44</pub-id> </citation>
</ref>
<ref id="B69">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Eilbeck</surname>
<given-names>K.</given-names>
</name>
<name>
<surname>Quinlan</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Yandell</surname>
<given-names>M.</given-names>
</name>
</person-group> (<year>2017</year>). <article-title>Settling the score: Variant prioritization and mendelian disease</article-title>. <source>Nat. Rev. Genet.</source> <volume>18</volume> (<issue>10</issue>), <fpage>599</fpage>&#x2013;<lpage>612</lpage>. <pub-id pub-id-type="doi">10.1038/nrg.2017.52</pub-id> </citation>
</ref>
<ref id="B70">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Fang</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Su</surname>
<given-names>Z.</given-names>
</name>
<name>
<surname>Abolhassani</surname>
<given-names>H.</given-names>
</name>
<name>
<surname>Itan</surname>
<given-names>Y.</given-names>
</name>
<name>
<surname>Jin</surname>
<given-names>X.</given-names>
</name>
<name>
<surname>Hammarstrom</surname>
<given-names>L.</given-names>
</name>
</person-group> (<year>2022</year>). <article-title>Vippid: A gene-specific single nucleotide variant pathogenicity prediction tool for primary immunodeficiency diseases</article-title>. <source>Brief. Bioinform.</source>, <fpage>bbac176</fpage>. <pub-id pub-id-type="doi">10.1093/bib/bbac176</pub-id> </citation>
</ref>
<ref id="B71">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Felipe-Medina</surname>
<given-names>N.</given-names>
</name>
<name>
<surname>Caburet</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Sanchez-Saez</surname>
<given-names>F.</given-names>
</name>
<name>
<surname>Condezo</surname>
<given-names>Y. B.</given-names>
</name>
<name>
<surname>de Rooij</surname>
<given-names>D. G.</given-names>
</name>
<name>
<surname>Gomez</surname>
<given-names>H. L.</given-names>
</name>
<etal/>
</person-group> (<year>2020</year>). <article-title>A missense in HSF2BP causing primary ovarian insufficiency affects meiotic recombination by its novel interactor C19ORF57/BRME1</article-title>. <source>Elife</source> <volume>9</volume>, <fpage>e56996</fpage>. <pub-id pub-id-type="doi">10.7554/eLife.56996</pub-id> </citation>
</ref>
<ref id="B72">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Feng</surname>
<given-names>B. J.</given-names>
</name>
</person-group> (<year>2017</year>). <article-title>Perch: A unified framework for disease gene prioritization</article-title>. <source>Hum. Mutat.</source> <volume>38</volume> (<issue>3</issue>), <fpage>243</fpage>&#x2013;<lpage>251</lpage>. <pub-id pub-id-type="doi">10.1002/humu.23158</pub-id> </citation>
</ref>
<ref id="B73">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Findlay</surname>
<given-names>G. M.</given-names>
</name>
<name>
<surname>Daza</surname>
<given-names>R. M.</given-names>
</name>
<name>
<surname>Martin</surname>
<given-names>B.</given-names>
</name>
<name>
<surname>Zhang</surname>
<given-names>M. D.</given-names>
</name>
<name>
<surname>Leith</surname>
<given-names>A. P.</given-names>
</name>
<name>
<surname>Gasperini</surname>
<given-names>M.</given-names>
</name>
<etal/>
</person-group> (<year>2018</year>). <article-title>Accurate classification of BRCA1 variants with saturation genome editing</article-title>. <source>Nature</source> <volume>562</volume> (<issue>7726</issue>), <fpage>217</fpage>&#x2013;<lpage>222</lpage>. <pub-id pub-id-type="doi">10.1038/s41586-018-0461-z</pub-id> </citation>
</ref>
<ref id="B74">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Fokkema</surname>
<given-names>I.</given-names>
</name>
<name>
<surname>Kroon</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Lopez Hernandez</surname>
<given-names>J. A.</given-names>
</name>
<name>
<surname>Asscheman</surname>
<given-names>D.</given-names>
</name>
<name>
<surname>Lugtenburg</surname>
<given-names>I.</given-names>
</name>
<name>
<surname>Hoogenboom</surname>
<given-names>J.</given-names>
</name>
<etal/>
</person-group> (<year>2021</year>). <article-title>The LOVD3 platform: Efficient genome-wide sharing of genetic variants</article-title>. <source>Eur. J. Hum. Genet.</source> <volume>29</volume> (<issue>12</issue>), <fpage>1796</fpage>&#x2013;<lpage>1803</lpage>. <pub-id pub-id-type="doi">10.1038/s41431-021-00959-x</pub-id> </citation>
</ref>
<ref id="B75">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Fokkema</surname>
<given-names>I.</given-names>
</name>
<name>
<surname>van der Velde</surname>
<given-names>K. J.</given-names>
</name>
<name>
<surname>Slofstra</surname>
<given-names>M. K.</given-names>
</name>
<name>
<surname>Ruivenkamp</surname>
<given-names>C. A. L.</given-names>
</name>
<name>
<surname>Vogel</surname>
<given-names>M. J.</given-names>
</name>
<name>
<surname>Pfundt</surname>
<given-names>R.</given-names>
</name>
<etal/>
</person-group> (<year>2019</year>). <article-title>Dutch genome diagnostic laboratories accelerated and improved variant interpretation and increased accuracy by sharing data</article-title>. <source>Hum. Mutat.</source> <volume>40</volume> (<issue>12</issue>), <fpage>2230</fpage>&#x2013;<lpage>2238</lpage>. <pub-id pub-id-type="doi">10.1002/humu.23896</pub-id> </citation>
</ref>
<ref id="B76">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Font-Porterias</surname>
<given-names>N.</given-names>
</name>
<name>
<surname>Caro-Consuegra</surname>
<given-names>R.</given-names>
</name>
<name>
<surname>Lucas-Sanchez</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Lopez</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Gimenez</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Carballo-Mesa</surname>
<given-names>A.</given-names>
</name>
<etal/>
</person-group> (<year>2021</year>). <article-title>The counteracting effects of demography on functional genomic variation: The roma paradigm</article-title>. <source>Mol. Biol. Evol.</source> <volume>38</volume> (<issue>7</issue>), <fpage>2804</fpage>&#x2013;<lpage>2817</lpage>. <pub-id pub-id-type="doi">10.1093/molbev/msab070</pub-id> </citation>
</ref>
<ref id="B77">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Fortuno</surname>
<given-names>C.</given-names>
</name>
<name>
<surname>James</surname>
<given-names>P. A.</given-names>
</name>
<name>
<surname>Young</surname>
<given-names>E. L.</given-names>
</name>
<name>
<surname>Feng</surname>
<given-names>B.</given-names>
</name>
<name>
<surname>Olivier</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Pesaran</surname>
<given-names>T.</given-names>
</name>
<etal/>
</person-group> (<year>2018</year>). <article-title>Improved, ACMG-compliant, <italic>in silico</italic> prediction of pathogenicity for missense substitutions encoded by TP53 variants</article-title>. <source>Hum. Mutat.</source> <volume>39</volume> (<issue>8</issue>), <fpage>1061</fpage>&#x2013;<lpage>1069</lpage>. <pub-id pub-id-type="doi">10.1002/humu.23553</pub-id> </citation>
</ref>
<ref id="B78">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Frazer</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Notin</surname>
<given-names>P.</given-names>
</name>
<name>
<surname>Dias</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Gomez</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Min</surname>
<given-names>J. K.</given-names>
</name>
<name>
<surname>Brock</surname>
<given-names>K.</given-names>
</name>
<etal/>
</person-group> (<year>2021</year>). <article-title>Disease variant prediction with deep generative models of evolutionary data</article-title>. <source>Nature</source> <volume>599</volume> (<issue>7883</issue>), <fpage>91</fpage>&#x2013;<lpage>95</lpage>. <pub-id pub-id-type="doi">10.1038/s41586-021-04043-8</pub-id> </citation>
</ref>
<ref id="B79">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Frederic</surname>
<given-names>M. Y.</given-names>
</name>
<name>
<surname>Lalande</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Boileau</surname>
<given-names>C.</given-names>
</name>
<name>
<surname>Hamroun</surname>
<given-names>D.</given-names>
</name>
<name>
<surname>Claustres</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Beroud</surname>
<given-names>C.</given-names>
</name>
<etal/>
</person-group> (<year>2009</year>). <article-title>UMD-Predictor, a new prediction tool for nucleotide substitution pathogenicity -- application to four genes: FBN1, FBN2, TGFBR1, and TGFBR2</article-title>. <source>Hum. Mutat.</source> <volume>30</volume> (<issue>6</issue>), <fpage>952</fpage>&#x2013;<lpage>959</lpage>. <pub-id pub-id-type="doi">10.1002/humu.20970</pub-id> </citation>
</ref>
<ref id="B80">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Fu</surname>
<given-names>W.</given-names>
</name>
<name>
<surname>O&#x27;Connor</surname>
<given-names>T. D.</given-names>
</name>
<name>
<surname>Jun</surname>
<given-names>G.</given-names>
</name>
<name>
<surname>Kang</surname>
<given-names>H. M.</given-names>
</name>
<name>
<surname>Abecasis</surname>
<given-names>G.</given-names>
</name>
<name>
<surname>Leal</surname>
<given-names>S. M.</given-names>
</name>
<etal/>
</person-group> (<year>2013</year>). <article-title>Analysis of 6, 515 exomes reveals the recent origin of most human protein-coding variants</article-title>. <source>Nature</source> <volume>493</volume> (<issue>7431</issue>), <fpage>216</fpage>&#x2013;<lpage>220</lpage>. <pub-id pub-id-type="doi">10.1038/nature11690</pub-id> </citation>
</ref>
<ref id="B81">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Ganesan</surname>
<given-names>K.</given-names>
</name>
<name>
<surname>Kulandaisamy</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Binny Priya</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Gromiha</surname>
<given-names>M. M.</given-names>
</name>
</person-group> (<year>2019</year>). <article-title>HuVarBase: A human variant database with comprehensive information at gene and protein levels</article-title>. <source>PLoS One</source> <volume>14</volume> (<issue>1</issue>), <fpage>e0210475</fpage>. <pub-id pub-id-type="doi">10.1371/journal.pone.0210475</pub-id> </citation>
</ref>
<ref id="B82">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Garber</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Guttman</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Clamp</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Zody</surname>
<given-names>M. C.</given-names>
</name>
<name>
<surname>Friedman</surname>
<given-names>N.</given-names>
</name>
<name>
<surname>Xie</surname>
<given-names>X.</given-names>
</name>
</person-group> (<year>2009</year>). <article-title>Identifying novel constrained elements by exploiting biased substitution patterns</article-title>. <source>Bioinformatics</source> <volume>25</volume> (<issue>12</issue>), <fpage>i54</fpage>&#x2013;<lpage>62</lpage>. <pub-id pub-id-type="doi">10.1093/bioinformatics/btp190</pub-id> </citation>
</ref>
<ref id="B83">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Gene Ontology</surname>
<given-names>C.</given-names>
</name>
</person-group> (<year>2021</year>). <article-title>The gene ontology resource: Enriching a GOld mine</article-title>. <source>Nucleic Acids Res.</source> <volume>49</volume> (<issue>D1</issue>), <fpage>D325</fpage>&#x2013;<lpage>D334</lpage>. <pub-id pub-id-type="doi">10.1093/nar/gkaa1113</pub-id> </citation>
</ref>
<ref id="B84">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Genomes Project</surname>
<given-names>C.</given-names>
</name>
<name>
<surname>Abecasis</surname>
<given-names>G. R.</given-names>
</name>
<name>
<surname>Auton</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Brooks</surname>
<given-names>L. D.</given-names>
</name>
<name>
<surname>DePristo</surname>
<given-names>M. A.</given-names>
</name>
<name>
<surname>Durbin</surname>
<given-names>R. M.</given-names>
</name>
<etal/>
</person-group> (<year>2012</year>). <article-title>An integrated map of genetic variation from 1, 092 human genomes</article-title>. <source>Nature</source> <volume>491</volume> (<issue>7422</issue>), <fpage>56</fpage>&#x2013;<lpage>65</lpage>. <pub-id pub-id-type="doi">10.1038/nature11632</pub-id> </citation>
</ref>
<ref id="B85">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Genomes Project</surname>
<given-names>C.</given-names>
</name>
<name>
<surname>Auton</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Brooks</surname>
<given-names>L. D.</given-names>
</name>
<name>
<surname>Durbin</surname>
<given-names>R. M.</given-names>
</name>
<name>
<surname>Garrison</surname>
<given-names>E. P.</given-names>
</name>
<name>
<surname>Kang</surname>
<given-names>H. M.</given-names>
</name>
<etal/>
</person-group> (<year>2015</year>). <article-title>A global reference for human genetic variation</article-title>. <source>Nature</source> <volume>526</volume> (<issue>7571</issue>), <fpage>68</fpage>&#x2013;<lpage>74</lpage>. <pub-id pub-id-type="doi">10.1038/nature15393</pub-id> </citation>
</ref>
<ref id="B86">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Giardine</surname>
<given-names>B.</given-names>
</name>
<name>
<surname>Borg</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Viennas</surname>
<given-names>E.</given-names>
</name>
<name>
<surname>Pavlidis</surname>
<given-names>C.</given-names>
</name>
<name>
<surname>Moradkhani</surname>
<given-names>K.</given-names>
</name>
<name>
<surname>Joly</surname>
<given-names>P.</given-names>
</name>
<etal/>
</person-group> (<year>2014</year>). <article-title>Updates of the HbVar database of human hemoglobin variants and thalassemia mutations</article-title>. <source>Nucleic Acids Res.</source> <volume>42</volume>, <fpage>D1063</fpage>&#x2013;<lpage>D1069</lpage>. <pub-id pub-id-type="doi">10.1093/nar/gkt911</pub-id> </citation>
</ref>
<ref id="B87">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Gonzalez-Perez</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Lopez-Bigas</surname>
<given-names>N.</given-names>
</name>
</person-group> (<year>2011</year>). <article-title>Improving the assessment of the outcome of nonsynonymous SNVs with a consensus deleteriousness score, Condel</article-title>. <source>Am. J. Hum. Genet.</source> <volume>88</volume> (<issue>4</issue>), <fpage>440</fpage>&#x2013;<lpage>449</lpage>. <pub-id pub-id-type="doi">10.1016/j.ajhg.2011.03.004</pub-id> </citation>
</ref>
<ref id="B88">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Greenblatt</surname>
<given-names>M. S.</given-names>
</name>
<name>
<surname>Brody</surname>
<given-names>L. C.</given-names>
</name>
<name>
<surname>Foulkes</surname>
<given-names>W. D.</given-names>
</name>
<name>
<surname>Genuardi</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Hofstra</surname>
<given-names>R. M.</given-names>
</name>
<name>
<surname>Olivier</surname>
<given-names>M.</given-names>
</name>
<etal/>
</person-group> (<year>2008</year>). <article-title>Locus-specific databases and recommendations to strengthen their contribution to the classification of variants in cancer susceptibility genes</article-title>. <source>Hum. Mutat.</source> <volume>29</volume> (<issue>11</issue>), <fpage>1273</fpage>&#x2013;<lpage>1281</lpage>. <pub-id pub-id-type="doi">10.1002/humu.20889</pub-id> </citation>
</ref>
<ref id="B89">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Gribskov</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>McLachlan</surname>
<given-names>A. D.</given-names>
</name>
<name>
<surname>Eisenberg</surname>
<given-names>D.</given-names>
</name>
</person-group> (<year>1987</year>). <article-title>Profile analysis: Detection of distantly related proteins</article-title>. <source>Proc. Natl. Acad. Sci. U. S. A.</source> <volume>84</volume> (<issue>13</issue>), <fpage>4355</fpage>&#x2013;<lpage>4358</lpage>. <pub-id pub-id-type="doi">10.1073/pnas.84.13.4355</pub-id> </citation>
</ref>
<ref id="B90">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Griffith</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Spies</surname>
<given-names>N. C.</given-names>
</name>
<name>
<surname>Krysiak</surname>
<given-names>K.</given-names>
</name>
<name>
<surname>McMichael</surname>
<given-names>J. F.</given-names>
</name>
<name>
<surname>Coffman</surname>
<given-names>A. C.</given-names>
</name>
<name>
<surname>Danos</surname>
<given-names>A. M.</given-names>
</name>
<etal/>
</person-group> (<year>2017</year>). <article-title>CIViC is a community knowledgebase for expert crowdsourcing the clinical interpretation of variants in cancer</article-title>. <source>Nat. Genet.</source> <volume>49</volume> (<issue>2</issue>), <fpage>170</fpage>&#x2013;<lpage>174</lpage>. <pub-id pub-id-type="doi">10.1038/ng.3774</pub-id> </citation>
</ref>
<ref id="B91">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Grimm</surname>
<given-names>D. G.</given-names>
</name>
<name>
<surname>Azencott</surname>
<given-names>C. A.</given-names>
</name>
<name>
<surname>Aicheler</surname>
<given-names>F.</given-names>
</name>
<name>
<surname>Gieraths</surname>
<given-names>U.</given-names>
</name>
<name>
<surname>MacArthur</surname>
<given-names>D. G.</given-names>
</name>
<name>
<surname>Samocha</surname>
<given-names>K. E.</given-names>
</name>
<etal/>
</person-group> (<year>2015</year>). <article-title>The evaluation of tools used to predict the impact of missense variants is hindered by two types of circularity</article-title>. <source>Hum. Mutat.</source> <volume>36</volume> (<issue>5</issue>), <fpage>513</fpage>&#x2013;<lpage>523</lpage>. <pub-id pub-id-type="doi">10.1002/humu.22768</pub-id> </citation>
</ref>
<ref id="B92">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Guerois</surname>
<given-names>R.</given-names>
</name>
<name>
<surname>Nielsen</surname>
<given-names>J. E.</given-names>
</name>
<name>
<surname>Serrano</surname>
<given-names>L.</given-names>
</name>
</person-group> (<year>2002</year>). <article-title>Predicting changes in the stability of proteins and protein complexes: A study of more than 1000 mutations</article-title>. <source>J. Mol. Biol.</source> <volume>320</volume> (<issue>2</issue>), <fpage>369</fpage>&#x2013;<lpage>387</lpage>. <pub-id pub-id-type="doi">10.1016/S0022-2836(02)00442-4</pub-id> </citation>
</ref>
<ref id="B93">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Haraksingh</surname>
<given-names>R. R.</given-names>
</name>
<name>
<surname>Snyder</surname>
<given-names>M. P.</given-names>
</name>
</person-group> (<year>2013</year>). <article-title>Impacts of variation in the human genome on gene regulation</article-title>. <source>J. Mol. Biol.</source> <volume>425</volume> (<issue>21</issue>), <fpage>3970</fpage>&#x2013;<lpage>3977</lpage>. <pub-id pub-id-type="doi">10.1016/j.jmb.2013.07.015</pub-id> </citation>
</ref>
<ref id="B94">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Hassan</surname>
<given-names>M. S.</given-names>
</name>
<name>
<surname>Shaalan</surname>
<given-names>A. A.</given-names>
</name>
<name>
<surname>Dessouky</surname>
<given-names>M. I.</given-names>
</name>
<name>
<surname>Abdelnaiem</surname>
<given-names>A. E.</given-names>
</name>
<name>
<surname>ElHefnawi</surname>
<given-names>M.</given-names>
</name>
</person-group> (<year>2019b</year>). <article-title>A review study: Computational techniques for expecting the impact of non-synonymous single nucleotide variants in human diseases</article-title>. <source>Gene</source> <volume>680</volume>, <fpage>20</fpage>&#x2013;<lpage>33</lpage>. <pub-id pub-id-type="doi">10.1016/j.gene.2018.09.028</pub-id> </citation>
</ref>
<ref id="B95">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Hassan</surname>
<given-names>M. S.</given-names>
</name>
<name>
<surname>Shaalan</surname>
<given-names>A. A.</given-names>
</name>
<name>
<surname>Dessouky</surname>
<given-names>M. I.</given-names>
</name>
<name>
<surname>Abdelnaiem</surname>
<given-names>A. E.</given-names>
</name>
<name>
<surname>ElHefnawi</surname>
<given-names>M.</given-names>
</name>
</person-group> (<year>2019a</year>). <article-title>Evaluation of computational techniques for predicting non-synonymous single nucleotide variants pathogenicity</article-title>. <source>Genomics</source> <volume>111</volume> (<issue>4</issue>), <fpage>869</fpage>&#x2013;<lpage>882</lpage>. <pub-id pub-id-type="doi">10.1016/j.ygeno.2018.05.013</pub-id> </citation>
</ref>
<ref id="B96">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Hebert</surname>
<given-names>L.</given-names>
</name>
<name>
<surname>Hillman</surname>
<given-names>P.</given-names>
</name>
<name>
<surname>Baker</surname>
<given-names>C.</given-names>
</name>
<name>
<surname>Brown</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Ashley-Koch</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Hixson</surname>
<given-names>J. E.</given-names>
</name>
<etal/>
</person-group> (<year>2020</year>). <article-title>Burden of rare deleterious variants in WNT signaling genes among 511 myelomeningocele patients</article-title>. <source>PLoS One</source> <volume>15</volume> (<issue>9</issue>), <fpage>e0239083</fpage>. <pub-id pub-id-type="doi">10.1371/journal.pone.0239083</pub-id> </citation>
</ref>
<ref id="B97">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Hecht</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Bromberg</surname>
<given-names>Y.</given-names>
</name>
<name>
<surname>Rost</surname>
<given-names>B.</given-names>
</name>
</person-group> (<year>2015</year>). <article-title>Better prediction of functional effects for sequence variants</article-title>. <source>BMC Genomics</source> <volume>16</volume> (<issue>8</issue>), <fpage>S1</fpage>. <pub-id pub-id-type="doi">10.1186/1471-2164-16-S8-S1</pub-id> </citation>
</ref>
<ref id="B98">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Hoie</surname>
<given-names>M. H.</given-names>
</name>
<name>
<surname>Cagiada</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Beck Frederiksen</surname>
<given-names>A. H.</given-names>
</name>
<name>
<surname>Stein</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Lindorff-Larsen</surname>
<given-names>K.</given-names>
</name>
</person-group> (<year>2022</year>). <article-title>Predicting and interpreting large-scale mutagenesis data using analyses of protein stability and conservation</article-title>. <source>Cell. Rep.</source> <volume>38</volume> (<issue>2</issue>), <fpage>110207</fpage>. <pub-id pub-id-type="doi">10.1016/j.celrep.2021.110207</pub-id> </citation>
</ref>
<ref id="B99">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Holtgrewe</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Stolpe</surname>
<given-names>O.</given-names>
</name>
<name>
<surname>Nieminen</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Mundlos</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Knaus</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Kornak</surname>
<given-names>U.</given-names>
</name>
<etal/>
</person-group> (<year>2020</year>). <article-title>VarFish: Comprehensive DNA variant analysis for diagnostics and research</article-title>. <source>Nucleic Acids Res.</source> <volume>48</volume> (<issue>W1</issue>), <fpage>W162-W169</fpage>&#x2013;<lpage>W169</lpage>. <pub-id pub-id-type="doi">10.1093/nar/gkaa241</pub-id> </citation>
</ref>
<ref id="B100">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Hopf</surname>
<given-names>T. A.</given-names>
</name>
<name>
<surname>Ingraham</surname>
<given-names>J. B.</given-names>
</name>
<name>
<surname>Poelwijk</surname>
<given-names>F. J.</given-names>
</name>
<name>
<surname>Scharfe</surname>
<given-names>C. P.</given-names>
</name>
<name>
<surname>Springer</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Sander</surname>
<given-names>C.</given-names>
</name>
<etal/>
</person-group> (<year>2017</year>). <article-title>Mutation effects predicted from sequence co-variation</article-title>. <source>Nat. Biotechnol.</source> <volume>35</volume> (<issue>2</issue>), <fpage>128</fpage>&#x2013;<lpage>135</lpage>. <pub-id pub-id-type="doi">10.1038/nbt.3769</pub-id> </citation>
</ref>
<ref id="B101">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Hu</surname>
<given-names>T.</given-names>
</name>
<name>
<surname>Chitnis</surname>
<given-names>N.</given-names>
</name>
<name>
<surname>Monos</surname>
<given-names>D.</given-names>
</name>
<name>
<surname>Dinh</surname>
<given-names>A.</given-names>
</name>
</person-group> (<year>2021</year>). <article-title>Next-generation sequencing technologies: An overview</article-title>. <source>Hum. Immunol.</source> <volume>82</volume> (<issue>11</issue>), <fpage>801</fpage>&#x2013;<lpage>811</lpage>. <pub-id pub-id-type="doi">10.1016/j.humimm.2021.02.012</pub-id> </citation>
</ref>
<ref id="B102">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Ingram</surname>
<given-names>V. M.</given-names>
</name>
</person-group> (<year>1957</year>). <article-title>Gene mutations in human haemoglobin: The chemical difference between normal and sickle cell haemoglobin</article-title>. <source>Nature</source> <volume>180</volume> (<issue>4581</issue>), <fpage>326</fpage>&#x2013;<lpage>328</lpage>. <pub-id pub-id-type="doi">10.1038/180326a0</pub-id> </citation>
</ref>
<ref id="B103">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>International HapMap</surname>
<given-names>C.</given-names>
</name>
</person-group> (<year>2003</year>). <article-title>The international HapMap project</article-title>. <source>Nature</source> <volume>426</volume> (<issue>6968</issue>), <fpage>789</fpage>&#x2013;<lpage>796</lpage>. <pub-id pub-id-type="doi">10.1038/nature02168</pub-id> </citation>
</ref>
<ref id="B104">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Ioannidis</surname>
<given-names>N. M.</given-names>
</name>
<name>
<surname>Rothstein</surname>
<given-names>J. H.</given-names>
</name>
<name>
<surname>Pejaver</surname>
<given-names>V.</given-names>
</name>
<name>
<surname>Middha</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>McDonnell</surname>
<given-names>S. K.</given-names>
</name>
<name>
<surname>Baheti</surname>
<given-names>S.</given-names>
</name>
<etal/>
</person-group> (<year>2016</year>). <article-title>Revel: An ensemble method for predicting the pathogenicity of rare missense variants</article-title>. <source>Am. J. Hum. Genet.</source> <volume>99</volume> (<issue>4</issue>), <fpage>877</fpage>&#x2013;<lpage>885</lpage>. <pub-id pub-id-type="doi">10.1016/j.ajhg.2016.08.016</pub-id> </citation>
</ref>
<ref id="B105">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Ip</surname>
<given-names>E.</given-names>
</name>
<name>
<surname>Chapman</surname>
<given-names>G.</given-names>
</name>
<name>
<surname>Winlaw</surname>
<given-names>D.</given-names>
</name>
<name>
<surname>Dunwoodie</surname>
<given-names>S. L.</given-names>
</name>
<name>
<surname>Giannoulatou</surname>
<given-names>E.</given-names>
</name>
</person-group> (<year>2019</year>). <article-title>Vpot: A customizable variant prioritization ordering tool for annotated variants</article-title>. <source>Genomics Proteomics Bioinforma.</source> <volume>17</volume> (<issue>5</issue>), <fpage>540</fpage>&#x2013;<lpage>545</lpage>. <pub-id pub-id-type="doi">10.1016/j.gpb.2019.11.001</pub-id> </citation>
</ref>
<ref id="B106">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Jagadeesh</surname>
<given-names>K. A.</given-names>
</name>
<name>
<surname>Birgmeier</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Guturu</surname>
<given-names>H.</given-names>
</name>
<name>
<surname>Deisseroth</surname>
<given-names>C. A.</given-names>
</name>
<name>
<surname>Wenger</surname>
<given-names>A. M.</given-names>
</name>
<name>
<surname>Bernstein</surname>
<given-names>J. A.</given-names>
</name>
<etal/>
</person-group> (<year>2019</year>). <article-title>Phrank measures phenotype sets similarity to greatly improve Mendelian diagnostic disease prioritization</article-title>. <source>Genet. Med.</source> <volume>21</volume> (<issue>2</issue>), <fpage>464</fpage>&#x2013;<lpage>470</lpage>. <pub-id pub-id-type="doi">10.1038/s41436-018-0072-y</pub-id> </citation>
</ref>
<ref id="B107">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Jagadeesh</surname>
<given-names>K. A.</given-names>
</name>
<name>
<surname>Wenger</surname>
<given-names>A. M.</given-names>
</name>
<name>
<surname>Berger</surname>
<given-names>M. J.</given-names>
</name>
<name>
<surname>Guturu</surname>
<given-names>H.</given-names>
</name>
<name>
<surname>Stenson</surname>
<given-names>P. D.</given-names>
</name>
<name>
<surname>Cooper</surname>
<given-names>D. N.</given-names>
</name>
<etal/>
</person-group> (<year>2016</year>). <article-title>M-CAP eliminates a majority of variants of uncertain significance in clinical exomes at high sensitivity</article-title>. <source>Nat. Genet.</source> <volume>48</volume> (<issue>12</issue>), <fpage>1581</fpage>&#x2013;<lpage>1586</lpage>. <pub-id pub-id-type="doi">10.1038/ng.3703</pub-id> </citation>
</ref>
<ref id="B108">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Javed</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Agrawal</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Ng</surname>
<given-names>P. C.</given-names>
</name>
</person-group> (<year>2014</year>). <article-title>Phen-gen: Combining phenotype and genotype to analyze rare disorders</article-title>. <source>Nat. Methods</source> <volume>11</volume> (<issue>9</issue>), <fpage>935</fpage>&#x2013;<lpage>937</lpage>. <pub-id pub-id-type="doi">10.1038/nmeth.3046</pub-id> </citation>
</ref>
<ref id="B109">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Ji</surname>
<given-names>X.</given-names>
</name>
<name>
<surname>Kember</surname>
<given-names>R. L.</given-names>
</name>
<name>
<surname>Brown</surname>
<given-names>C. D.</given-names>
</name>
<name>
<surname>Bucan</surname>
<given-names>M.</given-names>
</name>
</person-group> (<year>2016</year>). <article-title>Increased burden of deleterious variants in essential genes in autism spectrum disorder</article-title>. <source>Proc. Natl. Acad. Sci. U. S. A.</source> <volume>113</volume> (<issue>52</issue>), <fpage>15054</fpage>&#x2013;<lpage>15059</lpage>. <pub-id pub-id-type="doi">10.1073/pnas.1613195113</pub-id> </citation>
</ref>
<ref id="B110">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Johnston</surname>
<given-names>J. J.</given-names>
</name>
<name>
<surname>Biesecker</surname>
<given-names>L. G.</given-names>
</name>
</person-group> (<year>2013</year>). <article-title>Databases of genomic variation and phenotypes: Existing resources and future needs</article-title>. <source>Hum. Mol. Genet.</source> <volume>22</volume> (<issue>R1</issue>), <fpage>R27</fpage>&#x2013;<lpage>R31</lpage>. <pub-id pub-id-type="doi">10.1093/hmg/ddt384</pub-id> </citation>
</ref>
<ref id="B111">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Jones</surname>
<given-names>C. M.</given-names>
</name>
<name>
<surname>Charache</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Hathaway</surname>
<given-names>P. J.</given-names>
</name>
</person-group> (<year>1979</year>). <article-title>The effect of hemoglobin F-Chesapeake (alpha 2 92 Arg. leads to Leu gamma 2) on fetal oxygen affinity and erythropoiesis</article-title>. <source>Pediatr. Res.</source> <volume>13</volume> (<issue>7</issue>), <fpage>851</fpage>&#x2013;<lpage>853</lpage>. <pub-id pub-id-type="doi">10.1203/00006450-197907000-00011</pub-id> </citation>
</ref>
<ref id="B112">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Jordan</surname>
<given-names>D. M.</given-names>
</name>
<name>
<surname>Kiezun</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Baxter</surname>
<given-names>S. M.</given-names>
</name>
<name>
<surname>Agarwala</surname>
<given-names>V.</given-names>
</name>
<name>
<surname>Green</surname>
<given-names>R. C.</given-names>
</name>
<name>
<surname>Murray</surname>
<given-names>M. F.</given-names>
</name>
<etal/>
</person-group> (<year>2011</year>). <article-title>Development and validation of a computational method for assessment of missense variants in hypertrophic cardiomyopathy</article-title>. <source>Am. J. Hum. Genet.</source> <volume>88</volume> (<issue>2</issue>), <fpage>183</fpage>&#x2013;<lpage>192</lpage>. <pub-id pub-id-type="doi">10.1016/j.ajhg.2011.01.011</pub-id> </citation>
</ref>
<ref id="B113">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Jumper</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Evans</surname>
<given-names>R.</given-names>
</name>
<name>
<surname>Pritzel</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Green</surname>
<given-names>T.</given-names>
</name>
<name>
<surname>Figurnov</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Ronneberger</surname>
<given-names>O.</given-names>
</name>
<etal/>
</person-group> (<year>2021</year>). <article-title>Highly accurate protein structure prediction with AlphaFold</article-title>. <source>Nature</source> <volume>596</volume> (<issue>7873</issue>), <fpage>583</fpage>&#x2013;<lpage>589</lpage>. <pub-id pub-id-type="doi">10.1038/s41586-021-03819-2</pub-id> </citation>
</ref>
<ref id="B114">
<citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname>Ka</surname>
<given-names>W.</given-names>
</name>
</person-group> (<year>2021</year>). <source>DNA sequencing costs: Data from the NHGRI genome sequencing Program (GSP)</source>. <comment>[Online]. Available: <ext-link ext-link-type="uri" xlink:href="www.genome.gov/sequencingcostsdata">www.genome.gov/sequencingcostsdata</ext-link> (Accessed June 1, 2022 2022)</comment>. </citation>
</ref>
<ref id="B115">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Kaminker</surname>
<given-names>J. S.</given-names>
</name>
<name>
<surname>Zhang</surname>
<given-names>Y.</given-names>
</name>
<name>
<surname>Watanabe</surname>
<given-names>C.</given-names>
</name>
<name>
<surname>Zhang</surname>
<given-names>Z.</given-names>
</name>
</person-group> (<year>2007</year>). <article-title>CanPredict: A computational tool for predicting cancer-associated missense mutations</article-title>. <source>Nucleic Acids Res.</source> <volume>35</volume>, <fpage>W595</fpage>&#x2013;<lpage>W598</lpage>. <pub-id pub-id-type="doi">10.1093/nar/gkm405</pub-id> </citation>
</ref>
<ref id="B116">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Kanzi</surname>
<given-names>A. M.</given-names>
</name>
<name>
<surname>San</surname>
<given-names>J. E.</given-names>
</name>
<name>
<surname>Chimukangara</surname>
<given-names>B.</given-names>
</name>
<name>
<surname>Wilkinson</surname>
<given-names>E.</given-names>
</name>
<name>
<surname>Fish</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Ramsuran</surname>
<given-names>V.</given-names>
</name>
<etal/>
</person-group> (<year>2020</year>). <article-title>Next generation sequencing and bioinformatics analysis of family genetic inheritance</article-title>. <source>Front. Genet.</source> <volume>11</volume>, <fpage>544162</fpage>. <pub-id pub-id-type="doi">10.3389/fgene.2020.544162</pub-id> </citation>
</ref>
<ref id="B117">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Karczewski</surname>
<given-names>K. J.</given-names>
</name>
<name>
<surname>Francioli</surname>
<given-names>L. C.</given-names>
</name>
<name>
<surname>Tiao</surname>
<given-names>G.</given-names>
</name>
<name>
<surname>Cummings</surname>
<given-names>B. B.</given-names>
</name>
<name>
<surname>Alf&#xf6;ldi</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Wang</surname>
<given-names>Q.</given-names>
</name>
<etal/>
</person-group> (<year>2020</year>). <article-title>The mutational constraint spectrum quantified from variation in 141, 456 humans</article-title>. <source>Nature</source> <volume>581</volume> (<issue>7809</issue>), <fpage>434</fpage>&#x2013;<lpage>443</lpage>. <pub-id pub-id-type="doi">10.1038/s41586-020-2308-7</pub-id> </citation>
</ref>
<ref id="B118">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Karczewski</surname>
<given-names>K. J.</given-names>
</name>
<name>
<surname>Francioli</surname>
<given-names>L. C.</given-names>
</name>
<name>
<surname>Tiao</surname>
<given-names>G.</given-names>
</name>
<name>
<surname>Cummings</surname>
<given-names>B. B.</given-names>
</name>
<name>
<surname>Alfoldi</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Wang</surname>
<given-names>Q.</given-names>
</name>
<etal/>
</person-group> (<year>2020</year>). <article-title>The mutational constraint spectrum quantified from variation in 141, 456 humans</article-title>. <source>Nature</source> <volume>581</volume> (<issue>7809</issue>), <fpage>434</fpage>&#x2013;<lpage>443</lpage>. <pub-id pub-id-type="doi">10.1038/s41586-020-2308-7</pub-id> </citation>
</ref>
<ref id="B119">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Katsonis</surname>
<given-names>P.</given-names>
</name>
<name>
<surname>Lichtarge</surname>
<given-names>O.</given-names>
</name>
</person-group> (<year>2019</year>). <article-title>CAGI5: Objective performance assessments of predictions based on the Evolutionary Action equation</article-title>. <source>Hum. Mutat.</source> <volume>40</volume> (<issue>9</issue>), <fpage>1436</fpage>&#x2013;<lpage>1454</lpage>. <pub-id pub-id-type="doi">10.1002/humu.23873</pub-id> </citation>
</ref>
<ref id="B120">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Katsonis</surname>
<given-names>P.</given-names>
</name>
<name>
<surname>Wilhelm</surname>
<given-names>K.</given-names>
</name>
<name>
<surname>Williams</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Lichtarge</surname>
<given-names>O.</given-names>
</name>
</person-group> (<year>2022</year>). <article-title>Genome interpretation using <italic>in silico</italic> predictors of variant impact</article-title>. <source>Hum. Genet.</source> <pub-id pub-id-type="doi">10.1007/s00439-022-02457-6</pub-id> </citation>
</ref>
<ref id="B121">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Keerthikumar</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Raju</surname>
<given-names>R.</given-names>
</name>
<name>
<surname>Kandasamy</surname>
<given-names>K.</given-names>
</name>
<name>
<surname>Hijikata</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Ramabadran</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Balakrishnan</surname>
<given-names>L.</given-names>
</name>
<etal/>
</person-group> (<year>2009</year>). <article-title>Rapid: Resource of asian primary immunodeficiency diseases</article-title>. <source>Nucleic Acids Res.</source> <volume>37</volume>, <fpage>D863</fpage>&#x2013;<lpage>D867</lpage>. <pub-id pub-id-type="doi">10.1093/nar/gkn682</pub-id> </citation>
</ref>
<ref id="B122">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Kim</surname>
<given-names>Y.</given-names>
</name>
<name>
<surname>Kang</surname>
<given-names>C.</given-names>
</name>
<name>
<surname>Min</surname>
<given-names>B.</given-names>
</name>
<name>
<surname>Yi</surname>
<given-names>G. S.</given-names>
</name>
</person-group> (<year>2015</year>). <article-title>Detection and analysis of disease-associated single nucleotide polymorphism influencing post-translational modification</article-title>. <source>BMC Med. Genomics</source> <volume>8</volume> (<issue>2</issue>), <fpage>S7</fpage>. <pub-id pub-id-type="doi">10.1186/1755-8794-8-S2-S7</pub-id> </citation>
</ref>
<ref id="B123">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Kimura</surname>
<given-names>M.</given-names>
</name>
</person-group> (<year>1979</year>). <article-title>The neutral theory of molecular evolution</article-title>. <source>Sci. Am.</source> <volume>241</volume> (<issue>5</issue>), <fpage>98</fpage>&#x2013;<lpage>100</lpage>. <pub-id pub-id-type="doi">10.1038/scientificamerican1179-98</pub-id> </citation>
</ref>
<ref id="B124">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Kircher</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Witten</surname>
<given-names>D. M.</given-names>
</name>
<name>
<surname>Jain</surname>
<given-names>P.</given-names>
</name>
<name>
<surname>O&#x27;Roak</surname>
<given-names>B. J.</given-names>
</name>
<name>
<surname>Cooper</surname>
<given-names>G. M.</given-names>
</name>
<name>
<surname>Shendure</surname>
<given-names>J.</given-names>
</name>
</person-group> (<year>2014</year>). <article-title>A general framework for estimating the relative pathogenicity of human genetic variants</article-title>. <source>Nat. Genet.</source> <volume>46</volume> (<issue>3</issue>), <fpage>310</fpage>&#x2013;<lpage>315</lpage>. <pub-id pub-id-type="doi">10.1038/ng.2892</pub-id> </citation>
</ref>
<ref id="B125">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Koboldt</surname>
<given-names>D. C.</given-names>
</name>
</person-group> (<year>2020</year>). <article-title>Best practices for variant calling in clinical sequencing</article-title>. <source>Genome Med.</source> <volume>12</volume> (<issue>1</issue>), <fpage>91</fpage>. <pub-id pub-id-type="doi">10.1186/s13073-020-00791-w</pub-id> </citation>
</ref>
<ref id="B126">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Kohler</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Gargano</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Matentzoglu</surname>
<given-names>N.</given-names>
</name>
<name>
<surname>Carmody</surname>
<given-names>L. C.</given-names>
</name>
<name>
<surname>Lewis-Smith</surname>
<given-names>D.</given-names>
</name>
<name>
<surname>Vasilevsky</surname>
<given-names>N. A.</given-names>
</name>
<etal/>
</person-group> (<year>2021</year>). <article-title>The human phenotype ontology in 2021</article-title>. <source>Nucleic Acids Res.</source> <volume>49</volume> (<issue>D1</issue>), <fpage>D1207</fpage>&#x2013;<lpage>D1217</lpage>. <pub-id pub-id-type="doi">10.1093/nar/gkaa1043</pub-id> </citation>
</ref>
<ref id="B127">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Kohler</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Schulz</surname>
<given-names>M. H.</given-names>
</name>
<name>
<surname>Krawitz</surname>
<given-names>P.</given-names>
</name>
<name>
<surname>Bauer</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Dolken</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Ott</surname>
<given-names>C. E.</given-names>
</name>
<etal/>
</person-group> (<year>2009</year>). <article-title>Clinical diagnostics in human genetics with semantic similarity searches in ontologies</article-title>. <source>Am. J. Hum. Genet.</source> <volume>85</volume> (<issue>4</issue>), <fpage>457</fpage>&#x2013;<lpage>464</lpage>. <pub-id pub-id-type="doi">10.1016/j.ajhg.2009.09.003</pub-id> </citation>
</ref>
<ref id="B128">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Krogh</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Brown</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Mian</surname>
<given-names>I. S.</given-names>
</name>
<name>
<surname>Sjolander</surname>
<given-names>K.</given-names>
</name>
<name>
<surname>Haussler</surname>
<given-names>D.</given-names>
</name>
</person-group> (<year>1994</year>). <article-title>Hidden Markov models in computational biology. Applications to protein modeling</article-title>. <source>J. Mol. Biol.</source> <volume>235</volume> (<issue>5</issue>), <fpage>1501</fpage>&#x2013;<lpage>1531</lpage>. <pub-id pub-id-type="doi">10.1006/jmbi.1994.1104</pub-id> </citation>
</ref>
<ref id="B129">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Kulshreshtha</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Chaudhary</surname>
<given-names>V.</given-names>
</name>
<name>
<surname>Goswami</surname>
<given-names>G. K.</given-names>
</name>
<name>
<surname>Mathur</surname>
<given-names>N.</given-names>
</name>
</person-group> (<year>2016</year>). <article-title>Computational approaches for predicting mutant protein stability</article-title>. <source>J. Comput. Aided. Mol. Des.</source> <volume>30</volume> (<issue>5</issue>), <fpage>401</fpage>&#x2013;<lpage>412</lpage>. <pub-id pub-id-type="doi">10.1007/s10822-016-9914-3</pub-id> </citation>
</ref>
<ref id="B130">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Lai</surname>
<given-names>C.</given-names>
</name>
<name>
<surname>Zimmer</surname>
<given-names>A. D.</given-names>
</name>
<name>
<surname>O&#x27;Connor</surname>
<given-names>R.</given-names>
</name>
<name>
<surname>Kim</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Chan</surname>
<given-names>R.</given-names>
</name>
<name>
<surname>van den Akker</surname>
<given-names>J.</given-names>
</name>
<etal/>
</person-group> (<year>2020</year>). <article-title>Leap: Using machine learning to support variant classification in a clinical setting</article-title>. <source>Hum. Mutat.</source> <volume>41</volume> (<issue>6</issue>), <fpage>1079</fpage>&#x2013;<lpage>1090</lpage>. <pub-id pub-id-type="doi">10.1002/humu.24011</pub-id> </citation>
</ref>
<ref id="B131">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Laimer</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Hofer</surname>
<given-names>H.</given-names>
</name>
<name>
<surname>Fritz</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Wegenkittl</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Lackner</surname>
<given-names>P.</given-names>
</name>
</person-group> (<year>2015</year>). <article-title>MAESTRO--multi agent stability prediction upon point mutations</article-title>. <source>BMC Bioinforma.</source> <volume>16</volume>, <fpage>116</fpage>. <pub-id pub-id-type="doi">10.1186/s12859-015-0548-6</pub-id> </citation>
</ref>
<ref id="B132">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Landrum</surname>
<given-names>M. J.</given-names>
</name>
<name>
<surname>Chitipiralla</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Brown</surname>
<given-names>G. R.</given-names>
</name>
<name>
<surname>Chen</surname>
<given-names>C.</given-names>
</name>
<name>
<surname>Gu</surname>
<given-names>B.</given-names>
</name>
<name>
<surname>Hart</surname>
<given-names>J.</given-names>
</name>
<etal/>
</person-group> (<year>2020</year>). <article-title>ClinVar: Improvements to accessing data</article-title>. <source>Nucleic Acids Res.</source> <volume>48</volume> (<issue>D1</issue>), <fpage>D835-D844</fpage>&#x2013;<lpage>D844</lpage>. <pub-id pub-id-type="doi">10.1093/nar/gkz972</pub-id> </citation>
</ref>
<ref id="B133">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Lanktree</surname>
<given-names>M. B.</given-names>
</name>
<name>
<surname>Haghighi</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Guiard</surname>
<given-names>E.</given-names>
</name>
<name>
<surname>Iliuta</surname>
<given-names>I. A.</given-names>
</name>
<name>
<surname>Song</surname>
<given-names>X.</given-names>
</name>
<name>
<surname>Harris</surname>
<given-names>P. C.</given-names>
</name>
<etal/>
</person-group> (<year>2018</year>). <article-title>Prevalence estimates of polycystic kidney and liver disease by population sequencing</article-title>. <source>J. Am. Soc. Nephrol.</source> <volume>29</volume> (<issue>10</issue>), <fpage>2593</fpage>&#x2013;<lpage>2600</lpage>. <pub-id pub-id-type="doi">10.1681/ASN.2018050493</pub-id> </citation>
</ref>
<ref id="B134">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Lek</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Karczewski</surname>
<given-names>K. J.</given-names>
</name>
<name>
<surname>Minikel</surname>
<given-names>E. V.</given-names>
</name>
<name>
<surname>Samocha</surname>
<given-names>K. E.</given-names>
</name>
<name>
<surname>Banks</surname>
<given-names>E.</given-names>
</name>
<name>
<surname>Fennell</surname>
<given-names>T.</given-names>
</name>
<etal/>
</person-group> (<year>2016</year>). <article-title>Analysis of protein-coding genetic variation in 60, 706 humans</article-title>. <source>Nature</source> <volume>536</volume> (<issue>7616</issue>), <fpage>285</fpage>&#x2013;<lpage>291</lpage>. <pub-id pub-id-type="doi">10.1038/nature19057</pub-id> </citation>
</ref>
<ref id="B135">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Leu</surname>
<given-names>C.</given-names>
</name>
<name>
<surname>Balestrini</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Maher</surname>
<given-names>B.</given-names>
</name>
<name>
<surname>Hernandez-Hernandez</surname>
<given-names>L.</given-names>
</name>
<name>
<surname>Gormley</surname>
<given-names>P.</given-names>
</name>
<name>
<surname>Hamalainen</surname>
<given-names>E.</given-names>
</name>
<etal/>
</person-group> (<year>2015</year>). <article-title>Genome-wide polygenic burden of rare deleterious variants in sudden unexpected death in epilepsy</article-title>. <source>EBioMedicine</source> <volume>2</volume> (<issue>9</issue>), <fpage>1063</fpage>&#x2013;<lpage>1070</lpage>. <pub-id pub-id-type="doi">10.1016/j.ebiom.2015.07.005</pub-id> </citation>
</ref>
<ref id="B136">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Li</surname>
<given-names>B.</given-names>
</name>
<name>
<surname>Krishnan</surname>
<given-names>V. G.</given-names>
</name>
<name>
<surname>Mort</surname>
<given-names>M. E.</given-names>
</name>
<name>
<surname>Xin</surname>
<given-names>F.</given-names>
</name>
<name>
<surname>Kamati</surname>
<given-names>K. K.</given-names>
</name>
<name>
<surname>Cooper</surname>
<given-names>D. N.</given-names>
</name>
<etal/>
</person-group> (<year>2009</year>). <article-title>Automated inference of molecular mechanisms of disease from amino acid substitutions</article-title>. <source>Bioinformatics</source> <volume>25</volume> (<issue>21</issue>), <fpage>2744</fpage>&#x2013;<lpage>2750</lpage>. <pub-id pub-id-type="doi">10.1093/bioinformatics/btp528</pub-id> </citation>
</ref>
<ref id="B137">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Li</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Shi</surname>
<given-names>L.</given-names>
</name>
<name>
<surname>Zhang</surname>
<given-names>K.</given-names>
</name>
<name>
<surname>Zhang</surname>
<given-names>Y.</given-names>
</name>
<name>
<surname>Hu</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Zhao</surname>
<given-names>T.</given-names>
</name>
<etal/>
</person-group> (<year>2018</year>). <article-title>VarCards: An integrated genetic and clinical database for coding variants in the human genome</article-title>. <source>Nucleic Acids Res.</source> <volume>46</volume> (<issue>D1</issue>), <fpage>D1039-D1048</fpage>&#x2013;<lpage>D1048</lpage>. <pub-id pub-id-type="doi">10.1093/nar/gkx1039</pub-id> </citation>
</ref>
<ref id="B138">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Li</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Zhao</surname>
<given-names>T.</given-names>
</name>
<name>
<surname>Zhang</surname>
<given-names>Y.</given-names>
</name>
<name>
<surname>Zhang</surname>
<given-names>K.</given-names>
</name>
<name>
<surname>Shi</surname>
<given-names>L.</given-names>
</name>
<name>
<surname>Chen</surname>
<given-names>Y.</given-names>
</name>
<etal/>
</person-group> (<year>2018</year>). <article-title>Performance evaluation of pathogenicity-computation methods for missense variants</article-title>. <source>Nucleic Acids Res.</source> <volume>46</volume> (<issue>15</issue>), <fpage>7793</fpage>&#x2013;<lpage>7804</lpage>. <pub-id pub-id-type="doi">10.1093/nar/gky678</pub-id> </citation>
</ref>
<ref id="B139">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Li</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Li</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Li</surname>
<given-names>M. J.</given-names>
</name>
<name>
<surname>Pan</surname>
<given-names>Z.</given-names>
</name>
<name>
<surname>Hsu</surname>
<given-names>J. S.</given-names>
</name>
<name>
<surname>Liu</surname>
<given-names>D. J.</given-names>
</name>
<etal/>
</person-group> (<year>2017</year>). <article-title>Robust and rapid algorithms facilitate large-scale whole genome sequencing downstream analysis in an integrative framework</article-title>. <source>Nucleic Acids Res.</source> <volume>45</volume> (<issue>9</issue>), <fpage>e75</fpage>. <pub-id pub-id-type="doi">10.1093/nar/gkx019</pub-id> </citation>
</ref>
<ref id="B140">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Li</surname>
<given-names>M. X.</given-names>
</name>
<name>
<surname>Gui</surname>
<given-names>H. S.</given-names>
</name>
<name>
<surname>Kwan</surname>
<given-names>J. S.</given-names>
</name>
<name>
<surname>Bao</surname>
<given-names>S. Y.</given-names>
</name>
<name>
<surname>Sham</surname>
<given-names>P. C.</given-names>
</name>
</person-group> (<year>2012</year>). <article-title>A comprehensive framework for prioritizing variants in exome sequencing studies of Mendelian diseases</article-title>. <source>Nucleic Acids Res.</source> <volume>40</volume> (<issue>7</issue>), <fpage>e53</fpage>. <pub-id pub-id-type="doi">10.1093/nar/gkr1257</pub-id> </citation>
</ref>
<ref id="B141">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Li</surname>
<given-names>Q.</given-names>
</name>
<name>
<surname>Ren</surname>
<given-names>Z.</given-names>
</name>
<name>
<surname>Cao</surname>
<given-names>K.</given-names>
</name>
<name>
<surname>Li</surname>
<given-names>M. M.</given-names>
</name>
<name>
<surname>Wang</surname>
<given-names>K.</given-names>
</name>
<name>
<surname>Zhou</surname>
<given-names>Y.</given-names>
</name>
</person-group> (<year>2022</year>). <article-title>CancerVar: An artificial intelligence-empowered platform for clinical interpretation of somatic mutations in cancer</article-title>. <source>Sci. Adv.</source> <volume>8</volume> (<issue>18</issue>), <fpage>eabj1624</fpage>. <pub-id pub-id-type="doi">10.1126/sciadv.abj1624</pub-id> </citation>
</ref>
<ref id="B142">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Li</surname>
<given-names>Q.</given-names>
</name>
<name>
<surname>Wang</surname>
<given-names>K.</given-names>
</name>
</person-group> (<year>2017</year>). <article-title>InterVar: Clinical interpretation of genetic variants by the 2015 ACMG-AMP guidelines</article-title>. <source>Am. J. Hum. Genet.</source> <volume>100</volume> (<issue>2</issue>), <fpage>267</fpage>&#x2013;<lpage>280</lpage>. <pub-id pub-id-type="doi">10.1016/j.ajhg.2017.01.004</pub-id> </citation>
</ref>
<ref id="B143">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Li</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>van der Velde</surname>
<given-names>K. J.</given-names>
</name>
<name>
<surname>de Ridder</surname>
<given-names>D.</given-names>
</name>
<name>
<surname>van Dijk</surname>
<given-names>A. D. J.</given-names>
</name>
<name>
<surname>Soudis</surname>
<given-names>D.</given-names>
</name>
<name>
<surname>Zwerwer</surname>
<given-names>L. R.</given-names>
</name>
<etal/>
</person-group> (<year>2020</year>). <article-title>Capice: A computational method for consequence-agnostic pathogenicity interpretation of clinical exome variations</article-title>. <source>Genome Med.</source> <volume>12</volume> (<issue>1</issue>), <fpage>75</fpage>. <pub-id pub-id-type="doi">10.1186/s13073-020-00775-w</pub-id> </citation>
</ref>
<ref id="B144">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Li</surname>
<given-names>Y.</given-names>
</name>
<name>
<surname>Chen</surname>
<given-names>C. Y.</given-names>
</name>
<name>
<surname>Kaye</surname>
<given-names>A. M.</given-names>
</name>
<name>
<surname>Wasserman</surname>
<given-names>W. W.</given-names>
</name>
</person-group> (<year>2015</year>). <article-title>The identification of cis-regulatory elements: A review from a machine learning perspective</article-title>. <source>Biosystems.</source> <volume>138</volume>, <fpage>6</fpage>&#x2013;<lpage>17</lpage>. <pub-id pub-id-type="doi">10.1016/j.biosystems.2015.10.002</pub-id> </citation>
</ref>
<ref id="B145">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Liu</surname>
<given-names>C.</given-names>
</name>
<name>
<surname>Peres Kury</surname>
<given-names>F. S.</given-names>
</name>
<name>
<surname>Li</surname>
<given-names>Z.</given-names>
</name>
<name>
<surname>Ta</surname>
<given-names>C.</given-names>
</name>
<name>
<surname>Wang</surname>
<given-names>K.</given-names>
</name>
<name>
<surname>Weng</surname>
<given-names>C.</given-names>
</name>
</person-group> (<year>2019</year>). <article-title>Doc2Hpo: A web application for efficient and accurate HPO concept curation</article-title>. <source>Nucleic Acids Res.</source> <volume>47</volume> (<issue>W1</issue>), <fpage>W566-W570</fpage>&#x2013;<lpage>W570</lpage>. <pub-id pub-id-type="doi">10.1093/nar/gkz386</pub-id> </citation>
</ref>
<ref id="B146">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Liu</surname>
<given-names>Y.</given-names>
</name>
<name>
<surname>Sun</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Zhao</surname>
<given-names>M.</given-names>
</name>
</person-group> (<year>2017</year>). <article-title>ONGene: A literature-based database for human oncogenes</article-title>. <source>J. Genet. Genomics</source> <volume>44</volume> (<issue>2</issue>), <fpage>119</fpage>&#x2013;<lpage>121</lpage>. <pub-id pub-id-type="doi">10.1016/j.jgg.2016.12.004</pub-id> </citation>
</ref>
<ref id="B147">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Lo</surname>
<given-names>Y. H.</given-names>
</name>
<name>
<surname>Cheng</surname>
<given-names>H. C.</given-names>
</name>
<name>
<surname>Hsiung</surname>
<given-names>C. N.</given-names>
</name>
<name>
<surname>Yang</surname>
<given-names>S. L.</given-names>
</name>
<name>
<surname>Wang</surname>
<given-names>H. Y.</given-names>
</name>
<name>
<surname>Peng</surname>
<given-names>C. W.</given-names>
</name>
<etal/>
</person-group> (<year>2021</year>). <article-title>Detecting genetic ancestry and adaptation in the Taiwanese han people</article-title>. <source>Mol. Biol. Evol.</source> <volume>38</volume> (<issue>10</issue>), <fpage>4149</fpage>&#x2013;<lpage>4165</lpage>. <pub-id pub-id-type="doi">10.1093/molbev/msaa276</pub-id> </citation>
</ref>
<ref id="B148">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Ma</surname>
<given-names>L.</given-names>
</name>
<name>
<surname>Roman-Campos</surname>
<given-names>D.</given-names>
</name>
<name>
<surname>Austin</surname>
<given-names>E. D.</given-names>
</name>
<name>
<surname>Eyries</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Sampson</surname>
<given-names>K. S.</given-names>
</name>
<name>
<surname>Soubrier</surname>
<given-names>F.</given-names>
</name>
<etal/>
</person-group> (<year>2013</year>). <article-title>A novel channelopathy in pulmonary arterial hypertension</article-title>. <source>N. Engl. J. Med.</source> <volume>369</volume> (<issue>4</issue>), <fpage>351</fpage>&#x2013;<lpage>361</lpage>. <pub-id pub-id-type="doi">10.1056/NEJMoa1211097</pub-id> </citation>
</ref>
<ref id="B149">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>MacArthur</surname>
<given-names>D. G.</given-names>
</name>
<name>
<surname>Balasubramanian</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Frankish</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Huang</surname>
<given-names>N.</given-names>
</name>
<name>
<surname>Morris</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Walter</surname>
<given-names>K.</given-names>
</name>
<etal/>
</person-group> (<year>2012</year>). <article-title>A systematic survey of loss-of-function variants in human protein-coding genes</article-title>. <source>Science</source> <volume>335</volume> (<issue>6070</issue>), <fpage>823</fpage>&#x2013;<lpage>828</lpage>. <pub-id pub-id-type="doi">10.1126/science.1215040</pub-id> </citation>
</ref>
<ref id="B150">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Maffucci</surname>
<given-names>P.</given-names>
</name>
<name>
<surname>Bigio</surname>
<given-names>B.</given-names>
</name>
<name>
<surname>Rapaport</surname>
<given-names>F.</given-names>
</name>
<name>
<surname>Cobat</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Borghesi</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Lopez</surname>
<given-names>M.</given-names>
</name>
<etal/>
</person-group> (<year>2019</year>). <article-title>Blacklisting variants common in private cohorts but not in public databases optimizes human exome analysis</article-title>. <source>Proc. Natl. Acad. Sci. U. S. A.</source> <volume>116</volume> (<issue>3</issue>), <fpage>950</fpage>&#x2013;<lpage>959</lpage>. <pub-id pub-id-type="doi">10.1073/pnas.1808403116</pub-id> </citation>
</ref>
<ref id="B151">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Mahmood</surname>
<given-names>K.</given-names>
</name>
<name>
<surname>Jung</surname>
<given-names>C. H.</given-names>
</name>
<name>
<surname>Philip</surname>
<given-names>G.</given-names>
</name>
<name>
<surname>Georgeson</surname>
<given-names>P.</given-names>
</name>
<name>
<surname>Chung</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Pope</surname>
<given-names>B. J.</given-names>
</name>
<etal/>
</person-group> (<year>2017</year>). <article-title>Variant effect prediction tools assessed using independent, functional assay-based datasets: Implications for discovery and diagnostics</article-title>. <source>Hum. Genomics</source> <volume>11</volume> (<issue>1</issue>), <fpage>10</fpage>. <pub-id pub-id-type="doi">10.1186/s40246-017-0104-8</pub-id> </citation>
</ref>
<ref id="B152">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Martinez</surname>
<given-names>G.</given-names>
</name>
<name>
<surname>Lima</surname>
<given-names>F.</given-names>
</name>
<name>
<surname>Colombo</surname>
<given-names>B.</given-names>
</name>
</person-group> (<year>1977</year>). <article-title>Haemoglobin J Guantanamo (alpha 2 beta 2 128 (H6) Ala replaced by Asp). A new fast unstable haemoglobin found in a Cuban family</article-title>. <source>Biochim. Biophys. Acta</source> <volume>491</volume> (<issue>1</issue>), <fpage>1</fpage>&#x2013;<lpage>6</lpage>. <pub-id pub-id-type="doi">10.1016/0005-2795(77)90034-4</pub-id> </citation>
</ref>
<ref id="B153">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>McLaren</surname>
<given-names>W.</given-names>
</name>
<name>
<surname>Gil</surname>
<given-names>L.</given-names>
</name>
<name>
<surname>Hunt</surname>
<given-names>S. E.</given-names>
</name>
<name>
<surname>Riat</surname>
<given-names>H. S.</given-names>
</name>
<name>
<surname>Ritchie</surname>
<given-names>G. R.</given-names>
</name>
<name>
<surname>Thormann</surname>
<given-names>A.</given-names>
</name>
<etal/>
</person-group> (<year>2016</year>). <article-title>The ensembl variant effect predictor</article-title>. <source>Genome Biol.</source> <volume>17</volume> (<issue>1</issue>), <fpage>122</fpage>. <pub-id pub-id-type="doi">10.1186/s13059-016-0974-4</pub-id> </citation>
</ref>
<ref id="B154">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>McLaren</surname>
<given-names>W.</given-names>
</name>
<name>
<surname>Pritchard</surname>
<given-names>B.</given-names>
</name>
<name>
<surname>Rios</surname>
<given-names>D.</given-names>
</name>
<name>
<surname>Chen</surname>
<given-names>Y.</given-names>
</name>
<name>
<surname>Flicek</surname>
<given-names>P.</given-names>
</name>
<name>
<surname>Cunningham</surname>
<given-names>F.</given-names>
</name>
</person-group> (<year>2010</year>). <article-title>Deriving the consequences of genomic variants with the ensembl API and SNP effect predictor</article-title>. <source>Bioinformatics</source> <volume>26</volume> (<issue>16</issue>), <fpage>2069</fpage>&#x2013;<lpage>2070</lpage>. <pub-id pub-id-type="doi">10.1093/bioinformatics/btq330</pub-id> </citation>
</ref>
<ref id="B155">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Melendez-Aranda</surname>
<given-names>L.</given-names>
</name>
<name>
<surname>Jaloma-Cruz</surname>
<given-names>A. R.</given-names>
</name>
<name>
<surname>Pastor</surname>
<given-names>N.</given-names>
</name>
<name>
<surname>Romero-Prado</surname>
<given-names>M. M. J.</given-names>
</name>
</person-group> (<year>2019</year>). <article-title>
<italic>In silico</italic> analysis of missense mutations in exons 1-5 of the F9 gene that cause hemophilia B</article-title>. <source>BMC Bioinforma.</source> <volume>20</volume> (<issue>1</issue>), <fpage>363</fpage>. <pub-id pub-id-type="doi">10.1186/s12859-019-2919-x</pub-id> </citation>
</ref>
<ref id="B156">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Mi</surname>
<given-names>H.</given-names>
</name>
<name>
<surname>Ebert</surname>
<given-names>D.</given-names>
</name>
<name>
<surname>Muruganujan</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Mills</surname>
<given-names>C.</given-names>
</name>
<name>
<surname>Albou</surname>
<given-names>L. P.</given-names>
</name>
<name>
<surname>Mushayamaha</surname>
<given-names>T.</given-names>
</name>
<etal/>
</person-group> (<year>2021</year>). <article-title>PANTHER version 16: A revised family classification, tree-based classification tool, enhancer regions and extensive API</article-title>. <source>Nucleic Acids Res.</source> <volume>49</volume> (<issue>D1</issue>), <fpage>D394</fpage>&#x2013;<lpage>D403</lpage>. <pub-id pub-id-type="doi">10.1093/nar/gkaa1106</pub-id> </citation>
</ref>
<ref id="B157">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Miller</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Wang</surname>
<given-names>Y.</given-names>
</name>
<name>
<surname>Bromberg</surname>
<given-names>Y.</given-names>
</name>
</person-group> (<year>2019</year>). <article-title>What went wrong with variant effect predictor performance for the PCM1 challenge</article-title>. <source>Hum. Mutat.</source> <volume>40</volume> (<issue>9</issue>), <fpage>1486</fpage>&#x2013;<lpage>1494</lpage>. <pub-id pub-id-type="doi">10.1002/humu.23832</pub-id> </citation>
</ref>
<ref id="B158">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Moo-Penn</surname>
<given-names>W. F.</given-names>
</name>
<name>
<surname>Jue</surname>
<given-names>D. L.</given-names>
</name>
<name>
<surname>Johnson</surname>
<given-names>M. H.</given-names>
</name>
<name>
<surname>Olsen</surname>
<given-names>K. W.</given-names>
</name>
<name>
<surname>Shih</surname>
<given-names>D.</given-names>
</name>
<name>
<surname>Jones</surname>
<given-names>R. T.</given-names>
</name>
<etal/>
</person-group> (<year>1988</year>). <article-title>Hemoglobin brockton [beta 138 (H16) ala----pro]: An unstable variant near the C-terminus of the beta-subunits with normal oxygen-binding properties</article-title>. <source>Biochemistry</source> <volume>27</volume> (<issue>20</issue>), <fpage>7614</fpage>&#x2013;<lpage>7619</lpage>. <pub-id pub-id-type="doi">10.1021/bi00420a007</pub-id> </citation>
</ref>
<ref id="B159">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Morningstar-Kywi</surname>
<given-names>N.</given-names>
</name>
<name>
<surname>Haworth</surname>
<given-names>I. S.</given-names>
</name>
<name>
<surname>Mosley</surname>
<given-names>S. A.</given-names>
</name>
</person-group> (<year>2021</year>). <article-title>Ligand-specific pharmacogenetic effects of nonsynonymous mutations</article-title>. <source>Pharmacogenet. Genomics</source> <volume>31</volume> (<issue>4</issue>), <fpage>75</fpage>&#x2013;<lpage>82</lpage>. <pub-id pub-id-type="doi">10.1097/FPC.0000000000000424</pub-id> </citation>
</ref>
<ref id="B160">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Muller</surname>
<given-names>H.</given-names>
</name>
<name>
<surname>Jimenez-Heredia</surname>
<given-names>R.</given-names>
</name>
<name>
<surname>Krolo</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Hirschmugl</surname>
<given-names>T.</given-names>
</name>
<name>
<surname>Dmytrus</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Boztug</surname>
<given-names>K.</given-names>
</name>
<etal/>
</person-group> (<year>2017</year>). <article-title>VCF.Filter: Interactive prioritization of disease-linked genetic variants from sequencing data</article-title>. <source>Nucleic Acids Res.</source> <volume>45</volume> (<issue>W1</issue>), <fpage>W567-W572</fpage>&#x2013;<lpage>W572</lpage>. <pub-id pub-id-type="doi">10.1093/nar/gkx425</pub-id> </citation>
</ref>
<ref id="B161">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Ng</surname>
<given-names>P. C.</given-names>
</name>
<name>
<surname>Henikoff</surname>
<given-names>S.</given-names>
</name>
</person-group> (<year>2001</year>). <article-title>Predicting deleterious amino acid substitutions</article-title>. <source>Genome Res.</source> <volume>11</volume> (<issue>5</issue>), <fpage>863</fpage>&#x2013;<lpage>874</lpage>. <pub-id pub-id-type="doi">10.1101/gr.176601</pub-id> </citation>
</ref>
<ref id="B162">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Ng</surname>
<given-names>P. C.</given-names>
</name>
<name>
<surname>Henikoff</surname>
<given-names>S.</given-names>
</name>
</person-group> (<year>2003</year>). <article-title>Sift: Predicting amino acid changes that affect protein function</article-title>. <source>Nucleic Acids Res.</source> <volume>31</volume> (<issue>13</issue>), <fpage>3812</fpage>&#x2013;<lpage>3814</lpage>. <pub-id pub-id-type="doi">10.1093/nar/gkg509</pub-id> </citation>
</ref>
<ref id="B163">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Nikam</surname>
<given-names>R.</given-names>
</name>
<name>
<surname>Kulandaisamy</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Harini</surname>
<given-names>K.</given-names>
</name>
<name>
<surname>Sharma</surname>
<given-names>D.</given-names>
</name>
<name>
<surname>Gromiha</surname>
<given-names>M. M.</given-names>
</name>
</person-group> (<year>2021</year>). <article-title>ProThermDB: Thermodynamic database for proteins and mutants revisited after 15 years</article-title>. <source>Nucleic Acids Res.</source> <volume>49</volume> (<issue>D1</issue>), <fpage>D420</fpage>&#x2013;<lpage>D424</lpage>. <pub-id pub-id-type="doi">10.1093/nar/gkaa1035</pub-id> </citation>
</ref>
<ref id="B164">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Niroula</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Urolagin</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Vihinen</surname>
<given-names>M.</given-names>
</name>
</person-group> (<year>2015</year>). <article-title>PON-P2: Prediction method for fast and reliable identification of harmful variants</article-title>. <source>PLoS One</source> <volume>10</volume> (<issue>2</issue>), <fpage>e0117380</fpage>. <pub-id pub-id-type="doi">10.1371/journal.pone.0117380</pub-id> </citation>
</ref>
<ref id="B165">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Niroula</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Vihinen</surname>
<given-names>M.</given-names>
</name>
</person-group> (<year>2015</year>). <article-title>Classification of amino acid substitutions in Mismatch Repair proteins using PON-MMR2</article-title>. <source>Hum. Mutat.</source> <volume>36</volume> (<issue>12</issue>), <fpage>1128</fpage>&#x2013;<lpage>1134</lpage>. <pub-id pub-id-type="doi">10.1002/humu.22900</pub-id> </citation>
</ref>
<ref id="B166">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Niroula</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Vihinen</surname>
<given-names>M.</given-names>
</name>
</person-group> (<year>2019</year>). <article-title>How good are pathogenicity predictors in detecting benign variants?</article-title> <source>PLoS Comput. Biol.</source> <volume>15</volume> (<issue>2</issue>), <fpage>e1006481</fpage>. <pub-id pub-id-type="doi">10.1371/journal.pcbi.1006481</pub-id> </citation>
</ref>
<ref id="B167">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Nurk</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Koren</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Rhie</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Rautiainen</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Bzikadze</surname>
<given-names>A. V.</given-names>
</name>
<name>
<surname>Mikheenko</surname>
<given-names>A.</given-names>
</name>
<etal/>
</person-group> (<year>2022</year>). <article-title>The complete sequence of a human genome</article-title>. <source>Science</source> <volume>376</volume> (<issue>6588</issue>), <fpage>44</fpage>&#x2013;<lpage>53</lpage>. <pub-id pub-id-type="doi">10.1126/science.abj6987</pub-id> </citation>
</ref>
<ref id="B168">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Ohno</surname>
<given-names>K.</given-names>
</name>
<name>
<surname>Takeda</surname>
<given-names>J. I.</given-names>
</name>
<name>
<surname>Masuda</surname>
<given-names>A.</given-names>
</name>
</person-group> (<year>2018</year>). <article-title>Rules and tools to predict the splicing effects of exonic and intronic mutations</article-title>. <source>WIREs RNA</source> <volume>9</volume> (<issue>1</issue>). <pub-id pub-id-type="doi">10.1002/wrna.1451</pub-id> </citation>
</ref>
<ref id="B169">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Okido</surname>
<given-names>T.</given-names>
</name>
<name>
<surname>Kodama</surname>
<given-names>Y.</given-names>
</name>
<name>
<surname>Mashima</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Kosuge</surname>
<given-names>T.</given-names>
</name>
<name>
<surname>Fujisawa</surname>
<given-names>T.</given-names>
</name>
<name>
<surname>Ogasawara</surname>
<given-names>O.</given-names>
</name>
</person-group> (<year>2022</year>). <article-title>DNA Data Bank of Japan (DDBJ) update report 2021</article-title>. <source>Nucleic Acids Res.</source> <volume>50</volume> (<issue>D1</issue>), <fpage>D102</fpage>&#x2013;<lpage>D105</lpage>. <pub-id pub-id-type="doi">10.1093/nar/gkab995</pub-id> </citation>
</ref>
<ref id="B170">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Orgogozo</surname>
<given-names>V.</given-names>
</name>
<name>
<surname>Morizot</surname>
<given-names>B.</given-names>
</name>
<name>
<surname>Martin</surname>
<given-names>A.</given-names>
</name>
</person-group> (<year>2015</year>). <article-title>The differential view of genotype-phenotype relationships</article-title>. <source>Front. Genet.</source> <volume>6</volume>, <fpage>179</fpage>. <pub-id pub-id-type="doi">10.3389/fgene.2015.00179</pub-id> </citation>
</ref>
<ref id="B171">
<citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname>Pak</surname>
<given-names>M. A.</given-names>
</name>
<name>
<surname>Markhieva</surname>
<given-names>K. A.</given-names>
</name>
<name>
<surname>Novikova</surname>
<given-names>M. S.</given-names>
</name>
<name>
<surname>Petrov</surname>
<given-names>D. S.</given-names>
</name>
<name>
<surname>Vorobyev</surname>
<given-names>I. S.</given-names>
</name>
<name>
<surname>Maksimova</surname>
<given-names>E. S.</given-names>
</name>
<etal/>
</person-group> (<year>2021</year>). <source>Using AlphaFold to predict the impact of single mutations on protein stability and function</source>. <publisher-name>bioRxiv [Preprint]</publisher-name>. </citation>
</ref>
<ref id="B172">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Palmer</surname>
<given-names>D. S.</given-names>
</name>
<name>
<surname>Howrigan</surname>
<given-names>D. P.</given-names>
</name>
<name>
<surname>Chapman</surname>
<given-names>S. B.</given-names>
</name>
<name>
<surname>Adolfsson</surname>
<given-names>R.</given-names>
</name>
<name>
<surname>Bass</surname>
<given-names>N.</given-names>
</name>
<name>
<surname>Blackwood</surname>
<given-names>D.</given-names>
</name>
<etal/>
</person-group> (<year>2022</year>). <article-title>Exome sequencing in bipolar disorder identifies AKAP11 as a risk gene shared with schizophrenia</article-title>. <source>Nat. Genet.</source> <volume>54</volume> (<issue>5</issue>), <fpage>541</fpage>&#x2013;<lpage>547</lpage>. <pub-id pub-id-type="doi">10.1038/s41588-022-01034-x</pub-id> </citation>
</ref>
<ref id="B173">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Pandurangan</surname>
<given-names>A. P.</given-names>
</name>
<name>
<surname>Ochoa-Montano</surname>
<given-names>B.</given-names>
</name>
<name>
<surname>Ascher</surname>
<given-names>D. B.</given-names>
</name>
<name>
<surname>Blundell</surname>
<given-names>T. L.</given-names>
</name>
</person-group> (<year>2017</year>). <article-title>Sdm: A server for predicting effects of mutations on protein stability</article-title>. <source>Nucleic Acids Res.</source> <volume>45</volume> (<issue>W1</issue>), <fpage>W229-W235</fpage>&#x2013;<lpage>W235</lpage>. <pub-id pub-id-type="doi">10.1093/nar/gkx439</pub-id> </citation>
</ref>
<ref id="B174">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Pejaver</surname>
<given-names>V.</given-names>
</name>
<name>
<surname>Urresti</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Lugo-Martinez</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Pagel</surname>
<given-names>K. A.</given-names>
</name>
<name>
<surname>Lin</surname>
<given-names>G. N.</given-names>
</name>
<name>
<surname>Nam</surname>
<given-names>H. J.</given-names>
</name>
<etal/>
</person-group> (<year>2020</year>). <article-title>Inferring the molecular and phenotypic impact of amino acid variants with MutPred2</article-title>. <source>Nat. Commun.</source> <volume>11</volume> (<issue>1</issue>), <fpage>5918</fpage>. <pub-id pub-id-type="doi">10.1038/s41467-020-19669-x</pub-id> </citation>
</ref>
<ref id="B175">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Peng</surname>
<given-names>G.</given-names>
</name>
<name>
<surname>Shen</surname>
<given-names>P.</given-names>
</name>
<name>
<surname>Gandotra</surname>
<given-names>N.</given-names>
</name>
<name>
<surname>Le</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Fung</surname>
<given-names>E.</given-names>
</name>
<name>
<surname>Jelliffe-Pawlowski</surname>
<given-names>L.</given-names>
</name>
<etal/>
</person-group> (<year>2019</year>). <article-title>Combining newborn metabolic and DNA analysis for second-tier testing of methylmalonic acidemia</article-title>. <source>Genet. Med.</source> <volume>21</volume> (<issue>4</issue>), <fpage>896</fpage>&#x2013;<lpage>903</lpage>. <pub-id pub-id-type="doi">10.1038/s41436-018-0272-5</pub-id> </citation>
</ref>
<ref id="B176">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Pereira</surname>
<given-names>B.</given-names>
</name>
<name>
<surname>Chin</surname>
<given-names>S. F.</given-names>
</name>
<name>
<surname>Rueda</surname>
<given-names>O. M.</given-names>
</name>
<name>
<surname>Vollan</surname>
<given-names>H. K.</given-names>
</name>
<name>
<surname>Provenzano</surname>
<given-names>E.</given-names>
</name>
<name>
<surname>Bardwell</surname>
<given-names>H. A.</given-names>
</name>
<etal/>
</person-group> (<year>2016</year>). <article-title>The somatic mutation profiles of 2, 433 breast cancers refines their genomic and transcriptomic landscapes</article-title>. <source>Nat. Commun.</source> <volume>7</volume>, <fpage>11479</fpage>. <pub-id pub-id-type="doi">10.1038/ncomms11479</pub-id> </citation>
</ref>
<ref id="B177">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Perez-Enciso</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Zingaretti</surname>
<given-names>L. M.</given-names>
</name>
</person-group> (<year>2019</year>). <article-title>A guide for using deep learning for complex trait genomic prediction</article-title>. <source>Genes. (Basel)</source> <volume>10</volume> (<issue>7</issue>), <fpage>E553</fpage>. <pub-id pub-id-type="doi">10.3390/genes10070553</pub-id> </citation>
</ref>
<ref id="B178">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Petukh</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Kucukkal</surname>
<given-names>T. G.</given-names>
</name>
<name>
<surname>Alexov</surname>
<given-names>E.</given-names>
</name>
</person-group> (<year>2015</year>). <article-title>On human disease-causing amino acid variants: Statistical study of sequence and structural patterns</article-title>. <source>Hum. Mutat.</source> <volume>36</volume> (<issue>5</issue>), <fpage>524</fpage>&#x2013;<lpage>534</lpage>. <pub-id pub-id-type="doi">10.1002/humu.22770</pub-id> </citation>
</ref>
<ref id="B179">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Pires</surname>
<given-names>D. E.</given-names>
</name>
<name>
<surname>Blundell</surname>
<given-names>T. L.</given-names>
</name>
<name>
<surname>Ascher</surname>
<given-names>D. B.</given-names>
</name>
</person-group> (<year>2015</year>). <article-title>Platinum: A database of experimentally measured effects of mutations on structurally defined protein-ligand complexes</article-title>. <source>Nucleic Acids Res.</source> <volume>43</volume>, <fpage>D387</fpage>&#x2013;<lpage>D391</lpage>. <pub-id pub-id-type="doi">10.1093/nar/gku966</pub-id> </citation>
</ref>
<ref id="B180">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Pollard</surname>
<given-names>K. S.</given-names>
</name>
<name>
<surname>Hubisz</surname>
<given-names>M. J.</given-names>
</name>
<name>
<surname>Rosenbloom</surname>
<given-names>K. R.</given-names>
</name>
<name>
<surname>Siepel</surname>
<given-names>A.</given-names>
</name>
</person-group> (<year>2010</year>). <article-title>Detection of nonneutral substitution rates on mammalian phylogenies</article-title>. <source>Genome Res.</source> <volume>20</volume> (<issue>1</issue>), <fpage>110</fpage>&#x2013;<lpage>121</lpage>. <pub-id pub-id-type="doi">10.1101/gr.097857.109</pub-id> </citation>
</ref>
<ref id="B181">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Poon</surname>
<given-names>K. S.</given-names>
</name>
</person-group> (<year>2021</year>). <article-title>
<italic>In silico</italic> analysis of BRCA1 and BRCA2 missense variants and the relevance in molecular genetic testing</article-title>. <source>Sci. Rep.</source> <volume>11</volume> (<issue>1</issue>), <fpage>11114</fpage>. <pub-id pub-id-type="doi">10.1038/s41598-021-88586-w</pub-id> </citation>
</ref>
<ref id="B182">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Porta-Pardo</surname>
<given-names>E.</given-names>
</name>
<name>
<surname>Ruiz-Serra</surname>
<given-names>V.</given-names>
</name>
<name>
<surname>Valentini</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Valencia</surname>
<given-names>A.</given-names>
</name>
</person-group> (<year>2022</year>). <article-title>The structural coverage of the human proteome before and after AlphaFold</article-title>. <source>PLoS Comput. Biol.</source> <volume>18</volume> (<issue>1</issue>), <fpage>e1009818</fpage>. <pub-id pub-id-type="doi">10.1371/journal.pcbi.1009818</pub-id> </citation>
</ref>
<ref id="B183">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Pritchard</surname>
<given-names>J. K.</given-names>
</name>
<name>
<surname>Cox</surname>
<given-names>N. J.</given-names>
</name>
</person-group> (<year>2002</year>). <article-title>The allelic architecture of human disease genes: Common disease-common variant.or not?</article-title> <source>Hum. Mol. Genet.</source> <volume>11</volume> (<issue>20</issue>), <fpage>2417</fpage>&#x2013;<lpage>2423</lpage>. <pub-id pub-id-type="doi">10.1093/hmg/11.20.2417</pub-id> </citation>
</ref>
<ref id="B184">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Quang</surname>
<given-names>D.</given-names>
</name>
<name>
<surname>Chen</surname>
<given-names>Y.</given-names>
</name>
<name>
<surname>Xie</surname>
<given-names>X.</given-names>
</name>
</person-group> (<year>2015</year>). <article-title>Dann: A deep learning approach for annotating the pathogenicity of genetic variants</article-title>. <source>Bioinformatics</source> <volume>31</volume> (<issue>5</issue>), <fpage>761</fpage>&#x2013;<lpage>763</lpage>. <pub-id pub-id-type="doi">10.1093/bioinformatics/btu703</pub-id> </citation>
</ref>
<ref id="B185">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Quinodoz</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Peter</surname>
<given-names>V. G.</given-names>
</name>
<name>
<surname>Cisarova</surname>
<given-names>K.</given-names>
</name>
<name>
<surname>Royer-Bertrand</surname>
<given-names>B.</given-names>
</name>
<name>
<surname>Stenson</surname>
<given-names>P. D.</given-names>
</name>
<name>
<surname>Cooper</surname>
<given-names>D. N.</given-names>
</name>
<etal/>
</person-group> (<year>2022</year>). <article-title>Analysis of missense variants in the human genome reveals widespread gene-specific clustering and improves prediction of pathogenicity</article-title>. <source>Am. J. Hum. Genet.</source> <volume>109</volume> (<issue>3</issue>), <fpage>457</fpage>&#x2013;<lpage>470</lpage>. <pub-id pub-id-type="doi">10.1016/j.ajhg.2022.01.006</pub-id> </citation>
</ref>
<ref id="B186">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Rehm</surname>
<given-names>H. L.</given-names>
</name>
<name>
<surname>Berg</surname>
<given-names>J. S.</given-names>
</name>
<name>
<surname>Brooks</surname>
<given-names>L. D.</given-names>
</name>
<name>
<surname>Bustamante</surname>
<given-names>C. D.</given-names>
</name>
<name>
<surname>Evans</surname>
<given-names>J. P.</given-names>
</name>
<name>
<surname>Landrum</surname>
<given-names>M. J.</given-names>
</name>
<etal/>
</person-group> (<year>2015</year>). <article-title>ClinGen--the clinical genome resource</article-title>. <source>N. Engl. J. Med.</source> <volume>372</volume> (<issue>23</issue>), <fpage>2235</fpage>&#x2013;<lpage>2242</lpage>. <pub-id pub-id-type="doi">10.1056/NEJMsr1406261</pub-id> </citation>
</ref>
<ref id="B187">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Reva</surname>
<given-names>B.</given-names>
</name>
<name>
<surname>Antipin</surname>
<given-names>Y.</given-names>
</name>
<name>
<surname>Sander</surname>
<given-names>C.</given-names>
</name>
</person-group> (<year>2007</year>). <article-title>Determinants of protein function revealed by combinatorial entropy optimization</article-title>. <source>Genome Biol.</source> <volume>8</volume> (<issue>11</issue>), <fpage>R232</fpage>. <pub-id pub-id-type="doi">10.1186/gb-2007-8-11-r232</pub-id> </citation>
</ref>
<ref id="B188">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Reva</surname>
<given-names>B.</given-names>
</name>
<name>
<surname>Antipin</surname>
<given-names>Y.</given-names>
</name>
<name>
<surname>Sander</surname>
<given-names>C.</given-names>
</name>
</person-group> (<year>2011</year>). <article-title>Predicting the functional impact of protein mutations: Application to cancer genomics</article-title>. <source>Nucleic Acids Res.</source> <volume>39</volume> (<issue>17</issue>), <fpage>e118</fpage>. <pub-id pub-id-type="doi">10.1093/nar/gkr407</pub-id> </citation>
</ref>
<ref id="B189">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Richards</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Aziz</surname>
<given-names>N.</given-names>
</name>
<name>
<surname>Bale</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Bick</surname>
<given-names>D.</given-names>
</name>
<name>
<surname>Das</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Gastier-Foster</surname>
<given-names>J.</given-names>
</name>
<etal/>
</person-group> (<year>2015</year>). <article-title>Standards and guidelines for the interpretation of sequence variants: A joint consensus recommendation of the American College of medical genetics and genomics and the association for molecular pathology</article-title>. <source>Genet. Med.</source> <volume>17</volume> (<issue>5</issue>), <fpage>405</fpage>&#x2013;<lpage>424</lpage>. <pub-id pub-id-type="doi">10.1038/gim.2015.30</pub-id> </citation>
</ref>
<ref id="B190">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Riesselman</surname>
<given-names>A. J.</given-names>
</name>
<name>
<surname>Ingraham</surname>
<given-names>J. B.</given-names>
</name>
<name>
<surname>Marks</surname>
<given-names>D. S.</given-names>
</name>
</person-group> (<year>2018</year>). <article-title>Deep generative models of genetic variation capture the effects of mutations</article-title>. <source>Nat. Methods</source> <volume>15</volume> (<issue>10</issue>), <fpage>816</fpage>&#x2013;<lpage>822</lpage>. <pub-id pub-id-type="doi">10.1038/s41592-018-0138-4</pub-id> </citation>
</ref>
<ref id="B191">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Robinson</surname>
<given-names>P. N.</given-names>
</name>
<name>
<surname>Kohler</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Bauer</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Seelow</surname>
<given-names>D.</given-names>
</name>
<name>
<surname>Horn</surname>
<given-names>D.</given-names>
</name>
<name>
<surname>Mundlos</surname>
<given-names>S.</given-names>
</name>
</person-group> (<year>2008</year>). <article-title>The human phenotype ontology: A tool for annotating and analyzing human hereditary disease</article-title>. <source>Am. J. Hum. Genet.</source> <volume>83</volume> (<issue>5</issue>), <fpage>610</fpage>&#x2013;<lpage>615</lpage>. <pub-id pub-id-type="doi">10.1016/j.ajhg.2008.09.017</pub-id> </citation>
</ref>
<ref id="B192">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Robinson</surname>
<given-names>P. N.</given-names>
</name>
<name>
<surname>Ravanmehr</surname>
<given-names>V.</given-names>
</name>
<name>
<surname>Jacobsen</surname>
<given-names>J. O. B.</given-names>
</name>
<name>
<surname>Danis</surname>
<given-names>D.</given-names>
</name>
<name>
<surname>Zhang</surname>
<given-names>X. A.</given-names>
</name>
<name>
<surname>Carmody</surname>
<given-names>L. C.</given-names>
</name>
<etal/>
</person-group> (<year>2020</year>). <article-title>Interpretable clinical genomics with a likelihood ratio paradigm</article-title>. <source>Am. J. Hum. Genet.</source> <volume>107</volume> (<issue>3</issue>), <fpage>403</fpage>&#x2013;<lpage>417</lpage>. <pub-id pub-id-type="doi">10.1016/j.ajhg.2020.06.021</pub-id> </citation>
</ref>
<ref id="B193">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Rojano</surname>
<given-names>E.</given-names>
</name>
<name>
<surname>Seoane</surname>
<given-names>P.</given-names>
</name>
<name>
<surname>Ranea</surname>
<given-names>J. A. G.</given-names>
</name>
<name>
<surname>Perkins</surname>
<given-names>J. R.</given-names>
</name>
</person-group> (<year>2019</year>). <article-title>Regulatory variants: From detection to predicting impact</article-title>. <source>Brief. Bioinform.</source> <volume>20</volume> (<issue>5</issue>), <fpage>1639</fpage>&#x2013;<lpage>1654</lpage>. <pub-id pub-id-type="doi">10.1093/bib/bby039</pub-id> </citation>
</ref>
<ref id="B194">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Saito</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Ohno</surname>
<given-names>K.</given-names>
</name>
<name>
<surname>Sakuraba</surname>
<given-names>H.</given-names>
</name>
</person-group> (<year>2011</year>). <article-title>Fabry-database.org: Database of the clinical phenotypes, genotypes and mutant alpha-galactosidase A structures in Fabry disease</article-title>. <source>J. Hum. Genet.</source> <volume>56</volume> (<issue>6</issue>), <fpage>467</fpage>&#x2013;<lpage>468</lpage>. <pub-id pub-id-type="doi">10.1038/jhg.2011.31</pub-id> </citation>
</ref>
<ref id="B195">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Salgado</surname>
<given-names>D.</given-names>
</name>
<name>
<surname>Desvignes</surname>
<given-names>J. P.</given-names>
</name>
<name>
<surname>Rai</surname>
<given-names>G.</given-names>
</name>
<name>
<surname>Blanchard</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Miltgen</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Pinard</surname>
<given-names>A.</given-names>
</name>
<etal/>
</person-group> (<year>2016</year>). <article-title>UMD-predictor: A high-throughput sequencing compliant system for pathogenicity prediction of any human cDNA substitution</article-title>. <source>Hum. Mutat.</source> <volume>37</volume> (<issue>5</issue>), <fpage>439</fpage>&#x2013;<lpage>446</lpage>. <pub-id pub-id-type="doi">10.1002/humu.22965</pub-id> </citation>
</ref>
<ref id="B196">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Sallah</surname>
<given-names>S. R.</given-names>
</name>
<name>
<surname>Sergouniotis</surname>
<given-names>P. I.</given-names>
</name>
<name>
<surname>Barton</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Ramsden</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Taylor</surname>
<given-names>R. L.</given-names>
</name>
<name>
<surname>Safadi</surname>
<given-names>A.</given-names>
</name>
<etal/>
</person-group> (<year>2020</year>). <article-title>Using an integrative machine learning approach utilising homology modelling to clinically interpret genetic variants: CACNA1F as an exemplar</article-title>. <source>Eur. J. Hum. Genet.</source> <volume>28</volume> (<issue>9</issue>), <fpage>1274</fpage>&#x2013;<lpage>1282</lpage>. <pub-id pub-id-type="doi">10.1038/s41431-020-0623-y</pub-id> </citation>
</ref>
<ref id="B197">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Sanavia</surname>
<given-names>T.</given-names>
</name>
<name>
<surname>Birolo</surname>
<given-names>G.</given-names>
</name>
<name>
<surname>Montanucci</surname>
<given-names>L.</given-names>
</name>
<name>
<surname>Turina</surname>
<given-names>P.</given-names>
</name>
<name>
<surname>Capriotti</surname>
<given-names>E.</given-names>
</name>
<name>
<surname>Fariselli</surname>
<given-names>P.</given-names>
</name>
</person-group> (<year>2020</year>). <article-title>Limitations and challenges in protein stability prediction upon genome variations: Towards future applications in precision medicine</article-title>. <source>Comput. Struct. Biotechnol. J.</source> <volume>18</volume>, <fpage>1968</fpage>&#x2013;<lpage>1979</lpage>. <pub-id pub-id-type="doi">10.1016/j.csbj.2020.07.011</pub-id> </citation>
</ref>
<ref id="B198">
<citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname>Sarkar</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Yang</surname>
<given-names>Y.</given-names>
</name>
<name>
<surname>Vihinen</surname>
<given-names>M.</given-names>
</name>
</person-group> (<year>2020</year>). <source>Variation benchmark datasets: Update, criteria, quality and applications</source>. <publisher-loc>Oxford</publisher-loc>: <publisher-name>Database</publisher-name>. <pub-id pub-id-type="doi">10.1093/database/baz117</pub-id> </citation>
</ref>
<ref id="B199">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Sasidharan Nair</surname>
<given-names>P.</given-names>
</name>
<name>
<surname>Vihinen</surname>
<given-names>M.</given-names>
</name>
</person-group> (<year>2013</year>). <article-title>VariBench: A benchmark database for variations</article-title>. <source>Hum. Mutat.</source> <volume>34</volume> (<issue>1</issue>), <fpage>42</fpage>&#x2013;<lpage>49</lpage>. <pub-id pub-id-type="doi">10.1002/humu.22204</pub-id> </citation>
</ref>
<ref id="B200">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Savojardo</surname>
<given-names>C.</given-names>
</name>
<name>
<surname>Babbi</surname>
<given-names>G.</given-names>
</name>
<name>
<surname>Bovo</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Capriotti</surname>
<given-names>E.</given-names>
</name>
<name>
<surname>Martelli</surname>
<given-names>P. L.</given-names>
</name>
<name>
<surname>Casadio</surname>
<given-names>R.</given-names>
</name>
</person-group> (<year>2019</year>). <article-title>Are machine learning based methods suited to address complex biological problems? Lessons from CAGI-5 challenges</article-title>. <source>Hum. Mutat.</source> <volume>40</volume> (<issue>9</issue>), <fpage>1455</fpage>&#x2013;<lpage>1462</lpage>. <pub-id pub-id-type="doi">10.1002/humu.23784</pub-id> </citation>
</ref>
<ref id="B201">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Sayers</surname>
<given-names>E. W.</given-names>
</name>
<name>
<surname>Cavanaugh</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Clark</surname>
<given-names>K.</given-names>
</name>
<name>
<surname>Pruitt</surname>
<given-names>K. D.</given-names>
</name>
<name>
<surname>Schoch</surname>
<given-names>C. L.</given-names>
</name>
<name>
<surname>Sherry</surname>
<given-names>S. T.</given-names>
</name>
<etal/>
</person-group> (<year>2022</year>). <article-title>GenBank.</article-title> <source>GenBank. Nucleic Acids Res.</source> <volume>50</volume> (<issue>D1</issue>), <fpage>D161</fpage>&#x2013;<lpage>D164</lpage>. <pub-id pub-id-type="doi">10.1093/nar/gkab1135</pub-id> </citation>
</ref>
<ref id="B202">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Schaafsma</surname>
<given-names>G. C.</given-names>
</name>
<name>
<surname>Vihinen</surname>
<given-names>M.</given-names>
</name>
</person-group> (<year>2015</year>). <article-title>VariSNP, a benchmark database for variations from dbSNP</article-title>. <source>Hum. Mutat.</source> <volume>36</volume> (<issue>2</issue>), <fpage>161</fpage>&#x2013;<lpage>166</lpage>. <pub-id pub-id-type="doi">10.1002/humu.22727</pub-id> </citation>
</ref>
<ref id="B203">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Schiemann</surname>
<given-names>A. H.</given-names>
</name>
<name>
<surname>Stowell</surname>
<given-names>K. M.</given-names>
</name>
</person-group> (<year>2016</year>). <article-title>Comparison of pathogenicity prediction tools on missense variants in RYR1 and CACNA1S associated with malignant hyperthermia</article-title>. <source>Br. J. Anaesth.</source> <volume>117</volume> (<issue>1</issue>), <fpage>124</fpage>&#x2013;<lpage>128</lpage>. <pub-id pub-id-type="doi">10.1093/bja/aew065</pub-id> </citation>
</ref>
<ref id="B204">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Schwarz</surname>
<given-names>J. M.</given-names>
</name>
<name>
<surname>Cooper</surname>
<given-names>D. N.</given-names>
</name>
<name>
<surname>Schuelke</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Seelow</surname>
<given-names>D.</given-names>
</name>
</person-group> (<year>2014</year>). <article-title>MutationTaster2: Mutation prediction for the deep-sequencing age</article-title>. <source>Nat. Methods</source> <volume>11</volume> (<issue>4</issue>), <fpage>361</fpage>&#x2013;<lpage>362</lpage>. <pub-id pub-id-type="doi">10.1038/nmeth.2890</pub-id> </citation>
</ref>
<ref id="B205">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Schwarz</surname>
<given-names>J. M.</given-names>
</name>
<name>
<surname>Rodelsperger</surname>
<given-names>C.</given-names>
</name>
<name>
<surname>Schuelke</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Seelow</surname>
<given-names>D.</given-names>
</name>
</person-group> (<year>2010</year>). <article-title>MutationTaster evaluates disease-causing potential of sequence alterations</article-title>. <source>Nat. Methods</source> <volume>7</volume> (<issue>8</issue>), <fpage>575</fpage>&#x2013;<lpage>576</lpage>. <pub-id pub-id-type="doi">10.1038/nmeth0810-575</pub-id> </citation>
</ref>
<ref id="B206">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Sherry</surname>
<given-names>S. T.</given-names>
</name>
<name>
<surname>Ward</surname>
<given-names>M. H.</given-names>
</name>
<name>
<surname>Kholodov</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Baker</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Phan</surname>
<given-names>L.</given-names>
</name>
<name>
<surname>Smigielski</surname>
<given-names>E. M.</given-names>
</name>
<etal/>
</person-group> (<year>2001</year>). <article-title>dbSNP: the NCBI database of genetic variation</article-title>. <source>Nucleic Acids Res.</source> <volume>29</volume> (<issue>1</issue>), <fpage>308</fpage>&#x2013;<lpage>311</lpage>. <pub-id pub-id-type="doi">10.1093/nar/29.1.308</pub-id> </citation>
</ref>
<ref id="B207">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Shihab</surname>
<given-names>H. A.</given-names>
</name>
<name>
<surname>Gough</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Cooper</surname>
<given-names>D. N.</given-names>
</name>
<name>
<surname>Day</surname>
<given-names>I. N.</given-names>
</name>
<name>
<surname>Gaunt</surname>
<given-names>T. R.</given-names>
</name>
</person-group> (<year>2013a</year>). <article-title>Predicting the functional consequences of cancer-associated amino acid substitutions</article-title>. <source>Bioinformatics</source> <volume>29</volume> (<issue>12</issue>), <fpage>1504</fpage>&#x2013;<lpage>1510</lpage>. <pub-id pub-id-type="doi">10.1093/bioinformatics/btt182</pub-id> </citation>
</ref>
<ref id="B208">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Shihab</surname>
<given-names>H. A.</given-names>
</name>
<name>
<surname>Gough</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Cooper</surname>
<given-names>D. N.</given-names>
</name>
<name>
<surname>Stenson</surname>
<given-names>P. D.</given-names>
</name>
<name>
<surname>Barker</surname>
<given-names>G. L.</given-names>
</name>
<name>
<surname>Edwards</surname>
<given-names>K. J.</given-names>
</name>
<etal/>
</person-group> (<year>2013b</year>). <article-title>Predicting the functional, molecular, and phenotypic consequences of amino acid substitutions using hidden Markov models</article-title>. <source>Hum. Mutat.</source> <volume>34</volume> (<issue>1</issue>), <fpage>57</fpage>&#x2013;<lpage>65</lpage>. <pub-id pub-id-type="doi">10.1002/humu.22225</pub-id> </citation>
</ref>
<ref id="B209">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Shihab</surname>
<given-names>H. A.</given-names>
</name>
<name>
<surname>Gough</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Cooper</surname>
<given-names>D. N.</given-names>
</name>
<name>
<surname>Stenson</surname>
<given-names>P. D.</given-names>
</name>
<name>
<surname>Barker</surname>
<given-names>G. L.</given-names>
</name>
<name>
<surname>Edwards</surname>
<given-names>K. J.</given-names>
</name>
<etal/>
</person-group> (<year>2013</year>). <article-title>Predicting the functional, molecular, and phenotypic consequences of amino acid substitutions using hidden Markov models</article-title>. <source>Hum. Mutat.</source> <volume>34</volume> (<issue>1</issue>), <fpage>57</fpage>&#x2013;<lpage>65</lpage>. <pub-id pub-id-type="doi">10.1002/humu.22225</pub-id> </citation>
</ref>
<ref id="B210">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Shihab</surname>
<given-names>H. A.</given-names>
</name>
<name>
<surname>Gough</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Mort</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Cooper</surname>
<given-names>D. N.</given-names>
</name>
<name>
<surname>Day</surname>
<given-names>I. N.</given-names>
</name>
<name>
<surname>Gaunt</surname>
<given-names>T. R.</given-names>
</name>
</person-group> (<year>2014</year>). <article-title>Ranking non-synonymous single nucleotide polymorphisms based on disease concepts</article-title>. <source>Hum. Genomics</source> <volume>8</volume>, <fpage>11</fpage>. <pub-id pub-id-type="doi">10.1186/1479-7364-8-11</pub-id> </citation>
</ref>
<ref id="B211">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Siepel</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Bejerano</surname>
<given-names>G.</given-names>
</name>
<name>
<surname>Pedersen</surname>
<given-names>J. S.</given-names>
</name>
<name>
<surname>Hinrichs</surname>
<given-names>A. S.</given-names>
</name>
<name>
<surname>Hou</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Rosenbloom</surname>
<given-names>K.</given-names>
</name>
<etal/>
</person-group> (<year>2005</year>). <article-title>Evolutionarily conserved elements in vertebrate, insect, worm, and yeast genomes</article-title>. <source>Genome Res.</source> <volume>15</volume> (<issue>8</issue>), <fpage>1034</fpage>&#x2013;<lpage>1050</lpage>. <pub-id pub-id-type="doi">10.1101/gr.3715005</pub-id> </citation>
</ref>
<ref id="B212">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Sifrim</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Popovic</surname>
<given-names>D.</given-names>
</name>
<name>
<surname>Tranchevent</surname>
<given-names>L. C.</given-names>
</name>
<name>
<surname>Ardeshirdavani</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Sakai</surname>
<given-names>R.</given-names>
</name>
<name>
<surname>Konings</surname>
<given-names>P.</given-names>
</name>
<etal/>
</person-group> (<year>2013</year>). <article-title>eXtasy: variant prioritization by genomic data fusion</article-title>. <source>Nat. Methods</source> <volume>10</volume> (<issue>11</issue>), <fpage>1083</fpage>&#x2013;<lpage>1084</lpage>. <pub-id pub-id-type="doi">10.1038/nmeth.2656</pub-id> </citation>
</ref>
<ref id="B213">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Sim</surname>
<given-names>N. L.</given-names>
</name>
<name>
<surname>Kumar</surname>
<given-names>P.</given-names>
</name>
<name>
<surname>Hu</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Henikoff</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Schneider</surname>
<given-names>G.</given-names>
</name>
<name>
<surname>Ng</surname>
<given-names>P. C.</given-names>
</name>
</person-group> (<year>2012</year>). <article-title>SIFT web server: Predicting effects of amino acid substitutions on proteins</article-title>. <source>Nucleic Acids Res.</source> <volume>40</volume>, <fpage>W452</fpage>&#x2013;<lpage>W457</lpage>. <comment>Web Server issue)</comment>. <pub-id pub-id-type="doi">10.1093/nar/gks539</pub-id> </citation>
</ref>
<ref id="B214">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Singh</surname>
<given-names>T.</given-names>
</name>
<name>
<surname>Poterba</surname>
<given-names>T.</given-names>
</name>
<name>
<surname>Curtis</surname>
<given-names>D.</given-names>
</name>
<name>
<surname>Akil</surname>
<given-names>H.</given-names>
</name>
<name>
<surname>Al Eissa</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Barchas</surname>
<given-names>J. D.</given-names>
</name>
<etal/>
</person-group> (<year>2022</year>). <article-title>Rare coding variants in ten genes confer substantial risk for schizophrenia</article-title>. <source>Nature</source> <volume>604</volume> (<issue>7906</issue>), <fpage>509</fpage>&#x2013;<lpage>516</lpage>. <pub-id pub-id-type="doi">10.1038/s41586-022-04556-w</pub-id> </citation>
</ref>
<ref id="B215">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Smedley</surname>
<given-names>D.</given-names>
</name>
<name>
<surname>Jacobsen</surname>
<given-names>J. O.</given-names>
</name>
<name>
<surname>Jager</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Kohler</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Holtgrewe</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Schubach</surname>
<given-names>M.</given-names>
</name>
<etal/>
</person-group> (<year>2015</year>). <article-title>Next-generation diagnostics and disease-gene discovery with the Exomiser</article-title>. <source>Nat. Protoc.</source> <volume>10</volume> (<issue>12</issue>), <fpage>2004</fpage>&#x2013;<lpage>2015</lpage>. <pub-id pub-id-type="doi">10.1038/nprot.2015.124</pub-id> </citation>
</ref>
<ref id="B216">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Smigielski</surname>
<given-names>E. M.</given-names>
</name>
<name>
<surname>Sirotkin</surname>
<given-names>K.</given-names>
</name>
<name>
<surname>Ward</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Sherry</surname>
<given-names>S. T.</given-names>
</name>
</person-group> (<year>2000</year>). <article-title>dbSNP: a database of single nucleotide polymorphisms</article-title>. <source>Nucleic Acids Res.</source> <volume>28</volume> (<issue>1</issue>), <fpage>352</fpage>&#x2013;<lpage>355</lpage>. <pub-id pub-id-type="doi">10.1093/nar/28.1.352</pub-id> </citation>
</ref>
<ref id="B217">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Smith</surname>
<given-names>C. L.</given-names>
</name>
<name>
<surname>Goldsmith</surname>
<given-names>C. A.</given-names>
</name>
<name>
<surname>Eppig</surname>
<given-names>J. T.</given-names>
</name>
</person-group> (<year>2005</year>). <article-title>The Mammalian Phenotype Ontology as a tool for annotating, analyzing and comparing phenotypic information</article-title>. <source>Genome Biol.</source> <volume>6</volume> (<issue>1</issue>), <fpage>R7</fpage>. <pub-id pub-id-type="doi">10.1186/gb-2004-6-1-r7</pub-id> </citation>
</ref>
<ref id="B218">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Somody</surname>
<given-names>J. C.</given-names>
</name>
<name>
<surname>MacKinnon</surname>
<given-names>S. S.</given-names>
</name>
<name>
<surname>Windemuth</surname>
<given-names>A.</given-names>
</name>
</person-group> (<year>2017</year>). <article-title>Structural coverage of the proteome for pharmaceutical applications</article-title>. <source>Drug Discov. Today</source> <volume>22</volume> (<issue>12</issue>), <fpage>1792</fpage>&#x2013;<lpage>1799</lpage>. <pub-id pub-id-type="doi">10.1016/j.drudis.2017.08.004</pub-id> </citation>
</ref>
<ref id="B219">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Steinhaus</surname>
<given-names>R.</given-names>
</name>
<name>
<surname>Proft</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Schuelke</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Cooper</surname>
<given-names>D. N.</given-names>
</name>
<name>
<surname>Schwarz</surname>
<given-names>J. M.</given-names>
</name>
<name>
<surname>Seelow</surname>
<given-names>D.</given-names>
</name>
</person-group> (<year>2021</year>). <article-title>MutationTaster2021</article-title>. <source>Nucleic Acids Res.</source> <volume>49</volume> (<issue>W1</issue>), <fpage>W446</fpage>&#x2013;<lpage>W451</lpage>. <pub-id pub-id-type="doi">10.1093/nar/gkab266</pub-id> </citation>
</ref>
<ref id="B220">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Stone</surname>
<given-names>E. A.</given-names>
</name>
<name>
<surname>Sidow</surname>
<given-names>A.</given-names>
</name>
</person-group> (<year>2005</year>). <article-title>Physicochemical constraint violation by missense substitutions mediates impairment of protein function and disease severity</article-title>. <source>Genome Res.</source> <volume>15</volume> (<issue>7</issue>), <fpage>978</fpage>&#x2013;<lpage>986</lpage>. <pub-id pub-id-type="doi">10.1101/gr.3804205</pub-id> </citation>
</ref>
<ref id="B221">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Sudmant</surname>
<given-names>P. H.</given-names>
</name>
<name>
<surname>Rausch</surname>
<given-names>T.</given-names>
</name>
<name>
<surname>Gardner</surname>
<given-names>E. J.</given-names>
</name>
<name>
<surname>Handsaker</surname>
<given-names>R. E.</given-names>
</name>
<name>
<surname>Abyzov</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Huddleston</surname>
<given-names>J.</given-names>
</name>
<etal/>
</person-group> (<year>2015</year>). <article-title>An integrated map of structural variation in 2, 504 human genomes</article-title>. <source>Nature</source> <volume>526</volume> (<issue>7571</issue>), <fpage>75</fpage>&#x2013;<lpage>81</lpage>. <pub-id pub-id-type="doi">10.1038/nature15394</pub-id> </citation>
</ref>
<ref id="B222">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Sunyaev</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Ramensky</surname>
<given-names>V.</given-names>
</name>
<name>
<surname>Bork</surname>
<given-names>P.</given-names>
</name>
</person-group> (<year>2000</year>). <article-title>Towards a structural basis of human non-synonymous single nucleotide polymorphisms</article-title>. <source>Trends Genet.</source> <volume>16</volume> (<issue>5</issue>), <fpage>198</fpage>&#x2013;<lpage>200</lpage>. <pub-id pub-id-type="doi">10.1016/s0168-9525(00)01988-0</pub-id> </citation>
</ref>
<ref id="B223">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Suybeng</surname>
<given-names>V.</given-names>
</name>
<name>
<surname>Koeppel</surname>
<given-names>F.</given-names>
</name>
<name>
<surname>Harle</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Rouleau</surname>
<given-names>E.</given-names>
</name>
</person-group> (<year>2020</year>). <article-title>Comparison of pathogenicity prediction tools on somatic variants</article-title>. <source>J. Mol. Diagn.</source> <volume>22</volume> (<issue>12</issue>), <fpage>1383</fpage>&#x2013;<lpage>1392</lpage>. <pub-id pub-id-type="doi">10.1016/j.jmoldx.2020.08.007</pub-id> </citation>
</ref>
<ref id="B224">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Suzek</surname>
<given-names>B. E.</given-names>
</name>
<name>
<surname>Huang</surname>
<given-names>H.</given-names>
</name>
<name>
<surname>McGarvey</surname>
<given-names>P.</given-names>
</name>
<name>
<surname>Mazumder</surname>
<given-names>R.</given-names>
</name>
<name>
<surname>Wu</surname>
<given-names>C. H.</given-names>
</name>
</person-group> (<year>2007</year>). <article-title>UniRef: Comprehensive and non-redundant UniProt reference clusters</article-title>. <source>Bioinformatics</source> <volume>23</volume> (<issue>10</issue>), <fpage>1282</fpage>&#x2013;<lpage>1288</lpage>. <pub-id pub-id-type="doi">10.1093/bioinformatics/btm098</pub-id> </citation>
</ref>
<ref id="B225">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Tam</surname>
<given-names>V.</given-names>
</name>
<name>
<surname>Patel</surname>
<given-names>N.</given-names>
</name>
<name>
<surname>Turcotte</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Bosse</surname>
<given-names>Y.</given-names>
</name>
<name>
<surname>Pare</surname>
<given-names>G.</given-names>
</name>
<name>
<surname>Meyre</surname>
<given-names>D.</given-names>
</name>
</person-group> (<year>2019</year>). <article-title>Benefits and limitations of genome-wide association studies</article-title>. <source>Nat. Rev. Genet.</source> <volume>20</volume> (<issue>8</issue>), <fpage>467</fpage>&#x2013;<lpage>484</lpage>. <pub-id pub-id-type="doi">10.1038/s41576-019-0127-1</pub-id> </citation>
</ref>
<ref id="B226">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Tate</surname>
<given-names>J. G.</given-names>
</name>
<name>
<surname>Bamford</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Jubb</surname>
<given-names>H. C.</given-names>
</name>
<name>
<surname>Sondka</surname>
<given-names>Z.</given-names>
</name>
<name>
<surname>Beare</surname>
<given-names>D. M.</given-names>
</name>
<name>
<surname>Bindal</surname>
<given-names>N.</given-names>
</name>
<etal/>
</person-group> (<year>2019</year>). <article-title>Cosmic: The catalogue of somatic mutations in cancer</article-title>. <source>Nucleic Acids Res.</source> <volume>47</volume> (<issue>D1</issue>), <fpage>D941-D947</fpage>&#x2013;<lpage>D947</lpage>. <pub-id pub-id-type="doi">10.1093/nar/gky1015</pub-id> </citation>
</ref>
<ref id="B227">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Terui</surname>
<given-names>H.</given-names>
</name>
<name>
<surname>Akagi</surname>
<given-names>K.</given-names>
</name>
<name>
<surname>Kawame</surname>
<given-names>H.</given-names>
</name>
<name>
<surname>Yura</surname>
<given-names>K.</given-names>
</name>
</person-group> (<year>2013</year>). <article-title>CoDP: Predicting the impact of unclassified genetic variants in MSH6 by the combination of different properties of the protein</article-title>. <source>J. Biomed. Sci.</source> <volume>20</volume>, <fpage>25</fpage>. <pub-id pub-id-type="doi">10.1186/1423-0127-20-25</pub-id> </citation>
</ref>
<ref id="B228">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Thomas</surname>
<given-names>P. D.</given-names>
</name>
<name>
<surname>Campbell</surname>
<given-names>M. J.</given-names>
</name>
<name>
<surname>Kejariwal</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Mi</surname>
<given-names>H.</given-names>
</name>
<name>
<surname>Karlak</surname>
<given-names>B.</given-names>
</name>
<name>
<surname>Daverman</surname>
<given-names>R.</given-names>
</name>
<etal/>
</person-group> (<year>2003</year>). <article-title>Panther: A library of protein families and subfamilies indexed by function</article-title>. <source>Genome Res.</source> <volume>13</volume> (<issue>9</issue>), <fpage>2129</fpage>&#x2013;<lpage>2141</lpage>. <pub-id pub-id-type="doi">10.1101/gr.772403</pub-id> </citation>
</ref>
<ref id="B229">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Thomas</surname>
<given-names>P. D.</given-names>
</name>
<name>
<surname>Kejariwal</surname>
<given-names>A.</given-names>
</name>
</person-group> (<year>2004</year>). <article-title>Coding single-nucleotide polymorphisms associated with complex vs. Mendelian disease: Evolutionary evidence for differences in molecular effects</article-title>. <source>Proc. Natl. Acad. Sci. U. S. A.</source> <volume>101</volume> (<issue>43</issue>), <fpage>15398</fpage>&#x2013;<lpage>15403</lpage>. <pub-id pub-id-type="doi">10.1073/pnas.0404380101</pub-id> </citation>
</ref>
<ref id="B230">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Thomas</surname>
<given-names>P. D.</given-names>
</name>
<name>
<surname>Kejariwal</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Guo</surname>
<given-names>N.</given-names>
</name>
<name>
<surname>Mi</surname>
<given-names>H.</given-names>
</name>
<name>
<surname>Campbell</surname>
<given-names>M. J.</given-names>
</name>
<name>
<surname>Muruganujan</surname>
<given-names>A.</given-names>
</name>
<etal/>
</person-group> (<year>2006</year>). <article-title>Applications for protein sequence-function evolution data: mRNA/protein expression analysis and coding SNP scoring tools</article-title>. <source>Nucleic Acids Res.</source> <volume>34</volume>, <fpage>W645</fpage>&#x2013;<lpage>W650</lpage>. <comment>Web Server issue)</comment>. <pub-id pub-id-type="doi">10.1093/nar/gkl229</pub-id> </citation>
</ref>
<ref id="B231">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Thorisson</surname>
<given-names>G. A.</given-names>
</name>
<name>
<surname>Muilu</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Brookes</surname>
<given-names>A. J.</given-names>
</name>
</person-group> (<year>2009</year>). <article-title>Genotype-phenotype databases: Challenges and solutions for the post-genomic era</article-title>. <source>Nat. Rev. Genet.</source> <volume>10</volume> (<issue>1</issue>), <fpage>9</fpage>&#x2013;<lpage>18</lpage>. <pub-id pub-id-type="doi">10.1038/nrg2483</pub-id> </citation>
</ref>
<ref id="B232">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Tian</surname>
<given-names>Y.</given-names>
</name>
<name>
<surname>Pesaran</surname>
<given-names>T.</given-names>
</name>
<name>
<surname>Chamberlin</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Fenwick</surname>
<given-names>R. B.</given-names>
</name>
<name>
<surname>Li</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Gau</surname>
<given-names>C. L.</given-names>
</name>
<etal/>
</person-group> (<year>2019</year>). <article-title>REVEL and BayesDel outperform other <italic>in silico</italic> meta-predictors for clinical variant classification</article-title>. <source>Sci. Rep.</source> <volume>9</volume> (<issue>1</issue>), <fpage>12752</fpage>. <pub-id pub-id-type="doi">10.1038/s41598-019-49224-8</pub-id> </citation>
</ref>
<ref id="B260">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Tischkowitz</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Hamel</surname>
<given-names>M. A</given-names>
</name>
<name>
<surname>Carvalho</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Birrane</surname>
<given-names>G.</given-names>
</name>
<name>
<surname>Soni</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>van Beers</surname>
<given-names>E. H.</given-names>
</name>
</person-group> (<year>2008</year>). <article-title>Pathogenicity of the BRCA1 missense variant M1775K is determined by the disruption of the BRCT phosphopeptide-binding pocket: a multi-modal approach</article-title>. <source>Eur J Hum Genet</source> <volume>16</volume> (<issue>7</issue>), <fpage>820</fpage>&#x2013;<lpage>832</lpage>. <pub-id pub-id-type="doi">10.1038/ejhg.2008.13</pub-id> </citation>
</ref>
<ref id="B233">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Trisilowati, </surname>
</name>
<name>
<surname>Mallet</surname>
<given-names>D. G.</given-names>
</name>
</person-group> (<year>2012</year>). <article-title>
<italic>In silico</italic> experimental modeling of cancer treatment</article-title>. <source>ISRN Oncol.</source> <volume>2012</volume>, <fpage>828701</fpage>. <pub-id pub-id-type="doi">10.5402/2012/828701</pub-id> </citation>
</ref>
<ref id="B234">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Tunyasuvunakool</surname>
<given-names>K.</given-names>
</name>
<name>
<surname>Adler</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Wu</surname>
<given-names>Z.</given-names>
</name>
<name>
<surname>Green</surname>
<given-names>T.</given-names>
</name>
<name>
<surname>Zielinski</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Zidek</surname>
<given-names>A.</given-names>
</name>
<etal/>
</person-group> (<year>2021</year>). <article-title>Highly accurate protein structure prediction for the human proteome</article-title>. <source>Nature</source> <volume>596</volume> (<issue>7873</issue>), <fpage>590</fpage>&#x2013;<lpage>596</lpage>. <pub-id pub-id-type="doi">10.1038/s41586-021-03828-1</pub-id> </citation>
</ref>
<ref id="B235">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>UniProt</surname>
<given-names>C.</given-names>
</name>
</person-group> (<year>2021</year>). <article-title>UniProt: The universal protein knowledgebase in 2021</article-title>. <source>Nucleic Acids Res.</source> <volume>49</volume> (<issue>D1</issue>), <fpage>D480</fpage>&#x2013;<lpage>D489</lpage>. <pub-id pub-id-type="doi">10.1093/nar/gkaa1100</pub-id> </citation>
</ref>
<ref id="B236">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Vaser</surname>
<given-names>R.</given-names>
</name>
<name>
<surname>Adusumalli</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Leng</surname>
<given-names>S. N.</given-names>
</name>
<name>
<surname>Sikic</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Ng</surname>
<given-names>P. C.</given-names>
</name>
</person-group> (<year>2016</year>). <article-title>SIFT missense predictions for genomes</article-title>. <source>Nat. Protoc.</source> <volume>11</volume> (<issue>1</issue>), <fpage>1</fpage>&#x2013;<lpage>9</lpage>. <pub-id pub-id-type="doi">10.1038/nprot.2015.123</pub-id> </citation>
</ref>
<ref id="B237">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Vihinen</surname>
<given-names>M.</given-names>
</name>
</person-group> (<year>2021</year>). <article-title>Functional effects of protein variants</article-title>. <source>Biochimie</source> <volume>180</volume>, <fpage>104</fpage>&#x2013;<lpage>120</lpage>. <pub-id pub-id-type="doi">10.1016/j.biochi.2020.10.009</pub-id> </citation>
</ref>
<ref id="B238">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Vihinen</surname>
<given-names>M.</given-names>
</name>
</person-group> (<year>2013</year>). <article-title>Guidelines for reporting and using prediction tools for genetic variation analysis</article-title>. <source>Hum. Mutat.</source> <volume>34</volume> (<issue>2</issue>), <fpage>275</fpage>&#x2013;<lpage>282</lpage>. <pub-id pub-id-type="doi">10.1002/humu.22253</pub-id> </citation>
</ref>
<ref id="B239">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Vihinen</surname>
<given-names>M.</given-names>
</name>
</person-group> (<year>2012</year>). <article-title>How to evaluate performance of prediction methods? Measures and their interpretation in variation effect analysis</article-title>. <source>BMC Genomics</source> <volume>13</volume> (<issue>4</issue>), <fpage>S2</fpage>. <pub-id pub-id-type="doi">10.1186/1471-2164-13-S4-S2</pub-id> </citation>
</ref>
<ref id="B240">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Vihinen</surname>
<given-names>M.</given-names>
</name>
</person-group> (<year>2014</year>). <article-title>Variation Ontology for annotation of variation effects and mechanisms</article-title>. <source>Genome Res.</source> <volume>24</volume> (<issue>2</issue>), <fpage>356</fpage>&#x2013;<lpage>364</lpage>. <pub-id pub-id-type="doi">10.1101/gr.157495.113</pub-id> </citation>
</ref>
<ref id="B241">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Wang</surname>
<given-names>K.</given-names>
</name>
<name>
<surname>Li</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Hakonarson</surname>
<given-names>H.</given-names>
</name>
</person-group> (<year>2010</year>). <article-title>Annovar: Functional annotation of genetic variants from high-throughput sequencing data</article-title>. <source>Nucleic Acids Res.</source> <volume>38</volume> (<issue>16</issue>), <fpage>e164</fpage>. <pub-id pub-id-type="doi">10.1093/nar/gkq603</pub-id> </citation>
</ref>
<ref id="B242">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Weber</surname>
<given-names>L. M.</given-names>
</name>
<name>
<surname>Saelens</surname>
<given-names>W.</given-names>
</name>
<name>
<surname>Cannoodt</surname>
<given-names>R.</given-names>
</name>
<name>
<surname>Soneson</surname>
<given-names>C.</given-names>
</name>
<name>
<surname>Hapfelmeier</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Gardner</surname>
<given-names>P. P.</given-names>
</name>
<etal/>
</person-group> (<year>2019</year>). <article-title>Essential guidelines for computational method benchmarking</article-title>. <source>Genome Biol.</source> <volume>20</volume> (<issue>1</issue>), <fpage>125</fpage>. <pub-id pub-id-type="doi">10.1186/s13059-019-1738-8</pub-id> </citation>
</ref>
<ref id="B243">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Wei</surname>
<given-names>R.</given-names>
</name>
<name>
<surname>Wang</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Su</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Jia</surname>
<given-names>E.</given-names>
</name>
<name>
<surname>Chen</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Chen</surname>
<given-names>T.</given-names>
</name>
<etal/>
</person-group> (<year>2018</year>). <article-title>Missing value imputation approach for mass spectrometry-based metabolomics data</article-title>. <source>Sci. Rep.</source> <volume>8</volume> (<issue>1</issue>), <fpage>663</fpage>. <pub-id pub-id-type="doi">10.1038/s41598-017-19120-0</pub-id> </citation>
</ref>
<ref id="B244">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Witvliet</surname>
<given-names>D. K.</given-names>
</name>
<name>
<surname>Strokach</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Giraldo-Forero</surname>
<given-names>A. F.</given-names>
</name>
<name>
<surname>Teyra</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Colak</surname>
<given-names>R.</given-names>
</name>
<name>
<surname>Kim</surname>
<given-names>P. M.</given-names>
</name>
</person-group> (<year>2016</year>). <article-title>ELASPIC web-server: Proteome-wide structure-based prediction of mutation effects on protein stability and binding affinity</article-title>. <source>Bioinformatics</source> <volume>32</volume> (<issue>10</issue>), <fpage>1589</fpage>&#x2013;<lpage>1591</lpage>. <pub-id pub-id-type="doi">10.1093/bioinformatics/btw031</pub-id> </citation>
</ref>
<ref id="B245">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Won</surname>
<given-names>D. G.</given-names>
</name>
<name>
<surname>Kim</surname>
<given-names>D. W.</given-names>
</name>
<name>
<surname>Woo</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Lee</surname>
<given-names>K.</given-names>
</name>
</person-group> (<year>2021</year>). <article-title>3Cnet: Pathogenicity prediction of human variants using multitask learning with evolutionary constraints</article-title>. <source>Bioinformatics</source> <volume>37</volume>, <fpage>4626</fpage>&#x2013;<lpage>4634</lpage>. <pub-id pub-id-type="doi">10.1093/bioinformatics/btab529</pub-id> </citation>
</ref>
<ref id="B246">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Worth</surname>
<given-names>C. L.</given-names>
</name>
<name>
<surname>Preissner</surname>
<given-names>R.</given-names>
</name>
<name>
<surname>Blundell</surname>
<given-names>T. L.</given-names>
</name>
</person-group> (<year>2011</year>). <article-title>SDM--a server for predicting effects of mutations on protein stability and malfunction</article-title>. <source>Nucleic Acids Res.</source> <volume>39</volume>, <fpage>W215</fpage>&#x2013;<lpage>W222</lpage>. <comment>Web Server issue)</comment>. <pub-id pub-id-type="doi">10.1093/nar/gkr363</pub-id> </citation>
</ref>
<ref id="B247">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Xavier</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Scott</surname>
<given-names>R. J.</given-names>
</name>
<name>
<surname>Talseth-Palmer</surname>
<given-names>B. A.</given-names>
</name>
</person-group> (<year>2019</year>). <article-title>TAPES: A tool for assessment and prioritisation in exome studies</article-title>. <source>PLoS Comput. Biol.</source> <volume>15</volume> (<issue>10</issue>), <fpage>e1007453</fpage>. <pub-id pub-id-type="doi">10.1371/journal.pcbi.1007453</pub-id> </citation>
</ref>
<ref id="B248">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Yazar</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Ozbek</surname>
<given-names>P.</given-names>
</name>
</person-group> (<year>2021</year>). <article-title>
<italic>In silico</italic> tools and approaches for the prediction of functional and structural effects of single-nucleotide polymorphisms on proteins: An expert review.</article-title> <source>OMICS</source> <volume>25</volume> (<issue>1</issue>), <fpage>23</fpage>&#x2013;<lpage>37</lpage>. <pub-id pub-id-type="doi">10.1089/omi.2020.0141</pub-id> </citation>
</ref>
<ref id="B249">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Yuan</surname>
<given-names>X.</given-names>
</name>
<name>
<surname>Wang</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Dai</surname>
<given-names>B.</given-names>
</name>
<name>
<surname>Sun</surname>
<given-names>Y.</given-names>
</name>
<name>
<surname>Zhang</surname>
<given-names>K.</given-names>
</name>
<name>
<surname>Chen</surname>
<given-names>F.</given-names>
</name>
<etal/>
</person-group> (<year>2022</year>). <article-title>Evaluation of phenotype-driven gene prioritization methods for Mendelian diseases</article-title>. <source>Brief. Bioinform.</source> <volume>23</volume> (<issue>2</issue>), <fpage>bbac019</fpage>. <pub-id pub-id-type="doi">10.1093/bib/bbac019</pub-id> </citation>
</ref>
<ref id="B250">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Yue</surname>
<given-names>P.</given-names>
</name>
<name>
<surname>Li</surname>
<given-names>Z.</given-names>
</name>
<name>
<surname>Moult</surname>
<given-names>J.</given-names>
</name>
</person-group> (<year>2005</year>). <article-title>Loss of protein structure stability as a major causative factor in monogenic disease</article-title>. <source>J. Mol. Biol.</source> <volume>353</volume> (<issue>2</issue>), <fpage>459</fpage>&#x2013;<lpage>473</lpage>. <pub-id pub-id-type="doi">10.1016/j.jmb.2005.08.020</pub-id> </citation>
</ref>
<ref id="B251">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Yue</surname>
<given-names>P.</given-names>
</name>
<name>
<surname>Melamud</surname>
<given-names>E.</given-names>
</name>
<name>
<surname>Moult</surname>
<given-names>J.</given-names>
</name>
</person-group> (<year>2006</year>). <article-title>SNPs3D: Candidate gene and SNP selection for association studies</article-title>. <source>BMC Bioinforma.</source> <volume>7</volume>, <fpage>166</fpage>. <pub-id pub-id-type="doi">10.1186/1471-2105-7-166</pub-id> </citation>
</ref>
<ref id="B252">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Yue</surname>
<given-names>W. W.</given-names>
</name>
<name>
<surname>Froese</surname>
<given-names>D. S.</given-names>
</name>
<name>
<surname>Brennan</surname>
<given-names>P. E.</given-names>
</name>
</person-group> (<year>2014</year>). <article-title>The role of protein structural analysis in the next generation sequencing era</article-title>. <source>Top. Curr. Chem.</source> <volume>336</volume>, <fpage>67</fpage>&#x2013;<lpage>98</lpage>. <pub-id pub-id-type="doi">10.1007/128_2012_326</pub-id> </citation>
</ref>
<ref id="B253">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Zhang</surname>
<given-names>W.</given-names>
</name>
<name>
<surname>Zhang</surname>
<given-names>H.</given-names>
</name>
<name>
<surname>Yang</surname>
<given-names>H.</given-names>
</name>
<name>
<surname>Li</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Xie</surname>
<given-names>Z.</given-names>
</name>
<name>
<surname>Li</surname>
<given-names>W.</given-names>
</name>
</person-group> (<year>2019</year>). <article-title>Computational resources associating diseases with genotypes, phenotypes and exposures</article-title>. <source>Brief. Bioinform.</source> <volume>20</volume> (<issue>6</issue>), <fpage>2098</fpage>&#x2013;<lpage>2115</lpage>. <pub-id pub-id-type="doi">10.1093/bib/bby071</pub-id> </citation>
</ref>
<ref id="B254">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Zhang</surname>
<given-names>X.</given-names>
</name>
<name>
<surname>Walsh</surname>
<given-names>R.</given-names>
</name>
<name>
<surname>Whiffin</surname>
<given-names>N.</given-names>
</name>
<name>
<surname>Buchan</surname>
<given-names>R.</given-names>
</name>
<name>
<surname>Midwinter</surname>
<given-names>W.</given-names>
</name>
<name>
<surname>Wilk</surname>
<given-names>A.</given-names>
</name>
<etal/>
</person-group> (<year>2021</year>). <article-title>Disease-specific variant pathogenicity prediction significantly improves variant interpretation in inherited cardiac conditions</article-title>. <source>Genet. Med.</source> <volume>23</volume> (<issue>1</issue>), <fpage>69</fpage>&#x2013;<lpage>79</lpage>. <pub-id pub-id-type="doi">10.1038/s41436-020-00972-3</pub-id> </citation>
</ref>
<ref id="B255">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Zhao</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Havrilla</surname>
<given-names>J. M.</given-names>
</name>
<name>
<surname>Fang</surname>
<given-names>L.</given-names>
</name>
<name>
<surname>Chen</surname>
<given-names>Y.</given-names>
</name>
<name>
<surname>Peng</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Liu</surname>
<given-names>C.</given-names>
</name>
<etal/>
</person-group> (<year>2020</year>). <article-title>Phen2Gene: Rapid phenotype-driven gene prioritization for rare diseases</article-title>. <source>Nar. Genom. Bioinform.</source> <volume>2</volume>, <fpage>lqaa032</fpage>. <pub-id pub-id-type="doi">10.1093/nargab/lqaa032</pub-id> </citation>
</ref>
<ref id="B256">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Zhao</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Kim</surname>
<given-names>P.</given-names>
</name>
<name>
<surname>Mitra</surname>
<given-names>R.</given-names>
</name>
<name>
<surname>Zhao</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Zhao</surname>
<given-names>Z.</given-names>
</name>
</person-group> (<year>2016</year>). <article-title>TSGene 2.0: An updated literature-based knowledgebase for tumor suppressor genes</article-title>. <source>Nucleic Acids Res.</source> <volume>44</volume> (<issue>D1</issue>), <fpage>D1023</fpage>&#x2013;<lpage>D1031</lpage>. <pub-id pub-id-type="doi">10.1093/nar/gkv1268</pub-id> </citation>
</ref>
<ref id="B257">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Zheng</surname>
<given-names>X.</given-names>
</name>
<name>
<surname>Amos</surname>
<given-names>C. I.</given-names>
</name>
<name>
<surname>Frost</surname>
<given-names>H. R.</given-names>
</name>
</person-group> (<year>2020</year>). <article-title>Cancer prognosis prediction using somatic point mutation and copy number variation data: A comparison of gene-level and pathway-based models</article-title>. <source>BMC Bioinforma.</source> <volume>21</volume> (<issue>1</issue>), <fpage>467</fpage>. <pub-id pub-id-type="doi">10.1186/s12859-020-03791-0</pub-id> </citation>
</ref>
<ref id="B258">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Zhou</surname>
<given-names>H.</given-names>
</name>
<name>
<surname>Gao</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Skolnick</surname>
<given-names>J.</given-names>
</name>
</person-group> (<year>2016</year>). <article-title>Entprise: An algorithm for predicting human disease-associated amino acid substitutions from sequence entropy and predicted protein structures</article-title>. <source>PLoS One</source> <volume>11</volume> (<issue>3</issue>), <fpage>e0150965</fpage>. <pub-id pub-id-type="doi">10.1371/journal.pone.0150965</pub-id> </citation>
</ref>
</ref-list>
</back>
</article>