<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD Journal Publishing DTD v2.3 20070202//EN" "journalpublishing.dtd">
<article xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" article-type="research-article">
<front>
<journal-meta>
<journal-id journal-id-type="publisher-id">Front. Bioeng. Biotechnol.</journal-id>
<journal-title>Frontiers in Bioengineering and Biotechnology</journal-title>
<abbrev-journal-title abbrev-type="pubmed">Front. Bioeng. Biotechnol.</abbrev-journal-title>
<issn pub-type="epub">2296-4185</issn>
<publisher>
<publisher-name>Frontiers Media S.A.</publisher-name>
</publisher>
</journal-meta>
<article-meta>
<article-id pub-id-type="doi">10.3389/fbioe.2020.627335</article-id>
<article-categories>
<subj-group subj-group-type="heading">
<subject>Bioengineering and Biotechnology</subject>
<subj-group>
<subject>Original Research</subject>
</subj-group>
</subj-group>
</article-categories>
<title-group>
<article-title>Predicting Cell Wall Lytic Enzymes Using Combined Features</article-title>
</title-group>
<contrib-group>
<contrib contrib-type="author">
<name><surname>Jing</surname> <given-names>Xiao-Yang</given-names></name>
<uri xlink:href="http://loop.frontiersin.org/people/1137586/overview"/>
</contrib>
<contrib contrib-type="author" corresp="yes">
<name><surname>Li</surname> <given-names>Feng-Min</given-names></name>
<xref ref-type="corresp" rid="c001"><sup>&#x002A;</sup></xref>
<uri xlink:href="http://loop.frontiersin.org/people/1137453/overview"/>
</contrib>
</contrib-group>
<aff><institution>College of Science, Inner Mongolia Agricultural University</institution>, <addr-line>Hohhot</addr-line>, <country>China</country></aff>
<author-notes>
<fn fn-type="edited-by"><p>Edited by: Zhibin Lv, University of Electronic Science and Technology of China, China</p></fn>
<fn fn-type="edited-by"><p>Reviewed by: Fei Guo, Tianjin University, China; Hua Tang, Southwest Medical University, China</p></fn>
<corresp id="c001">&#x002A;Correspondence: Feng-Min Li, <email>fmli@imau.edu.cn</email></corresp>
<fn fn-type="other" id="fn004"><p>This article was submitted to Synthetic Biology, a section of the journal Frontiers in Bioengineering and Biotechnology</p></fn>
</author-notes>
<pub-date pub-type="epub">
<day>06</day>
<month>01</month>
<year>2021</year>
</pub-date>
<pub-date pub-type="collection">
<year>2020</year>
</pub-date>
<volume>8</volume>
<elocation-id>627335</elocation-id>
<history>
<date date-type="received">
<day>09</day>
<month>11</month>
<year>2020</year>
</date>
<date date-type="accepted">
<day>04</day>
<month>12</month>
<year>2020</year>
</date>
</history>
<permissions>
<copyright-statement>Copyright &#x00A9; 2021 Jing and Li.</copyright-statement>
<copyright-year>2021</copyright-year>
<copyright-holder>Jing and Li</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>Due to the overuse of antibiotics, people are worried that existing antibiotics will become ineffective against pathogens with the rapid rise of antibiotic-resistant strains. The use of cell wall lytic enzymes to destroy bacteria has become a viable alternative to avoid the crisis of antimicrobial resistance. In this paper, an improved method for cell wall lytic enzymes prediction was proposed and the amino acid composition (AAC), the dipeptide composition (DC), the position-specific score matrix auto-covariance (PSSM-AC), and the auto-covariance average chemical shift (acACS) were selected to predict the cell wall lytic enzymes with support vector machine (SVM). In order to overcome the imbalanced data classification problems and remove redundant or irrelevant features, the synthetic minority over-sampling technique (SMOTE) was used to balance the dataset. The F-score was used to select features. The S<sub><italic>n</italic></sub>, S<sub><italic>p</italic></sub>, MCC, and Acc were 99.35%, 99.02%, 0.98, and 99.19% with jackknife test using the optimized combination feature AAC+DC+acACS+PSSM-AC. The S<sub><italic>n</italic></sub>, S<sub><italic>p</italic></sub>, MCC, and Acc of cell wall lytic enzymes in our predictive model were higher than those in existing methods. This improved method may be helpful for protein function prediction.</p>
</abstract>
<kwd-group>
<kwd>cell wall lytic enzymes</kwd>
<kwd>optimized combination feature</kwd>
<kwd>synthetic minority over-sampling technique</kwd>
<kwd>F-score</kwd>
<kwd>support vector machine</kwd>
<kwd>jackknife test</kwd>
</kwd-group>
<counts>
<fig-count count="7"/>
<table-count count="3"/>
<equation-count count="16"/>
<ref-count count="64"/>
<page-count count="8"/>
<word-count count="0"/>
</counts>
</article-meta>
</front>
<body>
<sec id="S1">
<title>Introduction</title>
<p>Bacteria are constantly around us, and bacterial infections have become a major public health problem. The overuse of antibiotics leads to the rapid rise of antibiotic-resistant strains, and people are worried that existing antibiotics will become ineffective against pathogens. Using cell wall lytic enzymes to destroy bacteria has become a viable alternative method to avoid the crisis of antimicrobial resistance (<xref ref-type="bibr" rid="B39">Sommer et al., 2017</xref>; <xref ref-type="bibr" rid="B52">Wu et al., 2017</xref>; <xref ref-type="bibr" rid="B3">Bhagwat et al., 2019</xref>; <xref ref-type="bibr" rid="B10">Cheng et al., 2020</xref>). Cell wall lytic enzymes are divided into two enzymes: endolysin and autolysin. Endolysins are phage-encoded enzymes that have evolved to degrade the bacterial cell wall (<xref ref-type="bibr" rid="B37">Shavrina et al., 2016</xref>). Many studies have shown that endolysin has an excellent bactericidal effect on <italic>Staphylococcus aureus</italic> (<xref ref-type="bibr" rid="B1">Ajuebor et al., 2016</xref>), <italic>Escherichia coli</italic> (<xref ref-type="bibr" rid="B54">Yan et al., 2019</xref>), <italic>Streptococcus suis</italic> (<xref ref-type="bibr" rid="B14">Der Ploeg, 2008</xref>), and other pathogens. Compared with conventional antibiotics, endolysin has many advantages, such as rapid host killing, host specificity, low chances of developing drug resistance, and efficacy against multidrug-resistant bacteria (<xref ref-type="bibr" rid="B21">Gondil et al., 2020</xref>). Autolysin is the other cell wall lytic enzyme that degrades some bonds in the peptidoglycan backbone of the bacterial cell wall (<xref ref-type="bibr" rid="B44">Usobiaga et al., 1996</xref>), and it is closely related to the life of cells and participates in the control of cell growth, cell lysis, daughter-cell separation, and biofilm formation (<xref ref-type="bibr" rid="B27">Kalali et al., 2019</xref>). Cell wall lytic enzymes have become a valuable tool for biological researchers in the medical and food industry and in agricultural applications (<xref ref-type="bibr" rid="B57">Yu, 1997</xref>).</p>
<p>Experimental determination of the cell wall lytic enzymes is time-consuming and laborious, so it is necessary to use an effective method to predict cell wall lytic enzymes. Recently some computational methods for predicting cell wall lytic enzymes have been proposed. <xref ref-type="bibr" rid="B15">Ding et al. (2009)</xref> used Chou&#x2019;s amphiphilic pseudo to predict cell wall lytic enzymes; the predictive accuracy was 80.40% with jackknife test. <xref ref-type="bibr" rid="B7">Chen et al. (2016)</xref> developed a predictor called &#x201C;Lypred&#x201D; that used pseudo amino acid composition (PseAAC) as a feature vector; the predictive accuracy was 91.3% with fivefold cross-validation. <xref ref-type="bibr" rid="B35">Meng et al. (2020)</xref> developed a predictor called &#x201C;CWLy-SVM&#x201D; that employed the 473-dimensional sequence-based feature descriptor to predict cell wall lytic enzymes; the result was 95.50% with jackknife test. In this paper, the amino acid composition (AAC), the dipeptide composition (DC), the position-specific score matrix auto-covariance (PSSM-AC), and the Auto-covariance average chemical shift (acACS) were used to predict the cell wall lytic enzymes with the same datasets as investigated by <xref ref-type="bibr" rid="B7">Chen et al. (2016)</xref>.</p>
<p>Data imbalance is always considered a problem in developing efficient and reliable prediction systems; in imbalanced datasets, the classifier would tend to the majority class. Here, the synthetic minority over-sampling technique (SMOTE) was used to solve the problem of imbalance. To remove redundant or irrelevant features, we selected features using the F-score algorithm. The accuracy (Acc) was 99.19% with a balanced dataset in jackknife test by using the optimized combination feature AAC+DC+PSSM-AC+acACS.</p>
</sec>
<sec id="S2" sec-type="materials|methods">
<title>Materials and Methods</title>
<sec id="S2.SS1">
<title>Benchmark Dataset</title>
<p>The benchmark dataset was generated by <xref ref-type="bibr" rid="B7">Chen et al. (2016)</xref>, The dataset was taken from the Universal Protein Resource (UniProt), using the following steps to collect the sequence: (1) sequences annotated with &#x201C;Inferred from homology&#x201D; or &#x201C;Predicted&#x201D; were removed. (2) Sequences which were the fragments of other proteins were not included. (3) Sequences containing ambiguous letters such as &#x201C;B,&#x201D; &#x201C;J,&#x201D; &#x201C;O,&#x201D; &#x201C;U,&#x201D; &#x201C;X,&#x201D; and &#x201C;Z&#x201D; were excluded. To reduce homologous bias and redundancy, the program CD&#x2013;HIT (<xref ref-type="bibr" rid="B33">Li and Godzik, 2006</xref>) was used to remove those sequences that have &#x2265; 40% pairwise sequence identity. Finally, 375 sequences were obtained; they contained 68 lyases and 307 non-lyases, and the dataset can be expressed as:</p>
<disp-formula id="S2.E1">
<label>(1)</label>
<mml:math id="M1">
<mml:mrow>
<mml:mi>S</mml:mi>
<mml:mo>=</mml:mo>
<mml:mrow>
<mml:msub>
<mml:mi>S</mml:mi>
<mml:mrow>
<mml:mi>l</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>y</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>s</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>a</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>s</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>e</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>s</mml:mi>
</mml:mrow>
</mml:msub>
<mml:mo>&#x222A;</mml:mo>
<mml:msub>
<mml:mi>S</mml:mi>
<mml:mrow>
<mml:mi>n</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>o</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>n</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>l</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>y</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>s</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>a</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>s</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>e</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>s</mml:mi>
</mml:mrow>
</mml:msub>
</mml:mrow>
</mml:mrow>
</mml:math>
</disp-formula>
<p>The dataset can be freely downloaded from <ext-link ext-link-type="uri" xlink:href="http://lin-group.cn/server/Lypred/data.html">http://lin-group.cn/server/Lypred/data.html</ext-link>.</p>
</sec>
<sec id="S2.SS2">
<title>Feature Extraction Techniques</title>
<p>Feature extraction is a crucial step in developing a powerful predictor; a set of reasonable features contains more protein sequence information (<xref ref-type="bibr" rid="B62">Zhu et al., 2018</xref>; <xref ref-type="bibr" rid="B56">Yang et al., 2019</xref>; <xref ref-type="bibr" rid="B59">Zhang and Liu, 2019</xref>). Generally, the feature combination can boost the prediction performance. In this paper, the AAC, the DC, the PSSM-AC, and the acACS were used to predict the cell wall lytic enzymes.</p>
<sec id="S2.SS2.SSS1">
<title>Amino Acid Composition</title>
<p>The amino acid composition of proteins is the most basic feature information in all features. The protein sequence consists of 20 amino acids (A, C, D, E, F, G, H, I, K, L, M, N, P, Q, R, S, T, V, W, and Y). AAC calculates the occurrence frequency of the 20 native amino acids so that the protein sequence can be expressed as 20 features in a feature vector. It can be defined as:</p>
<disp-formula id="S2.E2">
<label>(2)</label>
<mml:math id="M2">
<mml:mrow>
<mml:mi>P</mml:mi>
<mml:mo>=</mml:mo>
<mml:mrow>
<mml:mo>[</mml:mo>
<mml:msub>
<mml:mi>x</mml:mi>
<mml:mn>1</mml:mn>
</mml:msub>
<mml:mo>,</mml:mo>
<mml:msub>
<mml:mi>x</mml:mi>
<mml:mn>2</mml:mn>
</mml:msub>
<mml:mo>,</mml:mo>
<mml:msub>
<mml:mi>x</mml:mi>
<mml:mn>3</mml:mn>
</mml:msub>
<mml:mo>,</mml:mo>
<mml:mi mathvariant="normal">&#x22EF;</mml:mi>
<mml:mo>,</mml:mo>
<mml:msub>
<mml:mi>x</mml:mi>
<mml:mi>i</mml:mi>
</mml:msub>
<mml:mo>,</mml:mo>
<mml:mi mathvariant="normal">&#x22EF;</mml:mi>
<mml:mo>,</mml:mo>
<mml:msub>
<mml:mi>x</mml:mi>
<mml:mn>20</mml:mn>
</mml:msub>
<mml:mo>]</mml:mo>
</mml:mrow>
</mml:mrow>
</mml:math>
</disp-formula>
<disp-formula id="S2.E3">
<label>(3)</label>
<mml:math id="M3">
<mml:mrow>
<mml:msub>
<mml:mi>x</mml:mi>
<mml:mi>i</mml:mi>
</mml:msub>
<mml:mo>=</mml:mo>
<mml:mfrac>
<mml:msub>
<mml:mi>n</mml:mi>
<mml:mi>i</mml:mi>
</mml:msub>
<mml:mi>L</mml:mi>
</mml:mfrac>
</mml:mrow>
</mml:math>
</disp-formula>
<p>Where <italic>n</italic><sub><italic>i</italic></sub> is the occurrence number of the 20 native amino acid in protein sequence and L is the length of the protein sequence.</p>
</sec>
<sec id="S2.SS2.SSS2">
<title>Dipeptide Composition</title>
<p>Dipeptide composition (DC) is calculated as the occurrence frequency of each two adjacent amino acid residues. There are 20<sup>&#x2217;</sup>20 = 400 combinations of amino acid pairs. Compared with AAC, DC is a feature that considers some sequence-order information. It can be calculated as:</p>
<disp-formula id="S2.E4">
<label>(4)</label>
<mml:math id="M4">
<mml:mrow>
<mml:mi>P</mml:mi>
<mml:mo>=</mml:mo>
<mml:mrow>
<mml:mo>[</mml:mo>
<mml:msub>
<mml:mi>f</mml:mi>
<mml:mn>1</mml:mn>
</mml:msub>
<mml:mo>,</mml:mo>
<mml:msub>
<mml:mi>f</mml:mi>
<mml:mn>2</mml:mn>
</mml:msub>
<mml:mo>,</mml:mo>
<mml:msub>
<mml:mi>f</mml:mi>
<mml:mn>3</mml:mn>
</mml:msub>
<mml:mo>,</mml:mo>
<mml:mi mathvariant="normal">&#x2026;</mml:mi>
<mml:mo>,</mml:mo>
<mml:msub>
<mml:mi>f</mml:mi>
<mml:mi>i</mml:mi>
</mml:msub>
<mml:mo>,</mml:mo>
<mml:mi mathvariant="normal">&#x2026;</mml:mi>
<mml:mo>,</mml:mo>
<mml:msub>
<mml:mi>f</mml:mi>
<mml:mn>400</mml:mn>
</mml:msub>
<mml:mo>]</mml:mo>
</mml:mrow>
</mml:mrow>
</mml:math>
</disp-formula>
<disp-formula id="S2.E5">
<label>(5)</label>
<mml:math id="M5">
<mml:mrow>
<mml:msub>
<mml:mi>f</mml:mi>
<mml:mi>i</mml:mi>
</mml:msub>
<mml:mo>=</mml:mo>
<mml:mfrac>
<mml:msub>
<mml:mi>m</mml:mi>
<mml:mi>i</mml:mi>
</mml:msub>
<mml:mrow>
<mml:mi>L</mml:mi>
<mml:mo>-</mml:mo>
<mml:mn>1</mml:mn>
</mml:mrow>
</mml:mfrac>
</mml:mrow>
</mml:math>
</disp-formula>
<p>Where <italic>m</italic><sub><italic>i</italic></sub> is the occurrence number of i-th dipeptide in protein sequence and L is the length of the protein sequence.</p>
</sec>
<sec id="S2.SS2.SSS3">
<title>Position-Specific Score Matrix Auto-Covariance</title>
<p>Position-Specific Score Matrix Auto-Covariance (PSSM-AC) is a feature that extracts the evolutionary information of a protein sequence. PSSM-AC was first proposed to predict the protein fold recognition by <xref ref-type="bibr" rid="B16">Dong et al. (2009)</xref>. Recently, the PSSM-AC was used successfully in many works for the prediction of protein function (<xref ref-type="bibr" rid="B63">Zou et al., 2013</xref>; <xref ref-type="bibr" rid="B22">Huang and Li, 2018</xref>; <xref ref-type="bibr" rid="B48">Wang et al., 2019b</xref>, <xref ref-type="bibr" rid="B47">2020a</xref>). In PSSM-AC, the PSI-BLAST (Position-Specific Iterative Basic Local Alignment Tool) was used to generate PSSM; the threshold of <italic>e</italic>-value is 0.001 and the maximum number of iterations is 3. PSSM-AC is calculated as the correlation between two residues within PSSM. This method can be represented as:</p>
<disp-formula id="S2.E6">
<label>(6)</label>
<mml:math id="M6">
<mml:mrow>
<mml:msub>
<mml:mi>P</mml:mi>
<mml:mrow>
<mml:mi>P</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>S</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>S</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>M</mml:mi>
</mml:mrow>
</mml:msub>
<mml:mo>=</mml:mo>
<mml:mrow>
<mml:mo>[</mml:mo>
<mml:mtable columnspacing="5pt" displaystyle="true" rowspacing="0pt">
<mml:mtr>
<mml:mtd columnalign="center">
<mml:msub>
<mml:mi>R</mml:mi>
<mml:mrow>
<mml:mn>1</mml:mn>
<mml:mo>,</mml:mo>
<mml:mn>1</mml:mn>
</mml:mrow>
</mml:msub>
</mml:mtd>
<mml:mtd columnalign="center">
<mml:msub>
<mml:mi>R</mml:mi>
<mml:mrow>
<mml:mn>1</mml:mn>
<mml:mo>,</mml:mo>
<mml:mn>2</mml:mn>
</mml:mrow>
</mml:msub>
</mml:mtd>
<mml:mtd columnalign="center">
<mml:mi mathvariant="normal">&#x2026;</mml:mi>
</mml:mtd>
<mml:mtd columnalign="center">
<mml:msub>
<mml:mi>R</mml:mi>
<mml:mrow>
<mml:mn>1</mml:mn>
<mml:mo>,</mml:mo>
<mml:mi>j</mml:mi>
</mml:mrow>
</mml:msub>
</mml:mtd>
<mml:mtd columnalign="center">
<mml:mi mathvariant="normal">&#x2026;</mml:mi>
</mml:mtd>
<mml:mtd columnalign="center">
<mml:msub>
<mml:mi>R</mml:mi>
<mml:mrow>
<mml:mn>1</mml:mn>
<mml:mo>,</mml:mo>
<mml:mn>20</mml:mn>
</mml:mrow>
</mml:msub>
</mml:mtd>
</mml:mtr>
<mml:mtr>
<mml:mtd columnalign="center">
<mml:msub>
<mml:mi>R</mml:mi>
<mml:mrow>
<mml:mn>2</mml:mn>
<mml:mo>,</mml:mo>
<mml:mn>1</mml:mn>
</mml:mrow>
</mml:msub>
</mml:mtd>
<mml:mtd columnalign="center">
<mml:msub>
<mml:mi>R</mml:mi>
<mml:mrow>
<mml:mn>2</mml:mn>
<mml:mo>,</mml:mo>
<mml:mn>2</mml:mn>
</mml:mrow>
</mml:msub>
</mml:mtd>
<mml:mtd columnalign="center">
<mml:mi mathvariant="normal">&#x2026;</mml:mi>
</mml:mtd>
<mml:mtd columnalign="center">
<mml:msub>
<mml:mi>R</mml:mi>
<mml:mrow>
<mml:mn>2</mml:mn>
<mml:mo>,</mml:mo>
<mml:mi>j</mml:mi>
</mml:mrow>
</mml:msub>
</mml:mtd>
<mml:mtd columnalign="center">
<mml:mi mathvariant="normal">&#x2026;</mml:mi>
</mml:mtd>
<mml:mtd columnalign="center">
<mml:msub>
<mml:mi>R</mml:mi>
<mml:mrow>
<mml:mn>2</mml:mn>
<mml:mo>,</mml:mo>
<mml:mn>20</mml:mn>
</mml:mrow>
</mml:msub>
</mml:mtd>
</mml:mtr>
<mml:mtr>
<mml:mtd columnalign="center">
<mml:mi mathvariant="normal">&#x22EE;</mml:mi>
</mml:mtd>
<mml:mtd columnalign="center">
<mml:mi mathvariant="normal">&#x22EE;</mml:mi>
</mml:mtd>
<mml:mtd columnalign="center">
<mml:mi mathvariant="normal">&#x22EE;</mml:mi>
</mml:mtd>
<mml:mtd columnalign="center">
<mml:mi mathvariant="normal">&#x22EE;</mml:mi>
</mml:mtd>
<mml:mtd columnalign="center">
<mml:mi mathvariant="normal">&#x22EE;</mml:mi>
</mml:mtd>
<mml:mtd columnalign="center">
<mml:mi mathvariant="normal">&#x22EE;</mml:mi>
</mml:mtd>
</mml:mtr>
<mml:mtr>
<mml:mtd columnalign="center">
<mml:msub>
<mml:mi>R</mml:mi>
<mml:mrow>
<mml:mi>i</mml:mi>
<mml:mo>,</mml:mo>
<mml:mn>1</mml:mn>
</mml:mrow>
</mml:msub>
</mml:mtd>
<mml:mtd columnalign="center">
<mml:msub>
<mml:mi>R</mml:mi>
<mml:mrow>
<mml:mi>i</mml:mi>
<mml:mo>,</mml:mo>
<mml:mn>2</mml:mn>
</mml:mrow>
</mml:msub>
</mml:mtd>
<mml:mtd columnalign="center">
<mml:mi mathvariant="normal">&#x2026;</mml:mi>
</mml:mtd>
<mml:mtd columnalign="center">
<mml:msub>
<mml:mi>R</mml:mi>
<mml:mrow>
<mml:mi>i</mml:mi>
<mml:mo>,</mml:mo>
<mml:mi>j</mml:mi>
</mml:mrow>
</mml:msub>
</mml:mtd>
<mml:mtd columnalign="center">
<mml:mi mathvariant="normal">&#x2026;</mml:mi>
</mml:mtd>
<mml:mtd columnalign="center">
<mml:msub>
<mml:mi>R</mml:mi>
<mml:mrow>
<mml:mi>i</mml:mi>
<mml:mo>,</mml:mo>
<mml:mn>20</mml:mn>
</mml:mrow>
</mml:msub>
</mml:mtd>
</mml:mtr>
<mml:mtr>
<mml:mtd columnalign="center">
<mml:mi mathvariant="normal">&#x22EE;</mml:mi>
</mml:mtd>
<mml:mtd columnalign="center">
<mml:mi mathvariant="normal">&#x22EE;</mml:mi>
</mml:mtd>
<mml:mtd columnalign="center">
<mml:mi mathvariant="normal">&#x22EE;</mml:mi>
</mml:mtd>
<mml:mtd columnalign="center">
<mml:mi mathvariant="normal">&#x22EE;</mml:mi>
</mml:mtd>
<mml:mtd columnalign="center">
<mml:mi mathvariant="normal">&#x22EE;</mml:mi>
</mml:mtd>
<mml:mtd columnalign="center">
<mml:mi mathvariant="normal">&#x22EE;</mml:mi>
</mml:mtd>
</mml:mtr>
<mml:mtr>
<mml:mtd columnalign="center">
<mml:msub>
<mml:mi>R</mml:mi>
<mml:mrow>
<mml:mi>L</mml:mi>
<mml:mo>,</mml:mo>
<mml:mn>1</mml:mn>
</mml:mrow>
</mml:msub>
</mml:mtd>
<mml:mtd columnalign="center">
<mml:msub>
<mml:mi>R</mml:mi>
<mml:mrow>
<mml:mi>L</mml:mi>
<mml:mo>,</mml:mo>
<mml:mn>2</mml:mn>
</mml:mrow>
</mml:msub>
</mml:mtd>
<mml:mtd columnalign="center">
<mml:mi mathvariant="normal">&#x2026;</mml:mi>
</mml:mtd>
<mml:mtd columnalign="center">
<mml:msub>
<mml:mi>R</mml:mi>
<mml:mrow>
<mml:mi>L</mml:mi>
<mml:mo>,</mml:mo>
<mml:mi>j</mml:mi>
</mml:mrow>
</mml:msub>
</mml:mtd>
<mml:mtd columnalign="center">
<mml:mi mathvariant="normal">&#x2026;</mml:mi>
</mml:mtd>
<mml:mtd columnalign="center">
<mml:msub>
<mml:mi>R</mml:mi>
<mml:mrow>
<mml:mi>L</mml:mi>
<mml:mo>,</mml:mo>
<mml:mn>20</mml:mn>
</mml:mrow>
</mml:msub>
</mml:mtd>
</mml:mtr>
</mml:mtable>
<mml:mo>]</mml:mo>
</mml:mrow>
</mml:mrow>
</mml:math>
</disp-formula>
<disp-formula id="S2.E7">
<label>(7)</label>
<mml:math id="M7">
<mml:mrow>
<mml:mrow>
<mml:msub>
<mml:mi>P</mml:mi>
<mml:mrow>
<mml:mi>P</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>S</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>S</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>M</mml:mi>
</mml:mrow>
</mml:msub>
<mml:mo>-</mml:mo>
<mml:mrow>
<mml:mi>A</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>C</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mi>j</mml:mi>
<mml:mo>,</mml:mo>
<mml:mi>lg</mml:mi>
<mml:mo>)</mml:mo>
</mml:mrow>
</mml:mrow>
</mml:mrow>
<mml:mo>=</mml:mo>
<mml:mrow>
<mml:mfrac>
<mml:mn>1</mml:mn>
<mml:mrow>
<mml:mi>L</mml:mi>
<mml:mo>-</mml:mo>
<mml:mi>lg</mml:mi>
</mml:mrow>
</mml:mfrac>
<mml:mo>&#x2062;</mml:mo>
<mml:mrow>
<mml:munderover>
<mml:mo largeop="true" movablelimits="false" symmetric="true">&#x2211;</mml:mo>
<mml:mrow>
<mml:mi>i</mml:mi>
<mml:mo>=</mml:mo>
<mml:mn>1</mml:mn>
</mml:mrow>
<mml:mrow>
<mml:mi>L</mml:mi>
<mml:mo>-</mml:mo>
<mml:mi>lg</mml:mi>
</mml:mrow>
</mml:munderover>
<mml:mrow>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mrow>
<mml:msub>
<mml:mi>R</mml:mi>
<mml:mrow>
<mml:mi>i</mml:mi>
<mml:mo>,</mml:mo>
<mml:mi>j</mml:mi>
</mml:mrow>
</mml:msub>
<mml:mo>-</mml:mo>
<mml:msub>
<mml:mover accent="true">
<mml:mi>R</mml:mi>
<mml:mo>&#x00AF;</mml:mo>
</mml:mover>
<mml:mi>j</mml:mi>
</mml:msub>
</mml:mrow>
<mml:mo>)</mml:mo>
</mml:mrow>
<mml:mo>&#x2062;</mml:mo>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mrow>
<mml:msub>
<mml:mi>R</mml:mi>
<mml:mrow>
<mml:mrow>
<mml:mi>i</mml:mi>
<mml:mo>+</mml:mo>
<mml:mi>lg</mml:mi>
</mml:mrow>
<mml:mo>,</mml:mo>
<mml:mi>j</mml:mi>
</mml:mrow>
</mml:msub>
<mml:mo>-</mml:mo>
<mml:msub>
<mml:mover accent="true">
<mml:mi>R</mml:mi>
<mml:mo>&#x00AF;</mml:mo>
</mml:mover>
<mml:mi>j</mml:mi>
</mml:msub>
</mml:mrow>
<mml:mo>)</mml:mo>
</mml:mrow>
</mml:mrow>
</mml:mrow>
</mml:mrow>
</mml:mrow>
</mml:math>
</disp-formula>
<disp-formula id="S2.E8">
<label>(8)</label>
<mml:math id="M9">
<mml:mrow>
<mml:msub>
<mml:mover accent="true">
<mml:mi>R</mml:mi>
<mml:mo>&#x00AF;</mml:mo>
</mml:mover>
<mml:mi>j</mml:mi>
</mml:msub>
<mml:mo>=</mml:mo>
<mml:mfrac>
<mml:mn>1</mml:mn>
<mml:mi>L</mml:mi>
</mml:mfrac>
<mml:munderover>
<mml:mo largeop="true" movablelimits="false" symmetric="true">&#x2211;</mml:mo>
<mml:mrow>
<mml:mi>i</mml:mi>
<mml:mo>=</mml:mo>
<mml:mn>1</mml:mn>
</mml:mrow>
<mml:mi>L</mml:mi>
</mml:munderover>
<mml:msub>
<mml:mi>R</mml:mi>
<mml:mrow>
<mml:mi>i</mml:mi>
<mml:mo>,</mml:mo>
<mml:mi>j</mml:mi>
</mml:mrow>
</mml:msub>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mi>j</mml:mi>
<mml:mo>=</mml:mo>
<mml:mn>1</mml:mn>
<mml:mo>,</mml:mo>
<mml:mi mathvariant="normal">&#x2026;</mml:mi>
<mml:mo>,</mml:mo>
<mml:mn>20</mml:mn>
<mml:mo>)</mml:mo>
</mml:mrow>
</mml:mrow>
</mml:math>
</disp-formula>
<p>Where <italic>R</italic><sub><italic>i,j</italic></sub> is the score of the residue of the i-th position mutated to the j-th amino acids residue in the protein sequence; a high score means a highly conserved position. L is the length of the protein sequence, <italic>lg</italic> is the distance along the sequence, and 0 &#x003C; <italic>lg</italic>&#x003C; L. As a result, the protein sequence generates a 20 &#x00D7; <italic>lg</italic> dimensional feature vector with PSSM-AC.</p>
</sec>
<sec id="S2.SS2.SSS4">
<title>Auto-Covariance Average Chemical Shift</title>
<p>As important parameters are measured by nuclear magnetic resonance (NMR) spectroscopy, the chemical shift has been used as a powerful indicator of the protein structure. Several researchers revealed that the average chemical shift (ACS) of a particular nucleus in the protein backbone empirically correlates to its secondary structure (<xref ref-type="bibr" rid="B38">Sibley et al., 2003</xref>). acACS was proposed by <xref ref-type="bibr" rid="B19">Fan et al. (2014)</xref>, In acACS, the secondary structure was converted into the average chemical shift, and then the auto-covariance function was used to construct the vector representing the protein sequence by selecting different. In this work, the secondary structure was obtained by submitting the protein sequence to PSIPRED<sup><xref ref-type="fn" rid="footnote1">1</xref></sup>, and then the protein sequence and the corresponding secondary structure were submitted to the acACS web server<sup><xref ref-type="fn" rid="footnote2">2</xref></sup>. It can be calculated as:</p>
<p>For a protein P, where each amino acid in the sequence is substituted by its averaged chemical shift, P can be expressed as:</p>
<disp-formula id="S2.E9">
<label>(9)</label>
<mml:math id="M10">
<mml:mrow>
<mml:mi>P</mml:mi>
<mml:mo>=</mml:mo>
<mml:mrow>
<mml:mo>[</mml:mo>
<mml:msubsup>
<mml:mi>A</mml:mi>
<mml:mn>1</mml:mn>
<mml:mi>i</mml:mi>
</mml:msubsup>
<mml:mo>,</mml:mo>
<mml:msubsup>
<mml:mi>A</mml:mi>
<mml:mn>2</mml:mn>
<mml:mi>i</mml:mi>
</mml:msubsup>
<mml:mo>,</mml:mo>
<mml:msubsup>
<mml:mi>A</mml:mi>
<mml:mn>3</mml:mn>
<mml:mi>i</mml:mi>
</mml:msubsup>
<mml:mo>,</mml:mo>
<mml:mi mathvariant="normal">&#x2026;</mml:mi>
<mml:mo>,</mml:mo>
<mml:msubsup>
<mml:mi>A</mml:mi>
<mml:mi>L</mml:mi>
<mml:mi>i</mml:mi>
</mml:msubsup>
<mml:mo>]</mml:mo>
</mml:mrow>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mi>i</mml:mi>
<mml:mo>=</mml:mo>
<mml:mmultiscripts>
<mml:mi>N</mml:mi>
<mml:mprescripts/>
<mml:none/>
<mml:mn>15</mml:mn>
</mml:mmultiscripts>
<mml:mo>,</mml:mo>
<mml:mmultiscripts>
<mml:mi>C</mml:mi>
<mml:mi mathvariant="normal">&#x03B1;</mml:mi>
<mml:none/>
<mml:mprescripts/>
<mml:none/>
<mml:mn>13</mml:mn>
</mml:mmultiscripts>
<mml:mo>,</mml:mo>
<mml:mmultiscripts>
<mml:mi>H</mml:mi>
<mml:mi mathvariant="normal">&#x03B1;</mml:mi>
<mml:none/>
<mml:mprescripts/>
<mml:none/>
<mml:mn>1</mml:mn>
</mml:mmultiscripts>
<mml:mo>,</mml:mo>
<mml:mmultiscripts>
<mml:mi>H</mml:mi>
<mml:mi>N</mml:mi>
<mml:none/>
<mml:mprescripts/>
<mml:none/>
<mml:mn>1</mml:mn>
</mml:mmultiscripts>
<mml:mo>)</mml:mo>
</mml:mrow>
</mml:mrow>
</mml:math>
</disp-formula>
<p>Where <sup>15</sup><italic>N</italic> stands for Nitrogen, <sup>13</sup><italic>C</italic><sub>&#x03B1;</sub> for alpha Carbon, <sup>1</sup><italic>H</italic><sub>&#x03B1;</sub> for alpha Hydrogen, and <sup>1</sup><italic>H</italic><sub><italic>N</italic></sub> for Hydrogen linked with Nitrogen.</p>
<p>After we select &#x03BB; = 17 and <inline-formula><mml:math id="INEQ5"><mml:mrow><mml:mi>i</mml:mi><mml:mo>=</mml:mo><mml:mrow><mml:mmultiscripts><mml:mi>N</mml:mi><mml:mprescripts/><mml:none/><mml:mn>15</mml:mn></mml:mmultiscripts><mml:mo>,</mml:mo><mml:mmultiscripts><mml:mi>C</mml:mi><mml:mi mathvariant="normal">&#x03B1;</mml:mi><mml:none/><mml:mprescripts/><mml:none/><mml:mn>13</mml:mn></mml:mmultiscripts><mml:mo>,</mml:mo><mml:mmultiscripts><mml:mi>H</mml:mi><mml:mi mathvariant="normal">&#x03B1;</mml:mi><mml:none/><mml:mprescripts/><mml:none/><mml:mn>1</mml:mn></mml:mmultiscripts><mml:mo>,</mml:mo><mml:mmultiscripts><mml:mi>H</mml:mi><mml:mprescripts/><mml:none/><mml:mn>1</mml:mn></mml:mmultiscripts></mml:mrow></mml:mrow></mml:math></inline-formula>, the acACS could be expressed as:</p>
<disp-formula id="S2.E10">
<label>(10)</label>
<mml:math id="M11">
<mml:mrow>
<mml:msubsup>
<mml:mi mathvariant="normal">&#x03C6;</mml:mi>
<mml:mi>i</mml:mi>
<mml:mi mathvariant="normal">&#x03BB;</mml:mi>
</mml:msubsup>
<mml:mo>=</mml:mo>
<mml:mfrac>
<mml:mn>1</mml:mn>
<mml:mrow>
<mml:mi>L</mml:mi>
<mml:mo>-</mml:mo>
<mml:mi mathvariant="normal">&#x03BB;</mml:mi>
</mml:mrow>
</mml:mfrac>
<mml:munderover>
<mml:mo largeop="true" movablelimits="false" symmetric="true">&#x2211;</mml:mo>
<mml:mrow>
<mml:mi>k</mml:mi>
<mml:mo>=</mml:mo>
<mml:mn>1</mml:mn>
</mml:mrow>
<mml:mrow>
<mml:mi>L</mml:mi>
<mml:mo>-</mml:mo>
<mml:mi mathvariant="normal">&#x03BB;</mml:mi>
</mml:mrow>
</mml:munderover>
<mml:mrow>
<mml:mo>[</mml:mo>
<mml:msubsup>
<mml:mi>A</mml:mi>
<mml:mi>k</mml:mi>
<mml:mi>i</mml:mi>
</mml:msubsup>
<mml:mo>-</mml:mo>
<mml:msubsup>
<mml:mi>A</mml:mi>
<mml:mrow>
<mml:mi>k</mml:mi>
<mml:mo>+</mml:mo>
<mml:mi mathvariant="normal">&#x03BB;</mml:mi>
</mml:mrow>
<mml:mi>i</mml:mi>
</mml:msubsup>
<mml:mo>]</mml:mo>
</mml:mrow>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mi>i</mml:mi>
<mml:mo>=</mml:mo>
<mml:mmultiscripts>
<mml:mi>N</mml:mi>
<mml:mprescripts/>
<mml:none/>
<mml:mn>15</mml:mn>
</mml:mmultiscripts>
<mml:mo>,</mml:mo>
<mml:mmultiscripts>
<mml:mi>C</mml:mi>
<mml:mi mathvariant="normal">&#x03B1;</mml:mi>
<mml:none/>
<mml:mprescripts/>
<mml:none/>
<mml:mn>13</mml:mn>
</mml:mmultiscripts>
<mml:mo>,</mml:mo>
<mml:mmultiscripts>
<mml:mi>H</mml:mi>
<mml:mi mathvariant="normal">&#x03B1;</mml:mi>
<mml:none/>
<mml:mprescripts/>
<mml:none/>
<mml:mn>1</mml:mn>
</mml:mmultiscripts>
<mml:mo>,</mml:mo>
<mml:mmultiscripts>
<mml:mi>H</mml:mi>
<mml:mi>N</mml:mi>
<mml:none/>
<mml:mprescripts/>
<mml:none/>
<mml:mn>1</mml:mn>
</mml:mmultiscripts>
<mml:mo>;</mml:mo>
<mml:mi mathvariant="normal">&#x03BB;</mml:mi>
<mml:mo>&lt;</mml:mo>
<mml:mi>L</mml:mi>
<mml:mo>)</mml:mo>
</mml:mrow>
</mml:mrow>
</mml:math>
</disp-formula>
<disp-formula id="S2.E11">
<label>(11)</label>
<mml:math id="M12">
<mml:mrow>
<mml:mi>P</mml:mi>
<mml:mo>=</mml:mo>
<mml:mrow>
<mml:mo>[</mml:mo>
<mml:msubsup>
<mml:mi mathvariant="normal">&#x03C6;</mml:mi>
<mml:mi>i</mml:mi>
<mml:mn>0</mml:mn>
</mml:msubsup>
<mml:mo>,</mml:mo>
<mml:msubsup>
<mml:mi mathvariant="normal">&#x03C6;</mml:mi>
<mml:mi>i</mml:mi>
<mml:mn>1</mml:mn>
</mml:msubsup>
<mml:mo>,</mml:mo>
<mml:msubsup>
<mml:mi mathvariant="normal">&#x03C6;</mml:mi>
<mml:mi>i</mml:mi>
<mml:mn>2</mml:mn>
</mml:msubsup>
<mml:mo>,</mml:mo>
<mml:mi mathvariant="normal">&#x2026;</mml:mi>
<mml:mo>,</mml:mo>
<mml:msubsup>
<mml:mi mathvariant="normal">&#x03C6;</mml:mi>
<mml:mi>i</mml:mi>
<mml:mi mathvariant="normal">&#x03BB;</mml:mi>
</mml:msubsup>
<mml:mo>]</mml:mo>
</mml:mrow>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mi>i</mml:mi>
<mml:mo>=</mml:mo>
<mml:mmultiscripts>
<mml:mi>N</mml:mi>
<mml:mprescripts/>
<mml:none/>
<mml:mn>15</mml:mn>
</mml:mmultiscripts>
<mml:mo>,</mml:mo>
<mml:mmultiscripts>
<mml:mi>C</mml:mi>
<mml:mi mathvariant="normal">&#x03B1;</mml:mi>
<mml:none/>
<mml:mprescripts/>
<mml:none/>
<mml:mn>13</mml:mn>
</mml:mmultiscripts>
<mml:mo>,</mml:mo>
<mml:mmultiscripts>
<mml:mi>H</mml:mi>
<mml:mi mathvariant="normal">&#x03B1;</mml:mi>
<mml:none/>
<mml:mprescripts/>
<mml:none/>
<mml:mn>1</mml:mn>
</mml:mmultiscripts>
<mml:mo>,</mml:mo>
<mml:mmultiscripts>
<mml:mi>H</mml:mi>
<mml:mi>N</mml:mi>
<mml:none/>
<mml:mprescripts/>
<mml:none/>
<mml:mn>1</mml:mn>
</mml:mmultiscripts>
<mml:mo>)</mml:mo>
</mml:mrow>
</mml:mrow>
</mml:math>
</disp-formula>
</sec>
</sec>
<sec id="S2.SS3">
<title>Synthetic Minority Over-Sampling Technique</title>
<p>The numbers of non-lyases are about 4.5 times that of lyases, and this leads to imbalanced data classification problems. In order to overcome this problem, we used SMOTE to solve the problem of imbalance. SMOTE is an over-sampling approach for imbalanced data classification (<xref ref-type="bibr" rid="B49">Wang et al., 2018a</xref>; <xref ref-type="bibr" rid="B61">Zhou et al., 2019</xref>). The algorithm of SMOTE is described as follows: (1) randomly choose the samples <italic>x</italic><sub><italic>i</italic></sub> from the minority class, and calculate the Euclidean distance to all other samples in this class, then K nearest neighbors of this sample were selected, (2) select <italic>x</italic><sub><italic>i</italic></sub> samples from the k nearest neighbors, and (3) generate a new sample <italic>x</italic><sub><italic>new</italic></sub> by: <italic>x</italic><sub><italic>n</italic><italic>e</italic><italic>w</italic></sub> = <italic>x</italic><sub><italic>i</italic></sub> + &#x03B1;(<italic>x</italic>&#x2212;<italic>x</italic><sub><italic>i</italic></sub>), &#x03B1; is a random number in (0, 1). In this paper, the protein numbers of lyases and non-lyases are in equilibrium with SMOTE.</p>
</sec>
<sec id="S2.SS4">
<title>Feature Selection</title>
<p>Redundant or irrelevant features will decrease the accuracy of prediction and increase computational time. In order to remove redundant or irrelevant features, a variety of feature selection techniques have been proposed: the analysis of variance (ANOVA) (<xref ref-type="bibr" rid="B40">Tan et al., 2018</xref>; <xref ref-type="bibr" rid="B32">Li et al., 2019</xref>; <xref ref-type="bibr" rid="B58">Zhang et al., 2020a</xref>), Max-Relevance-Max-Distance algorithms (MRMD) (<xref ref-type="bibr" rid="B64">Zou et al., 2016</xref>; <xref ref-type="bibr" rid="B45">Wan et al., 2017</xref>; <xref ref-type="bibr" rid="B36">Ru et al., 2019</xref>; <xref ref-type="bibr" rid="B28">Kwon et al., 2020</xref>), and Minimal-Redundancy-Maximal-Relevance (MRMR) (<xref ref-type="bibr" rid="B23">Jiao and Du, 2016</xref>; <xref ref-type="bibr" rid="B53">Xu et al., 2016</xref>; <xref ref-type="bibr" rid="B50">Wang et al., 2018b</xref>; <xref ref-type="bibr" rid="B26">Kabir et al., 2020</xref>) are the representative feature selection algorithms. In this study, we selected features using the F-score algorithm; the F-score algorithm was proposed by Yi-Wei (<xref ref-type="bibr" rid="B8">Chen and Lin, 2006</xref>). All features are ranked according to F-score values; a higher score indicates a higher likelihood that this feature is more discriminative (<xref ref-type="bibr" rid="B60">Zhang et al., 2020b</xref>). It can be calculated as:</p>
<disp-formula id="S2.E12">
<label>(12)</label>
<mml:math id="M13">
<mml:mrow>
<mml:msub>
<mml:mi>F</mml:mi>
<mml:mi>i</mml:mi>
</mml:msub>
<mml:mo>=</mml:mo>
<mml:mfrac>
<mml:mrow>
<mml:msup>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mrow>
<mml:msubsup>
<mml:mover accent="true">
<mml:mi>x</mml:mi>
<mml:mo stretchy="false">&#x00AF;</mml:mo>
</mml:mover>
<mml:mi>i</mml:mi>
<mml:mrow>
<mml:mo stretchy="false">(</mml:mo>
<mml:mo>+</mml:mo>
<mml:mo stretchy="false">)</mml:mo>
</mml:mrow>
</mml:msubsup>
<mml:mo>-</mml:mo>
<mml:msub>
<mml:mover accent="true">
<mml:mi>x</mml:mi>
<mml:mo stretchy="false">&#x00AF;</mml:mo>
</mml:mover>
<mml:mi>i</mml:mi>
</mml:msub>
</mml:mrow>
<mml:mo>)</mml:mo>
</mml:mrow>
<mml:mn>2</mml:mn>
</mml:msup>
<mml:mo>+</mml:mo>
<mml:msup>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mrow>
<mml:msubsup>
<mml:mover accent="true">
<mml:mi>x</mml:mi>
<mml:mo stretchy="false">&#x00AF;</mml:mo>
</mml:mover>
<mml:mi>i</mml:mi>
<mml:mrow>
<mml:mo stretchy="false">(</mml:mo>
<mml:mo>-</mml:mo>
<mml:mo stretchy="false">)</mml:mo>
</mml:mrow>
</mml:msubsup>
<mml:mo>-</mml:mo>
<mml:msub>
<mml:mover accent="true">
<mml:mi>x</mml:mi>
<mml:mo stretchy="false">&#x00AF;</mml:mo>
</mml:mover>
<mml:mi>i</mml:mi>
</mml:msub>
</mml:mrow>
<mml:mo>)</mml:mo>
</mml:mrow>
<mml:mn>2</mml:mn>
</mml:msup>
</mml:mrow>
<mml:mrow>
<mml:mrow>
<mml:msubsup>
<mml:mo largeop="true" symmetric="true">&#x2211;</mml:mo>
<mml:mrow>
<mml:mi>k</mml:mi>
<mml:mo>=</mml:mo>
<mml:mn>1</mml:mn>
</mml:mrow>
<mml:msup>
<mml:mi>n</mml:mi>
<mml:mo>+</mml:mo>
</mml:msup>
</mml:msubsup>
<mml:msup>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mrow>
<mml:msubsup>
<mml:mover accent="true">
<mml:mi>x</mml:mi>
<mml:mo stretchy="false">&#x00AF;</mml:mo>
</mml:mover>
<mml:mrow>
<mml:mi>k</mml:mi>
<mml:mo>,</mml:mo>
<mml:mi>i</mml:mi>
</mml:mrow>
<mml:mrow>
<mml:mo stretchy="false">(</mml:mo>
<mml:mo>+</mml:mo>
<mml:mo stretchy="false">)</mml:mo>
</mml:mrow>
</mml:msubsup>
<mml:mo>-</mml:mo>
<mml:msubsup>
<mml:mover accent="true">
<mml:mi>x</mml:mi>
<mml:mo stretchy="false">&#x00AF;</mml:mo>
</mml:mover>
<mml:mi>i</mml:mi>
<mml:mrow>
<mml:mo stretchy="false">(</mml:mo>
<mml:mo>+</mml:mo>
<mml:mo stretchy="false">)</mml:mo>
</mml:mrow>
</mml:msubsup>
</mml:mrow>
<mml:mo>)</mml:mo>
</mml:mrow>
<mml:mn>2</mml:mn>
</mml:msup>
</mml:mrow>
<mml:mo>+</mml:mo>
<mml:mrow>
<mml:mfrac>
<mml:mn>1</mml:mn>
<mml:mrow>
<mml:msup>
<mml:mi>n</mml:mi>
<mml:mo>-</mml:mo>
</mml:msup>
<mml:mo>-</mml:mo>
<mml:mn>1</mml:mn>
</mml:mrow>
</mml:mfrac>
<mml:mo>&#x2062;</mml:mo>
<mml:mrow>
<mml:msubsup>
<mml:mo largeop="true" symmetric="true">&#x2211;</mml:mo>
<mml:mrow>
<mml:mi>k</mml:mi>
<mml:mo>=</mml:mo>
<mml:mn>1</mml:mn>
</mml:mrow>
<mml:msup>
<mml:mi>n</mml:mi>
<mml:mo>-</mml:mo>
</mml:msup>
</mml:msubsup>
<mml:msup>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mrow>
<mml:msubsup>
<mml:mover accent="true">
<mml:mi>x</mml:mi>
<mml:mo stretchy="false">&#x00AF;</mml:mo>
</mml:mover>
<mml:mrow>
<mml:mi>k</mml:mi>
<mml:mo>,</mml:mo>
<mml:mi>i</mml:mi>
</mml:mrow>
<mml:mrow>
<mml:mo stretchy="false">(</mml:mo>
<mml:mo>-</mml:mo>
<mml:mo stretchy="false">)</mml:mo>
</mml:mrow>
</mml:msubsup>
<mml:mo>-</mml:mo>
<mml:msubsup>
<mml:mover accent="true">
<mml:mi>x</mml:mi>
<mml:mo stretchy="false">&#x00AF;</mml:mo>
</mml:mover>
<mml:mi>i</mml:mi>
<mml:mrow>
<mml:mo stretchy="false">(</mml:mo>
<mml:mo>-</mml:mo>
<mml:mo stretchy="false">)</mml:mo>
</mml:mrow>
</mml:msubsup>
</mml:mrow>
<mml:mo>)</mml:mo>
</mml:mrow>
<mml:mn>2</mml:mn>
</mml:msup>
</mml:mrow>
</mml:mrow>
</mml:mrow>
</mml:mfrac>
</mml:mrow>
</mml:math>
</disp-formula>
<p>Where <inline-formula><mml:math id="INEQ7"><mml:msub><mml:mover accent="true"><mml:mi>x</mml:mi><mml:mo stretchy="false">&#x00AF;</mml:mo></mml:mover><mml:mi>i</mml:mi></mml:msub></mml:math></inline-formula> is the average of the i-th feature of the whole sample, <inline-formula><mml:math id="INEQ8"><mml:msubsup><mml:mover accent="true"><mml:mi>x</mml:mi><mml:mo stretchy="false">&#x00AF;</mml:mo></mml:mover><mml:mi>i</mml:mi><mml:mrow><mml:mo stretchy="false">(</mml:mo><mml:mo>+</mml:mo><mml:mo stretchy="false">)</mml:mo></mml:mrow></mml:msubsup></mml:math></inline-formula> is the average of the i-th feature of the positive samples, <inline-formula><mml:math id="INEQ9"><mml:msubsup><mml:mover accent="true"><mml:mi>x</mml:mi><mml:mo stretchy="false">&#x00AF;</mml:mo></mml:mover><mml:mi>i</mml:mi><mml:mrow><mml:mo stretchy="false">(</mml:mo><mml:mo>-</mml:mo><mml:mo stretchy="false">)</mml:mo></mml:mrow></mml:msubsup></mml:math></inline-formula> is the average of the i-th feature of the negative samples; <italic>n</italic><sup>+</sup> is the total number of positive samples, <italic>n</italic><sup>&#x2212;</sup> is the total number of negative samples; <inline-formula><mml:math id="INEQ12"><mml:msubsup><mml:mover accent="true"><mml:mi>x</mml:mi><mml:mo stretchy="false">&#x00AF;</mml:mo></mml:mover><mml:mrow><mml:mi>k</mml:mi><mml:mo>,</mml:mo><mml:mi>i</mml:mi></mml:mrow><mml:mrow><mml:mo stretchy="false">(</mml:mo><mml:mo>+</mml:mo><mml:mo stretchy="false">)</mml:mo></mml:mrow></mml:msubsup></mml:math></inline-formula> is the average of the i-th feature of the k-th sample in the positive samples, and <inline-formula><mml:math id="INEQ13"><mml:msubsup><mml:mover accent="true"><mml:mi>x</mml:mi><mml:mo stretchy="false">&#x00AF;</mml:mo></mml:mover><mml:mrow><mml:mi>k</mml:mi><mml:mo>,</mml:mo><mml:mi>i</mml:mi></mml:mrow><mml:mrow><mml:mo stretchy="false">(</mml:mo><mml:mo>-</mml:mo><mml:mo stretchy="false">)</mml:mo></mml:mrow></mml:msubsup></mml:math></inline-formula> is the average of the i-th feature of the k-th sample in the negative samples.</p>
<p>To determine the optimal features, the incremental feature selection (IFS) (<xref ref-type="bibr" rid="B25">Ju and He, 2017</xref>; <xref ref-type="bibr" rid="B42">Tang et al., 2018</xref>) was employed based on the features ranked. The IFS procedure starts with one feature with the highest score, then adds features to the start feature based on their scores until all the features are added.</p>
</sec>
<sec id="S2.SS5">
<title>Support Vector Machine</title>
<p>The support vector machine was proposed by Vapnik; the basic idea of SVM is to transform the input data into a high-dimensional Hilbert space and then determine the optional separating hyperplane. SVM has been successfully applied in the field of computational biology and bioinformatics (<xref ref-type="bibr" rid="B18">Fan et al., 2013</xref>; <xref ref-type="bibr" rid="B31">Li and Wang, 2016</xref>; <xref ref-type="bibr" rid="B2">Arif et al., 2018</xref>; <xref ref-type="bibr" rid="B5">Chen et al., 2019</xref>; <xref ref-type="bibr" rid="B43">Tian et al., 2019</xref>; <xref ref-type="bibr" rid="B46">Wang et al., 2019a</xref>; <xref ref-type="bibr" rid="B17">Du et al., 2020</xref>; <xref ref-type="bibr" rid="B24">Jing and Li, 2020</xref>; <xref ref-type="bibr" rid="B55">Yang et al., 2020</xref>). Therefore, we used this classifier to build our model. The radial basis function (RBF) kernel was adopted to perform prediction. The regulation parameter c and kernel width parameter &#x03B3; were tuned via the grid search method. In this paper, the LibSVM package was used to predict cell wall lytic enzymes, which can be downloaded from <ext-link ext-link-type="uri" xlink:href="https://www.csie.ntu.edu.tw/~cjlin/libsvm">https://www.csie.ntu.edu.tw/~cjlin/libsvm</ext-link>.</p>
</sec>
<sec id="S2.SS6">
<title>Performance Evaluation</title>
<p>In statistical prediction, three cross-validation methods are commonly used to examine a predictor for its effectiveness in practical applications: k-fold cross-validation, independent dataset test, and jackknife test (<xref ref-type="bibr" rid="B30">Li and Li, 2008</xref>; <xref ref-type="bibr" rid="B41">Tan et al., 2019</xref>; <xref ref-type="bibr" rid="B12">Dao et al., 2020a</xref>,<xref ref-type="bibr" rid="B13">b</xref>). Among the three methods, the jackknife test is deemed the most objective and rigorous. Hence, the jackknife test was used to evaluate the performance of this paper.</p>
<p>In order to evaluate the predictive capability and reliability of our model, the sensitivity (Sn), specificity (Sp), Matthew&#x2019;s correlation coefficient (MCC), and accuracy (Acc) (<xref ref-type="bibr" rid="B4">Bustamam et al., 2019</xref>; <xref ref-type="bibr" rid="B9">Cheng, 2019</xref>; <xref ref-type="bibr" rid="B11">Cheng et al., 2019</xref>; <xref ref-type="bibr" rid="B20">Feng et al., 2019</xref>; <xref ref-type="bibr" rid="B34">Malebary et al., 2019</xref>; <xref ref-type="bibr" rid="B6">Chen et al., 2020</xref>; <xref ref-type="bibr" rid="B29">Li and Gao, 2020</xref>; <xref ref-type="bibr" rid="B51">Wang et al., 2020b</xref>) were measured and defined by:</p>
<disp-formula id="S2.E13">
<label>(13)</label>
<mml:math id="M14">
<mml:mrow>
<mml:msub>
<mml:mi>s</mml:mi>
<mml:mi>n</mml:mi>
</mml:msub>
<mml:mo>=</mml:mo>
<mml:mfrac>
<mml:mrow>
<mml:mi>T</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>P</mml:mi>
</mml:mrow>
<mml:mrow>
<mml:mrow>
<mml:mi>T</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>P</mml:mi>
</mml:mrow>
<mml:mo>+</mml:mo>
<mml:mrow>
<mml:mi>F</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>N</mml:mi>
</mml:mrow>
</mml:mrow>
</mml:mfrac>
</mml:mrow>
</mml:math>
</disp-formula>
<disp-formula id="S2.E14">
<label>(14)</label>
<mml:math id="M15">
<mml:mrow>
<mml:msub>
<mml:mi>s</mml:mi>
<mml:mi>p</mml:mi>
</mml:msub>
<mml:mo>=</mml:mo>
<mml:mfrac>
<mml:mrow>
<mml:mi>T</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>N</mml:mi>
</mml:mrow>
<mml:mrow>
<mml:mrow>
<mml:mi>T</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>N</mml:mi>
</mml:mrow>
<mml:mo>+</mml:mo>
<mml:mrow>
<mml:mi>F</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>N</mml:mi>
</mml:mrow>
</mml:mrow>
</mml:mfrac>
</mml:mrow>
</mml:math>
</disp-formula>
<disp-formula id="S2.E15">
<label>(15)</label>
<mml:math id="M16">
<mml:mrow>
<mml:mrow>
<mml:mi>M</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>C</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>C</mml:mi>
</mml:mrow>
<mml:mo>=</mml:mo>
<mml:mfrac>
<mml:mrow>
<mml:mrow>
<mml:mi>T</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>P</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mtext>&#x00D7;</mml:mtext>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>T</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>N</mml:mi>
</mml:mrow>
<mml:mo>-</mml:mo>
<mml:mrow>
<mml:mi>F</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>P</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mtext>&#x00D7;</mml:mtext>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>F</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>N</mml:mi>
</mml:mrow>
</mml:mrow>
<mml:msqrt>
<mml:mrow>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mrow>
<mml:mrow>
<mml:mi>T</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>P</mml:mi>
</mml:mrow>
<mml:mo>+</mml:mo>
<mml:mrow>
<mml:mi>F</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>P</mml:mi>
</mml:mrow>
</mml:mrow>
<mml:mo>)</mml:mo>
</mml:mrow>
<mml:mo>&#x2062;</mml:mo>
<mml:mtext>&#x00D7;</mml:mtext>
<mml:mo>&#x2062;</mml:mo>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mrow>
<mml:mrow>
<mml:mi>T</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>N</mml:mi>
</mml:mrow>
<mml:mo>+</mml:mo>
<mml:mrow>
<mml:mi>F</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>N</mml:mi>
</mml:mrow>
</mml:mrow>
<mml:mo>)</mml:mo>
</mml:mrow>
<mml:mo>&#x2062;</mml:mo>
<mml:mtext>&#x00D7;</mml:mtext>
<mml:mo>&#x2062;</mml:mo>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mrow>
<mml:mrow>
<mml:mi>T</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>P</mml:mi>
</mml:mrow>
<mml:mo>+</mml:mo>
<mml:mrow>
<mml:mi>F</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>N</mml:mi>
</mml:mrow>
</mml:mrow>
<mml:mo>)</mml:mo>
</mml:mrow>
<mml:mo>&#x2062;</mml:mo>
<mml:mtext>&#x00D7;</mml:mtext>
<mml:mo>&#x2062;</mml:mo>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mrow>
<mml:mrow>
<mml:mi>T</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>N</mml:mi>
</mml:mrow>
<mml:mo>+</mml:mo>
<mml:mrow>
<mml:mi>F</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>P</mml:mi>
</mml:mrow>
</mml:mrow>
<mml:mo>)</mml:mo>
</mml:mrow>
</mml:mrow>
</mml:msqrt>
</mml:mfrac>
</mml:mrow>
</mml:math>
</disp-formula>
<disp-formula id="S2.E16">
<label>(16)</label>
<mml:math id="M17">
<mml:mrow>
<mml:mrow>
<mml:mi>A</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>c</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>c</mml:mi>
</mml:mrow>
<mml:mo>=</mml:mo>
<mml:mfrac>
<mml:mrow>
<mml:mrow>
<mml:mi>T</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>P</mml:mi>
</mml:mrow>
<mml:mo>+</mml:mo>
<mml:mrow>
<mml:mi>T</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>N</mml:mi>
</mml:mrow>
</mml:mrow>
<mml:mrow>
<mml:mrow>
<mml:mi>T</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>P</mml:mi>
</mml:mrow>
<mml:mo>+</mml:mo>
<mml:mrow>
<mml:mi>T</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>N</mml:mi>
</mml:mrow>
<mml:mo>+</mml:mo>
<mml:mrow>
<mml:mi>F</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>P</mml:mi>
</mml:mrow>
<mml:mo>+</mml:mo>
<mml:mrow>
<mml:mi>F</mml:mi>
<mml:mo>&#x2062;</mml:mo>
<mml:mi>N</mml:mi>
</mml:mrow>
</mml:mrow>
</mml:mfrac>
</mml:mrow>
</mml:math>
</disp-formula>
<p>Where TP represents the true positive, TN represents the true negative, FP represents the false positive, and FN represents the false negative.</p>
</sec>
</sec>
<sec id="S3">
<title>Results and Discussion</title>
<sec id="S3.SS1">
<title>The Choice of Our Model Parameters lg, and Combination Schemes of Chemical Shifts</title>
<p>In order to investigate the effectiveness of the predictive model, the AAC, the DC, PSSM-AC, and the auto-covariance, average chemical shift was selected to predict the cell wall lytic enzymes. Furthermore, for the sake of the best performance of predicting cell wall lytic enzyme, the lg of the distance was selected, with results in <xref ref-type="fig" rid="F1">Figure 1</xref>, and the best lg was 28 when the accuracy was the highest. In addition, the combination mode of chemically shifted atoms and the best parameter &#x03BB; were selected. <xref ref-type="fig" rid="F2">Figure 2</xref> shows that the best parameter &#x03BB; was 17. The results of combination mode of chemically shifted atoms were shown in <xref ref-type="fig" rid="F3">Figure 3</xref>; the best combination mode of chemically shifted atoms was <inline-formula><mml:math id="INEQ19"><mml:mrow><mml:mrow><mml:msup><mml:mi/><mml:mn>15</mml:mn></mml:msup><mml:mo>&#x2062;</mml:mo><mml:mi>N</mml:mi></mml:mrow><mml:mo>,</mml:mo><mml:mmultiscripts><mml:mi>C</mml:mi><mml:mi mathvariant="normal">&#x03B1;</mml:mi><mml:none/><mml:mprescripts/><mml:none/><mml:mn>13</mml:mn></mml:mmultiscripts><mml:mo>,</mml:mo><mml:mmultiscripts><mml:mi>H</mml:mi><mml:mi mathvariant="normal">&#x03B1;</mml:mi><mml:none/><mml:mprescripts/><mml:none/><mml:mn>1</mml:mn></mml:mmultiscripts><mml:mo>,</mml:mo><mml:mmultiscripts><mml:mi>H</mml:mi><mml:mprescripts/><mml:none/><mml:mn>1</mml:mn></mml:mmultiscripts></mml:mrow></mml:math></inline-formula> when the accuracy was the highest.</p>
<fig id="F1" position="float">
<label>FIGURE 1</label>
<caption><p>The Acc of position-specific score matrix auto-covariance (PSSM-AC) with different <italic>lg</italic>.</p></caption>
<graphic xlink:href="fbioe-08-627335-g001.tif"/>
</fig>
<fig id="F2" position="float">
<label>FIGURE 2</label>
<caption><p>The Acc with respect to the correlation factor <italic>&#x03BB;</italic> of the combination mode of chemically shifted atoms <inline-formula><mml:math id="INEQ14"><mml:mrow><mml:mrow><mml:msup><mml:mi/><mml:mn>15</mml:mn></mml:msup><mml:mo>&#x2062;</mml:mo><mml:mi>N</mml:mi></mml:mrow><mml:mo>,</mml:mo><mml:mmultiscripts><mml:mi>C</mml:mi><mml:mi mathvariant="normal">&#x03B1;</mml:mi><mml:none/><mml:mprescripts/><mml:none/><mml:mn>13</mml:mn></mml:mmultiscripts><mml:mo>,</mml:mo><mml:mmultiscripts><mml:mi>H</mml:mi><mml:mi mathvariant="normal">&#x03B1;</mml:mi><mml:none/><mml:mprescripts/><mml:none/><mml:mn>1</mml:mn></mml:mmultiscripts><mml:mo>,</mml:mo><mml:mmultiscripts><mml:mi>H</mml:mi><mml:mprescripts/><mml:none/><mml:mn>1</mml:mn></mml:mmultiscripts></mml:mrow></mml:math></inline-formula>.</p></caption>
<graphic xlink:href="fbioe-08-627335-g002.tif"/>
</fig>
<fig id="F3" position="float">
<label>FIGURE 3</label>
<caption><p>The Acc of different combination schemes of chemical shifts. Numbers denote the chemical shifts of atoms: 1 denotes <sup>15</sup><italic>N</italic>, 2 denotes <sup>13</sup><italic>C</italic><sub>&#x03B1;</sub>, 3 denotes <sup>1</sup><italic>H</italic><sub>&#x03B1;</sub>, 4 denotes <sup>1</sup><italic>H</italic><sub><italic>N</italic></sub>.</p></caption>
<graphic xlink:href="fbioe-08-627335-g003.tif"/>
</fig>
</sec>
<sec id="S3.SS2">
<title>The Predictive Performance of Cell Wall Lytic Enzymes</title>
<p>The predictive performance of cell wall lytic enzymes by using the SVM classification algorithm with SMOTE was listed in <xref ref-type="table" rid="T1">Table 1</xref>. The highest sensitivity (Sn), specificity (Sp), Matthew&#x2019;s correlation coefficient (MCC), and accuracy (Acc) of individual parameters were 72.06%, 99.67%, 0.81, and 94.40% with jackknife test by using PSSM-AC. By comparison, the result of acACS was better than AAC and DC; this is probably due to the fact that acACS considers the protein secondary structure information. The sensitivity (Sn), Matthew&#x2019;s correlation coefficient (MCC), and accuracy (Acc) of AAC were all higher than DC, because DC displays redundant or irrelevant features, so we used &#x201C;F-score&#x201D; to select the feature. As shown in <xref ref-type="fig" rid="F4">Figure 4</xref>, the closer the color is to red, the higher the F-score of adjacent amino acid residue and the easier it is to distinguish. On the contrary, the closer the color is to blue, the harder it is to distinguish. It can be seen that DC has some redundant information; this redundant information will reduce the prediction success rate. <xref ref-type="fig" rid="F5">Figure 5</xref> showed the Acc of DC based on the incremental feature selection (IFS). The peak (the maximum accuracy) can be found in this curve, and it was 90.93% with 245D features. <xref ref-type="fig" rid="F6">Figure 6</xref> showed the comparison of DC with feature selection and non-feature selection; we can see that feature selection was successfully applied to remove the irrelevant and redundant features. The Sn, MCC, and Acc were improved remarkably; Acc increased from 86.67 to 90.93%, Sn increased from 38.24 to 60.29%, and the results indicate that feature selection was helpful to enhance the predictive performance. The predictive results of different combined features with SVM without SMOTE were displayed in <xref ref-type="fig" rid="F7">Figure 7</xref>. From <xref ref-type="fig" rid="F7">Figure 7</xref> we can see the combined feature AAC+DC+acACS+PSSM-AC was better than other parameters. The accuracy (Acc) of combined feature AAC+DC+acACS+PSSM-AC was 95.20% with the jackknife test. This result indicates that the combined feature was powerful in the prediction of cell wall lytic enzymes.</p>
<table-wrap position="float" id="T1">
<label>TABLE 1</label>
<caption><p>The predictive results of individual features with jackknife test by using SVM.</p></caption>
<table cellspacing="5" cellpadding="5" frame="hsides" rules="groups">
<thead>
<tr>
<td valign="top" align="left"><bold>Features</bold></td>
<td valign="top" align="center"><bold>Sn (%)</bold></td>
<td valign="top" align="center"><bold>Sp (%)</bold></td>
<td valign="top" align="center"><bold>MCC</bold></td>
<td valign="top" align="center"><bold>Acc (%)</bold></td>
</tr>
</thead>
<tbody>
<tr>
<td valign="top" align="left">AAC</td>
<td valign="top" align="center">47.06</td>
<td valign="top" align="center">95.77</td>
<td valign="top" align="center">0.51</td>
<td valign="top" align="center">86.93</td>
</tr>
<tr>
<td valign="top" align="left">DC</td>
<td valign="top" align="center">38.24</td>
<td valign="top" align="center">97.39</td>
<td valign="top" align="center">0.48</td>
<td valign="top" align="center">86.67</td>
</tr>
<tr>
<td valign="top" align="left">PSSM-AC</td>
<td valign="top" align="center">72.06</td>
<td valign="top" align="center">99.67</td>
<td valign="top" align="center">0.81</td>
<td valign="top" align="center">94.40</td>
</tr>
<tr>
<td valign="top" align="left">acACS</td>
<td valign="top" align="center">57.35</td>
<td valign="top" align="center">93.81</td>
<td valign="top" align="center">0.55</td>
<td valign="top" align="center">87.20</td>
</tr>
</tbody>
</table>
</table-wrap>
<fig id="F4" position="float">
<label>FIGURE 4</label>
<caption><p>Three-dimensional heat map of DC&#x2019;s F-score value.</p></caption>
<graphic xlink:href="fbioe-08-627335-g004.tif"/>
</fig>
<fig id="F5" position="float">
<label>FIGURE 5</label>
<caption><p>The Acc of dipeptide composition (DC) with the incremental feature selection.</p></caption>
<graphic xlink:href="fbioe-08-627335-g005.tif"/>
</fig>
<fig id="F6" position="float">
<label>FIGURE 6</label>
<caption><p>The Acc of DC with feature selection and non-feature selection.</p></caption>
<graphic xlink:href="fbioe-08-627335-g006.tif"/>
</fig>
<fig id="F7" position="float">
<label>FIGURE 7</label>
<caption><p>Prediction results of different combined features. Letters denote features: a for AAC, b for DC, c for acACS, d for PSSM-AC.</p></caption>
<graphic xlink:href="fbioe-08-627335-g007.tif"/>
</fig>
</sec>
<sec id="S3.SS3">
<title>Comparison With Different Classifiers</title>
<p>In order to display the power of our predictive model, our predictive model [Support Vector Machine (SVM)], Random Forest (RF), K-Nearest Neighbors (KNN), and Naive Bayes (NB) were used to predict cell wall lytic enzymes. The predictive performance of SVM, RF, KNN, and NB were listed in <xref ref-type="table" rid="T2">Table 2</xref>. From <xref ref-type="table" rid="T2">Table 2</xref>, we can see the predictive performance of SVM, RF, KNN, and NB with SMOTE were superior to those without SMOTE. The Acc of SVM, RF, KNN, and NB increased by 3.99, 3.89, 9.37, and 10.38% when using SMOTE; the MCC of SVM, RF, KNN, and NB increased by 0.15, 0.37, 0.37, and 0.21 when using SMOTE. In addition, the Sn, Sp, MCC, and Acc of SVM reached 99.35%, 99.02%, 0.98, and 99.19% by using SMOTE. The experimental results show that SVM was useful for improving the predictive performance of cell wall lytic enzymes.</p>
<table-wrap position="float" id="T2">
<label>TABLE 2</label>
<caption><p>The predictive results of combined feature AAC+DC+acACS+PSSM-AC by using different algorithms with and without SMOTE.</p></caption>
<table cellspacing="5" cellpadding="5" frame="hsides" rules="groups">
<thead>
<tr>
<td valign="top" align="left"><bold>Algorithms</bold></td>
<td valign="top" align="left"><bold>SMOTE (N/Y)</bold></td>
<td valign="top" align="center"><bold>Sn (%)</bold></td>
<td valign="top" align="center"><bold>Sp (%)</bold></td>
<td valign="top" align="center"><bold>MCC</bold></td>
<td valign="top" align="center"><bold>Acc (%)</bold></td>
</tr>
</thead>
<tbody>
<tr>
<td valign="top" align="left">SVM</td>
<td valign="top" align="left">N</td>
<td valign="top" align="center">75.00</td>
<td valign="top" align="center">99.67</td>
<td valign="top" align="center">0.83</td>
<td valign="top" align="center">95.20</td>
</tr>
<tr>
<td valign="top" align="left">RF</td>
<td/>
<td valign="top" align="center">41.18</td>
<td valign="top" align="center">85.99</td>
<td valign="top" align="center">0.27</td>
<td valign="top" align="center">77.87</td>
</tr>
<tr>
<td valign="top" align="left">KNN</td>
<td/>
<td valign="top" align="center">66.18</td>
<td valign="top" align="center">80.13</td>
<td valign="top" align="center">0.40</td>
<td valign="top" align="center">77.60</td>
</tr>
<tr>
<td valign="top" align="left">NB</td>
<td/>
<td valign="top" align="center">86.76</td>
<td valign="top" align="center">66.78</td>
<td valign="top" align="center">0.42</td>
<td valign="top" align="center">70.40</td>
</tr>
<tr>
<td valign="top" align="left">SVM</td>
<td valign="top" align="left">Y</td>
<td valign="top" align="center">99.35</td>
<td valign="top" align="center">99.02</td>
<td valign="top" align="center">0.98</td>
<td valign="top" align="center">99.19</td>
</tr>
<tr>
<td valign="top" align="left">RF</td>
<td/>
<td valign="top" align="center">85.99</td>
<td valign="top" align="center">77.52</td>
<td valign="top" align="center">0.64</td>
<td valign="top" align="center">81.76</td>
</tr>
<tr>
<td valign="top" align="left">KNN</td>
<td/>
<td valign="top" align="center">100.00</td>
<td valign="top" align="center">73.94</td>
<td valign="top" align="center">0.77</td>
<td valign="top" align="center">86.97</td>
</tr>
<tr>
<td valign="top" align="left">NB</td>
<td/>
<td valign="top" align="center">92.18</td>
<td valign="top" align="center">69.38</td>
<td valign="top" align="center">0.63</td>
<td valign="top" align="center">80.78</td>
</tr>
</tbody>
</table>
</table-wrap>
</sec>
<sec id="S3.SS4">
<title>Comparison With Existing Methods</title>
<p>To further investigate the effectiveness of our predictive model, we compared it with existing methods with the same dataset. The comparison results were listed in <xref ref-type="table" rid="T3">Table 3</xref>. From <xref ref-type="table" rid="T3">Table 3</xref>, we can see that the predictive results of cell wall lytic enzymes in our predictive model were better than those of the other methods. Furthermore, the Sn, Sp, MCC, and Acc in our predictive model reached 99.35%, 99.02%, 0.98, and 99.19%, which were 32.65%, 10.42%, 0.407, and 18.79% higher than the <xref ref-type="bibr" rid="B15">Ding et al. (2009)</xref> method, 22.88%, 5.86%, 0.302, and 7.89% higher than Lypred, and 14.05%, 1.32%, 0.135, and 3.69% higher than CWLy-SVM. These results indicate that our predictive model was superior to existing methods.</p>
<table-wrap position="float" id="T3">
<label>TABLE 3</label>
<caption><p>The comparison of the predictive results between this paper and existing methods.</p></caption>
<table cellspacing="5" cellpadding="5" frame="hsides" rules="groups">
<thead>
<tr>
<td valign="top" align="left"><bold>Method</bold></td>
<td valign="top" align="center"><bold>Sn (%)</bold></td>
<td valign="top" align="center"><bold>Sp (%)</bold></td>
<td valign="top" align="center"><bold>MCC</bold></td>
<td valign="top" align="center"><bold>Acc (%)</bold></td>
</tr>
</thead>
<tbody>
<tr>
<td valign="top" align="left">Ding et al.</td>
<td valign="top" align="center">66.70</td>
<td valign="top" align="center">88.60</td>
<td valign="top" align="center">0.573</td>
<td valign="top" align="center">80.40</td>
</tr>
<tr>
<td valign="top" align="left">Lypred</td>
<td valign="top" align="center">76.47</td>
<td valign="top" align="center">93.16</td>
<td valign="top" align="center">0.678</td>
<td valign="top" align="center">91.30</td>
</tr>
<tr>
<td valign="top" align="left">CWLy-SVM</td>
<td valign="top" align="center">85.30</td>
<td valign="top" align="center">97.70</td>
<td valign="top" align="center">0.845</td>
<td valign="top" align="center">95.50</td>
</tr>
<tr>
<td valign="top" align="left">Our predictive model</td>
<td valign="top" align="center">99.35</td>
<td valign="top" align="center">99.02</td>
<td valign="top" align="center">0.98</td>
<td valign="top" align="center">99.19</td>
</tr>
</tbody>
</table>
</table-wrap>
</sec>
</sec>
<sec id="S4">
<title>Conclusion</title>
<p>With the rapid rise of antibiotic-resistant strains, cell wall lytic enzymes used to destroy bacteria is a viable alternative method to avoid the crisis of antimicrobial resistance. In this work, a reliable and effective computational method was developed to identify the cell wall lytic enzymes. This model was derived from the SVM machine learning algorithm; SMOTE was used to counter the imbalanced data classification problems, and the F-score algorithm was used to remove redundant or irrelevant features. A series of experiments demonstrated that the proposed method is powerful. This method has good capability for distinguishing lyases.</p>
</sec>
<sec id="S5">
<title>Data Availability Statement</title>
<p>Publicly available datasets were analyzed in this study. This data can be found here: <ext-link ext-link-type="uri" xlink:href="http://lin-group.cn/server/Lypred/data.html">http://lin-group.cn/server/Lypred/data.html</ext-link>.</p>
</sec>
<sec id="S6">
<title>Author Contributions</title>
<p>F-ML conceived the selection of feature parameters and performed the results analysis. X-YJ carried out the computation and wrote the manuscript. Both authors reviewed the manuscript.</p>
</sec>
<sec sec-type="COI-statement" id="conf1">
<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>
</body>
<back>
<fn-group>
<fn fn-type="financial-disclosure">
<p><bold>Funding.</bold> This work was supported by the Natural Science Foundation of the Inner Mongolia of China (2019MS03015) and the National Natural Science Foundation of China (31360206).</p>
</fn>
</fn-group>
<ref-list>
<title>References</title>
<ref id="B1"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Ajuebor</surname> <given-names>J.</given-names></name> <name><surname>McAuliffe</surname> <given-names>O.</given-names></name> <name><surname>O&#x2019;Mahony</surname> <given-names>J.</given-names></name> <name><surname>Ross</surname> <given-names>R. P.</given-names></name> <name><surname>Hill</surname> <given-names>C.</given-names></name> <name><surname>Coffey</surname> <given-names>A.</given-names></name></person-group> (<year>2016</year>). <article-title>Bacteriophage endolysins and their applications.</article-title> <source><italic>Sci. Prog.</italic></source> <volume>99</volume> <fpage>183</fpage>&#x2013;<lpage>199</lpage>. <pub-id pub-id-type="doi">10.3184/003685016x14627913637705</pub-id> <pub-id pub-id-type="pmid">28742472</pub-id></citation></ref>
<ref id="B2"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Arif</surname> <given-names>M.</given-names></name> <name><surname>Hayat</surname> <given-names>M.</given-names></name> <name><surname>Jan</surname> <given-names>Z.</given-names></name></person-group> (<year>2018</year>). <article-title>iMem-2LSAAC: a two-level model for discrimination of membrane proteins and their types by extending the notion of SAAC into chou&#x2019;s pseudo amino acid composition.</article-title> <source><italic>J. Theor. Biol.</italic></source> <volume>442</volume> <fpage>11</fpage>&#x2013;<lpage>21</lpage>. <pub-id pub-id-type="doi">10.1016/j.jtbi.2018.01.008</pub-id> <pub-id pub-id-type="pmid">29337263</pub-id></citation></ref>
<ref id="B3"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Bhagwat</surname> <given-names>A.</given-names></name> <name><surname>Collins</surname> <given-names>C. H.</given-names></name> <name><surname>Dordick</surname> <given-names>J. S.</given-names></name></person-group> (<year>2019</year>). <article-title>Selective antimicrobial activity of cell lytic enzymes in a bacterial consortium.</article-title> <source><italic>Appl. Microbiol. Biotechnol.</italic></source> <volume>103</volume> <fpage>7041</fpage>&#x2013;<lpage>7054</lpage>. <pub-id pub-id-type="doi">10.1007/s00253-019-09955-0</pub-id> <pub-id pub-id-type="pmid">31203418</pub-id></citation></ref>
<ref id="B4"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Bustamam</surname> <given-names>A.</given-names></name> <name><surname>Musti</surname> <given-names>M. I. S.</given-names></name> <name><surname>Hartomo</surname> <given-names>S.</given-names></name> <name><surname>Aprilia</surname> <given-names>S.</given-names></name> <name><surname>Tampubolon</surname> <given-names>P. P.</given-names></name> <name><surname>Lestari</surname> <given-names>D.</given-names></name></person-group> (<year>2019</year>). <article-title>Performance of rotation forest ensemble classifier and feature extractor in predicting protein interactions using amino acid sequences.</article-title> <source><italic>BMC Genomics</italic></source> <volume>20</volume>:<issue>950</issue>. <pub-id pub-id-type="doi">10.1186/s12864-019-6304-y</pub-id> <pub-id pub-id-type="pmid">31874636</pub-id></citation></ref>
<ref id="B5"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Chen</surname> <given-names>J.</given-names></name> <name><surname>Zhao</surname> <given-names>J.</given-names></name> <name><surname>Yang</surname> <given-names>S.</given-names></name> <name><surname>Chen</surname> <given-names>Z.</given-names></name> <name><surname>Zhang</surname> <given-names>Z.</given-names></name></person-group> (<year>2019</year>). <article-title>Prediction of protein ubiquitination sites in <italic>Arabidopsis thaliana</italic>.</article-title> <source><italic>Curr. Bioinform.</italic></source> <volume>14</volume> <fpage>614</fpage>&#x2013;<lpage>620</lpage>. <pub-id pub-id-type="doi">10.2174/1574893614666190311141647</pub-id></citation></ref>
<ref id="B6"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Chen</surname> <given-names>W.</given-names></name> <name><surname>Feng</surname> <given-names>P.</given-names></name> <name><surname>Nie</surname> <given-names>F.</given-names></name></person-group> (<year>2020</year>). <article-title>iATP: a sequence based method for identifying anti-tubercular peptides.</article-title> <source><italic>Med. Chem.</italic></source> <volume>16</volume> <fpage>620</fpage>&#x2013;<lpage>625</lpage>. <pub-id pub-id-type="doi">10.2174/1573406415666191002152441</pub-id> <pub-id pub-id-type="pmid">31339073</pub-id></citation></ref>
<ref id="B7"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Chen</surname> <given-names>X.</given-names></name> <name><surname>Tang</surname> <given-names>H.</given-names></name> <name><surname>Li</surname> <given-names>W.</given-names></name> <name><surname>Wu</surname> <given-names>H.</given-names></name> <name><surname>Chen</surname> <given-names>W.</given-names></name> <name><surname>Ding</surname> <given-names>H.</given-names></name><etal/></person-group> (<year>2016</year>). <article-title>Identification of bacterial cell wall lyases via pseudo amino acid composition.</article-title> <source><italic>Biomed. Res. Int.</italic></source> <volume>2016</volume> <fpage>1654623</fpage>&#x2013;<lpage>1654623</lpage>. <pub-id pub-id-type="doi">10.1155/2016/1654623</pub-id> <pub-id pub-id-type="pmid">27437396</pub-id></citation></ref>
<ref id="B8"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Chen</surname> <given-names>Y. W.</given-names></name> <name><surname>Lin</surname> <given-names>C. J.</given-names></name></person-group> (<year>2006</year>). &#x201C;<article-title>Combining SVMs with various feature selection strategies</article-title>,&#x201D; in <source><italic>Feature Extraction. Studies in Fuzziness and Soft Computing</italic></source>, <volume>Vol. 207</volume> <role>eds</role> <person-group person-group-type="editor"><name><surname>Guyon</surname> <given-names>I.</given-names></name> <name><surname>Nikravesh</surname> <given-names>M.</given-names></name> <name><surname>Gunn</surname> <given-names>S.</given-names></name> <name><surname>Zadeh</surname> <given-names>L. A.</given-names></name></person-group> (<publisher-loc>Berlin</publisher-loc>: <publisher-name>Springer</publisher-name>).</citation></ref>
<ref id="B9"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Cheng</surname> <given-names>L.</given-names></name></person-group> (<year>2019</year>). <article-title>Computational and biological methods for gene therapy.</article-title> <source><italic>Curr. Gene Ther.</italic></source> <volume>19</volume>:<issue>210</issue>. <pub-id pub-id-type="doi">10.2174/156652321904191022113307</pub-id> <pub-id pub-id-type="pmid">31762421</pub-id></citation></ref>
<ref id="B10"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Cheng</surname> <given-names>L.</given-names></name> <name><surname>Qi</surname> <given-names>C.</given-names></name> <name><surname>Zhuang</surname> <given-names>H.</given-names></name> <name><surname>Fu</surname> <given-names>T.</given-names></name> <name><surname>Zhang</surname> <given-names>X.</given-names></name></person-group> (<year>2020</year>). <article-title>gutMDisorder: a comprehensive database for dysbiosis of the gut microbiota in disorders and interventions.</article-title> <source><italic>Nucleic Acids Res.</italic></source> <volume>48</volume> <fpage>D554</fpage>&#x2013;<lpage>D560</lpage>. <pub-id pub-id-type="doi">10.1093/nar/gkz843</pub-id> <pub-id pub-id-type="pmid">31584099</pub-id></citation></ref>
<ref id="B11"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Cheng</surname> <given-names>L.</given-names></name> <name><surname>Zhao</surname> <given-names>H.</given-names></name> <name><surname>Wang</surname> <given-names>P.</given-names></name> <name><surname>Zhou</surname> <given-names>W.</given-names></name> <name><surname>Luo</surname> <given-names>M.</given-names></name> <name><surname>Li</surname> <given-names>T.</given-names></name><etal/></person-group> (<year>2019</year>). <article-title>Computational Methods for Identifying Similar Diseases.</article-title> <source><italic>Mol. Ther. Nucleic Acids</italic></source> <volume>18</volume> <fpage>590</fpage>&#x2013;<lpage>604</lpage>. <pub-id pub-id-type="doi">10.1016/j.omtn.2019.09.019</pub-id> <pub-id pub-id-type="pmid">31678735</pub-id></citation></ref>
<ref id="B12"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Dao</surname> <given-names>F. Y.</given-names></name> <name><surname>Lv</surname> <given-names>H.</given-names></name> <name><surname>Yang</surname> <given-names>Y. H.</given-names></name> <name><surname>Zulfiqar</surname> <given-names>H.</given-names></name> <name><surname>Gao</surname> <given-names>H.</given-names></name> <name><surname>Lin</surname> <given-names>H.</given-names></name></person-group> (<year>2020a</year>). <article-title>Computational identification of N6-methyladenosine sites in multiple tissues of mammals.</article-title> <source><italic>Comput. Struct. Biotechnol. J.</italic></source> <volume>18</volume> <fpage>1084</fpage>&#x2013;<lpage>1091</lpage>. <pub-id pub-id-type="doi">10.1016/j.csbj.2020.04.015</pub-id> <pub-id pub-id-type="pmid">32435427</pub-id></citation></ref>
<ref id="B13"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Dao</surname> <given-names>F. Y.</given-names></name> <name><surname>Lv</surname> <given-names>H.</given-names></name> <name><surname>Zulfiqar</surname> <given-names>H.</given-names></name> <name><surname>Yang</surname> <given-names>H.</given-names></name> <name><surname>Su</surname> <given-names>W.</given-names></name> <name><surname>Gao</surname> <given-names>H.</given-names></name><etal/></person-group> (<year>2020b</year>). <article-title>A computational platform to identify origins of replication sites in eukaryotes.</article-title> <source><italic>Brief. Bioinform.</italic></source> <comment>bbaa017</comment>. <pub-id pub-id-type="doi">10.1093/bib/bbaa017</pub-id> <pub-id pub-id-type="pmid">32065211</pub-id></citation></ref>
<ref id="B14"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Der Ploeg</surname> <given-names>J. R. V.</given-names></name></person-group> (<year>2008</year>). <article-title>Characterization of <italic>Streptococcus gordonii</italic> prophage PH15: complete genome sequence and functional analysis of phage-encoded integrase and endolysin.</article-title> <source><italic>Microbiology</italic></source> <volume>154</volume> <fpage>2970</fpage>&#x2013;<lpage>2978</lpage>. <pub-id pub-id-type="doi">10.1099/mic.0.2008/018739-0</pub-id> <pub-id pub-id-type="pmid">18832303</pub-id></citation></ref>
<ref id="B15"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Ding</surname> <given-names>H.</given-names></name> <name><surname>Luo</surname> <given-names>L.</given-names></name> <name><surname>Lin</surname> <given-names>H.</given-names></name></person-group> (<year>2009</year>). <article-title>Prediction of cell wall lytic enzymes using Chou&#x2019;s amphiphilic pseudo amino acid composition.</article-title> <source><italic>Protein Pept. Lett.</italic></source> <volume>16</volume> <fpage>351</fpage>&#x2013;<lpage>355</lpage>. <pub-id pub-id-type="doi">10.2174/092986609787848045</pub-id> <pub-id pub-id-type="pmid">19356130</pub-id></citation></ref>
<ref id="B16"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Dong</surname> <given-names>Q.</given-names></name> <name><surname>Zhou</surname> <given-names>S.</given-names></name> <name><surname>Guan</surname> <given-names>J.</given-names></name></person-group> (<year>2009</year>). <article-title>A new taxonomy-based protein fold recognition approach based on autocross-covariance transformation.</article-title> <source><italic>Bioinformatics</italic></source> <volume>25</volume> <fpage>2655</fpage>&#x2013;<lpage>2662</lpage>. <pub-id pub-id-type="doi">10.1093/bioinformatics/btp500</pub-id> <pub-id pub-id-type="pmid">19706744</pub-id></citation></ref>
<ref id="B17"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Du</surname> <given-names>L.</given-names></name> <name><surname>Meng</surname> <given-names>Q.</given-names></name> <name><surname>Chen</surname> <given-names>Y.</given-names></name> <name><surname>Wu</surname> <given-names>P.</given-names></name></person-group> (<year>2020</year>). <article-title>Subcellular location prediction of apoptosis proteins using two novel feature extraction methods based on evolutionary information and LDA.</article-title> <source><italic>BMC Bioinform.</italic></source> <volume>21</volume>:<issue>212</issue>. <pub-id pub-id-type="doi">10.1186/s12859-020-3539-1</pub-id> <pub-id pub-id-type="pmid">32448129</pub-id></citation></ref>
<ref id="B18"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Fan</surname> <given-names>G. L.</given-names></name> <name><surname>Li</surname> <given-names>Q. Z.</given-names></name> <name><surname>Zuo</surname> <given-names>Y. C.</given-names></name></person-group> (<year>2013</year>). <article-title>Predicting acidic and alkaline enzymes by incorporating the average chemical shift and gene ontology informations into the general form of Chou&#x2019;s PseAAC.</article-title> <source><italic>Process Biochem.</italic></source> <volume>48</volume> <fpage>1048</fpage>&#x2013;<lpage>1053</lpage>. <pub-id pub-id-type="doi">10.1016/j.procbio.2013.05.012</pub-id></citation></ref>
<ref id="B19"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Fan</surname> <given-names>G. L.</given-names></name> <name><surname>Liu</surname> <given-names>Y. L.</given-names></name> <name><surname>Zuo</surname> <given-names>Y. C.</given-names></name> <name><surname>Mei</surname> <given-names>H. X.</given-names></name> <name><surname>Rang</surname> <given-names>Y.</given-names></name> <name><surname>Hou</surname> <given-names>B. Y.</given-names></name><etal/></person-group> (<year>2014</year>). <article-title>acACS: improving the prediction accuracy of protein subcellular locations and protein classification by incorporating the average chemical shifts composition.</article-title> <source><italic>Sci. World J.</italic></source> <volume>2014</volume>:<issue>864135</issue>. <pub-id pub-id-type="doi">10.1155/2014/864135</pub-id> <pub-id pub-id-type="pmid">25110749</pub-id></citation></ref>
<ref id="B20"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Feng</surname> <given-names>P.</given-names></name> <name><surname>Xu</surname> <given-names>Z.</given-names></name> <name><surname>Yang</surname> <given-names>H.</given-names></name> <name><surname>Lv</surname> <given-names>H.</given-names></name> <name><surname>Ding</surname> <given-names>H.</given-names></name> <name><surname>Liu</surname> <given-names>L.</given-names></name></person-group> (<year>2019</year>). <article-title>Identification of D modification sites by integrating heterogeneous features in <italic>Saccharomyces cerevisiae</italic>.</article-title> <source><italic>Molecules</italic></source> <volume>24</volume>:<issue>380</issue>. <pub-id pub-id-type="doi">10.3390/molecules24030380</pub-id> <pub-id pub-id-type="pmid">30678171</pub-id></citation></ref>
<ref id="B21"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Gondil</surname> <given-names>V. S.</given-names></name> <name><surname>Harjai</surname> <given-names>K.</given-names></name> <name><surname>Chhibber</surname> <given-names>S.</given-names></name></person-group> (<year>2020</year>). <article-title>Endolysins as emerging alternative therapeutic agents to counter drug-resistant infections.</article-title> <source><italic>Int. J. Antimicrob. Agents</italic></source> <volume>55</volume>:<issue>105844</issue>. <pub-id pub-id-type="doi">10.1016/j.ijantimicag.2019.11.001</pub-id> <pub-id pub-id-type="pmid">31715257</pub-id></citation></ref>
<ref id="B22"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Huang</surname> <given-names>G.</given-names></name> <name><surname>Li</surname> <given-names>J.</given-names></name></person-group> (<year>2018</year>). <article-title>Feature extractions for computationally predicting protein post- translational modifications.</article-title> <source><italic>Curr. Bioinform.</italic></source> <volume>12</volume> <fpage>387</fpage>&#x2013;<lpage>395</lpage>. <pub-id pub-id-type="doi">10.2174/1574893612666170707094916</pub-id></citation></ref>
<ref id="B23"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Jiao</surname> <given-names>Y. S.</given-names></name> <name><surname>Du</surname> <given-names>P. F.</given-names></name></person-group> (<year>2016</year>). <article-title>Prediction of golgi-resident protein types using general form of chou&#x2019;s pseudo-amino acid compositions: approaches with minimal redundancy maximal relevance feature selection.</article-title> <source><italic>J. Theor. Biol.</italic></source> <volume>402</volume> <fpage>38</fpage>&#x2013;<lpage>44</lpage>. <pub-id pub-id-type="doi">10.1016/j.jtbi.2016.04.032</pub-id> <pub-id pub-id-type="pmid">27155042</pub-id></citation></ref>
<ref id="B24"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Jing</surname> <given-names>X. Y.</given-names></name> <name><surname>Li</surname> <given-names>F. M.</given-names></name></person-group> (<year>2020</year>). <article-title>Identifying heat shock protein families from imbalanced data by using combined features.</article-title> <source><italic>Comput. Math. Methods Med.</italic></source> <volume>2020</volume>:<issue>8894478</issue>. <pub-id pub-id-type="doi">10.1155/2020/8894478</pub-id> <pub-id pub-id-type="pmid">33029195</pub-id></citation></ref>
<ref id="B25"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Ju</surname> <given-names>Z.</given-names></name> <name><surname>He</surname> <given-names>J. J.</given-names></name></person-group> (<year>2017</year>). <article-title>Prediction of lysine propionylation sites using biased SVM and incorporating four different sequence features into Chou&#x2019;s PseAAC.</article-title> <source><italic>J. Mol. Graph. Model.</italic></source> <volume>76</volume> <fpage>356</fpage>&#x2013;<lpage>363</lpage>. <pub-id pub-id-type="doi">10.1016/j.jmgm.2017.07.022</pub-id> <pub-id pub-id-type="pmid">28763688</pub-id></citation></ref>
<ref id="B26"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Kabir</surname> <given-names>M.</given-names></name> <name><surname>Ahmad</surname> <given-names>S.</given-names></name> <name><surname>Iqbal</surname> <given-names>M.</given-names></name> <name><surname>Hayat</surname> <given-names>M.</given-names></name></person-group> (<year>2020</year>). <article-title>iNR-2L: a two-level sequence-based predictor developed via Chou&#x2019;s 5-steps rule and general PseAAC for identifying nuclear receptors and their families.</article-title> <source><italic>Genomics</italic></source> <volume>112</volume> <fpage>276</fpage>&#x2013;<lpage>285</lpage>. <pub-id pub-id-type="doi">10.1016/j.ygeno.2019.02.006</pub-id> <pub-id pub-id-type="pmid">30779939</pub-id></citation></ref>
<ref id="B27"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Kalali</surname> <given-names>Y.</given-names></name> <name><surname>Haghighat</surname> <given-names>S.</given-names></name> <name><surname>Mahdavi</surname> <given-names>M.</given-names></name></person-group> (<year>2019</year>). <article-title>Passive immunotherapy with specific IgG fraction against autolysin: analogous protectivity in the MRSA infection with antibiotic therapy.</article-title> <source><italic>Immunol. Lett.</italic></source> <volume>212</volume> <fpage>125</fpage>&#x2013;<lpage>131</lpage>. <pub-id pub-id-type="doi">10.1016/j.imlet.2018.11.010</pub-id> <pub-id pub-id-type="pmid">30496765</pub-id></citation></ref>
<ref id="B28"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Kwon</surname> <given-names>E.</given-names></name> <name><surname>Cho</surname> <given-names>M.</given-names></name> <name><surname>Kim</surname> <given-names>H.</given-names></name> <name><surname>Son</surname> <given-names>H. S.</given-names></name></person-group> (<year>2020</year>). <article-title>A study on host tropism determinants of influenza virus using machine learning.</article-title> <source><italic>Curr. Bioinform.</italic></source> <volume>15</volume> <fpage>121</fpage>&#x2013;<lpage>134</lpage>. <pub-id pub-id-type="doi">10.2174/1574893614666191104160927</pub-id></citation></ref>
<ref id="B29"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Li</surname> <given-names>F. M.</given-names></name> <name><surname>Gao</surname> <given-names>X. W.</given-names></name></person-group> (<year>2020</year>). <article-title>Predicting gram-positive bacterial protein subcellular location by using combined features.</article-title> <source><italic>Biomed. Res. Int.</italic></source> <volume>2020</volume>:<issue>9701734</issue>. <pub-id pub-id-type="doi">10.1155/2020/9701734</pub-id> <pub-id pub-id-type="pmid">32802888</pub-id></citation></ref>
<ref id="B30"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Li</surname> <given-names>F. M.</given-names></name> <name><surname>Li</surname> <given-names>Q. Z.</given-names></name></person-group> (<year>2008</year>). <article-title>Predicting protein subcellular location using Chou&#x2019;s pseudo amino acid composition and improved hybrid approach.</article-title> <source><italic>Protein Pept. Lett.</italic></source> <volume>15</volume> <fpage>612</fpage>&#x2013;<lpage>616</lpage>. <pub-id pub-id-type="doi">10.2174/092986608784966930</pub-id> <pub-id pub-id-type="pmid">18680458</pub-id></citation></ref>
<ref id="B31"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Li</surname> <given-names>F. M.</given-names></name> <name><surname>Wang</surname> <given-names>X. Q.</given-names></name></person-group> (<year>2016</year>). <article-title>Identifying anticancer peptides by using improved hybrid compositions.</article-title> <source><italic>Sci. Rep.</italic></source> <volume>6</volume>:<issue>33910</issue>. <pub-id pub-id-type="doi">10.1038/srep33910</pub-id> <pub-id pub-id-type="pmid">27670968</pub-id></citation></ref>
<ref id="B32"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Li</surname> <given-names>S.</given-names></name> <name><surname>Zhang</surname> <given-names>J.</given-names></name> <name><surname>Zhao</surname> <given-names>Y.</given-names></name> <name><surname>Dao</surname> <given-names>F.</given-names></name> <name><surname>Ding</surname> <given-names>H.</given-names></name> <name><surname>Chen</surname> <given-names>W.</given-names></name><etal/></person-group> (<year>2019</year>). <article-title>iPhoPred: a predictor for identifying phosphorylation sites in human protein.</article-title> <source><italic>IEEE Access</italic></source> <volume>7</volume> <fpage>177517</fpage>&#x2013;<lpage>177528</lpage>. <pub-id pub-id-type="doi">10.1109/ACCESS.2019.2953951</pub-id></citation></ref>
<ref id="B33"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Li</surname> <given-names>W.</given-names></name> <name><surname>Godzik</surname> <given-names>A.</given-names></name></person-group> (<year>2006</year>). <article-title>Cd-hit: a fast program for clustering and comparing large sets of protein or nucleotide sequences.</article-title> <source><italic>Bioinformatics</italic></source> <volume>22</volume> <fpage>1658</fpage>&#x2013;<lpage>1659</lpage>. <pub-id pub-id-type="doi">10.1093/bioinformatics/btl158</pub-id> <pub-id pub-id-type="pmid">16731699</pub-id></citation></ref>
<ref id="B34"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Malebary</surname> <given-names>S. J.</given-names></name> <name><surname>Rehman</surname> <given-names>M. S. U.</given-names></name> <name><surname>Khan</surname> <given-names>Y. D.</given-names></name></person-group> (<year>2019</year>). <article-title>iCrotoK-PseAAC: identify lysine crotonylation sites by blending position relative statistical features according to the Chou&#x2019;s 5-step rule.</article-title> <source><italic>PloS One</italic></source> <volume>14</volume>:<issue>e0223993</issue>. <pub-id pub-id-type="doi">10.1371/journal.pone.0223993</pub-id> <pub-id pub-id-type="pmid">31751380</pub-id></citation></ref>
<ref id="B35"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Meng</surname> <given-names>C.</given-names></name> <name><surname>Guo</surname> <given-names>F.</given-names></name> <name><surname>Zou</surname> <given-names>Q.</given-names></name></person-group> (<year>2020</year>). <article-title>CWLy-SVM: a support vector machine-based tool for identifying cell wall lytic enzymes.</article-title> <source><italic>Comput. Biol. Chem.</italic></source> <volume>87</volume>:<issue>107304</issue>. <pub-id pub-id-type="doi">10.1016/j.compbiolchem.2020.107304</pub-id> <pub-id pub-id-type="pmid">32580129</pub-id></citation></ref>
<ref id="B36"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Ru</surname> <given-names>X.</given-names></name> <name><surname>Li</surname> <given-names>L.</given-names></name> <name><surname>Wang</surname> <given-names>C.</given-names></name></person-group> (<year>2019</year>). <article-title>Identification of phage viral proteins with hybrid sequence features.</article-title> <source><italic>Front. Microbiol.</italic></source> <volume>10</volume>:<issue>507</issue>. <pub-id pub-id-type="doi">10.3389/fmicb.2019.00507</pub-id> <pub-id pub-id-type="pmid">30972038</pub-id></citation></ref>
<ref id="B37"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Shavrina</surname> <given-names>M. S.</given-names></name> <name><surname>Zimin</surname> <given-names>A. A.</given-names></name> <name><surname>Molochkov</surname> <given-names>N. V.</given-names></name> <name><surname>Chernyshov</surname> <given-names>S. V.</given-names></name> <name><surname>Machulin</surname> <given-names>A. V.</given-names></name> <name><surname>Mikoulinskaia</surname> <given-names>G. V.</given-names></name></person-group> (<year>2016</year>). <article-title>In vitro study of the antibacterial effect of the bacteriophage T5 thermostable endolysin on <italic>Escherichia coli</italic> cells.</article-title> <source><italic>J. Appl. Microbiol.</italic></source> <volume>121</volume> <fpage>1282</fpage>&#x2013;<lpage>1290</lpage>. <pub-id pub-id-type="doi">10.1111/jam.13251</pub-id> <pub-id pub-id-type="pmid">27501055</pub-id></citation></ref>
<ref id="B38"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Sibley</surname> <given-names>A. B.</given-names></name> <name><surname>Cosman</surname> <given-names>M.</given-names></name> <name><surname>Krishnan</surname> <given-names>V. V.</given-names></name></person-group> (<year>2003</year>). <article-title>An empirical correlation between secondary structure content and averaged chemical shifts in proteins.</article-title> <source><italic>Biophys. J.</italic></source> <volume>84</volume> <fpage>1223</fpage>&#x2013;<lpage>1227</lpage>. <pub-id pub-id-type="doi">10.1016/s0006-3495(03)74937-6</pub-id></citation></ref>
<ref id="B39"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Sommer</surname> <given-names>M. O. A.</given-names></name> <name><surname>Munck</surname> <given-names>C.</given-names></name> <name><surname>Toftkehler</surname> <given-names>R. V.</given-names></name> <name><surname>Andersson</surname> <given-names>D. I.</given-names></name></person-group> (<year>2017</year>). <article-title>Prediction of antibiotic resistance: time for a new preclinical paradigm?</article-title> <source><italic>Nat. Rev. Microbiol.</italic></source> <volume>15</volume> <fpage>689</fpage>&#x2013;<lpage>696</lpage>. <pub-id pub-id-type="doi">10.1038/nrmicro.2017.75</pub-id> <pub-id pub-id-type="pmid">28757648</pub-id></citation></ref>
<ref id="B40"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Tan</surname> <given-names>J. X.</given-names></name> <name><surname>Dao</surname> <given-names>F. Y.</given-names></name> <name><surname>Lv</surname> <given-names>H.</given-names></name> <name><surname>Feng</surname> <given-names>P. M.</given-names></name> <name><surname>Ding</surname> <given-names>H.</given-names></name></person-group> (<year>2018</year>). <article-title>Identifying phage virion proteins by using two-step feature selection methods.</article-title> <source><italic>Molecules</italic></source> <volume>23</volume>:<issue>2000</issue>. <pub-id pub-id-type="doi">10.3390/molecules23082000</pub-id> <pub-id pub-id-type="pmid">30103458</pub-id></citation></ref>
<ref id="B41"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Tan</surname> <given-names>J. X.</given-names></name> <name><surname>Li</surname> <given-names>S. H.</given-names></name> <name><surname>Zhang</surname> <given-names>Z. M.</given-names></name> <name><surname>Chen</surname> <given-names>C. X.</given-names></name> <name><surname>Chen</surname> <given-names>W.</given-names></name> <name><surname>Tang</surname> <given-names>H.</given-names></name><etal/></person-group> (<year>2019</year>). <article-title>Identification of hormone binding proteins based on machine learning methods.</article-title> <source><italic>Math. Biosci. Eng.</italic></source> <volume>16</volume> <fpage>2466</fpage>&#x2013;<lpage>2480</lpage>. <pub-id pub-id-type="doi">10.3934/mbe.2019123</pub-id> <pub-id pub-id-type="pmid">31137222</pub-id></citation></ref>
<ref id="B42"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Tang</surname> <given-names>H.</given-names></name> <name><surname>Zhao</surname> <given-names>Y. W.</given-names></name> <name><surname>Zou</surname> <given-names>P.</given-names></name> <name><surname>Zhang</surname> <given-names>C. M.</given-names></name> <name><surname>Chen</surname> <given-names>R.</given-names></name> <name><surname>Huang</surname> <given-names>P.</given-names></name><etal/></person-group> (<year>2018</year>). <article-title>HBPred: a tool to identify growth hormone-binding proteins.</article-title> <source><italic>Int. J. Biol. Sci.</italic></source> <volume>14</volume> <fpage>957</fpage>&#x2013;<lpage>964</lpage>. <pub-id pub-id-type="doi">10.7150/ijbs.24174</pub-id> <pub-id pub-id-type="pmid">29989085</pub-id></citation></ref>
<ref id="B43"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Tian</surname> <given-names>B.</given-names></name> <name><surname>Wu</surname> <given-names>X.</given-names></name> <name><surname>Chen</surname> <given-names>C.</given-names></name> <name><surname>Qiu</surname> <given-names>W.</given-names></name> <name><surname>Ma</surname> <given-names>Q.</given-names></name> <name><surname>Yu</surname> <given-names>B.</given-names></name></person-group> (<year>2019</year>). <article-title>Predicting protein-protein interactions by fusing various Chou&#x2019;s pseudo components and using wavelet denoising approach.</article-title> <source><italic>J. Theor. Biol.</italic></source> <volume>462</volume> <fpage>329</fpage>&#x2013;<lpage>346</lpage>. <pub-id pub-id-type="doi">10.1016/j.jtbi.2018.11.011</pub-id> <pub-id pub-id-type="pmid">30452960</pub-id></citation></ref>
<ref id="B44"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Usobiaga</surname> <given-names>P.</given-names></name> <name><surname>Medrano</surname> <given-names>F. J.</given-names></name> <name><surname>Gasset</surname> <given-names>M.</given-names></name> <name><surname>Garcia</surname> <given-names>J. L.</given-names></name> <name><surname>Saiz</surname> <given-names>J. L.</given-names></name> <name><surname>Rivas</surname> <given-names>G.</given-names></name><etal/></person-group> (<year>1996</year>). <article-title>Structural organization of the major autolysin from <italic>Streptococcus pneumoniae</italic>.</article-title> <source><italic>J. Biol. Chem.</italic></source> <volume>271</volume> <fpage>6832</fpage>&#x2013;<lpage>6838</lpage>. <pub-id pub-id-type="doi">10.1074/jbc.271.12.6832</pub-id> <pub-id pub-id-type="pmid">8636107</pub-id></citation></ref>
<ref id="B45"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Wan</surname> <given-names>S.</given-names></name> <name><surname>Duan</surname> <given-names>Y.</given-names></name> <name><surname>Zou</surname> <given-names>Q.</given-names></name></person-group> (<year>2017</year>). <article-title>HPSLPred: an ensemble multi-label classifier for human protein subcellular location prediction with imbalanced source.</article-title> <source><italic>Proteomics</italic></source> <volume>17</volume> <fpage>17</fpage>&#x2013;<lpage>18</lpage>. <pub-id pub-id-type="doi">10.1002/pmic.201700262</pub-id> <pub-id pub-id-type="pmid">28776938</pub-id></citation></ref>
<ref id="B46"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Wang</surname> <given-names>C.</given-names></name> <name><surname>Li</surname> <given-names>J.</given-names></name> <name><surname>Liu</surname> <given-names>X.</given-names></name> <name><surname>Guo</surname> <given-names>M.</given-names></name></person-group> (<year>2019a</year>). <article-title>Predicting sub-Golgi apparatus resident protein with primary sequence hybrid features.</article-title> <source><italic>IEEE Access</italic></source> <volume>8</volume> <fpage>4442</fpage>&#x2013;<lpage>4450</lpage>. <pub-id pub-id-type="doi">10.1109/ACCESS.2019.2962821</pub-id></citation></ref>
<ref id="B47"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Wang</surname> <given-names>J.</given-names></name> <name><surname>Dai</surname> <given-names>W.</given-names></name> <name><surname>Li</surname> <given-names>J.</given-names></name> <name><surname>Xie</surname> <given-names>R.</given-names></name> <name><surname>Dunstan</surname> <given-names>R. A.</given-names></name> <name><surname>Stubenrauch</surname> <given-names>C.</given-names></name><etal/></person-group> (<year>2020a</year>). <article-title>PaCRISPR: a server for predicting and visualizing anti-CRISPR proteins.</article-title> <source><italic>Nucleic Acids Res.</italic></source> <volume>48</volume> <fpage>W348</fpage>&#x2013;<lpage>W357</lpage>. <pub-id pub-id-type="doi">10.1093/nar/gkaa432</pub-id> <pub-id pub-id-type="pmid">32459325</pub-id></citation></ref>
<ref id="B48"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Wang</surname> <given-names>J.</given-names></name> <name><surname>Yang</surname> <given-names>B.</given-names></name> <name><surname>An</surname> <given-names>Y.</given-names></name> <name><surname>Marquez-Lago</surname> <given-names>T.</given-names></name> <name><surname>Leier</surname> <given-names>A.</given-names></name> <name><surname>Wilksch</surname> <given-names>J.</given-names></name><etal/></person-group> (<year>2019b</year>). <article-title>Systematic analysis and prediction of type IV secreted effector proteins by machine learning approaches.</article-title> <source><italic>Brief. Bioinform.</italic></source> <volume>20</volume> <fpage>931</fpage>&#x2013;<lpage>951</lpage>. <pub-id pub-id-type="doi">10.1093/bib/bbx164</pub-id> <pub-id pub-id-type="pmid">29186295</pub-id></citation></ref>
<ref id="B49"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Wang</surname> <given-names>S.</given-names></name> <name><surname>Wang</surname> <given-names>D.</given-names></name> <name><surname>Li</surname> <given-names>J.</given-names></name> <name><surname>Huang</surname> <given-names>T.</given-names></name> <name><surname>Cai</surname> <given-names>Y. D.</given-names></name></person-group> (<year>2018a</year>). <article-title>Identification and analysis of the cleavage site in a signal peptide using SMOTE, dagging, and feature selection methods.</article-title> <source><italic>Mol. Omics</italic></source> <volume>14</volume> <fpage>64</fpage>&#x2013;<lpage>73</lpage>. <pub-id pub-id-type="doi">10.1039/c7mo00030h</pub-id> <pub-id pub-id-type="pmid">29725682</pub-id></citation></ref>
<ref id="B50"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Wang</surname> <given-names>S.</given-names></name> <name><surname>Zhang</surname> <given-names>Q.</given-names></name> <name><surname>Lu</surname> <given-names>J.</given-names></name> <name><surname>Cai</surname> <given-names>Y.</given-names></name></person-group> (<year>2018b</year>). <article-title>Analysis and prediction of nitrated tyrosine sites with the mRMR method and support vector machine algorithm.</article-title> <source><italic>Curr. Bioinform.</italic></source> <volume>13</volume> <fpage>3</fpage>&#x2013;<lpage>13</lpage>. <pub-id pub-id-type="doi">10.2174/1574893611666160608075753</pub-id></citation></ref>
<ref id="B51"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Wang</surname> <given-names>X. F.</given-names></name> <name><surname>Gao</surname> <given-names>P.</given-names></name> <name><surname>Liu</surname> <given-names>Y. F.</given-names></name> <name><surname>Li</surname> <given-names>H. F.</given-names></name> <name><surname>Lu</surname> <given-names>F.</given-names></name></person-group> (<year>2020b</year>). <article-title>Predicting thermophilic proteins by machine learning.</article-title> <source><italic>Curr. Bioinform.</italic></source> <volume>15</volume> <fpage>493</fpage>&#x2013;<lpage>502</lpage>. <pub-id pub-id-type="doi">10.2174/1574893615666200207094357</pub-id></citation></ref>
<ref id="B52"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Wu</surname> <given-names>X.</given-names></name> <name><surname>Kwon</surname> <given-names>S. J.</given-names></name> <name><surname>Kim</surname> <given-names>J.</given-names></name> <name><surname>Kane</surname> <given-names>R. S.</given-names></name> <name><surname>Dordick</surname> <given-names>J. S.</given-names></name></person-group> (<year>2017</year>). <article-title>Biocatalytic Nanocomposites for Combating Bacterial Pathogens.</article-title> <source><italic>Annu. Rev. Chem. Biomol. Eng.</italic></source> <volume>8</volume> <fpage>87</fpage>&#x2013;<lpage>113</lpage>. <pub-id pub-id-type="doi">10.1146/annurev-chembioeng-060816-101612</pub-id> <pub-id pub-id-type="pmid">28592177</pub-id></citation></ref>
<ref id="B53"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Xu</surname> <given-names>Y.</given-names></name> <name><surname>Ding</surname> <given-names>Y. X.</given-names></name> <name><surname>Ding</surname> <given-names>J.</given-names></name> <name><surname>Wu</surname> <given-names>L. Y.</given-names></name> <name><surname>Xue</surname> <given-names>Y.</given-names></name></person-group> (<year>2016</year>). <article-title>Mal-Lys: prediction of lysine malonylation sites in proteins integrated sequence-based features with mRMR feature selection.</article-title> <source><italic>Sci. Rep.</italic></source> <volume>6</volume>:<issue>38318</issue>. <pub-id pub-id-type="doi">10.1038/srep38318</pub-id> <pub-id pub-id-type="pmid">27910954</pub-id></citation></ref>
<ref id="B54"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Yan</surname> <given-names>G.</given-names></name> <name><surname>Yang</surname> <given-names>R.</given-names></name> <name><surname>Fan</surname> <given-names>K.</given-names></name> <name><surname>Dong</surname> <given-names>H.</given-names></name> <name><surname>Gao</surname> <given-names>C.</given-names></name> <name><surname>Wang</surname> <given-names>S.</given-names></name><etal/></person-group> (<year>2019</year>). <article-title>External lysis of <italic>Escherichia coli</italic> by a bacteriophage endolysin modified with hydrophobic amino acids.</article-title> <source><italic>AMB Express</italic></source> <volume>9</volume>:<issue>106</issue>. <pub-id pub-id-type="doi">10.1186/s13568-019-0838-x</pub-id> <pub-id pub-id-type="pmid">31309363</pub-id></citation></ref>
<ref id="B55"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Yang</surname> <given-names>H.</given-names></name> <name><surname>Yang</surname> <given-names>W.</given-names></name> <name><surname>Dao</surname> <given-names>F. Y.</given-names></name> <name><surname>Lv</surname> <given-names>H.</given-names></name> <name><surname>Ding</surname> <given-names>H.</given-names></name> <name><surname>Chen</surname> <given-names>W.</given-names></name><etal/></person-group> (<year>2020</year>). <article-title>A comparison and assessment of computational method for identifying recombination hotspots in <italic>Saccharomyces cerevisiae</italic>.</article-title> <source><italic>Brief. Bioinform.</italic></source> <volume>21</volume> <fpage>1568</fpage>&#x2013;<lpage>1580</lpage>. <pub-id pub-id-type="doi">10.1093/bib/bbz123</pub-id> <pub-id pub-id-type="pmid">31633777</pub-id></citation></ref>
<ref id="B56"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Yang</surname> <given-names>W.</given-names></name> <name><surname>Zhu</surname> <given-names>X. J.</given-names></name> <name><surname>Huang</surname> <given-names>J.</given-names></name> <name><surname>Ding</surname> <given-names>H.</given-names></name> <name><surname>Lin</surname> <given-names>H.</given-names></name></person-group> (<year>2019</year>). <article-title>A brief survey of machine learning methods in protein sub-golgi localization.</article-title> <source><italic>Curr. Bioinform.</italic></source> <volume>14</volume> <fpage>234</fpage>&#x2013;<lpage>240</lpage>. <pub-id pub-id-type="doi">10.2174/1574893613666181113131415</pub-id></citation></ref>
<ref id="B57"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Yu</surname> <given-names>J.</given-names></name></person-group> (<year>1997</year>). <article-title>Microbial cell wall lytic enzymes which can be used for industrial and pharmaceutical uses.</article-title> <source><italic>Food Sci. Biotechnol.</italic></source> <volume>6</volume> <fpage>65</fpage>&#x2013;<lpage>66</lpage>.</citation></ref>
<ref id="B58"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Zhang</surname> <given-names>H.</given-names></name> <name><surname>Xi</surname> <given-names>Q.</given-names></name> <name><surname>Huang</surname> <given-names>S.</given-names></name> <name><surname>Zheng</surname> <given-names>L.</given-names></name> <name><surname>Yang</surname> <given-names>W.</given-names></name> <name><surname>Zuo</surname> <given-names>Y.</given-names></name></person-group> (<year>2020a</year>). <article-title>iSP-RAAC: identify secretory proteins of malaria parasite using reduced amino acid composition.</article-title> <source><italic>Comb. Chem. High Throughput Screen.</italic></source> <volume>23</volume> <fpage>536</fpage>&#x2013;<lpage>545</lpage>. <pub-id pub-id-type="doi">10.2174/1386207323666200402084518</pub-id> <pub-id pub-id-type="pmid">32238133</pub-id></citation></ref>
<ref id="B59"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Zhang</surname> <given-names>J.</given-names></name> <name><surname>Liu</surname> <given-names>B.</given-names></name></person-group> (<year>2019</year>). <article-title>A review on the recent developments of sequence-based protein feature extraction methods.</article-title> <source><italic>Curr. Bioinform.</italic></source> <volume>14</volume> <fpage>190</fpage>&#x2013;<lpage>199</lpage>. <pub-id pub-id-type="doi">10.2174/1574893614666181212102749</pub-id></citation></ref>
<ref id="B60"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Zhang</surname> <given-names>Z.</given-names></name> <name><surname>Yang</surname> <given-names>Y.-H.</given-names></name> <name><surname>Ding</surname> <given-names>H.</given-names></name> <name><surname>Wang</surname> <given-names>D.</given-names></name> <name><surname>Chen</surname> <given-names>W.</given-names></name> <name><surname>Lin</surname> <given-names>H.</given-names></name></person-group> (<year>2020b</year>). <article-title>Design powerful predictor for mRNA subcellular location prediction in Homo sapiens.</article-title> <source><italic>Brief. Bioinform</italic></source> bbz177. <pub-id pub-id-type="doi">10.1093/bib/bbz177</pub-id> <pub-id pub-id-type="pmid">31994694</pub-id></citation></ref>
<ref id="B61"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Zhou</surname> <given-names>H.</given-names></name> <name><surname>Chen</surname> <given-names>C.</given-names></name> <name><surname>Wang</surname> <given-names>M.</given-names></name> <name><surname>Ma</surname> <given-names>Q.</given-names></name> <name><surname>Yu</surname> <given-names>B.</given-names></name></person-group> (<year>2019</year>). <article-title>Predicting golgi-resident protein types using conditional covariance minimization with XGBoost based on multiple features fusion.</article-title> <source><italic>IEEE Access</italic></source> <volume>7</volume> <fpage>144154</fpage>&#x2013;<lpage>144164</lpage>. <pub-id pub-id-type="doi">10.1109/ACCESS.2019.2938081</pub-id></citation></ref>
<ref id="B62"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Zhu</surname> <given-names>X.</given-names></name> <name><surname>Feng</surname> <given-names>C.</given-names></name> <name><surname>Lai</surname> <given-names>H.</given-names></name> <name><surname>Chen</surname> <given-names>W.</given-names></name> <name><surname>Hao</surname> <given-names>L.</given-names></name></person-group> (<year>2018</year>). <article-title>Predicting protein structural classes for low-similarity sequences by evaluating different features.</article-title> <source><italic>Knowl. Based Syst</italic></source> <volume>163</volume> <fpage>787</fpage>&#x2013;<lpage>793</lpage>. <pub-id pub-id-type="doi">10.1016/j.knosys.2018.10.007</pub-id></citation></ref>
<ref id="B63"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Zou</surname> <given-names>L.</given-names></name> <name><surname>Nan</surname> <given-names>C.</given-names></name> <name><surname>Hu</surname> <given-names>F.</given-names></name></person-group> (<year>2013</year>). <article-title>Accurate prediction of bacterial type IV secreted effectors using amino acid composition and PSSM profiles.</article-title> <source><italic>Bioinformatics</italic></source> <volume>29</volume> <fpage>3135</fpage>&#x2013;<lpage>3142</lpage>. <pub-id pub-id-type="doi">10.1093/bioinformatics/btt554</pub-id> <pub-id pub-id-type="pmid">24064423</pub-id></citation></ref>
<ref id="B64"><citation citation-type="journal"><person-group person-group-type="author"><name><surname>Zou</surname> <given-names>Q.</given-names></name> <name><surname>Zeng</surname> <given-names>J.</given-names></name> <name><surname>Cao</surname> <given-names>L.</given-names></name> <name><surname>Ji</surname> <given-names>R.</given-names></name></person-group> (<year>2016</year>). <article-title>A novel features ranking metric with application to scalable visual and bioinformatics data classification.</article-title> <source><italic>Neurocomputing</italic></source> <volume>173</volume> <fpage>346</fpage>&#x2013;<lpage>354</lpage>. <pub-id pub-id-type="doi">10.1016/j.neucom.2014.12.123</pub-id></citation></ref>
</ref-list>
<fn-group>
<fn id="footnote1">
<label>1</label>
<p><ext-link ext-link-type="uri" xlink:href="http://bioinf.cs.ucl.ac.uk/psipred/">http://bioinf.cs.ucl.ac.uk/psipred/</ext-link></p></fn>
<fn id="footnote2">
<label>2</label>
<p><ext-link ext-link-type="uri" xlink:href="http://202.207.14.87:8032/bioinformation/acACS/index.asp">http://202.207.14.87:8032/bioinformation/acACS/index.asp</ext-link></p></fn>
</fn-group>
</back>
</article>