AUTHOR=Cuppens Tania , Kaur Manpreet , Kumar Ajay A. , Shatto Julie , Ng Andy Cheuk-Him , Leclercq Mickael , Reformat Marek Z. , Droit Arnaud , Dunham Ian , Bolduc François V. 

TITLE=Developing a cluster-based approach for deciphering complexity in individuals with neurodevelopmental differences

JOURNAL=Frontiers in Pediatrics

VOLUME=Volume 11 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/pediatrics/articles/10.3389/fped.2023.1171920

DOI=10.3389/fped.2023.1171920

ISSN=2296-2360

ABSTRACT=Objective. Individuals with neurodevelopmental disorders such as global developmental delay (GDD) present both genotypic and phenotypic heterogeneity. This diversity has hampered development of targeted interventions given the relative rarity of each individual genetic etiology.Novel approaches to clinical trials where distinct but related diseases can be treated by a common drug, known as basket trials, which have shown benefit in oncology but have yet to be used in GDD.Nonetheless, it remains unclear how individuals with GDD could be clustered. Here we assess two different approaches: agglomerative and divisive clustering.Developmental Disorders (DDD)) characterized using a systematic approach, we extracted genotypic and phenotypic information from 6,588 individuals with GDD. We then used k-means clustering (divisive) and hierarchical agglomerative clustering to identify subgroups of individuals. Next, we extracted gene network and molecular function information about clusters identified by each approach.with GDD revealed 16 clusters, each presenting with one dominant phenotype displayed by most individuals in the cluster as well as other minor phenotypes. Among the most common were delayed speech, absent speech, and seizure. Interestingly, molecularly each phenotypic cluster included several (3-12) gene sub-networks of more closely related genes with diverse molecular function. kmeans clustering also segregated individuals harboring those phenotypes, but the genetic pathways identified were different from the ones from HAC. Conclusion. Our study illustrates how divisive (k-means) and agglomerative clustering can be used in order to group individuals for GDD for future basket trials. Moreover, our analysis suggests that Running Title: Clustering approach to Global Developmental Delay phenotypic clusters be subdivided into molecular sub-networks for increased likelihood of successful treatment. Finally, a combination of both agglomerative and divisive clustering may be required for a comprehensive treatment development.