Joint representation of molecular networks from multiple species improves gene classification

Christopher A Mancuso, Kayla A Johnson, Renming Liu and Arjun Krishnan

PLOS Computational Biology, 2024, vol. 20, issue 1, 1-20

Abstract: Network-based machine learning (ML) has the potential for predicting novel genes associated with nearly any health and disease context. However, this approach often uses network information from only the single species under consideration even though networks for most species are noisy and incomplete. While some recent methods have begun addressing this shortcoming by using networks from more than one species, they lack one or more key desirable properties: handling networks from more than two species simultaneously, incorporating many-to-many orthology information, or generating a network representation that is reusable across different types of and newly-defined prediction tasks. Here, we present GenePlexusZoo, a framework that casts molecular networks from multiple species into a single reusable feature space for network-based ML. We demonstrate that this multi-species network representation improves both gene classification within a single species and knowledge-transfer across species, even in cases where the inter-species correspondence is undetectable based on shared orthologous genes. Thus, GenePlexusZoo enables effectively leveraging the high evolutionary molecular, functional, and phenotypic conservation across species to discover novel genes associated with diverse biological contexts.Author summary: Our work addresses two major challenges; 1) computationally predicting the role a gene plays in various diseases, processes and phenotypes, and 2) accurately transferring genetic information discovered in one species to another. To simultaneously tackle both of these challenges, we developed the GenePlexusZoo method which builds a gene classification model by utilizing molecular interaction information from multiple species, seamlessly handling the complicated mapping of how genes across species are functionally related. We show that machine learning classifiers that utilize information from multiple species outperform those that only consider information from a single species. Additionally, we show that the GenePelxusZoo method is able to accurately transfer knowledge from one species to another, even in the cases where no previous connection would have been detected based solely on shared orthologous genes. Finally, we present an illustrative example of how GenePlexusZoo can provide novel insights into a complicated genetic-based disease.

Date: 2024
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1011773 (text/html)
https://journals.plos.org/ploscompbiol/article/fil ... 11773&type=printable (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:plo:pcbi00:1011773

DOI: 10.1371/journal.pcbi.1011773

Access Statistics for this article

More articles in PLOS Computational Biology from Public Library of Science
Bibliographic data for series maintained by ploscompbiol ().