Co-evolution based machine-learning for predicting functional interactions between human genes

Abstract

Over the next decade, more than a million eukaryotic species are expected to be fully sequenced. This has the potential to improve our understanding of genotype and phenotype crosstalk, gene function and interactions, and answer evolutionary questions. Here, we develop a machine-learning approach for utilizing phylogenetic profiles across 1154 eukaryotic species. This method integrates co-evolution across eukaryotic clades to predict functional interactions between human genes and the context for these interactions. We benchmark our approach showing a 14% performance increase (auROC) compared to previous methods. Using this approach, we predict functional annotations for less studied genes. We focus on DNA repair and verify that 9 of the top 50 predicted genes have been identified elsewhere, with others previously prioritized by high-throughput screens. Overall, our approach enables better annotation of function and functional interactions and facilitates the understanding of evolutionary processes underlying co-evolution. The manuscript is accompanied by a webserver available at: https://mlpp.cs.huji.ac.il.

In silico Analysis of SARS-CoV-2 ORF8-Binding Proteins Reveals the Involvement of ORF8 in Acquired-Immune and Innate-Immune Systems

“…One such approach is phylogenetic profiling, an independent technique to infer functionally related genes and protein-protein interactions via the correlation of the occurrence across a set of genomes or so-called profiles that show the degree of co-evolution between genes ( 9 ). Phylogenetic profiling relies on the hypothesis that genes that function together are associated with similar evolutionary pressures and are thus lost and gained together throughout evolution ( 20 ). Genes with close relationships in the cluster tree developed from phylogenetic profiling are considered to share common functionality and pathways.…”

Phylogenetic profiling in eukaryotes comes of age

“…Stupp et al. ( 11 ) reported that when considering the interactions within a specific clade of the species tree, gradient-boosted decision tree–based regression is able to outperform explicit vector distances and vector distances projected using singular value decomposition.…”

Machine Learning Advances in Microbiology: A Review of Methods and Applications

“…The intersection of genetics and ecology is established on the basis of the population concept. Stupp et al (2021) proposed supervised ML-based phylogenetic profiling (MLPP) to predict functional interactions between human genes and the interaction environment in which they occur (i.e., biological functions) and established a web server containing functional interaction predictions for all human genes. They predicted the probability of all possible gene pairs in each tag using the lightGBM model, which is related to RF after comparing it with the DT, LR, and NB algorithms.…”