A knowledge graph representation learning approach to predict novel kinase-substrate interactions

TL;DR

This paper introduces a knowledge graph-based machine learning method to predict new kinase-substrate interactions, aiding the study of understudied kinases with potential therapeutic relevance.

Contribution

It presents a novel approach combining knowledge graph embeddings and supervised learning to identify novel kinase interactions, integrating multiple biological data sources.

Findings

Successful prediction of novel kinase-substrate interactions

Insight into kinase biology through ablation studies

Enhanced understanding of understudied kinases

Abstract

The human proteome contains a vast network of interacting kinases and substrates. Even though some kinases have proven to be immensely useful as therapeutic targets, a majority are still understudied. In this work, we present a novel knowledge graph representation learning approach to predict novel interaction partners for understudied kinases. Our approach uses a phosphoproteomic knowledge graph constructed by integrating data from iPTMnet, Protein Ontology, Gene Ontology and BioKG. The representation of kinases and substrates in this knowledge graph are learned by performing directed random walks on triples coupled with a modified SkipGram or CBOW model. These representations are then used as an input to a supervised classification model to predict novel interactions for understudied kinases. We also present a post-predictive analysis of the predicted interactions and an ablation study of the phosphoproteomic knowledge graph to gain an insight into the biology of the understudied kinases.