Data-driven extraction of human kinase-substrate relationships from omics datasets

Abstract

AbstractPhosphorylation forms an important part of the signalling system that cells use for decision making and regulation of processes such as celll division and differentiation. To date, a large portion of identified phosphosites are not known to be targeted by any kinase. At the same time around 30% of kinases have no known target. This knowledge gap stresses the need to make large scale, data-driven computational predictions. In this paper, we have created a machine learning-based model to derive a probabilistic kinase-substrate network from omics datasets. We show that our methodology displays improved performance compared to other state of the art kinase-substrate predictions, and provides predictions for more kinases than most of them. Importantly, it better captures new experimentally-identified kinase-substrate relationships. It can therefore allow the improved prioritisation of kinase-substrate pairs for illuminating the dark human cell signalling space.