Accurate prediction of kinase-substrate networks using knowledge graphs

Vít Novácek, Gavin McGauran, David Matallanas, Adrián Vallejo Blanco, Piero Conca, Emir Muñoz, Luca Costabello, Kamalesh Kanakaraj, Zeeshan Nawaz, Brian Walsh, Sameh K. Mohamed, Pierre-Yves Vandenbussche, Colm J. Ryan, Walter Kolch, Dirk Fey

Abstract: Author summary LinkPhinder is a new approach to prediction of protein signalling networks based on kinase-substrate relationships that outperforms existing approaches. Phosphorylation networks govern virtually all fundamental biochemical processes in cells, and thus have moved into the centre of interest in biology, medicine and drug development. Fundamentally different from current approaches, LinkPhinder is inherently network-based and makes use of the most recent AI developments. We represent existing phosphorylation data as knowledge graphs, a format for large-scale and robust knowledge representation. Training a link prediction model on such a structure leads to novel, biologically valid phosphorylation network predictions that cannot be made with competing tools. Thus our new conceptual approach can lead to establishing a new niche of AI applications in computational biology.