Graph Neural Networks for the Prediction of Protein–Protein Interfaces

Recommended citation: Niccolò Pancino, Alberto Rossi, Giorgio Ciano, Giorgia Giacomini, Simone Bonechi, Paolo Andreini, Franco Scarselli, Monica Bianchini, and Pietro Bongini. Graph neural networks for the prediction of protein-protein interfaces. In ESANN 2020 - Proceedings, 28th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, pages 127–132, 2020 (BibTex)

Abstract

Binding site identification allows to determine the function-ality and the quaternary structure of protein–protein complexes. Variousapproaches to this problem have been proposed without reaching a viablesolution. Representing the interacting peptides as graphs, a correspon-dence graph describing their interaction can be built. Finding the maxi-mum clique in the correspondence graph allows to identify the secondarystructure elements belonging to the interaction site. Although the max-imum clique problem is NP-complete, Graph Neural Networks make foran approximation tool that can solve the problem in affordable time. Ourexperimental results are promising and suggest that this direction shouldbe explored further.

You can find the full paper here