DeepRank-GNN-esm: A Graph Neural Network for Scoring Protein-Protein Models using Protein Language Model

Abstract

Motivation Protein-Protein interactions (PPIs) play critical roles in numerous cellular processes. By modelling the three-dimensional structures of the correspond protein complexes valuable insights can be obtained, providing, for example, starting points for drug and protein design. One challenge in the modelling process is however the identification of near-native models from the large pool of generated models. To this end we previously developed DeepRank-GNN, a graph neural network that integrates structural and sequence information to enable effective pattern learning at PPI interfaces. Its main features are related to the Position Specific Scoring Matrices (PSSM), which are computationally expensive to generate and significantly limit the algorithm’s usability. Results We introduce here DeepRank-GNN-esm that includes as additional features protein language model embeddings from the EMS-2 model. We show that the ESM-2 embeddings can actually replace the PSSM features at no cost in-, or even better performance on two PPI-related tasks: scoring docking poses and detecting crystal artifacts. This new DeepRank version bypasses thus the need of generating PSSM, greatly improving the usability of the software and opening new application opportunities for systems for which PSSM profiles cannot be obtained or are irrelevant (e.g. antibody-antigen complexes).