Pre-training of Graph Neural Network for Modeling Effects of Mutations on Protein-Protein Binding Affinity

TL;DR

This paper introduces GraphPPI, a novel graph neural network framework that pre-trains on protein structures to accurately predict how mutations affect protein-protein binding affinity, advancing protein engineering and drug design.

Contribution

The study presents a new pre-training scheme for GNNs that captures mutation effects without labeled data, achieving state-of-the-art prediction accuracy on multiple datasets.

Findings

GraphPPI captures meaningful structural features without annotated signals.

Achieves state-of-the-art performance on benchmark mutation datasets.

Accurately predicts mutation effects on SARS-CoV-2 antibody binding.

Abstract

Modeling the effects of mutations on the binding affinity plays a crucial role in protein engineering and drug design. In this study, we develop a novel deep learning based framework, named GraphPPI, to predict the binding affinity changes upon mutations based on the features provided by a graph neural network (GNN). In particular, GraphPPI first employs a well-designed pre-training scheme to enforce the GNN to capture the features that are predictive of the effects of mutations on binding affinity in an unsupervised manner and then integrates these graphical features with gradient-boosting trees to perform the prediction. Experiments showed that, without any annotated signals, GraphPPI can capture meaningful patterns of the protein structures. Also, GraphPPI achieved new state-of-the-art performance in predicting the binding affinity changes upon both single- and multi-point mutations on five benchmark datasets. In-depth analyses also showed GraphPPI can accurately estimate the effects of mutations on the binding affinity between SARS-CoV-2 and its neutralizing antibodies. These results have established GraphPPI as a powerful and useful computational tool in the studies of protein design.