ContactNet: Geometric-Based Deep Learning Model for Predicting Protein-Protein Interactions

TL;DR

ContactNet is a novel attention-based Graph Neural Network that accurately classifies protein-protein interaction models without requiring multiple sequence alignments, significantly improving scoring accuracy over existing methods.

Contribution

The paper introduces ContactNet, a GNN-based model that enhances PPI model classification accuracy without MSA, applicable to various interaction types.

Findings

Doubles the accuracy of state-of-the-art scoring functions.

Achieves 43% Top-10 accuracy on docked antigen-antibody models.

Reaches 65% Top-10 accuracy on unbound antibody interactions.

Abstract

Deep learning approaches achieved significant progress in predicting protein structures. These methods are often applied to protein-protein interactions (PPIs) yet require Multiple Sequence Alignment (MSA) which is unavailable for various interactions, such as antibody-antigen. Computational docking methods are capable of sampling accurate complex models, but also produce thousands of invalid configurations. The design of scoring functions for identifying accurate models is a long-standing challenge. We develop a novel attention-based Graph Neural Network (GNN), ContactNet, for classifying PPI models obtained from docking algorithms into accurate and incorrect ones. When trained on docked antigen and modeled antibody structures, ContactNet doubles the accuracy of current state-of-the-art scoring functions, achieving accurate models among its Top-10 at 43% of the test cases. When applied to unbound antibodies, its Top-10 accuracy increases to 65%. This performance is achieved without MSA and the approach is applicable to other types of interactions, such as host-pathogens or general PPIs.