Multiscale Graph Neural Networks for Protein Residue Contact Map Prediction

TL;DR

This paper introduces a multiscale graph neural network approach that enhances the accuracy of protein residue contact map predictions across all distance ranges, especially long-range contacts, by integrating GNNs with RNNs.

Contribution

It presents a novel multiscale GNN framework combined with RNNs for improved protein contact prediction across short, medium, and long-range contacts.

Findings

Improved accuracy for all contact ranges.

Significant enhancement in long-range contact prediction.

Outperforms conventional methods on ProteinNet dataset.

Abstract

Machine learning (ML) is revolutionizing protein structural analysis, including an important subproblem of predicting protein residue contact maps, i.e., which amino-acid residues are in close spatial proximity given the amino-acid sequence of a protein. Despite recent progresses in ML-based protein contact prediction, predicting contacts with a wide range of distances (commonly classified into short-, medium- and long-range contacts) remains a challenge. Here, we propose a multiscale graph neural network (GNN) based approach taking a cue from multiscale physics simulations, in which a standard pipeline involving a recurrent neural network (RNN) is augmented with three GNNs to refine predictive capability for short-, medium- and long-range residue contacts, respectively. Test results on the ProteinNet dataset show improved accuracy for contacts of all ranges using the proposed multiscale RNN+GNN approach over the conventional approach, including the most challenging case of long-range contact prediction.