ProDyn0: Inferring calponin homology domain stretching behavior using graph neural networks

TL;DR

This paper introduces a graph neural network approach to predict the stretching behavior of calponin homology domains, using a new molecular dynamics dataset to improve understanding of protein mechanics.

Contribution

It develops neural message passing and residual gated graph convnets for protein force response prediction, and presents a benchmark dataset for graph neural network evaluation in biophysics.

Findings

Achieved 86.63% accuracy in force response prediction

Predicted force-related properties with MAEs of 81.59 kJ/mol/nm and 76.99 psec

Provided a new benchmark dataset for graph neural network applications in protein biophysics

Abstract

Graph neural networks are a quickly emerging field for non-Euclidean data that leverage the inherent graphical structure to predict node, edge, and global-level properties of a system. Protein properties can not easily be understood as a simple sum of their parts (i.e. amino acids), therefore, understanding their dynamical properties in the context of graphs is attractive for revealing how perturbations to their structure can affect their global function. To tackle this problem, we generate a database of 2020 mutated calponin homology (CH) domains undergoing large-scale separation in molecular dynamics. To predict the mechanosensitive force response, we develop neural message passing networks and residual gated graph convnets which predict the protein dependent force separation at 86.63 percent, 81.59 kJ/mol/nm MAE, 76.99 psec MAE for force mode classification, max force magnitude, max force time respectively-- significantly better than non-graph-based deep learning techniques. Towards uniting geometric learning techniques and biophysical observables, we premiere our simulation database as a benchmark dataset for further development/evaluation of graph neural network architectures.