Decoding the Protein-ligand Interactions Using Parallel Graph Neural Networks

TL;DR

This paper introduces a novel parallel graph neural network approach for predicting protein-ligand interactions using 3D structural data, outperforming traditional 2D sequence-based models and aiding drug discovery.

Contribution

The study develops two GNN architectures, GNNF and GNNP, that incorporate 3D structural information for improved PLI prediction and activity estimation, with GNNP functioning without prior interaction knowledge.

Findings

GNNF achieves 97.9% test accuracy in interaction prediction.

GNNP achieves 95.8% test accuracy, even without prior interaction knowledge.

The models outperform existing 2D sequence-based methods in predicting binding affinity and activity.

Abstract

Protein-ligand interactions (PLIs) are fundamental to biochemical research and their identification is crucial for estimating biophysical and biochemical properties for rational therapeutic design. Currently, experimental characterization of these properties is the most accurate method, however, this is very time-consuming and labor-intensive. A number of computational methods have been developed in this context but most of the existing PLI prediction heavily depends on 2D protein sequence data. Here, we present a novel parallel graph neural network (GNN) to integrate knowledge representation and reasoning for PLI prediction to perform deep learning guided by expert knowledge and informed by 3D structural data. We develop two distinct GNN architectures, GNNF is the base implementation that employs distinct featurization to enhance domain-awareness, while GNNP is a novel implementation that can predict with no prior knowledge of the intermolecular interactions. The comprehensive evaluation demonstrated that GNN can successfully capture the binary interactions between ligand and proteins 3D structure with 0.979 test accuracy for GNNF and 0.958 for GNNP for predicting activity of a protein-ligand complex. These models are further adapted for regression tasks to predict experimental binding affinities and pIC50 is crucial for drugs potency and efficacy. We achieve a Pearson correlation coefficient of 0.66 and 0.65 on experimental affinity and 0.50 and 0.51 on pIC50 with GNNF and GNNP, respectively, outperforming similar 2D sequence-based models. Our method can serve as an interpretable and explainable artificial intelligence (AI) tool for predicted activity, potency, and biophysical properties of lead candidates. To this end, we show the utility of GNNP on SARS-Cov-2 protein targets by screening a large compound library and comparing our prediction with the experimentally measured data.