G-PLIP: Knowledge graph neural network for structure-free protein-ligand affinity prediction

Abstract

Protein-ligand interaction (PLI) shapes efficacy and safety profiles of small molecule drugs. Existing methods rely on either structural information or resource-intensive computation to predict PLI, making us wonder whether it is possible to perform structure-free PLI prediction with low computational cost. Here we show that a light-weight graph neural network (GNN), trained with quantitative PLIs of a small number of proteins and ligands, is able to predict the strength of unseen PLIs. The model has no direct access to structural information of protein-ligand complexes. Instead, the predictive power is provided by encoding the entire chemical and proteomic space in a single heterogeneous graph, encapsulating primary protein sequence, gene expression, protein-protein interaction network, and structural similarities between ligands. The novel model performs competitively with or better than structure-aware models. Our observations suggest that existing PLI-prediction methods may be further improved by using representation learning techniques that embed biological and chemical knowledge.