Explainable Deep Relational Networks for Predicting Compound-Protein Affinities and Contacts
This addresses the need for interpretable machine learning in drug discovery, offering a novel approach that is not incremental but specifically designed for this domain.
The paper tackled the problem of predicting compound-protein affinity with a focus on interpretability, introducing DeepRelations, a physics-inspired deep relational network that improves contact prediction AUPRC by up to 19.3-fold without compromising affinity accuracy.
Predicting compound-protein affinity is critical for accelerating drug discovery. Recent progress made by machine learning focuses on accuracy but leaves much to be desired for interpretability. Through molecular contacts underlying affinities, our large-scale interpretability assessment finds commonly-used attention mechanisms inadequate. We thus formulate a hierarchical multi-objective learning problem whose predicted contacts form the basis for predicted affinities. We further design a physics-inspired deep relational network, DeepRelations, with intrinsically explainable architecture. Specifically, various atomic-level contacts or "relations" lead to molecular-level affinity prediction. And the embedded attentions are regularized with predicted structural contexts and supervised with partially available training contacts. DeepRelations shows superior interpretability to the state-of-the-art: without compromising affinity prediction, it boosts the AUPRC of contact prediction 9.5, 16.9, 19.3 and 5.7-fold for the test, compound-unique, protein-unique, and both-unique sets, respectively. Our study represents the first dedicated model development and systematic model assessment for interpretable machine learning of compound-protein affinity.