Explainable Deep Relational Networks for Predicting Compound-Protein Affinities and Contacts

Abstract

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.

References in corpus (14)

• Semi-Supervised Classification with Graph Convolutional Networks
• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• Towards A Rigorous Science of Interpretable Machine Learning
• DeepDTA: Deep Drug-Target Binding Affinity Prediction
• Accurate De Novo Prediction of Protein Contact Map by Ultra-Deep Learning Model
• DeepConv-DTI: Prediction of drug-target interactions via deep learning with convolution on protein sequences
• Interaction Networks for Learning about Objects, Relations and Physics
• DeepAffinity: Interpretable Deep Learning of Compound-Protein Affinity through Unified Recurrent and Convolutional Neural Networks
• AtomNet: A Deep Convolutional Neural Network for Bioactivity Prediction in Structure-based Drug Discovery
• How Powerful are Graph Neural Networks?
• Using Attribution to Decode Dataset Bias in Neural Network Models for Chemistry
• Atomic Convolutional Networks for Predicting Protein-Ligand Binding Affinity
• Learning Longer-term Dependencies in RNNs with Auxiliary Losses
• Evaluating Explanation Without Ground Truth in Interpretable Machine Learning

Cited by in corpus (1)

• Cross-Modality Protein Embedding for Compound-Protein Affinity and Contact Prediction