Where Black-box Drug-Target Interaction Prediction Models Look: Cross-Method Explainability

2026-06-12

AI Summary

Black-box drug–target interaction (DTI) prediction models suffer from limited interpretability, hindering their trustworthy application in drug discovery. This work addresses this challenge by proposing a cross-method consensus strategy for the BridgeDPI model, integrating gradient-based attribution techniques—including Integrated Gradients, SmoothGrad, saliency maps, and Layer-wise Relevance Propagation—with feature- and edge-level masking ablation to systematically dissect its reliance on sequence, fingerprint, and graph modalities. The study uncovers modality dominance patterns and dataset-dependent effects, while identifying key pharmacophoric fragments and structural motifs that align with established chemical knowledge. These findings yield testable hypotheses for experimental validation and significantly enhance the transparency and biological plausibility of the model’s predictions.

Abstract

Drug-target interaction (DTI) and affinity (DTA) predictors increasingly achieve strong benchmark scores, yet their internal use of sequence, fingerprint, and graph features often remains opaque. We present an interpretability audit of BridgeDPI architecture on three different datasets including Gao, Human, and C.elegans. This study combines gradient-based attributions -- integrated gradients, saliency, layer-wise relevance propagation, SmoothGrad, and SmoothGrad-IG -- with feature-wise occlusion ablation and strict intersection consensus across methods to reduce single-explainer bias. We summarize sensitivity and signed effects at raw inputs, at the bridge similarity scaffold, and through the graph convolution, including edge-level sensitivities and targeted edge removals. The results show that explainability is most informative when treated as model criticism: it reveals modality dominance, padding and special-token artifacts, dataset-dependent cooperative versus suppressive effects across layers, and chemistry-consistent fragment and composition motifs where methods agree. These analyses do not substitute for structural or experimental ground truth, yet they can provide testable hypotheses for downstream validation in computational drug discovery pipelines. More broadly, applying modern XAI to contemporary DTI/DTA models is still an early pass over the rich structure implicit in trained weights and data -- yet even this first layer of scrutiny already helps researchers relate predictions to drug- and target-side representations and to prioritize external validation.

Problem

• Drug-Target Interaction
• Explainability
• Black-box Models
• Interpretability
• Deep Learning

Innovation

• Explainable AI (XAI)
• Drug-Target Interaction
• Model Interpretability
• Gradient-based Attribution
• Graph Neural Networks