Tag
A study presenting a cross-method explainability audit of the BridgeDPI drug-target interaction model, combining gradient-based attributions and occlusion to reveal modality dominance and artifacts, providing testable hypotheses for drug discovery.
This paper introduces I-SAFE, a post-hoc distributional auditing framework for scientific AI models using Wasserstein Coherence Metrics, which reveals structural differences in model outputs that accuracy-based evaluation fails to capture. Demonstrated on drug-target interaction prediction, the framework is model-agnostic and applicable to any domain with structured inputs and external priors.