DiSPA: Differential Substructure-Pathway Attention for Drug Response Prediction

2026-01-20

AI Summary

Existing methods struggle to capture the fine-grained, context-dependent interactions between chemical substructures of drugs and cellular pathway states, and are often confounded by noise and sparsity in high-dimensional biological data. This work proposes a bidirectional conditional modeling framework that explicitly disentangles structure-driven and context-driven mechanisms of drug response through a differential cross-attention mechanism, thereby amplifying genuine associations while suppressing spurious signals. The approach enables zero-shot transfer across diverse data modalities—from bulk RNA-seq to spatial transcriptomics—uncovering region-specific drug sensitivities. It achieves state-of-the-art performance on the GDSC benchmark, with particularly notable gains in unseen drug–cell line combinations. Moreover, its attention patterns recapitulate known pharmacophores and distinguish distinct mechanisms of action, offering both high predictive accuracy and interpretability.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Diffusion Models for Vision
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

Accurate prediction of drug response in precision medicine requires models that capture how specific chemical substructures interact with cellular pathway states. However, most existing deep learning approaches treat chemical and transcriptomic modalities independently or combine them only at late stages, limiting their ability to model fine-grained, context-dependent mechanisms of drug action. In addition, standard attention mechanisms are often sensitive to noise and sparsity in high-dimensional biological networks, hindering both generalization and interpretability. We present DiSPA, a representation learning framework that explicitly disentangles structure-driven and context-driven mechanisms of drug response through bidirectional conditioning between chemical substructures and pathway-level gene expression. DiSPA introduces a differential cross-attention module that suppresses spurious pathway-substructure associations while amplifying contextually relevant interactions. Across multiple evaluation settings on the GDSC benchmark, DiSPA achieves state-of-the-art performance, with particularly strong improvements in the disjoint-set setting, which assesses generalization to unseen drug-cell combinations. Beyond predictive accuracy, DiSPA yields mechanistically informative representations: learned attention patterns recover known pharmacophores, distinguish structure-driven from context-dependent compounds, and exhibit coherent organization across biological pathways. Furthermore, we demonstrate that DiSPA trained solely on bulk RNA-seq data enables zero-shot transfer to spatial transcriptomics, revealing region-specific drug sensitivity patterns without retraining. Together, these results establish DiSPA as a robust and interpretable framework for integrative pharmacogenomic modeling, enabling principled analysis of drug response mechanisms beyond post hoc interpretation.

Problem

• drug response prediction
• chemical substructures
• cellular pathways
• attention mechanisms
• pharmacogenomic modeling

Innovation

• differential cross-attention
• substructure-pathway interaction
• disentangled drug response modeling
• zero-shot transfer
• interpretable pharmacogenomics