SADRP: A structurally aware multi-modal framework for drug response prediction.

SADRP outperforms state-of-the-art methods in drug response prediction by effectively modeling molecular structures and multi-omics data in cancer samples.

• Why it matters: Accurately predicting drug sensitivity is crucial for personalized cancer therapy and drug discovery, but current methods struggle to fully capture complex structural and multi-omics features.
• What they did: The framework uses SDP and edge encoding to represent drug structures and a multi-view encoder to integrate gene expression and DNA methylation, jointly modeling molecular and cellular features.
• The result: SADRP not only improves prediction accuracy but also identifies potential therapeutic candidates and biomarkers, enabling mechanistic insights and advancing personalized medicine.