[2603.26114] DPD-Cancer: Explainable Graph-based Deep Learning for Small Molecule Anti-Cancer Activity Prediction

Computer Science > Machine Learning arXiv:2603.26114 (cs) [Submitted on 27 Mar 2026] Title:DPD-Cancer: Explainable Graph-based Deep Learning for Small Molecule Anti-Cancer Activity Prediction Authors:Magnus H. Strømme, Alex G. C. de Sá, David B. Ascher View a PDF of the paper titled DPD-Cancer: Explainable Graph-based Deep Learning for Small Molecule Anti-Cancer Activity Prediction, by Magnus H. Str{\o}mme and 2 other authors View PDF Abstract:Accurate drug response prediction is a critical bottleneck in computational biochemistry, limited by the challenge of modelling the interplay between molecular structure and cellular context. In cancer research, this is acute due to tumour heterogeneity and genomic variability, which hinder the identification of effective therapies. Conventional approaches often fail to capture non-linear relationships between chemical features and biological outcomes across diverse cell lines. To address this, we introduce DPD-Cancer, a deep learning method based on a Graph Attention Transformer (GAT) framework. It is designed for small molecule anti-cancer activity classification and the quantitative prediction of cell-line specific responses, specifically growth inhibition concentration (pGI50). Benchmarked against state-of-the-art methods (pdCSM-cancer, ACLPred, and MLASM), DPD-Cancer demonstrated superior performance, achieving an Area Under ROC Curve (AUC) of up to 0.87 on strictly partitioned NCI60 data and up to 0.98 on ACLPred/MLASM datasets...