A comprehensive review recently published in\u00a0Current Molecular Pharmacology\u00a0(2026, Volume 19, Pages 85\u201396) examines the rapidly evolving landscape of computational tools for predicting tumour drug resistance. Led by Jia Wang, Hong\u2011Rui Zhu, and corresponding authors Zhi\u2011Chun Gu and Hou\u2011Wen Lin from Shanghai Jiao Tong University School of Medicine, the article systematically maps how artificial intelligence-particularly machine and deep learning-is being harnessed to integrate multi\u2011omics data from large\u2011scale repositories such as TCGA and GDSC. These approaches are helping to decode resistance mechanisms across chemotherapy, targeted therapy, and immunotherapy, while also pointing to novel predictive dimensions such as cancer\u2011associated thrombosis.<\/p>\n
The authors emphasize that standardised databases and sophisticated preprocessing pipelines are now essential for transforming heterogeneous genomic, transcriptomic, and clinical data into reliable model inputs. Yet they caution that data sparsity, batch effects, and the “black\u2011box” nature of many deep\u2011learning models remain substantial barriers to clinical adoption. “The inherent trade\u2011off between model accuracy and interpretability undermines clinician trust and limits real\u2011world adoption,” notes Dr. Gu. To address this, the review advocates for explainable AI frameworks, multimodal fusion strategies, and the integration of dynamic liquid\u2011biopsy<\/a> monitoring to capture resistance evolution in real time.<\/p>\n Looking forward, the team calls for a paradigm shift towards specialised tools for high\u2011risk subgroups, particularly patients with cancer\u2011associated thrombosis. By incorporating coagulation\u2011related signatures and longitudinal thrombotic markers, these next\u2011generation models could offer actionable predictions that guide combined anticancer and anticoagulant therapies. The authors also urge the establishment of unified data standards, prospective clinical validation, and interdisciplinary collaboration to bridge the gap between computational innovation and bedside application. “Our goal is to move beyond generic predictions and deliver tailored insights for the patients who need them most,” adds Professor Lin. The review concludes that with sustained efforts in data integration, interpretability, and clinical translation, AI\u2011driven resistance prediction holds transformative potential for precision oncology.<\/p>\n Source:<\/p>\n Journal reference:<\/p>\n