Model Validation Protocols for Machine Learning in Small Molecule Drug Discovery
Srijit Seal, Akshat Shirish Zalte, David Alencar Araripe, Renan Augusto Gomes, Deepa Korani, Mrinal Shekhar, Vishal B. Siramshetty, Arijit Patra, Zhongyu Mou, Xiang Yu, Daniel Kühn, Nils Weskamp, Jeremy R. Ash, Alan C. Cheng, Cheng Fang, , Cas Wognum
The paper presents a model validation framework for molecular property prediction models in drug discovery, revealing four failure modes and showing that common evaluation protocols overestimate performance.
bioRxiv · Aug 24, 2026 · PreprintBioinformatics