MAXWELL: Calibrating the probabilistic outputs of protein language models to the mutation-induced stability change landscape
Mingchen Li, Xiaoran Cheng, Fan Jiang, Liang Hong, Yuanxi Yu
MAXWELL calibrates protein language models to predict mutation-induced stability changes, outperforming existing methods and successfully designing stabilizing mutations in DhaA dehalogenase.
bioRxiv · Aug 4, 2026 · PreprintBioinformatics