[Submitted on 16 Nov 2026]
View a PDF of the paper titled tmol: a GPU-accelerated implementation of the Rosetta energy function for machine learning, by Andrew Leaver-Fay and Kieran Didi and Jeff Flatten and Alex Ford and Guangfeng Zhou and Nathaniel Corley and Hahnbeom Park and Maxwell W. Kazman and Rafael I. Brent and Joseph Kleinhenz and Henry Solberg and Andrew M. Watkins and Brian Kuhlman and David Baker and Frank DiMaio
Abstract:Physics-inspired forcefields complement generative machine learning models, showing better generalization beyond the training distribution. However, these forcefields are typically slow to evaluate, and their derivatives are difficult to integrate into ML frameworks. We introduce tmol, a GPU-native PyTorch library implementing the state-of-the-art RosettaGenFF forcefield. tmol supports efficient batched differentiable scoring and whole-structure refinement with up to 362-fold throughput increase (batched). Used as a reward in generative protein design, tmol increases hydrogen bonds and water bridges at designed interfaces.
Submission history
From: Andrew Leaver-Fay [view email]
[v1]
Mon, 16 Nov 2026 20:20:33 UTC (17,875 KB)
