Baker lab open-sources tmol: GPU Rosetta force field with up to 362x throughput
AllThingsApx · x · 2026-11-19
tmol (arXiv:2611.21857) is a GPU-native PyTorch library implementing the state-of-the-art RosettaGenFF force field, from Andrew Leaver-Fay, Kieran Didi, David Baker, Frank DiMaio and colleagues.
- Motivation: physics-inspired force fields generalize better beyond training distributions than generative models, but are slow and hard to differentiate in ML frameworks.
- Capability: efficient batched differentiable scoring and whole-structure refinement with up to 362-fold throughput increase (batched).
- Impact: used as a reward in generative protein design, it increases hydrogen bonds and water bridges at designed interfaces.
- Install: pip install tmol (CPU) or pip install "tmol[cu12]" / "tmol[cu13]" (GPU); code and docs are open.
Community members note TMol was a 'secret weapon' behind RFD4-Proteina, uniting AI and physics on GPU.
More from Research
- HiT Learns Its Own Abstraction Hierarchy End-to-End, Hits 1.48 FID on ImageNet 256 — niloofar_mire · 2026-11-19
- Interpretability solved—then what? Najoung Kim proposes filtering for recurrent constructs — najoungkim · 2026-11-19
- New preprint asks: if interpretability is "solved," what does it mean for the science of human language? — najoungkim · 2026-11-19
- Map of tabular foundation models shows only two are fully open — GaelVaroquaux · 2026-11-19
- Google open-sources TPU codesign guide: 8 principles for LLM/MoE performance — rseroter · 2026-11-19
- TMol was the 'secret weapon' behind RFD4-Proteina, researchers reveal — AllThingsApx · 2026-11-19