TMol brings Rosetta-style all-atom molecular energetics into differentiable PyTorch
gottapatchemall · x · 2026-11-19
Following up on the RFD4-Proteina thread, DidiKieran released the TMol paper on arXiv. TMol implements Rosetta-style all-atom energies with GPU batching and gradients in PyTorch, letting you put molecular energetics directly into your model — combining deep learning with physics.
It covers proteins, L/D residues, β/γ backbones, small molecules, modified DNA/RNA, PTMs, N-methyl peptides, cyclic peptides, and metals/cofactors, organized via PoseStack, and exposes Score, Minimize, Repack, FastRelax, and differentiable operations for protein design and molecular simulation.
More from Research
- Hashimoto's Stanford CS312 quiz: what happens if you untie a looped Transformer mid-training? — tatsu_hashimoto · 2026-11-19
- Stanford CS312 experiment: looping transformers lose; mid-training untying recovers 61% of gap — tatsu_hashimoto · 2026-11-19
- Benchtop synthesis device releases have 3x'd; half of active manufacturers are in China — JacquesThibs · 2026-11-19
- Perceptron launches Ego 1.0 API: egocentric video annotation at ~1/8 the cost of Astra — AkshatS07 · 2026-11-19
- Oxford paper: post-training makes LLM worldviews bleaker, models converge on 'spiritual bliss' — twiecki · 2026-11-19
- Researcher: Real scientific progress isn't rewarded, expect decades of incrementalism — gerardsans · 2026-11-19