Enregistré dans:
Détails bibliographiques
Auteurs principaux: Cheng, Kaihui, Cai, Zhiqiang, Xiang, Wenkai, Hu, Zhihang, Zhu, Siyu, Yang, Tzuhsiung, Qi, Yuan
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2606.01833
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914622138744832
author Cheng, Kaihui
Cai, Zhiqiang
Xiang, Wenkai
Hu, Zhihang
Zhu, Siyu
Yang, Tzuhsiung
Qi, Yuan
author_facet Cheng, Kaihui
Cai, Zhiqiang
Xiang, Wenkai
Hu, Zhihang
Zhu, Siyu
Yang, Tzuhsiung
Qi, Yuan
contents Generative emulators of protein dynamics produce plausible trajectories at a fraction of the cost of molecular dynamics, but they inherit their training distribution and tend to revisit known states rather than reach rare ones under long-horizon extrapolation. Inspired by classical enhanced sampling, we introduce an implicit, history-dependent bias in the generative space of a pretrained emulator. Specifically, a history-aware score estimator augments the frozen emulator with a distance-weighted bias that steers reverse-time sampling away from previously generated structures, regularized by an environment-support term. To preserve structural validity at long horizons, a score-based refinement step re-projects drifted samples onto the data manifold using the frozen emulator. Our experiments demonstrate that the method (i) raises diversity by $35\%$ on DynamicPDB-80; (ii) on $12$ zero-shot Fast-Folding proteins, the learned bias alone reaches the unbiased emulator's coverage up to ${\sim}15\times$ faster, and pairing it with refinement reaches the coverage up to ${\sim}37\times$ faster while covering ${\sim}3\times$ as many low-energy states. Code will be released soon.
format Preprint
id arxiv_https___arxiv_org_abs_2606_01833
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Learning Implicit Bias in Generative Spaces for Accelerating Protein Dynamics Emulation
Cheng, Kaihui
Cai, Zhiqiang
Xiang, Wenkai
Hu, Zhihang
Zhu, Siyu
Yang, Tzuhsiung
Qi, Yuan
Machine Learning
Artificial Intelligence
Generative emulators of protein dynamics produce plausible trajectories at a fraction of the cost of molecular dynamics, but they inherit their training distribution and tend to revisit known states rather than reach rare ones under long-horizon extrapolation. Inspired by classical enhanced sampling, we introduce an implicit, history-dependent bias in the generative space of a pretrained emulator. Specifically, a history-aware score estimator augments the frozen emulator with a distance-weighted bias that steers reverse-time sampling away from previously generated structures, regularized by an environment-support term. To preserve structural validity at long horizons, a score-based refinement step re-projects drifted samples onto the data manifold using the frozen emulator. Our experiments demonstrate that the method (i) raises diversity by $35\%$ on DynamicPDB-80; (ii) on $12$ zero-shot Fast-Folding proteins, the learned bias alone reaches the unbiased emulator's coverage up to ${\sim}15\times$ faster, and pairing it with refinement reaches the coverage up to ${\sim}37\times$ faster while covering ${\sim}3\times$ as many low-energy states. Code will be released soon.
title Learning Implicit Bias in Generative Spaces for Accelerating Protein Dynamics Emulation
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2606.01833