Scalable emulation of protein equilibrium ensembles with generative deep learning

• 成果类型: Article
• 署名作者: Lewis, Sarah; Hempel, Tim; Jimenez-Luna, Jose; Gastegger, Michael; Xie, Yu; Foong, Andrew Y. K.; Satorras, Victor Garcia; Abdin, Osama; Veeling, Bastiaan S.; Zaporozhets, Iryna; Chen, Yaoyi; Yang, Soojung; Foster, Adam E.; Schneuing, Arne; Nigam, Jigyasa; Barbero, Federico; Stimper, Vincent; Campbell, Andrew; Yim, Jason; Lienen, Marten; Shi, Yu; Zheng, Shuxin; Schulz, Hannes; Munir, Usman; Sordillo, Roberto; Tomioka, Ryota; Clementi, Cecilia; Noe, Frank
• 署名单位: Microsoft; Free University of Berlin; Rice University
• 刊物名称: SCIENCE
• ISSN/ISSBN: 0036-8465
• DOI: 10.1126/science.adv9817
• 发表日期: 2025-08-14
• 关键词: crystal-structure; escherichia-coli; molecular-dynamics; force-field; adenylate kinase; side-chain; ras p21; simulations; RESOLUTION; mechanism

摘要

Following the sequence and structure revolutions, predicting functionally relevant protein structure changes at scale remains an outstanding challenge. We introduce BioEmu, a deep learning system that emulates protein equilibrium ensembles by generating thousands of statistically independent structures per hour on a single graphics processing unit (GPU). BioEmu integrates more than 200 milliseconds of molecular dynamics (MD) simulations, static structures, and experimental protein stabilities using new training algorithms. It captures diverse functional motions-including cryptic pocket formation, local unfolding, and domain rearrangements-and predicts relative free energies with 1 kilocalorie per mole accuracy compared with millisecond-scale MD and experimental data. BioEmu provides mechanistic insights by jointly modeling structural ensembles and thermodynamic properties. This approach amortizes the cost of MD and experimental data generation, demonstrating a scalable path toward understanding and designing protein function.