arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.11216cs.LGphysics.bio-ph
收藏

蛋白质语言模型嵌入提升隐式转移算子的泛化能力

Protein Language Model Embeddings Improve Generalization of Implicit Transfer Operators

University of Copenhagen(哥本哈根大学);Chalmers University of Technology(查尔姆斯理工大学);University of Gothenburg(哥德堡大学);Technical University of Denmark(丹麦技术大学)

Panagiotis Antoniadis, Beatrice Pavesi, Simon Olsson, Ole Winther

AI总结:

本研究提出PLaTITO方法,通过整合蛋白质语言模型嵌入改进隐式转移算子,在分子动力学中实现更高效的数据利用和跨分子系统的泛化,在非平衡蛋白质系统采样中达到最优性能。

摘要:

分子动力学(MD)是物理学、化学和生物学中的核心计算工具,能够将实验可观测量作为高维分子分布(如玻尔兹曼分布和转移密度)的期望进行定量预测。然而,传统MD受到生成独立样本所需高计算成本的根本限制。生成式分子动力学(GenMD)最近作为一种替代方案出现,通过数据或与能量模型交互学习分子分布的替代模型。尽管这些方法实现了高效采样,但它们在不同分子系统间的可迁移性通常有限。在本工作中,我们表明整合辅助信息源可以提高可迁移隐式转移算子(TITO)在分子动力学中的数据效率和泛化能力。我们发现粗粒化TITO模型比玻尔兹曼模拟器在数据效率上显著更高,并且整合蛋白质语言模型(pLM)嵌入进一步改善了分布外泛化。我们的方法PLaTITO在非平衡蛋白质系统(包括快速折叠蛋白质)的平衡采样基准测试中达到了最先进的性能。我们进一步研究了额外条件信号(如结构嵌入、温度和大语言模型衍生嵌入)对模型性能的影响。

英文摘要:

Molecular dynamics (MD) is a central computational tool in physics, chemistry, and biology, enabling quantitative prediction of experimental observables as expectations over high-dimensional molecular distributions such as Boltzmann distributions and transition densities. However, conventional MD is fundamentally limited by the high computational cost required to generate independent samples. Generative molecular dynamics (GenMD) has recently emerged as an alternative, learning surrogates of molecular distributions either from data or through interaction with energy models. While these methods enable efficient sampling, their transferability across molecular systems is often limited. In this work, we show that incorporating auxiliary sources of information can improve the data efficiency and generalization of transferable implicit transfer operators (TITO) for molecular dynamics. We find that coarse-grained TITO models are substantially more data-efficient than Boltzmann Emulators, and that incorporating protein language model (pLM) embeddings further improves out-of-distribution generalization. Our approach, PLaTITO, achieves state-of-the-art performance on equilibrium sampling benchmarks for out-of-distribution protein systems, including fast-folding proteins. We further study the impact of additional conditioning signals such as structural embeddings, temperature, and large-language-model-derived embeddings on model performance.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑