arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.07237physics.comp-phcs.LGphysics.chem-ph
收藏

仅有力还不够:面向分子模拟的机器学习力场基准与关键评估

Forces are not Enough: Benchmark and Critical Evaluation for Machine Learning Force Fields with Molecular Simulations

Massachusetts Institute of Technology(麻省理工学院);Northwestern University(西北大学);Microsoft Research(微软研究院)

Xiang Fu, Zhenghao Wu, Wujie Wang, Tian Xie, Sinan Keten, Rafael Gomez-Bombarelli, Tommi Jaakkola

AI总结:

该研究针对现有机器学习力场多以力/能量误差为基准、与实际分子动力学模拟需求脱节的问题,构建了覆盖多体系的新型基准套件与对应指标,测试发现力精度与模拟指标匹配度低,指出稳定性是核心改进方向,并配套开源代码库。

摘要:

分子动力学(MD)模拟技术被广泛应用于各类自然科学研究场景。机器学习(ML)力场(FF)模型可直接从原子结构预测力,正逐渐取代从头算模拟。尽管该领域已取得显著进展,但这类技术目前主要以力/能量预测误差作为基准评估指标,而其实际应用场景是生成符合真实情况的MD轨迹。我们旨在填补这一空白,推出一套面向学习型MD模拟的新型基准套件。我们遴选了具有代表性的MD体系,涵盖水、有机分子、一种肽以及材料体系,并针对各体系的科学研究目标设计了相应的评估指标。我们对一系列当前最优(SOTA)的ML FF模型开展基准测试,尤其阐明了常用的力精度基准指标与相关模拟指标的匹配度并不高。我们揭示了选定的SOTA方法在何种情况下、以何种方式失效,并给出了后续改进方向。具体而言,我们发现稳定性是ML模型需要提升的一项关键指标。我们的基准套件配套有全面的开源代码库,可用于ML FF的训练与模拟,为后续相关研究提供便利。

英文摘要:

Molecular dynamics (MD) simulation techniques are widely used for various natural science applications. Increasingly, machine learning (ML) force field (FF) models begin to replace ab-initio simulations by predicting forces directly from atomic structures. Despite significant progress in this area, such techniques are primarily benchmarked by their force/energy prediction errors, even though the practical use case would be to produce realistic MD trajectories. We aim to fill this gap by introducing a novel benchmark suite for learned MD simulation. We curate representative MD systems, including water, organic molecules, a peptide, and materials, and design evaluation metrics corresponding to the scientific objectives of respective systems. We benchmark a collection of state-of-the-art (SOTA) ML FF models and illustrate, in particular, how the commonly benchmarked force accuracy is not well aligned with relevant simulation metrics. We demonstrate when and how selected SOTA methods fail, along with offering directions for further improvement. Specifically, we identify stability as a key metric for ML models to improve. Our benchmark suite comes with a comprehensive open-source codebase for training and simulation with ML FFs to facilitate future work.

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。

↑