arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.03753cs.LGphysics.comp-ph
收藏

基于不确定性的集体变量增强鲁棒分子数据集采样

Enhanced sampling of robust molecular datasets with uncertainty-based collective variables

Massachusetts Institute of Technology(麻省理工学院);University of Vienna(维也纳大学)

Aik Rui Tan, Johannes C. B. Dietschreit, Rafael Gomez-Bombarelli

AI总结:

本研究提出利用不确定性作为集体变量指导分子数据采样,通过高斯混合模型度量驱动偏置分子动力学,在丙氨酸二肽上验证了其克服势垒、增强主动学习数据集的效果。

摘要:

生成一个能代表分子系统可及构象空间的数据集,对于机器学习原子间势(MLIP)的鲁棒性至关重要。然而,分子系统的复杂性,其特征是具有众多局部极小值和能量势垒的复杂势能面(PESs),构成了重大挑战。传统的数据生成方法,如随机采样或穷举探索,要么不可行,要么可能无法捕获稀有但信息量大的构象。在本研究中,我们提出了一种方法,利用不确定性作为集体变量(CV)来指导获取化学相关数据点,重点关注机器学习模型预测最不确定的构象空间区域。该方法采用基于高斯混合模型的不确定性度量,从单一模型作为偏置分子动力学模拟的集体变量。我们在丙氨酸二肽基准系统上证明了该方法在克服能量势垒和探索未见能量极小值方面的有效性,从而在主动学习框架中增强了数据集。

英文摘要:

Generating a data set that is representative of the accessible configuration space of a molecular system is crucial for the robustness of machine learned interatomic potentials (MLIP). However, the complexity of molecular systems, characterized by intricate potential energy surfaces (PESs) with numerous local minima and energy barriers, presents a significant challenge. Traditional methods of data generation, such as random sampling or exhaustive exploration, are either intractable or may not capture rare, but highly informative configurations. In this study, we propose a method that leverages uncertainty as the collective variable (CV) to guide the acquisition of chemically-relevant data points, focusing on regions of the configuration space where ML model predictions are most uncertain. This approach employs a Gaussian Mixture Model-based uncertainty metric from a single model as the CV for biased molecular dynamics simulations. The effectiveness of our approach in overcoming energy barriers and exploring unseen energy minima, thereby enhancing the data set in an active learning framework, is demonstrated on the alanine dipeptide benchmark system.

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。

↑