Does a Machine-Learned Potential Perform Better Than an Optimally Tuned Traditional Force Field? A Case Study on Fluorohydrins.
Does a Machine-Learned Potential Perform Better Than an Optimally Tuned Traditional Force Field? A Case Study on Fluorohydrins.
复制标题
DOI：
10.1021/acs.jcim.2c01510
复制
发表时间：
2023-05-08
影响因子：
5.6
通讯作者：
Skylaris, Chris-Kriton
中科院分区：
文献类型：
--
作者：
Morado, Joao;Mortenson, Paul N.;Nissink, J. Willem M.;Essex, Jonathan W.;Skylaris, Chris-Kriton
我们提出了一项比较研究，评估了机器学习势（ANI-2x），常规力场（GAFF）和最佳调整的GAFF样力场在一组10个γ-氟代醇的建模中的性能，这些γ-氟代醇在确定构象稳定性时表现出分子内和分子间相互作用之间的复杂相互作用。为了对每个分子模型的性能进行基准测试，我们评估了它们相对于量子力学数据的能量、几何和采样精度。该基准涉及气相和氯仿溶液中的构象分析。我们还评估了上述分子模型在估计核自旋-自旋耦合常数的性能，通过比较他们的预测，实验数据在氯仿中。在这项研究中提出的结果和讨论表明，ANI-2x倾向于预测强于预期的氢键和过度稳定的全球最小值，并显示与色散相互作用的描述不足的问题。此外，虽然ANI-2x是气相建模的可行模型，但传统力场仍然发挥着重要作用，特别是对于凝相模拟。总的来说，这项研究强调了每个模型的优点和缺点，为力场和机器学习潜力的使用和未来发展提供了指导方针。
We present a comparative study that evaluates the performance of a machine learning potential (ANI-2x), a conventional force field (GAFF), and an optimally tuned GAFF-like force field in the modeling of a set of 10 γ-fluorohydrins that exhibit a complex interplay between intra- and intermolecular interactions in determining conformer stability. To benchmark the performance of each molecular model, we evaluated their energetic, geometric, and sampling accuracies relative to quantum-mechanical data. This benchmark involved conformational analysis both in the gas phase and chloroform solution. We also assessed the performance of the aforementioned molecular models in estimating nuclear spin–spin coupling constants by comparing their predictions to experimental data available in chloroform. The results and discussion presented in this study demonstrate that ANI-2x tends to predict stronger-than-expected hydrogen bonding and overstabilize global minima and shows problems related to inadequate description of dispersion interactions. Furthermore, while ANI-2x is a viable model for modeling in the gas phase, conventional force fields still play an important role, especially for condensed-phase simulations. Overall, this study highlights the strengths and weaknesses of each model, providing guidelines for the use and future development of force fields and machine learning potentials.
登录
查看更多内容
影响因子：
13.6
作者：
Bartók AP;De S;Poelking C;Bernstein N;Kermode JR;Csányi G;Ceriotti M
通讯作者：
Ceriotti M
影响因子：
1.7
作者：
DITCHFIELD, R
通讯作者：
DITCHFIELD, R
影响因子：
4.4
作者：
Christensen, Anders S.;Bratholm, Lars A.;von Lilienfeld, O. Anatole
通讯作者：
von Lilienfeld, O. Anatole
影响因子：
8.6
作者：
Behler, Joerg;Parrinello, Michele
通讯作者：
Parrinello, Michele
影响因子：
3.7
作者：
Bartok, Albert P.;Kondor, Risi;Csanyi, Gabor
通讯作者：
Csanyi, Gabor