PIP不再令人头疼:一种阿司匹林的PIP势能优于其他机器学习势能
No Headache for PIPs: A PIP Potential for Aspirin Outperforms Other Machine-Learned Potentials
AI总结:
本文使用rMD17数据集评估了21原子阿司匹林分子的线性回归置换不变多项式(PIP)方法,表明PIP势能在能量和力的精度及速度上均优于ANI、sGDML等主流机器学习势能。
摘要:
机器学习(ML)势能的评估是该领域快速发展的重要方面。我们最近报道了使用广泛使用的(修订版)MD17数据集对乙醇的线性回归置换不变多项式(PIP)方法的评估。我们证明了PIP方法在精度方面,尤其是在速度方面,优于许多其他方法,例如ANI、PhysNet、sGDML、p-KRR [Houston et al., J. Chem. Phys. 2022, 156, 044120.]。在此,我们使用rMD17数据集将此评估扩展到21原子的阿司匹林分子。能量和力均用于训练,并且检查了几个PIP对两者的精度。本文还给出了简正振动模式频率、甲基扭转势能以及OH伸缩的一维振动能。总体而言,我们表明PIP方法优于其他ML方法,包括sGDML、ANI、GAP、PhysNet和ACE,如Kovács et al.在J. Chem. Theory Comput. 2021, 17, 7696-7711中所报道的。
英文摘要:
Assessments of machine-learned (ML) potentials are an important aspect of the rapid development of this field. We recently reported an assessment of the linear-regression permutationally invariant polynomial (PIP) method for ethanol, using the widely used (revised) MD17 dataset. We demonstrated that the PIP approach outperformed numerous other methods, e.g., ANI, PhysNet, sGDML, p-KRR, with respect to precision and notably with respect to speed [Houston $et$ $al$., $J. Chem. Phys.$ 2022, 156, 044120.]. Here we extend this assessment to the 21-atom aspirin molecule, using the rMD17 dataset. Both energies and forces are used for training and the precision of several PIPs is examined for both. Normal mode frequencies, the methyl torsional potential, and 1d vibrational energies for an OH stretch are presented. Overall, we show that the PIPs approach outperforms other ML methods, including sGDML, ANI, GAP, PhysNet, and ACE, as reported by Kovács $et$ $al.$ in $J. Chem. Theory$ $Comput.$ 2021, 17, 7696-7711.
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。