Non-covalent interactions across organic and biological subsets of chemical space: Physics-based potentials parametrized from machine learning
Non-covalent interactions across organic and biological subsets of chemical space: Physics-based potentials parametrized from machine learning
复制标题
DOI：
10.1063/1.5009502
复制
发表时间：
2018-06-28
影响因子：
4.4
通讯作者：
von Lilienfeld, O. Anatole
中科院分区：
文献类型：
--
作者：
Bereau, Tristan;DiStasio, Robert A., Jr.;von Lilienfeld, O. Anatole
经典的分子间势通常需要一个广泛的参数化程序考虑任何新的化合物。为了消除先前的参数化，我们提出了一种基于物理的潜力与机器学习（ML）的组合，即IPML，它可以在小的中性有机分子和生物相关分子之间转移。ML模型提供了对环境相关的局部原子性质的动态预测：静电多极系数（与以前报道的相比，误差显著减少），价原子密度的人口和衰减率，以及H，C，N和O原子的构象和化学组成的极化率。这些参数使精确计算分子间的贡献-静电，电荷渗透，排斥，感应/极化，和多体分散。与其他势函数不同，该模型在处理新分子和构象的能力上是可转移的，而无需明确的先验参数化：所有局部原子性质都是从ML预测的，只剩下8个全局参数-在化合物中一次性优化。我们验证IPML在各种气相二聚体和远离平衡分离，在那里我们获得的平均绝对误差为0.4和0.7千卡/摩尔之间的几个化学和构象不同的数据集代表的非共价相互作用在生物相关的分子。我们进一步专注于氢键复合物-必不可少的，但具有挑战性的，由于其方向性的DNA碱基对和氨基酸的数据集产生一个非常令人鼓舞的1.4千卡/摩尔的错误。最后，作为第一次看，我们认为IPML密集的系统：水集群，超分子主客体复合物，和苯晶体。由AIP出版社出版。
Classical intermolecular potentials typically require an extensive parametrization procedure for any new compound considered. To do away with prior parametrization, we propose a combination of physics-based potentials with machine learning (ML), coined IPML, which is transferable across small neutral organic and biologically relevant molecules. ML models provide on-the-fly predictions for environment-dependent local atomic properties: electrostatic multipole coefficients (significant error reduction compared to previously reported), the population and decay rate of valence atomic densities, and polarizabilities across conformations and chemical compositions of H, C, N, and O atoms. These parameters enable accurate calculations of intermolecular contributions-electrostatics, charge penetration, repulsion, induction/polarization, and many-body dispersion. Unlike other potentials, this model is transferable in its ability to handle new molecules and conformations without explicit prior parametrization: All local atomic properties are predicted from ML, leaving only eight global parameters-optimized once and for all across compounds. We validate IPML on various gas-phase dimers at and away from equilibrium separation, where we obtain mean absolute errors between 0.4 and 0.7 kcal/mol for several chemically and conformationally diverse datasets representative of non-covalent interactions in biologically relevant molecules. We further focus on hydrogen-bonded complexes-essential but challenging due to their directional nature-where datasets of DNA base pairs and amino acids yield an extremely encouraging 1.4 kcal/mol error. Finally, and as a first look, we consider IPML for denser systems: water clusters, supramolecular host-guest complexes, and the benzene crystal. Published by AIP Publishing.