Machine Learning Predictions of Molecular Properties: Accurate Many-Body Potentials and Nonlocality in Chemical Space.
Machine Learning Predictions of Molecular Properties: Accurate Many-Body Potentials and Nonlocality in Chemical Space.
复制标题
DOI：
10.1021/acs.jpclett.5b00831
复制
发表时间：
2015-06-18
影响因子：
5.7
通讯作者：
Tkatchenko, Alexandre
中科院分区：
文献类型：
--
作者：
Hansen, Katja;Biegler, Franziska;Ramakrishnan, Raghunathan;Pronobis, Wiktor;von Lilienfeld, O. Anatole;Mueller, Klaus-Robert;Tkatchenko, Alexandre
同时，准确和有效地预测整个化合物空间的分子性质是化学和制药工业中合理化合物设计的关键因素。针对这一目标，我们开发和应用了一个系统的层次结构的有效的经验方法来估计原子化和分子的总能量。这些方法从简单的原子求和，到键能相加，再到成对的原子间力场，再到更复杂的机器学习方法，这些方法能够描述许多原子或键之间的集体相互作用。在平衡分子几何形状的情况下，即使是简单的成对力场也表现出与使用密度泛函理论与混合交换相关泛函计算的基准能量相当的预测精度;然而，考虑集体多体相互作用被证明是接近平衡和平衡几何形状的化学精度为1千卡/摩尔的“圣杯”所必需的。这种显着的准确性是通过分子的矢量化表示（所谓的Bag of Bonds模型）来实现的，该模型在化学空间中表现出很强的非定域性。此外，同样的表示使我们能够预测分子的准确的电子性质，如它们的极化率和分子前线轨道能量。
Simultaneously accurate and efficient prediction of molecular properties throughout chemical compound space is a critical ingredient toward rational compound design in chemical and pharmaceutical industries. Aiming toward this goal, we develop and apply a systematic hierarchy of efficient empirical methods to estimate atomization and total energies of molecules. These methods range from a simple sum over atoms, to addition of bond energies, to pairwise interatomic force fields, reaching to the more sophisticated machine learning approaches that are capable of describing collective interactions between many atoms or bonds. In the case of equilibrium molecular geometries, even simple pairwise force fields demonstrate prediction accuracy comparable to benchmark energies calculated using density functional theory with hybrid exchange-correlation functionals; however, accounting for the collective many-body interactions proves to be essential for approaching the “holy grail” of chemical accuracy of 1 kcal/mol for both equilibrium and out-of-equilibrium geometries. This remarkable accuracy is achieved by a vectorized representation of molecules (so-called Bag of Bonds model) that exhibits strong nonlocality in chemical space. In addition, the same representation allows us to predict accurate electronic properties of molecules, such as their polarizability and molecular frontier orbital energies.
登录
查看更多内容
影响因子：
5.5
作者：
Fletcher, Timothy L.;Davie, Stuart J.;Popelier, Paul L. A.
通讯作者：
Popelier, Paul L. A.
影响因子：
5.6
作者：
Fink, Tobias;Reymond, Jean-Louis
通讯作者：
Reymond, Jean-Louis
影响因子：
8.6
作者：
Behler, Joerg;Parrinello, Michele
通讯作者：
Parrinello, Michele
影响因子：
4.4
作者：
Perdew, JP;Ernzerhof, M;Burke, K
通讯作者：
Burke, K
影响因子：
3.3
作者：
Montavon, Gregoire;Rupp, Matthias;von Lilienfeld, O. Anatole
通讯作者：
von Lilienfeld, O. Anatole