arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.02806physics.chem-ph
收藏

基于机器学习的分子(闭壳层和开壳层)、过渡态和固体的无能结构预测

Machine learning based energy-free structure predictions of molecules (closed and open-shell), transition states, and solids

Dominik Lemm, Guido Falk von Rudorff, O. Anatole von Lilienfeld

摘要:

原子结构的计算预测是物理学、化学、材料学和生物学中一个长期存在的问题。在传统的力场或{ \em ab initio}计算中,结构是通过能量最小化来确定的,这是近似的或计算要求高的。唉,准确性-成本权衡禁止生成具有有意义的基于能量的构象搜索和结构弛豫输出的合成大数据记录。利用松弛结构之间的隐式相关性,我们的内核岭回归模型,称为图形到结构(G2 S),概括了整个化合物空间,能够直接预测样品外化合物的松弛结构,并有效地绕过能量优化任务。在对结构和组成异构体(无构象异构体)进行训练后,G2 S仅依赖于化学计量和键网络信息作为输入来推断原子坐标(我们的数值证据包括闭合和开放壳层分子,过渡态和固体)。对于所有考虑的数据,G2 S学习曲线在不到8000个训练结构中达到平均绝对原子间距离预测误差小于0.2 μ m-与流行的经验方法相当或更好。G2 S的适用性测试包括标准方法需要手动干预的分子的有意义的结构,用于后续常规的基于{ \em ab initio}的松弛的改进的初始猜测,以及用于量子机器学习模型中常用的基于结构的表示的输入(弥合基于图形和结构的模型之间的差距)。

英文摘要:

The computational prediction of atomistic structure is a long-standing problem in physics, chemistry, materials, and biology. Within conventional force-field or {\em ab initio} calculations, structure is determined through energy minimization, which is either approximate or computationally demanding. Alas, the accuracy-cost trade-off prohibits the generation of synthetic big data records with meaningful energy based conformational search and structure relaxation output. Exploiting implicit correlations among relaxed structures, our kernel ridge regression model, dubbed Graph-To-Structure (G2S), generalizes across chemical compound space, enabling direct predictions of relaxed structures for out-of-sample compounds, and effectively bypassing the energy optimization task. After training on constitutional and compositional isomers (no conformers) G2S infers atomic coordinates relying solely on stoichiometry and bond-network information as input (Our numerical evidence includes closed and open shell molecules, transition states, and solids). For all data considered, G2S learning curves reach mean absolute interatomic distance prediction errors of less than 0.2 Å for less than eight thousand training structures -- on par or better than popular empirical methods. Applicability test of G2S include meaningful structures of molecules for which standard methods require manual intervention, improved initial guesses for subsequent conventional {\em ab initio} based relaxation, and input for structural based representations commonly used in quantum machine learning models, (bridging the gap between graph and structure based models).

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。

↑