PubChemQC Project: A Large-Scale First-Principles Electronic Structure Database for Data-Driven Chemistry
PubChemQC Project: A Large-Scale First-Principles Electronic Structure Database for Data-Driven Chemistry
复制标题
DOI：
10.1021/acs.jcim.7b00083
复制
发表时间：
2017-06-01
影响因子：
5.6
通讯作者：
Shimazaki, Tomomi
中科院分区：
文献类型：
--
作者：
Nakata, Maho;Shimazaki, Tomomi
大型分子数据库在各种学科的研究中发挥着重要作用，例如有机材料的开发、计算机药物设计以及机器学习的数据驱动研究。我们开发了基于第一原理方法的大规模量子化学数据库。我们的数据库目前包含基于B3LYP/6-31G*水平的密度泛函理论（DFT）的300万个分子的基态电子结构，并且我们利用B3LYP泛函和6-31+G*基组通过时间相关的DFT连续计算了超过200万个分子的10个低激发态。为了选择在我们的项目中计算的分子，我们参考了 PubChem 项目，该项目被用作使用 InChI 和 SMILES 表示的短字符串分子结构的来源。因此，我们将我们的量子化学数据库项目命名为“PubChemQC”（http://pubchemqcsiken.jp/）并将其置于公共领域。在本文中，我们展示了 PubChemQC 数据库的基本特征，并讨论了用于构建大规模量子化学计算数据集的技术。我们还提出了一种预测分子电子结构的机器学习方法作为示例，以证明大规模量子化学数据库的适用性。
Large-scale molecular databases play an essential role in the investigation of various subjects such as the development of organic materials, in silico drug design, and data-driven studies with machine learning. We have developed a large-scale quantum chemistry database based on first principles methods. Our database currently contains the ground-state electronic structures of 3 million molecules based on density functional theory (DFT) at the B3LYP/6-31G* level, and we successively calculated 10 low-lying excited states of over 2 million molecules via time-dependent DFT with the B3LYP functional and the 6-31+G* basis set. To select the molecules calculated in our project, we referred to the PubChem Project, which was used as the source of the molecular structures in short strings using the InChI and SMILES representations. Accordingly, we have named our quantum chemistry database project "PubChemQC" (http://pubchemqcsiken.jp/) and placed it in the public domain. In this paper, we show the fundamental features of the PubChemQC database and discuss the techniques used to construct the data set for large-scale quantum chemistry calculations. We also present a machine learning approach to predict the electronic structure of molecules as an example to demonstrate the suitability of the large-scale quantum chemistry database.