ANI-1, A data set of 20 million calculated off-equilibrium conformations for organic molecules.
ANI-1, A data set of 20 million calculated off-equilibrium conformations for organic molecules.
复制标题
DOI：
10.1038/sdata.2017.193
复制
发表时间：
2017-12-19
期刊：
影响因子：
9.8
通讯作者：
Roitberg AE
中科院分区：
文献类型：
--
作者：
Smith JS;Isayev O;Roitberg AE
现代理论化学面临的重大挑战之一是设计和实现近似方法，以加快从头计算方法而不损失准确性。机器学习（ML）方法正在成为构建各种形式的可转移原子势的强大方法。它们已成功应用于化学、生物学、催化和固态物理等领域的各种应用。然而，这些模型在很大程度上取决于拟合中使用的数据的质量和数量。拟合高度灵活的机器学习潜力（例如神经网络）是有代价的：需要大量参考数据来正确训练这些模型。我们通过提供对大型计算 DFT 数据库的访问来满足这一需求，该数据库由 57,462 个有机小分子的超过 20M 个非平衡构象组成。我们相信它将成为机器学习潜在社区中当前和未来方法比较的新标准基准。
One of the grand challenges in modern theoretical chemistry is designing and implementing approximations that expedite ab initio methods without loss of accuracy. Machine learning (ML) methods are emerging as a powerful approach to constructing various forms of transferable atomistic potentials. They have been successfully applied in a variety of applications in chemistry, biology, catalysis, and solid-state physics. However, these models are heavily dependent on the quality and quantity of data used in their fitting. Fitting highly flexible ML potentials, such as neural networks, comes at a cost: a vast amount of reference data is required to properly train these models. We address this need by providing access to a large computational DFT database, which consists of more than 20 M off equilibrium conformations for 57,462 small organic molecules. We believe it will become a new standard benchmark for comparison of current and future methods in the ML potential community.
登录
查看更多内容
影响因子：
4.4
作者：
Huang, Bing;von Lilienfeld, O. Anatole
通讯作者：
von Lilienfeld, O. Anatole
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：
8.4
作者：
Gastegger M;Behler J;Marquetand P
通讯作者：
Marquetand P
影响因子：
4.4
作者：
DITCHFIELD, R;HEHRE, WJ;POPLE, JA
通讯作者：
POPLE, JA