Approaching coupled cluster accuracy with a general-purpose neural network potential through transfer learning
Approaching coupled cluster accuracy with a general-purpose neural network potential through transfer learning
复制标题
DOI：
10.1038/s41467-019-10827-4
复制
发表时间：
2019-07-01
影响因子：
16.6
通讯作者：
Roitberg, Adrian E.
中科院分区：
文献类型：
--
作者：
Smith, Justin S.;Nebgen, Benjamin T.;Roitberg, Adrian E.
原子分辨率的化学和生物系统的计算建模是化学家工具集中的一个重要工具。使用计算机模拟需要在成本和准确性之间取得平衡：量子力学方法提供高准确性，但计算成本高，并且难以扩展到大型系统，而经典力场便宜且可扩展，但缺乏对新系统的可移植性。机器学习可以用来实现这两种方法的最佳效果。在这里，我们训练了一个通用神经网络势（ANI-1ccx），它在反应热化学，异构化和药物样分子扭转的基准上接近CCSD（T）/CBS的准确性。这是通过将网络训练到DFT数据，然后使用迁移学习技术在最佳跨越化学空间的金标准QM计算（CCSD（T）/CBS）数据集上重新训练来实现的。由此产生的潜力广泛适用于材料科学，生物学和化学，比CCSD（T）/CBS计算快数十亿倍。
Computational modeling of chemical and biological systems at atomic resolution is a crucial tool in the chemist's toolset. The use of computer simulations requires a balance between cost and accuracy: quantum-mechanical methods provide high accuracy but are computationally expensive and scale poorly to large systems, while classical force fields are cheap and scalable, but lack transferability to new systems. Machine learning can be used to achieve the best of both approaches. Here we train a general-purpose neural network potential (ANI-1ccx) that approaches CCSD(T)/CBS accuracy on benchmarks for reaction thermochemistry, isomerization, and drug-like molecular torsions. This is achieved by training a network to DFT data then using transfer learning techniques to retrain on a dataset of gold standard QM calculations (CCSD(T)/CBS) that optimally spans chemical space. The resulting potential is broadly applicable to materials science, biology, and chemistry, and billions of times faster than CCSD(T)/CBS calculations.