Accurate and transferable multitask prediction of chemical properties with an atoms-in-molecules neural network
Accurate and transferable multitask prediction of chemical properties with an atoms-in-molecules neural network
复制标题
DOI：
10.1126/sciadv.aav6490
复制
发表时间：
2018-10
期刊：
影响因子：
13.6
通讯作者：
R. Zubatyuk;Justin S. Smith;J. Leszczynski;O. Isayev
中科院分区：
文献类型：
--
作者：
R. Zubatyuk;Justin S. Smith;J. Leszczynski;O. Isayev
我们介绍了一个模块化的，化学启发的深度神经网络模型，用于预测几种原子和分子的性质。原子和分子的性质可以从基本的薛定谔方程来评估，因此它们代表了相同量子现象的不同形态。在这里，我们提出了AIMNet，一个模块化和化学启发的深度神经网络潜力。我们使用AIMNet和多目标训练来学习分子系统中原子状态的多种模态。所得到的模型在几个基准数据集上显示出最先进的精度，与更昂贵的DFT方法的结果相当。它可以在不增加计算成本的情况下同时预测几个原子和分子的性质。通过AIMNet，我们展示了可转移性的一个新维度：利用以前训练的多模态信息学习新目标的能力。该模型仅使用原始训练数据的一小部分即可学习隐式溶剂化能（SMD方法），与MNSol数据库中的实验溶剂化自由能相比，该模型的中位数绝对偏差误差为1.1 kcal/mol。
We introduce a modular, chemically inspired deep neural network model for prediction of several atomic and molecular properties. Atomic and molecular properties could be evaluated from the fundamental Schrodinger’s equation and therefore represent different modalities of the same quantum phenomena. Here, we present AIMNet, a modular and chemically inspired deep neural network potential. We used AIMNet with multitarget training to learn multiple modalities of the state of the atom in a molecular system. The resulting model shows on several benchmark datasets state-of-the-art accuracy, comparable to the results of orders of magnitude more expensive DFT methods. It can simultaneously predict several atomic and molecular properties without an increase in the computational cost. With AIMNet, we show a new dimension of transferability: the ability to learn new targets using multimodal information from previous training. The model can learn implicit solvation energy (SMD method) using only a fraction of the original training data and an archive median absolute deviation error of 1.1 kcal/mol compared to experimental solvation free energies in the MNSol database.