OrbNet Denali: A machine learning potential for biological and organic chemistry with semi-empirical cost and DFT accuracy
OrbNet Denali: A machine learning potential for biological and organic chemistry with semi-empirical cost and DFT accuracy
复制标题
DOI：
10.1063/5.0061990
复制
发表时间：
2021-11-28
影响因子：
4.4
通讯作者：
Miller, Thomas F., III
中科院分区：
文献类型：
--
作者：
Christensen, Anders S.;Sirumalla, Sai Krishna;Miller, Thomas F., III
我们提出了OrbNet Denali，这是一种用于电子结构的机器学习模型，旨在取代基态密度泛函理论（DFT）能量计算。该模型是一个消息传递图神经网络，它使用来自低成本量子计算的自适应原子轨道特征来预测分子的能量。OrbNet Denali在分子和几何结构的2.3 x 10（6）DFT计算的庞大数据集上进行训练。该数据集涵盖了生物化学和有机化学中最常见的元素（H、Li、B、C、N、O、F、Na、Mg、Si、P、S、Cl、K、Ca、Br和I）以及带电分子。OrbNet Denali在几个成熟的基准数据集上进行了演示，我们发现它提供了与现代DFT方法相当的精度，同时提供了高达三个数量级的加速。对于GMTKN 55基准测试集，OrbNet Denali的WTMAD-1和WTMAD-2得分分别为7.19和9.84，与现代DFT泛函相当。对于几个GMTKN 55子集，其中包含训练集中不存在的化学问题，OrbNet Denali产生的平均绝对误差与DFT方法相当。对于Hutchison conformer基准集，与参考DLPNO-CCSD（T）计算相比，OrbNet Denali的中位相关系数为R-2 = 0.90，与用于生成训练数据的方法相比，R-2 = 0.97（欧米茄B 97 X-D3/def 2-TZVP），超过了具有类似成本的任何其他方法的性能。同样，该模型在S66 x10数据集中达到了非共价相互作用的化学准确性。对于扭转曲线，OrbNet Denali再现了omega B 97 X-D3/def 2-TZVP的扭转曲线，对于TorsionNet 500数据集中不同片段的势能面，平均绝对误差为0.12 kcal/mol。由AIP Publishing独家授权出版。
We present OrbNet Denali, a machine learning model for an electronic structure that is designed as a drop-in replacement for ground-state density functional theory (DFT) energy calculations. The model is a message-passing graph neural network that uses symmetry-adapted atomic orbital features from a low-cost quantum calculation to predict the energy of a molecule. OrbNet Denali is trained on a vast dataset of 2.3 x 10(6) DFT calculations on molecules and geometries. This dataset covers the most common elements in biochemistry and organic chemistry (H, Li, B, C, N, O, F, Na, Mg, Si, P, S, Cl, K, Ca, Br, and I) and charged molecules. OrbNet Denali is demonstrated on several well-established benchmark datasets, and we find that it provides accuracy that is on par with modern DFT methods while offering a speedup of up to three orders of magnitude. For the GMTKN55 benchmark set, OrbNet Denali achieves WTMAD-1 and WTMAD-2 scores of 7.19 and 9.84, on par with modern DFT functionals. For several GMTKN55 subsets, which contain chemical problems that are not present in the training set, OrbNet Denali produces a mean absolute error comparable to those of DFT methods. For the Hutchison conformer benchmark set, OrbNet Denali has a median correlation coefficient of R-2 = 0.90 compared to the reference DLPNO-CCSD(T) calculation and R-2 = 0.97 compared to the method used to generate the training data (omega B97X-D3/def2-TZVP), exceeding the performance of any other method with a similar cost. Similarly, the model reaches chemical accuracy for non-covalent interactions in the S66x10 dataset. For torsional profiles, OrbNet Denali reproduces the torsion profiles of omega B97X-D3/def2-TZVP with an average mean absolute error of 0.12 kcal/mol for the potential energy surfaces of the diverse fragments in the TorsionNet500 dataset. Published under an exclusive license by AIP Publishing.