arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2207.09971physics.comp-phcs.LGphysics.chem-ph
收藏

NeuralNEB --神经网络可以快速找到反应路径

NeuralNEB -- Neural Networks can find Reaction Paths Fast

DTU Compute, Technical University of Denmark (DTU)(丹麦技术大学(DTU)计算系);DTU Energy, Technical University of Denmark (DTU)(丹麦技术大学(DTU)能源系);Department of Biology, University of Copenhagen (UCph)(哥本哈根大学(UCph)生物系);Genomic Medicine, Copenhagen University Hospital, Rigshospitalet(哥本哈根大学医院(Rigshospitalet)基因组医学部)

Mathias Schreiner, Arghya Bhowmik, Tejs Vegge, Peter Bjørn Jørgensen, Ole Winther

摘要:

量子力学方法,如密度泛函理论(DFT)的使用与有效的搜索算法一起用于研究反应体系的动力学,取得了巨大的成功。然而,DFT对于大规模勘探来说过于昂贵。机器学习(ML)模型已被证明是小分子DFT计算的优秀仿真器,并可能在此类任务中取代DFT。对于动力学,成功主要依赖于模型准确预测过渡态周围的势能面(PES)和最小能量路径(MEP)的能力。以前,由于文献中相关数据的缺乏,这是不可能的。在本文中,我们训练了最先进的基于等变图神经网络(GNN)的模型,这些模型来自Transition 1x数据集的大约10.000个基本反应。我们将这些模型作为Nudged Elastic Band(NEB)算法的势,并在看不见的反应的势垒能量上实现了0.13+/-0.03 eV的平均误差(MAE)。我们将结果与在QM 9和ANI 1x上训练的等效模型进行了比较。我们还比较和优于密度泛函紧束缚(DFTB)的准确性和计算资源。这意味着,在给定相关数据的情况下,ML模型现在可以应用于量子化学的下游任务,而不仅仅是预测简单的分子特征。

英文摘要:

Quantum mechanical methods like Density Functional Theory (DFT) are used with great success alongside efficient search algorithms for studying kinetics of reactive systems. However, DFT is prohibitively expensive for large scale exploration. Machine Learning (ML) models have turned out to be excellent emulators of small molecule DFT calculations and could possibly replace DFT in such tasks. For kinetics, success relies primarily on the models capability to accurately predict the Potential Energy Surface (PES) around transition-states and Minimal Energy Paths (MEPs). Previously this has not been possible due to scarcity of relevant data in the literature. In this paper we train state of the art equivariant Graph Neural Network (GNN)-based models on around 10.000 elementary reactions from the Transition1x dataset. We apply the models as potentials for the Nudged Elastic Band (NEB) algorithm and achieve a Mean Average Error (MAE) of 0.13+/-0.03 eV on barrier energies on unseen reactions. We compare the results against equivalent models trained on QM9 and ANI1x. We also compare with and outperform Density Functional based Tight Binding (DFTB) on both accuracy and computational resource. The implication is that ML models, given relevant data, are now at a level where they can be applied for downstream tasks in quantum chemistry transcending prediction of simple molecular features.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑