.png){kind=icon}
返回
Transferable Dynamic Molecular Charge Assignment Using Deep Neural Networks
.png){kind=icon}
PRE
AI
DOI：10.1021/acs.jctc.8b00524.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The ability to accurately and efficiently compute quantum-mechanical partial atomistic charges has many practical applications, such as calculations of IR spectra, analysis of chemical bonding, and classical force field parametrization. Machine learning (ML) techniques provide a possible avenue for the efficient prediction of atomic partial charges. Modern ML advances in the prediction of molecular energies [i.e., the hierarchical interacting particle neural network (HIP-NN)] has provided the necessary model framework and architecture to predict transferable, extensible, and conformationally dynamic atomic partial charges based on reference density functional theory (DFT) simulations. Utilizing HIP-NN, we show that ML charge prediction can be highly accurate over a wide range of molecules (both small and large) across a variety of charge partitioning schemes such as the Hirshfeld, CMS, MSK, and NBO methods. To demonstrate transferability and size extensibility, we compare ML results with reference DFT calculations on the COMP6 benchmark, achieving errors of 0.004e(-) (elementary charge). This is remarkable since this benchmark contains two proteins that are multiple times larger than the largest molecules in the training set. An application of our atomic charge predictions on nonequilibrium geometries is the generation of IR spectra for organic molecules from dynamical trajectories on a variety of organic molecules, which show good agreement with calculated IR spectra with reference method. Critically, HIP-NN charge predictions are many orders of magnitude faster than direct DFT calculations. These combined results provide further evidence that ML (specifically HIP-NN) provides a pathway to greatly increase the range of feasible simulations while retaining quantum-level accuracy.
Keyword:
MACHINE LEARNING-MODELS
CHEMICAL UNIVERSE
VIRTUAL EXPLORATION
PREDICTIONS
POTENTIALS
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
5.5
论文数:
1.1W
被引数:
5.4W
机构
引用论文
Chemical and Electrochemical Parameters for Oxygen Reduction on Pt ‐ H 2 WO 4 / Carbon Electrodes in 99 % H 3 PO 499 % h3 3 po 4中pt - h 2 wo 4 / carbon 电极上氧还原的化学和电化学参数
.png){kind=icon}
PREAI
分享收藏Job tenure and quality of work life of people with psychiatric disabilities working in social enterprises在社会企业工作的精神病患者的工作任期和工作生活质量
PREAI
分享收藏Simultaneously assessing amplitude and temporal effects in biomechanical trajectories using nonlinear registration and statistical nonparametric mapping同时评估生物力学轨迹中的幅度和时间效应，采用非线性配准和统计非参数映射。
OAAI
OAAI分享收藏
分享收藏分享收藏Virtual exploration of the chemical universe up to 11 atoms of C, N, O, F: Assembly of 26.4 million structures (110.9 million stereoisomers) and analysis for new ring systems, stereochemistry, physicochemical properties, compound classes, and drug discovery虚拟探索多达11个C，N，O，F原子的化学宇宙: 2640万结构 (1.109亿个立体异构体) 的组装以及对新环系，立体化学，理化性质，化合物课程和药物发现的分析
PREAI
分享收藏
查看更多内容