Predicting scalar coupling constants by graph angle-attention neural network

Abstract Scalar coupling constant (SCC), directly measured by nuclear magnetic resonance (NMR) spectroscopy, is a key parameter for molecular structure analysis, and widely used to predict unknown molecular structure. Restricted by the high cost of NMR experiments, it is impossible to measure the SC...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Jia Fang, Linyuan Hu, Jianfeng Dong, Haowei Li, Hui Wang, Huafen Zhao, Yao Zhang, Min Liu
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/26938c079f914428b59f6a95757082b4
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:26938c079f914428b59f6a95757082b4
record_format dspace
spelling oai:doaj.org-article:26938c079f914428b59f6a95757082b42021-12-02T18:48:23ZPredicting scalar coupling constants by graph angle-attention neural network10.1038/s41598-021-97146-12045-2322https://doaj.org/article/26938c079f914428b59f6a95757082b42021-09-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-97146-1https://doaj.org/toc/2045-2322Abstract Scalar coupling constant (SCC), directly measured by nuclear magnetic resonance (NMR) spectroscopy, is a key parameter for molecular structure analysis, and widely used to predict unknown molecular structure. Restricted by the high cost of NMR experiments, it is impossible to measure the SCC of unknown molecules on a large scale. Using density functional theory (DFT) to theoretically calculate the SCC of molecules is incredibly challenging, due to the cost of substantial computational time and space. Graph neural networks (GNN) of artificial intelligence (AI) have great potential in constructing molecul ar-like topology models, which endows them the ability to rapidly predict SCC through data-driven machine learning methods, and avoiding time-consuming quantum chemical calculations. With a priori knowledge of angles, we propose a graph angle-attention neural network (GAANN) model to predict SCC by means of some easily accessible related information. GAANN, with a multilayer message-passing network and a self-attention mechanism, can accurately simulate the molecular-like topological structure and predict molecular properties. Our simulations show that the prediction accuracy by GAANN, with the log(MAE) = −2.52, is close to that by DFT calculations. Different from conventional AI methods, GAANN combining the AI method with quantum chemistry theory (Karplus equation) has a strong physicochemical interpretability about angles. From an AI perspective, we find that bond angle has the highest correlation with the SCC among all angle features (dihedral angle, bond angle, geometric angles) about multiple coupling types in the small molecule datasets.Jia FangLinyuan HuJianfeng DongHaowei LiHui WangHuafen ZhaoYao ZhangMin LiuNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-11 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Jia Fang
Linyuan Hu
Jianfeng Dong
Haowei Li
Hui Wang
Huafen Zhao
Yao Zhang
Min Liu
Predicting scalar coupling constants by graph angle-attention neural network
description Abstract Scalar coupling constant (SCC), directly measured by nuclear magnetic resonance (NMR) spectroscopy, is a key parameter for molecular structure analysis, and widely used to predict unknown molecular structure. Restricted by the high cost of NMR experiments, it is impossible to measure the SCC of unknown molecules on a large scale. Using density functional theory (DFT) to theoretically calculate the SCC of molecules is incredibly challenging, due to the cost of substantial computational time and space. Graph neural networks (GNN) of artificial intelligence (AI) have great potential in constructing molecul ar-like topology models, which endows them the ability to rapidly predict SCC through data-driven machine learning methods, and avoiding time-consuming quantum chemical calculations. With a priori knowledge of angles, we propose a graph angle-attention neural network (GAANN) model to predict SCC by means of some easily accessible related information. GAANN, with a multilayer message-passing network and a self-attention mechanism, can accurately simulate the molecular-like topological structure and predict molecular properties. Our simulations show that the prediction accuracy by GAANN, with the log(MAE) = −2.52, is close to that by DFT calculations. Different from conventional AI methods, GAANN combining the AI method with quantum chemistry theory (Karplus equation) has a strong physicochemical interpretability about angles. From an AI perspective, we find that bond angle has the highest correlation with the SCC among all angle features (dihedral angle, bond angle, geometric angles) about multiple coupling types in the small molecule datasets.
format article
author Jia Fang
Linyuan Hu
Jianfeng Dong
Haowei Li
Hui Wang
Huafen Zhao
Yao Zhang
Min Liu
author_facet Jia Fang
Linyuan Hu
Jianfeng Dong
Haowei Li
Hui Wang
Huafen Zhao
Yao Zhang
Min Liu
author_sort Jia Fang
title Predicting scalar coupling constants by graph angle-attention neural network
title_short Predicting scalar coupling constants by graph angle-attention neural network
title_full Predicting scalar coupling constants by graph angle-attention neural network
title_fullStr Predicting scalar coupling constants by graph angle-attention neural network
title_full_unstemmed Predicting scalar coupling constants by graph angle-attention neural network
title_sort predicting scalar coupling constants by graph angle-attention neural network
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/26938c079f914428b59f6a95757082b4
work_keys_str_mv AT jiafang predictingscalarcouplingconstantsbygraphangleattentionneuralnetwork
AT linyuanhu predictingscalarcouplingconstantsbygraphangleattentionneuralnetwork
AT jianfengdong predictingscalarcouplingconstantsbygraphangleattentionneuralnetwork
AT haoweili predictingscalarcouplingconstantsbygraphangleattentionneuralnetwork
AT huiwang predictingscalarcouplingconstantsbygraphangleattentionneuralnetwork
AT huafenzhao predictingscalarcouplingconstantsbygraphangleattentionneuralnetwork
AT yaozhang predictingscalarcouplingconstantsbygraphangleattentionneuralnetwork
AT minliu predictingscalarcouplingconstantsbygraphangleattentionneuralnetwork
_version_ 1718377610638000128