Algebraic graph-assisted bidirectional transformers for molecular property prediction

Despite considerable efforts, quantitative prediction of various molecular properties remains a challenge. Here, the authors propose an algebraic graph-assisted bidirectional transformer, which can incorporate massive unlabeled molecular data into molecular representations via a self-supervised lear...

Full description

Bibliographic Details
Main Authors: Dong Chen, Kaifu Gao, Duc Duy Nguyen, Xin Chen, Yi Jiang, Guo-Wei Wei, Feng Pan
Format: Article
Language:English
Published: Nature Publishing Group 2021-06-01
Series:Nature Communications
Online Access:https://doi.org/10.1038/s41467-021-23720-w
id doaj-964aeff00e454f149f1ac6578c7f6305
record_format Article
spelling doaj-964aeff00e454f149f1ac6578c7f63052021-06-13T11:16:15ZengNature Publishing GroupNature Communications2041-17232021-06-011211910.1038/s41467-021-23720-wAlgebraic graph-assisted bidirectional transformers for molecular property predictionDong Chen0Kaifu Gao1Duc Duy Nguyen2Xin Chen3Yi Jiang4Guo-Wei Wei5Feng Pan6School of Advanced Materials, Peking University, Shenzhen Graduate SchoolDepartment of Mathematics, Michigan State UniversityDepartment of Mathematics, University of KentuckySchool of Advanced Materials, Peking University, Shenzhen Graduate SchoolSchool of Advanced Materials, Peking University, Shenzhen Graduate SchoolDepartment of Mathematics, Michigan State UniversitySchool of Advanced Materials, Peking University, Shenzhen Graduate SchoolDespite considerable efforts, quantitative prediction of various molecular properties remains a challenge. Here, the authors propose an algebraic graph-assisted bidirectional transformer, which can incorporate massive unlabeled molecular data into molecular representations via a self-supervised learning strategy and assisted with 3D stereochemical information from graphs.https://doi.org/10.1038/s41467-021-23720-w
collection DOAJ
language English
format Article
sources DOAJ
author Dong Chen
Kaifu Gao
Duc Duy Nguyen
Xin Chen
Yi Jiang
Guo-Wei Wei
Feng Pan
spellingShingle Dong Chen
Kaifu Gao
Duc Duy Nguyen
Xin Chen
Yi Jiang
Guo-Wei Wei
Feng Pan
Algebraic graph-assisted bidirectional transformers for molecular property prediction
Nature Communications
author_facet Dong Chen
Kaifu Gao
Duc Duy Nguyen
Xin Chen
Yi Jiang
Guo-Wei Wei
Feng Pan
author_sort Dong Chen
title Algebraic graph-assisted bidirectional transformers for molecular property prediction
title_short Algebraic graph-assisted bidirectional transformers for molecular property prediction
title_full Algebraic graph-assisted bidirectional transformers for molecular property prediction
title_fullStr Algebraic graph-assisted bidirectional transformers for molecular property prediction
title_full_unstemmed Algebraic graph-assisted bidirectional transformers for molecular property prediction
title_sort algebraic graph-assisted bidirectional transformers for molecular property prediction
publisher Nature Publishing Group
series Nature Communications
issn 2041-1723
publishDate 2021-06-01
description Despite considerable efforts, quantitative prediction of various molecular properties remains a challenge. Here, the authors propose an algebraic graph-assisted bidirectional transformer, which can incorporate massive unlabeled molecular data into molecular representations via a self-supervised learning strategy and assisted with 3D stereochemical information from graphs.
url https://doi.org/10.1038/s41467-021-23720-w
work_keys_str_mv AT dongchen algebraicgraphassistedbidirectionaltransformersformolecularpropertyprediction
AT kaifugao algebraicgraphassistedbidirectionaltransformersformolecularpropertyprediction
AT ducduynguyen algebraicgraphassistedbidirectionaltransformersformolecularpropertyprediction
AT xinchen algebraicgraphassistedbidirectionaltransformersformolecularpropertyprediction
AT yijiang algebraicgraphassistedbidirectionaltransformersformolecularpropertyprediction
AT guoweiwei algebraicgraphassistedbidirectionaltransformersformolecularpropertyprediction
AT fengpan algebraicgraphassistedbidirectionaltransformersformolecularpropertyprediction
_version_ 1721380040352989184