Molecular geometric deep learning.
CP: Molecular biology
CP: Systems biology
geometric deep learning
graph neural network
molecular property prediction
Journal
Cell reports methods
ISSN: 2667-2375
Titre abrégé: Cell Rep Methods
Pays: United States
ID NLM: 9918227360606676
Informations de publication
Date de publication:
20 Nov 2023
20 Nov 2023
Historique:
received:
19
01
2023
revised:
16
06
2023
accepted:
28
09
2023
medline:
27
11
2023
pubmed:
25
10
2023
entrez:
24
10
2023
Statut:
ppublish
Résumé
Molecular representation learning plays an important role in molecular property prediction. Existing molecular property prediction models rely on the de facto standard of covalent-bond-based molecular graphs for representing molecular topology at the atomic level and totally ignore the non-covalent interactions within the molecule. In this study, we propose a molecular geometric deep learning model to predict the properties of molecules that aims to comprehensively consider the information of covalent and non-covalent interactions of molecules. The essential idea is to incorporate a more general molecular representation into geometric deep learning (GDL) models. We systematically test molecular GDL (Mol-GDL) on fourteen commonly used benchmark datasets. The results show that Mol-GDL can achieve a better performance than state-of-the-art (SOTA) methods. Extensive tests have demonstrated the important role of non-covalent interactions in molecular property prediction and the effectiveness of Mol-GDL models.
Identifiants
pubmed: 37875121
pii: S2667-2375(23)00285-0
doi: 10.1016/j.crmeth.2023.100621
pmc: PMC10694498
pii:
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
100621Informations de copyright
Copyright © 2023 The Author(s). Published by Elsevier Inc. All rights reserved.
Déclaration de conflit d'intérêts
Declaration of interests The authors declare no competing interests.
Références
Sci Adv. 2021 May 7;7(19):
pubmed: 33962954
J Chem Inf Model. 2017 Nov 27;57(11):2672-2685
pubmed: 29019671
Nucleic Acids Res. 2016 Jan 4;44(D1):D1075-9
pubmed: 26481350
J Chem Inf Model. 2016 Oct 24;56(10):1936-1949
pubmed: 27689393
Drug Discov Today. 2019 Mar;24(3):773-780
pubmed: 30472429
Drug Discov Today. 2018 Aug;23(8):1538-1546
pubmed: 29750902
Nat Commun. 2021 Jun 10;12(1):3521
pubmed: 34112777
J Chem Inf Model. 2009 Feb;49(2):169-84
pubmed: 19434821
Drug Discov Today. 2017 Nov;22(11):1680-1685
pubmed: 28881183
Chem Sci. 2017 Oct 31;9(2):513-530
pubmed: 29629118
Chem Sci. 2018 Nov 19;10(6):1692-1701
pubmed: 30842833
Cell Chem Biol. 2016 Oct 20;23(10):1294-1301
pubmed: 27642066
Drug Discov Today Technol. 2020 Dec;37:1-12
pubmed: 34895648
Nat Rev Drug Discov. 2019 Jun;18(6):463-477
pubmed: 30976107
J Chem Inf Model. 2019 Aug 26;59(8):3370-3388
pubmed: 31361484
J Chem Inf Model. 2005 Sep-Oct;45(5):1159-68
pubmed: 16180893
Neural Netw. 2022 Sep;153:104-119
pubmed: 35716619
Bioinformatics. 2018 May 1;34(9):1538-1546
pubmed: 29253077
J Chem Inf Model. 2017 Aug 28;57(8):1757-1772
pubmed: 28696688
Phys Rev Lett. 2020 Oct 16;125(16):166001
pubmed: 33124874
Trends Pharmacol Sci. 2019 Oct;40(10):801
pubmed: 31451243
Brief Bioinform. 2022 Jan 17;23(1):
pubmed: 34571537
J Chem Phys. 2018 Jun 28;148(24):241722
pubmed: 29960322
Cell. 2020 Feb 20;180(4):688-702.e13
pubmed: 32084340
Nat Mach Intell. 2020;2(2):116-123
pubmed: 34170981
Bioinformatics. 2020 Aug 15;36(16):4483-4489
pubmed: 32369563
J Chem Inf Model. 2012 Jun 25;52(6):1686-97
pubmed: 22612593
Drug Discov Today. 2018 Jun;23(6):1241-1250
pubmed: 29366762
PLoS Comput Biol. 2021 Feb 12;17(2):e1008653
pubmed: 33577560
J Med Chem. 2020 Aug 27;63(16):8749-8760
pubmed: 31408336