• Group Contribution Method Supe...

Treffer: Group Contribution Method Supervised Neural Network for Precise Design of Organic Nonlinear Optical Materials.

Title:
Group Contribution Method Supervised Neural Network for Precise Design of Organic Nonlinear Optical Materials.
Authors:
Fan J; College of Chemical and Biological Engineering, Zhejiang Provincial Key Laboratory of Advanced Chemical Engineering Manufacture Technology, Zhejiang University, Hangzhou 310027, P. R. China.; Zhejiang Provincial Innovation Center of Advanced Chemicals Technology, Institute of Zhejiang University-Quzhou, Quzhou 324000, P. R. China., Yuan B; College of Chemical and Biological Engineering, Zhejiang Provincial Key Laboratory of Advanced Chemical Engineering Manufacture Technology, Zhejiang University, Hangzhou 310027, P. R. China.; Zhejiang Provincial Innovation Center of Advanced Chemicals Technology, Institute of Zhejiang University-Quzhou, Quzhou 324000, P. R. China., Qian C; College of Chemical and Biological Engineering, Zhejiang Provincial Key Laboratory of Advanced Chemical Engineering Manufacture Technology, Zhejiang University, Hangzhou 310027, P. R. China.; Zhejiang Provincial Innovation Center of Advanced Chemicals Technology, Institute of Zhejiang University-Quzhou, Quzhou 324000, P. R. China., Zhou S; College of Chemical and Biological Engineering, Zhejiang Provincial Key Laboratory of Advanced Chemical Engineering Manufacture Technology, Zhejiang University, Hangzhou 310027, P. R. China.; Zhejiang Provincial Innovation Center of Advanced Chemicals Technology, Institute of Zhejiang University-Quzhou, Quzhou 324000, P. R. China.
Source:
Precision chemistry [Precis Chem] 2024 Apr 08; Vol. 2 (6), pp. 263-272. Date of Electronic Publication: 2024 Apr 08 (Print Publication: 2024).
Publication Type:
Journal Article
Language:
English
Journal Info:
Publisher: American Chemical Society Country of Publication: United States NLM ID: 9918574281706676 Publication Model: eCollection Cited Medium: Internet ISSN: 2771-9316 (Electronic) Linking ISSN: 27719316 NLM ISO Abbreviation: Precis Chem Subsets: PubMed not MEDLINE
Imprint Name(s):
Original Publication: Washington, District of Columbia : Anhui, China : American Chemical Society ; University of Science and Technology of China, [2023]-
References:
Nature. 2015 May 28;521(7553):436-44. (PMID: 26017442)
ACS Cent Sci. 2018 Jan 24;4(1):52-62. (PMID: 29392176)
Chem Asian J. 2021 Aug 16;16(16):2267-2271. (PMID: 34180155)
Phys Chem Chem Phys. 2022 Mar 23;24(12):7466-7473. (PMID: 35274653)
Nat Protoc. 2021 Dec;16(12):5426-5459. (PMID: 34741152)
Science. 1994 Jan 28;263(5146):511-4. (PMID: 17754885)
Nature. 2020 May;581(7807):178-183. (PMID: 32405017)
Research (Wash D C). 2023 Apr 20;6:0115. (PMID: 37287889)
J Comput Chem. 2011 Apr 30;32(6):1128-34. (PMID: 21387339)
Nature. 2018 Jul;559(7714):377-381. (PMID: 30022133)
Nat Commun. 2021 Jul 22;12(1):4468. (PMID: 34294693)
J Org Chem. 2017 Sep 15;82(18):9435-9451. (PMID: 28836778)
Nat Commun. 2022 Feb 21;13(1):973. (PMID: 35190542)
Chem Rev. 2019 Oct 9;119(19):10856-10915. (PMID: 31469277)
Sci Adv. 2018 Jul 25;4(7):eaap7885. (PMID: 30050984)
Nat Commun. 2017 Mar 06;8:14621. (PMID: 28262694)
ACS Cent Sci. 2018 Feb 28;4(2):268-276. (PMID: 29532027)
ACS Cent Sci. 2021 Aug 25;7(8):1356-1367. (PMID: 34471680)
Nature. 2018 Jul;559(7715):547-555. (PMID: 30046072)
Entry Date(s):
Date Created: 20241030 Latest Revision: 20241030
Update Code:
20250114
PubMed Central ID:
PMC11504572
DOI:
10.1021/prechem.4c00015
PMID:
39474201
Database:
MEDLINE

Weitere Informationen

To rationalize the design of D-π-A type organic small-molecule nonlinear optical materials, a theory guided machine learning framework is constructed. Such an approach is based on the recognition that the optical property of the molecule is predictable upon accumulating the contribution of each component, which is in line with the concept of group contribution method in thermodynamics. To realize this, a Lewis-mode group contribution method (LGC) has been developed in this work, which is combined with the multistage Bayesian neural network and the evolutionary algorithm to constitute an interactive framework (LGC-msBNN-EA). Thus, different optical properties of molecules are afforded accurately and efficiently-by using only a small data set for training. Moreover, by employing the EA model designed specifically for LGC, structural search is well achievable. The origins of the satisfying performance of the framework are discussed in detail. Considering that such a framework combines chemical principles and data-driven tools, most likely, it will be proven to be rational and efficient to complete mission regarding structure design in related fields.
(© 2024 The Authors. Co-published by University of Science and Technology of China and American Chemical Society.)

The authors declare no competing financial interest.