Spectrochimica Acta - Part A: Molecular and Biomolecular Spectroscopy, volume 267, pages 120577

Deep neural network model for highly accurate prediction of BODIPYs absorption

Ksenofontov Alexander A ¹

Lukanov Michail M ^{1, 2}

Bocharov Pavel S ^{1, 2}

Berezin Michail B ¹

Tetko Igor V ¹

Hide authors affiliations Show authors affiliations: 2 affiliations

G.A. Krestov Institute of Solution Chemistry of the Russian Academy of Sciences, Akademicheskaya Street, 153045 Ivanovo, Russia |

Ivanovo State University of Chemistry and Technology, 7, Sheremetevskiy Avenue, Ivanovo 153000, Russia |

Publication type: Journal Article

Publication date: 2022-02-01

Elsevier

Journal: Spectrochimica Acta - Part A: Molecular and Biomolecular Spectroscopy

Quartile SCImago

Quartile WOS

Impact factor: 4.4

ISSN: 13861425

DOI: 10.1016/j.saa.2021.120577

Copy DOI

Spectroscopy

Analytical Chemistry

Atomic and Molecular Physics, and Optics

Instrumentation

Abstract

A possibility to accurately predict the absorption maximum wavelength of BODIPYs was investigated. We found that previously reported models had a low accuracy (40-57 nm) to predict BODIPYs due to the limited dataset sizes and/or number of BODIPYs (few hundreds). New models developed in this study were based on data of 6000-plus fluorescent dyes (including 4000-plus BODIPYs) and the deep neural network architecture. The high prediction accuracy (five-fold cross-validation room mean squared error (RMSE) of 18.4 nm) was obtained using a consensus model, which was more accurate than individual models. This model provided the excellent accuracy (RMSE of 8 nm) for molecules previously synthesized in our laboratory as well as for prospective validation of three new BODIPYs. We found that solvent properties did not significantly influence the model accuracy since only few BODIPYs exhibited solvatochromism. The analysis of large prediction errors suggested that compounds able to have intermolecular interactions with solvent or salts were likely to be incorrectly predicted. The consensus model is freely available at https://ochem.eu/article/134921 and can help the other researchers to accelerate design of new dyes with desired properties.

By date By citations

Citations by journals

	1 2 3
Dyes and Pigments	Dyes and Pigments, 3, 21.43% Dyes and Pigments 3 publications, 21.43%
Spectrochimica Acta - Part A: Molecular and Biomolecular Spectroscopy	Spectrochimica Acta - Part A: Molecular and Biomolecular Spectroscopy, 2, 14.29% Spectrochimica Acta - Part A: Molecular and Biomolecular Spectroscopy 2 publications, 14.29%
International Journal of Molecular Sciences	International Journal of Molecular Sciences, 1, 7.14% International Journal of Molecular Sciences 1 publication, 7.14%
npj Computational Materials	npj Computational Materials, 1, 7.14% npj Computational Materials 1 publication, 7.14%
Physical Chemistry Chemical Physics	Physical Chemistry Chemical Physics, 1, 7.14% Physical Chemistry Chemical Physics 1 publication, 7.14%
Journal of Molecular Liquids	Journal of Molecular Liquids, 1, 7.14% Journal of Molecular Liquids 1 publication, 7.14%
Journal of Chemical Theory and Computation	Journal of Chemical Theory and Computation, 1, 7.14% Journal of Chemical Theory and Computation 1 publication, 7.14%
Journal of Chemical Information and Modeling	Journal of Chemical Information and Modeling, 1, 7.14% Journal of Chemical Information and Modeling 1 publication, 7.14%
Journal of Computational Science	Journal of Computational Science, 1, 7.14% Journal of Computational Science 1 publication, 7.14%
SSRN Electronic Journal	SSRN Electronic Journal, 1, 7.14% SSRN Electronic Journal 1 publication, 7.14%
APL Machine Learning	APL Machine Learning, 1, 7.14% APL Machine Learning 1 publication, 7.14%
	1 2 3

Citations by publishers

	1 2 3 4 5 6 7
Elsevier	Elsevier, 7, 50% Elsevier 7 publications, 50%
American Chemical Society (ACS)	American Chemical Society (ACS), 2, 14.29% American Chemical Society (ACS) 2 publications, 14.29%
Multidisciplinary Digital Publishing Institute (MDPI)	Multidisciplinary Digital Publishing Institute (MDPI), 1, 7.14% Multidisciplinary Digital Publishing Institute (MDPI) 1 publication, 7.14%
Springer Nature	Springer Nature, 1, 7.14% Springer Nature 1 publication, 7.14%
Royal Society of Chemistry (RSC)	Royal Society of Chemistry (RSC), 1, 7.14% Royal Society of Chemistry (RSC) 1 publication, 7.14%
Social Science Electronic Publishing	Social Science Electronic Publishing, 1, 7.14% Social Science Electronic Publishing 1 publication, 7.14%
American Institute of Physics (AIP)	American Institute of Physics (AIP), 1, 7.14% American Institute of Physics (AIP) 1 publication, 7.14%
	1 2 3 4 5 6 7

We do not take into account publications that without a DOI.
Statistics recalculated only for publications connected to researchers, organizations and labs registered on the platform.
Statistics recalculated weekly.

{"yearsCitations":{"type":"bar","data":{"show":true,"labels":[2022,2023,2024],"ids":[0,0,0],"codes":[0,0,0],"imageUrls":["","",""],"datasets":[{"label":"Citations number","data":[5,6,3],"backgroundColor":["#3B82F6","#3B82F6","#3B82F6"],"percentage":["35.71","42.86","21.43"],"barThickness":null}]},"options":{"indexAxis":"x","maintainAspectRatio":true,"scales":{"y":{"ticks":{"precision":0,"autoSkip":false,"font":{"family":"Montserrat"},"color":"#000000"}},"x":{"ticks":{"stepSize":1,"precision":0,"font":{"family":"Montserrat"},"color":"#000000"}}},"plugins":{"legend":{"position":"top","labels":{"font":{"family":"Montserrat"},"color":"#000000"}},"title":{"display":true,"text":"Citations per year","font":{"size":24,"family":"Montserrat","weight":600},"color":"#000000"}}}},"journals":{"type":"bar","data":{"show":true,"labels":["Dyes and Pigments","Spectrochimica Acta - Part A: Molecular and Biomolecular Spectroscopy","International Journal of Molecular Sciences","npj Computational Materials","Physical Chemistry Chemical Physics","Journal of Molecular Liquids","Journal of Chemical Theory and Computation","Journal of Chemical Information and Modeling","Journal of Computational Science","SSRN Electronic Journal","APL Machine Learning"],"ids":[10101,6337,14627,19672,1773,13597,58,13608,21058,26531,35222],"codes":[0,0,0,0,0,0,0,0,0,0,0],"imageUrls":["\/storage\/images\/resized\/GDnYOu1UpMMfMMRV6Aqle4H0YLLsraeD9IP9qScG_medium.webp","\/storage\/images\/resized\/GDnYOu1UpMMfMMRV6Aqle4H0YLLsraeD9IP9qScG_medium.webp","\/storage\/images\/resized\/MjH1ITP7lMYGxeqUZfkt2BnVLgjkk413jwBV97XX_medium.webp","\/storage\/images\/resized\/voXLqlsvTwv5p3iMQ8Dhs95nqB4AXOG7Taj7G4ra_medium.webp","\/storage\/images\/resized\/leiAYcRDGTSl5B1eCnwpSGqmDEUEfDPPoYisFGhT_medium.webp","\/storage\/images\/resized\/GDnYOu1UpMMfMMRV6Aqle4H0YLLsraeD9IP9qScG_medium.webp","\/storage\/images\/resized\/iLiQsFqFaSEx6chlGQ5fbAwF6VYU3WWa08hkss0g_medium.webp","\/storage\/images\/resized\/iLiQsFqFaSEx6chlGQ5fbAwF6VYU3WWa08hkss0g_medium.webp","\/storage\/images\/resized\/GDnYOu1UpMMfMMRV6Aqle4H0YLLsraeD9IP9qScG_medium.webp","\/storage\/images\/resized\/VB6UIgqsyDBgrsTtqT4C2ImAHGDidVrMrprJV4LS_medium.webp","\/storage\/images\/resized\/ARM4e6URKRsbRZvIF0vFis9DjxGloBjnBYJXbHmZ_medium.webp"],"datasets":[{"label":"","data":[3,2,1,1,1,1,1,1,1,1,1],"backgroundColor":["#3B82F6","#3B82F6","#3B82F6","#3B82F6","#3B82F6","#3B82F6","#3B82F6","#3B82F6","#3B82F6","#3B82F6","#3B82F6"],"percentage":[21.43,14.29,7.14,7.14,7.14,7.14,7.14,7.14,7.14,7.14,7.14],"barThickness":13}]},"options":{"indexAxis":"y","maintainAspectRatio":false,"scales":{"y":{"ticks":{"precision":0,"autoSkip":false,"font":{"family":"Montserrat"},"color":"#000000"}},"x":{"ticks":{"stepSize":null,"precision":0,"font":{"family":"Montserrat"},"color":"#000000"}}},"plugins":{"legend":{"position":"top","labels":{"font":{"family":"Montserrat"},"color":"#000000"}},"title":{"display":true,"text":"Journals","font":{"size":24,"family":"Montserrat","weight":600},"color":"#000000"}}}},"publishers":{"type":"bar","data":{"show":true,"labels":["Elsevier","American Chemical Society (ACS)","Multidisciplinary Digital Publishing Institute (MDPI)","Springer Nature","Royal Society of Chemistry (RSC)","Social Science Electronic Publishing","American Institute of Physics (AIP)"],"ids":[17,40,202,8,123,7090,250],"codes":[0,0,0,0,0,0,0],"imageUrls":["\/storage\/images\/resized\/GDnYOu1UpMMfMMRV6Aqle4H0YLLsraeD9IP9qScG_medium.webp","\/storage\/images\/resized\/iLiQsFqFaSEx6chlGQ5fbAwF6VYU3WWa08hkss0g_medium.webp","\/storage\/images\/resized\/MjH1ITP7lMYGxeqUZfkt2BnVLgjkk413jwBV97XX_medium.webp","\/storage\/images\/resized\/voXLqlsvTwv5p3iMQ8Dhs95nqB4AXOG7Taj7G4ra_medium.webp","\/storage\/images\/resized\/leiAYcRDGTSl5B1eCnwpSGqmDEUEfDPPoYisFGhT_medium.webp","\/storage\/images\/resized\/VB6UIgqsyDBgrsTtqT4C2ImAHGDidVrMrprJV4LS_medium.webp","\/storage\/images\/resized\/ARM4e6URKRsbRZvIF0vFis9DjxGloBjnBYJXbHmZ_medium.webp"],"datasets":[{"label":"","data":[7,2,1,1,1,1,1],"backgroundColor":["#3B82F6","#3B82F6","#3B82F6","#3B82F6","#3B82F6","#3B82F6","#3B82F6"],"percentage":[50,14.29,7.14,7.14,7.14,7.14,7.14],"barThickness":13}]},"options":{"indexAxis":"y","maintainAspectRatio":false,"scales":{"y":{"ticks":{"precision":0,"autoSkip":false,"font":{"family":"Montserrat"},"color":"#000000"}},"x":{"ticks":{"stepSize":null,"precision":0,"font":{"family":"Montserrat"},"color":"#000000"}}},"plugins":{"legend":{"position":"top","labels":{"font":{"family":"Montserrat"},"color":"#000000"}},"title":{"display":true,"text":"Publishers","font":{"size":24,"family":"Montserrat","weight":600},"color":"#000000"}}}}}

Metrics

Cite this

GOST |

Cite this

GOST Copy

Ksenofontov A. A. et al. Deep neural network model for highly accurate prediction of BODIPYs absorption // Spectrochimica Acta - Part A: Molecular and Biomolecular Spectroscopy. 2022. Vol. 267. p. 120577.

GOST all authors (up to 50) Copy

Ksenofontov A. A., Lukanov M. M., Bocharov P. S., Berezin M. B., Tetko I. V. Deep neural network model for highly accurate prediction of BODIPYs absorption // Spectrochimica Acta - Part A: Molecular and Biomolecular Spectroscopy. 2022. Vol. 267. p. 120577.

RIS |

Cite this

RIS Copy

TY - JOUR

DO - 10.1016/j.saa.2021.120577

UR - https://doi.org/10.1016%2Fj.saa.2021.120577

TI - Deep neural network model for highly accurate prediction of BODIPYs absorption

T2 - Spectrochimica Acta - Part A: Molecular and Biomolecular Spectroscopy

AU - Ksenofontov, Alexander A

AU - Lukanov, Michail M

AU - Bocharov, Pavel S

AU - Berezin, Michail B

AU - Tetko, Igor V

PY - 2022

DA - 2022/02/01 00:00:00

PB - Elsevier

SP - 120577

VL - 267

SN - 1386-1425

ER -

BibTex

Cite this

BibTex Copy

@article{2022_Ksenofontov,

author = {Alexander A Ksenofontov and Michail M Lukanov and Pavel S Bocharov and Michail B Berezin and Igor V Tetko},

title = {Deep neural network model for highly accurate prediction of BODIPYs absorption},

journal = {Spectrochimica Acta - Part A: Molecular and Biomolecular Spectroscopy},

year = {2022},

volume = {267},

publisher = {Elsevier},

month = {feb},

url = {https://doi.org/10.1016%2Fj.saa.2021.120577},

pages = {120577},

doi = {10.1016/j.saa.2021.120577}

}

Found error?

Publisher

Elsevier

Journal

Spectrochimica Acta - Part A: Molecular and Biomolecular Spectroscopy

Quartile SCImago

Quartile WOS

Impact factor

4.4

ISSN

13861425 (Print)

Profiles