Predictive modeling of visible-light azo-photoswitches’ properties using structural features

Abstract In this manuscript we present the strategy for modeling photoswitch properties (maximum absorption wavelength and thermal half-life of photoisomers) of visible-light azo-photoswitches using structural data. We compile a comprehensive data set from literature sources and perform a rigorous b...

Full description

Saved in:
Bibliographic Details
Main Authors: Said Byadi, P. K. Hashim, Pavel Sidorov
Format: Article
Language:English
Published: BMC 2025-04-01
Series:Journal of Cheminformatics
Subjects:
Online Access:https://doi.org/10.1186/s13321-025-00993-7
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850153561340510208
author Said Byadi
P. K. Hashim
Pavel Sidorov
author_facet Said Byadi
P. K. Hashim
Pavel Sidorov
author_sort Said Byadi
collection DOAJ
description Abstract In this manuscript we present the strategy for modeling photoswitch properties (maximum absorption wavelength and thermal half-life of photoisomers) of visible-light azo-photoswitches using structural data. We compile a comprehensive data set from literature sources and perform a rigorous benchmark to select the best feature type and modeling approach. The fragment counts have demonstrated the best performance in the benchmark for both properties. We validate the models in cross-validation and on an external set. The predictions of absorption wavelengths for this set are highly accurate; on the other hand, the model for thermal half-life is less reliable, likely due to the modest size of the data set related to half-life of photoisomers, although consensus modeling approach allows to improve the predictivity. We also provide an interpretation of the modeling results using ColorAtom approach and the insights into the chemical space covered by the data set. Scientific contribution The paper provides a machine learning approach based only on structural features to predict two important photoswitch properties. Unlike previous studies, we do not use any quantum chemical features which accelerates the modeling procedure, while the accuracy of models remains high. Moreover, the fragment counts offer unique approach to model interpretation that is useful for rational design of photoswitches with desired properties.
format Article
id doaj-art-1cb1f7484e5a409d91145286d6fd641e
institution OA Journals
issn 1758-2946
language English
publishDate 2025-04-01
publisher BMC
record_format Article
series Journal of Cheminformatics
spelling doaj-art-1cb1f7484e5a409d91145286d6fd641e2025-08-20T02:25:41ZengBMCJournal of Cheminformatics1758-29462025-04-011711910.1186/s13321-025-00993-7Predictive modeling of visible-light azo-photoswitches’ properties using structural featuresSaid Byadi0P. K. Hashim1Pavel Sidorov2Institute for Chemical Reaction Design and Discovery (WPI-ICReDD), Hokkaido UniversityResearch Institute for Electronic Science, Hokkaido UniversityInstitute for Chemical Reaction Design and Discovery (WPI-ICReDD), Hokkaido UniversityAbstract In this manuscript we present the strategy for modeling photoswitch properties (maximum absorption wavelength and thermal half-life of photoisomers) of visible-light azo-photoswitches using structural data. We compile a comprehensive data set from literature sources and perform a rigorous benchmark to select the best feature type and modeling approach. The fragment counts have demonstrated the best performance in the benchmark for both properties. We validate the models in cross-validation and on an external set. The predictions of absorption wavelengths for this set are highly accurate; on the other hand, the model for thermal half-life is less reliable, likely due to the modest size of the data set related to half-life of photoisomers, although consensus modeling approach allows to improve the predictivity. We also provide an interpretation of the modeling results using ColorAtom approach and the insights into the chemical space covered by the data set. Scientific contribution The paper provides a machine learning approach based only on structural features to predict two important photoswitch properties. Unlike previous studies, we do not use any quantum chemical features which accelerates the modeling procedure, while the accuracy of models remains high. Moreover, the fragment counts offer unique approach to model interpretation that is useful for rational design of photoswitches with desired properties.https://doi.org/10.1186/s13321-025-00993-7PhotoswitchesAzobenzeneQuantitative structure–property relationshipMachine learningMolecular descriptors
spellingShingle Said Byadi
P. K. Hashim
Pavel Sidorov
Predictive modeling of visible-light azo-photoswitches’ properties using structural features
Journal of Cheminformatics
Photoswitches
Azobenzene
Quantitative structure–property relationship
Machine learning
Molecular descriptors
title Predictive modeling of visible-light azo-photoswitches’ properties using structural features
title_full Predictive modeling of visible-light azo-photoswitches’ properties using structural features
title_fullStr Predictive modeling of visible-light azo-photoswitches’ properties using structural features
title_full_unstemmed Predictive modeling of visible-light azo-photoswitches’ properties using structural features
title_short Predictive modeling of visible-light azo-photoswitches’ properties using structural features
title_sort predictive modeling of visible light azo photoswitches properties using structural features
topic Photoswitches
Azobenzene
Quantitative structure–property relationship
Machine learning
Molecular descriptors
url https://doi.org/10.1186/s13321-025-00993-7
work_keys_str_mv AT saidbyadi predictivemodelingofvisiblelightazophotoswitchespropertiesusingstructuralfeatures
AT pkhashim predictivemodelingofvisiblelightazophotoswitchespropertiesusingstructuralfeatures
AT pavelsidorov predictivemodelingofvisiblelightazophotoswitchespropertiesusingstructuralfeatures