Home > Research > Publications & Outputs > Data-driven discovery of molecular photoswitche...

Links

Text available via DOI:

View graph of relations

Data-driven discovery of molecular photoswitches with multioutput Gaussian processes

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Data-driven discovery of molecular photoswitches with multioutput Gaussian processes. / Griffiths, Ryan-Rhys; Greenfield, Jake L; Thawani, Aditya R et al.
In: Chemical Science, Vol. 13, No. 45, 07.12.2022, p. 13541-13551.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Griffiths, R-R, Greenfield, JL, Thawani, AR, Jamasb, AR, Moss, HB, Bourached, A, Jones, P, McCorkindale, W, Aldrick, AA & Fuchter, MJ 2022, 'Data-driven discovery of molecular photoswitches with multioutput Gaussian processes', Chemical Science, vol. 13, no. 45, pp. 13541-13551. https://doi.org/10.1039/D2SC04306H

APA

Griffiths, R.-R., Greenfield, J. L., Thawani, A. R., Jamasb, A. R., Moss, H. B., Bourached, A., Jones, P., McCorkindale, W., Aldrick, A. A., & Fuchter, M. J. (2022). Data-driven discovery of molecular photoswitches with multioutput Gaussian processes. Chemical Science, 13(45), 13541-13551. https://doi.org/10.1039/D2SC04306H

Vancouver

Griffiths RR, Greenfield JL, Thawani AR, Jamasb AR, Moss HB, Bourached A et al. Data-driven discovery of molecular photoswitches with multioutput Gaussian processes. Chemical Science. 2022 Dec 7;13(45):13541-13551. Epub 2022 Nov 10. doi: 10.1039/D2SC04306H

Author

Griffiths, Ryan-Rhys ; Greenfield, Jake L ; Thawani, Aditya R et al. / Data-driven discovery of molecular photoswitches with multioutput Gaussian processes. In: Chemical Science. 2022 ; Vol. 13, No. 45. pp. 13541-13551.

Bibtex

@article{6a38628de38c4cfca06ae0a83e094f8c,
title = "Data-driven discovery of molecular photoswitches with multioutput Gaussian processes",
abstract = "Photoswitchable molecules display two or more isomeric forms that may be accessed using light. Separating the electronic absorption bands of these isomers is key to selectively addressing a specific isomer and achieving high photostationary states whilst overall red-shifting the absorption bands serves to limit material damage due to UV-exposure and increases penetration depth in photopharmacological applications. Engineering these properties into a system through synthetic design however, remains a challenge. Here, we present a data-driven discovery pipeline for molecular photoswitches underpinned by dataset curation and multitask learning with Gaussian processes. In the prediction of electronic transition wavelengths, we demonstrate that a multioutput Gaussian process (MOGP) trained using labels from four photoswitch transition wavelengths yields the strongest predictive performance relative to single-task models as well as operationally outperforming time-dependent density functional theory (TD-DFT) in terms of the wall-clock time for prediction. We validate our proposed approach experimentally by screening a library of commercially available photoswitchable molecules. Through this screen, we identified several motifs that displayed separated electronic absorption bands of their isomers, exhibited red-shifted absorptions, and are suited for information transfer and photopharmacological applications. Our curated dataset, code, as well as all models are made available at https://github.com/Ryan-Rhys/The-Photoswitch-Dataset.",
author = "Ryan-Rhys Griffiths and Greenfield, {Jake L} and Thawani, {Aditya R} and Jamasb, {Arian R} and Moss, {Henry B} and Anthony Bourached and Penelope Jones and William McCorkindale and Aldrick, {Alexander A} and Fuchter, {Matthew J}",
year = "2022",
month = dec,
day = "7",
doi = "10.1039/D2SC04306H",
language = "English",
volume = "13",
pages = "13541--13551",
journal = "Chemical Science",
issn = "2041-6520",
publisher = "Royal Society of Chemistry",
number = "45",

}

RIS

TY - JOUR

T1 - Data-driven discovery of molecular photoswitches with multioutput Gaussian processes

AU - Griffiths, Ryan-Rhys

AU - Greenfield, Jake L

AU - Thawani, Aditya R

AU - Jamasb, Arian R

AU - Moss, Henry B

AU - Bourached, Anthony

AU - Jones, Penelope

AU - McCorkindale, William

AU - Aldrick, Alexander A

AU - Fuchter, Matthew J

PY - 2022/12/7

Y1 - 2022/12/7

N2 - Photoswitchable molecules display two or more isomeric forms that may be accessed using light. Separating the electronic absorption bands of these isomers is key to selectively addressing a specific isomer and achieving high photostationary states whilst overall red-shifting the absorption bands serves to limit material damage due to UV-exposure and increases penetration depth in photopharmacological applications. Engineering these properties into a system through synthetic design however, remains a challenge. Here, we present a data-driven discovery pipeline for molecular photoswitches underpinned by dataset curation and multitask learning with Gaussian processes. In the prediction of electronic transition wavelengths, we demonstrate that a multioutput Gaussian process (MOGP) trained using labels from four photoswitch transition wavelengths yields the strongest predictive performance relative to single-task models as well as operationally outperforming time-dependent density functional theory (TD-DFT) in terms of the wall-clock time for prediction. We validate our proposed approach experimentally by screening a library of commercially available photoswitchable molecules. Through this screen, we identified several motifs that displayed separated electronic absorption bands of their isomers, exhibited red-shifted absorptions, and are suited for information transfer and photopharmacological applications. Our curated dataset, code, as well as all models are made available at https://github.com/Ryan-Rhys/The-Photoswitch-Dataset.

AB - Photoswitchable molecules display two or more isomeric forms that may be accessed using light. Separating the electronic absorption bands of these isomers is key to selectively addressing a specific isomer and achieving high photostationary states whilst overall red-shifting the absorption bands serves to limit material damage due to UV-exposure and increases penetration depth in photopharmacological applications. Engineering these properties into a system through synthetic design however, remains a challenge. Here, we present a data-driven discovery pipeline for molecular photoswitches underpinned by dataset curation and multitask learning with Gaussian processes. In the prediction of electronic transition wavelengths, we demonstrate that a multioutput Gaussian process (MOGP) trained using labels from four photoswitch transition wavelengths yields the strongest predictive performance relative to single-task models as well as operationally outperforming time-dependent density functional theory (TD-DFT) in terms of the wall-clock time for prediction. We validate our proposed approach experimentally by screening a library of commercially available photoswitchable molecules. Through this screen, we identified several motifs that displayed separated electronic absorption bands of their isomers, exhibited red-shifted absorptions, and are suited for information transfer and photopharmacological applications. Our curated dataset, code, as well as all models are made available at https://github.com/Ryan-Rhys/The-Photoswitch-Dataset.

U2 - 10.1039/D2SC04306H

DO - 10.1039/D2SC04306H

M3 - Journal article

VL - 13

SP - 13541

EP - 13551

JO - Chemical Science

JF - Chemical Science

SN - 2041-6520

IS - 45

ER -