Design and Experimental Validation of a Photocatalyst Recommender Based on a Large Language Model

F Francis Millward (Organic Semiconductor Centre, EaStCHEM School of Chemistry) M Michał Kulczykowski (Allchemy, Inc. Highland Indiana 46322 USA) J Jay Badland‐Shaw (Organic Semiconductor Centre, EaStCHEM School of Chemistry University of St Andrews St Andrews KY16 9ST UK) S Sara Szymkuc (Allchemy, Inc. Highland Indiana 46322 USA) R Rajan Suraksha (Organic Semiconductor Centre, EaStCHEM School of Chemistry University of St Andrews St Andrews KY16 9ST UK) A Aniket Kumar Srivastawa (Organic Semiconductor Centre, EaStCHEM School of Chemistry University of St Andrews St Andrews KY16 9ST UK) V Violaine Manet (Organic Semiconductor Centre, EaStCHEM School of Chemistry University of St Andrews St Andrews KY16 9ST UK) M Máire Griffin (Organic Semiconductor Centre, EaStCHEM School of Chemistry University of St Andrews St Andrews KY16 9ST UK) M Megan Bryden (Organic Semiconductor Centre, EaStCHEM School of Chemistry University of St Andrews St Andrews KY16 9ST UK) T Thomas Comerford (Organic Semiconductor Centre, EaStCHEM School of Chemistry University of St Andrews St Andrews KY16 9ST UK) L Lea Hämmerling (Organic Semiconductor Centre, EaStCHEM School of Chemistry University of St Andrews St Andrews KY16 9ST UK) A Aminata Mariko (Organic Semiconductor Centre, EaStCHEM School of Chemistry University of St Andrews St Andrews KY16 9ST UK) B Bartosz A. Grzybowski E Eli Zysman‐Colman (Organic Semiconductor Centre, EaStCHEM School of Chemistry University of St Andrews St Andrews UK)

Abstract

Abstract Utilizing an extensive library of literature on photocatalytic transformations, we disclose the development of a machine learning (ML) model for the recommendation of photocatalysts most suitable for reactions of interest. The model is trained on > 36 000 such literature examples and uses an architecture inspired by the Bidirectional Encoder Representations from Transformer (BERT) large language model. Under cross‐validation, it can suggest the “correct” photocatalysts with ∼90% accuracy. When experimentally tested on five out‐of‐box reactions, this algorithm consistently suggested photocatalysts that gave yields competitive to those chosen by human researchers and frequently suggested alternative photocatalysts that are potentially more appealing than the originally selected photocatalyst. Altogether, this platform serves as a valuable tool for researchers undertaking reaction optimization programs. The model is free to use at https://photocatals.grzybowskigroup.pl/predict/ .

Article Details

Volume / Issue Vol. 65, Issue 4
Published January 22, 2026
ISSN 1433-7851
Publisher Wiley

Journal Info

Angewandte Chemie International Edition

Wiley

ISSN: 1433-7851 Physical Sciences

Authors (14)

F

Francis Millward

Organic Semiconductor Centre, EaStCHEM School of Chemistry

M

Michał Kulczykowski

Allchemy, Inc. Highland Indiana 46322 USA

J

Jay Badland‐Shaw

Organic Semiconductor Centre, EaStCHEM School of Chemistry University of St Andrews St Andrews KY16 9ST UK

S

Sara Szymkuc

Allchemy, Inc. Highland Indiana 46322 USA

R

Rajan Suraksha

Organic Semiconductor Centre, EaStCHEM School of Chemistry University of St Andrews St Andrews KY16 9ST UK

A

Aniket Kumar Srivastawa

Organic Semiconductor Centre, EaStCHEM School of Chemistry University of St Andrews St Andrews KY16 9ST UK

V

Violaine Manet

Organic Semiconductor Centre, EaStCHEM School of Chemistry University of St Andrews St Andrews KY16 9ST UK

M

Máire Griffin

Organic Semiconductor Centre, EaStCHEM School of Chemistry University of St Andrews St Andrews KY16 9ST UK

M

Megan Bryden

Organic Semiconductor Centre, EaStCHEM School of Chemistry University of St Andrews St Andrews KY16 9ST UK

T

Thomas Comerford

Organic Semiconductor Centre, EaStCHEM School of Chemistry University of St Andrews St Andrews KY16 9ST UK

L

Lea Hämmerling

Organic Semiconductor Centre, EaStCHEM School of Chemistry University of St Andrews St Andrews KY16 9ST UK

A

Aminata Mariko

Organic Semiconductor Centre, EaStCHEM School of Chemistry University of St Andrews St Andrews KY16 9ST UK

B

Bartosz A. Grzybowski

E

Eli Zysman‐Colman

Organic Semiconductor Centre, EaStCHEM School of Chemistry University of St Andrews St Andrews UK