A Fragment Based Approach Towards Curating, Comparing and Developing Machine Learning Models Applied in Photochemistry
Preprint
- 30 July 2025
- preprint
- Published by American Chemical Society (ACS) in ChemRxiv
Abstract
The development of Graph Neural Networks for the task of predicting molecular properties has gained a great deal of attention as it typically allows the correlation of quick to compute atomic and bond descriptors with overall molecular properties. With the raising interest in photochemistry and photocatalysis as sustainable alternatives to thermal reactions, curation of virtual databases of computed photophysical properties for training of machine learning models has become popular. Unfortunately, current efforts fail to consider the exciton localization onto different chromophores of the same molecule, leading to potentially large prediction errors. Here we describe a molecular fragmentation strategy that can be used to overcome this limitation, while also providing a way to compare structural diversity between different libraries. Using a newly generated a database of 46,432 adiabatic S0-T1 energy gaps (ALFAST-DB), we compare its diversity against two datasets from the literature and demonstrate that a fragment-based delta learning approach improves model generalizability while achieving accuracies matching those of traditional message passing graph neural network architectures (MPGNN)Keywords
All Related Versions
This publication has 4 references indexed in Scilit:
- Predicting homopolymer and copolymer solubility through machine learningDigital Discovery, 2024
- EnTdecker − A Machine Learning-Based Platform for Guiding Substrate Discovery in Energy Transfer CatalysisJournal of the American Chemical Society, 2024
- Expansion of bond dissociation prediction with machine learning to medicinally and environmentally relevant chemical spaceDigital Discovery, 2023
- Organic Spectroscopy2005