Predicting three-component reaction outcomes from ~40,000 miniaturized reactant combinations
Science Advances · 30.05.2025 · 11 (22)
DOI: 10.1126/sciadv.adw6047 ↗Kurz gefasst
Fachartikel in der Zeitschrift Science Advances, erschienen am 30.05.2025. Verfasst von Julian Götz und 7 weiteren Autor:innen. Beteiligte Einrichtung: Laboratory for Organic Chemistry, Department of Chemistry and Applied Biosciences, ETH Zürich, 8093 Zürich, Switzerland. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Efficient drug discovery depends on reliable synthetic access to candidate molecules, but emerging machine learning approaches to predicting reaction outcomes are hampered by poor availability of high-quality data. Here, we demonstrate an on-demand synthesis platform based on a three-component reaction that delivers drug-like molecules. Miniaturization and automation enable the execution and analysis of 50,000 distinct reactions on a 3-microliter scale from 193 different substrates, producing the largest public reaction outcome dataset. With machine learning, we accurately predict the result of unknown reactions and analyze the impact of dataset size on model training, both enabling accurate outcome predictions even for unseen reactants and providing a sufficiently large dataset to critically evaluate emerging machine learning approaches to chemical reactivity.
Autor:innen und Institutionen
- Laboratory for Organic Chemistry, Department of Chemistry and Applied Biosciences, ETH Zürich, 8093 Zürich, Switzerland.
- Molecular and Biomolecular Analysis Service (MoBiAS), Department of Chemistry and Applied Biosciences, ETH Zürich, 8093 Zürich, Switzerland.
ORCID-Profile: Julian Götz, Euan Richards, Iain A Stepek, Yu Takahashi, Jeffrey W Bode
Zitieren
APA
Götz, J., Richards, E., Stepek, I. A., Takahashi, Y., Huang, Y. L., Bertschi, L., Rubi, B., & Bode, J. W. (2025). Predicting three-component reaction outcomes from ~40,000 miniaturized reactant combinations. Science Advances, 11(22). https://doi.org/10.1126/sciadv.adw6047
Vancouver
Götz J, Richards E, Stepek IA, Takahashi Y, Huang YL, Bertschi L, et al. Predicting three-component reaction outcomes from ~40,000 miniaturized reactant combinations. Science Advances. 2025;11(22). doi:10.1126/sciadv.adw6047
BibTeX
@article{Gtz2025,
author = {Götz, Julian and Richards, Euan and Stepek, Iain A and Takahashi, Yu and Huang, Yi-Lin and Bertschi, Louis and Rubi, Bertran and Bode, Jeffrey W},
title = {Predicting three-component reaction outcomes from ~40,000 miniaturized reactant combinations},
journal = {Science Advances},
year = {2025},
volume = {11},
number = {22},
doi = {10.1126/sciadv.adw6047}
}
EUVIMED