Data-Guided Descriptor Rebalancing for Monophosphine Ligand Training Set Development
Organic Process Research & Development · 28.10.2026
DOI: 10.1021/acs.oprd.6c00355 ↗Kurz gefasst
Fachartikel in der Zeitschrift Organic Process Research & Development, online erschienen am 28.10.2026. Verfasst von Jamie A. Cadge und 3 weiteren Autor:innen. Die Arbeit nennt 38 Literaturangaben. Gefördert von: Division of Chemistry.
Abstract (Originalsprache)
Data-guided optimization strategies increasingly rely on well-designed training sets and meaningful chemical space representations, yet identifying appropriate descriptors and ensuring domain applicability remain persistent challenges. Here, we present an iterative workflow for refining monodentate phosphine-based training sets by coupling experimental reaction data with systematic feature evaluation. Using a pharmaceutically relevant cross-coupling reaction as a case study, we demonstrate how imbalances in steric and electronic descriptors of monodentate phosphines derived from the kraken database, along with limited feature overlap between training and validation sets, can challenge classification models and virtual screening performance. By rebalancing descriptor types, we generated a more chemically intuitive representation that improved predictive performance in a classification model. This approach enables the development of a redesigned monophosphine ligand screening set with an enhanced coverage of key structural and electronic dimensions. The resulting workflow provides a generalizable template for constructing more robust, diverse, and application-ready training sets for catalyst screening and reaction optimization within process chemistry.
Förderung
- Division of Chemistry
Zitieren
APA
Cadge, J. A., Sach, N. W., Bernier, L., & Sigman, M. S. (2026). Data-Guided Descriptor Rebalancing for Monophosphine Ligand Training Set Development. Organic Process Research & Development. https://doi.org/10.1021/acs.oprd.6c00355
Vancouver
Cadge JA, Sach NW, Bernier L, Sigman MS. Data-Guided Descriptor Rebalancing for Monophosphine Ligand Training Set Development. Organic Process Research & Development. 2026. doi:10.1021/acs.oprd.6c00355
BibTeX
@article{Cadge2026,
author = {Cadge, Jamie A. and Sach, Neal W. and Bernier, Louise and Sigman, Matthew S.},
title = {Data-Guided Descriptor Rebalancing for Monophosphine Ligand Training Set Development},
journal = {Organic Process Research & Development},
year = {2026},
doi = {10.1021/acs.oprd.6c00355}
}
EUVIMED