Predicting Enantioselectivity of Ruthenium-Catalyzed Ketone Hydrogenation with 3D Structure-Based Deep Learning

We report machine-learning (ML) models that predict with high accuracy the enantioselectivity of ketone hydrogenation with Noyori-type diphosphine-diamine catalysts. To mitigate bias in published data, we combined a data set curated from the literature with >1,000 examples from our own high-throughput experimentation. We demonstrate that 3D graph neural networks, trained on 3D representations derived from the enantiodetermining transition state, outperform models based on 2D graphs, molecular fingerprints, and descriptors derived from semiempirical quantum calculations. These results indicate that models trained on 3D structural representations that reflect catalyst-substrate interactions relevant to enantioselectivity can accurately extrapolate to structures distinct from those in the training set.

Authors

Institutions

Publication Details

Journal
Journal of the American Chemical Society
Published
2026-07-23
DOI
https://doi.org/10.1021/jacs.6c07313
Primary Topic
Machine Learning in Materials Science
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Predicting Enantioselectivity of Ruthenium-Catalyzed Ketone Hydrogenation with 3D Structure-Based Deep Learning

Nicholas Hadler, Joscha Hoche, Masha Elkin, Jan Gerit Brandenburg et al.
Journal of the American Chemical Society
Machine Learning in Materials Science
article

Predicting Enantioselectivity of Ruthenium-Catalyzed Ketone Hydrogenation with 3D Structure-Based Deep Learning

Nicholas Hadler, Joscha Hoche, Masha Elkin, Jan Gerit Brandenburg, N. Ian Rinehart, Matthew Avaylon, John F. Hartwig, Gunther H. Weber, Evelyn Ramirez, Michael W. Mahoney, Talita Perciano
article en

Abstract

We report machine-learning (ML) models that predict with high accuracy the enantioselectivity of ketone hydrogenation with Noyori-type diphosphine-diamine catalysts. To mitigate bias in published data, we combined a data set curated from the literature with >1,000 examples from our own high-throughput experimentation. We demonstrate that 3D graph neural networks, trained on 3D representations derived from the enantiodetermining transition state, outperform models based on 2D graphs, molecular fingerprints, and descriptors derived from semiempirical quantum calculations. These results indicate that models trained on 3D structural representations that reflect catalyst-substrate interactions relevant to enantioselectivity can accurately extrapolate to structures distinct from those in the training set.

Journal of the American Chemical Society
International Computer Science Institute (US), Lawrence Berkeley National Laboratory (US), Merck KGaA, Darmstadt (Germany) (DE), Scientific Data Systems (United States) (US), NOAA Chemical Sciences Laboratory (US), University of California, Berkeley (US)
National Science Foundation, National Institutes of Health
Openalex Percentile: Top 19%
Machine Learning in Materials Science
DOISourceOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Predicting Enantioselectivity of Ruthenium-Catalyzed Ketone Hydrogenation with 3D Structure-Based Deep Learning — Nicholas Hadler, Joscha Hoche, et al. · Journal of the American Chemical Society (2026) | TGRS Research Map | TGRS