Bridging Chemical Literature and Molecular Graphs: LLM-Augmented Enantioselectivity Prediction for Iridium-Catalyzed Asymmetric C-H Borylation.
4 affiliations
- 1Hong Kong University of Science and Technology, Hong Kong, China.
- 2Shenzhen Bay Laboratory, Shen Zhen, China.
- 3Shenzhen Medical Academy of Research and Translation, Shen Zhen, China.
- 4School of Materials and New Energy, South China Normal University, Shan Wei, China.
Abstract
Asymmetric C-H borylation provides direct access to enantioenriched organoboron compounds. Predictive catalyst design for this reaction class remains challenging, as stereocontrol arises from coupled interactions among catalyst, substrate, and product structures. Moreover, mechanistic knowledge is dispersed across the literature. Here we report a machine-learning framework for predicting enantioselectivity in iridium-catalyzed asymmetric C-H borylation that bridges molecular graphs and chemical literature. A unified dataset comprising 800 literature-reported reactions was constructed for this reaction class. The model combines a multi-entity three-dimensional graph encoder for catalyst, substrate, and product with temperature-aware kinetic treatment, and a large-language-model prior module that extracts atom-resolved mechanistic annotations from primary publications. On a scaffold-based held-out test set, the STEREO-Lit (Spatial Three-Entity Reaction Encoder Literature) model achieves strong predictive performance, outperforming conventional machine-learning baselines and a geometry-grounded control. Perturbation studies further show that literature-derived semantic annotations contribute chemically meaningful, site-specific information rather than merely increasing model capacity. The trained model was subsequently applied to explore a reaction space of about 100 000 catalyst-substrate combinations and identify promising high-improvement candidates, several of which were supported by DFT calculations. The framework couples multi-entity 3D encoding with literature-derived priors, and remains predictive when training data are limited to a few hundred reactions.
Related
- Universal Model for Atoms (UMA) in Computational Asymmetric Catalysis: Comparing Enantioselectivity Predictions
- Literature-Scale Mössbauer Data Enable Prediction, Electronic-State Interpretation, and Chemical Insight in Molecular Iron Chemistry
- Graph attention framework for site-selectivity prediction in undirected C(sp3)–H borylation
- Sustainable photocatalytic borylation: updated review
- Zinc Redox Catalysis in the Photochemical Borylation of Fluorocarbons
BibTeX
@article{wang2026bridging,
title = {{Bridging Chemical Literature and Molecular Graphs: LLM-Augmented Enantioselectivity Prediction for Iridium-Catalyzed Asymmetric C-H Borylation.}},
author = {Zhe Wang and Baohua Zhang and Yi Isaac Yang and Yuan Yao and Yinwu Li},
journal = {Advanced science (Weinheim, Baden-Wurttemberg, Germany)},
year = {2026},
month = oct,
doi = {10.1002/advs.78094},
url = {https://europepmc.org/article/MED/42876088},
note = {CC BY},
}
RIS
TY - JOUR
TI - Bridging Chemical Literature and Molecular Graphs: LLM-Augmented Enantioselectivity Prediction for Iridium-Catalyzed Asymmetric C-H Borylation.
AU - Zhe Wang
AU - Baohua Zhang
AU - Yi Isaac Yang
AU - Yuan Yao
AU - Yinwu Li
PY - 2026
DA - 2026/10/14
JO - Advanced science (Weinheim, Baden-Wurttemberg, Germany)
DO - 10.1002/advs.78094
UR - https://europepmc.org/article/MED/42876088
AB - Asymmetric C-H borylation provides direct access to enantioenriched organoboron compounds. Predictive catalyst design for this reaction class remains challenging, as stereocontrol arises from coupled interactions among catalyst, substrate, and product structures. Moreover, mechanistic knowledge is dispersed across the literature. Here we report a machine-learning framework for predicting enantioselectivity in iridium-catalyzed asymmetric C-H borylation that bridges molecular graphs and chemical literature. A unified dataset comprising 800 literature-reported reactions was constructed for this reaction class. The model combines a multi-entity three-dimensional graph encoder for catalyst, substrate, and product with temperature-aware kinetic treatment, and a large-language-model prior module that extracts atom-resolved mechanistic annotations from primary publications. On a scaffold-based held-out test set, the STEREO-Lit (Spatial Three-Entity Reaction Encoder Literature) model achieves strong predictive performance, outperforming conventional machine-learning baselines and a geometry-grounded control. Perturbation studies further show that literature-derived semantic annotations contribute chemically meaningful, site-specific information rather than merely increasing model capacity. The trained model was subsequently applied to explore a reaction space of about 100 000 catalyst-substrate combinations and identify promising high-improvement candidates, several of which were supported by DFT calculations. The framework couples multi-entity 3D encoding with literature-derived priors, and remains predictive when training data are limited to a few hundred reactions.
SN - 2198-3844
ER -