Context-Aware Automated NMR Structure Elucidation
Abstract
Machine learning approaches are rapidly revolutionizing the ability to analyze and extract structural insights from chemical data, enabling high-throughput chemical discovery. While existing data-driven approaches have shown remarkable promise for predicting chemical structures in the de novo setting, incorporating additional chemically informed context offers the opportunity to further improve these models' performance and extend their real-world utility. Here we provide a straightforward protocol to combine artificial-intelligence-based spectroscopic elucidation pipelines with contextual chemical data, e.g., known reactants or a desired product, by using automated retrosynthetic analysis to generate large training sets of molecules and contextual data in the form of synthetic precursors. We demonstrate our approach by showing that our recently introduced NMR structure elucidation framework can be trained to effectively leverage molecular precursor context. We show that when the chemical context provides useful information on the target molecule we obtain dramatically improved accuracy over using NMR spectra alone, obtaining Top-15 accuracies of up to 95.4% for molecules up to 40 heavy atoms spanning the full elemental range of organic chemistry. Furthermore, we demonstrate that our approach is highly robust, such that even when the context provided is uncorrelated with the target, one still obtains accuracies commensurate with those of the original NMR structure elucidation framework. This approach provides an efficient route to improve a wide range of spectroscopic structure elucidation platforms using contextual data.
Related
- Pushing the Limits of One-Dimensional NMR Spectroscopy for Automated Structure Elucidation Using Artificial Intelligence
- Chemistry-Informed Multimodal Model for Structure Elucidation in Automated Reaction Discovery
- A Modular Rapid-Injection NMR for Structure Elucidation and Kinetic Analysis.
- End-to-end multimodal structure elucidation from raw spectra combining contrastive learning and evolutionary algorithms
- MAST: Motif-Augmented Diffusion with Search Tree for Spectroscopic Molecular Structure Elucidation
BibTeX
@misc{hu2026contextaware,
title = {{Context-Aware Automated NMR Structure Elucidation}},
author = {Frank Hu and Jonathan M. Tubb and Grant M. Rotskoff and Matthew W. Kanan and Thomas E. Markland},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.07133},
eprint = {2611.07133},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.07133},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Context-Aware Automated NMR Structure Elucidation
AU - Frank Hu
AU - Jonathan M. Tubb
AU - Grant M. Rotskoff
AU - Matthew W. Kanan
AU - Thomas E. Markland
PY - 2026
DA - 2026/11/04
PB - arXiv
DO - 10.48550/arxiv.2611.07133
UR - https://arxiv.org/abs/2611.07133
AB - Machine learning approaches are rapidly revolutionizing the ability to analyze and extract structural insights from chemical data, enabling high-throughput chemical discovery. While existing data-driven approaches have shown remarkable promise for predicting chemical structures in the de novo setting, incorporating additional chemically informed context offers the opportunity to further improve these models' performance and extend their real-world utility. Here we provide a straightforward protocol to combine artificial-intelligence-based spectroscopic elucidation pipelines with contextual chemical data, e.g., known reactants or a desired product, by using automated retrosynthetic analysis to generate large training sets of molecules and contextual data in the form of synthetic precursors. We demonstrate our approach by showing that our recently introduced NMR structure elucidation framework can be trained to effectively leverage molecular precursor context. We show that when the chemical context provides useful information on the target molecule we obtain dramatically improved accuracy over using NMR spectra alone, obtaining Top-15 accuracies of up to 95.4% for molecules up to 40 heavy atoms spanning the full elemental range of organic chemistry. Furthermore, we demonstrate that our approach is highly robust, such that even when the context provided is uncorrelated with the target, one still obtains accuracies commensurate with those of the original NMR structure elucidation framework. This approach provides an efficient route to improve a wide range of spectroscopic structure elucidation platforms using contextual data.
ER -