Pushing the limits of one-dimensional NMR spectroscopy for automated structure elucidation using artificial intelligence

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hu, Frank, Tubb, Jonathan M., Argyropoulos, Dimitris, Golotvin, Sergey, Elyashberg, Mikhail, Rotskoff, Grant M., Kanan, Matthew W., Markland, Thomas E.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917160336490496
author Hu, Frank
Tubb, Jonathan M.
Argyropoulos, Dimitris
Golotvin, Sergey
Elyashberg, Mikhail
Rotskoff, Grant M.
Kanan, Matthew W.
Markland, Thomas E.
author_facet Hu, Frank
Tubb, Jonathan M.
Argyropoulos, Dimitris
Golotvin, Sergey
Elyashberg, Mikhail
Rotskoff, Grant M.
Kanan, Matthew W.
Markland, Thomas E.
contents One-dimensional NMR spectroscopy is one of the most widely used techniques for the characterization of organic compounds and natural products. For molecules with up to 36 non-hydrogen atoms, the number of possible structures has been estimated to range from $10^{20} - 10^{60}$. The task of determining the structure (formula and connectivity) of a molecule of this size using only its one-dimensional $^1$H and/or $^{13}$C NMR spectrum, i.e. de novo structure generation, thus appears completely intractable. Here we show how it is possible to achieve this task for systems with up to 40 non-hydrogen atoms across the full elemental coverage typically encountered in organic chemistry (C, N, O, H, P, S, Si, B, and the halogens) using a deep learning framework, thus covering a vast portion of the drug-like chemical space. Leveraging insights from natural language processing, we show that our transformer-based architecture predicts the correct molecule with 55.2% accuracy within the first 15 predictions using only the $^1$H and $^{13}$C NMR spectra, thus overcoming the combinatorial growth of the chemical space while also being extensible to experimental data via fine-tuning.
format Preprint
id arxiv_https___arxiv_org_abs_2512_18531
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Pushing the limits of one-dimensional NMR spectroscopy for automated structure elucidation using artificial intelligence
Hu, Frank
Tubb, Jonathan M.
Argyropoulos, Dimitris
Golotvin, Sergey
Elyashberg, Mikhail
Rotskoff, Grant M.
Kanan, Matthew W.
Markland, Thomas E.
Chemical Physics
Machine Learning
One-dimensional NMR spectroscopy is one of the most widely used techniques for the characterization of organic compounds and natural products. For molecules with up to 36 non-hydrogen atoms, the number of possible structures has been estimated to range from $10^{20} - 10^{60}$. The task of determining the structure (formula and connectivity) of a molecule of this size using only its one-dimensional $^1$H and/or $^{13}$C NMR spectrum, i.e. de novo structure generation, thus appears completely intractable. Here we show how it is possible to achieve this task for systems with up to 40 non-hydrogen atoms across the full elemental coverage typically encountered in organic chemistry (C, N, O, H, P, S, Si, B, and the halogens) using a deep learning framework, thus covering a vast portion of the drug-like chemical space. Leveraging insights from natural language processing, we show that our transformer-based architecture predicts the correct molecule with 55.2% accuracy within the first 15 predictions using only the $^1$H and $^{13}$C NMR spectra, thus overcoming the combinatorial growth of the chemical space while also being extensible to experimental data via fine-tuning.
title Pushing the limits of one-dimensional NMR spectroscopy for automated structure elucidation using artificial intelligence
topic Chemical Physics
Machine Learning
url https://arxiv.org/abs/2512.18531