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

TL;DR

This paper demonstrates that a transformer-based deep learning model can accurately predict complex organic molecular structures from one-dimensional NMR spectra, significantly advancing automated structure elucidation in organic chemistry.

Contribution

It introduces a novel AI framework that achieves de novo molecular structure prediction for molecules with up to 40 non-hydrogen atoms using only NMR data, covering a broad chemical space.

Findings

55.2% accuracy within top 15 predictions

Effective for molecules with up to 40 non-hydrogen atoms

Extensible to experimental data through fine-tuning

Abstract

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.