Direct deduction of chemical class from NMR spectra

Stefan Kuhn, Carlos Cobas, Agustin Barba, Simon Colreavy-Donnelly, Fabio Caraffini, Ricardo Moreira Borges

Research output: Contribution to journalArticlepeer-review

Abstract

This paper presents a proof-of-concept method for classifying chemical compounds directly from NMR data without performing structure elucidation. This can help to reduce the time in finding good structure candidates, as in most cases matching must be done by a human engineer, or at the very least a process for matching must be meaningfully interpreted by one. The method identified as suitable for classification is a convolutional neural network (CNN). Other methods, including clustering and image registration, have not been found to be suitable for the task in a comparative analysis. The result shows that deep learning can offer solutions to spectral interpretation problems.

Original languageEnglish
Article number107381
Pages (from-to)107381
JournalJournal of Magnetic Resonance
Volume348
DOIs
Publication statusPublished - Mar 2023

Keywords

  • Chemical classification
  • Convolutional neural network
  • Deep learning
  • Image processing
  • NMR

Fingerprint

Dive into the research topics of 'Direct deduction of chemical class from NMR spectra'. Together they form a unique fingerprint.

Cite this