Interpreting 2D-NMR spectra using Grad-CAM

It has been shown that it is possible to train a (simple) neural network to classify nuclear magnetic resonance spectra by a substructures either being part of the chemical structure measured or not. We now explore the interpretability of such models using techniques from explainable AI, specifically Grad-CAM. We show that those techniques do not give ideal results in the context of NMR, which would be able to identify individual peaks. On the other hand, they enable a better interpretation of the results than those metrics just based on "right or wrong". We can also confirm the result from our previous work, that the trained network performs well for pure compounds, but its generalisability to mixtures is questionable, a limitation that could only be assumed in the original study.

• Publication year

  2026

• Venue

  Research Ideas and Outcomes

• Publication date

  2026-01-07

• Fields of study

  Not labeled

• Identifiers
  DOI 10.3897/rio.12.e183261
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• How should the advancement of large language models affect the practice of science?

  2025cited by this paper
• Accurate and Efficient Structure Elucidation from Routine One-Dimensional NMR Spectra Using Multitask Machine Learning

  2024cited by this paper
• DeepSAT: Learning Molecular Structures from Nuclear Magnetic Resonance Data

  2023cited by this paper
• Sherlock—A Free and Open-Source System for the Computer-Assisted Structure Elucidation of Organic Compounds from NMR Data

  2023cited by this paper
• A Pilot Study For Fragment Identification Using 2D NMR and Deep Learning

  2021cited by this paper
• Applying NMR compound identification using NMRfilter to match predicted to experimental data

  2020cited by this paper
• Identification of tentative marker in Corvina and Primitivo wines with CMC‐se

  2018cited by this paper
• Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization

  2016cited by this paper
• Identification and structure elucidation by NMR spectroscopy

  2015cited by this paper
• Automatic Structure Determination of Organic Molecules： Principle and Implementation of the LSD Program

  2010cited by this paper
• BioMagResBank

  2007cited by this paper
• Structure Elucidator: A Versatile Expert System for Molecular Structure Elucidation from 1D and 2D NMR Data and Molecular Fragments

  2004cited by this paper
• Cocon: From NMR Correlation Data to Molecular Constitutions

  1997cited by this paper

• No citing papers are available for this paper.