Neural Networks for Conversion of Simulated NMR Spectra from Low-Field to High-Field for Quantitative Metabolomics
2024

Using Neural Networks to Improve NMR Spectra Analysis

Sample size: 20000 publication 10 minutes Evidence: moderate

Author Information

Author(s): Hayden Johnson, Aaryani Tipirneni-Sajja, Abhinav Dubey

Primary Institution: Department of Biomedical Engineering, The University of Memphis

Hypothesis

Can neural networks effectively convert low-field NMR spectra to high-field spectra for better metabolite quantification?

Conclusion

The transformer method was effective in converting low-field simulated spectra to high-field for metabolomic applications.

Supporting Evidence

  • The transformer was the only architecture that reliably converted low-field NMR spectra to high-field spectra.
  • Direct quantification of low-field spectra was slightly more accurate than quantification of converted high-field spectra.
  • Further research is needed to validate the findings with experimental data.

Takeaway

Scientists used computers to help make low-quality NMR data better, so they can understand more about tiny substances in samples.

Methodology

Neural networks were trained to convert simulated low-field NMR spectra to high-field spectra and to quantify metabolites directly.

Limitations

The study used simulated spectra, which may not fully reflect real-world data, and did not include experimental validation.

Digital Object Identifier (DOI)

10.3390/metabo14120666

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication