Using Neural Networks to Improve NMR Spectra Analysis
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)
Want to read the original?
Access the complete publication on the publisher's website