A robust, deep learning-based analysis of time-domain signals for NMR spectroscopy
Abstract When analyzing the Free Induction Decay (FID) signal produced by nuclear magnetic resonance (NMR) spectroscopy, Fourier transforms (FT) are used to decompose time-domain signals arising from nuclear interactions. This transformation enables the extraction of frequency-domain information, al...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2025-02-01
|
| Series: | Journal of Analytical Science and Technology |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40543-025-00474-4 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823861989608259584 |
|---|---|
| author | Kyungdoe Han Eunhee Kim Kyoung-Seok Ryu Donghan Lee |
| author_facet | Kyungdoe Han Eunhee Kim Kyoung-Seok Ryu Donghan Lee |
| author_sort | Kyungdoe Han |
| collection | DOAJ |
| description | Abstract When analyzing the Free Induction Decay (FID) signal produced by nuclear magnetic resonance (NMR) spectroscopy, Fourier transforms (FT) are used to decompose time-domain signals arising from nuclear interactions. This transformation enables the extraction of frequency-domain information, allowing for the recognition of patterns within the generated NMR spectra. Most modern NMR processing software applies FT to generate the final spectra. Researchers process FID using various techniques, such as phase correction, windowing, and FT, to enhance the interpretation of the obtained spectra. This processing step requires careful consideration of the characteristics of the original data and can also be influenced by the researchers' experience, often making it time-consuming to produce reliable results. However, recent advancements in artificial intelligence, particularly deep learning, have demonstrated superior pattern recognition capabilities compared to humans in complex scenarios. These developments have been successfully applied to various aspects of NMR spectroscopy. In this study, we demonstrate that neural networks can replace FT in NMR spectroscopy, enabling robust and rapid prediction of spectra and peak lists from FID signals. Our results confirm that deep learning can efficiently process NMR data to generate final spectra. As a proof of concept, we present the resulting spectra, along with peak lists predicted by supplying only FID input to the deep learning algorithm. The generated peak lists can be considered as spectra with infinite resolution. |
| format | Article |
| id | doaj-art-9f553f74a90f4b3c86d8624876400566 |
| institution | Kabale University |
| issn | 2093-3371 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Journal of Analytical Science and Technology |
| spelling | doaj-art-9f553f74a90f4b3c86d86248764005662025-02-09T12:41:15ZengSpringerOpenJournal of Analytical Science and Technology2093-33712025-02-0116111010.1186/s40543-025-00474-4A robust, deep learning-based analysis of time-domain signals for NMR spectroscopyKyungdoe Han0Eunhee Kim1Kyoung-Seok Ryu2Donghan Lee3Department of Civil and Environmental Engineering, University of Wisconsin - MadisonProtein Structure Research Team, Korea Basic Science InstituteProtein Structure Research Team, Korea Basic Science InstituteProtein Structure Research Team, Korea Basic Science InstituteAbstract When analyzing the Free Induction Decay (FID) signal produced by nuclear magnetic resonance (NMR) spectroscopy, Fourier transforms (FT) are used to decompose time-domain signals arising from nuclear interactions. This transformation enables the extraction of frequency-domain information, allowing for the recognition of patterns within the generated NMR spectra. Most modern NMR processing software applies FT to generate the final spectra. Researchers process FID using various techniques, such as phase correction, windowing, and FT, to enhance the interpretation of the obtained spectra. This processing step requires careful consideration of the characteristics of the original data and can also be influenced by the researchers' experience, often making it time-consuming to produce reliable results. However, recent advancements in artificial intelligence, particularly deep learning, have demonstrated superior pattern recognition capabilities compared to humans in complex scenarios. These developments have been successfully applied to various aspects of NMR spectroscopy. In this study, we demonstrate that neural networks can replace FT in NMR spectroscopy, enabling robust and rapid prediction of spectra and peak lists from FID signals. Our results confirm that deep learning can efficiently process NMR data to generate final spectra. As a proof of concept, we present the resulting spectra, along with peak lists predicted by supplying only FID input to the deep learning algorithm. The generated peak lists can be considered as spectra with infinite resolution.https://doi.org/10.1186/s40543-025-00474-4Nuclear magnetic resonance (NMR)Free induction decay (FID)Fourier transform (FT)Deep learning |
| spellingShingle | Kyungdoe Han Eunhee Kim Kyoung-Seok Ryu Donghan Lee A robust, deep learning-based analysis of time-domain signals for NMR spectroscopy Journal of Analytical Science and Technology Nuclear magnetic resonance (NMR) Free induction decay (FID) Fourier transform (FT) Deep learning |
| title | A robust, deep learning-based analysis of time-domain signals for NMR spectroscopy |
| title_full | A robust, deep learning-based analysis of time-domain signals for NMR spectroscopy |
| title_fullStr | A robust, deep learning-based analysis of time-domain signals for NMR spectroscopy |
| title_full_unstemmed | A robust, deep learning-based analysis of time-domain signals for NMR spectroscopy |
| title_short | A robust, deep learning-based analysis of time-domain signals for NMR spectroscopy |
| title_sort | robust deep learning based analysis of time domain signals for nmr spectroscopy |
| topic | Nuclear magnetic resonance (NMR) Free induction decay (FID) Fourier transform (FT) Deep learning |
| url | https://doi.org/10.1186/s40543-025-00474-4 |
| work_keys_str_mv | AT kyungdoehan arobustdeeplearningbasedanalysisoftimedomainsignalsfornmrspectroscopy AT eunheekim arobustdeeplearningbasedanalysisoftimedomainsignalsfornmrspectroscopy AT kyoungseokryu arobustdeeplearningbasedanalysisoftimedomainsignalsfornmrspectroscopy AT donghanlee arobustdeeplearningbasedanalysisoftimedomainsignalsfornmrspectroscopy AT kyungdoehan robustdeeplearningbasedanalysisoftimedomainsignalsfornmrspectroscopy AT eunheekim robustdeeplearningbasedanalysisoftimedomainsignalsfornmrspectroscopy AT kyoungseokryu robustdeeplearningbasedanalysisoftimedomainsignalsfornmrspectroscopy AT donghanlee robustdeeplearningbasedanalysisoftimedomainsignalsfornmrspectroscopy |