Deep learning network for NMR spectra reconstruction in time-frequency domain and quality assessment
Abstract High-quality nuclear magnetic resonance (NMR) spectra can be rapidly acquired by combining non-uniform sampling techniques (NUS) with reconstruction algorithms. However, current deep learning (DL) based reconstruction methods focus only on single-domain reconstruction (time or frequency dom...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-03-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-025-57721-w |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850253149777952768 |
|---|---|
| author | Yao Luo Wenhan Chen Zhenhua Su Xiaoqi Shi Jie Luo Xiaobo Qu Zhong Chen Yanqin Lin |
| author_facet | Yao Luo Wenhan Chen Zhenhua Su Xiaoqi Shi Jie Luo Xiaobo Qu Zhong Chen Yanqin Lin |
| author_sort | Yao Luo |
| collection | DOAJ |
| description | Abstract High-quality nuclear magnetic resonance (NMR) spectra can be rapidly acquired by combining non-uniform sampling techniques (NUS) with reconstruction algorithms. However, current deep learning (DL) based reconstruction methods focus only on single-domain reconstruction (time or frequency domain), leading to drawbacks like peak loss and artifact peaks and ultimately failing to achieve optimal performance. Moreover, the lack of fully sampled spectra makes it difficult, even impossible, to determine the quality of reconstructed spectra, presenting challenges in the practical applications of NUS. In this study, a joint time-frequency domain deep learning network, referred to as JTF-Net, is proposed. It effectively combines time domain and frequency domain features, exhibiting better reconstruction performance on protein spectra across various dimensions compared to traditional algorithms and single-domain DL methods. In addition, the reference-free quality assessment metric, denoted as REconstruction QUalIty assuRancE Ratio (REQUIRER), is proposed base on an established quality space in the field of NMR spectral reconstruction. The metric is capable of evaluating the quality of reconstructed NMR spectra without the fully sampled spectra, making it more suitable for practical applications. |
| format | Article |
| id | doaj-art-87d44dc99a7a4bd3b5f0c6a082aef13b |
| institution | OA Journals |
| issn | 2041-1723 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj-art-87d44dc99a7a4bd3b5f0c6a082aef13b2025-08-20T01:57:27ZengNature PortfolioNature Communications2041-17232025-03-0116111110.1038/s41467-025-57721-wDeep learning network for NMR spectra reconstruction in time-frequency domain and quality assessmentYao Luo0Wenhan Chen1Zhenhua Su2Xiaoqi Shi3Jie Luo4Xiaobo Qu5Zhong Chen6Yanqin Lin7Department of Electronic Science, Xiamen UniversityDepartment of Electronic Science, Xiamen UniversityDepartment of Electronic Science, Xiamen UniversityDepartment of Electronic Science, Xiamen UniversityDepartment of Electronic Science, Xiamen UniversityDepartment of Electronic Science, Xiamen UniversityDepartment of Electronic Science, Xiamen UniversityDepartment of Electronic Science, Xiamen UniversityAbstract High-quality nuclear magnetic resonance (NMR) spectra can be rapidly acquired by combining non-uniform sampling techniques (NUS) with reconstruction algorithms. However, current deep learning (DL) based reconstruction methods focus only on single-domain reconstruction (time or frequency domain), leading to drawbacks like peak loss and artifact peaks and ultimately failing to achieve optimal performance. Moreover, the lack of fully sampled spectra makes it difficult, even impossible, to determine the quality of reconstructed spectra, presenting challenges in the practical applications of NUS. In this study, a joint time-frequency domain deep learning network, referred to as JTF-Net, is proposed. It effectively combines time domain and frequency domain features, exhibiting better reconstruction performance on protein spectra across various dimensions compared to traditional algorithms and single-domain DL methods. In addition, the reference-free quality assessment metric, denoted as REconstruction QUalIty assuRancE Ratio (REQUIRER), is proposed base on an established quality space in the field of NMR spectral reconstruction. The metric is capable of evaluating the quality of reconstructed NMR spectra without the fully sampled spectra, making it more suitable for practical applications.https://doi.org/10.1038/s41467-025-57721-w |
| spellingShingle | Yao Luo Wenhan Chen Zhenhua Su Xiaoqi Shi Jie Luo Xiaobo Qu Zhong Chen Yanqin Lin Deep learning network for NMR spectra reconstruction in time-frequency domain and quality assessment Nature Communications |
| title | Deep learning network for NMR spectra reconstruction in time-frequency domain and quality assessment |
| title_full | Deep learning network for NMR spectra reconstruction in time-frequency domain and quality assessment |
| title_fullStr | Deep learning network for NMR spectra reconstruction in time-frequency domain and quality assessment |
| title_full_unstemmed | Deep learning network for NMR spectra reconstruction in time-frequency domain and quality assessment |
| title_short | Deep learning network for NMR spectra reconstruction in time-frequency domain and quality assessment |
| title_sort | deep learning network for nmr spectra reconstruction in time frequency domain and quality assessment |
| url | https://doi.org/10.1038/s41467-025-57721-w |
| work_keys_str_mv | AT yaoluo deeplearningnetworkfornmrspectrareconstructionintimefrequencydomainandqualityassessment AT wenhanchen deeplearningnetworkfornmrspectrareconstructionintimefrequencydomainandqualityassessment AT zhenhuasu deeplearningnetworkfornmrspectrareconstructionintimefrequencydomainandqualityassessment AT xiaoqishi deeplearningnetworkfornmrspectrareconstructionintimefrequencydomainandqualityassessment AT jieluo deeplearningnetworkfornmrspectrareconstructionintimefrequencydomainandqualityassessment AT xiaoboqu deeplearningnetworkfornmrspectrareconstructionintimefrequencydomainandqualityassessment AT zhongchen deeplearningnetworkfornmrspectrareconstructionintimefrequencydomainandqualityassessment AT yanqinlin deeplearningnetworkfornmrspectrareconstructionintimefrequencydomainandqualityassessment |