EUVIMEDEUVIMED entdecken
Crossref

Clean PSYCHE Pure Shift Spectra Obtained by Deep Learning

Xiaoxu Zheng, Wen Zhu, Ziqiao Chen, Upanshu Gangwar, Zixuan Xue iD, Ralph W Adams iD, Zhong Chen iD, Gareth A Morris, Mathias Nilsson iD, Yanqin Lin iD

Analytical Chemistry · 18.08.2026 · 98 (32) · 23886-23894

DOI: 10.1021/acs.analchem.6c03944 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Analytical Chemistry, online erschienen am 04.08.2026. Verfasst von Xiaoxu Zheng und 9 weiteren Autor:innen. Beteiligte Einrichtung: Fujian Provincial Key Laboratory of Plasma and Magnetic Resonance, Department of Electronic Science, the MOE Key Laboratory of Spectrochemical Analys…. Die Arbeit nennt 47 Literaturangaben. Gefördert von: Royal Society, National Natural Science Foundation of China (NSFC), Engineering and Physical Sciences Research Council (EPSRC).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Proton (1H) nuclear magnetic resonance (NMR) is the most extensively utilized NMR technique due to its high sensitivity and information content. Nonetheless, its narrow chemical shift range and complex multiplet splitting often lead to severe spectral overlap, complicating spectral analysis. Pure shift methods address this challenge by converting weakly coupled multiplets into singlets, thereby significantly improving spectral resolution. Current pure shift methods struggle, however, with strongly coupled spin systems, yielding both main peaks that can be slightly displaced from the exact chemical shift and extra peaks, often at frequencies intermediate between the shifts of strongly coupled protons. These “strong coupling artifacts” can complicate spectral analysis. In this work, a multiscale residual network model is developed to postprocess PSYCHE pure shift spectra to remove strong coupling artifacts. Within the applicable ranges of spectral parameters, the model can correctly retain the desired pure shift signals and recover pure singlets. The method introduces no additional acquisition-related sensitivity loss by postprocessing PSYCHE spectra and exhibits superior performance compared to TSE-PSYCHE in suppressing strong coupling artifacts. Additionally, it preserves the parent PSYCHE method’s direct proportionality between signal intensity and analyte concentration, enabling the monitoring of concentration changes for different analytes in a mixture. The new method offers a novel strategy for obtaining clean pure shift spectra and is expected to facilitate molecular structure elucidation and composition analysis in chemistry research.

Autor:innen und Institutionen

  • Fujian Provincial Key Laboratory of Plasma and Magnetic Resonance, Department of Electronic Science, the MOE Key Laboratory of Spectrochemical Analysis & Instrumentation, Xiamen University, Xiamen361005, China.
  • Department of Chemistry, University of Manchester, ManchesterM13 9PL, U.K.

ORCID-Profile: Zixuan Xue, Ralph W Adams, Zhong Chen, Mathias Nilsson, Yanqin Lin

Förderung

  • Royal Society
  • National Natural Science Foundation of China (NSFC)
  • Engineering and Physical Sciences Research Council (EPSRC)

Zitieren

APA

Zheng, X., Zhu, W., Chen, Z., Gangwar, U., Xue, Z., Adams, R. W., Chen, Z., Morris, G. A., Nilsson, M., & Lin, Y. (2026). Clean PSYCHE Pure Shift Spectra Obtained by Deep Learning. Analytical Chemistry, 98(32), 23886-23894. https://doi.org/10.1021/acs.analchem.6c03944

Vancouver

Zheng X, Zhu W, Chen Z, Gangwar U, Xue Z, Adams RW, et al. Clean PSYCHE Pure Shift Spectra Obtained by Deep Learning. Analytical Chemistry. 2026;98(32):23886-23894. doi:10.1021/acs.analchem.6c03944

BibTeX
@article{Zheng2026,
  author = {Zheng, Xiaoxu and Zhu, Wen and Chen, Ziqiao and Gangwar, Upanshu and Xue, Zixuan and Adams, Ralph W and Chen, Zhong and Morris, Gareth A and Nilsson, Mathias and Lin, Yanqin},
  title = {Clean PSYCHE Pure Shift Spectra Obtained by Deep Learning},
  journal = {Analytical Chemistry},
  year = {2026},
  volume = {98},
  number = {32},
  pages = {23886--23894},
  doi = {10.1021/acs.analchem.6c03944}
}
Kostenlos starten →