使用深度学习提高代谢J-ResNMR光谱的分辨率
Yan Yan1, Michael T Judge1, Toby Athersuch1
1Section of Bioinformatics, Division of Systems Medicine, Department of Metabolism, Digestion and Reproduction, Faculty of Medicine, Imperial College London, London W12 0NN, U.K.
深度学习增强了J-Res (J-Res) 核磁共振 (NMR) 光谱的分辨率. J-RESRGAN模型显著改善了代谢学数据的峰值分离,提高了分析精度.
科学领域:
- 代谢学 代谢学 代谢学
- 核磁共振 (NMR) 光谱学 核磁共振 (NMR) 光谱学
- 深度学习 (Deep Learning) 是一种深度学习.
背景情况:
- J-Resolved (J-Res) NMR光谱对于代谢学至关重要,但在低分辨率 (LR) 实验中会出现峰值重叠.
- 高分辨率 (HR) 实验耗时,在速度和数据质量之间进行权衡.
研究的目的:
- 开发一个深度学习模型来提高2D NMR J-Res频谱的分辨率.
- 在使用J-Res NMR数据的代谢分析中提高峰值可分辨率.
主要方法:
- 介绍J-RESRGAN,一个适用于NMR光谱超分辨率 (SR) 的生成对抗网络 (GAN).
- 在模拟的HR J-Res光谱及其通过模糊和下方采样生成的LR对应物上训练模型.
- 整合了一个新的对称损失函数,利用J-Res光谱的垂直对称性.
主要成果:
- 在各种样本类型中,J-RESRGAN显示了峰值对可解决性的显著改善.
- 100%的峰值对在模拟的血数据中显示了增强的分辨率.
- 在实验血 (80.8-100%),尿液 (85.0-96.7%),牛奶 (94.4-98.9%) 和汁 (82.6-91.7%) 中观察到高分辨率增强.
结论:
- 深度学习,特别是J-RESRGAN,有效地提高了NMR代谢数据的分辨率.
- 该模型具有多功能性,独立于样品类型,光谱仪或场强度,并提供快速分析.
- 通过阐明重叠的峰值,J-RESRGAN在基于NMR的代谢学中提高了精度.
更多相关视频
11:02Identification and Quantification of Deranged Metabolites in Critically Ill Patients Using NMR-Based Metabolomics
Published on: November 29, 2024
11:47Concentration of Metabolites from Low-density Planktonic Communities for Environmental Metabolomics using Nuclear Magnetic Resonance Spectroscopy
Published on: April 7, 2012
相关概念视频
NMR Spectrometers: Resolution and Error Correction
¹³C NMR: Distortionless Enhancement by Polarization Transfer (DEPT)
Double Resonance Techniques: Overview
Spin decoupling is usually achieved by...
¹H NMR Signal Integration: Overview
¹H NMR: Interpreting Distorted and Overlapping Signals
As Δν decreases and the signals move closer, the doublets appear increasingly distorted. The intensities of the inner lines increase at the cost of those of the outer lines as the signals are...
Raman Spectroscopy: Overview
However, a small fraction of the scattered light exhibits a frequency shift due to the exchange of energy between the incident photons and...
