NASR: an effective approach for simultaneous noise and artifact suppression in NMR spectroscopy

Deep Learning Methodology for Obtaining Ultraclean Pure Shift Proton Nuclear Magnetic Resonance Spectra

Nuclear magnetic resonance (NMR) is one of the most powerful analytical techniques. In order to obtain high-quality NMR spectra, a real-time Zangger-Sterk (ZS) pulse sequence is employed to collect low-quality pure shift NMR data with high efficiency. Then, a neural network named AC-ResNet and a loss function named SM-CDMANE are developed to train a network model. The model with excellent abilities of suppressing noise, reducing line widths, discerning peaks, and removing artifacts is utilized to process the acquired NMR data. The processed spectra with noise and artifact suppression and small line widths are ultraclean and high-resolution. Peaks overlapped heavily can be resolved. Weak peaks, even hidden in the noise, can be discerned from noise. Artifacts, even as high as spectral peaks, can be removed completely while not suppressing peaks. Eliminating perfectly noise and artifacts and smoothing baseline make spectra ultraclean. The proposed methodology would greatly promote various NMR applications.

NMR-Based Metabolomics in Cancer Research

Nuclear magnetic resonance (NMR) spectroscopy offers reproducible quantitative analysis and structural identification of metabolites in various complex biological samples, such as biofluids (plasma, serum, and urine), cells, tissue extracts, and even intact organs. Therefore, NMR-based metabolomics, a mainstream metabolomic platform, has been extensively applied in many research fields, including pharmacology, toxicology, pathophysiology, nutritional intervention, disease diagnosis/prognosis, and microbiology. In particular, NMR-based metabolomics has been successfully used for cancer research to investigate cancer metabolism and identify biomarker and therapeutic targets. This chapter highlights the innovations and challenges of NMR-based metabolomics platform and its applications in cancer research.

Fast reconstruction of non-uniform sampling multidimensional NMR spectroscopy via a deep neural network

Multidimensional nuclear magnetic resonance (NMR) spectroscopy is used to examine the chemical structures of the studied systems. Unfortunately, the application of NMR spectra is limited by their long acquisition time, especially for 3D, 4D, and higher dimensional spectra. Non-uniform sampling (NUS) has been widely recognized as a powerful tool to reduce the NMR experimental time. But the quality of NUS spectra depends on appropriate reconstruction algorithms. As an effective data processing method, deep learning has been widely used in many fields in recent years. In this work, a deep learning-based strategy for fast reconstruction of non-uniform sampling NMR spectra is proposed. In our experiments, the proposed deep neural network has better performance in removing artifacts and preserving weak peaks than typical convolutional neural networks of U-Net and DenseNet. Besides, a novel approach of generating training data is utilized to reduce the computational burden of neural networks, and thus training our network can be easier and faster than previous deep learning-based works. Compared with the two currently available methods, SMILE and hmsIST, our strategy can provide comparable reconstruction quality in terms of peak intensities and the fidelity of peak shape. The reconstruction time of our methods is also comparable to or faster than the two methods, especially for 3D spectra.

Resolution-enhanced 2D NMR of complex mixtures by non-uniform sampling

NMR is a powerful tool for the analysis of complex mixtures and the identification of individual components. Two-dimensional (2D) NMR potentially offers a wealth of information, but resolution is often sacrificed in order to contain experimental times. We explore the use of non-uniform sampling (NUS) to increase substantially the resolution of 2D NMR spectra of complex mixtures of small molecules, with no increase in experimental time. Two common pulse sequences for metabolomics applications are analysed, HSQC and TOCSY. Specific attention is paid to sensitivity in resolution-enhanced NUS spectra, using the signal-to-maximum-noise ratio as a metric. With a careful choice of sampling schedule and reconstruction algorithm, resolution in the (13) C dimension for HSQC is increased by a factor of at least 32, with no loss in sensitivity and no spurious peaks. For TOCSY, multiplets can be resolved in the indirect dimension in a reasonable experimental time. These properties should increase the usefulness of 2D NMR for metabolomics applications by, for example, increasing the chances of metabolite identification.

A single-scan method for NMR 2D J-resolved spectroscopy

A single-scan NMR 2D J-resolved method is proposed for obtaining decoupled proton spectra and fine scalar-coupling splitting patterns.