Accelerated Pure Shift NMR Spectroscopy with Deep Learning.

Pure shift nuclear magnetic resonance (NMR) spectroscopy presents a promising solution to provide sufficient spectral resolution and has been increasingly applied in various branches of chemistry, but the optimal resolution is generally accompanied by long experimental times. We present a proof of concept of deep learning for fast, high-quality, and reliable pure shift NMR reconstruction. The deep learning (DL) protocol allows one to eliminate undersampling artifacts, distinguish peaks with close chemical shifts, and reconstruct high-resolution pure shift NMR spectroscopy along with accelerated acquisition. More meaningfully, the lightweight neural network delivers satisfactory reconstruction performance on personal computers by several hundred simulated data learning, which somewhat lifts the prohibiting demand for a large volume of real training samples and advanced computing hardware generally required in DL projects. Additionally, an M-to-S strategy applicable to common DL cases is further exploited to boost the network generalization capability. As a result, this study takes a meaningful step toward deep learning protocols for broad chemical applications.

Combining Fast Pure Shift NMR and GEMSTONE-Based Selective TOCSY for Efficient NMR Analysis of Complex Systems.

As one of the commonly used intact detection techniques, liquid NMR spectroscopy offers unparalleled insights into the chemical environments, structures, and dynamics of molecules. However, it generally encounters the challenges of crowded or even overlapped spectra, especially when probing complex sample systems containing numerous components and complicated molecular structures. Herein, we exploit a general NMR protocol for efficient NMR analysis of complex systems by combining fast pure shift NMR and GEMSTONE-based selective TOCSY. First, this protocol enables ultrahigh-selective observation on the coupling networks that are totally correlated with targeted resonances or components, even where they are situated in severely overlapped spectral regions. Second, pure shift simplification is introduced to enhance the spectral resolution and further resolve the subspectra containing spectral congestion, thus facilitating the dissection of overlapped spectra. Additionally, sparse sampling accompanied by spectral reconstruction is adopted to significantly accelerate acquisition and improve spectral quality. The advantages of this protocol were demonstrated on different complex sample systems, including a challenging compound of estradiol, a mixture of sucrose and d-glucose, and natural grape juice, verifying its feasibility and power, and boosting the potential application landscapes in various chemical fields.

Strong Built-In Electric Field-Assisted ZnO/ZnIn2S4 S-Scheme Heterostructure to Promote Photocatalytic Hydrogen Production.

Photocatalysis is an eco-friendly and significant perspective for generating hydrogen. Our study investigated the ZnO/ZnIn2S4 heterojunction photocatalytic system prepared through hydrothermal technique. Accordingly, the ZnIn2S4 nanofibers loaded with 11 mol % ZnO exhibited the hydrogen evolution rate of about 1998 µmol g-1 h-1, which was 2.6 times higher than the pristine ZnIn2S4. In situ electron paramagnetic resonance results proved the S-scheme photocarrier transport route, and in situ KPFM further characterized the internal electric field between ZnO and ZnIn2S4. The development of S-scheme heterojunctions allows for the spatial segregation and transport of charges by preserving photoexcited holes and electrons with a tremendous redox potential. Furthermore, the photoelectrochemical analysis demonstrated that the S-scheme heterojunction could also be employed for the separation of photoexcited species.

Fast Pure Shift NMR Spectroscopy Using Attention-Assisted Deep Neural Network.

Pure shift NMR spectroscopy enables the robust probing on molecular structure and dynamics, benefiting from great resolution enhancements. Despite extensive application landscapes in various branches of chemistry, the long experimental times induced by the additional time dimension generally hinder its further developments and practical deployments, especially for multi-dimensional pure shift NMR. Herein, this study proposes and implements the fast, reliable, and robust reconstruction for accelerated pure shift NMR spectroscopy with lightweight attention-assisted deep neural network. This deep learning protocol allows one to regain high-resolution signals and suppress undersampling artifacts, as well as furnish high-fidelity signal intensities along with the accelerated pure shift acquisition, benefitting from the introduction of the attention mechanism to highlight the spectral feature and information of interest. Extensive results of simulated and experimental NMR data demonstrate that this attention-assisted deep learning protocol enables the effective recovery of weak signals that are almost drown in the serious undersampling artifacts, and the distinction and recognition of close chemical shifts even though using merely 5.4% data, highlighting its huge potentials on fast pure shift NMR spectroscopy. As a result, this study affords a promising paradigm for the AI-assisted NMR protocols toward broader applications in chemistry, biology, materials, and life sciences, and among others.