Prediction of order parameters based on protein NMR structure ensemble and machine learning.

The fast motions of proteins at the picosecond to nanosecond timescale, known as fast dynamics, are closely related to protein conformational entropy and rearrangement, which in turn affect catalysis, ligand binding and protein allosteric effects. The most used NMR approach to study fast protein dynamics is the model free method, which uses order parameter S2 to describe the amplitude of the internal motion of local group. However, to obtain order parameter through NMR experiments is quite complex and lengthy. In this paper, we present a machine learning approach for predicting backbone 1H-15N order parameters based on protein NMR structure ensemble. A random forest model is used to learn the relationship between order parameters and structural features. Our method achieves high accuracy in predicting backbone 1H-15N order parameters for a test dataset of 10 proteins, with a Pearson correlation coefficient of 0.817 and a root-mean-square error of 0.131.

Restore High-Resolution Nuclear Magnetic Resonance Spectra from Inhomogeneous Magnetic Fields Using a Neural Network.

High-resolution nuclear magnetic resonance (NMR) spectroscopy is a powerful analytical tool with wide applications. However, the conventional shim technique may not guarantee the homogeneity of the magnetic field when the experimental conditions are unfavorable. In this study, we proposed a data postprocessing method called Restore High-resolution Unet (RH-Unet), which uses a convolutional neural network to restore distorted NMR spectra that have been acquired in inhomogeneous magnetic fields. The method generates feature-label pairs from singlet peak regions and ideal Lorentzian line shapes and trains a RH-Unet model to map low-resolution spectra to high-resolution spectra. The method was applied to different samples and showed superior performance than the reference deconvolution method incorporated in Bruker Topspin software. The proposed method provides a simple and fast way to obtain high-resolution NMR spectra in inhomogeneous fields that can facilitate the application of NMR spectroscopy in various fields.

CSI-LSTM: a web server to predict protein secondary structure using bidirectional long short term memory and NMR chemical shifts.

Protein secondary structure provides rich structural information, hence the description and understanding of protein structure relies heavily on it. Identification or prediction of secondary structures therefore plays an important role in protein research. In protein NMR studies, it is more convenient to predict secondary structures from chemical shifts as compared to the traditional determination methods based on inter-nuclear distances provided by NOESY experiment. In recent years, there was a significant improvement observed in deep neural networks, which had been applied in many research fields. Here we proposed a deep neural network based on bidirectional long short term memory (biLSTM) to predict protein 3-state secondary structure using NMR chemical shifts of backbone nuclei. While comparing with the existing methods the proposed method showed better prediction accuracy. Based on the proposed method, a web server has been built to provide protein secondary structure prediction service.

Using neural networks to obtain NMR spectra of both small and macromolecules from blood samples in a single experiment.

Metabolomics plays a crucial role in understanding metabolic processes within biological systems. Using specific pulse sequences, NMR-based metabolomics detects small and macromolecular metabolites that are altered in blood samples. Here we proposed a method called spectral editing neural network, which can effectively edit and separate the spectral signals of small and macromolecules in 1H NMR spectra of serum and plasma based on the linewidth of the peaks. We applied the model to process the 1H NMR spectra of plasma and serum. The extracted small and macromolecular spectra were then compared with experimentally obtained relaxation-edited and diffusion-edited spectra. Correlation analysis demonstrated the quantitative capability of the model in the extracted small molecule signals from 1H NMR spectra. The principal component analysis showed that the spectra extracted by the model and those obtained by NMR spectral editing methods reveal similar group information, demonstrating the effectiveness of the model in signal extraction.

NMR-based Metabolomics Analysis of Liver from C57BL/6 Mouse Exposed to Ionizing Radiation.

The effects of ionizing radiation to human health are of great concern in the field of space exploration and for patients considering radiotherapy. However, to date, the effect of high-dose radiation on metabolism in the liver has not been clearly defined. In this study, 1H nuclear magnetic resonance (NMR)-based metabolomics combined with multivariate data analysis was applied to study the changes of metabolism in the liver of C57BL/6 mouse after whole-body gamma (3.0 and 7.8 Gy) or proton (3.0 Gy) irradiation. Principal component analysis (PCA) and orthogonal projection to latent structures analysis (OPLS) were used for classification and identification of potential biomarkers associated with exposure to gamma and proton radiation. The results show that the radiation exposed groups can be well separated from the control group. Where the same dose was received, the proton exposed group was nevertheless well separated from the gamma-exposed group, indicating that different radiation sources induce different alterations in the metabolic profile. Common among all high-dose gamma and proton exposed groups were the statistically decreased concentrations of choline, O-phosphocholine and trimethylamine N-oxide, while the concentrations of glutamine, glutathione, malate, creatinine, phosphate, betaine and 4-hydroxyphenylacetate were statistically and significantly elevated. Since these altered metabolites are associated with multiple biological pathways, the results suggest that radiation induces abnormality in multiple biological pathways. In particular, metabolites such as 4-hydroxyphenylacetate, betaine, glutamine, choline and trimethylamine N-oxide may be prediagnostic biomarkers candidates for ionizing exposure of the liver.