Resolution Enhancement of Metabolomic J-Res NMR Spectra Using Deep Learning.

J-Resolved (J-Res) nuclear magnetic resonance (NMR) spectroscopy is pivotal in NMR-based metabolomics, but practitioners face a choice between time-consuming high-resolution (HR) experiments or shorter low-resolution (LR) experiments which exhibit significant peak overlap. Deep learning neural networks have been successfully used in many fields to enhance quality of natural images, especially with regard to resolution, and therefore offer the prospect of improving two-dimensional (2D) NMR data. Here, we introduce the J-RESRGAN, an adapted and modified generative adversarial network (GAN) for image super-resolution (SR), which we trained specifically for metabolomic J-Res spectra to enhance peak resolution. A novel symmetric loss function was introduced, exploiting the inherent vertical symmetry of J-Res NMR spectra. Model training used simulated high-resolution J-Res spectra of complex mixtures, with corresponding low-resolution spectra generated via blurring and down-sampling. Evaluation of peak pair resolvability on J-RESRGAN demonstrated remarkable improvement in resolution across a variety of samples. In simulated plasma data, 100% of peak pairs exhibited enhanced resolution in super-resolution spectra compared to their low-resolution counterparts. Similarly, enhanced resolution was observed in 80.8-100% of peak pairs in experimental plasma, 85.0-96.7% in urine, 94.4-98.9% in full fat milk, and 82.6-91.7% in orange juice. J-RESRGAN is not sample type, spectrometer or field strength dependent and improvements on previously acquired data can be seen in seconds on a standard desktop computer. We believe this demonstrates the promise of deep learning methods to enhance NMR metabolomic data, and in particular, the power of J-RESRGAN to elucidate overlapping peaks, advancing precision in a wide variety of NMR-based metabolomics studies. The model, J-RESRGAN, is openly accessible for download on GitHub at https://github.com/yanyan5420/J-RESRGAN.

Problems, principles and progress in computational annotation of NMR metabolomics data.

BACKGROUND: Compound identification remains a critical bottleneck in the process of exploiting Nuclear Magnetic Resonance (NMR) metabolomics data, especially for 1H 1-dimensional (1H 1D) data. As databases of reference compound spectra have grown, workflows have evolved to rely heavily on their search functions to facilitate this process by generating lists of potential metabolites found in complex mixture data, facilitating annotation and identification. However, approaches for validating and communicating annotations are most often guided by expert knowledge, and therefore are highly variable despite repeated efforts to align practices and define community standards. AIM OF REVIEW: This review is aimed at broadening the application of automated annotation tools by discussing the key ideas of spectral matching and beginning to describe a set of terms to classify this information, thus advancing standards for communicating annotation confidence. Additionally, we hope that this review will facilitate the growing collaboration between chemical data scientists, software developers and the NMR metabolomics community aiding development of long-term software solutions. KEY SCIENTIFIC CONCEPTS OF REVIEW: We begin with a brief discussion of the typical untargeted NMR identification workflow. We differentiate between annotation (hypothesis generation, filtering), and identification (hypothesis testing, verification), and note the utility of different NMR data features for annotation. We then touch on three parts of annotation: (1) generation of queries, (2) matching queries to reference data, and (3) scoring and confidence estimation of potential matches for verification. In doing so, we highlight existing approaches to automated and semi-automated annotation from the perspective of the structural information they utilize, as well as how this information can be represented computationally.

Uncovering in vivo biochemical patterns from time-series metabolic dynamics.

System biology relies on holistic biomolecule measurements, and untangling biochemical networks requires time-series metabolomics profiling. With current metabolomic approaches, time-series measurements can be taken for hundreds of metabolic features, which decode underlying metabolic regulation. Such a metabolomic dataset is untargeted with most features unannotated and inaccessible to statistical analysis and computational modeling. The high dimensionality of the metabolic space also causes mechanistic modeling to be rather cumbersome computationally. We implemented a faster exploratory workflow to visualize and extract chemical and biochemical dependencies. Time-series metabolic features (about 300 for each dataset) were extracted by Ridge Tracking-based Extract (RTExtract) on measurements from continuous in vivo monitoring of metabolism by NMR (CIVM-NMR) in Neurospora crassa under different conditions. The metabolic profiles were then smoothed and projected into lower dimensions, enabling a comparison of metabolic trends in the cultures. Next, we expanded incomplete metabolite annotation using a correlation network. Lastly, we uncovered meaningful metabolic clusters by estimating dependencies between smoothed metabolic profiles. We thus sidestepped the processes of time-consuming mechanistic modeling, difficult global optimization, and labor-intensive annotation. Multiple clusters guided insights into central energy metabolism and membrane synthesis. Dense connections with glucose 1-phosphate indicated its central position in metabolism in N. crassa. Our approach was benchmarked on simulated random network dynamics and provides a novel exploratory approach to analyzing high-dimensional metabolic dynamics.

RTExtract: time-series NMR spectra quantification based on 3D surface ridge tracking.

MOTIVATION: Time-series nuclear magnetic resonance (NMR) has advanced our knowledge about metabolic dynamics. Before analyzing compounds through modeling or statistical methods, chemical features need to be tracked and quantified. However, because of peak overlap and peak shifting, the available protocols are time consuming at best or even impossible for some regions in NMR spectra. RESULTS: We introduce Ridge Tracking-based Extract (RTExtract), a computer vision-based algorithm, to quantify time-series NMR spectra. The NMR spectra of multiple time points were formulated as a 3D surface. Candidate points were first filtered using local curvature and optima, then connected into ridges by a greedy algorithm. Interactive steps were implemented to refine results. Among 173 simulated ridges, 115 can be tracked (RMSD < 0.001). For reproducing previous results, RTExtract took less than 2 h instead of ∼48 h, and two instead of seven parameters need tuning. Multiple regions with overlapping and changing chemical shifts are accurately tracked. AVAILABILITY AND IMPLEMENTATION: Source code is freely available within Metabolomics toolbox GitHub repository (https://github.com/artedison/Edison_Lab_Shared_Metabolomics_UGA/tree/master/metabolomics_toolbox/code/ridge_tracking) and is implemented in MATLAB and R. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Correlations Between LC-MS/MS-Detected Glycomics and NMR-Detected Metabolomics in Caenorhabditis elegans Development.

This study examined the relationship between glycans, metabolites, and development in C. elegans. Samples of N2 animals were synchronized and grown to five different time points ranging from L1 to a mixed population of adults, gravid adults, and offspring. Each time point was replicated seven times. The samples were each assayed by a large particle flow cytometer (Biosorter) for size distribution data, LC-MS/MS for targeted N- and O-linked glycans, and NMR for metabolites. The same samples were utilized for all measurements, which allowed for statistical correlations between the data. A new protocol was developed to correlate Biosorter developmental data with LC-MS/MS data to obtain stage-specific information of glycans. From the five time points, four distinct sizes of worms were observed from the Biosorter distributions, ranging from the smallest corresponding to L1 to adult animals. A network model was constructed using the four binned sizes of worms as starting nodes and adding glycans and metabolites that had correlations with r ≥ 0.5 to those nodes. The emerging structure of the network showed distinct patterns of N- and O-linked glycans that were consistent with previous studies. Furthermore, some metabolites that were correlated to these glycans and worm sizes showed interesting interactions. Of note, UDP-GlcNAc had strong positive correlations with many O-glycans that were expressed in the largest animals. Similarly, phosphorylcholine correlated with many N-glycans that were expressed in L1 animals.

Continuous in vivo Metabolism by NMR.

Dense time-series metabolomics data are essential for unraveling the underlying dynamic properties of metabolism. Here we extend high-resolution-magic angle spinning (HR-MAS) to enable continuous in vivo monitoring of metabolism by NMR (CIVM-NMR) and provide analysis tools for these data. First, we reproduced a result in human chronic lymphoid leukemia cells by using isotope-edited CIVM-NMR to rapidly and unambiguously demonstrate unidirectional flux in branched-chain amino acid metabolism. We then collected untargeted CIVM-NMR datasets for Neurospora crassa, a classic multicellular model organism, and uncovered dynamics between central carbon metabolism, amino acid metabolism, energy storage molecules, and lipid and cell wall precursors. Virtually no sample preparation was required to yield a dynamic metabolic fingerprint over hours to days at ~4-min temporal resolution with little noise. CIVM-NMR is simple and readily adapted to different types of cells and microorganisms, offering an experimental complement to kinetic models of metabolism for diverse biological systems.