Chemical shift calibration of 1H MAS NMR liver tissue spectra exemplified using a study of glycine protection of galactosamine toxicity

Platelet Metabolites as Candidate Biomarkers in Sepsis Diagnosis and Management Using the Proposed Explainable Artificial Intelligence Approach

Background: Sepsis is characterized by an atypical immune response to infection and is a dangerous health problem leading to significant mortality. Current diagnostic methods exhibit insufficient sensitivity and specificity and require the discovery of precise biomarkers for the early diagnosis and treatment of sepsis. Platelets, known for their hemostatic abilities, also play an important role in immunological responses. This study aims to develop a model integrating machine learning and explainable artificial intelligence (XAI) to identify novel platelet metabolomics markers of sepsis. Methods: A total of 39 participants, 25 diagnosed with sepsis and 14 control subjects, were included in the study. The profiles of platelet metabolites were analyzed using quantitative 1H-nuclear magnetic resonance (NMR) technology. Data were processed using the synthetic minority oversampling method (SMOTE)-Tomek to address the issue of class imbalance. In addition, missing data were filled using a technique based on random forests. Three machine learning models, namely extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), and kernel tree boosting (KTBoost), were used for sepsis prediction. The models were validated using cross-validation. Clinical annotations of the optimal sepsis prediction model were analyzed using SHapley Additive exPlanations (SHAP), an XAI technique. Results: The results showed that the KTBoost model (0.900 accuracy and 0.943 AUC) achieved better performance than the other models in sepsis diagnosis. SHAP results revealed that metabolites such as carnitine, glutamate, and myo-inositol are important biomarkers in sepsis prediction and intuitively explained the prediction decisions of the model. Conclusion: Platelet metabolites identified by the KTBoost model and XAI have significant potential for the early diagnosis and monitoring of sepsis and improving patient outcomes.

Metabolomics: An Emerging "Omics" Platform for Systems Biology and Its Implications for Huntington Disease Research

Huntington's disease (HD) is a progressive, fatal neurodegenerative disease characterized by motor, cognitive, and psychiatric symptoms. The precise mechanisms of HD progression are poorly understood; however, it is known that there is an expansion of the trinucleotide cytosine-adenine-guanine (CAG) repeat in the Huntingtin gene. Important new strategies are of paramount importance to identify early biomarkers with predictive value for intervening in disease progression at a stage when cellular dysfunction has not progressed irreversibly. Metabolomics is the study of global metabolite profiles in a system (cell, tissue, or organism) under certain conditions and is becoming an essential tool for the systemic characterization of metabolites to provide a snapshot of the functional and pathophysiological states of an organism and support disease diagnosis and biomarker discovery. This review briefly highlights the historical progress of metabolomic methodologies, followed by a more detailed review of the use of metabolomics in HD research to enable a greater understanding of the pathogenesis, its early prediction, and finally the main technical platforms in the field of metabolomics.

Malignancy prediction among tissues from Oral SCC patients including neck invasions: a 1H HRMAS NMR based metabolomic study

INTRODUCTION

Oral cancer is a sixth commonly occurring cancer globally. The use of tobacco and alcohol consumption are being considered as the major risk factors for oral cancer. The metabolic profiling of tissue specimens for developing carcinogenic perturbations will allow better prognosis.

OBJECTIVES

To profile and generate precise ¹H HRMAS NMR spectral and quantitative statistical models of oral squamous cell carcinoma (OSCC) in tissue specimens including tumor, bed, margin and facial muscles. To apply the model in blinded prediction of malignancy among oral and neck tissues in an unknown set of patients suffering from OSCC along with neck invasion.

METHODS

Statistical models of ¹H HRMAS NMR spectral data on 180 tissues comprising tumor, margin and bed from 43 OSCC patients were performed. The combined metabolites, lipids spectral intensity and concentration-based malignancy prediction models were proposed. Further, 64 tissue specimens from twelve patients, including neck invasions, were tested for malignancy in a blinded manner.

RESULTS

Forty-eight metabolites including lipids have been quantified in tumor and adjacent tissues. All metabolites other than lipids were found to be upregulated in malignant tissues except for ambiguous glucose. All of three prediction models have successfully identified malignancy status among blinded set of 64 tissues from 12 OSCC patients with an accuracy of above 90%.

CONCLUSION

The efficiency of the models in malignancy prediction based on tumor induced metabolic perturbations supported by histopathological validation may revolutionize the OSCC assessment. Further, the results may enable machine learning to trace tumor induced altered metabolic pathways for better pattern recognition. Thus, it complements the newly developed REIMS-MS iKnife real time precession during surgery.

NMR Spectroscopy for Metabolomics Research

Over the past two decades, nuclear magnetic resonance (NMR) has emerged as one of the three principal analytical techniques used in metabolomics (the other two being gas chromatography coupled to mass spectrometry (GC-MS) and liquid chromatography coupled with single-stage mass spectrometry (LC-MS)). The relative ease of sample preparation, the ability to quantify metabolite levels, the high level of experimental reproducibility, and the inherently nondestructive nature of NMR spectroscopy have made it the preferred platform for long-term or large-scale clinical metabolomic studies. These advantages, however, are often outweighed by the fact that most other analytical techniques, including both LC-MS and GC-MS, are inherently more sensitive than NMR, with lower limits of detection typically being 10 to 100 times better. This review is intended to introduce readers to the field of NMR-based metabolomics and to highlight both the advantages and disadvantages of NMR spectroscopy for metabolomic studies. It will also explore some of the unique strengths of NMR-based metabolomics, particularly with regard to isotope selection/detection, mixture deconvolution via 2D spectroscopy, automation, and the ability to noninvasively analyze native tissue specimens. Finally, this review will highlight a number of emerging NMR techniques and technologies that are being used to strengthen its utility and overcome its inherent limitations in metabolomic applications.

NMR-based metabolomics in wine science

As metabolomics is becoming an emerging field of 'omics' research, NMR serves as one of the major analytical approaches of the decade in metabolomic study, producing information-rich, highly reliable and reproducible data set in non-targeted or global and multivariate statistical analysis. Recently, NMR is successfully being used to characterize wine and find an association of wine metabolite with environmental and fermentative factors in vineyard and making wine. This review describes important analytical features and recent applications in/of NMR-based metabolomics in wine science.

High-resolution magic-angle-spinning NMR spectroscopy for metabolic profiling of intact tissues

Metabolic profiling, metabolomic and metabonomic studies require robust study protocols for any large-scale comparisons and evaluations. Detailed methods for solution-state NMR spectroscopy have been summarized in an earlier protocol. This protocol details the analysis of intact tissue samples by means of high-resolution magic-angle-spinning (HR-MAS) NMR spectroscopy and we provide a detailed description of sample collection, preparation and analysis. Described here are (1)H NMR spectroscopic techniques such as the standard one-dimensional, relaxation-edited, diffusion-edited and two-dimensional J-resolved pulse experiments, as well as one-dimensional (31)P NMR spectroscopy. These are used to monitor different groups of metabolites, e.g., sugars, amino acids and osmolytes as well as larger molecules such as lipids, non-invasively. Through the use of NMR-based diffusion coefficient and relaxation times measurements, information on molecular compartmentation and mobility can be gleaned. The NMR methods are often combined with statistical analysis for further metabonomics analysis and biomarker identification. The standard acquisition time per sample is 8-10 min for a simple one-dimensional (1)H NMR spectrum, giving access to metabolite information while retaining tissue integrity and hence allowing direct comparison with histopathology and MRI/MRS findings or the evaluation together with biofluid metabolic-profiling data.