Target Metabolome Profiling-Based Machine Learning as a Diagnostic Approach for Cardiovascular Diseases in Adults

Targeted metabolomic profiling of acute ST-segment elevation myocardial infarction

Myocardial infarction is a major cause of morbidity and mortality worldwide. Metabolomic investigations may be useful for understanding the pathogenesis of ST-segment elevation myocardial infarction (STEMI). STEMI patients were comprehensively examined via targeted metabolomic profiling, machine learning and weighted correlation network analysis. A total of 195 subjects, including 68 STEMI patients, 84 patients with stable angina pectoris (SAP) and 43 non-CVD patients, were enrolled in the study. Metabolomic profiling involving the quantitative analysis of 87 endogenous metabolites in plasma was conducted. This study is the first to perform targeted metabolomic profiling in patients with STEMI. We identified 36 significantly altered metabolites in STEMI patients. Increased levels of four amino acids, eight acylcarnitines, six metabolites of the NO-urea cycle and neurotransmitters, and three intermediates of tryptophan metabolism were detected. The following metabolites exhibited decreased levels: six amino acids, three acylcarnitines, three components of the NO-urea cycle and neurotransmitters, and three intermediates of tryptophan metabolism. We found that the significant changes in tryptophan metabolism observed in STEMI patients-the increase in anthranilic acid and tryptophol and decrease in xanthurenic acid and 3-OH-kynurenine-may play important roles in STEMI pathogenesis. On the basis of the differences in the constructed weighted correlation networks, new significant metabolite ratios were identified. Among the 22 significantly altered metabolite ratios identified, 13 were between STEMI patients and non-CVD patients, and 17 were between STEMI patients and SAP patients. Seven of these ratios were common to both comparisons (STEMI patients vs. non-CVD patients and STEMI patients vs. SAP patients). Additionally, two ratios were consistently observed among the STEMI, SAP and non-CVD groups (anthranilic acid: aspartic acid and GSG (glutamine: serine + glycine)). These findings provide new insight into the diagnosis and pathogenesis of STEMI.

Postmortem metabolomics as a high-throughput cause-of-death screening tool for human death investigations

Autopsy rates are declining globally, impacting cause-of-death (CoD) diagnoses and quality control. Postmortem metabolomics was evaluated for CoD screening using 4,282 human cases, encompassing CoD groups: acidosis, drug intoxication, hanging, ischemic heart disease (IHD), and pneumonia. Cases were split 3:1 into training and test sets. High-resolution mass spectrometry data from femoral blood were analyzed via orthogonal-partial least squares discriminant analysis (OPLS-DA) to discriminate CoD groups. OPLS-DA achieved an R2 = 0.52 and Q2 = 0.30, with true-positive prediction rates of 68% and 65% for training and test sets, respectively, across all groups. Specificity-optimized thresholds predicted 56% of test cases with a unique CoD, average 45% sensitivity, and average 96% specificity. Prediction accuracies varied: 98.7% for acidosis, 80.5% for drug intoxication, 81.6% for hanging, 73.1% for IHD, and 93.6% for pneumonia. This study demonstrates the potential of large-scale postmortem metabolomics for CoD screening, offering high specificity and enhancing throughput and decision-making in human death investigations.

A novel preliminary metabolomic panel for IHD diagnostics and pathogenesis

Cardiovascular disease (CVD) represents one of the main causes of mortality worldwide and nearly a half of it is related to ischemic heart disease (IHD). The article represents a comprehensive study on the diagnostics of IHD through the targeted metabolomic profiling and machine learning techniques. A total of 112 subjects were enrolled in the study, consisting of 76 IHD patients and 36 non-CVD subjects. Metabolomic profiling was conducted, involving the quantitative analysis of 87 endogenous metabolites in plasma. A novel regression method of age-adjustment correction of metabolomics data was developed. We identified 36 significantly changed metabolites which included increased cystathionine and dimethylglycine and the decreased ADMA and arginine. Tryptophan catabolism pathways showed significant alterations with increased levels of serotonin, intermediates of the kynurenine pathway and decreased intermediates of indole pathway. Amino acid profiles indicated elevated branched-chain amino acids and increased amino acid ratios. Short-chain acylcarnitines were reduced, while long-chain acylcarnitines were elevated. Based on these metabolites data, machine learning algorithms: logistic regression, support vector machine, decision trees, random forest, and gradient boosting, were used for IHD diagnostic models. Random forest demonstrated the highest accuracy with an AUC of 0.98. The metabolites Norepinephrine; Xanthurenic acid; Anthranilic acid; Serotonin; C6-DC; C14-OH; C16; C16-OH; GSG; Phenylalanine and Methionine were found to be significant and may serve as a novel preliminary panel for IHD diagnostics. Further studies are needed to confirm these findings.

Advances in Mass Spectrometry-Based Blood Metabolomics Profiling for Non-Cancer Diseases: A Comprehensive Review

Blood metabolomics profiling using mass spectrometry has emerged as a powerful approach for investigating non-cancer diseases and understanding their underlying metabolic alterations. Blood, as a readily accessible physiological fluid, contains a diverse repertoire of metabolites derived from various physiological systems. Mass spectrometry offers a universal and precise analytical platform for the comprehensive analysis of blood metabolites, encompassing proteins, lipids, peptides, glycans, and immunoglobulins. In this comprehensive review, we present an overview of the research landscape in mass spectrometry-based blood metabolomics profiling. While the field of metabolomics research is primarily focused on cancer, this review specifically highlights studies related to non-cancer diseases, aiming to bring attention to valuable research that often remains overshadowed. Employing natural language processing methods, we processed 507 articles to provide insights into the application of metabolomic studies for specific diseases and physiological systems. The review encompasses a wide range of non-cancer diseases, with emphasis on cardiovascular disease, reproductive disease, diabetes, inflammation, and immunodeficiency states. By analyzing blood samples, researchers gain valuable insights into the metabolic perturbations associated with these diseases, potentially leading to the identification of novel biomarkers and the development of personalized therapeutic approaches. Furthermore, we provide a comprehensive overview of various mass spectrometry approaches utilized in blood metabolomics research, including GC-MS, LC-MS, and others discussing their advantages and limitations. To enhance the scope, we propose including recent review articles supporting the applicability of GC×GC-MS for metabolomics-based studies. This addition will contribute to a more exhaustive understanding of the available analytical techniques. The Integration of mass spectrometry-based blood profiling into clinical practice holds promise for improving disease diagnosis, treatment monitoring, and patient outcomes. By unraveling the complex metabolic alterations associated with non-cancer diseases, researchers and healthcare professionals can pave the way for precision medicine and personalized therapeutic interventions. Continuous advancements in mass spectrometry technology and data analysis methods will further enhance the potential of blood metabolomics profiling in non-cancer diseases, facilitating its translation from the laboratory to routine clinical application.

Pharmacokinetics, quorum-sensing signal molecules and tryptophan-related metabolomics of the novel anti-virulence drug Fluorothiazinon in a Pseudomonas aeruginosa-induced pneumonia murine model

Pseudomonas aeruginosa (PA) infection is commonly associated with hospital-acquired infections in patients with immune deficiency and/or severe lung diseases. Managing this bacterium is complex due to drug resistance and high adaptability. Fluorothiazinon (FT) is an anti-virulence drug developed to suppress the virulence of bacteria as opposed to bacterial death increasing host's immune response to infection and improving treatment to inhibit drug resistant bacteria. We aimed to evaluate FT pharmacokinetics, quorum sensing signal molecules profiling and tryptophan-related metabolomics in blood, liver, kidneys, and lungs of mice. Study comprised three groups: a group infected with PA that was treated with 400 mg/kg FT ("infected treated group"); a non-infected group, but also treated with the same single drug dose ("non-infected treated group"); and an infected group that received a vehicle ("infected non-treated group"). PA-mediated infection blood pharmacokinetics profiling was indicative of increased drug concentrations as shown by increased Cmax and AUCs. Tissue distribution in liver, kidneys, and lungs, showed that liver presented the most consistently higher concentrations of FT in the infected versus non-infected mice. FT showed that HHQ levels were decreased at 1 h after dosing in lungs while PQS levels were lower across time in lungs of infected treated mice in comparison to infected non-treated mice. Metabolomics profiling performed in lungs and blood of infected treated versus infected non-treated mice revealed drug-associated metabolite alterations, especially in the kynurenic and indole pathways.

Machine learning for predicting diabetic metabolism in the Indian population using polar metabolomic and lipidomic features

AIMS

To identify metabolite and lipid biomarkers of diabetes in the Indian subpopulation in newly diagnosed diabetic and long-term diabetic individuals. To utilize the global polar metabolomic and lipidomic profiles to predict the susceptibility of an individual to diabetes using machine learning algorithms.

MATERIALS AND METHODS

87 individuals, including healthy, newly diabetic, and long-term diabetics on medication, were included in the study. Post consent, their serum was used to isolate polar metabolome and lipidome. NMR and LCMS were used to identify the polar metabolites and lipids, respectively. Statistical analysis was done to determine significantly altered molecules. NMR and LCMS comprehensive data were utilized to generate diabetic models using machine learning algorithms. 10 more individuals (pre-diabetic) were recruited, and their polar metabolomic and lipidomic profiles were generated. Pre-diabetic metabolic profiles were then utilized to predict the diabetic status of the metabolome and lipidome beyond glucose levels.

RESULTS

Mannose, Betaine, Xanthine, Triglyceride (38:1), Sphingomyelin (d63:7), and Phosphatidic acid (37:2) are some of the top key biomarkers of diabetes. The predictive model generated showed the receiver operating characteristic area under the curve (ROC-AUC) as 1 on both test and validation data indicating excellent accuracy. This model then predicted the diabetic closeness of the metabolism of pre-diabetic individuals based on probability scores.

CONCLUSION

Polar metabolic and lipid profile of diabetic individuals is very different from that of healthy individuals. Lipid profile alters before the polar metabolic profile in diabetes-susceptible individuals. Without regard to glucose, the diabetic closeness of the metabolism of any individual can be determined.

Relationship of Acylcarnitines to Myocardial Ischemic Remodeling and Clinical Manifestations in Chronic Heart Failure

BACKGROUND

Progressive myocardial remodeling (MR) in chronic heart failure (CHF) leads to aggravation of systolic dysfunction (SD) and clinical manifestations. Identification of metabolomic markers of these processes may help in the search for new therapeutic approaches aimed at achieving reversibility of MR and improving prognosis in patients with CHF.

METHODS

To determine the relationship between plasma acylcarnitine (ACs) levels, MR parameters and clinical characteristics, in patients with CHF of ischemic etiology (n = 79) and patients with coronary heart disease CHD (n = 19) targeted analysis of 30 ACs was performed by flow injection analysis mass spectrometry.

RESULTS

Significant differences between cohorts were found for the levels of 11 ACs. Significant positive correlations (r > 0.3) between the medium- and long-chain ACs (MCACs and LCACs) and symptoms (CHF NYHA functional class (FC); r = 0.31-0.39; p < 0.05); negative correlation (r = -0.31-0.34; p < 0.05) between C5-OH and FC was revealed. Positive correlations of MCACs and LCACs (r = 0.31-0.48; p < 0.05) with the left atrium size and volume, the right atrium volume, right ventricle, and the inferior vena cava sizes, as well as the pulmonary artery systolic pressure level were shown. A negative correlation between C18:1 and left ventricular ejection fraction (r = -0.31; p < 0.05) was found. However, a decrease in levels compared to referent values of ACs with medium and long chain lengths was 50% of the CHF-CHD cohort. Carnitine deficiency was found in 6% and acylcarnitine deficiency in 3% of all patients with chronic heart disease.

CONCLUSIONS

ACs may be used in assessing the severity of the clinical manifestations and MR. ACs are an important locus to study in terms of altered metabolic pathways in patients with CHF of ischemic etiology and SD. Further larger prospective trials are warranted and needed to determine the potential benefits to treat patients with CV diseases with aberrate AC levels.

Targeted metabolomic profiling as a tool for diagnostics of patients with non-small-cell lung cancer

Lung cancer is referred to as the second most common cancer worldwide and is mainly associated with complex diagnostics and the absence of personalized therapy. Metabolomics may provide significant insights into the improvement of lung cancer diagnostics through identification of the specific biomarkers or biomarker panels that characterize the pathological state of the patient. We performed targeted metabolomic profiling of plasma samples from individuals with non-small cell lung cancer (NSLC, n = 100) and individuals without any cancer or chronic pathologies (n = 100) to identify the relationship between plasma endogenous metabolites and NSLC by means of modern comprehensive bioinformatics tools, including univariate analysis, multivariate analysis, partial correlation network analysis and machine learning. Through the comparison of metabolomic profiles of patients with NSCLC and noncancer individuals, we identified significant alterations in the concentration levels of metabolites mainly related to tryptophan metabolism, the TCA cycle, the urea cycle and lipid metabolism. Additionally, partial correlation network analysis revealed new ratios of the metabolites that significantly distinguished the considered groups of participants. Using the identified significantly altered metabolites and their ratios, we developed a machine learning classification model with an ROC AUC value equal to 0.96. The developed machine learning lung cancer model may serve as a prototype of the approach for the in-time diagnostics of lung cancer that in the future may be introduced in routine clinical use. Overall, we have demonstrated that the combination of metabolomics and up-to-date bioinformatics can be used as a potential tool for proper diagnostics of patients with NSCLC.