Applications of machine learning in metabolomics: Disease modeling and classification

Serum metabolic signatures and MetalnFF diagnostic score for mild and moderate metabolic dysfunction-associated steatotic liver disease

To explore serum metabolic changes in metabolic dysfunction-associated steatotic liver disease (MASLD) with mild or moderate steatosis and develop a diagnostic index based on liver fat content to differentiate these stages. A total of 149 participants were enrolled from the Nutrition Health Atlas Project in 2019 (Stage 1, n = 92) and 2022 (Stage 2, n = 57). Serum levels of amino acids, free fatty acids (FFAs) and other organic acids were quantified using liquid or gas chromatography-mass spectrometry. The relationships between serum metabolites and magnetic resonance imaging proton density hepatic fat fraction were analyzed and a predictive model fitting fat fraction was constructed in Stage 1 and validated in Stage 2. Patients with moderate MASLD had significantly higher pyruvic acid, 2-ketoglutaric acid, malic acid, 2-hydroxyisocaproic acid and FFA(C14:0) than mild MASLD. Pathway analysis indicated that liver fat accumulation is associated with alterations in amino acid, FFA metabolism and tricarboxylic acid cycle (TCA). The MetalnFF score was developed to discriminate among three groups, achieving an area under the curve (AUC) of 0.956 (95 %CI:0.905, 1.00) for MASLD and 0.857 (95 %CI:0.745, 0.968) for moderate MASLD in Stage 1, and was further validated in Stage 2 with an AUC of 0.986 (95 %CI: 0.951, 1.00) and 0.759 (95 %CI:0.607, 0.921), respectively. In the early stages of MASLD, disrupted amino acid, FFAs metabolism and TCA cycle have occurred. As the disease progresses, metabolic disturbances in pyruvate metabolism become more severe. These findings enhance a deeper understanding of pathogenesis and propose MetalnFF score as a potential diagnostic tool.

Simplex-structured matrix factorisation: application of soft clustering to metabolomic data

Metabolomics is the measurement of metabolites in biological samples to reveal information on metabolic pathways and phenotypes. Cluster analysis is a popular multivariate technique employed in metabolomics to characterise observations with similar features. Previous work in the field has applied hard clustering approaches to group observations into distinct clusters. This approach can be overly restrictive in some practical applications. Therefore, there is a growing need for soft clustering methods that allow for the clustering of observations into more than one cluster. Simplex-structured matrix factorisation (SSMF) is proposed and applied in a simulation study and to a metabolomic dataset to demonstrate its utility for soft clustering. In the simulation study, the cluster prototypes and cluster memberships were well estimated. In the real data application to metabolomic data, the presence of four soft clusters was suggested by the gap statistic. Furthermore, the Shannon diversity index indicated that several observations have memberships in three clusters. Additionally, the introduction of the covariates sex, age and BMI revealed that sex and age mainly associated with the cluster memberships. The results indicate that a majority of men and young people were in the cluster predominantly characterised by high levels of amino acids and low levels of phosphatidylcholines and sphingomyelins. However, a high proportion of older people were characterised by low levels of amino acids, biogenic amines, acylcarnitines and lysophosphatidylcholines. The SSMF presented successfully estimates a soft clustering of the metabolomic data. It provides an interpretable representation of the data structure using the cluster prototypes combined with cluster memberships. A software package called MetabolSSMF has been developed, which is freely available as an R package, to facilitate the implementation of soft clustering in the field of metabolomics.

Integration of metabolomics and machine learning for precise management and prevention of cardiometabolic risk in Asians

Rapid changes in dietary patterns have led to a rise in cardiometabolic diseases (CMDs) worldwide, highlighting the urgent need for effective dietary strategies to address the health issues. Compared to Caucasians, Asians are more susceptible to CMDs. Understanding the complex factors driving this increased susceptibility is essential for developing targeted interventions and preventive measures for Asian populations. Metabolomics plays a key role in identifying specific metabolic markers and pathways associated with CMDs, providing insights into disease mechanisms and helping to create individualized risk profiles. However, metabolomics faces several challenges, including difficulties in interpreting results across diverse ethnic groups, limitations in study design, variability in analytical platforms, and inconsistencies in data processing methods. Overcoming these challenges requires the adoption of advanced technologies, standardized approaches, and integration of multi-omics data to maximize the utility of metabolomics in clinical settings. As the volume and complexity of metabolomic data continue to increase, machine learning (ML) algorithms have become essential for effective data integration, interpretation, and knowledge extraction. Advanced ML techniques, such as deep learning and network analysis, can reveal hidden patterns, relationships, and metabolic pathways within large datasets, leading to deeper insights into biological systems and disease processes. By combining metabolomics and ML, we can facilitate early detection, enable personalized interventions, and support the development of targeted nutritional strategies, ultimately improving therapeutic outcomes and reducing the socioeconomic burden of CMDs in this region.

Fingerprinting and Quantification of Procyanidins via LC-MS/MS and ESI In-Source Fragmentation

Procyanidins (PCs), or condensed tannins (CTs), are critical for the quality of red wine and other polyphenol-rich foods because of their contribution to the mouthfeel. However, current analytical methods often show a lack of correlation with perceived astringency, biological activities (such as antioxidant activity), and health-related benefits. This is partly because methods such as the Folin-Ciocalteu and tannin affinity precipitation assays report a simplified total phenolic or tannin value that does not consider the diverse structures of CTs. Using procyanidin in-source fragmentation (PC-ISF) allows visualization of diverse CTs, from smaller oligomers to larger polymers, after chromatographic separation and compound depolymerization in the ion source. However, previous PC-ISF has not been optimized, particularly for predicting the structure of CTs with a degree of polymerization (DP) greater than 3. This study introduces a rapid ISF-based PC fingerprinting method, condensed tannin fragmentation fingerprinting (C-TFF), that uses three in-source energies per instrument, cone voltages of 30, 110, and 140 V on the Waters system and fragmentor voltages of 135, 330, and 380 V on the Agilent system, to depolymerize PCs and generate their in-source ions and fragments. The depolymerized spectra that contribute the most to PC differentiation are further fragmented in the collision cell, using multiple reaction monitoring (MRM). The collected MRM transitions of analytical PC standards are correlated to target samples with unidentified PCs via multiple linear regression (MLR), allowing for comprehensive fingerprinting by identifying and quantifying each PC. Nineteen mixtures of five B-type PCs (DPs 1-5) with a known mean degree of polymerization (mDP) and commercial cider samples were characterized via C-TFF, demonstrating high accuracy and precision. This study contributes to the analysis of CTs in complex samples. Future efforts will focus on characterizing structures with mDPs > 5, such as those found in wines with diverse CT profiles.

Transforming neurodegenerative disorder care with machine learning: Strategies and applications

Neurodegenerative diseases (NDs), characterized by progressive neuronal degeneration and manifesting in diverse forms such as memory loss and movement disorders, pose significant challenges due to their complex molecular mechanisms and heterogeneous patient presentations. Diagnosis often relies heavily on clinical assessments and neuroimaging, with definitive confirmation frequently requiring post-mortem autopsy. However, the emergence of Artificial Intelligence (AI) and Machine Learning (ML) offers a transformative potential. These technologies can enable the development of non-invasive tools for early diagnosis, biomarker identification, personalized treatment strategies, patient subtyping and stratification, and disease risk prediction. This review aims to provide a starting point for researchers, both with and without clinical backgrounds, who are interested in applying ML to NDs. We will discuss available data resources for key diseases like Alzheimer's and Parkinson's, explore how ML can revolutionize neurodegenerative care, and emphasize the importance of integrating multiple high-dimensional data sources to gain deeper insights and inform effective therapeutic strategies.

Plasma metabolomics signatures predict COVID-19 patient outcome at ICU admission comparable to clinical scores

SARS-CoV-2 significantly impacts the human metabolome. This study aims to evaluate the predictive capability of a comprehensive module clustering approach in plasma metabolomics for identifying the risk of critical complications in COVID-19 patients admitted to intensive care units (ICUs). We conducted a prospective monocenter study, gathering blood samples within 24 h of ICU admission, alongside clinical, biological, and demographic patient characteristics. Subsequently, we quantified patients' plasma metabolome using a comprehensive untargeted metabolomics approach. First, we stratified patients based on a composite outcome score indicating critical status. Analysis of potential predictors revealed that older patients with higher severity scores and pronounced alterations in key biological parameters are more likely to experience critical complications. Next, we identified 6,667 metabolic features clustered into 57 annotated metabolic modules across all patients by employing an integrative metabolomics approach. Furthermore, we identified the most differentially expressed metabolic modules related to patients' outcomes. Moreover, we defined the top five most predictive metabolites of critical status: homoserine, urobilinogen, methionine, xanthine and pipecolic acid. These five predictors alone demonstrated similar or superior performance compared to clinical and demographic variables in predicting patients' outcomes. This innovative metabolic module inference approach offers a valuable framework for identifying patients prone to complications upon ICU admission for COVID-19. Its potential applications extend to enhancing patient management across diverse clinical settings.

Metabolomics for dental caries diagnosis: Past, present, and future

Dental caries, a prevalent global infectious condition affecting over 95% of adults, remains elusive in its precise etiology. Addressing the complex dynamics of caries demands a thorough exploration of taxonomic, potential, active, and encoded functions within the oral ecosystem. Metabolomic profiling emerges as a crucial tool, offering immediate insights into microecosystem physiology and linking directly to the phenotype. Identified metabolites, indicative of caries status, play a pivotal role in unraveling the metabolic processes underlying the disease. Despite challenges in metabolite variability, the use of metabolomics, particularly via mass spectrometry and nuclear magnetic resonance spectroscopy, holds promise in caries research. This review comprehensively examines metabolomics in caries prevention, diagnosis, and treatment, highlighting distinct metabolite expression patterns and their associations with disease-related bacterial communities. Pioneering in approach, it integrates singular and combinatory metabolomics methodologies, diverse biofluids, and study designs, critically evaluating prior limitations while offering expert insights for future investigations. By synthesizing existing knowledge, this review significantly advances our comprehension of caries, providing a foundation for improved prevention and treatment strategies.

Metabolomic profiling in heart failure as a new tool for diagnosis and phenotyping

Classifying heart failure (HF) by stages and ejection fraction (EF) remains a debated topic in cardiology. Metabolomic profiling (MP) offers a means to identify unique pathophysiological changes across different phenotypes, presenting a promising approach for the diagnosis and prognosis of HF, as well as for the development of targeted therapies. In our study, MP was performed on 408 HF patients (54.9% male). The mean ages of patients were 62 [53;68], 67 [65;74], 68 [61;72], and 69 [65;73] years for stages A, B, C, and D, respectively. This study demonstrates high accuracy in HF stage classification, distinguishing Stage A from Stage B with an AUC ROC of 0.91 and Stage B from Stage C with an AUC ROC of 0.97, by integrating chromatography-mass spectrometry data through multiparametric machine learning models. The observed metabolic similarities between HF with mildly reduced EF and HF with reduced EF phenotypes (AUC ROC 0.96) once again highlight the fundamental differences at the cellular and molecular levels between HF with preserved EF and HF with EF < 50%. Hierarchical clustering based on MP identified four distinct HF phenotypes and 26 key metabolites, including metabolites of tryptophan catabolism, glutamine, riboflavin, norepinephrine, serine, and long- and medium-chain acylcarnitines. The average follow-up period was 542.37 [16;1271] days. A downward change in the trajectory of EF [HR 3,008, 95% CI 1,035 to 8,743, p = 0,043] and metabolomic cluster 3 [HR 2,880; 95% CI 1,062 to 7,810, p = 0,0376] were associated with increased risk of all-cause mortality. MP can refine HF phenotyping and deepen the understanding of its underlying mechanisms. Metabolomic analysis illuminates the biochemical landscape of HF, aiding in its classification and suggesting new therapeutic pathways.

Disrupted fetal carbohydrate metabolism in children with autism spectrum disorder

BACKGROUND

Despite the power and promise of early detection and treatment in autism spectrum disorder (ASD), early-life biomarkers are limited. An early-life risk biosignature would advance the field's understanding of ASD pathogenies and targets for early diagnosis and intervention. We therefore sought to add to the growing ASD biomarker literature and evaluate whether fetal metabolomics are altered in idiopathic ASD.

METHODS

Banked cord blood plasma samples (N = 36 control, 16 ASD) were analyzed via gas chromatography and mass spectrometry (GC-MS). Samples were from babies later diagnosed with idiopathic ASD (non-familial, non-syndromic) or matched, neurotypical controls. Metabolite set enrichment analysis (MSEA) and biomarker prediction were performed (MetaboAnalyst).

RESULTS

We detected 76 metabolites in all samples. Of these, 20 metabolites differed significantly between groups: 10 increased and 10 decreased in ASD samples relative to neurotypical controls (p < 0.05). MSEA revealed significant changes in metabolic pathways related to carbohydrate metabolism and glycemic control. Untargeted principle components analysis of all metabolites did not reveal group differences, while targeted biomarker assessment (using only Fructose 6-phosphate, D-Mannose, and D-Fructose) by a Random Forest algorithm generated an area under the curve (AUC) = 0.766 (95% CI: 0.612-0.896) for ASD prediction.

CONCLUSIONS

Despite a high and increasing prevalence, ASD has no definitive biomarkers or available treatments for its core symptoms. ASD's earliest developmental antecedents remain unclear. We find that fetal plasma metabolomics differ with child ASD status, in particular invoking altered carbohydrate metabolism. While prior clinical and preclinical work has linked carbohydrate metabolism to ASD, no prior fetal studies have reported these disruptions in neonates or fetuses who go on to be diagnosed with ASD. Future work will investigate concordance with maternal metabolomics to determine maternal-fetal mechanisms.

DMoVGPE: predicting gut microbial associated metabolites profiles with deep mixture of variational Gaussian Process experts

BACKGROUND

Understanding the metabolic activities of the gut microbiome is vital for deciphering its impact on human health. While direct measurement of these metabolites through metabolomics is effective, it is often expensive and time-consuming. In contrast, microbial composition data obtained through sequencing is more accessible, making it a promising resource for predicting metabolite profiles. However, current computational models frequently face challenges related to limited prediction accuracy, generalizability, and interpretability.

METHOD

Here, we present the Deep Mixture of Variational Gaussian Process Experts (DMoVGPE) model, designed to overcome these issues. DMoVGPE utilizes a dynamic gating mechanism, implemented through a neural network with fully connected layers and dropout for regularization, to select the most relevant Gaussian Process experts. During training, the gating network refines expert selection, dynamically adjusting their contribution based on the input features. The model also incorporates an Automatic Relevance Determination (ARD) mechanism, which assigns relevance scores to microbial features by evaluating their predictive power. Features linked to metabolite profiles are given smaller length scales to increase their influence, while irrelevant features are down-weighted through larger length scales, improving both prediction accuracy and interpretability.

CONCLUSIONS

Through extensive evaluations on various datasets, DMoVGPE consistently achieves higher prediction performance than existing models. Furthermore, our model reveals significant associations between specific microbial taxa and metabolites, aligning well with findings from existing studies. These results highlight DMoVGPE's potential to provide accurate predictions and to uncover biologically meaningful relationships, paving the way for its application in disease research and personalized healthcare strategies.

Predictive model using systemic inflammation markers to assess neoadjuvant chemotherapy efficacy in breast cancer

Background

Pathological complete response (pCR) is an important indicator for evaluating the efficacy of neoadjuvant chemotherapy (NAC) in breast cancer. The role of systemic inflammation markers in predicting pCR and the long-term prognosis of breast cancer patients undergoing NAC remains controversial. The purpose of this study was to explore the potential predictive and prognostic value of systemic inflammation markers (NLR, PLR, LMR, NMR) and clinicopathological characteristics in breast cancer patients receiving NAC and construct a pCR prediction model based on these indicators.

Methods

A retrospective analysis was conducted on 209 breast cancer patients who received NAC at Nanjing Drum Tower Hospital between January 2010 and March 2020. Independent sample t-tests, chi-square tests, and logistic regression models were used to evaluate the correlation between clinicopathological data, systemic inflammation markers, and pCR. Receiver operating characteristic (ROC) curves were utilized to determine the optimal cut-off values for NLR, PLR, and LMR. Survival analysis was performed using the Kaplan-Meier method and log-rank test. A predictive model for pCR was constructed using machine learning algorithms.

Results

Among the 209 breast cancer patients, 29 achieved pCR. During a median follow-up of 68 months, 74 patients experienced local or distant metastasis, and 56 patients died. Univariate logistic regression analysis showed that lymph node status, HER-2 status, NLR, PLR, and LMR were associated with pCR. ROC curve analysis revealed that the optimal cut-off values for NLR, PLR, and LMR were 1.525, 113.620, and 6.225, respectively. Multivariate logistic regression analysis indicated that lymph node status, NLR, and LMR were independent predictive factors for pCR. Survival analysis demonstrated that lymph node status, NLR, and LMR were associated with prognosis. Machine learning algorithm analysis identified the random forest (RF) model as the optimal predictive model for pCR.

Conclusion

This study demonstrated that lymph node status, NLR, and LMR had significant value in predicting pCR and prognosis in breast cancer patients. The RF model provides a simple and cost-effective tool for pCR prediction, offering strong support for clinical decision-making in breast cancer treatment and aiding in the optimization of individualized treatment strategies.

A Comparative Study of Network-Based Machine Learning Approaches for Binary Classification in Metabolomics

Background/Objectives: Metabolomics has recently emerged as a key tool in the biological sciences, offering insights into metabolic pathways and processes. Over the last decade, network-based machine learning approaches have gained significant popularity and application across various fields. While several studies have utilized metabolomics profiles for sample classification, many network-based machine learning approaches remain unexplored for metabolomic-based classification tasks. This study aims to compare the performance of various network-based machine learning approaches, including recently developed methods, in metabolomics-based classification. Methods: A standard data preprocessing procedure was applied to 17 metabolomic datasets, and Bayesian neural network (BNN), convolutional neural network (CNN), feedforward neural network (FNN), Kolmogorov-Arnold network (KAN), and spiking neural network (SNN) were evaluated on each dataset. The datasets varied widely in size, mass spectrometry method, and response variable. Results: With respect to AUC on test data, BNN, CNN, FNN, KAN, and SNN were the top-performing models in 4, 1, 5, 3, and 4 of the 17 datasets, respectively. Regarding F1-score, the top-performing models were BNN (3 datasets), CNN (3 datasets), FNN (4 datasets), KAN (4 datasets), and SNN (3 datasets). For accuracy, BNN, CNN, FNN, KAN, and SNN performed best in 4, 1, 4, 4, and 4 datasets, respectively. Conclusions: No network-based modeling approach consistently outperformed others across the metrics of AUC, F1-score, or accuracy. Our results indicate that while no single network-based modeling approach is superior for metabolomics-based classification tasks, BNN, KAN, and SNN may be underappreciated and underutilized relative to the more commonly used CNN and FNN.

Metabolomics and (craft) beers - recent advances

Craft beers have encountered a steady rise in popularity over the years, as these artisanal beers produced by microbreweries have responded to consumer preferences for added novelty in such beverages. With this gain in appeal and interest for the beverage, craft beers have also become a growing industry in many parts of the world, and the same can be said for research within the field. This also extends to the chemistry of craft beers, where one method of exploration involves that of metabolomics, appropriately addressing the multi-faceted aspects of craft beer development and chemistry. Alongside advances in metabolomics in general beer and brewing research, the field also mirrors potential in growth. This review touches on relevant aspects of the beer industry and brewing process as preliminaries for discussions on advances in the field of beer metabolomics, leading to the application of metabolomics in pursuit of studying craft beers; future directions, challenges, and opportunities are also presented.

Early detection of feline chronic kidney disease via 3-hydroxykynurenine and machine learning

Feline chronic kidney disease (CKD) is one of the most frequently encountered diseases in veterinary practice, and the leading cause of mortality in cats over five years of age. While diagnosing advanced CKD is straightforward, current routine tests fail to diagnose early CKD. Therefore, this study aimed to identify early metabolic biomarkers. First, cats were retrospectively divided into two populations to conduct a case-control study, comparing the urinary and serum metabolome of healthy (n = 61) and CKD IRIS stage 2 cats (CKD2, n = 63). Subsequently, longitudinal validation was conducted in an independent population comprising healthy cats that remained healthy (n = 26) and cats that developed CKD2 (n = 22) within one year. Univariate, multivariate, and machine learning-based (ML) approaches were compared. The serum-to-urine ratio of 3-hydroxykynurenine was identified as a single biomarker candidate, yielding a high AUC (0.844) and accuracy (0.804), while linear support vector machine-based modelling employing metabolites and clinical parameters enhanced AUC (0.929) and accuracy (0.862) six months before traditional diagnosis. Furthermore, analysis of variable importance indicated consistent key serum metabolites, namely creatinine, SDMA, 2-hydroxyethanesulfonate, and aconitic acid. By enabling accurate diagnosis at least six months earlier, the highlighted metabolites may pave the way for improved diagnostics, ultimately contributing to timely disease management.

Artificial intelligence in the management of metabolic disorders: a comprehensive review

This review explores the significant role of artificial intelligence (AI) in managing metabolic disorders like diabetes, obesity, metabolic dysfunction-associated fatty liver disease (MAFLD), and thyroid dysfunction. AI applications in this context encompass early diagnosis, personalized treatment plans, risk assessment, prevention, and biomarker discovery for early and accurate disease management. This review also delves into techniques involving machine learning (ML), deep learning (DL), natural language processing (NLP), computer vision, and reinforcement learning associated with AI and their application in metabolic disorders. The following study also enlightens the challenges and ethical considerations associated with AI implementation, such as data privacy, model interpretability, and bias mitigation. We have reviewed various AI-based tools utilized for the diagnosis and management of metabolic disorders, such as Idx, Guardian Connect system, and DreaMed for diabetes. Further, the paper emphasizes the potential of AI to revolutionize the management of metabolic disorders through collaborations among clinicians and AI experts, the integration of AI into clinical practice, and the necessity for long-term validation studies. The references provided in the paper cover a range of studies related to AI, ML, personalized medicine, metabolic disorders, and diagnostic tools in healthcare, including research on disease diagnostics, personalized therapy, chronic disease management, and the application of AI in diabetes care and nutrition.

Precision Dietary Intervention: Gut Microbiome and Meta-metabolome as Functional Readouts

Gut microbiome, the group of commensals residing within the intestinal tract, is closely associated with dietary patterns by interacting with food components. The gut microbiome is modifiable by the diet, and in turn, it utilizes the undigested food components as substrates and generates a group of small molecule-metabolites that addressed as "meta-metabolome" in this review. Profiling and mapping of meta-metabolome could yield insightful information at higher resolution and serve as functional readouts for precision nutrition and formation of personalized dietary strategies. For assessing the meta-metabolome, sample preparation is important, and it should aim for retrieval of gut microbial metabolites as intact as possible. The meta-metabolome can be investigated via untargeted and targeted meta-metabolomics with analytical platforms such as nuclear magnetic resonance spectroscopy and mass spectrometry. Employing flux analysis with meta-metabolomics using available database could further elucidate metabolic pathways that lead to biomarker discovery. In conclusion, integration of gut microbiome and meta-metabolomics is a promising supplementary approach to tailor precision dietary intervention. In this review, relationships among diet, gut microbiome, and meta-metabolome are elucidated, with an emphasis on recent advances in alternative analysis techniques proposed for nutritional research. We hope that this review will provide information for establishing pipelines complementary to traditional approaches for achieving precision dietary intervention.

A Comprehensive Machine Learning Approach for COVID-19 Target Discovery in the Small-Molecule Metabolome

Background/Objectives: Respiratory viruses, including Influenza, RSV, and COVID-19, cause various respiratory infections. Distinguishing these viruses relies on diagnostic methods such as PCR testing. Challenges stem from overlapping symptoms and the emergence of new strains. Advanced diagnostics are crucial for accurate detection and effective management. This study leveraged nasopharyngeal metabolome data to predict respiratory virus scenarios including control vs. RSV, control vs. Influenza A, control vs. COVID-19, control vs. all respiratory viruses, and COVID-19 vs. Influenza A/RSV. Method: We proposed a stacking-based ensemble technique, integrating the top three best-performing ML models from the initial results to enhance prediction accuracy by leveraging the strengths of multiple base learners. Key techniques such as feature ranking, standard scaling, and SMOTE were used to address class imbalances, thus enhancing model robustness. SHAP analysis identified crucial metabolites influencing positive predictions, thereby providing valuable insights into diagnostic markers. Results: Our approach not only outperformed existing methods but also revealed top dominant features for predicting COVID-19, including Lysophosphatidylcholine acyl C18:2, Kynurenine, Phenylalanine, Valine, Tyrosine, and Aspartic Acid (Asp). Conclusions: This study demonstrates the effectiveness of leveraging nasopharyngeal metabolome data and stacking-based ensemble techniques for predicting respiratory virus scenarios. The proposed approach enhances prediction accuracy, provides insights into key diagnostic markers, and offers a robust framework for managing respiratory infections.

High-throughput untargeted metabolomics reveals metabolites and metabolic pathways that differentiate two divergent pig breeds

Metabolomics can describe the molecular phenome and may contribute to dissecting the biological processes linked to economically relevant traits in livestock species. Comparative analyses of metabolomic profiles in purebred pigs can provide insights into the basic biological mechanisms that may explain differences in production performances. Following this concept, this study was designed to compare, on a large scale, the plasma metabolomic profiles of two Italian heavy pig breeds (Italian Duroc and Italian Large White) to indirectly evaluate the impact of their different genetic backgrounds on the breed metabolomes. We utilised a high-throughput untargeted metabolomics approach in a total of 962 pigs that allowed us to detect and relatively quantify 722 metabolites from various biological classes. The molecular data were analysed using a bioinformatics pipeline specifically designed for identifying differentially abundant metabolites between the two breeds in a robust and statistically significant manner, including the Boruta algorithm, which is a Random Forest wrapper, and sparse Partial Least Squares Discriminant Analysis (sPLS-DA) for feature selection. After thoroughly evaluating the impact of random components on missing value imputation, 100 discriminant metabolites were selected by Boruta and 17 discriminant metabolites (all included within the previous list) were identified with sPLS-DA. About half of the 100 discriminant metabolites had a higher concentration in one or the other breed (48 in Italian Large White pigs, with a prevalence of amino acids and peptides; 52 in Italian Duroc pigs, with a prevalence of lipids). These metabolites were from seven distinct super pathways and had an absolute mean value of percentage difference between the two breeds (|Δ|%) of 39.2 ± 32.4. Six of these metabolites had |Δ|%> 100. A general correlation network analysis based on Boruta-identified metabolites consisted of 31 singletons and 69 metabolites connected by 141 edges, with two large clusters (> 15 nodes), three medium clusters (3-6 nodes) and eight additional pairs, with most metabolites belonging to the same super pathway. The major cluster representing the lipids super-pathway included 24 metabolites, primarily sphingomyelins. Overall, this study identified metabolomic differences between Italian Duroc and Italian Large White pigs explained by the specific genetic background of the two breeds. These biomarkers can explain the biological differences between these two breeds and can have potential practical applications in pig breeding and husbandry.

Clinical applications of volatilomic assays

The study of metabolomics is revealing immense potential for diagnosis, therapy monitoring, and understanding of pathogenesis processes. Volatilomics is a subcategory of metabolomics interested in the detection of molecules that are small enough to be released in the gas phase. Volatile compounds produced by cellular processes are released into the blood and lymph, and can reach the external environment through different pathways, such as the blood-air interface in the lung that are detected in breath, or the blood-water interface in the kidney that leads to volatile compounds detected in urine. Besides breath and urine, additional sources of volatile compounds such as saliva, blood, feces, and skin are available. Volatilomics traces its roots back over fifty years to the pioneering investigations in the 1970s. Despite extensive research, the field remains in its infancy, hindered by a lack of standardization despite ample experimental evidence. The proliferation of analytical instrumentations, sample preparations and methods of volatilome sampling still make it difficult to compare results from different studies and to establish a common standard approach to volatilomics. This review aims to provide an overview of volatilomics' diagnostic potential, focusing on two key technical aspects: sampling and analysis. Sampling poses a challenge due to the susceptibility of human samples to contamination and confounding factors from various sources like the environment and lifestyle. The discussion then delves into targeted and untargeted approaches in volatilomics. Some case studies are presented to exemplify the results obtained so far. Finally, the review concludes with a discussion on the necessary steps to fully integrate volatilomics into clinical practice.

Application of machine learning for mass spectrometry-based multi-omics in thyroid diseases

Thyroid diseases, including functional and neoplastic diseases, bring a huge burden to people's health. Therefore, a timely and accurate diagnosis is necessary. Mass spectrometry (MS) based multi-omics has become an effective strategy to reveal the complex biological mechanisms of thyroid diseases. The exponential growth of biomedical data has promoted the applications of machine learning (ML) techniques to address new challenges in biology and clinical research. In this review, we presented the detailed review of applications of ML for MS-based multi-omics in thyroid disease. It is primarily divided into two sections. In the first section, MS-based multi-omics, primarily proteomics and metabolomics, and their applications in clinical diseases are briefly discussed. In the second section, several commonly used unsupervised learning and supervised algorithms, such as principal component analysis, hierarchical clustering, random forest, and support vector machines are addressed, and the integration of ML techniques with MS-based multi-omics data and its application in thyroid disease diagnosis is explored.

Research on Lipidomic Profiling and Biomarker Identification for Osteonecrosis of the Femoral Head

Objectives: Abnormal lipid metabolism is increasingly recognized as a contributing factor to the development of osteonecrosis of the femoral head (ONFH). This study aimed to explore the lipidomic profiles of ONFH patients, focusing on distinguishing between traumatic ONFH (TONFH) and non-traumatic ONFH (NONFH) subtypes and identifying potential biomarkers for diagnosis and understanding pathogenesis. Methods: Plasma samples were collected from 92 ONFH patients (divided into TONFH and NONFH subtypes) and 33 healthy normal control (NC) participants. Lipidomic profiling was performed using ultra-high performance liquid chromatography-tandem mass spectrometry (UHPLC-MS/MS). Data analysis incorporated a machine learning-based feature selection method, least absolute shrinkage and selection operator (LASSO) regression, to identify significant lipid biomarkers. Results: Distinct lipidomic signatures were observed in both TONFH and NONFH groups compared to the NC group. LASSO regression identified 11 common lipid biomarkers that signify shared metabolic disruptions in both ONFH subtypes, several of which exhibited strong diagnostic performance with areas under the curve (AUCs) > 0.7. Additionally, subtype-specific lipid markers unique to TONFH and NONFH were identified, providing insights into the differential pathophysiological mechanisms underlying these subtypes. Conclusions: This study highlights the importance of lipidomic profiling in understanding ONFH-associated metabolic disorders and demonstrates the utility of machine learning approaches, such as LASSO regression, in high-dimensional data analysis. These findings not only improve disease characterization but also facilitate the discovery of diagnostic and mechanistic biomarkers, paving the way for more personalized therapeutic strategies in ONFH.

Integrating omics data and machine learning techniques for precision detection of oral squamous cell carcinoma: evaluating single biomarkers

Introduction

Early detection of oral squamous cell carcinoma (OSCC) is critical for improving clinical outcomes. Precision diagnostics integrating metabolomics and machine learning offer promising non-invasive solutions for identifying tumor-derived biomarkers.

Methods

We analyzed a multicenter public dataset comprising 61 OSCC patients and 61 healthy controls. Plasma metabolomics data were processed to extract 29 numerical and 47 ratio features. The Extra Trees (ET) algorithm was applied for feature selection, and the TabPFN model was used for classification and prediction.

Results

The model achieved an area under the curve (AUC) of 93% and an overall accuracy of 76.6% when using top-ranked individual biomarkers. Key metabolic features significantly differentiated OSCC patients from healthy controls, providing a detailed metabolic fingerprint of the disease.

Discussion

Our findings demonstrate the utility of integrating omics data with advanced machine learning techniques to develop accurate, non-invasive diagnostic tools for OSCC. The study highlights actionable metabolic signatures that have potential applications in personalized therapeutics and early intervention strategies.

Integrating Metabolomics Domain Knowledge with Explainable Machine Learning in Atherosclerotic Cardiovascular Disease Classification

Metabolomic data often present challenges due to high dimensionality, collinearity, and variability in metabolite concentrations. Machine learning (ML) application in metabolomic analyses is enabling the extraction of meaningful information from complex data. Bringing together domain-specific knowledge from metabolomics with explainable ML methods can refine the predictive performance and interpretability of models used in atherosclerosis research. In this work, we aimed to identify the most impactful metabolites associated with the presence of atherosclerotic cardiovascular disease (ASCVD) in cross-sectional case-control studies using explainable ML methods integrated with metabolomics domain knowledge. For this, a subset from the FLEMENGHO cohort with metabolomic data available was used as the training cohort, including 63 patients with a history of ASCVD and 52 non-smoking controls matched by age, sex, and body mass index from the same population. First, Partial Least Squares Discriminant Analysis (PLS-DA) was applied for dimensionality reduction. The selected metabolites' correlations were analyzed by considering their chemical categorization. Then, eXtreme Gradient Boosting (XGBoost) was used to identify metabolites that characterize ASCVD. Next, the selected metabolites were evaluated in an external cohort to determine their effectiveness in distinguishing between cases and controls. A total of 56 metabolites were selected for ASCVD discrimination using PLS-DA. The primary identified metabolites' superclasses included lipids, organic acids, and organic oxygen compounds. Upon integrating these metabolites with the XGBoost model, the classification yielded a test area under the curve (AUC) of 0.75. SHAP analyses ranked cholesterol, 3-methylhistidine, and glucuronic acid among the most impactful features and showed the diversity of metabolites considered for building the ASCVD discriminator. Also using XGBoost, the selected metabolites achieved an AUC of 0.93 in an independent external validation cohort. In conclusion, the combination of different metabolites has the potential to build classifiers for ASCVD. Integrating metabolite categorization within the SHAP analysis further enhanced the interpretability of the model, offering insights into metabolite-specific contributions to ASCVD risk.

Classifying Dry Eye Disease Patients from Healthy Controls Using Machine Learning and Metabolomics Data

Background: Dry eye disease is a common disorder of the ocular surface, leading patients to seek eye care. Clinical signs and symptoms are currently used to diagnose dry eye disease. Metabolomics, a method for analyzing biological systems, has been found helpful in identifying distinct metabolites in patients and in detecting metabolic profiles that may indicate dry eye disease at early stages. In this study, we explored the use of machine learning and metabolomics data to identify cataract patients who suffer from dry eye disease, a topic that, to our knowledge, has not been previously explored. As there is no one-size-fits-all machine learning model for metabolomics data, choosing the most suitable model can significantly affect the quality of predictions and subsequent metabolomics analyses. Methods: To address this challenge, we conducted a comparative analysis of eight machine learning models on two metabolomics data sets from cataract patients with and without dry eye disease. The models were evaluated and optimized using nested k-fold cross-validation. To assess the performance of these models, we selected a set of suitable evaluation metrics tailored to the data set's challenges. Results: The logistic regression model overall performed the best, achieving the highest area under the curve score of 0.8378, balanced accuracy of 0.735, Matthew's correlation coefficient of 0.5147, an F1-score of 0.8513, and a specificity of 0.5667. Additionally, following the logistic regression, the XGBoost and Random Forest models also demonstrated good performance. Conclusions: The results show that the logistic regression model with L2 regularization can outperform more complex models on an imbalanced data set with a small sample size and a high number of features, while also avoiding overfitting and delivering consistent performance across cross-validation folds. Additionally, the results demonstrate that it is possible to identify dry eye in cataract patients from tear film metabolomics data using machine learning models.

Urinary metabolomics provide insights into coronary artery disease in individuals with type 1 diabetes

BACKGROUND

Type 1 diabetes increases the risk of coronary artery disease (CAD). High-throughput metabolomics may be utilized to identify metabolites associated with disease, thus, providing insight into disease pathophysiology, and serving as predictive markers in clinical practice. Urine is less tightly regulated than blood, and therefore, may enable earlier discovery of disease-associated markers. We studied urine metabolomics in relation to incident CAD in individuals with type 1 diabetes.

METHODS

We prospectively studied CAD in 2501 adults with type 1 diabetes from the Finnish Diabetic Nephropathy Study. 209 participants experienced incident CAD within the 10-year follow-up. We analyzed the baseline urine samples with a high-throughput targeted urine metabolomics platform, which yielded 54 metabolites. With the data, we performed metabolome-wide survival analyses, correlation network analyses, and metabolomic state profiling for prediction of incident CAD.

RESULTS

Urinary 3-hydroxyisobutyrate was associated with decreased 10-year incident CAD, which according to the network analysis, likely reflects younger age and improved kidney function. Urinary xanthosine was associated with 10-year incident CAD. In the network analysis, xanthosine correlated with baseline urinary allantoin, which is a marker of oxidative stress. In addition, urinary trans-aconitate and 4-deoxythreonate were associated with decreased 5-year incident CAD. Metabolomic state profiling supported the usage of CAD-associated urinary metabolites to improve prediction accuracy, especially during shorter follow-up. Furthermore, urinary trans-aconitate and 4-deoxythreonate were associated with decreased 5-year incident CAD. The network analysis further suggested glomerular filtration rate to influence the urinary metabolome differently between individuals with and without future CAD.

CONCLUSIONS

We have performed the first high-throughput urinary metabolomics analysis on CAD in individuals with type 1 diabetes and found xanthosine, 3-hydroxyisobutyrate, trans-aconitate, and 4-deoxythreonate to be associated with incident CAD. In addition, metabolomic state profiling improved prediction of incident CAD.

Artificial intelligence with mass spectrometry-based multimodal molecular profiling methods for advancing therapeutic discovery of infectious diseases

Infectious diseases, driven by a diverse array of pathogens, can swiftly undermine public health systems. Accurate diagnosis and treatment of infectious diseases-centered around the identification of biomarkers and the elucidation of disease mechanisms-are in dire need of more versatile and practical analytical approaches. Mass spectrometry (MS)-based molecular profiling methods can deliver a wealth of information on a range of functional molecules, including nucleic acids, proteins, and metabolites. While MS-driven omics analyses can yield vast datasets, the sheer complexity and multi-dimensionality of MS data can significantly hinder the identification and characterization of functional molecules within specific biological processes and events. Artificial intelligence (AI) emerges as a potent complementary tool that can substantially enhance the processing and interpretation of MS data. AI applications in this context lead to the reduction of spurious signals, the improvement of precision, the creation of standardized analytical frameworks, and the increase of data integration efficiency. This critical review emphasizes the pivotal roles of MS based omics strategies in the discovery of biomarkers and the clarification of infectious diseases. Additionally, the review underscores the transformative ability of AI techniques to enhance the utility of MS-based molecular profiling in the field of infectious diseases by refining the quality and practicality of data produced from omics analyses. In conclusion, we advocate for a forward-looking strategy that integrates AI with MS-based molecular profiling. This integration aims to transform the analytical landscape and the performance of biological molecule characterization, potentially down to the single-cell level. Such advancements are anticipated to propel the development of AI-driven predictive models, thus improving the monitoring of diagnostics and therapeutic discovery for the ongoing challenge related to infectious diseases.

Metabolomics-driven approaches for identifying therapeutic targets in drug discovery

Identification of therapeutic targets can directly elucidate the mechanism and effect of drug therapy, which is a central step in drug development. The disconnect between protein targets and phenotypes under complex mechanisms hampers comprehensive target understanding. Metabolomics, as a systems biology tool that captures phenotypic changes induced by exogenous compounds, has emerged as a valuable approach for target identification. A comprehensive overview was provided in this review to illustrate the principles and advantages of metabolomics, delving into the application of metabolomics in target identification. This review outlines various metabolomics-based methods, such as dose-response metabolomics, stable isotope-resolved metabolomics, and multiomics, which identify key enzymes and metabolic pathways affected by exogenous substances through dose-dependent metabolite-drug interactions. Emerging techniques, including single-cell metabolomics, artificial intelligence, and mass spectrometry imaging, are also explored for their potential to enhance target discovery. The review emphasizes metabolomics' critical role in advancing our understanding of disease mechanisms and accelerating targeted drug development, while acknowledging current challenges in the field.

Potential of pre-diagnostic metabolomics for colorectal cancer risk assessment or early detection

This systematic review investigates the efficacy of metabolite biomarkers for risk assessment or early detection of colorectal cancer (CRC) and its precursors, focusing on pre-diagnostic biospecimens. Searches in PubMed, Web of Science, and SCOPUS through December 2023 identified relevant prospective studies. Relevant data were extracted, and the risk of bias was assessed with the QUADAS-2 tool. Among the 26 studies included, significant heterogeneity existed for case numbers, metabolite identification, and validation approaches. Thirteen studies evaluated individual metabolites, mainly lipids, while eleven studies derived metabolite panels, and two studies did both. Nine panels were internally validated, resulting in an area under the curve (AUC) ranging from 0.69 to 0.95 for CRC precursors and 0.72 to 1.0 for CRC. External validation was limited to one panel (AUC = 0.72). Metabolite panels and lipid-based biomarkers show promise for CRC risk assessment and early detection but require standardization and extensive validation for clinical use.

Identification of metabolic biomarkers in idiopathic pulmonary arterial hypertension using targeted metabolomics and bioinformatics analysis

Pulmonary arterial hypertension (PAH) is a life-threatening disease with a poor prognosis, and metabolic abnormalities play a critical role in its development. This study used metabolomics, machine learning algorithms and bioinformatics to screen for potential metabolic biomarkers associated with the diagnosis of PAH. In this study, plasma samples were collected from 17 patients diagnosed with idiopathic pulmonary arterial hypertension (IPAH) and 20 healthy controls. Plasma metabolomic profiling was performed by high-performance liquid chromatography-mass spectrometry. Gene profiles of PAH patients were obtained from the GEO database. Key differentially expressed metabolites (DEMs) and metabolism-related genes were subsequently identified using machine learning algorithms. Twenty differential plasma metabolites associated with IPAH were identified (VIP score > 1 and p < 0 0.05), and enrichment analysis revealed the arginine biosynthesis pathway as the most altered pathway. Using machine learning models, including least absolute shrinkage and selection operator (LASSO), random forest (RF) and support vector machine (SVM), we extracted key metabolites that correlated with clinical phenotypes. Our results suggested that five metabolites, kynurenine, homoserine, tryptophan, AMP, and spermine, are potential biomarkers for IPAH. Bioinformatics analysis also identified 3 metabolism-related genes, MAPK6, SLC7A11 and CDC42BPA, that are strongly correlated with pulmonary hypertension, demonstrating strong predictive power and clinical relevance. Our findings revealed some key genes associated with metabolism in PH, and provided crucial information about complex metabolic reprogramming signals and may lead to the identification of useful metabolic biomarkers for the diagnosis of PAH.

Integrating Molecular Perspectives: Strategies for Comprehensive Multi-Omics Integrative Data Analysis and Machine Learning Applications in Transcriptomics, Proteomics, and Metabolomics

With the advent of high-throughput technologies, the field of omics has made significant strides in characterizing biological systems at various levels of complexity. Transcriptomics, proteomics, and metabolomics are the three most widely used omics technologies, each providing unique insights into different layers of a biological system. However, analyzing each omics data set separately may not provide a comprehensive understanding of the subject under study. Therefore, integrating multi-omics data has become increasingly important in bioinformatics research. In this article, we review strategies for integrating transcriptomics, proteomics, and metabolomics data, including co-expression analysis, metabolite-gene networks, constraint-based models, pathway enrichment analysis, and interactome analysis. We discuss combined omics integration approaches, correlation-based strategies, and machine learning techniques that utilize one or more types of omics data. By presenting these methods, we aim to provide researchers with a better understanding of how to integrate omics data to gain a more comprehensive view of a biological system, facilitating the identification of complex patterns and interactions that might be missed by single-omics analyses.

Causal Metabolomic and Lipidomic Analysis of Circulating Plasma Metabolites in Autism: A Comprehensive Mendelian Randomization Study with Independent Cohort Validation

BACKGROUND

The increasing prevalence of autism spectrum disorder (ASD) highlights the need for objective diagnostic markers and a better understanding of its pathogenesis. Metabolic differences have been observed between individuals with and without ASD, but their causal relevance remains unclear.

METHODS

Bidirectional two-sample Mendelian randomization (MR) was used to assess causal associations between circulating plasma metabolites and ASD using large-scale genome-wide association study (GWAS) datasets-comprising 1091 metabolites, 309 ratios, and 179 lipids-and three European autism datasets (PGC 2015: n = 10,610 and 10,263; 2017: n = 46,351). Inverse-variance weighted (IVW) and weighted median methods were employed, along with robust sensitivity and power analyses followed by independent cohort validation.

RESULTS

Higher genetically predicted levels of sphingomyelin (SM) (d17:1/16:0) (OR, 1.129; 95% CI, 1.024-1.245; p = 0.015) were causally linked to increased ASD risk. Additionally, ASD children had higher plasma creatine/carnitine ratios. These MR findings were validated in an independent US autism cohort using machine learning analysis.

CONCLUSION

Utilizing large datasets, two MR approaches, robust sensitivity analyses, and independent validation, our novel findings provide evidence for the potential roles of metabolomics and circulating metabolites in ASD diagnosis and etiology.

Metabolomic profiling of dengue infection: unraveling molecular signatures by LC-MS/MS and machine learning models

BACKGROUND & OBJECTIVE

The progression of dengue fever to severe dengue (SD) is a major public health concern that impairs the capacity of the medical system to predict and treat dengue patients. Hence, the present study used a metabolomic approach integrated with machine models to identify differentially expressed metabolites in patients with SD compared to nonsevere patients and healthy controls.

METHODS

Comprehensively, the plasma was collected at different clinical phases during dengue without warning signs (DWOW, N = 10), dengue with warning signs (DWW, N = 10), and SD (N = 10) at different stages [i.e., day of admission (DOA), day of defervescence (DOD), and day of convalescent (DOC)] in comparison to healthy control (HC). The samples were subjected to LC‒ESI‒MS/MS to identify metabolites. Statistical and machine learning analyses were performed using R and Python language. Further, biomarker, pathway and correlation analysis was performed to identify potential predictors of dengue.

RESULTS & CONCLUSION

A total of 423 metabolites were identified in all the study groups. Paired and unpaired t-tests revealed 14 highly differentially expressed metabolites between and across the dengue groups, with four metabolites (shikimic acid, ureidosuccinic acid, propionyl carnitine, and alpha-tocopherol) showing significant differences compared to HC. Furthermore, biomarker (ROC) analysis revealed 11 potential molecules with a significant AUC value of 1 that could serve as potential biomarkers for identifying different dengue clinical stages that are beneficial for predicting dengue disease outcomes. The logistic regression model revealed that S-adenosylhomocysteine, hypotaurine, and shikimic acid metabolites could be beneficial indicators for predicting severe dengue, with an accuracy and AUC of 0.75. The data showed that dengue infection is related to lipid metabolism, oxidative stress, inflammation, metabolomic adaptation, and virus manipulation. Moreover, the biomarkers had a significant correlation with biochemical parameters like platelet count, and hematocrit. These results shed some light on host-derived small-molecule biomarkers that are associated with dengue severity and novel insights into metabolomics mechanisms interlinked with disease severity.

Techniques, Databases and Software Used for Studying Polar Metabolites and Lipids of Gastrointestinal Parasites

Gastrointestinal parasites (GIPs) are organisms known to have coevolved for millennia with their mammalian hosts. These parasites produce small molecules, peptides, and proteins to evade or fight their hosts' immune systems and also to protect their host for their own survival/coexistence. The small molecules include polar compounds, amino acids, lipids, and carbohydrates. Metabolomics and lipidomics are emerging fields of research that have recently been applied to study helminth infections, host-parasite interactions and biochemicals of GIPs. This review comprehensively discusses metabolomics and lipidomics studies of the small molecules of GIPs, providing insights into the available tools and techniques, databases, and analytical software. Most metabolomics and lipidomics investigations employed LC-MS, MS or MS/MS, NMR, or a combination thereof. Recent advancements in artificial intelligence (AI)-assisted software tools and databases have propelled parasitomics forward, offering new avenues to explore host-parasite interactions, immunomodulation, and the intricacies of parasitism. As our understanding of AI technologies and their utilisation continue to expand, it promises to unveil novel perspectives and enrich the knowledge of these complex host-parasite relationships.

Machine Learning-Based Plasma Metabolomics in Liraglutide-Treated Type 2 Diabetes Mellitus Patients and Diet-Induced Obese Mice

Liraglutide, a glucagon-like peptide-1 receptor agonist, is effective in the treatment of type 2 diabetes mellitus (T2DM) and obesity. Despite its benefits, including improved glycemic control and weight loss, the common metabolic changes induced by liraglutide and correlations between those in rodents and humans remain unknown. Here, we used advanced machine learning techniques to analyze the plasma metabolomic data in diet-induced obese (DIO) mice and patients with T2DM treated with liraglutide. Among the machine learning models, Support Vector Machine was the most suitable for DIO mice, and Gradient Boosting was the most suitable for patients with T2DM. Through the cross-evaluation of machine learning models, we found that liraglutide promotes metabolic shifts and interspecies correlations in these shifts between DIO mice and patients with T2DM. Our comparative analysis helped identify metabolic correlations influenced by liraglutide between humans and rodents and may guide future therapeutic strategies for T2DM and obesity.

Use of Serum Protein Measurements as Biomarkers that Can Predict the Outcome of Diabetic Foot Ulceration

Objectives: To identify proteins that are prognostic for diabetic foot ulcer (DFU) healing and may serve as biomarkers for its management, serum samples were analyzed from diabetic mellitus (DM) patients. Approach: The serum specimens that were evaluated in this study were obtained from DM patients with DFU who participated in a prospective study and were seen biweekly until they healed their ulcer or the exit visit at 12 weeks. The group was divided into Healers (who healed their DFU during the study) and Non-Healers. Results: Interleukin (IL)-10, IL-4, IL-5, IL-6, and IL-13 and interferon-gamma were higher in the Healers while Fractalkine, IL-8, and TNFα were higher in the Non-Healers. The trajectory of IL-10 levels remained stable over time within and across groups, resulting in a strong prognostic ability for the prospective DFU healing course. Classification and Regression Tree analysis created an 11-node decision tree with healing status as the categorical response. Innovation: Consecutive measurements of proteins associated with wound healing can identify biomarkers that can predict DFU healing over a 12-week period. IL-10 was the strongest candidate for prediction. Conclusion: Measurement of serum proteins can serve as a successful strategy in guiding clinical management of DFU. The data also indicate likely superior performance of building a multiprotein biomarker score instead of relying on single biomarkers.

Artificial Intelligence in Metabolomics: A Current Review

Metabolomics and artificial intelligence (AI) form a synergistic partnership. Metabolomics generates large datasets comprising hundreds to thousands of metabolites with complex relationships. AI, aiming to mimic human intelligence through computational modeling, possesses extraordinary capabilities for big data analysis. In this review, we provide a recent overview of the methodologies and applications of AI in metabolomics studies in the context of systems biology and human health. We first introduce the AI concept, history, and key algorithms for machine learning and deep learning, summarizing their strengths and weaknesses. We then discuss studies that have successfully used AI across different aspects of metabolomic analysis, including analytical detection, data preprocessing, biomarker discovery, predictive modeling, and multi-omics data integration. Lastly, we discuss the existing challenges and future perspectives in this rapidly evolving field. Despite limitations and challenges, the combination of metabolomics and AI holds great promises for revolutionary advancements in enhancing human health.

Machine learning for the advancement of genome-scale metabolic modeling

Constraint-based modeling (CBM) has evolved as the core systems biology tool to map the interrelations between genotype, phenotype, and external environment. The recent advancement of high-throughput experimental approaches and multi-omics strategies has generated a plethora of new and precise information from wide-ranging biological domains. On the other hand, the continuously growing field of machine learning (ML) and its specialized branch of deep learning (DL) provide essential computational architectures for decoding complex and heterogeneous biological data. In recent years, both multi-omics and ML have assisted in the escalation of CBM. Condition-specific omics data, such as transcriptomics and proteomics, helped contextualize the model prediction while analyzing a particular phenotypic signature. At the same time, the advanced ML tools have eased the model reconstruction and analysis to increase the accuracy and prediction power. However, the development of these multi-disciplinary methodological frameworks mainly occurs independently, which limits the concatenation of biological knowledge from different domains. Hence, we have reviewed the potential of integrating multi-disciplinary tools and strategies from various fields, such as synthetic biology, CBM, omics, and ML, to explore the biochemical phenomenon beyond the conventional biological dogma. How the integrative knowledge of these intersected domains has improved bioengineering and biomedical applications has also been highlighted. We categorically explained the conventional genome-scale metabolic model (GEM) reconstruction tools and their improvement strategies through ML paradigms. Further, the crucial role of ML and DL in omics data restructuring for GEM development has also been briefly discussed. Finally, the case-study-based assessment of the state-of-the-art method for improving biomedical and metabolic engineering strategies has been elaborated. Therefore, this review demonstrates how integrating experimental and in silico strategies can help map the ever-expanding knowledge of biological systems driven by condition-specific cellular information. This multiview approach will elevate the application of ML-based CBM in the biomedical and bioengineering fields for the betterment of society and the environment.

Using matrix assisted laser desorption ionisation mass spectrometry combined with machine learning for vaccine authenticity screening

The global population is increasingly reliant on vaccines to maintain population health with billions of doses used annually in immunisation programmes. Substandard and falsified vaccines are becoming more prevalent, caused by both the degradation of authentic vaccines but also deliberately falsified vaccine products. These threaten public health, and the increase in vaccine falsification is now a major concern. There is currently no coordinated global infrastructure or screening methods to monitor vaccine supply chains. In this study, we developed and validated a matrix-assisted laser desorption/ionisation-mass spectrometry (MALDI-MS) workflow that used open-source machine learning and statistical analysis to distinguish authentic and falsified vaccines. We validated the method on two different MALDI-MS instruments used worldwide for clinical applications. Our results show that multivariate data modelling and diagnostic mass spectra can be used to distinguish authentic and falsified vaccines providing proof-of-concept that MALDI-MS can be used as a screening tool to monitor vaccine supply chains.

The impact and future of artificial intelligence in medical genetics and molecular medicine: an ongoing revolution

Artificial intelligence (AI) platforms have emerged as pivotal tools in genetics and molecular medicine, as in many other fields. The growth in patient data, identification of new diseases and phenotypes, discovery of new intracellular pathways, availability of greater sets of omics data, and the need to continuously analyse them have led to the development of new AI platforms. AI continues to weave its way into the fabric of genetics with the potential to unlock new discoveries and enhance patient care. This technology is setting the stage for breakthroughs across various domains, including dysmorphology, rare hereditary diseases, cancers, clinical microbiomics, the investigation of zoonotic diseases, omics studies in all medical disciplines. AI's role in facilitating a deeper understanding of these areas heralds a new era of personalised medicine, where treatments and diagnoses are tailored to the individual's molecular features, offering a more precise approach to combating genetic or acquired disorders. The significance of these AI platforms is growing as they assist healthcare professionals in the diagnostic and treatment processes, marking a pivotal shift towards more informed, efficient, and effective medical practice. In this review, we will explore the range of AI tools available and show how they have become vital in various sectors of genomic research supporting clinical decisions.

Plasma Instead of Serum Avoids Critical Confounding of Clinical Metabolomics Studies by Platelets

Metabolomics is an emerging and powerful bioanalytical method supporting clinical investigations. Serum and plasma are commonly used without rational prioritization. Serum is collected after blood coagulation, a complex biochemical process involving active platelet metabolism. This may affect the metabolome and increase the variance, as platelet counts and function may vary substantially in individuals. A multiomics approach systematically investigating the suitability of serum and plasma for clinical studies demonstrated that metabolites correlated well (n = 461, R2 = 0.991), whereas lipid mediators (n = 83, R2 = 0.906) and proteins (n = 322, R2 = 0.860) differed substantially between specimen. Independently, analysis of platelet releasates identified most biomolecules significantly enriched in serum compared to plasma. A prospective, randomized, controlled parallel group metabolomics trial with acetylsalicylic acid administered for 7 days demonstrated that the apparent drug effects significantly differ depending on the analyzed specimen. Only serum analyses of healthy individuals suggested a significant downregulation of TXB2 and 12-HETE, which were specifically formed during coagulation in vitro. Plasma analyses reliably identified acetylsalicylic acid effects on metabolites and lipids occurring in vivo such as an increase in serotonin, 15-deoxy-PGJ2 and sphingosine-1-phosphate and a decrease in polyunsaturated fatty acids. The present data suggest that plasma should be preferred above serum for clinical metabolomics studies as the serum metabolome may be substantially confounded by platelets.

Serum Metabolites as Potential Markers and Predictors of Depression-like Behavior and Effective Fluoxetine Treatment in Chronically Socially Isolated Rats

Metabolic perturbation has been associated with depression. An untargeted metabolomics approach using liquid chromatography-high resolution mass spectrometry was employed to detect and measure the rat serum metabolic changes following chronic social isolation (CSIS), an animal model of depression, and effective antidepressant fluoxetine (Flx) treatment. Univariate and multivariate statistics were used for metabolic data analysis and differentially expressed metabolites (DEMs) determination. Potential markers and predictive metabolites of CSIS-induced depressive-like behavior and Flx efficacy in CSIS were evaluated by the receiver operating characteristic (ROC) curve, and machine learning (ML) algorithms, such as support vector machine with linear kernel (SVM-LK) and random forest (RF). Upregulated choline following CSIS may represent a potential marker of depressive-like behavior. Succinate, stachydrine, guanidinoacetate, kynurenic acid, and 7-methylguanine were revealed as potential markers of effective Flx treatment in CSIS rats. RF yielded better accuracy than SVM-LK (98.50% vs. 85.70%, respectively) in predicting Flx efficacy in CSIS vs. CSIS, however, it performed almost identically in classifying CSIS vs. control (75.83% and 75%, respectively). Obtained DEMs combined with ROC curve and ML algorithms provide a research strategy for assessing potential markers or predictive metabolites for the designation or classification of stress-induced depressive phenotype and mode of drug action.

Discovery of urinary biosignatures for tuberculosis and nontuberculous mycobacteria classification using metabolomics and machine learning

Nontuberculous mycobacteria (NTM) infection diagnosis remains a challenge due to its overlapping clinical symptoms with tuberculosis (TB), leading to inappropriate treatment. Herein, we employed noninvasive metabolic phenotyping coupled with comprehensive statistical modeling to discover potential biomarkers for the differential diagnosis of NTM infection versus TB. Urine samples from 19 NTM and 35 TB patients were collected, and untargeted metabolomics was performed using rapid liquid chromatography-mass spectrometry. The urine metabolome was analyzed using a combination of univariate and multivariate statistical approaches, incorporating machine learning. Univariate analysis revealed significant alterations in amino acids, especially tryptophan metabolism, in NTM infection compared to TB. Specifically, NTM infection was associated with upregulated levels of methionine but downregulated levels of glutarate, valine, 3-hydroxyanthranilate, and tryptophan. Five machine learning models were used to classify NTM and TB. Notably, the random forest model demonstrated excellent performance [area under the receiver operating characteristic (ROC) curve greater than 0.8] in distinguishing NTM from TB. Six potential biomarkers for NTM infection diagnosis, including methionine, valine, glutarate, 3-hydroxyanthranilate, corticosterone, and indole-3-carboxyaldehyde, were revealed from univariate ROC analysis and machine learning models. Altogether, our study suggested new noninvasive biomarkers and laid a foundation for applying machine learning to NTM differential diagnosis.

Machine learning of cellular metabolic rewiring

Metabolic rewiring allows cells to adapt their metabolism in response to evolving environmental conditions. Traditional metabolomics techniques, whether targeted or untargeted, often struggle to interpret these adaptive shifts. Here, we introduce MetaboLiteLearner, a lightweight machine learning framework that harnesses the detailed fragmentation patterns from electron ionization (EI) collected in scan mode during gas chromatography/mass spectrometry to predict changes in the metabolite composition of metabolically adapted cells. When tested on breast cancer cells with different preferences to metastasize to specific organs, MetaboLiteLearner predicted the impact of metabolic rewiring on metabolites withheld from the training dataset using only the EI spectra, without metabolite identification or pre-existing knowledge of metabolic networks. Despite its simplicity, the model learned captured shared and unique metabolomic shifts between brain- and lung-homing metastatic lineages, suggesting cellular adaptations associated with metastasis to specific organs. Integrating machine learning and metabolomics paves the way for new insights into complex cellular adaptations.

Finding the best predictive model for hypertensive depression in older adults based on machine learning and metabolomics research

Objective

Depression is a common comorbidity in hypertensive older adults, yet depression is more difficult to diagnose correctly. Our goal is to find predictive models of depression in hypertensive patients using a combination of various machine learning (ML) methods and metabolomics.

Methods

Methods We recruited 379 elderly people aged ≥65 years from the Chinese community. Plasma samples were collected and assayed by gas chromatography/liquid chromatography-mass spectrometry (GC/LC-MS). Orthogonal partial least squares discriminant analysis (OPLS-DA), volcano diagrams and thermograms were used to distinguish metabolites. The attribute discriminators CfsSubsetEval combined with search method BestFirst in WEKA software was used to find the best predicted metabolite combinations, and then 24 classification methods with 10-fold cross-validation were used for prediction.

Results

34 individuals were considered hypertensive combined with depression according to our criteria, and 34 subjects with hypertension only were matched according to age and sex. 19 metabolites by GC-MS and 65 metabolites by LC-MS contributed significantly to the differentiation between the depressed and non-depressed cohorts, with a VIP value of more than 1 and a P value of less than 0.05. There were multiple metabolic pathway alterations. The metabolite combinations screened with WEKA for optimal diagnostic value included 12 metabolites. The machine learning methods with AUC values greater than 0.9 were bayesNet and random forests, and their other evaluation measures are also better.

Conclusion

Altered metabolites and metabolic pathways are present in older adults with hypertension combined with depression. Methods using metabolomics and machine learning performed quite well in predicting depression in hypertensive older adults, contributing to further clinical research.

Automated Machine Learning and Explainable AI (AutoML-XAI) for Metabolomics: Improving Cancer Diagnostics

Metabolomics generates complex data necessitating advanced computational methods for generating biological insight. While machine learning (ML) is promising, the challenges of selecting the best algorithms and tuning hyperparameters, particularly for nonexperts, remain. Automated machine learning (AutoML) can streamline this process; however, the issue of interpretability could persist. This research introduces a unified pipeline that combines AutoML with explainable AI (XAI) techniques to optimize metabolomics analysis. We tested our approach on two data sets: renal cell carcinoma (RCC) urine metabolomics and ovarian cancer (OC) serum metabolomics. AutoML, using Auto-sklearn, surpassed standalone ML algorithms like SVM and k-Nearest Neighbors in differentiating between RCC and healthy controls, as well as OC patients and those with other gynecological cancers. The effectiveness of Auto-sklearn is highlighted by its AUC scores of 0.97 for RCC and 0.85 for OC, obtained from the unseen test sets. Importantly, on most of the metrics considered, Auto-sklearn demonstrated a better classification performance, leveraging a mix of algorithms and ensemble techniques. Shapley Additive Explanations (SHAP) provided a global ranking of feature importance, identifying dibutylamine and ganglioside GM(d34:1) as the top discriminative metabolites for RCC and OC, respectively. Waterfall plots offered local explanations by illustrating the influence of each metabolite on individual predictions. Dependence plots spotlighted metabolite interactions, such as the connection between hippuric acid and one of its derivatives in RCC, and between GM3(d34:1) and GM3(18:1_16:0) in OC, hinting at potential mechanistic relationships. Through decision plots, a detailed error analysis was conducted, contrasting feature importance for correctly versus incorrectly classified samples. In essence, our pipeline emphasizes the importance of harmonizing AutoML and XAI, facilitating both simplified ML application and improved interpretability in metabolomics data science.

Exploring machine learning for untargeted metabolomics using molecular fingerprints

BACKGROUND

Metabolomics, the study of substrates and products of cellular metabolism, offers valuable insights into an organism's state under specific conditions and has the potential to revolutionise preventive healthcare and pharmaceutical research. However, analysing large metabolomics datasets remains challenging, with available methods relying on limited and incompletely annotated metabolic pathways.

METHODS

This study, inspired by well-established methods in drug discovery, employs machine learning on metabolite fingerprints to explore the relationship of their structure with responses in experimental conditions beyond known pathways, shedding light on metabolic processes. It evaluates fingerprinting effectiveness in representing metabolites, addressing challenges like class imbalance, data sparsity, high dimensionality, duplicate structural encoding, and interpretable features. Feature importance analysis is then applied to reveal key chemical configurations affecting classification, identifying related metabolite groups.

RESULTS

The approach is tested on two datasets: one on Ataxia Telangiectasia and another on endothelial cells under low oxygen. Machine learning on molecular fingerprints predicts metabolite responses effectively, and feature importance analysis aligns with known metabolic pathways, unveiling new affected metabolite groups for further study.

CONCLUSION

In conclusion, the presented approach leverages the strengths of drug discovery to address critical issues in metabolomics research and aims to bridge the gap between these two disciplines. This work lays the foundation for future research in this direction, possibly exploring alternative structural encodings and machine learning models.

Mechanotransducive surfaces for enhanced cell osteogenesis, a review

Novel strategies employing mechano-transducing materials eliciting biological outcomes have recently emerged for controlling cellular behaviour. Targeted cellular responses are achieved by manipulating physical, chemical, or biochemical modification of material properties. Advances in techniques such as nanopatterning, chemical modification, biochemical molecule embedding, force-tuneable materials, and artificial extracellular matrices are helping understand cellular mechanotransduction. Collectively, these strategies manipulate cellular sensing and regulate signalling cascades including focal adhesions, YAP-TAZ transcription factors, and multiple osteogenic pathways. In this minireview, we are providing a summary of the influence that these materials, particularly titanium-based orthopaedic materials, have on cells. We also highlight recent complementary methodological developments including, but not limited to, the use of metabolomics for identification of active biomolecules that drive cellular differentiation.

Multi-Omics Analysis Reveals the Toxicity of Polyvinyl Chloride Microplastics toward BEAS-2B Cells

Polyvinyl chloride microplastics (PVC-MPs) are microplastic pollutants widely present in the environment, but their potential risks to human lung health and underlying toxicity mechanisms remain unknown. In this study, we systematically analyzed the effects of PVC-MPs on the transcriptome and metabolome of BEAS-2B cells using high-throughput RNA sequencing and untargeted metabolomics technologies. The results showed that exposure to PVC-MPs significantly reduced the viability of BEAS-2B cells, leading to the differential expression of 530 genes and 3768 metabolites. Further bioinformatics analyses showed that PVC-MP exposure influenced the expression of genes associated with fluid shear stress, the MAPK and TGF-β signaling pathways, and the levels of metabolites associated with amino acid metabolism. In particular, integrated pathway analysis showed that lipid metabolic pathways (including glycerophospholipid metabolism, glycerolipid metabolism, and sphingolipid metabolism) were significantly perturbed in BEAS-2B cells following PVC-MPs exposure. This study provides new insights and targets for a deeper understanding of the toxicity mechanism of PVC-MPs and for the prevention and treatment of PVC-MP-associated lung diseases.

Amino acid metabolomics and machine learning for assessment of post-hepatectomy liver regeneration

Objective

Amino acid (AA) metabolism plays a vital role in liver regeneration. However, its measuring utility for post-hepatectomy liver regeneration under different conditions remains unclear. We aimed to combine machine learning (ML) models with AA metabolomics to assess liver regeneration in health and non-alcoholic steatohepatitis (NASH).

Methods

The liver index (liver weight/body weight) was calculated following 70% hepatectomy in healthy and NASH mice. The serum levels of 39 amino acids were measured using ultra-high performance liquid chromatography-tandem mass spectrometry analysis. We used orthogonal partial least squares discriminant analysis to determine differential AAs and disturbed metabolic pathways during liver regeneration. The SHapley Additive exPlanations algorithm was performed to identify potential AA signatures, and five ML models including least absolute shrinkage and selection operator, random forest, K-nearest neighbor (KNN), support vector regression, and extreme gradient boosting were utilized to assess the liver index.

Results

Eleven and twenty-two differential AAs were identified in the healthy and NASH groups, respectively. Among these metabolites, arginine and proline metabolism were commonly disturbed metabolic pathways related to liver regeneration in both groups. Five AA signatures were identified, including hydroxylysine, L-serine, 3-methylhistidine, L-tyrosine, and homocitrulline in healthy group, and L-arginine, 2-aminobutyric acid, sarcosine, beta-alanine, and L-cysteine in NASH group. The KNN model demonstrated the best evaluation performance with mean absolute error, root mean square error, and coefficient of determination values of 0.0037, 0.0047, 0.79 and 0.0028, 0.0034, 0.71 for the healthy and NASH groups, respectively.

Conclusion

The KNN model based on five AA signatures performed best, which suggests that it may be a valuable tool for assessing post-hepatectomy liver regeneration in health and NASH.

Paper spray mass spectrometry combined with machine learning as a rapid diagnostic for chronic kidney disease

A new analytical method for chronic kidney disease (CKD) detection utilizing paper spray mass spectrometry (PS-MS) combined with machine learning is presented. The analytical protocol is rapid and simple, based on metabolic profile alterations in urine. Anonymized raw urine samples were deposited (10 μL each) onto pointed PS-MS sample strips. Without waiting for the sample to dry, 75 μL of acetonitrile and high voltage were applied to the strips, using high resolution mass spectrometry measurement (15 s per sample) with polarity switching to detect a wide range of metabolites. Random forest machine learning was used to classify the resulting data. The diagnostic performance for the potential diagnosis of CKD was evaluated for accuracy, sensitivity, and specificity, achieving results >96% for the training data and >91% for validation and test data sets. Metabolites selected by the classification model as up- or down-regulated in healthy or CKD samples were tentatively identified and in agreement with previously reported literature. The potential utilization of this approach to discriminate albuminuria categories (normo, micro, and macroalbuminuria) was also demonstrated. This study indicates that PS-MS combined with machine learning has the potential to be used as a rapid and simple diagnostic tool for CKD.