Covid-19 Automated Diagnosis and Risk Assessment through Metabolomics and Machine Learning

Metabolic signatures of acute respiratory distress syndrome: COVID versus non-COVID

Acute respiratory distress syndrome (ARDS) is a fatal pulmonary disorder characterized by severe hypoxia and inflammation. ARDS is commonly triggered by systemic and pulmonary infections, with bacteria and viruses. Notable pathogens include Pseudomonas aeruginosa, Streptococcus aureus, Enterobacter species, coronaviruses, influenza viruses, and herpesviruses. COVID-19 ARDS represents the latest etiological phenotype of the disease. The pathogenesis of ARDS caused by bacteria and viruses exhibits variations in host immune responses and lung mesenchymal injury. We postulate that the systemic and pulmonary metabolomics profiles of ARDS induced by COVID-19 pathogens may exhibit distinctions compared with those induced by other infectious agents. This review aims to compare metabolic signatures in blood and lung specimens specifically within the context of ARDS. Both prevalent and phenotype-specific metabolomic signatures, including but not limited to glycolysis, ketone body production, lipid oxidation, and dysregulation of the kynurenine pathways, were thoroughly examined in this review. The distinctions in metabolic signatures between COVID-19 and non-COVID ARDS have the potential to reveal new biomarkers, elucidate pathogenic mechanisms, identify druggable targets, and facilitate differential diagnosis in the future.

Comparing plasma and skin imprint metabolic profiles in COVID-19 diagnosis and severity assessment

As SARS-CoV-2 continues to produce new variants, the demand for diagnostics and a better understanding of COVID-19 remain key topics in healthcare. Skin manifestations have been widely reported in cases of COVID-19, but the mechanisms and markers of these symptoms are poorly described. In this cross-sectional study, 101 patients (64 COVID-19 positive patients and 37 controls) were enrolled between April and June 2020, during the first wave of COVID-19, in São Paulo, Brazil. Enrolled patients had skin imprints sampled non-invasively using silica plates; plasma samples were also collected. Samples were used for untargeted lipidomics/metabolomics through high-resolution mass spectrometry. We identified 558 molecular ions, with lipids comprising most of them. We found 245 plasma ions that were significant for COVID-19 diagnosis, compared to 61 from the skin imprints. Plasma samples outperformed skin imprints in distinguishing patients with COVID-19 from controls, with F1-scores of 91.9% and 84.3%, respectively. Skin imprints were excellent for assessing disease severity, exhibiting an F1-score of 93.5% when discriminating between patient hospitalization and home care statuses. Specifically, oleamide and linoleamide were the most discriminative biomarkers for identifying hospitalized patients through skin imprinting, and palmitic amides and N-acylethanolamine 18:0 were also identified as significant biomarkers. These observations underscore the importance of primary fatty acid amides and N-acylethanolamines in immunomodulatory processes and metabolic disorders. These findings confirm the potential utility of skin imprinting as a valuable non-invasive sampling method for COVID-19 screening; a method that may also be applied in the evaluation of other medical conditions. KEY MESSAGES: Skin imprints complement plasma in disease metabolomics. The annotated markers have a role in immunomodulation and metabolic diseases. Skin imprints outperformed plasma samples at assessing disease severity. Skin imprints have potential as non-invasive sampling strategy for COVID-19.

Nucleotide, Phospholipid, and Kynurenine Metabolites Are Robustly Associated with COVID-19 Severity and Time of Plasma Sample Collection in a Prospective Cohort Study

Understanding the molecular underpinnings of disease severity and progression in human studies is necessary to develop metabolism-related preventative strategies for severe COVID-19. Metabolites and metabolic pathways that predispose individuals to severe disease are not well understood. In this study, we generated comprehensive plasma metabolomic profiles in >550 patients from the Longitudinal EMR and Omics COVID-19 Cohort. Samples were collected before (n = 441), during (n = 86), and after (n = 82) COVID-19 diagnosis, representing 555 distinct patients, most of which had single timepoints. Regression models adjusted for demographics, risk factors, and comorbidities, were used to determine metabolites associated with predisposition to and/or persistent effects of COVID-19 severity, and metabolite changes that were transient/lingering over the disease course. Sphingolipids/phospholipids were negatively associated with severity and exhibited lingering elevations after disease, while modified nucleotides were positively associated with severity and had lingering decreases after disease. Cytidine and uridine metabolites, which were positively and negatively associated with COVID-19 severity, respectively, were acutely elevated, reflecting the particular importance of pyrimidine metabolism in active COVID-19. This is the first large metabolomics study using COVID-19 plasma samples before, during, and/or after disease. Our results lay the groundwork for identifying putative biomarkers and preventive strategies for severe COVID-19.

Metabolomics-directed nanotechnology in viral diseases management: COVID-19 a case study

The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is currently regarded as the twenty-first century's plague accounting for coronavirus disease 2019 (COVID-19). Besides its reported symptoms affecting the respiratory tract, it was found to alter several metabolic pathways inside the body. Nanoparticles proved to combat viral infections including COVID-19 to demonstrate great success in developing vaccines based on mRNA technology. However, various types of nanoparticles can affect the host metabolome. Considering the increasing proportion of nano-based vaccines, this review compiles and analyses how COVID-19 and nanoparticles affect lipids, amino acids, and carbohydrates metabolism. A search was conducted on PubMed, ScienceDirect, Web of Science for available information on the interrelationship between metabolomics and immunity in the context of SARS-CoV-2 infection and the effect of nanoparticles on metabolite levels. It was clear that SARS-CoV-2 disrupted several pathways to ensure a sufficient supply of its building blocks to facilitate its replication. Such information can help in developing treatment strategies against viral infections and COVID-19 based on interventions that overcome these metabolic changes. Furthermore, it showed that even drug-free nanoparticles can exert an influence on biological systems as evidenced by metabolomics.

Meta-Analysis of COVID-19 Metabolomics Identifies Variations in Robustness of Biomarkers

The global COVID-19 pandemic resulted in widespread harms but also rapid advances in vaccine development, diagnostic testing, and treatment. As the disease moves to endemic status, the need to identify characteristic biomarkers of the disease for diagnostics or therapeutics has lessened, but lessons can still be learned to inform biomarker research in dealing with future pathogens. In this work, we test five sets of research-derived biomarkers against an independent targeted and quantitative Liquid Chromatography-Mass Spectrometry metabolomics dataset to evaluate how robustly these proposed panels would distinguish between COVID-19-positive and negative patients in a hospital setting. We further evaluate a crowdsourced panel comprising the COVID-19 metabolomics biomarkers most commonly mentioned in the literature between 2020 and 2023. The best-performing panel in the independent dataset-measured by F1 score (0.76) and AUROC (0.77)-included nine biomarkers: lactic acid, glutamate, aspartate, phenylalanine, β-alanine, ornithine, arachidonic acid, choline, and hypoxanthine. Panels comprising fewer metabolites performed less well, showing weaker statistical significance in the independent cohort than originally reported in their respective discovery studies. Whilst the studies reviewed here were small and may be subject to confounders, it is desirable that biomarker panels be resilient across cohorts if they are to find use in the clinic, highlighting the importance of assessing the robustness and reproducibility of metabolomics analyses in independent populations.

A Survey of COVID-19 Diagnosis Using Routine Blood Tests with the Aid of Artificial Intelligence Techniques

Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2), causing a disease called COVID-19, is a class of acute respiratory syndrome that has considerably affected the global economy and healthcare system. This virus is diagnosed using a traditional technique known as the Reverse Transcription Polymerase Chain Reaction (RT-PCR) test. However, RT-PCR customarily outputs a lot of false-negative and incorrect results. Current works indicate that COVID-19 can also be diagnosed using imaging resolutions, including CT scans, X-rays, and blood tests. Nevertheless, X-rays and CT scans cannot always be used for patient screening because of high costs, radiation doses, and an insufficient number of devices. Therefore, there is a requirement for a less expensive and faster diagnostic model to recognize the positive and negative cases of COVID-19. Blood tests are easily performed and cost less than RT-PCR and imaging tests. Since biochemical parameters in routine blood tests vary during the COVID-19 infection, they may supply physicians with exact information about the diagnosis of COVID-19. This study reviewed some newly emerging artificial intelligence (AI)-based methods to diagnose COVID-19 using routine blood tests. We gathered information about research resources and inspected 92 articles that were carefully chosen from a variety of publishers, such as IEEE, Springer, Elsevier, and MDPI. Then, these 92 studies are classified into two tables which contain articles that use machine Learning and deep Learning models to diagnose COVID-19 while using routine blood test datasets. In these studies, for diagnosing COVID-19, Random Forest and logistic regression are the most widely used machine learning methods and the most widely used performance metrics are accuracy, sensitivity, specificity, and AUC. Finally, we conclude by discussing and analyzing these studies which use machine learning and deep learning models and routine blood test datasets for COVID-19 detection. This survey can be the starting point for a novice-/beginner-level researcher to perform on COVID-19 classification.

Targeted plasma metabolomics combined with machine learning for the diagnosis of severe acute respiratory syndrome virus type 2

Introduction

The routine clinical diagnosis of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is largely restricted to real-time reverse transcription quantitative PCR (RT-qPCR), and tests that detect SARS-CoV-2 nucleocapsid antigen. Given the diagnostic delay and suboptimal sensitivity associated with these respective methods, alternative diagnostic strategies are needed for acute infection.

Methods

We studied the use of a clinically validated liquid chromatography triple quadrupole method (LC/MS–MS) for detection of amino acids from plasma specimens. We applied machine learning models to distinguish between SARS-CoV-2-positive and negative samples and analyzed amino acid feature importance.

Results

A total of 200 samples were tested, including 70 from individuals with COVID-19, and 130 from negative controls. The top performing model overall allowed discrimination between SARS-CoV-2-positive and negative control samples with an area under the receiver operating characteristic curve (AUC) of 0.96 (95%CI 0.91, 1.00), overall sensitivity of 0.99 (95%CI 0.92, 1.00), and specificity of 0.92 (95%CI 0.85, 0.95).

Discussion

This approach holds potential as an alternative to existing methods for the rapid and accurate diagnosis of acute SARS-CoV-2 infection.

Diagnostic, Prognostic and Mechanistic Biomarkers of COVID-19 Identified by Mass Spectrometric Metabolomics

A number of studies have assessed the impact of SARS-CoV-2 infection and COVID-19 severity on the metabolome of exhaled air, saliva, plasma, and urine to identify diagnostic and prognostic biomarkers. In spite of the richness of the literature, there is no consensus about the utility of metabolomic analyses for the management of COVID-19, calling for a critical assessment of the literature. We identified mass spectrometric metabolomic studies on specimens from SARS-CoV2-infected patients and subjected them to a cross-study comparison. We compared the clinical design, technical aspects, and statistical analyses of published studies with the purpose to identify the most relevant biomarkers. Several among the metabolites that are under- or overrepresented in the plasma from patients with COVID-19 may directly contribute to excessive inflammatory reactions and deficient immune control of SARS-CoV2, hence unraveling important mechanistic connections between whole-body metabolism and the course of the disease. Altogether, it appears that mass spectrometric approaches have a high potential for biomarker discovery, especially if they are subjected to methodological standardization.

Potential of vibrational spectroscopy coupled with machine learning as a non-invasive diagnostic method for COVID-19

BACKGROUND AND OBJECTIVE

Efforts to alleviate the ongoing coronavirus disease 2019 (COVID-19) crisis showed that rapid, sensitive, and large-scale screening is critical for controlling the current infection and that of ongoing pandemics.

METHODS

Here, we explored the potential of vibrational spectroscopy coupled with machine learning to screen COVID-19 patients in its initial stage. Herein presented is a hybrid classification model called grey wolf optimized support vector machine (GWO-SVM). The proposed model was tested and comprehensively compared with other machine learning models via vibrational spectroscopic fingerprinting including saliva FTIR spectra dataset and serum Raman scattering spectra dataset.

RESULTS

For the unknown vibrational spectra, the presented GWO-SVM model provided an accuracy, specificity and F1_score value of 0.9825, 0.9714 and 0.9778 for saliva FTIR spectra dataset, respectively, while an overall accuracy, specificity and F1_score value of 0.9085, 0.9552 and 0.9036 for serum Raman scattering spectra dataset, respectively, which showed superiority than those of state-of-the-art models, thereby suggesting the suitability of the GWO-SVM model to be adopted in a clinical setting for initial screening of COVID-19 patients.

CONCLUSIONS

Prospectively, the presented vibrational spectroscopy based GWO-SVM model can facilitate in screening of COVID-19 patients and alleviate the medical service burden. Therefore, herein proof-of-concept results showed the chance of vibrational spectroscopy coupled with GWO-SVM model to help COVID-19 diagnosis and have the potential be further used for early screening of other infectious diseases.

Applications of liquid chromatography-mass spectrometry based metabolomics in predictive and personalized medicine

Metabolomics is a fast-developing technique used in biomedical researches focusing on pathological mechanism illustration or novel biomarker development for diseases. The ability of simultaneously quantifying thousands of metabolites in samples makes metabolomics a promising technique in predictive or personalized medicine-oriented researches and applications. Liquid chromatography-mass spectrometry is the most widely employed analytical strategy for metabolomics. In this current mini-review, we provide a brief update on the recent developments and novel applications of LC-MS based metabolomics in the predictive and personalized medicine sector, such as early diagnosis, molecular phenotyping or prognostic evaluation. COVID-19 related metabolomic studies are also summarized. We also discuss the prospects of metabolomics in precision medicine-oriented researches, as well as critical issues that need to be addressed when employing metabolomic strategy in clinical applications.

Visual Detection of COVID-19 from Materials Aspect

ABSTRACT

In the recent COVID-19 pandemic, World Health Organization emphasized that early detection is an effective strategy to reduce the spread of SARS-CoV-2 viruses. Several diagnostic methods, such as reverse transcription-polymerase chain reaction (RT-PCR) and lateral flow immunoassay (LFIA), have been applied based on the mechanism of specific recognition and binding of the probes to viruses or viral antigens. Although the remarkable progress, these methods still suffer from inadequate cellular materials or errors in the detection and sampling procedure of nasopharyngeal/oropharyngeal swab collection. Therefore, developing accurate, ultrafast, and visualized detection calls for more advanced materials and technology urgently to fight against the epidemic. In this review, we first summarize the current methodologies for SARS-CoV-2 diagnosis. Then, recent representative examples are introduced based on various output signals (e.g., colorimetric, fluorometric, electronic, acoustic). Finally, we discuss the limitations of the methods and provide our perspectives on priorities for future test development.

Untargeted lipidomics reveals specific lipid profiles in COVID-19 patients with different severity from Campania region (Italy)

COVID-19 infection evokes various systemic alterations that push patients not only towards severe acute respiratory syndrome but causes an important metabolic dysregulation with following multi-organ alteration and potentially poor outcome. To discover novel potential biomarkers able to predict disease's severity and patient's outcome, in this study we applied untargeted lipidomics, by a reversed phase ultra-high performance liquid chromatography-trapped ion mobility mass spectrometry platform (RP-UHPLC-TIMS-MS), on blood samples collected at hospital admission in an Italian cohort of COVID-19 patients (45 mild, 54 severe, 21 controls). In a subset of patients, we also collected a second blood sample in correspondence of clinical phenotype modification (longitudinal population). Plasma lipid profiles revealed several lipids significantly modified in COVID-19 patients with respect to controls and able to discern between mild and severe clinical phenotype. Severe patients were characterized by a progressive decrease in the levels of LPCs, LPC-Os, PC-Os, and, on the contrary, an increase in overall TGs, PEs, and Ceramides. A machine learning model was built by using both the entire dataset and with a restricted lipid panel dataset, delivering comparable results in predicting severity (AUC= 0.777, CI: 0.639-0.904) and outcome (AUC= 0.789, CI: 0.658-0.910). Finally, re-building the model with 25 longitudinal (t1) samples, this resulted in 21 patients correctly classified. In conclusion, this study highlights specific lipid profiles that could be used monitor the possible trajectory of COVID-19 patients at hospital admission, which could be used in targeted approaches.

Early Prediction of COVID-19 Patient Survival by Targeted Plasma Multi-Omics and Machine Learning

The recent surge of coronavirus disease 2019 (COVID-19) hospitalizations severely challenges healthcare systems around the globe and has increased the demand for reliable tests predictive of disease severity and mortality. Using multiplexed targeted mass spectrometry assays on a robust triple quadrupole MS setup which is available in many clinical laboratories, we determined the precise concentrations of hundreds of proteins and metabolites in plasma from hospitalized COVID-19 patients. We observed a clear distinction between COVID-19 patients and controls and, strikingly, a significant difference between survivors and nonsurvivors. With increasing length of hospitalization, the survivors' samples showed a trend toward normal concentrations, indicating a potential sensitive readout of treatment success. Building a machine learning multi-omic model that considers the concentrations of 10 proteins and five metabolites, we could predict patient survival with 92% accuracy (area under the receiver operating characteristic curve: 0.97) on the day of hospitalization. Hence, our standardized assays represent a unique opportunity for the early stratification of hospitalized COVID-19 patients.

Effect of a Functional Phospholipid Metabolome-Protein Association Pathway on the Mechanism of COVID-19 Disease Progression

This study aimed to explore the clinical practice of phospholipid metabolic pathways in COVID-19. In this study, 48 COVID-19 patients and 17 healthy controls were included. Patients were divided into mild (n=40) and severe (n=8) according to their severity. Phospholipid metabolites, TCA circulating metabolites, eicosanoid metabolites, and closely associated enzymes and transfer proteins were detected in the plasma of all individuals using metabolomics and proteomics assays, respectively. 30 of the 33 metabolites found differed significantly (P<0.05) between patients and healthy controls (P<0.05), with D-dimmer significantly correlated with all of the lysophospholipid metabolites (LysoPE, LysoPC, LysoPI and LPA). In particular, we found that phosphatidylinositol (PI) and phosphatidylcholine (PC) could identify patients from healthy controls (AUC 0.771 and 0.745, respectively) and that the severity of the patients could be determined (AUC 0.663 and 0.809, respectively). The last measurement before discharge also revealed significant changes in both PI and PC. For the first time, our study explores the significance of the phospholipid metabolic system in COVID-19 patients. Based on molecular pathway mechanisms, three important phospholipid pathways related to Ceramide-Malate acid (Cer-SM), Lysophospholipid (LPs), and membrane function were established. Clinical values discovered included the role of Cer in maintaining the inflammatory internal environment, the modulation of procoagulant LPA by upstream fibrinolytic metabolites, and the role of PI and PC in predicting disease aggravation.

Machine learning and semi-targeted lipidomics identify distinct serum lipid signatures in hospitalized COVID-19-positive and COVID-19-negative patients

BACKGROUND

Lipids are involved in the interaction between viral infection and the host metabolic and immunological responses. Several studies comparing the lipidome of COVID-19-positive hospitalized patients vs. healthy subjects have already been reported. It is largely unknown, however, whether these differences are specific to this disease. The present study compared the lipidomic signature of hospitalized COVID-19-positive patients with that of healthy subjects, as well as with COVID-19-negative patients hospitalized for other infectious/inflammatory diseases.

METHODS

We analyzed the lipidomic signature of 126 COVID-19-positive patients, 45 COVID-19-negative patients hospitalized with other infectious/inflammatory diseases and 50 healthy volunteers. A semi-targeted lipidomics analysis was performed using liquid chromatography coupled to mass spectrometry. Two-hundred and eighty-three lipid species were identified and quantified. Results were interpreted by machine learning tools.

RESULTS

We identified acylcarnitines, lysophosphatidylethanolamines, arachidonic acid and oxylipins as the most altered species in COVID-19-positive patients compared to healthy volunteers. However, we found similar alterations in COVID-19-negative patients who had other causes of inflammation. Conversely, lysophosphatidylcholine 22:6-sn2, phosphatidylcholine 36:1 and secondary bile acids were the parameters that had the greatest capacity to discriminate between COVID-19-positive and COVID-19-negative patients.

CONCLUSION

This study shows that COVID-19 infection shares many lipid alterations with other infectious/inflammatory diseases, and which differentiate them from the healthy population. The most notable alterations were observed in oxylipins, while alterations in bile acids and glycerophospholipis best distinguished between COVID-19-positive and COVID-19-negative patients. Our results highlight the value of integrating lipidomics with machine learning algorithms to explore the pathophysiology of COVID-19 and, consequently, improve clinical decision making.

Clinical and Laboratory Approach to Diagnose COVID-19 Using Machine Learning

Coronavirus 2 (SARS-CoV-2), often known by the name COVID-19, is a type of acute respiratory syndrome that has had a significant influence on both economy and health infrastructure worldwide. This novel virus is diagnosed utilising a conventional method known as the RT-PCR (Reverse Transcription Polymerase Chain Reaction) test. This approach, however, produces a lot of false-negative and erroneous outcomes. According to recent studies, COVID-19 can also be diagnosed using X-rays, CT scans, blood tests and cough sounds. In this article, we use blood tests and machine learning to predict the diagnosis of this deadly virus. We also present an extensive review of various existing machine-learning applications that diagnose COVID-19 from clinical and laboratory markers. Four different classifiers along with a technique called Synthetic Minority Oversampling Technique (SMOTE) were used for classification. Shapley Additive Explanations (SHAP) method was utilized to calculate the gravity of each feature and it was found that eosinophils, monocytes, leukocytes and platelets were the most critical blood parameters that distinguished COVID-19 infection for our dataset. These classifiers can be utilized in conjunction with RT-PCR tests to improve sensitivity and in emergency situations such as a pandemic outbreak that might happen due to new strains of the virus. The positive results indicate the prospective use of an automated framework that could help clinicians and medical personnel diagnose and screen patients.

Metabolomic Profiling of Plasma Reveals Differential Disease Severity Markers in COVID-19 Patients

The severity, disabilities, and lethality caused by the coronavirus 2019 (COVID-19) disease have dumbfounded the entire world on an unprecedented scale. The multifactorial aspect of the infection has generated interest in understanding the clinical history of COVID-19, particularly the classification of severity and early prediction on prognosis. Metabolomics is a powerful tool for identifying metabolite signatures when profiling parasitic, metabolic, and microbial diseases. This study undertook a metabolomic approach to identify potential metabolic signatures to discriminate severe COVID-19 from non-severe COVID-19. The secondary aim was to determine whether the clinical and laboratory data from the severe and non-severe COVID-19 patients were compatible with the metabolomic findings. Metabolomic analysis of samples revealed that 43 metabolites from 9 classes indicated COVID-19 severity: 29 metabolites for non-severe and 14 metabolites for severe disease. The metabolites from porphyrin and purine pathways were significantly elevated in the severe disease group, suggesting that they could be potential prognostic biomarkers. Elevated levels of the cholesteryl ester CE (18:3) in non-severe patients matched the significantly different blood cholesterol components (total cholesterol and HDL, both p < 0.001) that were detected. Pathway analysis identified 8 metabolomic pathways associated with the 43 discriminating metabolites. Metabolomic pathway analysis revealed that COVID-19 affected glycerophospholipid and porphyrin metabolism but significantly affected the glycerophospholipid and linoleic acid metabolism pathways (p = 0.025 and p = 0.035, respectively). Our results indicate that these metabolomics-based markers could have prognostic and diagnostic potential when managing and understanding the evolution of COVID-19.

Using machine learning for the personalised prediction of revision endoscopic sinus surgery

BACKGROUND

Revision endoscopic sinus surgery (ESS) is often considered for chronic rhinosinusitis (CRS) if maximal conservative treatment and baseline ESS prove insufficient. Emerging research outlines the risk factors of revision ESS. However, accurately predicting revision ESS at the individual level remains uncertain. This study aims to examine the prediction accuracy of revision ESS and to identify the effects of risk factors at the individual level.

METHODS

We collected demographic and clinical variables from the electronic health records of 767 surgical CRS patients ≥16 years of age. Revision ESS was performed on 111 (14.5%) patients. The prediction accuracy of revision ESS was examined by training and validating different machine learning models, while the effects of variables were analysed using the Shapley values and partial dependence plots.

RESULTS

The logistic regression, gradient boosting and random forest classifiers performed similarly in predicting revision ESS. Area under the receiving operating characteristic curve (AUROC) values were 0.744, 0.741 and 0.730, respectively, using data collected from the baseline visit until six months after baseline ESS. The length of time during which data were collected improved the prediction performance. For data collection times of 0, 3, 6 and 12 months after baseline ESS, AUROC values for the logistic regression were 0.682, 0.715, 0.744 and 0.784, respectively. The number of visits before or after baseline ESS, the number of days from the baseline visit to the baseline ESS, patient age, CRS with nasal polyps (CRSwNP), asthma, non-steroidal anti-inflammatory drug exacerbated respiratory disease and immunodeficiency or suspicion of it all associated with revision ESS. Patient age and number of visits before baseline ESS carried non-linear effects for predictions.

CONCLUSIONS

Intelligent data analysis identified important predictors of revision ESS at the individual level, such as the frequency of clinical visits, patient age, Type 2 high diseases and immunodeficiency or a suspicion of it.

Profiling metabolites and lipoproteins in COMETA, an Italian cohort of COVID-19 patients

Metabolomics and lipidomics have been used in several studies to define the biochemical alterations induced by COVID-19 in comparison with healthy controls. Those studies highlighted the presence of a strong signature, attributable to both metabolites and lipoproteins/lipids. Here, 1H NMR spectra were acquired on EDTA-plasma from three groups of subjects: i) hospitalized COVID-19 positive patients (≤21 days from the first positive nasopharyngeal swab); ii) hospitalized COVID-19 positive patients (>21 days from the first positive nasopharyngeal swab); iii) subjects after 2–6 months from SARS-CoV-2 eradication. A Random Forest model built using the EDTA-plasma spectra of COVID-19 patients ≤21 days and Post COVID-19 subjects, provided a high discrimination accuracy (93.6%), indicating both the presence of a strong fingerprint of the acute infection and the substantial metabolic healing of Post COVID-19 subjects. The differences originate from significant alterations in the concentrations of 16 metabolites and 74 lipoprotein components. The model was then used to predict the spectra of COVID-19>21 days subjects. In this group, the metabolite levels are closer to those of the Post COVID-19 subjects than to those of the COVID-19≤21 days; the opposite occurs for the lipoproteins. Within the acute phase patients, characteristic trends in metabolite levels are observed as a function of the disease severity. The metabolites found altered in COVID-19≤21 days patients with respect to Post COVID-19 individuals overlap with acute infection biomarkers identified previously in comparison with healthy subjects. Along the trajectory towards healing, the metabolome reverts back to the “healthy” state faster than the lipoproteome.

Alterations of Urinary Microbial Metabolites and Immune Indexes Linked With COVID-19 Infection and Prognosis

Coronavirus disease 2019 (COVID-19) has evolved into an established global pandemic. Metabolomic studies in COVID-19 patients is worth exploring for further available screening methods. In our study, we recruited a study cohort of 350 subjects comprising 248 COVID-19 patients (161 non-severe cases, 60 asymptomatic cases, and 27 severe cases) and 102 healthy controls (HCs), and herein present data with respect to their demographic features, urinary metabolome, immunological indices, and follow-up health status. We found that COVID-19 resulted in alterations of 39 urinary, mainly microbial, metabolites. Using random forest analysis, a simplified marker panel including three microbial metabolites (oxoglutaric acid, indoxyl, and phenylacetamide) was constructed (AUC=0.963, 95% CI, 0.930-0.983), which exhibited higher diagnostic performance than immune feature-based panels between COVID-19 and HC groups (P<0.0001). Meanwhile, we observed that urine metabolic markers enabled discriminating asymptomatic patients (ASY) from HCs (AUC = 0.981, 95% CI, 0.946-0.996), and predicting the incidence of high-risk sequalae in COVID-19 individuals (AUC=0.931, 95% CI, 0.877-0.966). Co-expression network analysis showed that 13 urinary microbial metabolites (e.g., oxoglutaric acid) were significantly correlated with alterations of CD4⁺, CD3⁺, and CD8⁺ T-cells, as well as IFN-γ, IL-2 and IL-4 levels, suggesting close interactions between microbial metabolites and host immune dysregulation in COVID-19. Taken together, our findings indicate that urinary metabolites may have promising potential for screening of COVID-19 in different application scenarios, and provide a new entry point to understand the microbial metabolites and related immune dysfunction in COVID-19.

MALDI-TOF mass spectrometry of saliva samples as a prognostic tool for COVID-19

Background

Methods

Results

Conclusion

MS-based targeted profiling of oxylipins in COVID-19: A new insight into inflammation regulation

The key role of inflammation in COVID-19 induced many authors to study the cytokine storm, whereas the role of other inflammatory mediators such as oxylipins is still poorly understood. IMPRECOVID was a monocentric retrospective observational pilot study with COVID-19 related pneumonia patients (n = 52) admitted to Pisa University Hospital between March and April 2020. Our MS-based analytical platform permitted the simultaneous determination of sixty plasma oxylipins in a single run at ppt levels for a comprehensive characterisation of the inflammatory cascade in COVID-19 patients. The datasets containing oxylipin and cytokine plasma levels were analysed by principal component analysis (PCA), computation of Fisher's canonical variable, and a multivariate receiver operating characteristic (ROC) curve. Differently from cytokines, the panel of oxylipins clearly differentiated samples collected in COVID-19 wards (n = 43) and Intensive Care Units (ICUs) (n = 27), as shown by the PCA and the multivariate ROC curve with a resulting AUC equal to 0.92. ICU patients showed lower (down to two orders of magnitude) plasma concentrations of anti-inflammatory and pro-resolving lipid mediators, suggesting an impaired inflammation response as part of a prolonged and unsolvable pro-inflammatory status. In conclusion, our targeted oxylipidomics platform helped shedding new light in this field. Targeting the lipid mediator class switching is extremely important for a timely picture of a patient's ability to respond to the viral attack. A prediction model exploiting selected lipid mediators as biomarkers seems to have good chances to classify patients at risk of severe COVID-19.

Metabolic Snapshot of Plasma Samples Reveals New Pathways Implicated in SARS-CoV-2 Pathogenesis

Despite the scientific and human efforts to understand COVID-19, there are questions still unanswered. Variations in the metabolic reaction to SARS-CoV-2 infection could explain the striking differences in the susceptibility to infection and the risk of severe disease. Here, we used untargeted metabolomics to examine novel metabolic pathways related to SARS-CoV-2 susceptibility and COVID-19 clinical severity using capillary electrophoresis coupled to a time-of-flight mass spectrometer (CE-TOF-MS) in plasma samples. We included 27 patients with confirmed COVID-19 and 29 healthcare workers heavily exposed to SARS-CoV-2 but with low susceptibility to infection ("nonsusceptible"). We found a total of 42 metabolites of SARS-CoV-2 susceptibility or COVID-19 clinical severity. We report the discovery of new plasma biomarkers for COVID-19 that provide mechanistic explanations for the clinical consequences of SARS-CoV-2, including mitochondrial and liver dysfunction as a consequence of hypoxemia (citrulline, citric acid, and 3-aminoisobutyric acid (BAIBA)), energy production and amino acid catabolism (phenylalanine and histidine), and endothelial dysfunction and thrombosis (citrulline, asymmetric dimethylarginine (ADMA), and 2-aminobutyric acid (2-AB)), and we found interconnections between these pathways. In summary, in this first report several metabolic pathways implicated in SARS-CoV-2 susceptibility and COVID-19 clinical progression were found by CE-MS based metabolomics that could be developed as biomarkers of COVID-19.

Metabolomics study of COVID-19 patients in four different clinical stages

SARS-CoV-2 (severe acute respiratory syndrome coronavirus 2) is the coronavirus strain causing the respiratory pandemic COVID-19 (coronavirus disease 2019). To understand the pathobiology of SARS-CoV-2 in humans it is necessary to unravel the metabolic changes that are produced in the individuals once the infection has taken place. The goal of this work is to provide new information about the altered biomolecule profile and with that the altered biological pathways of patients in different clinical situations due to SARS-CoV-2 infection. This is done via metabolomics using HPLC-QTOF-MS analysis of plasma samples at COVID-diagnose from a total of 145 adult patients, divided into different clinical stages based on their subsequent clinical outcome (25 negative controls (non-COVID); 28 positive patients with asymptomatic disease not requiring hospitalization; 27 positive patients with mild disease defined by a total time in hospital lower than 10 days; 36 positive patients with severe disease defined by a total time in hospital over 20 days and/or admission at the ICU; and 29 positive patients with fatal outcome or deceased). Moreover, follow up samples between 2 and 3 months after hospital discharge were also obtained from the hospitalized patients with mild prognosis. The final goal of this work is to provide biomarkers that can help to better understand how the COVID-19 illness evolves and to predict how a patient could progress based on the metabolites profile of plasma obtained at an early stage of the infection. In the present work, several metabolites were found as potential biomarkers to distinguish between the end-stage and the early-stage (or non-COVID) disease groups. These metabolites are mainly involved in the metabolism of carnitines, ketone bodies, fatty acids, lysophosphatidylcholines/phosphatidylcholines, tryptophan, bile acids and purines, but also omeprazole. In addition, the levels of several of these metabolites decreased to "normal" values at hospital discharge, suggesting some of them as early prognosis biomarkers in COVID-19 at diagnose.

Infection Biomarkers Based on Metabolomics

Current infection biomarkers are highly limited since they have low capability to predict infection in the presence of confounding processes such as in non-infectious inflammatory processes, low capability to predict disease outcomes and have limited applications to guide and evaluate therapeutic regimes. Therefore, it is critical to discover and develop new and effective clinical infection biomarkers, especially applicable in patients at risk of developing severe illness and critically ill patients. Ideal biomarkers would effectively help physicians with better patient management, leading to a decrease of severe outcomes, personalize therapies, minimize antibiotics overuse and hospitalization time, and significantly improve patient survival. Metabolomics, by providing a direct insight into the functional metabolic outcome of an organism, presents a highly appealing strategy to discover these biomarkers. The present work reviews the desired main characteristics of infection biomarkers, the main metabolomics strategies to discover these biomarkers and the next steps for developing the area towards effective clinical biomarkers.

SARS-CoV-2 monitoring by automated target-driven molecular machine-based engineering

Biosensors based on nucleic acid-structured electrochemiluminescence are rapidly developing for medical diagnostics. Here, we build an automated DNA molecular machine on Ti₃C₂/polyethyleneimine-Ru(dcbpy)₃ ²⁺@Au composite, which alters the situation that a DNA molecular machine requires laying down motion tracks. We use this DNA molecular machine to transduce the target concentration information to enhance the electrochemiluminescence signal based on DNA hybridization calculations. Complex bioanalytical processes are centralized in a single nucleic acid probe unit, thus eliminating the tedious steps of laying down motion tracks required by the traditional molecular machine. We found a detection limit of 0.68 pM and a range of 1 pM to 1 nM for the analysis of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) specific DNA target. Recoveries range between 96.4 and 104.8% for the analysis of SARS-CoV-2 in human saliva.

SUPPLEMENTARY INFORMATION

The online version contains supplementary material available at 10.1007/s10311-022-01434-9.

Systematic review with meta-analysis of diagnostic test accuracy for COVID-19 by mass spectrometry

BACKGROUND

The global COVID-19 pandemic has led to extensive development in many fields, including the diagnosis of COVID-19 infection by mass spectrometry. The aim of this systematic review and meta-analysis was to assess the accuracy of mass spectrometry diagnostic tests developed so far, across a wide range of biological matrices, and additionally to assess risks of bias and applicability in studies published to date.

METHOD

23 retrospective observational cohort studies were included in the systematic review using the PRISMA-DTA framework, with a total of 2858 COVID-19 positive participants and 2544 controls. Risks of bias and applicability were assessed via a QUADAS-2 questionnaire. A meta-analysis was also performed focusing on sensitivity, specificity, diagnostic accuracy and Youden's Index, in addition to assessing heterogeneity.

FINDINGS

Sensitivity averaged 0.87 in the studies reviewed herein (interquartile range 0.81-0.96) and specificity 0.88 (interquartile range 0.82-0.98), with an area under the receiver operating characteristic summary curve of 0.93. By subgroup, the best diagnostic results were achieved by viral proteomic analyses of nasopharyngeal swabs and metabolomic analyses of plasma and serum. The performance of other sampling matrices (breath, sebum, saliva) was less good, indicating that these protocols are currently insufficiently mature for clinical application.

CONCLUSIONS

This systematic review and meta-analysis demonstrates the potential for mass spectrometry and 'omics in achieving accurate test results for COVID-19 diagnosis, but also highlights the need for further work to optimize and harmonize practice across laboratories before these methods can be translated to clinical applications.

Metabolomics, Microbiomics, Machine learning during the COVID-19 pandemic

COVID-19 pandemic has a significant impact worldwide, from the point of view of public health, social, and economic aspects. The correct strategies of diagnosis and global management are still under debate. In the next future, we firmly believe that combining the so-called 3 M's (metabolomics, microbiomics, and machine learning [artificial intelligence]) will be the optimal, accurate tool for the early diagnosis of COVID-19 subjects, risk assessment and stratification, patient management, and decision-making. If the currently available preliminary data obtain further confirms, through future studies on larger samples, simple biomarkers will provide predictive models for data analysis and interpretation, allowing a step toward personalized holistic medicine.

Machine Learning Approaches to Analyze MALDI-TOF Mass Spectrometry Protein Profiles

Machine learning is being employed for the development of diagnostic methods for several diseases, but prognostic techniques are still poorly explored. The development of such approaches is essential to assist healthcare workers to ensure the most appropriate treatment for patients. In this chapter, we demonstrate a detailed protocol for the application of machine learning to MALDI-TOF MS spectra of COVID-19-infected plasma samples for risk classification and biomarker identification.

Mass spectrometry applied to diagnosis, prognosis, and therapeutic targets identification for the novel coronavirus SARS-CoV-2: A review

Mass spectrometry (MS) has found numerous applications in medicine and has been widely used in the detection and characterization of biomolecules associated with viral infections such as COVID-19. COVID-19 is a multisystem disease and, therefore, the need arises to carry out a careful and conclusive assessment of the pathophysiological parameters involved in the infection, to develop an effective therapeutic approach, assess the prognosis of the disease, and especially the early diagnosis of the infected population. Thus, the urgent need for highly accurate methods of diagnosis and prognosis of this infection presents new challenges for the development of laboratory medicine, whose methods require sensitivity, speed, and accuracy of the techniques for analyzing the biological markers involved in the infection. In this context, MS stands out as a robust analytical tool, with high sensitivity and selectivity, accuracy, low turnaround time, and versatility for the analysis of biological samples. However, it has not yet been adopted as a frontline clinical laboratory technique. Therefore, this review explores the potential and trends of current MS methods and their contribution to the development of new strategies to COVID-19 diagnosis and prognosis and how this tool can assist in the discovery of new therapeutic targets, in addition, to comment what could be the future of MS in medicine.

Kynurenine and Hemoglobin as Sex-Specific Variables in COVID-19 Patients: A Machine Learning and Genetic Algorithms Approach

Differences in clinical manifestations, immune response, metabolic alterations, and outcomes (including disease severity and mortality) between men and women with COVID-19 have been reported since the pandemic outbreak, making it necessary to implement sex-specific biomarkers for disease diagnosis and treatment. This study aimed to identify sex-associated differences in COVID-19 patients by means of a genetic algorithm (GALGO) and machine learning, employing support vector machine (SVM) and logistic regression (LR) for the data analysis. Both algorithms identified kynurenine and hemoglobin as the most important variables to distinguish between men and women with COVID-19. LR and SVM identified C10:1, cough, and lysoPC a 14:0 to discriminate between men with COVID-19 from men without, with LR being the best model. In the case of women with COVID-19 vs. women without, SVM had a higher performance, and both models identified a higher number of variables, including 10:2, lysoPC a C26:0, lysoPC a C28:0, alpha-ketoglutaric acid, lactic acid, cough, fever, anosmia, and dysgeusia. Our results demonstrate that differences in sexes have implications in the diagnosis and outcome of the disease. Further, genetic and machine learning algorithms are useful tools to predict sex-associated differences in COVID-19.

Early Stage Identification of COVID-19 Patients in Mexico Using Machine Learning: A Case Study for the Tijuana General Hospital

Background: The current pandemic caused by SARS-CoV-2 is an acute illness of global concern. SARS-CoV-2 is an infectious disease caused by a recently discovered coronavirus. Most people who get sick from COVID-19 experience either mild, moderate, or severe symptoms. In order to help make quick decisions regarding treatment and isolation needs, it is useful to determine which significant variables indicate infection cases in the population served by the Tijuana General Hospital (Hospital General de Tijuana). An Artificial Intelligence (Machine Learning) mathematical model was developed in order to identify early-stage significant variables in COVID-19 patients. Methods: The individual characteristics of the study subjects included age, gender, age group, symptoms, comorbidities, diagnosis, and outcomes. A mathematical model that uses supervised learning algorithms, allowing the identification of the significant variables that predict the diagnosis of COVID-19 with high precision, was developed. Results: Automatic algorithms were used to analyze the data: for Systolic Arterial Hypertension (SAH), the Logistic Regression algorithm showed results of 91.0% in area under ROC (AUC), 80% accuracy (CA), 80% F1 and 80% Recall, and 80.1% precision for the selected variables, while for Diabetes Mellitus (DM) with the Logistic Regression algorithm it obtained 91.2% AUC, 89.2% accuracy, 88.8% F1, 89.7% precision, and 89.2% recall for the selected variables. The neural network algorithm showed better results for patients with Obesity, obtaining 83.4% AUC, 91.4% accuracy, 89.9% F1, 90.6% precision, and 91.4% recall. Conclusions: Statistical analyses revealed that the significant predictive symptoms in patients with SAH, DM, and Obesity were more substantial in fatigue and myalgias/arthralgias. In contrast, the third dominant symptom in people with SAH and DM was odynophagia.

Machine Learning of Serum Metabolic Patterns Encodes Asymptomatic SARS-CoV-2 Infection

Asymptomatic COVID-19 has become one of the biggest challenges for controlling the spread of the SARS-CoV-2. Diagnosis of asymptomatic COVID-19 mainly depends on quantitative reverse transcription PCR (qRT-PCR), which is typically time-consuming and requires expensive reagents. The application is limited in countries that lack sufficient resources to handle large-scale assay during the COVID-19 outbreak. Here, we demonstrated a new approach to detect the asymptomatic SARS-CoV-2 infection using serum metabolic patterns combined with ensemble learning. The direct patterns of metabolites and lipids were extracted by matrix-assisted laser desorption/ionization mass spectrometry (MALDI-MS) within 1 s with simple sample preparation. A new ensemble learning model was developed using stacking strategy with a new voting algorithm. This approach was validated in a large cohort of 274 samples (92 asymptomatic COVID-19 and 182 healthy control), and provided the high accuracy of 93.4%, with only 5% false negative and 7% false positive rates. We also identified a biomarker panel of ten metabolites and lipids, as well as the altered metabolic pathways during asymptomatic SARS-CoV-2 Infection. The proposed rapid and low-cost approach holds promise to apply in the large-scale asymptomatic COVID-19 screening.

Distinct lipid metabolic dysregulation in asymptomatic COVID-19

Asymptomatic infection is a big challenge in curbing the spread of COVID-19. However, its identification and pathogenesis elucidation remain issues. Here, by performing comprehensive lipidomic characterization of serum samples from 89 asymptomatic COVID-19 patients and 178 healthy controls, we screened out a panel of 15 key lipids that could accurately identify asymptomatic patients using a new ensemble learning model based on stacking strategy with a voting algorithm. This strategy provided a high accuracy of 96.0% with only 3.6% false positive rate and 4.8% false negative rate. More importantly, the unique lipid metabolic dysregulation was revealed, especially the enhanced synthesis of membrane phospholipids, altered sphingolipids homeostasis, and differential fatty acids metabolic pattern, implicating the specific host immune, inflammatory, and antiviral responses in asymptomatic COVID-19. This study provides a potential prediagnostic method for asymptomatic COVID-19 and molecular clues for the pathogenesis and therapy of this disease.

Rapid Screening of COVID-19 Directly from Clinical Nasopharyngeal Swabs Using the MasSpec Pen

The outbreak of COVID-19 has created an unprecedent global crisis. While the polymerase chain reaction (PCR) is the gold standard method for detecting active SARS-CoV-2 infection, alternative high-throughput diagnostic tests are of a significant value to meet universal testing demands. Here, we describe a new design of the MasSpec Pen technology integrated to electrospray ionization (ESI) for direct analysis of clinical swabs and investigate its use for COVID-19 screening. The redesigned MasSpec Pen system incorporates a disposable sampling device refined for uniform and efficient analysis of swab tips via liquid extraction directly coupled to an ESI source. Using this system, we analyzed nasopharyngeal swabs from 244 individuals including symptomatic COVID-19 positive, symptomatic negative, and asymptomatic negative individuals, enabling rapid detection of rich lipid profiles. Two statistical classifiers were generated based on the lipid information acquired. Classifier 1 was built to distinguish symptomatic PCR-positive from asymptomatic PCR-negative individuals, yielding a cross-validation accuracy of 83.5%, sensitivity of 76.6%, and specificity of 86.6%, and validation set accuracy of 89.6%, sensitivity of 100%, and specificity of 85.3%. Classifier 2 was built to distinguish symptomatic PCR-positive patients from negative individuals including symptomatic PCR-negative patients with moderate to severe symptoms and asymptomatic individuals, yielding a cross-validation accuracy of 78.4%, specificity of 77.21%, and sensitivity of 81.8%. Collectively, this study suggests that the lipid profiles detected directly from nasopharyngeal swabs using MasSpec Pen-ESI mass spectrometry (MS) allow fast (under a minute) screening of the COVID-19 disease using minimal operating steps and no specialized reagents, thus representing a promising alternative high-throughput method for screening of COVID-19.

Application of omics technology to combat the COVID-19 pandemic

As of August 27, 2021, the ongoing pandemic of coronavirus disease 2019 (COVID-19), caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), has spread to over 220 countries, areas, and territories. Thus far, 214,468,601 confirmed cases, including 4,470,969 deaths, have been reported to the World Health Organization. To combat the COVID-19 pandemic, multiomics-based strategies, including genomics, transcriptomics, proteomics, and metabolomics, have been used to study the diagnosis methods, pathogenesis, prognosis, and potential drug targets of COVID-19. In order to help researchers and clinicians to keep up with the knowledge of COVID-19, we summarized the most recent progresses reported in omics-based research papers. This review discusses omics-based approaches for studying COVID-19, summarizing newly emerged SARS-CoV-2 variants as well as potential diagnostic methods, risk factors, and pathological features of COVID-19. This review can help researchers and clinicians gain insight into COVID-19 features, providing direction for future drug development and guidance for clinical treatment, so that patients can receive appropriate treatment as soon as possible to reduce the risk of disease progression.

Genome-scale metabolic modelling of SARS-CoV-2 in cancer cells reveals an increased shift to glycolytic energy production

Cancer is considered a high‐risk condition for severe illness resulting from COVID‐19. The interaction between severe acute respiratory syndrome coronavirus‐2 (SARS‐CoV‐2) and human metabolism is key to elucidating the risk posed by COVID‐19 for cancer patients and identifying effective treatments, yet it is largely uncharacterised on a mechanistic level. We present a genome‐scale map of short‐term metabolic alterations triggered by SARS‐CoV‐2 infection of cancer cells. Through transcriptomic‐ and proteomic‐informed genome‐scale metabolic modelling, we characterise the role of RNA and fatty acid biosynthesis in conjunction with a rewiring in energy production pathways and enhanced cytokine secretion. These findings link together complementary aspects of viral invasion of cancer cells, while providing mechanistic insights that can inform the development of treatment strategies.

Longitudinal metabolomics of human plasma reveals prognostic markers of COVID-19 disease severity

There is an urgent need to identify which COVID-19 patients will develop life-threatening illness so that medical resources can be optimally allocated and rapid treatment can be administered early in the disease course, when clinical management is most effective. To aid in the prognostic classification of disease severity, we perform untargeted metabolomics on plasma from 339 patients, with samples collected at six longitudinal time points. Using the temporal metabolic profiles and machine learning, we build a predictive model of disease severity. We discover that a panel of metabolites measured at the time of study entry successfully determines disease severity. Through analysis of longitudinal samples, we confirm that most of these markers are directly related to disease progression and that their levels return to baseline upon disease recovery. Finally, we validate that these metabolites are also altered in a hamster model of COVID-19.

Comparison of machine learning techniques to handle imbalanced COVID-19 CBC datasets

The Coronavirus pandemic caused by the novel SARS-CoV-2 has significantly impacted human health and the economy, especially in countries struggling with financial resources for medical testing and treatment, such as Brazil's case, the third most affected country by the pandemic. In this scenario, machine learning techniques have been heavily employed to analyze different types of medical data, and aid decision making, offering a low-cost alternative. Due to the urgency to fight the pandemic, a massive amount of works are applying machine learning approaches to clinical data, including complete blood count (CBC) tests, which are among the most widely available medical tests. In this work, we review the most employed machine learning classifiers for CBC data, together with popular sampling methods to deal with the class imbalance. Additionally, we describe and critically analyze three publicly available Brazilian COVID-19 CBC datasets and evaluate the performance of eight classifiers and five sampling techniques on the selected datasets. Our work provides a panorama of which classifier and sampling methods provide the best results for different relevant metrics and discuss their impact on future analyses. The metrics and algorithms are introduced in a way to aid newcomers to the field. Finally, the panorama discussed here can significantly benefit the comparison of the results of new ML algorithms.

High-Throughput Salivary Metabolite Profiling on an Ultralow Noise Tip-Enhanced Laser Desorption Ionization Mass Spectrometry Platform for Noninvasive Diagnosis of Early Lung Cancer

Lung cancer (LC) is a widespread cancer that is the cause of the highest mortality rate accounting for 25% of all cancer deaths. To date, most LC patients are diagnosed at the advanced stage owing to the lack of obvious symptoms in the early stage and the limitations of current clinical diagnostic techniques. Therefore, developing a high throughput technique for early screening is of great importance. In this work, we established an effective and rapid salivary metabolic analysis platform for early LC diagnosis and combined metabolomics and transcriptomics to reveal the metabolic fluctuations correlated to LC. Saliva samples were collected from a total of 150 volunteers including 89 patients with early LC, 11 patients with advanced LC, and 50 healthy controls. The metabolic profiling of noninvasive samples was investigated on an ultralow noise TELDI-MS platform. In addition, data normalization methods were screened and assessed to overcome the MS signal variation caused by individual difference for biomarker mining. For untargeted metabolic profiling of saliva samples, around 264 peaks could be reliably detected in each sample. After multivariate analysis, 23 metabolites were sorted out and verified to be related to the dysfunction of the amino acid and nucleotide metabolism in early LC. Notably, transcriptomic data from online TCGA repository were utilized to support findings from the salivary metabolomics experiment, including the disorder of amino acid biosynthesis and amino acid metabolism. Based on the verified differential metabolites, early LC patients could be clearly distinguished from healthy controls with a sensitivity of 97.2% and a specificity of 92%. The ultralow noise TELDI-MS platform displayed satisfactory ability to explore salivary metabolite information and discover potential biomarkers that may help develop a noninvasive screening tool for early LC.

The snapshot of metabolic health in evaluating micronutrient status, the risk of infection and clinical outcome of COVID-19

COVID-19 has re-established the significance of analyzing the organism through a metabolic perspective to uncover the dynamic interconnections within the biological systems. The role of micronutrient status and metabolic health emerge as pivotal in COVID-19 pathogenesis and the immune system's response. Metabolic disruption, proceeding from modifiable factors, has been proposed as a significant risk factor accounting for infection susceptibility, disease severity and risk for post-COVID complications. Metabolomics, the comprehensive study and quantification of intermediates and products of metabolism, is a rapidly evolving field and a novel tool in biomarker discovery. In this article, we propose that leveraging insulin resistance biomarkers along with biomarkers of micronutrient deficiencies, will allow for a diagnostic window and provide functional therapeutic targets. Specifically, metabolomics can be applied as: a. At-home test to assess the risk of infection and propose nutritional support, b. A screening tool for high-risk COVID-19 patients to develop serious illness during hospital admission and prioritize medical support, c(i). A tool to match nutritional support with specific nutrient requirements for mildly ill patients to reduce the risk for hospitalization, and c(ii). for critically ill patients to reduce recovery time and risk of post-COVID complications, d. At-home test to monitor metabolic health and reduce post-COVID symptomatology. Metabolic rewiring offers potential virtues towards disease prevention, dissection of high-risk patients, taking actionable therapeutic measures, as well as shielding against post-COVID syndrome.

A machine learning PROGRAM to identify COVID-19 and other diseases from hematology data

AIM

We propose a method for screening full blood count metadata for evidence of communicable and noncommunicable diseases using machine learning (ML).

MATERIALS & METHODS

High dimensional hematology metadata was extracted over an 11-month period from Sysmex hematology analyzers from 43,761 patients. Predictive models for age, sex and individuality were developed to demonstrate the personalized nature of hematology data. Both numeric and raw flow cytometry data were used for both supervised and unsupervised ML to predict the presence of pneumonia, urinary tract infection and COVID-19. Heart failure was used as an objective to prove method generalizability.

RESULTS

Chronological age was predicted by a deep neural network with R2: 0.59; mean absolute error: 12; sex with AUROC: 0.83, phi: 0.47; individuality with 99.7% accuracy, phi: 0.97; pneumonia with AUROC: 0.74, sensitivity 58%, specificity 79%, 95% CI: 0.73-0.75, p < 0.0001; urinary tract infection AUROC: 0.68, sensitivity 52%, specificity 79%, 95% CI: 0.67-0.68, p < 0.0001; COVID-19 AUROC: 0.8, sensitivity 82%, specificity 75%, 95% CI: 0.79-0.8, p = 0.0006; and heart failure area under the receiver operator curve (AUROC): 0.78, sensitivity 72%, specificity 72%, 95% CI: 0.77-0.78; p < 0.0001.

CONCLUSION

ML applied to hematology data could predict communicable and noncommunicable diseases, both at local and global levels.

Could metabolomics drive the fate of COVID-19 pandemic? A narrative review on lights and shadows

Human Severe Acute Respiratory Syndrome CoronaVirus 2 (SARS-CoV-2) infection activates a complex interaction host/virus, leading to the reprogramming of the host metabolism aimed at the energy supply for viral replication. Alterations of the host metabolic homeostasis strongly influence the immune response to SARS-CoV-2, forming the basis of a wide range of outcomes, from the asymptomatic infection to the onset of COVID-19 and up to life-threatening acute respiratory distress syndrome, vascular dysfunction, multiple organ failure, and death. Deciphering the molecular mechanisms associated with the individual susceptibility to SARS-CoV-2 infection calls for a system biology approach; this strategy can address multiple goals, including which patients will respond effectively to the therapeutic treatment. The power of metabolomics lies in the ability to recognize endogenous and exogenous metabolites within a biological sample, measuring their concentration, and identifying perturbations of biochemical pathways associated with qualitative and quantitative metabolic changes. Over the last year, a limited number of metabolomics- and lipidomics-based clinical studies in COVID-19 patients have been published and are discussed in this review. Remarkable alterations in the lipid and amino acid metabolism depict the molecular phenotype of subjects infected by SARS-CoV-2; notably, structural and functional data on the lipids-virus interaction may open new perspectives on targeted therapeutic interventions. Several limitations affect most metabolomics-based studies, slowing the routine application of metabolomics. However, moving metabolomics from bench to bedside cannot imply the mere determination of a given metabolite panel; rather, slotting metabolomics into clinical practice requires the conversion of metabolic patient-specific data into actionable clinical applications.

Metabolic shift of chronic myeloid leukemia patients under imatinib-pioglitazone regimen and discontinuation

The Estudo de Descontinuação de Imatinibe após Pioglitazona (EDI-PIO) is a single-center, longitudinal, prospective, phase 2, non-randomized, open, clinical trial (NCT02852486, August 2, 2016 retrospectively registered) for the discontinuation of imatinib after concomitant use of pioglitazone, being the first of its kind in a Brazilian population with chronic myeloid leukemia. Due to remaining of leukemic quiescent cells that are not affected by tyrosine kinase inhibitors, it has been suggested the use of pioglitazone, a PPARγ agonist, together with imatinib as a strategy for the maintenance of deep molecular response. The clinical benefit to this association is still controversial, and the metabolic alteration along this process remains unclear. Therefore, we applied a metabolomic protocol using high-resolution mass spectrometry to profile plasmatic metabolic response of a prospective cohort of ten individuals under discontinuation of imatinib and pioglitazone protocol. By comparing patients under pioglitazone and imatinib treatment with imatinib monotherapy and discontinuation phase, we were able to annotate 41 and 36 metabolites, respectively. The metabolic alterations observed during imatinib-pioglitazone combined therapy are associated with an extensive lipid remodeling, with activation of β-oxidation pathway, in addition to the presence of markers that suggest mitochondrial dysfunction.

Metabolomics in the Diagnosis and Prognosis of COVID-19

Coronavirus disease 2019 (COVID-19) pandemic triggered an unprecedented global effort in developing rapid and inexpensive diagnostic and prognostic tools. Since the genome of SARS-CoV-2 was uncovered, detection of viral RNA by RT-qPCR has played the most significant role in preventing the spread of the virus through early detection and tracing of suspected COVID-19 cases and through screening of at-risk population. However, a large number of alternative test methods based on SARS-CoV-2 RNA or proteins or host factors associated with SARS-CoV-2 infection have been developed and evaluated. The application of metabolomics in infectious disease diagnostics is an evolving area of science that was boosted by the urgency of COVID-19 pandemic. Metabolomics approaches that rely on the analysis of volatile organic compounds exhaled by COVID-19 patients hold promise for applications in a large-scale screening of population in point-of-care (POC) setting. On the other hand, successful application of mass-spectrometry to detect specific spectral signatures associated with COVID-19 in nasopharyngeal swab specimens may significantly save the cost and turnaround time of COVID-19 testing in the diagnostic microbiology and virology laboratories. Active research is also ongoing on the discovery of potential metabolomics-based prognostic markers for the disease that can be applied to serum or plasma specimens. Several metabolic pathways related to amino acid, lipid and energy metabolism were found to be affected by severe disease with COVID-19. In particular, tryptophan metabolism via the kynurenine pathway were persistently dysregulated in several independent studies, suggesting the roles of several metabolites of this pathway such as tryptophan, kynurenine and 3-hydroxykynurenine as potential prognostic markers of the disease. However, standardization of the test methods and large-scale clinical validation are necessary before these tests can be applied in a clinical setting. With rapidly expanding data on the metabolic profiles of COVID-19 patients with varying degrees of severity, it is likely that metabolomics will play an important role in near future in predicting the outcome of the disease with a greater degree of certainty.

Targeted metabolomics identifies high performing diagnostic and prognostic biomarkers for COVID-19

Research exploring the development and outcome of COVID-19 infections has led to the need to find better diagnostic and prognostic biomarkers. This cross-sectional study used targeted metabolomics to identify potential COVID-19 biomarkers that predicted the course of the illness by assessing 110 endogenous plasma metabolites from individuals admitted to a local hospital for diagnosis/treatment. Patients were classified into four groups (≈ 40 each) according to standard polymerase chain reaction (PCR) COVID-19 testing and disease course: PCR-/controls (i.e., non-COVID controls), PCR+/not-hospitalized, PCR+/hospitalized, and PCR+/intubated. Blood samples were collected within 2 days of admission/PCR testing. Metabolite concentration data, demographic data and clinical data were used to propose biomarkers and develop optimal regression models for the diagnosis and prognosis of COVID-19. The area under the receiver operating characteristic curve (AUC; 95% CI) was used to assess each models' predictive value. A panel that included the kynurenine: tryptophan ratio, lysoPC a C26:0, and pyruvic acid discriminated non-COVID controls from PCR+/not-hospitalized (AUC = 0.947; 95% CI 0.931-0.962). A second panel consisting of C10:2, butyric acid, and pyruvic acid distinguished PCR+/not-hospitalized from PCR+/hospitalized and PCR+/intubated (AUC = 0.975; 95% CI 0.968-0.983). Only lysoPC a C28:0 differentiated PCR+/hospitalized from PCR+/intubated patients (AUC = 0.770; 95% CI 0.736-0.803). If additional studies with targeted metabolomics confirm the diagnostic value of these plasma biomarkers, such panels could eventually be of clinical use in medical practice.

Immune age and biological age as determinants of vaccine responsiveness among elderly populations: the Human Immunomics Initiative research program

The Human Immunomics Initiative (HII), a joint project between the Harvard T.H. Chan School of Public Health and the Human Vaccines Project (HVP), focuses on studying immunity and the predictability of immuneresponsiveness to vaccines in aging populations. This paper describes the hypotheses and methodological approaches of this new collaborative initiative. Central to our thinking is the idea that predictors of age-related non-communicable diseases are the same as predictors for infectious diseases like COVID-19 and influenza. Fundamental to our approach is to differentiate between chronological, biological and immune age, and to use existing large-scale population cohorts. The latter provide well-typed phenotypic data on individuals’ health status over time, readouts of routine clinical biochemical biomarkers to determine biological age, and bio-banked plasma samples to deep phenotype humoral immune responses as biomarkers of immune age. The first phase of the program involves 1. the exploration of biological age, humoral biomarkers of immune age, and genetics in a large multigenerational cohort, and 2. the subsequent development of models of immunity in relation to health status in a second, prospective cohort of an aging population. In the second phase, vaccine responses and efficacy of licensed COVID-19 vaccines in the presence and absence of influenza-, pneumococcal- and pertussis vaccines routinely offered to elderly, will be studied in older aged participants of prospective population-based cohorts in different geographical locations who will be selected for representing distinct biological and immune ages. The HII research program is aimed at relating vaccine responsiveness to biological and immune age, and identifying aging-related pathways crucial to enhance vaccine effectiveness in aging populations.

The remodel of the "central dogma": a metabolomics interaction perspective

BACKGROUND

In 1957, Francis Crick drew a linear diagram on a blackboard. This diagram is often called the "central dogma." Subsequently, the relationships between different steps of the "central dogma" have been shown to be considerably complex, mostly because of the emerging world of small molecules. It is noteworthy that metabolites can be generated from the diet through gut microbiome metabolism, serve as substrates for epigenetic modifications, destabilize DNA quadruplexes, and follow Lamarckian inheritance. Small molecules were once considered the missing link in the "central dogma"; however, recently they have acquired a central role, and their general perception as downstream products has become reductionist. Metabolomics is a large-scale analysis of metabolites, and this emerging field has been shown to be the closest omics associated with the phenotype and concomitantly, the basis for all omics.

AIM OF REVIEW

Herein, we propose a broad updated perspective for the flux of information diagram centered in metabolomics, including the influence of other factors, such as epigenomics, diet, nutrition, and the gut- microbiome.

KEY SCIENTIFIC CONCEPTS OF REVIEW

Metabolites are the beginning and the end of the flux of information.