Dataset Information

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

ABSTRACT: 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.

SUBMITTER: Wan Q

PROVIDER: S-EPMC8517325 | biostudies-literature | 2021

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Wan Qiongqiong Q Chen Moran M Zhang Zheng Z Yuan Yu Y Wang Hao H Hao Yanhong Y Nie Wenjing W Wu Liang L Chen Suming S

Frontiers in chemistry 20211001

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 s ...[more]

PMID: 34660538

Similar Datasets

Project description:Coronavirus disease (COVID-19) is a contagious respiratory disease that is causing significant global morbidity and mortality. Understanding the impact of the Severe Acute Respiratory Syndrome Coronavirus-2 (SARS-CoV-2) infection on the host metabolism is still in its infancy but of great importance. Herein, we investigated the metabolic response during viral shedding and post-shedding in an asymptomatic SARS-CoV-2 ferret model (n = 6) challenged with two SARS-CoV-2 isolates. Virological and metabolic analyses were performed on (minimally invasive) collected oral swabs, rectal swabs, and nasal washes. Fragments of SARS-CoV-2 RNA were only found in the nasal wash samples in four of the six ferrets, and in the samples collected 3 to 9 days post-infection (referred to as viral shedding). Central carbon metabolism metabolites were analyzed during viral shedding and post-shedding periods using a dynamic Multiple Reaction Monitoring (dMRM) database and method. Subsequent untargeted metabolomics and lipidomics of the same samples were performed using a Liquid Chromatography Quadrupole Time-of-Flight Mass Spectrometry (LC-QToF-MS) methodology, building upon the identified differentiated central carbon metabolism metabolites. Multivariate analysis of the acquired data identified 29 significant metabolites and three lipids that were subjected to pathway enrichment and impact analysis. The presence of viral shedding coincided with the challenge dose administered and significant changes in the citric acid cycle, purine metabolism, and pentose phosphate pathways, amongst others, in the host nasal wash samples. An elevated immune response in the host was also observed between the two isolates studied. These results support other metabolomic-based findings in clinical observational studies and indicate the utility of metabolomics applied to ferrets for further COVID-19 research that advances early diagnosis of asymptomatic and mild clinical COVID-19 infections, in addition to assessing the effectiveness of new or repurposed drug therapies.

Project description:ImportanceReal-world evidence of SARS-CoV-2 transmission is needed to understand the prevalence of infection in the Japanese population.ObjectiveTo conduct sentinel screening of the Japanese population to determine the prevalence of SARS-CoV-2 infection in asymptomatic individuals, with complementary analysis for symptomatic patients as reported by active epidemiologic surveillance used by the government.Design, setting, and participantsThis cross-sectional study of a sentinel screening program investigated approximately 1 million asymptomatic individuals with polymerase chain reaction (PCR) testing for SARS-CoV-2 infection between February 22 and December 8, 2021. Participants included children, students, employed adults, and older individuals, as well as volunteers to broadly reflect the general Japanese population in the 14 prefectures of Japan that declared a state of emergency. Saliva samples and a cycle threshold (Ct) value of approximately 40 as standard in Japan were used. Polymerase chain reaction testing for symptomatic patients was separately done by public health authorities, and the results were obtained from the Ministry of Health, Labour, and Welfare of Japan to complement data on asymptomatic infections from the present study.Main outcomes and measuresTemporal trends in positivity and prevalence (including surges of different variants) and demographic associations (eg, age, geographic location, and vaccination status) were assessed.ResultsThe positive rate of SARS-CoV-2 infection in 1 082 976 asymptomatic individuals (52.08% males; mean [SD] age 39.4 [15.7] years) was 0.03% (95% CI, 0.02%-0.05%) during periods without surges and a maximum of 0.33% (95% CI, 0.25%-0.43%) during peak surges at the Japanese standard Ct value of approximately 40; however, the positive rate would have been 10-fold less at a Ct value of 25 as used elsewhere in the world (eg, UK). There was an increase in patients with a positive PCR test result with a Ct value of 25 or 30 preceding surges in infection and hotspots of asymptomatic infections.Conclusions and relevanceIn this cross-sectional study of asymptomatic SARS-CoV-2 infection in the general population of Japan in 2021, as investigated by sentinel surveillance, a low rate of infection was seen in the Japanese population compared with reported levels elsewhere in the world. This finding provides real-world data on the state of infection in Japan.

Dataset Information

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

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets