Related Experiment Video
Updated: Jul 13, 2026
Using a Pan-Viral Microarray Assay Virochip to Screen Clinical Samples for Viral Pathogens
Published on: April 27, 2011
A Novel 3-Gene Signature for Identifying COVID-19 Patients Based on Bioinformatics and Machine Learning
Guichuan Lai1, Hui Liu1, Jielian Deng1
1Department of Epidemiology and Health Statistics, School of Public Health, Chongqing Medical University, Yixue Road, Chongqing 400016, China.
Insights
A new three-gene signature, including CLEC4D, DUSP13, and UNC5A, accurately identifies COVID-19 patients. This discovery offers potential new biomarkers for coronavirus disease 2019 diagnosis and immune cell analysis.
Area of Science:
- Immunology
- Genomics
- Bioinformatics
Background:
- Biomarkers for coronavirus disease 2019 (COVID-19) are crucial, yet signatures linked to immune cell infiltration remain underdeveloped.
- Understanding the immune cell landscape in COVID-19 is key to developing diagnostic and prognostic tools.
Purpose of the Study:
- To develop a novel immune cell-based gene signature for identifying COVID-19 patients.
- To identify key immune cells and genes associated with COVID-19 pathogenesis.
Main Methods:
- Utilized CIBERSORT for immune cell fraction analysis and WGCNA for identifying key gene modules.
- Employed Gene Ontology (GO) enrichment analysis for biological function discovery.
- Applied Boruta and LASSO algorithms for gene screening and collinearity reduction, followed by multivariate logistic regression for signature development.
Main Results:
- Identified M0 macrophages and neutrophils as critical immune cells in COVID-19, with high predictive values (PRAUC > 0.89).
- Selected 43 intersected genes involved in immune activities, leading to a three-gene signature (CLEC4D, DUSP13, UNC5A).
- The signature demonstrated high accuracy in distinguishing COVID-19 patients from controls across training, internal, and external test sets (ROCAUC up to 0.974).
Conclusions:
- A robust three-gene signature comprising CLEC4D, DUSP13, and UNC5A was successfully constructed for COVID-19 identification.
- These genes represent potential novel biomarkers for diagnosing COVID-19 and understanding its immune-related aspects.
Abstract:
Although many biomarkers associated with coronavirus disease 2019 (COVID-19) were found, a novel signature relevant to immune cells has not been developed. In this work, the "CIBERSORT" algorithm was used to assess the fraction of immune infiltrating cells in GSE152641 and GSE171110. Key modules associated with important immune cells were selected by the "WGCNA" package. The "GO" enrichment analysis was used to reveal the biological function associated with COVID-19. The "Boruta" algorithm was used to screen candidate genes, and the "LASSO" algorithm was used for collinearity reduction. A novel gene signature was developed based on multivariate logistic regression analysis. Subsequently, M0 macrophages (PRAUC = 0.948 in GSE152641 and PRAUC = 0.981 in GSE171110) and neutrophils (PRAUC = 0.892 in GSE152641 and PRAUC = 0.960 in GSE171110) were considered as important immune cells. Forty-three intersected genes from two modules were selected, which mainly participated in some immune-related activities. Finally, a three-gene signature comprising CLEC4D, DUSP13, and UNC5A that can accurately distinguish COVID-19 patients and healthy controls in three datasets was constructed. The ROCAUC was 0.974 in the training set, 0.946 in the internal test set, and 0.709 in the external test set. In conclusion, we constructed a three-gene signature to identify COVID-19, and CLEC4D, DUSP13, and UNC5A may be potential biomarkers for COVID-19 patients.
Related Concept Videos
01:05Single Nucleotide Polymorphisms-SNPs
01:25Rapid Identification of Pathogens