Comprehensive characterization of costimulatory molecule gene for diagnosis, prognosis and recognition of immune microenvironment features in sepsis

The present study, which involved 10 GEO datasets and 3 ArrayExpress datasets, comprehensively characterized the potential effects of CMGs in sepsis. Based on machine learning algorithms (Lasso, SVM and ANN), the CMG classifier was constructed by integrating 6 hub CMGs (CD28, CD40, LTB, TMIGD2, TNFR...

Full description

Saved in:
Bibliographic Details
Published in:Clinical immunology (Orlando, Fla.) Fla.), 2022-12, Vol.245, p.109179-109179, Article 109179
Main Authors: Chen, Zhen, Dong, Xinhuai, Liu, Genglong, Ou, Yangpeng, Lu, Chuangang, Yang, Ben, Zhu, Xuelian, Zuo, Liuer
Format: Article
Language:English
Subjects:
Algorithms
CD28 Antigens
CD40 Antigens
Costimulatory molecule
Humans
Immune microenvironment
Machine learning approach
Multi-transcriptome
OX40 Ligand
Prognosis
sepsis
Sepsis - diagnosis
Sepsis - genetics
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The present study, which involved 10 GEO datasets and 3 ArrayExpress datasets, comprehensively characterized the potential effects of CMGs in sepsis. Based on machine learning algorithms (Lasso, SVM and ANN), the CMG classifier was constructed by integrating 6 hub CMGs (CD28, CD40, LTB, TMIGD2, TNFRSF13C and TNFSF4). The CMG classifier exhibit excellent diagnostic values across multiple datasets and time points, and was able to distinguish sepsis from other critical diseases. The CMG classifier performed better in predicting mortality than other clinical characteristics or endotypes. More importantly, from clinical specimens, the CMG classifier showed more superior diagnostic values than PCT and CRP. Alternatively, the CMG classifier/hub CMGs is significantly correlated with immune cells infiltration (B cells, T cells, Tregs, and MDSC), pivotal immune and molecular pathways (inflammation-promoting, complement and coagulation cascades), and several cytokines. Collectively, CMG classifier was a robust tool for diagnosis, prognosis and recognition of immune microenvironment features in sepsis. [Display omitted] •Currently, the role of costimulatory molecules in sepsis remains largely elusive.•Based on machine learning algorithms (Lasso, SVM and ANN), we identify 6 sepsis-specific CMGs.•The predictive performance of our CMG classifier was superior to the classical SRS endotypes and MARS phenotypes.•The CMG classifier could efficiently reflect the immune microenvironment in sepsis.•More importantly, the CMG classifier showed superior diagnostic values than PCT and CRP.
ISSN:1521-6616
1521-7035
DOI:10.1016/j.clim.2022.109179