Predicting patients with septic shock and sepsis through analyzing whole-blood expression of NK cell-related hub genes using an advanced machine learning framework

Simple item page
dc.contributor.authorDu, Chaoen
dc.contributor.authorTan, Stephanie C.en
dc.contributor.authorBu, Heng-Fuen
dc.contributor.authorSubramanian, Saravananen
dc.contributor.authorGeng, Huaen
dc.contributor.authorWang, Xiaoen
dc.contributor.authorXie, Hehuangen
dc.contributor.authorWu, Xiaoweien
dc.contributor.authorZhou, Tingfaen
dc.contributor.authorLiu, Ruijinen
dc.contributor.authorXu, Zhenen
dc.contributor.authorLiu, Bingen
dc.contributor.authorTan, Xiao-Dien
dc.date.accessioned2025-01-03T15:41:51Zen
dc.date.available2025-01-03T15:41:51Zen
dc.date.issued2024-11-28en
dc.description.abstractBackground: Sepsis is a life-threatening condition that causes millions of deaths globally each year. The need for biomarkers to predict the progression of sepsis to septic shock remains critical, with rapid, reliable methods still lacking. Transcriptomics data has recently emerged as a valuable resource for disease phenotyping and endotyping, making it a promising tool for predicting disease stages. Therefore, we aimed to establish an advanced machine learning framework to predict sepsis and septic shock using transcriptomics datasets with rapid turnaround methods. Methods: We retrieved four NCBI GEO transcriptomics datasets previously generated from peripheral blood samples of healthy individuals and patients with sepsis and septic shock. The datasets were processed for bioinformatic analysis and supplemented with a series of bench experiments, leading to the identification of a hub gene panel relevant to sepsis and septic shock. The hub gene panel was used to establish a novel prediction model to distinguish sepsis from septic shock through a multistage machine learning pipeline, incorporating linear discriminant analysis, risk score analysis, and ensemble method combined with Least Absolute Shrinkage and Selection Operator analysis. Finally, we validated the prediction model with the hub gene dataset generated by RT-qPCR using peripheral blood samples from newly recruited patients. Results: Our analysis led to identify six hub genes (GZMB, PRF1, KLRD1, SH2D1A, LCK, and CD247) which are related to NK cell cytotoxicity and septic shock, collectively termed 6-HubGss. Using this panel, we created SepxFindeR, a machine learning model that demonstrated high accuracy in predicting sepsis and septic shock and distinguishing septic shock from sepsis in a cross-database context. Remarkably, the SepxFindeR model proved compatible with RT-qPCR datasets based on the 6-HubGss panel, facilitating the identification of newly recruited patients with sepsis and septic shock. Conclusions: Our bioinformatic approach led to the discovery of the 6-HubGss biomarker panel and the development of the SepxFindeR machine learning model, enabling accurate prediction of septic shock and distinction from sepsis with rapid processing capabilities.en
dc.description.versionPublished versionen
dc.format.extent15 page(s)en
dc.format.mimetypeapplication/pdfen
dc.identifierARTN 1493895 (Article number)en
dc.identifier.doihttps://doi.org/10.3389/fimmu.2024.1493895en
dc.identifier.eissn1664-3224en
dc.identifier.issn1664-3224en
dc.identifier.orcidWu, Xiaowei [0000-0001-9916-3624]en
dc.identifier.orcidXie, Hehuang [0000-0001-5739-1653]en
dc.identifier.pmid39669564en
dc.identifier.urihttps://hdl.handle.net/10919/123889en
dc.identifier.volume15en
dc.language.isoenen
dc.publisherFrontiersen
dc.relation.urihttps://www.ncbi.nlm.nih.gov/pubmed/39669564en
dc.rightsCreative Commons Attribution 4.0 Internationalen
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/en
dc.subjectsepsisen
dc.subjectseptic shocken
dc.subjectbiomarkersen
dc.subjectmachine learning for disease diagnosisen
dc.subjecttranslational medicineen
dc.subjectSepxFindeR modelen
dc.subject.meshKiller Cells, Naturalen
dc.subject.meshHumansen
dc.subject.meshSepsisen
dc.subject.meshShock, Septicen
dc.subject.meshPrognosisen
dc.subject.meshGene Expression Profilingen
dc.subject.meshComputational Biologyen
dc.subject.meshFemaleen
dc.subject.meshMaleen
dc.subject.meshTranscriptomeen
dc.subject.meshBiomarkersen
dc.subject.meshMachine Learningen
dc.titlePredicting patients with septic shock and sepsis through analyzing whole-blood expression of NK cell-related hub genes using an advanced machine learning frameworken
dc.title.serialFrontiers in Immunologyen
dc.typeArticle - Refereeden
dc.type.dcmitypeTexten
dc.type.otherArticleen
dc.type.otherJournalen
dcterms.dateAccepted2024-10-29en
pubs.organisational-groupVirginia Techen
pubs.organisational-groupVirginia Tech/Scienceen
pubs.organisational-groupVirginia Tech/Science/Statisticsen
pubs.organisational-groupVirginia Tech/Veterinary Medicineen
pubs.organisational-groupVirginia Tech/Veterinary Medicine/Biomedical Sciences and Pathobiologyen
pubs.organisational-groupVirginia Tech/Faculty of Health Sciencesen
pubs.organisational-groupVirginia Tech/All T&R Facultyen
pubs.organisational-groupVirginia Tech/Science/COS T&R Facultyen
pubs.organisational-groupVirginia Tech/Veterinary Medicine/CVM T&R Facultyen
pubs.organisational-groupVirginia Tech/Veterinary Medicine/Biomedical Sciences and Pathobiology/Otheren

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Predicting patients with septic shock and sepsis through analyzing whole-blood expression of NK cell-related hub genes using an advanced machine learning framework.pdf
Size:
5.3 MB
Format:
Adobe Portable Document Format
Description:
Published version
Download
License bundle
Now showing 1 - 1 of 1
Name:
license.txt
Size:
1.5 KB
Format:
Plain Text
Description:
Download

Collections

All Faculty Deposits
Scholarly Works, Biomedical Sciences and Pathobiology
Scholarly Works, Statistics