AUTHOR=Wen Jian , Wan Lijia , Dong Xieping 

TITLE=Novel peripheral blood diagnostic biomarkers screened by machine learning algorithms in ankylosing spondylitis

JOURNAL=Frontiers in Genetics

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/genetics/articles/10.3389/fgene.2022.1032010

DOI=10.3389/fgene.2022.1032010

ISSN=1664-8021

ABSTRACT=Background: Ankylosing spondylitis (AS) is a chronic inflammatory disorder with unknown etiology and hard to early diagnose. Therefore, it’s imperative to explore novel biomarkers, which may contribute to easy and early diagnosis of AS.
Methods: Common differential expressed genes between normal and AS patients in GSE73754 and GSE25101 were screened by machine learning algorithms. A diagnostic model was established by the hubgenes screened. Then, the model was validated in several datasets. 
Results: IL2RB and ZDHHC18 were screened by machine learning algorithms and established a diagnostic model. Nomograms suggested that the higher the expression of ZDHHC18, the higher the risk of AS, while the reverse was true for IL2RB in vivo. C-indexes of the model were no less than 0.84 in validation sets. Calibration analyses suggested high prediction accuracy of the model in training and validation cohorts. The AUC values of the model in GSE73754, GSE25101, GSE18781 and GSE11886 were 0.86, 0.84, 0.85 and 0.89 respectively. Decision curve analyses suggested high net benefit by the model. Functional analysis of the differential expressed genes indicated that they were mainly clustered in processes related to immune response. Immune microenvironment analysis revealed that neutrophils were expanded and activated in AS, while some T cells were decreased.
Conclusions: IL2RB and ZDHHC18 were potential blood biomarkers for AS and might be used for early diagnosis and a supplementary diagnostic tool to the existing methods. Our study deepened the insight into the pathogenesis of AS.