AUTHOR=Li Jing , Lan Chun-Na , Kong Ying , Feng Song-Shan , Huang Tao 

TITLE=Identification and Analysis of Blood Gene Expression Signature for Osteoarthritis With Advanced Feature Selection Methods

JOURNAL=Frontiers in Genetics

VOLUME=Volume 9 - 2018

YEAR=2018

URL=https://www.frontiersin.org/journals/genetics/articles/10.3389/fgene.2018.00246

DOI=10.3389/fgene.2018.00246

ISSN=1664-8021

ABSTRACT=Osteoarthritis (OA) is a complex disease that affect articular joints and may cause disability. The incidence of OA is extremely high. Most elder people have the symptoms of osteoarthritis. The physiotherapy of OA is time consuming and the chance of full recovery from OA is very small. The most effective way of fighting OA is early diagnosis and early intervention. The liquid biopsy has become a popular way for non-invasive test. To find the blood gene expression signature for OA, we re-analyzed the publicly available blood gene expression profiles of 106 OA patients and 33 control samples using an automatic computational pipeline based on advanced feature selection methods. At last, a compact 23 gene set were identified. Based on these 23 genes, we constructed an SVM (Support Vector Machine) classifier and evaluated it with leave-one-out cross validation. Its Sensitivity (Sn), Specificity (Sp), Accuracy (ACC) and Mathew's correlation coefficient (MCC) were 0.991, 0.909, 0.971 and 0.920, respectively. Obviously, the performance needed to be validated in an independent large dataset, but the in-depth biological analysis of the 23 biomarkers showed great promises and suggested that mRNA surveillance pathway and multicellular organism growth played important roles in OA. Our results shield light on OA diagnosis through liquid biopsy.