Identification of Biomarkers Associated with Diagnosis of Osteoarthritis Patients Based on Bioinformatics and Machine Learning

Abstract

Osteoarthritis (OA) is thought to be the most prevalent chronic joint disease. The incidence of OA is rising because of the ageing population and the epidemic of obesity. This research was designed for the identification of novel diagnostic biomarkers for OA and analyzing the possible association between critical genes and infiltrated immune cells. 10 OA samples from patients with spinal OA and 10 normal samples were collected. GSE55235 and GSE55457 datasets including human OA and normal samples were downloaded from the GEO datasets. Differentially expressed genes (DEGs) were identified between 20 OA and 20 controls. SVM-RFE analysis and LASSO regression model were carried out to screen possible markers. The compositional patterns of the 22 types of immune cell fraction in OA were determined by the use of CIBERSORT. The expression level of the biomarkers in OA was examined by the use of RT-PCR. In this study, an overall 44 DEGs were identified: 18 genes were remarkably upregulated and 26 genes were distinctly downregulated. KEGG pathway analyses revealed that pathways were significantly enriched including IL-17 signal path, rheumatoid arthritis, TNF signal path, and lipid and atherosclerosis. Based on the results of machine learning, we identified APOLD1 and EPYC as critical diagnostic genes in OA, which were further confirmed using ROC assays. Immune cell infiltration analysis revealed that APOLD1 was correlated with mastocytes stimulated, NK cells resting, T cells CD4 memory resting, DCs stimulated, T cells gamma delta, macrophages M0, NK cells stimulated, and mastocytes resting. Moreover, we found that EPYC was correlated with mastocytes stimulated, NK cells resting, T cells CD4 memory resting, DCs stimulated, T cells gamma delta, macrophages M0, NK cells stimulated, and mastocytes resting. Overall, our findings might provide some novel clue for the exploration of novel markers for OA diagnosis. The critical genes and their associations with immune infiltration may offer new insight into understanding OA developments.

Identification of Immune-Related Risk Genes in Osteoarthritis Based on Bioinformatics Analysis and Machine Learning

“…Identifying potential disease markers of osteoarthritis has been a research hotspot in different aspects. However, most reports only utilized limited, even single, datasets [ 35 , 36 , 37 ]. We believe that merging datasets from different sources could result in a more persuasive conclusion.…”

Integrated analysis reveals potential significance of FKBP5 in the prognosis and immunity of osteoarthritis and pan-cancer

“…Previous studies have identi ed biomarkers of OA using machine-learning methods. For example, Liang et al (39) used SVM-RFE and Lasso algorithms to screen APOLD1 and EPYC as diagnostic genes for OA; Zhang JY et al (40) used similar screening methods to select EPYC and KLF9 as diagnostic genes, which may indicate that differences in logFC values, gene set selection, and parameter selection affect the screening of candidate genes. However, they did not validate the expression of diagnostic genes based on intra-articular cavity samples, while the EPYC and KLF9 genes were identi ed as diagnostic markers for OA, which also indicated the feasibility of our analysis strategy.…”

Multi-database analysis showed that genes associated with inflammatory response are important for prognosis prediction of renal clear cell carcinoma

“…In humans, the main function of APOLD1 is to encode apolipoprotein, which has an important role in regulating vascular function. [11] Studies have con rmed the important role of APOLD1 in in ammatory response-related diseases, such as diabetic nephropathy and osteoarthritis. [11,12] Similarly, this gene can predict the prognosis of patients with clear cell carcinoma of the kidney.…”

“…[11] Studies have con rmed the important role of APOLD1 in in ammatory response-related diseases, such as diabetic nephropathy and osteoarthritis. [11,12] Similarly, this gene can predict the prognosis of patients with clear cell carcinoma of the kidney. [13] CPA3 is associated with histone deacetylase activation.…”