Machine learning-based endoplasmic reticulum-related diagnostic biomarker and immune microenvironment landscape for osteoarthritis.

Abstract

Osteoarthritis (OA) is the most common degenerative joint disease worldwide. Further improving the current limited understanding of osteoarthritis has positive clinical value. OA samples were collected from GEO database and endoplasmic reticulum related genes (ERRGs) were identified. The WGCNA network was further built to identify the crucial gene module. Based on the expression profiles of characteristic ERRGs, LASSO algorithm was used to select key factors according to the minimum λ value. Random forest (RF) algorithm was used to calculate the importance of ERRGs. Subsequently, overlapping genes based on LASSO and RF algorithms were identified as ERRGs-related diagnostic biomarkers. In addition, OA specimens were also collected and performed qRT-PCR quantitative analysis of selected ERRGs. We identified four ERRGs associated with OA risk assessment through machine learning methods, and verified the abnormal expressions of these screened markers in OA patients through in vitro experiments. The influence of selected markers on OA immune infiltration was also evaluated. Our results provide new evidence for the role of ER stress in the OA progression, as well as new markers and potential intervention targets for OA.