AUTHOR=Hao Song , Xinqi Mao , Weicheng Xu , Shiwei Yang , Lumin Cao , Xiao Wang , Dong Liu , Jun Hua 

TITLE=Identification of key immune genes of osteoporosis based on bioinformatics and machine learning

JOURNAL=Frontiers in Endocrinology

VOLUME=Volume 14 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/endocrinology/articles/10.3389/fendo.2023.1118886

DOI=10.3389/fendo.2023.1118886

ISSN=1664-2392

ABSTRACT=Osteoporosis (OP) is common among older adults, especially postmenopausal women, which attaches great burden on society.Osteoporosis is often considered an endocrine related disease. However, recent studies have found that immune regulation is involved in bone metabolism.This study aimed to explore new bone immune-related markers and evaluate their ability to predict osteoporosis.Integrated analysis of GSE7158 in Gene expression Omnibus (GEO) and ImmPort database identified 1158 differentially expressed genes (DEGs) and 66 different immune-related genes (DIRGs) related to bone mineral density (BMD). Then, protein-protein interaction (PPIs) networks were used to analyze the interrelationships between different immune-related genes (DIRGs). Gene Ontology (GO), and Kyoto Encyclopedia of Genes and Genomes (KEGG) were adopted to analyze the functions of DIRGs. Based on the least absolute shrinkage and selection operation (LASSO) regression model and multiple Support Vector Machine-Recursive Feature Elimination (mSVM-RFE) model, five hub genes (CCR5, IAPP, IFNA4, IGHV3-73 and PTGER1) were identified and used as features to construct a predictive prognostic model for osteoporosis. GSE13850 dataset is used to validate the model. Subsequently, we constructed a nomogram model for predicting osteoporosis based on five immune-related genes. CIBERSORT algorithm was used to calculate the relative proportion of 22 immune cells. Together, the differential expression of immune-related genes in different bone mass samples provides important insights into the development of bone immunity and would be promising diagnostic biomarkers for osteoporosis.