Screening of Important Markers in Peripheral Blood Mononuclear Cells to Predict Female Osteoporosis Risk Using LASSO Regression Algorithm and SVM Method. (January 2022)

• Record Type: Journal Article
• Authors: Tang, Hongwei; Han, Qingtian; Yin, Yong
• Is Part Of: Evolutionary bioinformatics online. Volume 18(2022)
• Publication Date: 2022-01
• Subjects: Integration analysis -- SVM -- osteoporosis -- differentially expressed genes -- diagnosis -- PPI; Bioinformatics -- Periodicals; Evolutionary computation -- Periodicals; Genetic programming (Computer science) -- Periodicals; Computational Biology; Evolution, Molecular; Bioinformatics; Electronic journals; Periodicals; Fulltext; Internet Resources; Periodicals; Periodicals; 576.8
• DOI: 10.1177/11769343221075014
• Languages: English
• ISSNs: 1176-9343

Abstract

Background: Osteoporosis is a bone disease that increases the patient's risk of fracture. We aimed to identify robust marker genes related to osteoporosis based on different bioinformatic methods and multiple datasets. Methods: Three datasets from Gene Expression Omnibus (GEO) were utilized for analysis separately. Significantly differentially expressed genes (DEGs) from comparing high hip and low hip low bone mineral density (BMD) groups in the first dataset were identified for Gene Ontology (GO), Gene set enrichment analysis (GSEA) and Kyoto encyclopedia of genes and genomes (KEGG) to investigate the discrepantly enriched biological processes between high hip and low hip group. Last absolute shrinkage and selection operator (LASSO), SVM model and protein-protein interaction (PPI) regulatory network were performed and generated robust marker genes for downstream TF-target and miRNA-target prediction. Results: Several DEGs between high hip BMD group and low hip BMD group were obtained. And the metabolism-related pathways such as metabolic pathways, carbon metabolism, glyoxylate and dicarboxylate metabolism shown enrichment in these DEGs. Integration with LASSO regression analysis, 8 differential expression genes ( SH3BP1, NARF, ANKRD34B, RNF40, ZNF473, AKT1, SHMT1, and VASH1 ) in GSE62402 were identified as the optimal differential genes combination. Moreover, the SVM validation analysis in GSE56814 and GSE56815 datasets showed that the characteristic gene combinations presented high diagnostic effects, and the model AUC areas for GSE56814 was 0.899 and for GSE56815 was 0.921. Furthermore, the subcellular localization analysis of the 8 genes revealed that 4 proteins were located in the cytoplasm, 3 proteins were located in the nucleus, and 1 protein was located in the mitochondria. Additionally, the related TFs and miRNAs by performing TF-target and miRNA-target prediction for 5 genes ( AKT1, SHMT1, ZNF473, RNF40 and VASH1 ) were investigated from PPI network. Conclusion: The optimal differential genes combination ( SH3BP1, NARF, ANKRD34B, RNF40, ZNF473, AKT1, SHMT1, and VASH1 ) presented high diagnostic effect for osteoporosis risk.