Machine learning analysis of gene expression profile reveals a novel diagnostic signature for osteoporosis

Investigating the impact of Wnt pathway-related genes on biomarker and diagnostic model development for osteoporosis in postmenopausal females

The Wnt signaling pathway is essential for bone development and maintaining skeletal homeostasis, making it particularly relevant in osteoporosis patients. Our study aimed to identify distinct molecular clusters associated with the Wnt pathway and develop a diagnostic model for osteoporosis in postmenopausal Caucasian women. We downloaded three datasets (GSE56814, GSE56815 and GSE2208) related to osteoporosis from the GEO database. Our analysis identified a total of 371 differentially expressed genes (DEGs) between low and high bone mineral density (BMD) groups, with 12 genes associated with the Wnt signaling pathway, referred to as osteoporosis-associated Wnt pathway-related genes. Employing four independent machine learning models, we established a diagnostic model using the 12 osteoporosis-associated Wnt pathway-related genes in the training set. The XGB model showed the most promising discriminative potential. We further validate the predictive capability of our diagnostic model by applying it to three external datasets specifically related to osteoporosis. Subsequently, we constructed a diagnostic nomogram based on the five crucial genes identified from the XGB model. In addition, through the utilization of DGIdb, we identified a total of 30 molecular compounds or medications that exhibit potential as promising therapeutic targets for osteoporosis. In summary, our comprehensive analysis provides valuable insights into the relationship between the osteoporosis and Wnt signaling pathway.

Protein profile pattern analysis: A multifarious, in vitro diagnosis technique for universal screening

Universal health care is attracting increased attention nowadays, because of the large increase in population all over the world, and a similar increase in life expectancy, leading to an increase in the incidence of non-communicable (various cancers, coronary diseases, neurological and old-age-related diseases) and communicable diseases/pandemics like SARS-COVID 19. This has led to an immediate need for a healthcare technology that should be cost-effective and accessible to all. A technology being considered as a possible one at present is liquid biopsy, which looks for markers in readily available samples like body fluids which can be accessed non- or minimally- invasive manner. Two approaches are being tried now towards this objective. The first involves the identification of suitable, specific markers for each condition, using established methods like various Mass Spectroscopy techniques (Surface-Enhanced Laser Desorption/Ionization Mass Spectroscopy (SELDI-MS), Matrix-Assisted Laser Desorption/Ionization (MALDI-MS), etc., immunoassays (Enzyme-Linked Immunoassay (ELISA), Proximity Extension Assays, etc.) and separation methods like 2-Dimensional Polyacrylamide Gel Electrophoresis (2-D PAGE), Sodium Dodecyl-Sulfate Polyacrylamide Gel Electrophoresis (SDS-PAGE), Capillary Electrophoresis (CE), etc. In the second approach, no attempt is made the identification of specific markers; rather an efficient separation method like High-Performance Liquid Chromatography/ Ultra-High-Performance Liquid Chromatography (HPLC/UPLC) is used to separate the protein markers, and a profile of the protein pattern is recorded, which is analysed by Artificial Intelligence (AI)/Machine Learning (MI) methods to derive characteristic patterns and use them for identifying the disease condition. The present report gives a summary of the current status of these two approaches and compares the two in the use of their suitability for universal healthcare.

Identification of hub genes associated with osteoporosis development by comprehensive bioinformatics analysis

Osteoporosis (OP) is a systemic bone disease caused by various factors, including, the decrease of bone density and quality, the destruction of bone microstructure, and the increase of bone fragility. It is a disease with a high incidence in a large proportion of the world's elderly population. However, osteoporosis lacks obvious symptoms and sensitive biomarkers. Therefore, it is extremely urgent to discover and identify disease-related biomarkers for early clinical diagnosis and effective intervention for osteoporosis. In our study, the Linear Models for Microarray Data (LIMMA) tool was used to screen differential expressed genes from transcriptome sequencing data of OP blood samples downloaded from the GEO database, and cluster Profiler was used for enriching analysis of differently expressed genes. In order to analyzed the relevance of gene modules, clinical symptoms, and the most related module setting genes associated with disease progression, we adapted Weighted Gene Co-expression Network Analysis (WGCNA) to screen and analyze the related pathways and relevant molecules. We used the Search Tool for the Retrieval of Interacting Genes/Proteins (STRING) database to construct protein interaction network of key modules, and Cytoscape software was used to complete network visualization and screen of core genes in the network. Various plug-in algorithms of cytoHubba were used to identify key genes of OP. Finally, correlation analysis and single-gene gene probe concentration analysis (GSEA) analysis were performed for each core gene. Results of a total of 8 key genes that were closely related to the occurrence and development of OP were screened out, which provided a brand-new idea for the clinical diagnosis and early prevention of OP. Quantitative real-time PCR (qRT-PCR) was performed for validation, the expression levels of CUL1, PTEN and STAT1 genes in the OS group were significantly higher than in the non-OS groups. Receiver operating characteristic analysis demonstrated that CUL1, PTEN and STAT1 displayed considerable diagnostic accuracy for OS.

Identification of osteoporosis based on gene biomarkers using support vector machine

Osteoporosis is a major health concern worldwide. The present study aimed to identify effective biomarkers for osteoporosis detection. In osteoporosis, 559 differentially expressed genes (DEGs) were enriched in PI3K-Akt signaling pathway and Foxo signaling pathway. Weighted gene co-expression network analysis showed that green, pink, and tan modules were clinically significant modules, and that six genes (VEGFA, DDX5, SOD2, HNRNPD, EIF5B, and HSP90B1) were identified as “real” hub genes in the protein–protein interaction network, co-expression network, and 559 DEGs. The sensitivity and specificity of the support vector machine (SVM) for identifying patients with osteoporosis was 100%, with an area under curve of 1 in both training and validation datasets. Our results indicated that the current system using the SVM method could identify patients with osteoporosis.