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

Chen, Xinlei; Liu, Guangping; Wang, Shuxiang; Zhang, Haiyang; Xue, Peng

doi:10.1186/s13018-021-02329-1

Cited by 11 publications

(4 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since OP doesn't have any obvious clinical symptoms before the occurrence of the first fracture, early diagnosis is key to timely intervention and to alleviating the pain of patients (Dera et al, 2019;Yong and Logan, 2021). Compared to previous studies (Chen et al, 2021), our studies not only screened genes related to OP occurrence and development in the GSE database, but also verified the correlation and differential expressions between core genes and the data set. Furthermore, additional facts confirmed that CDC5L, CUL1, CXCL10, EIF2AK2, POLR2B, PTEN, STAT1, TBP and other 8 genes play an important role in the occurrence of OP.…”

Section: Discussionmentioning

confidence: 91%

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

et al. 2023

View full text Add to dashboard Cite

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.

show abstract

Section: Discussionmentioning

confidence: 91%

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

et al. 2023

View full text Add to dashboard Cite

show abstract

“…For instance, Xue et al conducted a study where they developed a diagnostic model by incorporating six specific genes associated with osteoporosis. Their model achieved an impressive AUC value of 0.7265, indicating its high predictive power 34 . Similarly, Hwang utilized five different machine learning algorithms to develop models for osteoporosis screening.…”

Section: Discussionmentioning

confidence: 99%

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

Lai,

Yang,

Huang

et al. 2024

Sci Rep

View full text Add to dashboard Cite

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.

show abstract

“…Genes and their expression product can help to finish that job by working as biomarkers. Machine learning models like regressions and clusters were used by a team of researchers led by Chen, X., Liu, G. et al [12] to correlate the gene characteristics of OP patients. By comparing the samples of OP and non-OP patients, they find out which gene or RNA plays a crucial part in the development of OP and then identify promising biomarkers for predicting OP.…”

Section: Other Diseasesmentioning

confidence: 99%

Making Medical Predictions about Diseases with Gene Expression Data

Li¹

2022

HSET

View full text Add to dashboard Cite

Exploration and studies of human genes play a critical role for improving the healthcare and society development. By using previous data as input, machine learning enables software applications to forecast values more precisely and is a good tool to complete the task of predicting diseases with gene expression data. This paper provides a comprehensive review of studies regarding the combination of machine learning and gene expression analysis related to diseases. The main three applications are (a) the disease prediction: cancer detection and other diseases detection, (b) the control of cancers: the metastasis of cancer and the complete remission of cancers, and (c) the drug response prediction. The reviewed molding method in this paper mainly focus on Regressions, K nearest neighbor (KNN) and Support vector machine (SVM). The combination of gene data and machine learning is meaningful for developing new techniques for detecting diseases and testing new drugs, which improves accuracy and effectiveness.

show abstract

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

Cited by 11 publications

References 34 publications

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

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

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

Making Medical Predictions about Diseases with Gene Expression Data

Contact Info

Product

Resources

About