Comprehensive analysis of anoikis-related genes in diagnosis osteoarthritis: based on machine learning and single-cell RNA sequencing data
AbstractOsteoarthritis (OA) is a degenerative disease closely associated with Anoikis. The objective of this work was to discover novel transcriptome-based anoikis-related biomarkers and pathways for OA progression.The microarray datasets GSE114007 and GSE89408 were downloaded using the Gene Express...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2024-12-01
|
| Series: | Artificial Cells, Nanomedicine, and Biotechnology |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/21691401.2024.2318210 |
| _version_ | 1797289787716009984 |
|---|---|
| author | Jun-Song Zhang Run-Sang Pan Guo-Lu Li Jian-Xiang Teng Hong-Bo Zhao Chang-Hua Zhou Ji-Sheng Zhu Hao Zheng Xiao-Bin Tian |
| author_facet | Jun-Song Zhang Run-Sang Pan Guo-Lu Li Jian-Xiang Teng Hong-Bo Zhao Chang-Hua Zhou Ji-Sheng Zhu Hao Zheng Xiao-Bin Tian |
| author_sort | Jun-Song Zhang |
| collection | DOAJ |
| description | AbstractOsteoarthritis (OA) is a degenerative disease closely associated with Anoikis. The objective of this work was to discover novel transcriptome-based anoikis-related biomarkers and pathways for OA progression.The microarray datasets GSE114007 and GSE89408 were downloaded using the Gene Expression Omnibus (GEO) database. A collection of genes linked to anoikis has been collected from the GeneCards database. The intersection genes of the differential anoikis-related genes (DEARGs) were identified using a Venn diagram. Infiltration analyses were used to identify and study the differentially expressed genes (DEGs). Anoikis clustering was used to identify the DEGs. By using gene clustering, two OA subgroups were formed using the DEGs. GSE152805 was used to analyse OA cartilage on a single cell level. 10 DEARGs were identified by lasso analysis, and two Anoikis subtypes were constructed. MEgreen module was found in disease WGCNA analysis, and MEturquoise module was most significant in gene clusters WGCNA. The XGB, SVM, RF, and GLM models identified five hub genes (CDH2, SHCBP1, SCG2, C10orf10, P FKFB3), and the diagnostic model built using these five genes performed well in the training and validation cohorts. analysing single-cell RNA sequencing data from GSE152805, including 25,852 cells of 6 OA cartilage. |
| first_indexed | 2024-03-07T19:11:03Z |
| format | Article |
| id | doaj.art-22a3dcc2528e41db97fbccc95f170c57 |
| institution | Directory Open Access Journal |
| issn | 2169-1401 2169-141X |
| language | English |
| last_indexed | 2024-03-07T19:11:03Z |
| publishDate | 2024-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Artificial Cells, Nanomedicine, and Biotechnology |
| spelling | doaj.art-22a3dcc2528e41db97fbccc95f170c572024-03-01T00:09:02ZengTaylor & Francis GroupArtificial Cells, Nanomedicine, and Biotechnology2169-14012169-141X2024-12-0152115617410.1080/21691401.2024.2318210Comprehensive analysis of anoikis-related genes in diagnosis osteoarthritis: based on machine learning and single-cell RNA sequencing dataJun-Song Zhang0Run-Sang Pan1Guo-Lu Li2Jian-Xiang Teng3Hong-Bo Zhao4Chang-Hua Zhou5Ji-Sheng Zhu6Hao Zheng7Xiao-Bin Tian8School of Clinical Medicine, Guizhou Medical University, Guiyang, ChinaSchool of Basic Medicine, Guizhou Medical University, Guiyang, ChinaEmergency Surgery, Guizhou Provincial People’s Hospital, Guiyang, ChinaSchool of Clinical Medicine, Guizhou Medical University, Guiyang, ChinaSchool of Clinical Medicine, Guizhou Medical University, Guiyang, ChinaSchool of Clinical Medicine, Guizhou Medical University, Guiyang, ChinaSchool of Clinical Medicine, Guizhou Medical University, Guiyang, ChinaSchool of Clinical Medicine, Guizhou Medical University, Guiyang, ChinaSchool of Clinical Medicine, Guizhou Medical University, Guiyang, ChinaAbstractOsteoarthritis (OA) is a degenerative disease closely associated with Anoikis. The objective of this work was to discover novel transcriptome-based anoikis-related biomarkers and pathways for OA progression.The microarray datasets GSE114007 and GSE89408 were downloaded using the Gene Expression Omnibus (GEO) database. A collection of genes linked to anoikis has been collected from the GeneCards database. The intersection genes of the differential anoikis-related genes (DEARGs) were identified using a Venn diagram. Infiltration analyses were used to identify and study the differentially expressed genes (DEGs). Anoikis clustering was used to identify the DEGs. By using gene clustering, two OA subgroups were formed using the DEGs. GSE152805 was used to analyse OA cartilage on a single cell level. 10 DEARGs were identified by lasso analysis, and two Anoikis subtypes were constructed. MEgreen module was found in disease WGCNA analysis, and MEturquoise module was most significant in gene clusters WGCNA. The XGB, SVM, RF, and GLM models identified five hub genes (CDH2, SHCBP1, SCG2, C10orf10, P FKFB3), and the diagnostic model built using these five genes performed well in the training and validation cohorts. analysing single-cell RNA sequencing data from GSE152805, including 25,852 cells of 6 OA cartilage.https://www.tandfonline.com/doi/10.1080/21691401.2024.2318210Osteoarthritisanoikisimmunitymachine learningsingle-cell analysis |
| spellingShingle | Jun-Song Zhang Run-Sang Pan Guo-Lu Li Jian-Xiang Teng Hong-Bo Zhao Chang-Hua Zhou Ji-Sheng Zhu Hao Zheng Xiao-Bin Tian Comprehensive analysis of anoikis-related genes in diagnosis osteoarthritis: based on machine learning and single-cell RNA sequencing data Artificial Cells, Nanomedicine, and Biotechnology Osteoarthritis anoikis immunity machine learning single-cell analysis |
| title | Comprehensive analysis of anoikis-related genes in diagnosis osteoarthritis: based on machine learning and single-cell RNA sequencing data |
| title_full | Comprehensive analysis of anoikis-related genes in diagnosis osteoarthritis: based on machine learning and single-cell RNA sequencing data |
| title_fullStr | Comprehensive analysis of anoikis-related genes in diagnosis osteoarthritis: based on machine learning and single-cell RNA sequencing data |
| title_full_unstemmed | Comprehensive analysis of anoikis-related genes in diagnosis osteoarthritis: based on machine learning and single-cell RNA sequencing data |
| title_short | Comprehensive analysis of anoikis-related genes in diagnosis osteoarthritis: based on machine learning and single-cell RNA sequencing data |
| title_sort | comprehensive analysis of anoikis related genes in diagnosis osteoarthritis based on machine learning and single cell rna sequencing data |
| topic | Osteoarthritis anoikis immunity machine learning single-cell analysis |
| url | https://www.tandfonline.com/doi/10.1080/21691401.2024.2318210 |
| work_keys_str_mv | AT junsongzhang comprehensiveanalysisofanoikisrelatedgenesindiagnosisosteoarthritisbasedonmachinelearningandsinglecellrnasequencingdata AT runsangpan comprehensiveanalysisofanoikisrelatedgenesindiagnosisosteoarthritisbasedonmachinelearningandsinglecellrnasequencingdata AT guoluli comprehensiveanalysisofanoikisrelatedgenesindiagnosisosteoarthritisbasedonmachinelearningandsinglecellrnasequencingdata AT jianxiangteng comprehensiveanalysisofanoikisrelatedgenesindiagnosisosteoarthritisbasedonmachinelearningandsinglecellrnasequencingdata AT hongbozhao comprehensiveanalysisofanoikisrelatedgenesindiagnosisosteoarthritisbasedonmachinelearningandsinglecellrnasequencingdata AT changhuazhou comprehensiveanalysisofanoikisrelatedgenesindiagnosisosteoarthritisbasedonmachinelearningandsinglecellrnasequencingdata AT jishengzhu comprehensiveanalysisofanoikisrelatedgenesindiagnosisosteoarthritisbasedonmachinelearningandsinglecellrnasequencingdata AT haozheng comprehensiveanalysisofanoikisrelatedgenesindiagnosisosteoarthritisbasedonmachinelearningandsinglecellrnasequencingdata AT xiaobintian comprehensiveanalysisofanoikisrelatedgenesindiagnosisosteoarthritisbasedonmachinelearningandsinglecellrnasequencingdata |