Loading...

Exploring Pivot Genes and Clinical Prognosis Using Combined Bioinformatics Approaches in the Colon Cancer

Vazirimoghadam, Ayoub | 2023

89 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 55967 (19)
  4. University: Sharif University of Technology
  5. Department: Computer Engineering
  6. Advisor(s): Foroughmand Araabi, Mohammad Hadi
  7. Abstract:
  8. Colorectal cancer (CRC) is one of the most common cause of cancer death worldwide. Identification of pivot genes in colorectal cancer can play an important role as biomarkers in predicting and early diagnosis and reducing the number of deaths caused by this disease. In this study, the aim of which is to discover pivot genes in colorectal cancer, six microarray datasets selected from the GEO database including 277 tumor tissue samples and 325 normal colon tissue samples. After data processing, differentially expressed genes and CRC-related genes were screened and 285 shared genes between them were identified for subsequent analysis. Based on 285 shared genes, the protein-protein interaction (PPI) network was constructed and centrality analysis was performed using principal component analysis (PCA) to rank the network nodes and finally, among the ranked nodes, the top 20 nodes were selected as essential genes. In order to screen essential genes and identify driver genes (cancer developing genes), the LASSO logistic regression model and recursive feature elimination in random forest (RF-RFE) method were investigated. Based on the validation results obtained from the receiver operating characteristic (ROC) curve, it was found that driver genes BGN, BMP2, CCND1, CXCL1, MMP3, MMP7, PLAU, and SPP1 can be biomarkers for CRC diagnosis. In addition, the results of the survival analysis showed that genes BGN and SPP1 can be prognostic biomarkers in colorectal cancer in addition to their diagnostic role
  9. Keywords:
  10. Colon Cancer ; Bioinformatics ; Machine Learning ; Pivot Genes ; Early Detection ; Biomarker ; Protein-Protein Interaction

 Digital Object List

 Bookmark

No TOC