Loading...

Identifying Cancer-related Genes Via Network Feature Learning and Multi-Omics Data Integration

Safari, Monireh | 2022

472 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 55032 (19)
  4. University: Sharif University of Technology
  5. Department: Computer Engineering
  6. Advisor(s): Rabiee, Hamid Reza
  7. Abstract:
  8. The highly developed biological data collection methods enable scientists to capture protein-protein interaction (PPI) in the human body, which could be analyzed as biological networks such as protein-protein interaction networks. These networks reveal essential information about the biological process in human cells and can be used to identify genes associated with cancers. Effectively identifying disease-related genes would contribute to improving the treatment and diagnosis of various diseases. Current methods for identifying disease-related genes mainly focus on the hypothesis of guilt-by-association and do not consider the global information in the PPI network. Besides, most methods pay little attention to gene's biological and molecular functions, which could significantly impact identifying disease-related genes. In this project, we proposed a novel framework for identifying disease-related genes of 5 different cancers using network representation learning (NRL) algorithms. The proposed framework has three main steps. Firstly, we capture the topological structure of the PPI network using three NRL methods which have the most promising performance on the same task. Secondly, we integrate learned features for each gene from the PPI networks with the biological and molecular features obtained from the UniProt database. Finally, a binary classification model was built to classify genes into two classes. Comprehensive experiments demonstrate that our proposed framework significantly outperforms state-of-the-art methods for disease gene prediction across four different cancers.
  9. Keywords:
  10. Protein-Protein Interaction ; Representation Learning ; Cancer Treatment ; Biological Networks ; Gene Expression Data ; Disease-Related Genes

 Digital Object List

 Bookmark

...see more