Loading...

Exploration of Existing Patterns in Copy Number Variations of Genetic Diseases and Disorders

Rahaie, Zahra | 2023

46 Viewed
  1. Type of Document: Ph.D. Dissertation
  2. Language: Farsi
  3. Document No: 56777 (19)
  4. University: Sharif University of Technology
  5. Department: Computer Engineering
  6. Advisor(s): Rabiee, Hamid Reza
  7. Abstract:
  8. One of the main sources of genetic variations are structural variations, including the widespread Copy Number Variations (CNVs). CNVs include two types, copy of genetic material (duplication) and loss of part of genetic sequence (deletion) and typically range from one kilobase pairs (Kbp) to several megabase pairs (Mbp) in size. Most of the copy number variations are occured in in healthy people; however, these variants can also contribute to numerous diseases through several genetic mechanisms (e.g. change gene dosage through insertions, duplications or deletions). The CNV study can provide greater insight into the etiology of disease phenotypes. Nowadays, with the huge amount of investment in CNV sampling on patients and healthy population, there is a great deal of hope for a sudden jump in discovering the possible genetic etiology of many diseases, followed by their definitive treatment. In the analysis of CNV data, application of machine learning and systems biology techniques have become more attractive given the rising complexity and abundancy of the data. Here, we used deep learning to study patterns exist in the dataset of copy number variations in the neurodevelopmental disorders (including autism spectrum disorder, schizophrenia, and developmental delay). In the dataset, there exists interesting regions that our method detected them. For evaluating the obtained results, we used p values, genes expressed in the mouse nervous system, brain enriched genes, and DECIPHER dataset (for association with other phenotypes). In the evaluation, we obtained acceptable results. Besides extracting important regions, we investigated the relation of each significant region with the phenotypes with the help of DECIPHER data source. One of the main issues in bioinformatics is gene prioritization which tries to predict the extent of a gene involvement in the occurrence a disease. In addition to examining copy number variations, we tried to prioritize the genes’ associations with the neurodevelopmental disorders. Our findings indicate a 12% increase in fold enrichment in brain-expressed genes compared to previous studies and a 15% increase in genes associated with mouse nervous system phenotypes
  9. Keywords:
  10. Deep Learning ; Bioinformatics ; Gene Expression ; Gene Expression Data ; Copy Number Variations (CNVs) ; Gene Prioritization

 Digital Object List

 Bookmark

No TOC