Date of Award
2013
Publication Type
Master Thesis
Degree Name
M.Sc.
Department
Computer Science
Keywords
Biological sciences, Applied sciences, Health and environmental sciences, Prostate cancer, Rna-seq, Splice junctions, Svm
Supervisor
Rueda, Luis G.
Rights
info:eu-repo/semantics/openAccess
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Abstract
Alternative RNA splicing is a naturally occurring phenomenon that has been associated with different types of cancer. Detecting splice junctions in the genome of an organism is the key to the study of alternative splicing. RNA-Seq as a high-throughput sequencing technology has recently opened new horizons on the studying of various fields of transcriptomics, such as gene expression, chimeric events and alternative splicing. In this research, we study prostate cancer from the viewpoint of splicing events as the second most common cancer in North America. We have proposed a method for differentially detecting splice junctions, and in a broader sense splice variants, from RNA-Seq data. We have designed a 2-D peak finding algorithm to combine and remove the dubious junctions across different samples of our population. A scoring mechanism is used to select junctions as features for prediction of cancer RNA-Seq data belonging to patients diagnosed with prostate cancer against benign samples. These junctions could be proposed as potential biomarkers for prostate cancer. We have employed support vector machines which proved to be highly successful in prediction of prostate cancer.
Recommended Citation
Tavakoli, Ahmad, "Finding differential splice junctions in RNA-Seq data as transcriptional biomarkers for prostate cancer" (2013). Electronic Theses and Dissertations. 5001.
https://scholar.uwindsor.ca/etd/5001