Date of Award
10-19-2015
Publication Type
Master Thesis
Degree Name
M.Sc.
Department
Computer Science
Keywords
Alternative Splicing, Classification, Feature Selection, Machine Learning, Next Generation Sequencing, Prostate Cancer Progression
Supervisor
Rueda, Luis
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
Prostate Cancer is one of the most common types of cancer among Canadian men. Next generation sequencing that uses RNA-Seq can be valuable in studying cancer, since it provides large amounts of data as a source for information about biomarkers. For these reasons, we have chosen RNA-Seq data for prostate cancer progression in our study. In this research, we propose a new method for finding transcripts that can be used as genomic features. In this regard, we have gathered a very large amount of transcripts. There are a large number of transcripts that are not quite relevant, and we filter them by applying a feature selection algorithm. The results are then processed through a machine learning technique for classification such as the support vector machine which is used to classify different stages of prostate cancer. Finally, we have identified potential transcripts associated with prostate cancer progression. Ideally, these transcripts can be used for improving diagnosis, treatment, and drug development.
Recommended Citation
Singi Reddy, Siva Charan Reddy, "USING MACHINE LEARNING TECHNIQUES FOR FINDING MEANINGFUL TRANSCRIPTS IN PROSTATE CANCER PROGRESSION" (2015). Electronic Theses and Dissertations. 5433.
https://scholar.uwindsor.ca/etd/5433