Exploration of Regression Models for Cancer Noncoding Mutation Recurrence Public Deposited

http://ir.library.oregonstate.edu/concern/graduate_thesis_or_dissertations/x346d9344

Descriptions

Attribute NameValues
Creator
Abstract or Summary
  • An important impact of the genome technology revolution will be the elucidation of mechanisms of cancer pathogenesis, leading to improvements in the diagnosis of cancer and the selection of cancer treatment. Integrated with current well-studied massive knowledge and findings about the role of protein-coding mutations in cancer, demystifying the functional role of human "junk" DNA (non-protein-coding DNA) mutations for cancer development and progression is one of the most popular and promising approaches these days to improve our understanding of the complicated cellular mechanisms in cancer. In light of one recent finding that non-protein-coding driver mutations tend to be highly recurrent, in this thesis we explore three different kinds of regression models for predicting non-protein-coding mutation recurrence: generalized linear models, conventional machine learning approaches and deep neural network learning models. We compare the regression model results and find the most accurate model for non-protein-coding mutation recurrence prediction so that we can prioritize somatic mutations based on their predicted recurrence and provide insights for further biological validation and eventually improved cancer therapy.
License
Resource Type
Date Available
Date Copyright
Date Issued
Degree Level
Degree Name
Degree Field
Degree Grantor
Commencement Year
Advisor
Committee Member
Academic Affiliation
Non-Academic Affiliation
Keyword
Subject
Rights Statement
Peer Reviewed
Language
Replaces

Relationships

In Administrative Set:
Last modified: 10/28/2017

Downloadable Content

Download PDF
Citations:

EndNote | Zotero | Mendeley

Items