Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form

BAYESIAN FRAMEWORKS FOR PARSIMONIOUS MODELING OF MOLECULAR CANCER DATA

Lopez Pineda, Arturo (2015) BAYESIAN FRAMEWORKS FOR PARSIMONIOUS MODELING OF MOLECULAR CANCER DATA. Doctoral Dissertation, University of Pittsburgh. (Unpublished)

[img] PDF
Primary Text
Restricted to University of Pittsburgh users only until 11 December 2020.

Download (3MB) | Request a Copy

Abstract

In this era of precision medicine, clinicians and researchers critically need the assistance of computational models that can accurately predict various clinical events and outcomes (e.g,, diagnosis of disease, determining the stage of the disease, or molecular subtyping). Typically, statistics and machine learning are applied to ‘omic’ datasets, yielding computational models that can be used for prediction. In cancer research there is still a critical need for computational models that have high classification performance but are also parsimonious in the number of variables they use. Some models are very good at performing their intended classification task, but are too complex for human researchers and clinicians to understand, due to the large number of variables they use. In contrast, some models are specifically built with a small number of variables, but may lack excellent predictive performance.

This dissertation proposes a novel framework, called Junction to Knowledge (J2K), for the construction of parsimonious computational models. The J2K framework consists of four steps: filtering (discretization and variable selection), Bayesian network generation, Junction tree generation, and clique evaluation. The outcome of applying J2K to a particular dataset is a parsimonious Bayesian network model with high predictive performance, but also that is composed of a small number of variables. Not only does J2K find parsimonious gene cliques, but also provides the ability to create multi-omic models that can further improve the classification performance. These multi-omic models have the potential to accelerate biomedical discovery, followed by translation of their results into clinical practice.


Share

Citation/Export:
Social Networking:
Share |

Details

Item Type: University of Pittsburgh ETD
Status: Unpublished
Creators/Authors:
CreatorsEmailPitt UsernameORCID
Lopez Pineda, Arturoarl68@pitt.eduARL680000-0002-3409-1815
ETD Committee:
TitleMemberEmail AddressPitt UsernameORCID
Committee ChairGopalakrishnan, Vanathivanathi@pitt.eduVANATHI
Committee MemberVisweswaran, Shyamshv3@pitt.eduSHV3
Committee MemberCooper, Gregory F.gfc@pitt.edu GFC
Committee MemberRangel Escareno, Claudiacrangel@inmegen.gob.mx
Date: 11 December 2015
Date Type: Publication
Defense Date: 1 December 2015
Approval Date: 11 December 2015
Submission Date: 11 December 2015
Access Restriction: 5 year -- Restrict access to University of Pittsburgh for a period of 5 years.
Number of Pages: 140
Institution: University of Pittsburgh
Schools and Programs: School of Medicine > Biomedical Informatics
Degree: PhD - Doctor of Philosophy
Thesis Type: Doctoral Dissertation
Refereed: Yes
Uncontrolled Keywords: Biomedical Informatics, Artificial Intelligence, Machine Learning, Bayesian Classifiers, Computational Genomics, Neoplasms, Early Detection of Cancer, Gene Expression, DNA Methylation
Date Deposited: 11 Dec 2015 19:23
Last Modified: 15 Nov 2016 14:31
URI: http://d-scholarship.pitt.edu/id/eprint/26656

Metrics

Monthly Views for the past 3 years

Plum Analytics


Actions (login required)

View Item View Item