Multinet Bayesian network models for large-scale transcriptome integration in computational medicine
Name
826515154-MIT.pdf
Description
Full printable version
Size
2.54 MB
Format
Adobe PDF
Checksum (MD5)
6980c5020efd9cb62950fa56754aa8c7
Author(s)
Lin, Tiffany J
Advisor(s)
Gil Alterovitz.
Alternative Title
Linking drugs and their side effects to gene mechanisms
Date Issued
2012
Publisher
Massachusetts Institute of Technology
Abstract
Motivation: This work utilizes the closed loop Bayesian network framework for predictive medicine via integrative analysis of publicly available gene expression findings pertaining to various diseases and analyzes the results to determine which model, single net or multinet, is a more accurate predictor for determining disease status. Results: In general, it is suggested to use the multinet Bayesian network framework for predictive medicine instead of the single net Bayesian network, because for large numbers of samples and features, it is highly likely that it is the stronger predictor, and for smaller numbers of samples and features, if the multinet returns good results, it is likely to be a better predictor than the single net Bayesian network.
Description
Thesis (M. Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2012.
Cataloged from PDF version of thesis.
Includes bibliographical references (p. 30).
Subjects
Electrical Engineering and Computer Science.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
M.I.T. theses are protected by
copyright. They may be viewed from this source for any purpose, but
reproduction or distribution in any format is prohibited without written
permission. See provided URL for inquiries about permission.
copyright. They may be viewed from this source for any purpose, but
reproduction or distribution in any format is prohibited without written
permission. See provided URL for inquiries about permission.
Persistent DSpace Link
