Multinet Bayesian network models for large-scale transcriptome integration in computational medicine
Author(s)Lin, Tiffany J
Linking drugs and their side effects to gene mechanisms
Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science.
MetadataShow full item record
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.
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).
DepartmentMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Massachusetts Institute of Technology
Electrical Engineering and Computer Science.