DocumentCode :
78063
Title :
Incorporation of Biological Pathway Knowledge in the Construction of Priors for Optimal Bayesian Classification
Author :
Esfahani, Mohammad Shahrokh ; Dougherty, Edward
Author_Institution :
Dept. of Electr. & Comput. Eng., Texas A&M Univ., College Station, TX, USA
Volume :
11
Issue :
1
fYear :
2014
fDate :
Jan.-Feb. 2014
Firstpage :
202
Lastpage :
218
Abstract :
Small samples are commonplace in genomic/proteomic classification, the result being inadequate classifier design and poor error estimation. The problem has recently been addressed by utilizing prior knowledge in the form of a prior distribution on an uncertainty class of feature-label distributions. A critical issue remains: how to incorporate biological knowledge into the prior distribution. For genomics/proteomics, the most common kind of knowledge is in the form of signaling pathways. Thus, it behooves us to find methods of transforming pathway knowledge into knowledge of the feature-label distribution governing the classification problem. In this paper, we address the problem of prior probability construction by proposing a series of optimization paradigms that utilize the incomplete prior information contained in pathways (both topological and regulatory). The optimization paradigms employ the marginal log-likelihood, established using a small number of feature-label realizations (sample points) regularized with the prior pathway information about the variables. In the special case of a Normal-Wishart prior distribution on the mean and inverse covariance matrix (precision matrix) of a Gaussian distribution, these optimization problems become convex. Companion website: gsp.tamu.edu/Publications/supplementary/shahrokh13a.
Keywords :
Bayes methods; Gaussian distribution; genomics; normal distribution; optimisation; probability; proteomics; Gaussian distribution; Normal-Wishart prior distribution; biological pathway knowledge; error estimation; feature-label distributions; feature-label realizations; genomic-proteomic classification; inadequate classifier design; inverse covariance matrix; marginal log-likelihood; optimal Bayesian classification; optimization paradigms; optimization problems; prior probability construction; Bayes methods; Bioinformatics; Computational biology; Genomics; Optimization; Uncertainty; Phenotype classification; biological pathway knowledge; convex optimization; optimal Bayesian classifier (OBC); prior probability construction; regularization; synthetic pathway generation;
fLanguage :
English
Journal_Title :
Computational Biology and Bioinformatics, IEEE/ACM Transactions on
Publisher :
ieee
ISSN :
1545-5963
Type :
jour
DOI :
10.1109/TCBB.2013.143
Filename :
6654120
Link To Document :
بازگشت