國立高雄大學圖資館 |

Language: English

Back

Machine learning methods for microar...

Gabbur, Prasad Amaresh.

Machine learning methods for microarray data analysis.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Machine learning methods for microarray data analysis.
Author:	Gabbur, Prasad Amaresh.
Description:	204 p.
Notes:	Source: Dissertation Abstracts International, Volume: 71-05, Section: B, page: 2759.
Notes:	Adviser: Jacobus Barnard.
Contained By:	Dissertation Abstracts International71-05B.
Subject:	Engineering, Biomedical.
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3402871
ISBN:	9781109754636

Machine learning methods for microarray data analysis.
Gabbur, Prasad Amaresh.

Machine learning methods for microarray data analysis. - 204 p.

Source: Dissertation Abstracts International, Volume: 71-05, Section: B, page: 2759.

Thesis (Ph.D.)--The University of Arizona, 2010.

Microarrays emerged in the 1990s as a consequence of the efforts to speed up the process of drug discovery. They revolutionized molecular biological research by enabling monitoring of thousands of genes together. Typical microarray experiments measure the expression levels of a large number of genes on very few tissue samples. The resulting sparsity of data presents major challenges to statistical methods used to perform any kind of analysis on this data. This research posits that phenotypic classification and prediction serve as good objective functions for both optimization and evaluation of microarray data analysis methods. This is because classification measures what is needed for diagnostics and provides quantitative performance measures such as leave-one-out (LOO) or held-out prediction accuracy and confidence. Under the classification framework, various microarray data normalization procedures are evaluated using a class label hypothesis testing framework and also employing Support Vector Machines (SVM) and linear discriminant based classifiers. A novel normalization technique based on minimizing the squared correlation coefficients between expression levels of gene pairs is proposed and evaluated along with the other methods. Our results suggest that most normalization methods helped classification on the datasets considered except the rank method, most likely due to its quantization effects.

ISBN: 9781109754636Subjects--Topical Terms:

227004
Engineering, Biomedical.

Machine learning methods for microarray data analysis.
LDR:03616nmm 2200325 4500 001 280821
005 20110119095002.5
008 110301s2010 ||||||||||||||||| ||eng d
020 $a 9781109754636
035 $a (UMI)AAI3402871
035 $a AAI3402871
040 $a UMI $c UMI
100 1 $a Gabbur, Prasad Amaresh. $3 492952
245 1 0 $a Machine learning methods for microarray data analysis.
300 $a 204 p.
500 $a Source: Dissertation Abstracts International, Volume: 71-05, Section: B, page: 2759.
500 $a Adviser: Jacobus Barnard.
502 $a Thesis (Ph.D.)--The University of Arizona, 2010.
520 $a Microarrays emerged in the 1990s as a consequence of the efforts to speed up the process of drug discovery. They revolutionized molecular biological research by enabling monitoring of thousands of genes together. Typical microarray experiments measure the expression levels of a large number of genes on very few tissue samples. The resulting sparsity of data presents major challenges to statistical methods used to perform any kind of analysis on this data. This research posits that phenotypic classification and prediction serve as good objective functions for both optimization and evaluation of microarray data analysis methods. This is because classification measures what is needed for diagnostics and provides quantitative performance measures such as leave-one-out (LOO) or held-out prediction accuracy and confidence. Under the classification framework, various microarray data normalization procedures are evaluated using a class label hypothesis testing framework and also employing Support Vector Machines (SVM) and linear discriminant based classifiers. A novel normalization technique based on minimizing the squared correlation coefficients between expression levels of gene pairs is proposed and evaluated along with the other methods. Our results suggest that most normalization methods helped classification on the datasets considered except the rank method, most likely due to its quantization effects.
520 $a Another contribution of this research is in developing machine learning methods for incorporating an independent source of information, in the form of gene annotations, to analyze microarray data. Recently, genes of many organisms have been annotated with terms from a limited vocabulary called Gene Ontologies (GO), describing the genes' roles in various biological processes, molecular functions and their locations within the cell. Novel probabilistic generative models are proposed for clustering genes using both their expression levels and GO tags. These models are similar in essence to the ones used for multimodal data, such as images and words, with learning and inference done in a Bayesian framework. The multimodal generative models are used for phenotypic class prediction. More specifically, the problems of phenotype prediction for static gene expression data and state prediction for time-course data are emphasized. Using GO tags for organisms whose genes have been studied more comprehensively leads to an improvement in prediction. Our methods also have the potential to provide a way to assess the quality of available GO tags for the genes of various model organisms.
590 $a School code: 0009.
650 4 $a Engineering, Biomedical. $3 227004
650 4 $a Engineering, Electronics and Electrical. $3 226981
650 4 $a Biology, Bioinformatics. $3 264207
690 $a 0541
690 $a 0544
690 $a 0715
710 2 $a The University of Arizona. $b Electrical & Computer Engineering. $3 492953
773 0 $t Dissertation Abstracts International $g 71-05B.
790 1 0 $a Barnard, Jacobus, $e advisor
790 1 0 $a Rodriguez, Jeffrey $e committee member
790 1 0 $a Hua, Hong $e committee member
790 $a 0009
791 $a Ph.D.
792 $a 2010
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3402871