東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Context-sensitive methods for learni...

Myers, Chad L.

FindBook

Google Book

Amazon

博客來

Context-sensitive methods for learning from genomic data.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Context-sensitive methods for learning from genomic data./
作者:	Myers, Chad L.
面頁冊數:	233 p.
附註:	Source: Dissertation Abstracts International, Volume: 68-12, Section: B, page: 8142.
Contained By:	Dissertation Abstracts International68-12B.
標題:	Biology, Bioinformatics. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3295311
ISBN:	9780549401155

Context-sensitive methods for learning from genomic data.
Myers, Chad L.

Context-sensitive methods for learning from genomic data. - 233 p.

Source: Dissertation Abstracts International, Volume: 68-12, Section: B, page: 8142.

Thesis (Ph.D.)--Princeton University, 2008.

Recent developments in biotechnology have enabled high-throughput measurement of several cellular phenomena including gene expression, protein-protein interactions, protein localization, and DNA sequences. The wealth of data generated by this technology promises to support computational prediction of network models, but so far, successful approaches that translate these data into accurate, experimentally testable hypotheses have been limited. This dissertation focuses on machine learning and signal processing approaches that utilize contextual clues often inherent in genomic data to extract useful information and make precise predictions.

ISBN: 9780549401155Subjects--Topical Terms:

1018415
Biology, Bioinformatics.

Context-sensitive methods for learning from genomic data.
LDR:03052nam 2200289 a 45 001 939113
005 20110512
008 110512s2008 ||||||||||||||||| ||eng d
020 $a 9780549401155
035 $a (UMI)AAI3295311
035 $a AAI3295311
040 $a UMI $c UMI
100 1 $a Myers, Chad L. $3 1263104
245 1 0 $a Context-sensitive methods for learning from genomic data.
300 $a 233 p.
500 $a Source: Dissertation Abstracts International, Volume: 68-12, Section: B, page: 8142.
502 $a Thesis (Ph.D.)--Princeton University, 2008.
520 $a Recent developments in biotechnology have enabled high-throughput measurement of several cellular phenomena including gene expression, protein-protein interactions, protein localization, and DNA sequences. The wealth of data generated by this technology promises to support computational prediction of network models, but so far, successful approaches that translate these data into accurate, experimentally testable hypotheses have been limited. This dissertation focuses on machine learning and signal processing approaches that utilize contextual clues often inherent in genomic data to extract useful information and make precise predictions.
520 $a First, we describe methods for using microarray technology to detect chromosomal aberrations. Amplification and deletion of portions of chromosomes often serve as a mechanism of rapid adaptation and have been associated with numerous cancers. Accurate and precise identification of when and where these changes occur will help us understand this important adaptive mechanism and is an important step towards effective cancer treatment.
520 $a Secondly, we address the more general problem of integrating diverse types of functional genomic data to understand gene function and predict biological networks. We demonstrate that Bayesian methods can leverage unique noise characteristics of genomic data to predict accurate network models. We illustrate the practical use of these methods in a web-based system that supports intelligent exploration of large repositories of noisy genomic data. We have used this system to generate specific hypotheses about previously uncharacterized genes, many of which have been confirmed through experimental validation.
520 $a Finally, this dissertation addresses the question of how to use machine learning methods to direct genome-scale experiments. Until now, most bioinformatics methods have been used exclusively downstream of data-generating experiments. Here, we discuss approaches for using computational predictions to actually direct further large-scale experiments. We demonstrate that such approaches can dramatically improve the efficiency with which we use high-throughput genomic technology and, ultimately, help us to discover more novel biology.
590 $a School code: 0181.
650 4 $a Biology, Bioinformatics. $3 1018415
650 4 $a Computer Science. $3 626642
690 $a 0715
690 $a 0984
710 2 $a Princeton University. $3 645579
773 0 $t Dissertation Abstracts International $g 68-12B.
790 $a 0181
791 $a Ph.D.
792 $a 2008
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3295311