Comparative Evaluation of Set-level Techniques in Predictive Classification of Gene Expression Samples

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F12%3A00193325" target="_blank" >RIV/68407700:21230/12:00193325 - isvavai.cz</a>

Result on the web

<a href="http://www.biomedcentral.com" target="_blank" >http://www.biomedcentral.com</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1186/1471-2105-13-S10-S15" target="_blank" >10.1186/1471-2105-13-S10-S15</a>

Result language

angličtina

Original language name

Comparative Evaluation of Set-level Techniques in Predictive Classification of Gene Expression Samples

Original language description

Background: Analysis of gene expression data in terms of a priori defined gene sets has recently received significant attention as this approach typically yields more compact and interpretable results than those produced by traditional methods that relyon individual genes. The set level strategy can also be adopted with similar benefits in predictive classification tasks accomplished with machine learning algorithms. Initial studies into the predictive performance of set level classifiers have yieldedrather controversial results. The goal of this study is to provide a more conclusive evaluation by testing various components of the set level framework within a large collection of machine learning experiments. Results: Genuine curated gene sets constitute better features for classification than sets assembled without biological relevance. For identifying the best gene sets for classification, the Global test outperforms the gene set methods GSEA and SAM GS as well as two generic featur

Czech name

—

Czech description

—

Type

J_x - Unclassified - Peer-reviewed scientific article (Jimp, Jsc and Jost)

CEP classification

IN - Informatics

OECD FORD branch

—

Project

<a href="/en/project/GA201%2F09%2F1665" target="_blank" >GA201/09/1665: Bridging the gap between system biology and machine learning</a><br>

Continuities

Z - Vyzkumny zamer (s odkazem do CEZ)

Publication year

2012

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

BMC Bioinformatics

ISSN

1471-2105

e-ISSN

—

Volume of the periodical

12

Issue of the periodical within the volume

13

Country of publishing house

GB - UNITED KINGDOM

Number of pages

29

Pages from-to

"S15"

UT code for WoS article

000306140100015

EID of the result in the Scopus database

—