Reference : GenePEN: analysis of network activity alterations in complex diseases via the pairwis...

	Document type :	Scientific journals : Article
	Discipline(s) :	Life sciences : Biotechnology
	To cite this reference:	http://hdl.handle.net/10993/19958

Title :	GenePEN: analysis of network activity alterations in complex diseases via the pairwise elastic net
Language :	English
Author, co-author :	Vlassis, Nikos [Adobe Research > Systems Technology Lab/Imagination Lab]
	Glaab, Enrico [University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB) > >]
Publication date :	2015
Journal title :	Statistical Applications in Genetics and Molecular Biology
Publisher :	University of California, Berkeley
Volume :	14
Issue/season :	2
Pages :	221-224
Peer reviewed :	Yes (verified by ORBilu)
Audience :	International
ISSN :	1544-6115
City :	Berkeley
Country :	CA
Keywords :	[en] machine learning ; microarray analysis ; network analysis
Abstract :	[en] Complex diseases are often characterized by coordinated expression alterations of genes and proteins which are grouped together in a molecular network. Identifying such interconnected and jointly altered gene/protein groups from functional omics data and a given molecular interaction network is a key challenge in bioinformatics. <br />We describe GenePEN, a penalized logistic regression approach for sample classification via convex optimization, using a newly designed Pairwise Elastic Net penalty that favors the selection of discriminative genes/proteins according to their connectedness in a molecular interaction graph. An efficient implementation of the method finds provably optimal solutions on high-dimensional omics data in a few seconds and is freely available at http://lcsb-portal.uni.lu/bioinformatics.Complex diseases are often characterized by coordinated expression alterations of genes and proteins which are grouped together in a molecular network. Identifying such interconnected and jointly altered gene/protein groups from functional omics data and a given molecular interaction network is a key challenge in bioinformatics. <br />We describe GenePEN, a penalized logistic regression approach for sample classification via convex optimization, using a newly designed Pairwise Elastic Net penalty that favors the selection of discriminative genes/proteins according to their connectedness in a molecular interaction graph. An efficient implementation of the method finds provably optimal solutions on high-dimensional omics data in a few seconds and is freely available at http://lcsb-portal.uni.lu/bioinformatics.
Research centres :	Luxembourg Centre for Systems Biomedicine (LCSB): Biomedical Data Science (Glaab Group) ; Luxembourg Centre for Systems Biomedicine (LCSB): Bioinformatics Core (R. Schneider Group) ; Luxembourg Centre for Systems Biomedicine (LCSB): Machine Learning (Vlassis Group)
Target :	Researchers ; Professionals ; Students
Permalink :	http://hdl.handle.net/10993/19958
	also: http://hdl.handle.net/10993/20293
DOI :	10.1515/sagmb-2014-0045
Other URL :	http://www.degruyter.com/view/j/sagmb.2015.14.issue-2/sagmb-2014-0045/sagmb-2014-0045.xml

	File(s) associated to this reference
	Fulltext file(s): File Commentary Version Size Access Open access sagmb-2014-0045.pdf Publisher postprint 274.29 kB View/Open

All documents in ORBi^lu are protected by a user license.

 

University of Luxembourg Library |  Feedback |  Legal notices Site Map