Network-Based Penalized Regression With Application to Genomic Data

Penalized regression approaches are attractive in dealing with high-dimensional data such as arising in high-throughput genomic studies. New methods have been introduced to utilize the network structure of predictors, for example, gene networks, to improve parameter estimation and variable selection...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Biometrics Ročník 69; číslo 3; s. 582 - 593
Hlavní autori: Kim, Sunkyung, Pan, Wei, Shen, Xiaotong
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: England Blackwell Publishing Ltd 01.09.2013
International Biometric Society
Predmet:
algorithms
BIOMETRIC METHODOLOGY
Biometry - methods
breast neoplasms
Breast Neoplasms - genetics
Data analysis
data collection
Databases, Genetic - statistics & numerical data
Female
Gene Expression
Gene Regulatory Networks
genes
Genes, BRCA1
Genes, BRCA2
Genes, p53
Genomics
Genomics - statistics & numerical data
High-Throughput Nucleotide Sequencing - statistics & numerical data
Humans
Models, Statistical
Networks analysis
Nonconvex minimization
Penalty
Regression Analysis
Truncated Lasso penalty
Gene expression
Truncated Lasso penalty
Networks analysis
Penalty
Nonconvex minimization
ISSN:0006-341X, 1541-0420, 1541-0420
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Penalized regression approaches are attractive in dealing with high-dimensional data such as arising in high-throughput genomic studies. New methods have been introduced to utilize the network structure of predictors, for example, gene networks, to improve parameter estimation and variable selection. All the existing network-based penalized methods are based on an assumption that parameters, for example, regression coefficients, of neighboring nodes in a network are close in magnitude, which however may not hold. Here we propose a novel penalized regression method based on a weaker prior assumption that the parameters of neighboring nodes in a network are likely to be zero (or non-zero) at the same time, regardless of their specific magnitudes. We propose a novel non-convex penalty function to incorporate this prior, and an algorithm based on difference convex programming. We use simulated data and two breast cancer gene expression datasets to demonstrate the advantages of the proposed methods over some existing methods. Our proposed methods can be applied to more general problems for group variable selection.
Bibliografia:ark:/67375/WNG-7KLQ0JRJ-6
ArticleID:BIOM12035
istex:C4251D76F178792B11638ED8823AD4868118EB9E
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-1
ObjectType-Feature-2
content type line 23
ISSN:0006-341X
1541-0420
1541-0420
DOI:10.1111/biom.12035