Dataset Information

Network-based penalized regression with application to genomic data.

ABSTRACT: 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.

SUBMITTER: Kim S

PROVIDER: S-EPMC4007772 | biostudies-literature | 2013 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Network-based penalized regression with application to genomic data.

Kim Sunkyung S Pan Wei W Shen Xiaotong X

Biometrics 20130703 3

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 how ...[more]

PMID: 23822182

Similar Datasets

Project description:Omics data integration is becoming necessary to investigate the still unknown genomic mechanisms of complex diseases. During the integration process, many challenges arise such as data heterogeneity, the smaller number of individuals in comparison to the number of parameters, multicollinearity, and interpretation and validation of results due to their complexity and lack of knowledge about biological mechanisms. To overcome some of these issues, innovative statistical approaches are being developed. In this work, we applied penalized regression methods (LASSO and ENET) to explore relationships between common genetic variants, DNA methylation and gene expression measured in bladder tumor samples and have proposed a permutation-based method to concomitantly assess significance and correct by multiple testing with the MaxT algorithm. The overall analysis flow consisted of three steps: (1) SNPs/CpGs were selected per each gene probe within 1Mb window upstream and downstream the gene; (2) LASSO and ENET were applied to assess the association between each expression probe and the selected SNPs/CpGs in three multivariable models (SNP, CPG, and Global models, the latter integrating SNPs and CPGs); and (3) the significance of each model was assessed using the permutation-based MaxT method. We identified 48 genes whom expression levels were associated with both SNPs and GPGs. Importantly, we replicated results for 36 (75%) of them in an independent data set (TCGA). We checked the performance of the proposed method with a simulation study and further supported our results with a biological interpretation based on an enrichment analysis. The approach we propose allows reducing computational time and is flexibly and easy to implement when analyzing several omics data. Our results highlight the importance of integrating omics data by applying appropriate statistical strategies to discover new insights into the complexity of disease genetic mechanisms. Gene expression data were obtained from 44 tumor samples using the Affymetrix DNA Microarray Human Gene 1.0 ST Array with 32,321 probes.

Project description:Omics data integration is becoming necessary to investigate the still unknown genomic mechanisms of complex diseases. During the integration process, many challenges arise such as data heterogeneity, the smaller number of individuals in comparison to the number of parameters, multicollinearity, and interpretation and validation of results due to their complexity and lack of knowledge about biological mechanisms. To overcome some of these issues, innovative statistical approaches are being developed. In this work, we applied penalized regression methods (LASSO and ENET) to explore relationships between common genetic variants, DNA methylation and gene expression measured in bladder tumor samples and have proposed a permutation-based method to concomitantly assess significance and correct by multiple testing with the MaxT algorithm. The overall analysis flow consisted of three steps: (1) SNPs/CpGs were selected per each gene probe within 1Mb window upstream and downstream the gene; (2) LASSO and ENET were applied to assess the association between each expression probe and the selected SNPs/CpGs in three multivariable models (SNP, CPG, and Global models, the latter integrating SNPs and CPGs); and (3) the significance of each model was assessed using the permutation-based MaxT method. We identified 48 genes whom expression levels were associated with both SNPs and GPGs. Importantly, we replicated results for 36 (75%) of them in an independent data set (TCGA). We checked the performance of the proposed method with a simulation study and further supported our results with a biological interpretation based on an enrichment analysis. The approach we propose allows reducing computational time and is flexibly and easy to implement when analyzing several omics data. Our results highlight the importance of integrating omics data by applying appropriate statistical strategies to discover new insights into the complexity of disease genetic mechanisms. Bisulphite modification of 46 tumor DNA samples using EZ-96 DNA METHYLATIONGOLD KIT (Zymo Research, Irvin, CA, USA), CpG methylation data was generated using the Infinum Human Methylation 27 BeadChip Kit that detected the CpG sites with two probes, one designed against the unmethylated site (signal U) and the other against the methylated site (signal M).

Dataset Information

Network-based penalized regression with application to genomic data.

Publications

Network-based penalized regression with application to genomic data.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure