Genomewide Multiple-Loci Mapping in Experimental Crosses by Iterative Adaptive Penalized Regression
Authors:
- 1 May 2010
- journal article
- Published by Oxford University Press (OUP) in Genetics
- Vol. 185 (1) , 349-359
Abstract
Genomewide multiple-loci mapping can be viewed as a challenging variable selection problem where the major objective is to select genetic markers related to a trait of interest. It is challenging because the number of genetic markers is large (often much larger than the sample size) and there is often strong linkage or linkage disequilibrium between markers. In this article, we developed two methods for genomewide multiple loci mapping: the Bayesian adaptive Lasso and the iterative adaptive Lasso. Compared with eight existing methods, the proposed methods have improved variable selection performance in both simulation and real data studies. The advantages of our methods come from the assignment of adaptive weights to different genetic makers and the iterative updating of these adaptive weights. The iterative adaptive Lasso is also computationally much more efficient than the commonly used marginal regression and stepwise regression methods. Although our methods are motivated by multiple-loci mapping, they are general enough to be applied to other variable selection problems.Keywords
This publication has 40 references indexed in Scilit:
- A Bayesian Partition Method for Detecting Pleiotropic and Epistatic eQTL ModulesPLOS Computational Biology, 2010
- Hierarchical Generalized Linear Models for Multiple Quantitative Trait Locus MappingGenetics, 2009
- One-step sparse estimates in nonconcave penalized likelihood modelsThe Annals of Statistics, 2008
- Simultaneous Analysis of All SNPs in Genome-Wide and Re-Sequencing Association StudiesPLOS Genetics, 2008
- Integrating large-scale functional genomic data to dissect the complexity of yeast regulatory networksNature Genetics, 2008
- On the “degrees of freedom” of the lassoThe Annals of Statistics, 2007
- An Efficient Bayesian Model Selection Approach for Interacting Quantitative Trait Loci Models With Many EffectsGenetics, 2007
- A new multipoint method for genome-wide association studies by imputation of genotypesNature Genetics, 2007
- Mathematical multi-locus approaches to localizing complex human trait genesNature Reviews Genetics, 2003
- Trans-acting regulatory variation in Saccharomyces cerevisiae and the role of transcription factorsNature Genetics, 2003