Maximal conditional chi-square importance in random forests

MOTIVATION High-dimensional data are frequently generated in genome-wide association studies (GWAS) and other studies. It is important to identify features such as single nucleotide polymorphisms (SNPs) in GWAS that are associated with a disease. Random forests represent a very useful approach for this purpose, using a variable importance score. This importance score has several shortcomings. We propose an alternative importance measure to overcome those shortcomings. RESULTS We characterized the effect of multiple SNPs under various models using our proposed importance measure in random forests, which uses maximal conditional chi-square (MCC) as a measure of association between a SNP and the trait conditional on other SNPs. Based on this importance measure, we employed a permutation test to estimate empirical P-values of SNPs. Our method was compared to a univariate test and the permutation test using the Gini and permutation importance. In simulation, the proposed method performed consistently superior to the other methods in identifying of risk SNPs. In a GWAS of age-related macular degeneration, the proposed method confirmed two significant SNPs (at the genome-wide adjusted level of 0.05). Further analysis showed that these two SNPs conformed with a heterogeneity model. Compared with the existing importance measures, the MCC importance measure is more sensitive to complex effects of risk SNPs by utilizing conditional information on different SNPs. The permutation test with the MCC importance measure provides an efficient way to identify candidate SNPs in GWAS and facilitates the understanding of the etiology between genetic variants and complex diseases. CONTACT heping.zhang@yale.edu SUPPLEMENTARY INFORMATION Supplementary data are available at Bioinformatics online.

[1]  N. Risch.  Linkage strategies for genetically complex traits. I. Multilocus models. , 1990, American journal of human genetics.

[2]  Heping Zhang,et al.  A forest-based approach to identifying gene and gene–gene interactions , 2007, Proceedings of the National Academy of Sciences.

[3]  Yi Yu,et al.  Performance of random forest when SNPs are in linkage disequilibrium , 2009, BMC Bioinformatics.

[4]  C. Gieger,et al.  Genomewide association analysis of coronary artery disease. , 2007, The New England journal of medicine.

[5]  Heping Zhang,et al.  A tree-based method for modeling a multivariate ordinal response. , 2008, Statistics and its interface.

[6]  Heping Zhang,et al.  Cell and tumor classification using gene expression data: Construction of forests , 2003, Proceedings of the National Academy of Sciences of the United States of America.

[7]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[8]  J. Ott,et al.  Complement Factor H Polymorphism in Age-Related Macular Degeneration , 2005, Science.

[9]  A. Edwards,et al.  Complement Factor H Polymorphism and Age-Related Macular Degeneration , 2005, Science.

[10]  Stephen P. Daiger,et al.  Was the Human Genome Project Worth the Effort? , 2005, Science.

[11]  Ramón Díaz-Uriarte,et al.  Gene selection and classification of microarray data using random forest , 2006, BMC Bioinformatics.

[12]  F. Chu,et al.  Gene Selection and Cancer Classification Using a , 2004 .

[13]  Jean Marx.  Gene Offers Insight Into Macular Degeneration , 2006, Science.

[14]  Simon C. Potter,et al.  Genome-wide association study of 14,000 cases of seven common diseases and 3,000 shared controls , 2007, Nature.

[15]  A. Gylfason,et al.  A Common Variant on Chromosome 9p21 Affects the Risk of Myocardial Infarction , 2007, Science.

[16]  Yun Li,et al.  CFH haplotypes without the Y402H coding variant show strong association with susceptibility to age-related macular degeneration , 2006, Nature Genetics.

[17]  Insuk Sohn,et al.  A permutation-based multiple testing method for time-course microarray experiments , 2009, BMC Bioinformatics.

[18]  S. Daiger,et al.  Was the Human Genome Project Worth the Effort? , 2005, Science.

[19]  Heping Zhang,et al.  A genome-wide tree- and forest-based association analysis of comorbidity of alcoholism and smoking , 2005, BMC Genetics.

[20]  Jonathan C. Cohen,et al.  A Common Allele on Chromosome 9 Associated with Coronary Heart Disease , 2007, Science.

[21]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[22]  N. Risch.  Linkage strategies for genetically complex traits. II. The power of affected relative pairs. , 1990, American journal of human genetics.

[23]  J. Gilbert,et al.  Complement Factor H Variant Increases the Risk of Age-Related Macular Degeneration , 2005, Science.

[24]  Heping Zhang,et al.  Use of classification trees for association studies , 2000, Genetic epidemiology.

[25]  K. Lunetta,et al.  Identifying SNPs predictive of phenotype using random forests , 2005, Genetic epidemiology.

[26]  Yung-Seop Lee,et al.  Enriched random forests , 2008, Bioinform..

[27]  Rui Jiang,et al.  A random forest approach to the detection of epistatic interactions in case-control studies , 2009, BMC Bioinformatics.

[28]  K. Lunetta,et al.  Screening large-scale association study data: exploiting interactions using random forests , 2004, BMC Genetics.

[29]  C. Pang,et al.  Multiple gene polymorphisms in the complement factor h gene are associated with exudative age-related macular degeneration in chinese. , 2008, Investigative ophthalmology & visual science.

[30]  Ivana K. Kim,et al.  The NEI/NCBI dbGAP database: Genotypes and haplotypes that may specifically predispose to risk of neovascular age-related macular degeneration , 2008, BMC Medical Genetics.

[31]  Donald W. Bowden,et al.  The influence of carnosinase gene polymorphisms on diabetic nephropathy risk in African-Americans , 2009, Human Genetics.

[32]  Heping Zhang,et al.  Detecting significant single-nucleotide polymorphisms in a rheumatoid arthritis study using random forests , 2009 .

[33]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[34]  A. G. Heidema,et al.  A framework to identify physiological responses in microarray-based gene expression studies: selection and interpretation of biologically relevant genes. , 2008, Physiological genomics.