TY - GEN
T1 - Stratified random forest for genome-wide association study
AU - Wu, Qingyao
AU - Ye, Yunming
AU - Liu, Yang
AU - Ng, Michael
N1 - Copyright:
Copyright 2012 Elsevier B.V., All rights reserved.
PY - 2011
Y1 - 2011
N2 - For high dimensional genome-wide association (GWA) case-control data of complex disease, there are usually a large portion of single-nucleotide polymorphisms (SNPs) that are irrelevant with the disease. A simple random sampling method in random forest using default mtry parameter to choose feature subspace, will select too many subspaces without informative SNPs. Exhaustive searching an optimal mtry is often required in order to include useful and relevant SNPs and get rid of vast of non-informative SNPs. However, it is very time-consuming and not favorable in GWA study for high dimensional data. This paper proposes a stratified sampling method for feature subspace selection to generate decision trees in a random forest for GWA high-dimensional data. We employ two genome-wide SNP data sets (Parkinson case control data comprised of 408,803 SNPs and Alzheimer case control data comprised of 380,157 SNPs) to demonstrate that the proposed stratified sampling method is effective, and it can generate better random forest with higher accuracy and lower error bound than those by Breiman's random forest generation method.
AB - For high dimensional genome-wide association (GWA) case-control data of complex disease, there are usually a large portion of single-nucleotide polymorphisms (SNPs) that are irrelevant with the disease. A simple random sampling method in random forest using default mtry parameter to choose feature subspace, will select too many subspaces without informative SNPs. Exhaustive searching an optimal mtry is often required in order to include useful and relevant SNPs and get rid of vast of non-informative SNPs. However, it is very time-consuming and not favorable in GWA study for high dimensional data. This paper proposes a stratified sampling method for feature subspace selection to generate decision trees in a random forest for GWA high-dimensional data. We employ two genome-wide SNP data sets (Parkinson case control data comprised of 408,803 SNPs and Alzheimer case control data comprised of 380,157 SNPs) to demonstrate that the proposed stratified sampling method is effective, and it can generate better random forest with higher accuracy and lower error bound than those by Breiman's random forest generation method.
KW - Genome-wide association study
KW - random forest classifier
KW - significant SNP selection
KW - stratified sampling
UR - http://www.scopus.com/inward/record.url?scp=84862941007&partnerID=8YFLogxK
U2 - 10.1109/BIBM.2011.9
DO - 10.1109/BIBM.2011.9
M3 - Conference proceeding
AN - SCOPUS:84862941007
SN - 9780769545745
T3 - Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011
SP - 10
EP - 15
BT - Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011
T2 - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011
Y2 - 12 November 2011 through 15 November 2011
ER -