On safari to Random Jungle: a fast implementation of Random Forests for high-dimensional data - PubMed (original) (raw)

On safari to Random Jungle: a fast implementation of Random Forests for high-dimensional data

Daniel F Schwarz et al. Bioinformatics. 2010.

Erratum in

Abstract

Motivation: Genome-wide association (GWA) studies have proven to be a successful approach for helping unravel the genetic basis of complex genetic diseases. However, the identified associations are not well suited for disease prediction, and only a modest portion of the heritability can be explained for most diseases, such as Type 2 diabetes or Crohn's disease. This may partly be due to the low power of standard statistical approaches to detect gene-gene and gene-environment interactions when small marginal effects are present. A promising alternative is Random Forests, which have already been successfully applied in candidate gene analyses. Important single nucleotide polymorphisms are detected by permutation importance measures. To this day, the application to GWA data was highly cumbersome with existing implementations because of the high computational burden.

Results: Here, we present the new freely available software package Random Jungle (RJ), which facilitates the rapid analysis of GWA data. The program yields valid results and computes up to 159 times faster than the fastest alternative implementation, while still maintaining all options of other programs. Specifically, it offers the different permutation importance measures available. It includes new options such as the backward elimination method. We illustrate the application of RJ to a GWA of Crohn's disease. The most important single nucleotide polymorphisms (SNPs) validate recent findings in the literature and reveal potential interactions.

Availability: The RJ software package is freely available at http://www.randomjungle.org

PubMed Disclaimer

Figures

Fig. 1.

Fig. 1.

Comparison of computing time and memory usage of several RF implementations. Each program analyzed a simulated dataset comprising 1006 samples genotyped at 275 153 SNPs. A short bar indicates a fast implementation of RF in comparison to other programs: (a) Comparison of computing time of five implementations. The figure reads for example: For analyzing data, RJ calculations took 0.53 h. (b) Comparison of memory usage of five programs. Memory was sparsely used by Willows and RJ in comparison to randomForest and RF in Fortran. (Asterisk indicates memory usage of each computer node.)

Fig. 2.

Fig. 2.

CVI scores of SNPs and their chromosomal position. The axis of CVI scores was log transformed. Small and negative CVI values were omitted.

Fig. 3.

Fig. 3.

Six of the 10 most important genes can be combined to a potential pathway. TNFSF10 potentially interacts with IL23R, NOD2 and PRKG1. The NOD2 conceivably interacts with CDKAL1.

Similar articles

Cited by

References

    1. Archer KJ, Kimes RV. Empirical characterization of random forest variable importance measures. Comput. Stat. Data Anal. 2008;52:2249–2260.
    1. Baader E, et al. Tumor necrosis factor-related apoptosis-inducing ligand-mediated proliferation of tumor cells with receptor-proximal apoptosis defects. Cancer Res. 2005;65:7888–7895. - PubMed
    1. Baetu TM, et al. Disruption of NF-kappaB signaling reveals a novel role for NF-kappaB in the regulation of TNF-related apoptosis-inducing ligand expression. J. Immunol. 2001;167:3164–3173. - PubMed
    1. Barrett JC, et al. Genome-wide association defines more than 30 distinct susceptibility loci for Crohn's disease. Nat. Genet. 2008;40:955–962. - PMC - PubMed
    1. Breiman L. Bagging predictors. Mach. Learn. 1996;24:123–140.

Publication types

MeSH terms

Grants and funding

LinkOut - more resources