Fuzzy Forests

Fuzzy forests, a new algorithm based on random forests, is designed to reduce the bias seen in random forest feature selection caused by the presence of correlated features. Fuzzy forests uses recursive feature elimination random forests to select features from separate blocks of correlated features where the correlation within each block of features is high and the correlation between blocks of features is low. One final random forest is fit using the surviving features. This package fits random forests using the 'randomForest' package and allows for easy use of 'WGCNA' to split features into distinct blocks. See D. Conn, Ngun, T., C. Ramirez, and G. Li (2019) for further details.

fuzzyforest

fuzzyforest is an extension of random forests designed to yield less biased variable importance rankings when features are correlated with one another. The algorithm requires that features be partitioned into seperate groups or modules such that the correlation within groups are large and the correlation between groups is small. fuzzyforest allows for easy integration the package WGCNA.

• the latest released version can be downloaded from CRAN: install.packages("fuzzyforest")

To enable use of the full functionality of fuzzyforest packages WGCNA must be installed. However, WGCNA requires the installation of a few packages form bioConductor. To install WGCNA, type the following lines into the console:

setRepositories(ind=1:2)  
install.packages("WGCNA")
source("http://bioconductor.org/biocLite.R")
biocLite("AnnotationDbi", type="source")
biocLite("GO.db")

If further issues with the installation of WGCNA arise see the WGCNA website: http://labs.genetics.ucla.edu/horvath/CoexpressionNetwork/Rpackages/WGCNA/index.html#manualInstall

Acknowledgments

This work is partially supported through NSF grant IIS 1251151.