PLS Analyses for Genomics

Anne-Laure Boulesteix [email protected], Ghislain Durif [email protected], Sophie Lambert-Lacroix [email protected], Julie Peyre [email protected], and Korbinian Strimmer [email protected].

Maintainer: Ghislain Durif [email protected]

Routines for PLS-based genomic analyses, implementing PLS methods for classification with microarray data and prediction of transcription factor activities from combined ChIP-chip analysis. The >=1.2-1 versions include two new classification methods for microarray data: GSIM and Ridge PLS. The >=1.3 versions includes a new classification method combining variable selection and compression in logistic regression context: logit-SPLS; and an adaptive version of the sparse PLS.

You can install the CRAN version of the plsgenomics R package with the following R commands:

install.packages("plsgenomics")

To get the latest development version, you can install the github version:

devtools::install_github("gdurif/plsgenomics", subdir="pkg")

To install the devtools package, you can run:

install.packages("devtools")

You can also use the git repository available at https://github.com/gdurif/plsgenomics, then build and install the package with Rstudio (the project file is set accordingly) or with the R command line tools.

Or, once you cloned the git repository, you can run:

devtools::install("plsgenomics/pkg") # you should edit the path if necessary

The plsgenomics package is distributed under the GPL (>=2) licence.

Examples regarding the sparse PLS method and the sparse PLS approach for logistic regression developped in Durif et al. (2018) can be respectively found in these two scripts: spls_example.R and logit_spls_example.R.

Durif, G., Modolo, L., Michaelsson, J., Mold, J.E., Lambert-Lacroix, S., Picard, F., 2018. High dimensional classification with combined adaptive sparse PLS and logistic regression. Bioinformatics 34, 485–493. https://doi.org/10.1093/bioinformatics/btx571