CCA: An R Package to Extend Canonical Correlation Analysis

By Ignacio González, Sébastien Déjean, Pascal G. P. Martin, Alain Baccini. 2008

363 citations recorded by the source corpus.

Canonical correlations analysis (CCA) is an exploratory statistical method to highlight correlations between two data sets acquired on the same experimental units. The cancor() function in R (R Development Core Team 2007) performs the core of computations but further work was required to provide the user with additional tools to facilitate the interpretation of the results. We implemented an R package, CCA, freely available from the Comprehensive R Archive Network (CRAN, http://CRAN.R-project.org/), to develop numerical and graphical outputs and to enable the user to handle missing values. The CCA package also includes a regularized version of CCA to deal with data sets with more variables than units. Illustrations are given through the analysis of a data set coming from a nutrigenomic study in the mouse.

Subfields: Molecular Biology

View Paper: https://www.semanticscholar.org/paper/95d378c8ae42b2c3cce5c6255fc5755e2b821538

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Molecular Biology

Citations in the corpus

integrOmics: an R package to unravel relationships between two omics datasets (2009, neutral): “Vinod (1976) and González et al. (2008), therefore, introduced l2 penalties on the covariance matrices so as to make them invertible in a ridge CCA (rCCA).”
Sparse kernel canonical correlation analysis for discovery of nonlinear interactions in high-dimensional data (2017, methodology): “We then analyzed a nutrigenomic dataset from a previous mouse study [22, 23].”
mixOmics: An R package for ‘omics feature selection and multiple data integration (2017, methodology): “Unsupervised analyses methods include Principal Component Analysis—based on NonLinear Iterative Partial Least Squares for missing values [18], Independent Component Analysis [19], Partial Least Squares regression—PLS, also known as Projection to Latent Structures [20], multi-group PLS [21], regulari”
Bayesian Canonical correlation analysis (2013, methodology): “We followed Gonzales et al. (2008) as the reference implementation of a regularized CCA, but replaced the leave-one-out validation for the two regularization parameters with 20-fold cross-validation instead, after verifying that it does not result in statistically significant differences in accuracy”
Succession of microbial consortia in the developing infant gut microbiome (2010, methodology): “An RCCAwas performed to highlight correlations between the phylum abundance matrix (X of order n × p) and the gene functions matrix (Y of order n × q) retrieved from metagenomics as well as bacterial phyla and SCFAs using the R software CCA package (40).”
Bayesian group factor analysis with structured sparsity (2016, methodology): “…of GFA that allows element-wise sparsity with independent ARD priors (sGFA) (Khan et al., 2014; Suvitaival et al., 2014), a regularized version of CCA (RCCA) (González et al., 2008), sparse CCA (SCCA) (Witten and Tibshirani, 2009), and Bayesian joint factor analysis (JFA) (Ray et al., 2014).”