CSFA {CSFA}R Documentation

Computing connectivity scores with Factor Analysis methodology.

Description

CSFA is a wrapper of multiple packages containing a factor analysis method. These methods are used to derive the the connectivity scores of reference gene signatures with one or multiple query signatures. CSFA will apply them, output the scores and immediately produce a number of meaningful plots interactively. The included methods are PCA and MFA from the FactoMineR package, FABIA from the fabia package and Sparse PCA/MFA from the elasticnet package. Further, CSFA also contains an implementation of the Zhang and Gant score.

References

Abdi, H. et al. (2013), "Multiple factor analysis: principal component analysis for multitable and multiblock data sets," WIREs Comput Stat, 1-31.

Hochreiter, S. et al., "FABIA: Factor Analysis for Bicluster acquisition," Bioinformatics, 26, 1520-1527.

Lamb, J. et al. (2006), "The Connectivity Map: Using Gene-Expression Signatures to Connect Small Molecules, Genes, and Disease," Science, 313, 1929-1934.

Zhang, S.-D. and Gant, T.W. (2008), "A simple and robust method for connecting small-molecule drugs using gene-expression signatures," BMC Bioinformatics, 9, 10.

Working Paper: De Troyer E., Shkedzy Z., Kasim A. and Perualila-Tan N.-J. (2018), Connectivity Mapping Using Multiple Factor Analysis


[Package CSFA version 1.2.0 Index]