This package provides functions for calculating the Gini, the Pearson, the Spearman, the Kendall and Tukey's Biweight correlations, Compared to the other mentioned correlation methods, the GCC may perform better to detect regulatory relationships from gene expression data. In addition, the GCC also has some other advantageous merits, such as independent of distribution forms, more capable of detecting non-linear relationships, more tolerant to outliers and less dependence on sample size. For more information about these correlation methods, please refer to (Ma and Wang, 2012). This package also provides an graphical user interface (GUI) to perform clustering analysis of microarray and RNA-Seq data in a coherent step-by-step manner.
1) The implement of rsgcc requires several R packages developed by other developers(e.g., biwt, cairoDevice, fBasics, snowfall, grDevices, gplots, gWidgets, gWidgetsRGtk2, stringr, ctc). Please make sure that these packages have been successfully installed before loading the rsgcc package.
2) A general method to install a new package on the computer is to use the command:
Some other methods can be found at http://math.usask.ca/~longhai/software/installrpkg.html.
For the installation of ctc package, please use the biocLite resource with the following commands:
3) To run the "rsgcc.gui()" function, please do remember to select the GUI toolkit "gWidgetsRGtk2".
4) Bug reports and suggestions/questions can be sent to Chuang Ma (firstname.lastname@example.org) or Xiangfeng Wang (email@example.com).
Chuang Ma, Xiangfeng Wang. Maintainer: Chuang Ma <firstname.lastname@example.org>
Chuang Ma, Xiangfeng Wang. Application of the Gini correlation coefficient to infer regulatory relationships in transcriptome analysis. Plant Physiology, 2012, 160(1):192-203.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.