This is fork of ramhiser/datamicroarray in order to have a persistent data source within the boost-R project.

datamicroarray

The R package datamicroarray provides a collection of scripts to download, process, and load small-sample, high-dimensional microarray data sets to assess machine learning algorithms and models. For each data set, we include a small set of scripts that automatically download, clean, and save the data set.

Data Sets

Each data set is listed below by the first author on the original paper. The data sets are organized them by category; note that most of the data sets are cancer-related. Click a data set to see its description, a link to the original paper, and additional information.

• Breast Cancer
  • Chin (2006)
  • Chowdary (2006)
  • Gravier (2010)
  • Sorlie (2001)
  • West (2001)
• Central Nervous System Disorders
  • Pomeroy (2002)
• Crohn's Disease
  • Burczynski (2006)
• Colon Cancer
  • Alon (1999)
• Glioma
  • Sun (2006)
• Huntington's Disease
  • Borovecki (2005)
• Leukemia
  • Chiaretti (2004)
  • Golub (1999)
  • Yeoh (2002)
• Lung Cancer
  • Gordon (2002)
• Lymphoma
  • Shipp (2002)
• Myeloma
  • Tian (2003)
• Prostate Cancer
  • Singh (2002)
• Sarcoma
  • Nakayama (2007)
• Small Round Blue Cell Tumors
  • Khan (2001)
• Miscellaneous
  • Christensen (2009)
  • Su (2002)
  • Subramanian (2005)

Installation

You can install the latest package version by typing the following at the R console:

library(devtools)
install_github('ramhiser/datamicroarray')

Note that you need to install the devtools package beforehand.

Usage

Once you have installed and loaded the datamicroarray package, you can load a data set with the data command. For example, to load the well-known Alon et al. (1999) Colon Cancer data set, type the following at the R console:

library(datamicroarray)
data('alon', package='datamicroarray')

After loading the data set, the resulting object is a named list with two elements:

1. x - the data matrix. The rows are the n observations, and the columns are the p features.
2. y - a factor vector of length n with the corresponding class labels.

Here is a summary for the Alon et al. (1999) Colon Cancer data set.

> dim(alon$x)
[1] 622000> table(alon$y)
nt2240

You can see all of the data sets available along with a brief summary of each with the describe_data helper function. Here it is in action:

> describe_data()
authoryearnpKDisease1alon19996220002ColonCancer2borovecki200531222832Huntington's Disease3 burczynski 2006 127 22283 3 Crohn'sDisease4chiaretti2004111126252Leukemia5chin2006118222152BreastCancer6chowdary2006104222832BreastCancer7christensen200921714133N/A8golub19997271293Leukemia9gordon2002181125332LungCancer10gravier201016829052BreastCancer11khan20016323084SRBCT12pomeroy20026071282CNSTumor13shipp20025868172Lymphoma14singh2002102126002ProstateCancer15sorlie2001854565BreastCancer16su200210255654N/A17subramanian200550101002N/A18tian2003173126252Myeloma19west20014971292BreastCancer20yeoh2002248126256Leukemia