The data consist of the gene expression profiles measured from Affymetrix human 95Av2 arrays for 128 individuals with Acute Lymphoblastic Leukemia (ALL). The ALL package on Bioconductor contains the entire data set with a variety of covariates for each individual. We are primarily interested in the gene expression profiles and the assigned molecular biology of the cancer (mainly for those with B-cell ALL), BCR/ABL, ALL/AF4, and E2APBX etc. for machine learning studies including classification and clustering.

The ALL data have been studied in numerous journal articles and online resources.

We have collected the ALL data from the ALL package on Bioconductor. The robust multichip average (RMA) normalization method has been applied to all 12,625 gene expression levels.

Link to Original Paper

@article{Chiaretti:2004gq,
author = {Chiaretti, S. and Li, X. and Gentleman, R. and Vitale, A. and Vignetti, M. and Mandelli, F. and Ritz, J. and Foa, R.},
title = {{Gene expression profile of adult T-cell acute lymphocytic leukemia identifies distinct subsets of patients with different response to therapy and survival}},
journal = {Blood},
year = {2004},
volume = {103},
number = {7},
pages = {2771--2778}
}

TODO