This file contains microarray (genetic expression) data for 74 patients with two 
types of Leukemia: 
      ALL (Acute Lymphoblastic leukemia) and 
      AML (Acute Myelogenous Leukemia)

The original data had over 7,000 genes but this data has selected genes which have been 
already determined to be relevant.

In addition it has several field describing the sample: 
SNUM: sample number (note that the samples are not strictly ordered by sample number)
CLASS: Sample Class
Year: year sample taken
Gender: patient gender
BM_PB: subtype of leukemia
TB_if_ALL: subtype of ALL 
FAB_if_AML: subtype of AML
pct_Blasts: treatment related
Treatment_Response: outcome
PS: treatment related
Source: the hospital the data came from

Note that many of the sample values are missing and are represented by "?".

Fields D49950_at, etc correspond to gene expression values for the respective genes, measured by an Affymetrix chip.

The target field is Class.

In addition, you are provided with the following documentation about the fields.


SNUM: sample number
CLASS: ALL, AML.
BM_PB: discrete
TB_if_ALL: discrete
FAB_if_AML: discrete
Year: continuous.
Gender: M, F.
pct_Blasts: continuous.
Treatment_Response: discrete.
PS: continuous.
Source: discrete. 
D49950_at: continuous.
D63880_at: continuous.
J03473_at: continuous.
J05243_at: continuous.
L13278_at: continuous.
L47738_at: continuous.
M21551_rna1_at: continuous.
M55150_at: continuous.
M62762_at: continuous.
M81933_at: continuous.
M91432_at: continuous.
S50223_at: continuous.
U12471_cds1_at: continuous.
U32944_at: continuous.
U35451_at: continuous.
U50136_rna1_at: continuous.
U53468_at: continuous.
U72342_at: continuous.
U82759_at: continuous.
X15949_at: continuous.
X52142_at: continuous.
X56411_rna1_at: continuous.
X63469_at: continuous.
X74262_at: continuous.
X76061_at: continuous.
X76648_at: continuous.
X95735_at: continuous.
Y08612_at: continuous.
Y12670_at: continuous.
D38073_at: continuous.
AF012024_s_at: continuous.
D26156_s_at: continuous.
M84371_rna1_s_at: continuous.
M31211_s_at: continuous.
U09087_s_at: continuous.
U26266_s_at: continuous.
L49229_f_at: continuous.
M31523_at: continuous.
M28170_at: continuous.
U29175_at: continuous.