Binary Classification Disease Biomarker Data

This data set consists of 903 rows and 126018 columns in a tab delimited text file. The first 9 columns correspond to the sample meta data. The first column, sample, corresponds to a given donor. The second column, analysis_set, identifies the cohort as testing or training. The third column, process_lock,is an indicator of what process was used to create this particular set of arrays. The fourth column, Ab2, is the secondary antibody either Anti-IgA or Anti-IgG. The fifth column is diagnostic class either healthy or chagas. The sixth column,med_SCO, is the median ELISA S/CO values. The seventh column is the donors' age. The eigth column the donors' Gender listed as F (Female), M (Male), or U (Unknown). The 9th column, Ethnicity, provides any ethnicity information associated with the donor. The remaining 126009 correspond to the raw intensities associated with the peptide sequence that defines that column name.