The ability to measure genome-wide expression holds great promise for characterizing cells and distinguishing diseased from normal tissues. Thus far, microarray technology has only been useful for measuring relative expression between two or more samples, which has handicapped its ability to classify tissue types. This paper presents the first method that can successfully predict tissue type based on data from a single hybridization. A preliminary web-tool is available at http://rafalab.jhsph.edu/barcode/ The high throughput analysis of cells and tissues is revolutionizing biological research. The ability of microarrays to measure thousands of RNA transcripts at one time allows for the characterization of cells and tissues in greater depth than was previously possible, but has not yet led to big advances in diagnosis or treatment. The main reason for this is that feature characteristics, such as probe sequence, can cloud the relationship between observed intensity and actual expression. Although this probe effect is large, it is also very consistent across different hybridizations, which implies that relative measures of expression are substantially more useful than absolute ones 1, 2 . To understand this, consider that when comparing intensities from different hybridizations for the same gene, the probe effect is very similar and cancels out. On the other hand, when comparing intensities for two genes from the same hybridization, the different probe effects can alter the observed differences. For this reason the overwhelming majority of results based on microarray data rely on measures of relative expression: genes are reported to be differentially expressed rather than expressed or unexpressed.Approaches for thresholding noisy data have been successfully used in many applications including microarray studies 3, 4 . We used this as motivation to develop the first method that can accurately demarcate expressed from unexpressed genes and therefore defines a unique gene expression barcode for each tissue type. To do this we took advantage of the vast amount of publicly available datasets. These data were also used to assess the algorithm. With clinical data, we find near perfect predictability of normal from diseased tissue for three cancer studies and one Alzheimer's disease study. The barcode method also discovers new tumor subsets in previously published breast cancer studies that can be used for the prognosis of tumor recurrence and survival time.