Stefanie Scheid and Rainer Spang
A False Discovery Rate approach to separate the score distributions
of induced and non-induced genes
*******************************************************************

The distribution of scores for differential gene expression observed in
microarray experiments give rise to the assumption that the underlying
score distributions of induced and non-induced genes share wide
overlapping regions. Our aim is to reconstruct this mixture not only for
extremal score regions but over the whole range of scores. We propose
and evaluate a method based on the theory of False Discovery Rates.