Abstract
To determine the level of expression of a gene whole in different conditions, the biologist prepares a DNA microarray by condition and in every microarray; we find the level of expression of every gene in the corresponding condition. After the read picture analysis from DNA microarray, the biologist gets a picture to duplicate spliced Xij (i=1,... n; j=1,..., m) where, n represents the number of genes and m represents the number of conditions. The gotten picture contains the evolution of the quantity of transcriptorn according to various applied conditions. This picture which represents a context to several values will be used in entrance of the stage of genes classification. In this paper, we present a method of associative rule generation from DNA microarray based on "conceptual scaling". The generated rules express behaviors of a gene whole related to whole experiences; these behaviors can be identical (same level of expression) or different (level of expression different from a gene to another).