Signal models

GENSCAN uses different signal models to model different functional units. One of the models is weight matrix model (WMM) in which every position has its own specific independent distribution. It is used for modeling polyadenylation signals, translation initiation signal, translation termination signal and promoters. Another model is the the weighted array model (WAM). The WAM model is a generalization of the WMM model that allows dependencies between adjacent positions. The WAM model is used for the recognition of the splice sites ([7] p. 61). Correct recognition of these sites greatly enhances ability to predict correct exon boundaries. This modeling of splice sites gave GENESCAN a substantial improvement in performance.