Motif Extraction: Normalization of Scores

Y. Fujiwara [1] (yukiko@csl.cl.nec.co.jp)
M. Asogawa [2] (asogawa@csl.cl.nec.co.jp)

[1] Computer System Research Laboratory, C&C Research Laboratories,
NEC Corporation
4-1-1, Miyazaki, Miyamae-ku, Kawasaki, Kanagawa 216 Japan
[2] Massively Parallel Systems NEC Laboratory, RWCP

This paper examines a method to normalize a score of a stochastic motif, represented by a hidden Markov model (HMM). The accuracy of the Z score method, which is one of the score normalization method, is compared with that of the whole search method.