(1)Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing 100080;(2)The Institute of Theoretical Physics, Chinese Academy of Sciences, Beijing 100080
In this paper, grouped weight matrix (GWM) method is proposed for splice site recognition. The GWM model for splice signals is a mixture of weight matrix models (WMM) with unknown number of components. For computation of the unknown parameters' MLE, the EM method is applied; and the number of components is determined by using the gap statistics. The algorithm for the whole procedure is given. The GWM procedure is applied to donor and acceptor recognition of human and rice genome, and compared with the commonly applied methods. The results show that the GWM provides higher accuracy.
Gao Shaogen
, Li Guoying
, Zheng Weimou. , {{custom_author.name_en}}.
GROUPED WEIGHT MATRIX FOR SPLICE SITE RECOGNITION. Journal of Systems Science and Mathematical Sciences, 2007, 27(1): 51-58 https://doi.org/10.12341/jssms08740