Gaussian Mixture Model for automatic motif finding in promoter sequences

Motif finding is an important part of bioinformatics studies. This paper proposed an algorithm used for automatic motif finding. Gaussian Mixture Model is applied to build a motifs finding model in promoter sequence. The fuzzy cluster is used to determine the optimal numbers of GMM components and apply the initial values for the expectation maximization (EM) algorithm which is used to obtain the parameter estimates. The approach can identify the most important motifs around transcription start site and can also be used for other biological functional sequences motif finding. The simulation results show the proposed method is more effective for different motif finding than finding tools proposed in paper [10] and improves the precision of detection.