MProfiler: A Profile-Based Method for DNA Motif Discovery

Authors:
Doaa Altarawy;Mohamed A. Ismail;Sahar M. Ghanem
Affiliations:
Computer and Systems Engineering Dept. Faculty of Engineering, Alexandria University, Alexandria, Egypt 21544;Computer and Systems Engineering Dept. Faculty of Engineering, Alexandria University, Alexandria, Egypt 21544;Computer and Systems Engineering Dept. Faculty of Engineering, Alexandria University, Alexandria, Egypt 21544
Venue:
PRIB '09 Proceedings of the 4th IAPR International Conference on Pattern Recognition in Bioinformatics
Year:
2009

Citing 4
Cited 0

Unsupervised Learning of Multiple Motifs in Biopolymers Using Expectation Maximization

Machine Learning - Special issue on applications in molecular biology
BEST: Binding-site Estimation Suite of Tools

Bioinformatics
Detection of generic spaced motifs using submotif pattern mining

Bioinformatics
MotifVoter

Bioinformatics

Quantified Score

Hi-index	0.02

Visualization

Abstract

Motif Finding is one of the most important tasks in gene regulation which is essential in understanding biological cell functions. Based on recent studies, the performance of current motif finders is not satisfactory. A number of ensemble methods have been proposed to enhance the accuracy of the results. Existing ensemble methods overall performance is better than stand-alone motif finders. A recent ensemble method, MotifVoter, significantly outperforms all existing stand-alone and ensemble methods. In this paper, we propose a method, MProfiler, to increase the accuracy of MotifVoter without increasing the run time by introducing an idea called center profiling. Our experiments show improvement in the quality of generated clusters over MotifVoter in both accuracy and cluster compactness. Using 56 datasets, the accuracy of the final results using our method achieves 80% improvement in correlation coefficient nCC , and 93% improvement in performance coefficient nPC over MotifVoter.