A co-evolutionary framework for regulatory motif discovery

@inproceedings{citeulike:2738593, abstract = {In previous work, we have shown how an evolutionary algorithm with a clustered population can be used to concurrently discover multiple regulatory motifs present within the promoter sequences of co-expressed genes. In this paper, we extend the algorithm by co-evolving a population of Boolean classification rules in parallel with the motif population. Results using synthetic data suggest that this approach allows poorly conserved motifs to be identified in promoter sequences an order of magnitude longer than using population clustering alone, whilst results using muscle-specific promoter data show the algorithm is able to evolve meaningful sequence classifiers in parallel with motifs-suggesting that co-evolution provides a suitable framework for composite motif discovery within eukaryotic sequences.}, author = {Lones, Michael A. and Tyrrell, Andy M. }, booktitle = {Evolutionary Computation, 2007. CEC 2007. IEEE Congress on}, citeulike-article-id = {2738593}, doi = {10.1109/CEC.2007.4424978}, journal = {Evolutionary Computation, 2007. CEC 2007. IEEE Congress on}, keywords = {evolutionary}, pages = {3894--3901}, posted-at = {2008-04-30 14:26:07}, priority = {2}, title = {A co-evolutionary framework for regulatory motif discovery}, url = {http://dx.doi.org/10.1109/CEC.2007.4424978}, year = {2007} }

TY - CONF ID - citeulike:2738593 L3 - citeulike-article-id:2738593 TI - A co-evolutionary framework for regulatory motif discovery T2 - Evolutionary Computation, 2007. CEC 2007. IEEE Congress on JF - Evolutionary Computation, 2007. CEC 2007. IEEE Congress on SP - 3894 EP - 3901 N2 - In previous work, we have shown how an evolutionary algorithm with a clustered population can be used to concurrently discover multiple regulatory motifs present within the promoter sequences of co-expressed genes. In this paper, we extend the algorithm by co-evolving a population of Boolean classification rules in parallel with the motif population. Results using synthetic data suggest that this approach allows poorly conserved motifs to be identified in promoter sequences an order of magnitude longer than using population clustering alone, whilst results using muscle-specific promoter data show the algorithm is able to evolve meaningful sequence classifiers in parallel with motifs-suggesting that co-evolution provides a suitable framework for composite motif discovery within eukaryotic sequences. KW - evolutionary AU - Lones, Michael AU - Tyrrell, Andy PY - 2007/// UR - http://dx.doi.org/10.1109/CEC.2007.4424978 ER -