A Co-Evolutionary Framework for Regulatory Motif Discovery

Research output: Contribution to conferenceOtherpeer-review


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 classi¿cation rules in parallel with the motif population. Results using synthetic data suggest that this approach allows poorly conserved motifs to be identi¿ed in promoter sequences a magnitude longer than using population clustering alone, whilst results using muscle-speci¿c data suggest the algorithm is able to evolve meaningful sequence classi¿ers in parallel with motifs.
Original languageEnglish
Publication statusPublished - 1 Sept 2007

Cite this