A Co-Evolutionary Framework for Regulatory Motif Discovery

M. A. Lones; A.M. Tyrrell

doi:10.1109/CEC.2007.4424978

A Co-Evolutionary Framework for Regulatory Motif Discovery

M. A. Lones, A.M. Tyrrell

Electronic Engineering

Research output: Contribution to conference › Other › peer-review

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 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 language	English
Pages	3894-3901
DOIs	https://doi.org/10.1109/CEC.2007.4424978
Publication status	Published - 1 Sept 2007

Access to Document

10.1109/CEC.2007.4424978

Cite this

@conference{bab449f94d8e4ab7924359a9b580ef12,

title = "A Co-Evolutionary Framework for Regulatory Motif Discovery",

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 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.",

author = "Lones, {M. A.} and A.M. Tyrrell",

year = "2007",

month = sep,

day = "1",

doi = "10.1109/CEC.2007.4424978",

language = "English",

pages = "3894--3901",

}

TY - CONF

T1 - A Co-Evolutionary Framework for Regulatory Motif Discovery

AU - Lones, M. A.

AU - Tyrrell, A.M.

PY - 2007/9/1

Y1 - 2007/9/1

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 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.

AB - 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.

U2 - 10.1109/CEC.2007.4424978

DO - 10.1109/CEC.2007.4424978

M3 - Other

SP - 3894

EP - 3901

ER -