- author = "Rolv Seehuus and Amund Tveit and Ole Edsberg",
- title = "Discovering biological motifs with genetic programming",
- booktitle = "{GECCO 2005}: Proceedings of the 2005 conference on Genetic and evolutionary computation",
- year = "2005",
- editor = "Hans-Georg Beyer and Una-May O'Reilly and Dirk V. Arnold and Wolfgang Banzhaf and Christian Blum and Eric W. Bonabeau and Erick Cantu-Paz and Dipankar Dasgupta and Kalyanmoy Deb and James A. Foster and Edwin D. {de Jong} and Hod Lipson and Xavier Llora and Spiros Mancoridis and Martin Pelikan and Guenther R. Raidl and Terence Soule and Andy M. Tyrrell and Jean-Paul Watson and Eckart Zitzler",
- volume = "1",
- ISBN = "1-59593-010-8",
- pages = "401--408",
- address = "Washington DC, USA",
-
URL = "
http://gpbib.cs.ucl.ac.uk/gecco2005/docs/p401.pdf",
-
DOI = "
doi:10.1145/1068009.1068074",
- publisher = "ACM Press",
- publisher_address = "New York, NY, 10286-1405, USA",
- month = "25-29 " # jun,
- organisation = "ACM SIGEVO (formerly ISGEC)",
- keywords = "genetic algorithms, genetic programming, Biological Applications, performance, protein motifs, representations",
- size = "8 pages",
-
abstract = "Choosing the right representation for a problem is
important. In this article we introduce a linear
genetic programming approach for motif discovery in
protein families, and we also present a thorough
comparison between our approach and Koza-style genetic
programming using ADFs.
In a study of 45 protein families, we demonstrate that our algorithm, given equal processing resources and no prior knowledge in shaping of datasets, consistently generates motifs that are of significantly better quality than those we found by using trees as representation. For several of the studied protein families we evolve motifs comparable to those found in Prosite, a manually curated database of protein motifs.
Our linear genome gave better results than Koza-style genetic programming for 37 of 45 families. The difference is statistically significant for 24 of the families at the 99 percent confidence level.",
-
notes = "GECCO-2005 A joint meeting of the fourteenth
international conference on genetic algorithms
(ICGA-2005) and the tenth annual genetic programming
conference (GP-2005).
ACM Order Number 910052",
