- title = "The Evaluation of a Stochastic Regular Motif Language for Protein Sequences",
- author = "Brian J. Ross",
- pages = "120--128",
- year = "2001",
- publisher = "Morgan Kaufmann",
- booktitle = "Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2001)",
- editor = "Lee Spector and Erik D. Goodman and Annie Wu and W. B. Langdon and Hans-Michael Voigt and Mitsuo Gen and Sandip Sen and Marco Dorigo and Shahram Pezeshk and Max H. Garzon and Edmund Burke",
- address = "San Francisco, California, USA",
- publisher_address = "San Francisco, CA 94104, USA",
- month = "7-11 " # jul,
- keywords = "genetic algorithms, genetic programming, motif, stochastic regular expressions, grammatical genetic",
- ISBN = "1-55860-774-9",
-
URL = "
http://www.cosc.brocku.ca/~bross/research/gp002.pdf",
-
URL = "
http://citeseer.ist.psu.edu/503937.html",
-
URL = "http://gpbib.cs.ucl.ac.uk/gecco2001/d01.pdf",
- abstract = "A probabilistic regular motif language for protein sequences is evaluated. SRE-DNA is a stochastic regular expression language that combines characteristics of regular expressions and stochastic representations such as Hidden Markov Models. To evaluate its expressive merits, genetic programming is used to evolve SRE-DNA motifs for aligned sets of protein sequences. Different constrained grammatical forms of SRE-DNA expressions are applied to aligned protein sequences from the PROSITE database. Some sequences patterns were precisely determined, while others resulted in good solutions having considerably different features from the PROSITE equivalents. This research establishes the viability of SRE-DNA as a new representation language for protein sequence identification. The practicality of using grammatical genetic programming in stochastic biosequence expression classification is also demonstrated.",
-
notes = "GECCO-2001 A joint meeting of the tenth International
Conference on Genetic Algorithms (ICGA-2001) and the
sixth Annual Genetic Programming Conference (GP-2001)
Part of \cite{spector:2001:GECCO}
DCTG-GP Kleene closure=()* 4 grammars tried. Initial pop 2000 culled to 1000. bloat. 'full version of SRE-DNA without guards or nested iteration constraints...was very inefficient' Sicstus Prolog 3.8.5.",
