Derivation of context-free stochastic L-Grammar rules for promoter sequence modeling using Support Vector Machine

Created by W.Langdon from gp-bibliography.bib Revision:1.7615

@InProceedings{Damasevicius:ITA:2008,

• author = "Robertas Damasevicius",
• title = "Derivation of context-free stochastic {L}-Grammar rules for promoter sequence modeling using Support Vector Machine",
• booktitle = "XI-th Joint International Scientific Events on Informatics, Book 2, Advanced Research in Artificial Intelligence",
• year = "2008",
• editor = "K. Markov and {K. Ivanova} and I. Mitov",
• series = "Information Science and Computing",
• pages = "98--104",
• address = "Varna, Bulgaria",
• publisher_address = "Sofia, Bulgaria",
• month = "23 " # jun # " - 03 " # jul,
• publisher = "Ithea",
• keywords = "genetic algorithms, genetic programming, pattern recognition, J, 3 life and medical sciences",
• annote = "The Pennsylvania State University CiteSeerX Archives",
• bibsource = "OAI-PMH server at citeseerx.ist.psu.edu",
• language = "en",
• oai = "oai:CiteSeerX.psu:10.1.1.386.8512",
• rights = "Metadata may be used without restrictions as long as the oai identifier remains attached to it.",
• URL = "http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.386.8512",
• URL = "http://www.foibg.com/ibs_isc/ibs-02/ibs-02.htm",
• URL = "http://www.foibg.com/ibs_isc/ibs-02/IBS-02-p13.pdf",
• size = "7 pages",
• abstract = "Formal grammars can used for describing complex repeatable structures such as DNA sequences. In this paper, we describe the structural composition of DNA sequences using a context-free stochastic L-grammar. L-grammars are a special class of parallel grammars that can model the growth of living organisms, e.g. plant development, and model the morphology of a variety of organisms. We believe that parallel grammars also can be used for modelling genetic mechanisms and sequences such as promoters. Promoters are short regulatory DNA sequences located upstream of a gene. Detection of promoters in DNA sequences is important for successful gene prediction. Promoters can be recognised by certain patterns that are conserved within a species, but there are many exceptions which makes the promoter recognition a complex problem. We replace the problem of promoter recognition by induction of context-free stochastic L-grammar rules, which are later used for the structural analysis of promoter sequences. L-grammar rules are derived automatically from the drosophila and vertebrate promoter datasets using a genetic programming technique and their fitness is evaluated using a Support Vector Machine (SVM) classifier. The artificial promoter sequences generated using the derived L-grammar rules are analysed and compared with natural promoter sequences.",
• notes = "http://www.foibg.com/conf/itaf2008.htm",

}

Genetic Programming entries for Robertas Damasevicius

Citations