Evolving Protein Motifs Using a Stochastic Regular Language with Codon-Level Probabilities

Created by W.Langdon from gp-bibliography.bib Revision:1.4221

  title =        "Evolving Protein Motifs Using a Stochastic Regular
                 Language with Codon-Level Probabilities",
  author =       "Brian J. Ross",
  year =         "2002",
  booktitle =    "6th IASTED International Conference, Artificial
                 Intelligence and Soft Computing, ASC 2002",
  address =      "The Banff Centre for Conferences, Box 1020, 107 Tunnel
                 Mountain Drive, Banff, Alberta, T0L 0C0, Canada",
  month =        "17-19 " # jul,
  organisation = "The International Association of Science and
                 Technology for Development (IASTED)",
  keywords =     "genetic algorithms, genetic programming, stochastic
                 regular expressions, protein motif",
  citeseer-isreferencedby = "oai:CiteSeerPSU:79088",
  citeseer-references = "oai:CiteSeerPSU:42914; oai:CiteSeerPSU:212791;
                 oai:CiteSeerPSU:215947; oai:CiteSeerPSU:331862;
                 oai:CiteSeerPSU:503937; oai:CiteSeerPSU:506252",
  annote =       "The Pennsylvania State University CiteSeer Archives",
  language =     "en",
  oai =          "oai:CiteSeerPSU:503706",
  rights =       "unrestricted",
  URL =          "http://www.cosc.brocku.ca/~bross/research/asc357035.pdf",
  URL =          "http://citeseer.ist.psu.edu/503706.html",
  abstract =     "Experiments involving the evolution of protein motifs
                 using genetic programming are presented. The motifs use
                 a stochastic regular expression language that uses
                 codon-level probabilities within conserved sets
                 (masks). Experiments compared basic genetic programming
                 with Lamarckian evolution, as well as the use of
                 {"}natural{"} probability distributions for masks
                 obtained from the sequence database. It was found that
                 Lamarckian evolution was detrimental to the probability
                 performance of motifs. A comparison of evolved and
                 natural mask probability schemes is inconclusive, since
                 these strategies produce incompatible characterisations
                 of motif fitness as used by the genetic programming

Genetic Programming entries for Brian J Ross