An Evolutionary-based Approach for Feature Generation: Eukaryotic Promoter Recognition

Created by W.Langdon from gp-bibliography.bib Revision:1.3872

@InProceedings{Kamath:2011:AEAfFGEPR,
  title =        "An Evolutionary-based Approach for Feature Generation:
                 Eukaryotic Promoter Recognition",
  author =       "Uday Kamath and Kenneth {De Jong} and Amarda Shehu",
  pages =        "277--284",
  booktitle =    "Proceedings of the 2011 IEEE Congress on Evolutionary
                 Computation",
  year =         "2011",
  editor =       "Alice E. Smith",
  month =        "5-8 " # jun,
  address =      "New Orleans, USA",
  organization = "IEEE Computational Intelligence Society",
  publisher =    "IEEE Press",
  ISBN =         "0-7803-8515-2",
  keywords =     "genetic algorithms, genetic programming, SVM,
                 eukaryotic DNA, eukaryotic promoter recognition,
                 evolutionary-based approach, feature generation,
                 genetic programming techniques, promoter region
                 classification, promoter region identification,
                 promoter region prediction, support vector machines,
                 DNA, biology computing, genetics, pattern
                 classification, support vector machines",
  DOI =          "doi:10.1109/CEC.2011.5949629",
  abstract =     "Prediction of promoter regions continues to be a
                 challenging subproblem in mapping out eukaryotic DNA.
                 While this task is key to understanding the regulation
                 of differential transcription, the gene-specific
                 architecture of promoter sequences does not readily
                 lend itself to general strategies.

                 To date, the best approaches are based on Support
                 Vector Machines (SVMs) that employ standard
                 {"}spectrum{"} features and achieve promoter region
                 classification accuracies from a low of 84percent to a
                 high of 94percent depending on the particular species
                 involved. In this paper, we propose a general and
                 powerful methodology that uses Genetic Programming (GP)
                 techniques to generate more complex and more
                 gene-specific features to be used with a standard SVM
                 for promoter region identification.

                 We evaluate our methodology on three data sets from
                 different species and observe consistent classification
                 accuracies in the 94-95percent range. In addition,
                 because the GP-generated features are gene-specific,
                 they can be used by biologists to advance their
                 understanding of the architecture of eukaryotic
                 promoter regions.",
  notes =        "CEC2011 sponsored by the IEEE Computational
                 Intelligence Society, and previously sponsored by the
                 EPS and the IET.",
}

Genetic Programming entries for Uday Kamath Kenneth De Jong Amarda Shehu

Citations