Evolved Matrix Operations for Post-Processing Protein Secondary Structure Predictions

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

@InProceedings{maccallum:2004:eurogp,
  author =       "Varun Aggarwal and Robert MacCallum",
  title =        "Evolved Matrix Operations for Post-Processing Protein
                 Secondary Structure Predictions",
  booktitle =    "Genetic Programming 7th European Conference, EuroGP
                 2004, Proceedings",
  year =         "2004",
  editor =       "Maarten Keijzer and Una-May O'Reilly and 
                 Simon M. Lucas and Ernesto Costa and Terence Soule",
  volume =       "3003",
  series =       "LNCS",
  pages =        "220--229",
  address =      "Coimbra, Portugal",
  publisher_address = "Berlin",
  month =        "5-7 " # apr,
  organisation = "EvoNet",
  publisher =    "Springer-Verlag",
  keywords =     "genetic algorithms, genetic programming: Poster",
  ISBN =         "3-540-21346-5",
  URL =          "http://web.mit.edu/varun_ag/www/aggarwal-eurogp2004.pdf",
  URL =          "http://www.springerlink.com/openurl.asp?genre=article&issn=0302-9743&volume=3003&spage=220",
  DOI =          "doi:10.1007/978-3-540-24650-3_20",
  abstract =     "Predicting the three-dimensional structure of proteins
                 is a hard problem, so many have opted instead to
                 predict the secondary structural state (usually helix,
                 strand or coil) of each amino acid residue. This should
                 be an easier task, but it now seems that a ceiling of
                 around 76 percent per-residue three-state accuracy has
                 been reached. Further improvements will require the
                 correct processing of so-called {"}long-range
                 information{"}. We present a novel application of
                 genetic programming to evolve high level matrix
                 operations to post-process secondary structure
                 prediction probabilities produced by the popular,
                 state-of-the-art neural network based PSIPRED by David
                 Jones. We show that global and long-range information
                 may be used to increase three-state accuracy by at
                 least 0.26 percentage points - a small but
                 statistically significant difference. This is on top of
                 the 0.14 percentage point increase already made by
                 PSIPRED's built-in filters.",
  notes =        "Part of \cite{keijzer:2004:GP} EuroGP'2004 held in
                 conjunction with EvoCOP2004 and EvoWorkshops2004",
}

Genetic Programming entries for Varun Aggarwal Robert M MacCallum

Citations