@techreport{TR-IC-98-37,
  number = {IC-98-37},
  author = {Nalvo Franco de {Almeida Jr.}  and  João Carlos Setubal},
  title = {Um {Modelo} {Oculto} de {Markov} para Encontrar Promotores em Seqüências de {DNA}},
  month = {October},
  year = {1998}, 
  institution = {Institute of Computing, University of Campinas},
  note = {In Portuguese, 12 pages.
    \par\selectlanguage{english}\textbf{Abstract}
      We present a Hidden Markov Model (HMM) to find binding sites,
      like promoters, in a DNA sequence. This approach allows
      variable-length spacers between the consensus sequences. The
      model was built using 150 known promoters of the {\em
      Escherichia coli} genome and uses the Expectation-Maximization
      (EM) algorithm to reestimate parameters. In order to test the
      model, we used 30 regions of {\em E.~coli}, each one known to
      contain a promoter. By cutting randomly these regions, we
      produced 20 sets of 30 sequences. The model was able to
      determine the correct or nearly correct (within 6 bp) 78$\%$ of the
      consensus sequences of a set, on average. The program is
      available through the WWW and can be useful as a tool to find a
      promoter in any procaryotic DNA sequence.
  }
}