binaries/src/disembl/biopython-1.50/Bio/Alphabet/IUPAC.py

   1 # Copyright 2000-2001 by Andrew Dalke.
   2 # Revisions copyright 2008 by Peter Cock.
   3 # All rights reserved.
   4 # This code is part of the Biopython distribution and governed by its
   5 # license.  Please see the LICENSE file that should have been included
   6 # as part of this package.
   7
   8 """Standard nucleotide and protein alphabets defined by IUPAC."""
   9
  10 from Bio import Alphabet
  11 from Bio.Data import IUPACData
  12
  13 ##################### Protein
  14
  15 # From the IUPAC definition at:
  16 #   http://www.chem.qmw.ac.uk/iupac/AminoAcid/A2021.html#AA21
  17
  18 assert IUPACData.extended_protein_letters == IUPACData.extended_protein_letters.upper()
  19 class ExtendedIUPACProtein(Alphabet.ProteinAlphabet):
  20     """Extended uppercase IUPAC protein single letter alphabet including X etc.
  21
  22     In addition to the standard 20 single letter protein codes, this includes:
  23
  24     B = "Asx";  Aspartic acid (R) or Asparagine (N)
  25     X = "Xxx";  Unknown or 'other' amino acid
  26     Z = "Glx";  Glutamic acid (E) or Glutamine (Q)
  27     J = "Xle";  Leucine (L) or Isoleucine (I), used in mass-spec (NMR)
  28     U = "Sec";  Selenocysteine
  29     O = "Pyl";  Pyrrolysine
  30
  31     This alphabet is not intended to be used with X for Selenocysteine
  32     (an ad-hoc standard prior to the IUPAC adoption of U instead).
  33     """
  34     letters = IUPACData.extended_protein_letters
  35
  36 extended_protein = ExtendedIUPACProtein()
  37
  38 assert IUPACData.protein_letters == IUPACData.protein_letters.upper()
  39 class IUPACProtein(ExtendedIUPACProtein):
  40     """Uppercase IUPAC protein single letter alphabet of the 20 standard amino acids."""
  41     letters = IUPACData.protein_letters
  42
  43 protein = IUPACProtein()
  44
  45 ##################### DNA
  46
  47 # The next two are the IUPAC definitions, from:
  48 #   http://www.chem.qmw.ac.uk/iubmb/misc/naseq.html
  49 class IUPACAmbiguousDNA(Alphabet.DNAAlphabet):
  50     """Uppercase IUPAC ambiguous DNA."""
  51     letters = IUPACData.ambiguous_dna_letters
  52
  53 ambiguous_dna = IUPACAmbiguousDNA()
  54
  55 class IUPACUnambiguousDNA(IUPACAmbiguousDNA):
  56     """Uppercase IUPAC unambiguous DNA (letters GATC only)."""
  57     letters = IUPACData.unambiguous_dna_letters
  58
  59 unambiguous_dna = IUPACUnambiguousDNA()
  60
  61
  62 # Also from the URL, but not part of the standard
  63 class ExtendedIUPACDNA(Alphabet.DNAAlphabet):
  64     """Extended IUPAC DNA alphabet.
  65
  66     In addition to the standard letter codes GATC, this includes:
  67
  68     B = 5-bromouridine
  69     D = 5,6-dihydrouridine
  70     S = thiouridine
  71     W = wyosine
  72     """
  73     letters = IUPACData.extended_dna_letters
  74
  75 extended_dna = ExtendedIUPACDNA()
  76
  77 ##################### RNA
  78
  79 class IUPACAmbiguousRNA(Alphabet.RNAAlphabet):
  80     """Uppercase IUPAC ambiguous RNA."""
  81     letters = IUPACData.ambiguous_rna_letters
  82
  83 ambiguous_rna = IUPACAmbiguousRNA()
  84
  85 class IUPACUnambiguousRNA(IUPACAmbiguousRNA):
  86     """Uppercase IUPAC unambiguous RNA (letters GAUC only)."""
  87     letters = IUPACData.unambiguous_rna_letters
  88
  89 unambiguous_rna = IUPACUnambiguousRNA()
  90
  91 # are there extended forms?
  92 #class ExtendedIUPACRNA(Alphabet.RNAAlphabet):
  93 #    letters = extended_rna_letters
  94 #    #   B == 5-bromouridine
  95 #    #   D == 5,6-dihydrouridine
  96 #    #   S == thiouridine
  97 #    #   W == wyosine
  98
  99
 100 # We need to load the property resolution information, but we need to
 101 # wait until after the systems have been loaded. (There's a nasty loop
 102 # where, eg, translation objects need an alphabet, which need to be
 103 # assocated with translators.)
 104
 105 from Bio.PropertyManager import default_manager
 106
 107 def _bootstrap(manager, klass, property):
 108     assert manager is default_manager
 109     del default_manager.class_resolver[IUPACProtein]
 110     del default_manager.class_resolver[ExtendedIUPACProtein]
 111     del default_manager.class_resolver[IUPACAmbiguousDNA]
 112     del default_manager.class_resolver[IUPACUnambiguousDNA]
 113     del default_manager.class_resolver[ExtendedIUPACDNA]
 114     del default_manager.class_resolver[IUPACAmbiguousRNA]
 115     del default_manager.class_resolver[IUPACUnambiguousRNA]
 116
 117     from Bio.Encodings import IUPACEncoding
 118
 119     return manager.resolve_class(klass, property)
 120
 121 default_manager.class_resolver[IUPACProtein] = _bootstrap
 122 default_manager.class_resolver[ExtendedIUPACProtein] = _bootstrap
 123 default_manager.class_resolver[IUPACAmbiguousDNA] = _bootstrap
 124 default_manager.class_resolver[IUPACUnambiguousDNA] = _bootstrap
 125 default_manager.class_resolver[ExtendedIUPACDNA] = _bootstrap
 126 default_manager.class_resolver[IUPACAmbiguousRNA] = _bootstrap
 127 default_manager.class_resolver[IUPACUnambiguousRNA] = _bootstrap