Source Code for Module Bio.Alphabet.IUPAC

  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   
 20   
 21 -class ExtendedIUPACProtein(Alphabet.ProteinAlphabet): 
 22      """Extended uppercase IUPAC protein single letter alphabet including X etc. 
 23   
 24      In addition to the standard 20 single letter protein codes, this includes: 
 25   
 26      B = "Asx";  Aspartic acid (R) or Asparagine (N) 
 27      X = "Xxx";  Unknown or 'other' amino acid 
 28      Z = "Glx";  Glutamic acid (E) or Glutamine (Q) 
 29      J = "Xle";  Leucine (L) or Isoleucine (I), used in mass-spec (NMR) 
 30      U = "Sec";  Selenocysteine 
 31      O = "Pyl";  Pyrrolysine 
 32   
 33      This alphabet is not intended to be used with X for Selenocysteine 
 34      (an ad-hoc standard prior to the IUPAC adoption of U instead). 
 35      """ 
 36      letters = IUPACData.extended_protein_letters 
 37   
 38  extended_protein = ExtendedIUPACProtein() 
 39   
 40  assert IUPACData.protein_letters == IUPACData.protein_letters.upper() 
 41   
 42   
 43 -class IUPACProtein(ExtendedIUPACProtein): 
 44      """Uppercase IUPAC protein single letter alphabet of the 20 standard amino acids.""" 
 45      letters = IUPACData.protein_letters 
 46   
 47  protein = IUPACProtein() 
 48   
 49  ##################### DNA 
 50   
 51   
 52  # The next two are the IUPAC definitions, from: 
 53  #   http://www.chem.qmw.ac.uk/iubmb/misc/naseq.html 
 54 -class IUPACAmbiguousDNA(Alphabet.DNAAlphabet): 
 55      """Uppercase IUPAC ambiguous DNA.""" 
 56      letters = IUPACData.ambiguous_dna_letters 
 57   
 58  ambiguous_dna = IUPACAmbiguousDNA() 
 59   
 60   
 61 -class IUPACUnambiguousDNA(IUPACAmbiguousDNA): 
 62      """Uppercase IUPAC unambiguous DNA (letters GATC only).""" 
 63      letters = IUPACData.unambiguous_dna_letters 
 64   
 65  unambiguous_dna = IUPACUnambiguousDNA() 
 66   
 67   
 68  # Also from the URL, but not part of the standard 
 69 -class ExtendedIUPACDNA(Alphabet.DNAAlphabet): 
 70      """Extended IUPAC DNA alphabet. 
 71   
 72      In addition to the standard letter codes GATC, this includes: 
 73   
 74      B = 5-bromouridine 
 75      D = 5,6-dihydrouridine 
 76      S = thiouridine 
 77      W = wyosine 
 78      """ 
 79      letters = IUPACData.extended_dna_letters 
 80   
 81  extended_dna = ExtendedIUPACDNA() 
 82   
 83  ##################### RNA 
 84   
 85   
 86 -class IUPACAmbiguousRNA(Alphabet.RNAAlphabet): 
 87      """Uppercase IUPAC ambiguous RNA.""" 
 88      letters = IUPACData.ambiguous_rna_letters 
 89   
 90  ambiguous_rna = IUPACAmbiguousRNA() 
 91   
 92   
 93 -class IUPACUnambiguousRNA(IUPACAmbiguousRNA): 
 94      """Uppercase IUPAC unambiguous RNA (letters GAUC only).""" 
 95      letters = IUPACData.unambiguous_rna_letters 
 96   
 97  unambiguous_rna = IUPACUnambiguousRNA() 
 98   
 99  # are there extended forms? 
100  #class ExtendedIUPACRNA(Alphabet.RNAAlphabet): 
101  #    letters = extended_rna_letters 
102  #    #   B == 5-bromouridine 
103  #    #   D == 5,6-dihydrouridine 
104  #    #   S == thiouridine 
105  #    #   W == wyosine 
106