binaries/src/disembl/biopython-1.50/Bio/Translate.py

   1 """Code to translate DNA or RNA into proteins (OBSOLETE).
   2
   3 Instead of Bio.Translate, for translation you are now encouraged to use the
   4 Seq object's translate method, or the translate function in the Bio.Seq
   5 module.  Translate-to-stop functionality is via an optional argument.
   6
   7 Bio.Seq does not offer any back-translation function like the one here. It
   8 was concluded that a since a simple back-translation giving a Seq or python
   9 string could only capture some of the possible back translations, there were
  10 no practical uses for such a method/function.
  11
  12 This module is now considered to be obsolete, and is likely to be deprecated
  13 in a future release of Biopython, and later removed.
  14 """
  15 from Bio import Alphabet, Seq
  16 from Bio.Data import CodonTable
  17
  18 class Translator:
  19     def __init__(self, table):
  20         self.table = table
  21         self._encoded = {}
  22
  23     def __str__(self) :
  24         return "Translator object\n" + str(self.table)
  25
  26     def translate(self, seq, stop_symbol = "*"):
  27         #Allow different instances of the same class to be used:
  28         assert seq.alphabet.__class__ == \
  29                self.table.nucleotide_alphabet.__class__, \
  30                "cannot translate from given alphabet (have %s, need %s)" %\
  31                (seq.alphabet, self.table.nucleotide_alphabet)
  32         s = seq.data
  33         letters = []
  34         append = letters.append
  35         table = self.table
  36         get = table.forward_table.get
  37         n = len(seq)
  38         for i in range(0, n-n%3, 3):
  39             append(get(s[i:i+3], stop_symbol))
  40
  41         # return with the correct alphabet encoding (cache the encoding)
  42         try:
  43             alphabet = self._encoded[stop_symbol]
  44         except KeyError:
  45             alphabet = Alphabet.HasStopCodon(table.protein_alphabet,
  46                                              stop_symbol)
  47             self._encoded[stop_symbol] = alphabet
  48
  49         return Seq.Seq("".join(letters), alphabet)
  50
  51     def translate_to_stop(self, seq):
  52         # This doesn't have a stop encoding
  53
  54         #Allow different instances of the same class to be used:
  55         assert seq.alphabet.__class__ == \
  56                self.table.nucleotide_alphabet.__class__, \
  57                "cannot translate from given alphabet (have %s, need %s)" %\
  58                (seq.alphabet, self.table.nucleotide_alphabet)
  59         s = seq.data
  60         letters = []
  61         append = letters.append
  62         table = self.table.forward_table
  63         n = len(seq)
  64         try:
  65             for i in range(0, n-n%3, 3):
  66                 append(table[s[i:i+3]])
  67         except KeyError:
  68             # Stop at the first codon failure
  69             pass
  70         return Seq.Seq("".join(letters), self.table.protein_alphabet)
  71
  72     def back_translate(self, seq):
  73         # includes the stop codon
  74         if not isinstance(seq.alphabet, Alphabet.HasStopCodon):
  75             return self._back_translate_no_stop(seq)
  76         assert seq.alphabet.alphabet == self.table.protein_alphabet, \
  77                "cannot back translate from the given alphabet (%s)" % \
  78                seq.alphabet.alphabet
  79         s = seq.data
  80         letter = seq.alphabet.stop_symbol
  81         letters = []
  82         append = letters.append
  83         table = self.table.back_table
  84         for c in seq.data:
  85             if c == letter:
  86                 append(table[None])
  87             else:
  88                 append(table[c])
  89         return Seq.Seq("".join(letters),
  90                        self.table.nucleotide_alphabet)
  91
  92     def _back_translate_no_stop(self, seq):
  93         # does not allow a stop codon
  94         assert seq.alphabet == self.table.protein_alphabet, \
  95                "cannot back translate from the given alphabet (%s)" % \
  96                seq.alphabet
  97         s = seq.data
  98         letters = []
  99         append = letters.append
 100         table = self.table.back_table
 101         for c in seq.data:
 102             append(table[c])
 103         return Seq.Seq("".join(letters),
 104                        self.table.nucleotide_alphabet)
 105
 106 unambiguous_dna_by_name = {}
 107 for key, value in CodonTable.unambiguous_dna_by_name.items():
 108     unambiguous_dna_by_name[key] = Translator(value)
 109 unambiguous_dna_by_id = {}
 110 for key, value in CodonTable.unambiguous_dna_by_id.items():
 111     unambiguous_dna_by_id[key] = Translator(value)
 112
 113 unambiguous_rna_by_name = {}
 114 for key, value in CodonTable.unambiguous_rna_by_name.items():
 115     unambiguous_rna_by_name[key] = Translator(value)
 116 unambiguous_rna_by_id = {}
 117 for key, value in CodonTable.unambiguous_rna_by_id.items():
 118     unambiguous_rna_by_id[key] = Translator(value)
 119
 120 # XXX Ambiguous - can be done the same except for stop codons!
 121 ambiguous_dna_by_name = {}
 122 for key, value in CodonTable.ambiguous_dna_by_name.items():
 123     ambiguous_dna_by_name[key] = Translator(value)
 124 ambiguous_dna_by_id = {}
 125 for key, value in CodonTable.ambiguous_dna_by_id.items():
 126     ambiguous_dna_by_id[key] = Translator(value)
 127
 128 ambiguous_rna_by_name = {}
 129 for key, value in CodonTable.ambiguous_rna_by_name.items():
 130     ambiguous_rna_by_name[key] = Translator(value)
 131 ambiguous_rna_by_id = {}
 132 for key, value in CodonTable.ambiguous_rna_by_id.items():
 133     ambiguous_rna_by_id[key] = Translator(value)