Returning dict instead of defaultdict, updated documentation.

README.md

@@ -2,33 +2,44 @@
 This library provides functions for back translation from amino acids to
 nucleotides.
 
-    from __future__ import unicode_literals
+    >>> from __future__ import unicode_literals
 
-    from backtranslate.backtranslate import BackTranslate
+    >>> from backtranslate.backtranslate import BackTranslate
 
-    # Create a class instance, optionally giving the translation table id.
-    bt = BackTranslate()
-    # Find all substitutions that transform the codon 'TTG' into a stop codon.
-    substitutions = bt.with_dna('TGG', '*')
+    >>> # Create a class instance, optionally giving the translation table id.
+    >>> bt = BackTranslate()
+    >>> # Find all substitutions that transform the codon 'TTG' into a stop
+    >>> # codon.
+    >>> bt.with_dna('TGG', '*')
+    {1: set([('G', 'A')]), 2: set([('G', 'A')])}
 
 
 Sometimes we do not have access to the DNA sequence so we have to find
 possible substitutions from the amino acids directly.
 
-    # Find all substitutions that transform a Tryptophan into a stop codon.
-    substitutions = bt.without_dna('W', '*')
+    >>> # Find all substitutions that transform a Tryptophan into a stop codon.
+    >>> bt.without_dna('W', '*')
+    {1: set([('G', 'A')]), 2: set([('G', 'A')])}
 
 To find out which substitution predictions can be improved by adding codon
 information, use the following function.
 
-    bt.improvable()
+    >>> bt.improvable()
+    set([('I', 'L'), ('R', 'W'), ('Q', 'H'), ('C', '*'), ('*', 'W'),
+        ('K', 'N'), ('C', 'W'), ('S', 'R'), ('L', 'I'), ('*', 'S'), ('S', '*'),
+        ('L', '*'), ('L', 'M'), ('L', 'F'), ('*', 'L'), ('D', 'E'), ('R', 'G'),
+        ('S', 'C'), ('E', 'D'), ('R', 'S'), ('N', 'K'), ('H', 'Q'), ('S', 'T'),
+        ('T', 'S'), ('G', 'R'), ('L', 'V'), ('I', 'M'), ('F', 'L'), ('*', 'Y'),
+        ('Y', '*'), ('V', 'L'), ('R', '*')])
 
 To get substitutions in a readable format, we can use the following:
 
-    from backtranslate.util import subst_to_cds
+    >>> from backtranslate.util import subst_to_cds
 
-    # Transform the substitutions to CDS coordinates.
-    variants = subst_to_cds(substitutions, 12)
+    >>> substitutions = bt.without_dna('W', '*')
+    >>> # Transform the substitutions to CDS coordinates.
+    >>> subst_to_cds(substitutions, 12)
+    set([(15, 'G', 'A'), (14, 'G', 'A')])
 
 ## Command line interface
 Use the command `backtranslate` to find substitutions that explain an amino

backtranslate/backtranslate.py

@@ -43,7 +43,7 @@ def reverse_translation_table(table_id=1):
     for codon in forward_table.forward_table:
         back_table[str(forward_table.forward_table[codon])].add(str(codon))
 
-    return back_table
+    return dict(back_table)
 
 
 class BackTranslate(object):
@@ -64,8 +64,8 @@ class BackTranslate(object):
         Find single nucleotide substitutions that given a reference codon
         explains an observed amino acid.
 
-        :arg dictsubstitutions: Set of single nucleotide substitutions indexed
-            by position.
+        :arg defaultdict(set) substitutions: Set of single nucleotide
+            substitutions indexed by position.
         :arg str reference_codon: Original codon.
         :arg str amino_acid: Observed amino acid.
         """
@@ -92,7 +92,7 @@ class BackTranslate(object):
 
         self._one_subst(substitutions, reference_codon, amino_acid)
 
-        return substitutions
+        return dict(substitutions)
 
 
     def without_dna(self, reference_amino_acid, amino_acid):
@@ -111,7 +111,7 @@ class BackTranslate(object):
         for reference_codon in self._back_table[reference_amino_acid]:
             self._one_subst(substitutions, reference_codon, amino_acid)
 
-        return substitutions
+        return dict(substitutions)
 
 
     def improvable(self):