def reduce_ambiguous_seqs(seqs, seqtype='DNA'):
'''Get the most specific ambiguous DNA/RNA sequence of a set'''
if seqtype == 'DNA':
from Bio.Data.IUPACData import ambiguous_dna_values as ttable
elif seqtype == 'RNA':
from Bio.Data.IUPACData import ambiguous_rna_values as ttable
del ttable['X']
ttable_back = {frozenset(value): key for (key, value) in ttable.iteritems()}
from itertools import imap, izip
seq = ''.join(imap(ttable_back.get, imap(frozenset, izip(*seqs))))
return seq
def complement(sequence):
#TODO - Add a complement function to Bio/Seq.py?
#There is already a complement method on the Seq and MutableSeq objects.
return Seq.reverse_complement(sequence)[::-1]
def sorted_dict(d):
"""A sorted repr of a dictionary."""
return "{%s}" % ", ".join("%s: %s" % (repr(k), repr(v))
for k, v in sorted(d.iteritems()))
print
print "DNA Ambiguity mapping:", sorted_dict(ambiguous_dna_values)
print "DNA Complement mapping:", sorted_dict(ambiguous_dna_complement)
for ambig_char, values in sorted(ambiguous_dna_values.iteritems()):
compl_values = complement(values)
print "%s={%s} --> {%s}=%s" % \
(ambig_char, values, compl_values, ambiguous_dna_complement[ambig_char])
assert set(compl_values) == set(
ambiguous_dna_values[ambiguous_dna_complement[ambig_char]])
print
print "RNA Ambiguity mapping:", sorted_dict(ambiguous_rna_values)
print "RNA Complement mapping:", sorted_dict(ambiguous_rna_complement)
for ambig_char, values in sorted(ambiguous_rna_values.iteritems()):
compl_values = complement(values).replace(
"T", "U") # need to help as no alphabet
print "%s={%s} --> {%s}=%s" % \
(ambig_char, values, compl_values, ambiguous_rna_complement[ambig_char])
assert set(compl_values) == set(
assert "?" not in ambiguous_dna_values
def complement(sequence) :
#TODO - Add a complement function to Bio/Seq.py?
#There is already a complement method on the Seq and MutableSeq objects.
return Seq.reverse_complement(sequence)[::-1]
def sorted_dict(d) :
"""A sorted repr of a dictionary."""
return "{%s}" % ", ".join("%s: %s" % (repr(k),repr(v)) \
for k,v in sorted(d.iteritems()))
print
print "DNA Ambiguity mapping:", sorted_dict(ambiguous_dna_values)
print "DNA Complement mapping:", sorted_dict(ambiguous_dna_complement)
for ambig_char, values in sorted(ambiguous_dna_values.iteritems()) :
compl_values = complement(values)
print "%s={%s} --> {%s}=%s" % \
(ambig_char, values, compl_values, ambiguous_dna_complement[ambig_char])
assert set(compl_values) == set(ambiguous_dna_values[ambiguous_dna_complement[ambig_char]])
print
print "RNA Ambiguity mapping:", sorted_dict(ambiguous_rna_values)
print "RNA Complement mapping:", sorted_dict(ambiguous_rna_complement)
for ambig_char, values in sorted(ambiguous_rna_values.iteritems()) :
compl_values = complement(values).replace("T","U") #need to help as no alphabet
print "%s={%s} --> {%s}=%s" % \
(ambig_char, values, compl_values, ambiguous_rna_complement[ambig_char])
assert set(compl_values) == set(ambiguous_rna_values[ambiguous_rna_complement[ambig_char]])
print
#See bug 2380, Bio.Nexus was polluting the dictionary.
assert "-" not in ambiguous_dna_values
assert "?" not in ambiguous_dna_values
def complement(sequence):
#TODO - Add a complement function to Bio/Seq.py?
#There is already a complement method on the Seq and MutableSeq objects.
return Seq.reverse_complement(sequence)[::-1]
print
print "DNA Ambiguity mapping:", ambiguous_dna_values
print "DNA Complement mapping:", ambiguous_dna_complement
for ambig_char, values in ambiguous_dna_values.iteritems():
compl_values = complement(values)
print "%s={%s} --> {%s}=%s" % \
(ambig_char, values, compl_values, ambiguous_dna_complement[ambig_char])
assert set(compl_values) == set(
ambiguous_dna_values[ambiguous_dna_complement[ambig_char]])
print
print "RNA Ambiguity mapping:", ambiguous_rna_values
print "RNA Complement mapping:", ambiguous_rna_complement
for ambig_char, values in ambiguous_rna_values.iteritems():
compl_values = complement(values).replace(
"T", "U") #need to help as no alphabet
print "%s={%s} --> {%s}=%s" % \
(ambig_char, values, compl_values, ambiguous_rna_complement[ambig_char])
assert set(compl_values) == set(
print "Checking ambiguous complements"
print "=============================="
#See bug 2380, Bio.Nexus was polluting the dictionary.
assert "-" not in ambiguous_dna_values
assert "?" not in ambiguous_dna_values
def complement(sequence) :
#TODO - Add a complement function to Bio/Seq.py?
#There is already a complement method on the Seq and MutableSeq objects.
return Seq.reverse_complement(sequence)[::-1]
print
print "DNA Ambiguity mapping:", ambiguous_dna_values
print "DNA Complement mapping:", ambiguous_dna_complement
for ambig_char, values in ambiguous_dna_values.iteritems() :
compl_values = complement(values)
print "%s={%s} --> {%s}=%s" % \
(ambig_char, values, compl_values, ambiguous_dna_complement[ambig_char])
assert set(compl_values) == set(ambiguous_dna_values[ambiguous_dna_complement[ambig_char]])
print
print "RNA Ambiguity mapping:", ambiguous_rna_values
print "RNA Complement mapping:", ambiguous_rna_complement
for ambig_char, values in ambiguous_rna_values.iteritems() :
compl_values = complement(values).replace("T","U") #need to help as no alphabet
print "%s={%s} --> {%s}=%s" % \
(ambig_char, values, compl_values, ambiguous_rna_complement[ambig_char])
assert set(compl_values) == set(ambiguous_rna_values[ambiguous_rna_complement[ambig_char]])
print
