def test_complement_ambiguous_dna_values(self):
for ambig_char, values in sorted(ambiguous_dna_values.items()):
compl_values = str(
Seq.Seq(values, alphabet=IUPAC.ambiguous_dna).complement())
ambig_values = ambiguous_dna_values[
ambiguous_dna_complement[ambig_char]]
self.assertEqual(set(compl_values), set(ambig_values))
def _calc_at_content_values():
at_u = {}
at_a = {}
unamb = "GCTASWN"
for b, opts in ambiguous_dna_values.items():
d = at_u if b in unamb else at_a
d[b] = float(opts.count("A") + opts.count("T")) / len(opts)
d[b.lower()] = d[b]
return at_u, at_a
def _calc_gc_content_values():
gc_u = {}
gc_a = {}
unamb = "GCTASWN"
for b, opts in ambiguous_dna_values.items():
d = gc_u if b in unamb else gc_a
d[b] = float(opts.count("C") + opts.count("G")) / len(opts)
d[b.lower()] = d[b]
return gc_u, gc_a
def load_iupac():
iupac_code = {
tuple(letters): code
for code, letters in ambiguous_dna_values.items()
}
return {
permutation: (code, )
for letters, code in iupac_code.items()
for permutation in permutations(letters)
}
def test_complement_ambiguous_dna_values(self):
for ambig_char, values in sorted(ambiguous_dna_values.items()):
compl_values = Seq.Seq(values).complement()
ambig_values = ambiguous_dna_values[ambiguous_dna_complement[ambig_char]]
self.assertCountEqual(compl_values, ambig_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.items()))
print("")
print("DNA Ambiguity mapping: %s" % sorted_dict(ambiguous_dna_values))
print("DNA Complement mapping: %s" % sorted_dict(ambiguous_dna_complement))
for ambig_char, values in sorted(ambiguous_dna_values.items()):
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: %s" % sorted_dict(ambiguous_rna_values))
print("RNA Complement mapping: %s" % sorted_dict(ambiguous_rna_complement))
for ambig_char, values in sorted(ambiguous_rna_values.items()):
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(
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.items()))
print("")
print("DNA Ambiguity mapping: %s" % sorted_dict(ambiguous_dna_values))
print("DNA Complement mapping: %s" % sorted_dict(ambiguous_dna_complement))
for ambig_char, values in sorted(ambiguous_dna_values.items()):
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: %s" % sorted_dict(ambiguous_rna_values))
print("RNA Complement mapping: %s" % sorted_dict(ambiguous_rna_complement))
for ambig_char, values in sorted(ambiguous_rna_values.items()):
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("")
def test_complement_ambiguous_dna_values(self):
for ambig_char, values in sorted(ambiguous_dna_values.items()):
compl_values = str(Seq.Seq(values, alphabet=IUPAC.ambiguous_dna).complement())
self.assertEqual(set(compl_values),
set(ambiguous_dna_values[ambiguous_dna_complement[ambig_char]]))
def _calc_base_values(base):
d = {}
for b, opts in ambiguous_dna_values.items():
d[b] = float(opts.count(base)) / len(opts)
d[b.lower()] = float(opts.count(base)) / len(opts)
return d
if debug:
print('yield', segment_smpl_seqs,
[(snp_['start'], snp_['stop'] - 1)
for snp_ in snps_to_yield])
yield segment, segment_smpl_seqs, snps_to_yield
reamining_smpl_seqs = [srfs[pos - offset:] for srfs in sample_ref_seqs]
#remaining_seq = ref_seq[pos - offset:]
if reamining_smpl_seqs[0]:
reg = pos, region[2] if len(region) > 2 else None
yield reg, reamining_smpl_seqs, []
IUPAC = {
tuple(sorted(nucls)): iupac.encode('utf8')
for iupac, nucls in ambiguous_dna_values.items()
}
def to_str(bytes_):
if isinstance(bytes_, bytes):
return bytes_.decode('utf-8')
else:
return bytes_
def to_bytes(str_):
if not isinstance(str_, bytes):
return str_.encode('utf-8')
else:
return str_
pos = max([snp_['stop'] for snp_ in snps_to_yield])
if len(region) < 3 or pos <= region[2]:
# Are the SNPs inside the region to return?
if debug:
print('yield', segment_smpl_seqs,
[(snp_['start'], snp_['stop'] - 1) for snp_ in snps_to_yield])
yield segment, segment_smpl_seqs, snps_to_yield
reamining_smpl_seqs = [srfs[pos - offset:] for srfs in sample_ref_seqs]
#remaining_seq = ref_seq[pos - offset:]
if reamining_smpl_seqs[0]:
reg = pos, region[2] if len(region) > 2 else None
yield reg, reamining_smpl_seqs, []
IUPAC = {tuple(sorted(nucls)): iupac.encode('utf8') for iupac, nucls in ambiguous_dna_values.items()}
def to_str(bytes_):
if isinstance(bytes_, bytes):
return bytes_.decode('utf-8')
else:
return bytes_
def to_bytes(str_):
if not isinstance(str_, bytes):
return str_.encode('utf-8')
else:
return str_