def test_sequentual_phy__different_length_names_1():
msa = MSA([FASTA("A_short_name", None, "ACGTTGATAACCAGG"),
FASTA("Another_really_long_sequence_name_that_is_too_long", None, "TGCAGAGTACGACGT")])
expected = \
"""2 15
A_short_name ACGTTGATAA CCAGG
Another_really_long_sequence_n TGCAGAGTAC GACGT"""
print interleaved_phy(msa), expected
assert_equal(interleaved_phy(msa), expected)
def test_sequentual_phy__different_length_names_2():
msa = MSA([FASTA("Burchelli_4", None, "ACGTTGATAACCAGG"),
FASTA("Donkey", None, "TGCAGAGTACGACGT")])
expected = \
"""2 15
Burchelli_4 ACGTTGATAA CCAGG
Donkey TGCAGAGTAC GACGT"""
print interleaved_phy(msa), expected
assert_equal(interleaved_phy(msa), expected)
def test_sequentual_phy__different_length_names_2():
msa = MSA([
FASTA("Burchelli_4", None, "ACGTTGATAACCAGG"),
FASTA("Donkey", None, "TGCAGAGTACGACGT")
])
expected = \
"""2 15
Burchelli_4 ACGTTGATAA CCAGG
Donkey TGCAGAGTAC GACGT"""
print interleaved_phy(msa), expected
assert_equal(interleaved_phy(msa), expected)
def test_sequentual_phy__different_length_names_1():
msa = MSA([
FASTA("A_short_name", None, "ACGTTGATAACCAGG"),
FASTA("Another_really_long_sequence_name_that_is_too_long", None,
"TGCAGAGTACGACGT")
])
expected = \
"""2 15
A_short_name ACGTTGATAA CCAGG
Another_really_long_sequence_n TGCAGAGTAC GACGT"""
print interleaved_phy(msa), expected
assert_equal(interleaved_phy(msa), expected)
def test_interleaved_phy__short_sequences():
expected = \
"""2 44
seq1 ACGTTGATAA CCAGGAGGGA TTCGCGATTG GTGGTAACGT AGCC
seq2 TGCAGAGTAC GACGTCTCCT AGATCCTGGA CAATTTAAAC CGAA"""
assert_equal(interleaved_phy(_MSA_MEDIUM_SEQUENCES), expected)
def test_interleaved_phy__with_flag():
expected = \
"""2 15 I
seq1 ACGTTGATAA CCAGG
seq2 TGCAGAGTAC GACGT"""
assert_equal(interleaved_phy(_MSA_SHORT_SEQUENCES, add_flag = True), expected)
def test_interleaved_phy__medium_names():
expected = \
"""2 15
A_really_long_sequence ACGTTGATAA CCAGG
Another_real_long_one! TGCAGAGTAC GACGT"""
assert_equal(interleaved_phy(_MSA_MEDIUM_NAMES), expected)
def test_interleaved_phy__long_names():
expected = \
"""2 15
A_really_long_sequence_name_th ACGTTGATAA CCAGG
Another_really_long_sequence_n TGCAGAGTAC GACGT"""
assert_equal(interleaved_phy(_MSA_LONG_NAMES), expected)
def test_interleaved_phy__medium_names():
expected = \
"""2 15
A_really_long_sequence ACGTTGATAA CCAGG
Another_real_long_one! TGCAGAGTAC GACGT"""
assert_equal(interleaved_phy(_MSA_MEDIUM_NAMES), expected)
def test_interleaved_phy__short_sequences():
expected = \
"""2 44
seq1 ACGTTGATAA CCAGGAGGGA TTCGCGATTG GTGGTAACGT AGCC
seq2 TGCAGAGTAC GACGTCTCCT AGATCCTGGA CAATTTAAAC CGAA"""
assert_equal(interleaved_phy(_MSA_MEDIUM_SEQUENCES), expected)
def test_interleaved_phy__long_names():
expected = \
"""2 15
A_really_long_sequence_name_th ACGTTGATAA CCAGG
Another_really_long_sequence_n TGCAGAGTAC GACGT"""
assert_equal(interleaved_phy(_MSA_LONG_NAMES), expected)
def test_interleaved_phy__with_flag():
expected = \
"""2 15 I
seq1 ACGTTGATAA CCAGG
seq2 TGCAGAGTAC GACGT"""
assert_equal(interleaved_phy(_MSA_SHORT_SEQUENCES, add_flag=True),
expected)
def test_interleaved_phy__multi_line_sequences():
expected = \
"""2 140
seq1 CGGATCTGCT CCTCCACTGG CCACGTTTAC TGTCCCCCAA CCGTTCGTCC
seq2 AGTTGAAGAG GCGGAACGTT TGTAAACCGC GCTAACGTAG TTCTACAACC
CGACCTAGTT ATACTTCTTA GCAAGGTGTA AAACCAGAGA TTGAGGTTAT AACGTTCCTA
AGCCACCCGG TTCGAAGGAA CAACTGGTCG CCATAATTAG GCGAAACGAT AGTGCACTAA
ATCAGTTATT AAATTACCGC GCCCCGACAG
GGTCAGGTGC GCCCCTGTAA ATAATTAGAT"""
assert_equal(interleaved_phy(_MSA_LONG_SEQUENCES), expected)
def test_interleaved_phy__multi_line_sequences():
expected = \
"""2 140
seq1 CGGATCTGCT CCTCCACTGG CCACGTTTAC TGTCCCCCAA CCGTTCGTCC
seq2 AGTTGAAGAG GCGGAACGTT TGTAAACCGC GCTAACGTAG TTCTACAACC
CGACCTAGTT ATACTTCTTA GCAAGGTGTA AAACCAGAGA TTGAGGTTAT AACGTTCCTA
AGCCACCCGG TTCGAAGGAA CAACTGGTCG CCATAATTAG GCGAAACGAT AGTGCACTAA
ATCAGTTATT AAATTACCGC GCCCCGACAG
GGTCAGGTGC GCCCCTGTAA ATAATTAGAT"""
assert_equal(interleaved_phy(_MSA_LONG_SEQUENCES), expected)
def _run(self, _config, temp):
msas = []
for filename in sorted(self._infiles):
split_by = self._infiles[filename].get("partition_by", self._part_by)
for (key, msa) in sorted(split_msa(read_msa(filename), split_by).items()):
for excluded_group in self._excluded:
msa.pop(excluded_group)
msas.append(("%s_%s" % (self._infiles[filename]["name"], key), msa))
msa = join_msa(*(msa for (_, msa) in msas))
with open(reroot_path(temp, self._out_prefix + ".phy"), "w") as output:
output.write(interleaved_phy(msa, add_flag = self._add_flag))
with open(reroot_path(temp, self._out_prefix + ".partitions"), "w") as output:
end = 0
for (name, msa) in msas:
length = len(msa.itervalues().next())
output.write("DNA, %s = %i-%i\n" % (name, end + 1, end + length))
end += length
def _run(self, _config, temp):
merged_msas = []
for (name, files_dd) in sorted(self._infiles.iteritems()):
partitions = files_dd["partitions"]
msas = dict((key, []) for key in partitions)
for filename in files_dd["filenames"]:
msa = MSA.from_file(filename)
if self._excluded:
msa = msa.exclude(self._excluded)
for (key, msa_part) in msa.split(partitions).iteritems():
msas[key].append(msa_part)
msas.pop("X", None)
for (key, msa_parts) in sorted(msas.iteritems()):
merged_msa = MSA.join(*msa_parts)
if self._reduce:
merged_msa = merged_msa.reduce()
if merged_msa is not None:
merged_msas.append(("%s_%s" % (name, key),
merged_msa))
out_fname_phy = reroot_path(temp, self._out_prefix + ".phy")
with open(out_fname_phy, "w") as output_phy:
final_msa = MSA.join(*(msa for (_, msa) in merged_msas))
output_phy.write(interleaved_phy(final_msa))
partition_end = 0
out_fname_parts = reroot_path(temp, self._out_prefix + ".partitions")
with open(out_fname_parts, "w") as output_part:
for (name, msa) in merged_msas:
length = msa.seqlen()
output_part.write("DNA, %s = %i-%i\n"
% (name,
partition_end + 1,
partition_end + length))
partition_end += length
def _run(self, _config, temp):
merged_msas = []
for (name, files_dd) in sorted(self._infiles.iteritems()):
partitions = files_dd["partitions"]
msas = dict((key, []) for key in partitions)
for filename in files_dd["filenames"]:
msa = MSA.from_file(filename)
if self._excluded:
msa = msa.exclude(self._excluded)
for (key, msa_part) in msa.split(partitions).iteritems():
msas[key].append(msa_part)
msas.pop("X", None)
for (key, msa_parts) in sorted(msas.iteritems()):
merged_msa = MSA.join(*msa_parts)
if self._reduce:
merged_msa = merged_msa.reduce()
if merged_msa is not None:
merged_msas.append(("%s_%s" % (name, key), merged_msa))
out_fname_phy = reroot_path(temp, self._out_prefix + ".phy")
with open(out_fname_phy, "w") as output_phy:
final_msa = MSA.join(*(msa for (_, msa) in merged_msas))
output_phy.write(interleaved_phy(final_msa))
partition_end = 0
out_fname_parts = reroot_path(temp, self._out_prefix + ".partitions")
with open(out_fname_parts, "w") as output_part:
for (name, msa) in merged_msas:
length = msa.seqlen()
output_part.write(
"DNA, %s = %i-%i\n" %
(name, partition_end + 1, partition_end + length))
partition_end += length
def test_interleaved_phy__different_lengths():
_mock = flexmock(MSA).should_receive('validate').at_least.once
interleaved_phy(_MSA_MEDIUM_NAMES)
def _run(self, _config, temp):
msa = MSA.join(*(MSA.from_file(filename)
for filename in sorted(self.input_files)))
with open(reroot_path(temp, self._out_phy), "w") as output:
output.write(interleaved_phy(msa, add_flag=self._add_flag))
def _run(self, _config, temp):
msa = MSA.join(*(MSA.from_file(filename) for filename in sorted(self.input_files)))
with open(reroot_path(temp, self._out_phy), "w") as output:
output.write(interleaved_phy(msa, add_flag = self._add_flag))
def test_interleaved_phy__different_lengths():
_mock = flexmock(MSA).should_receive('validate').at_least.once
interleaved_phy(_MSA_MEDIUM_NAMES)
