def _teardown(self, config, temp):
# Validate output from MAFFT
output_file = reroot_path(temp, self._output_file)
try:
MSA.from_file(output_file)
except MSAError, error:
raise NodeError("Invalid MSA produced by MAFFT:\n%s" % (error,))
def _read_sequences(filenames):
results = {}
for filename in filenames:
results[filename] = MSA.from_file(filename)
MSA.validate(*results.values())
return results.iteritems()
def _read_sequences(filenames):
results = {}
for filename in filenames:
results[filename] = MSA.from_file(filename)
MSA.validate(*results.values())
return results.iteritems()
def _run(self, _config, temp):
alignment = MSA.from_file(self._input_file)
for (to_filter, groups) in self._filter_by.iteritems():
alignment = alignment.filter_singletons(to_filter, groups)
temp_filename = fileutils.reroot_path(temp, self._output_file)
with open(temp_filename, "w") as handle:
alignment.to_file(handle)
fileutils.move_file(temp_filename, self._output_file)
def _run(self, _config, temp):
alignment = MSA.from_file(self._input_file)
for (to_filter, groups) in self._filter_by.iteritems():
alignment = alignment.filter_singletons(to_filter, groups)
temp_filename = fileutils.reroot_path(temp, self._output_file)
with open(temp_filename, "w") as handle:
alignment.to_file(handle)
fileutils.move_file(temp_filename, self._output_file)
def _run(self, _config, temp):
# Read and check that MSAs share groups
msas = [MSA.from_file(filename) for filename in sorted(self.input_files)]
MSA.validate(*msas)
blocks = []
for msa in msas:
blocks.append(sequential_phy(msa, add_flag = self._add_flag))
with open(reroot_path(temp, self._out_phy), "w") as output:
output.write("\n\n".join(blocks))
def _is_sufficently_covered(filepath, min_coverage):
msa = MSA.from_file(filepath)
if msa.seqlen() % 3:
return False
total_bases_not_covered = 0
for fasta_record in msa:
total_bases_not_covered += fasta_record.sequence.upper().count("N")
total_bases_not_covered += fasta_record.sequence.count("-")
total_bases = float(len(msa) * msa.seqlen())
frac_covered = 1.0 - total_bases_not_covered / total_bases
return frac_covered >= min_coverage
def _run(self, _config, temp):
# Read and check that MSAs share groups
msas = [
MSA.from_file(filename) for filename in sorted(self.input_files)
]
MSA.validate(*msas)
blocks = []
for msa in msas:
blocks.append(sequential_phy(msa, add_flag=self._add_flag))
with open(reroot_path(temp, self._out_phy), "w") as output:
output.write("\n\n".join(blocks))
def _is_sufficently_covered(filepath, min_coverage):
msa = MSA.from_file(filepath)
if msa.seqlen() % 3:
return False
total_bases_not_covered = 0
for fasta_record in msa:
total_bases_not_covered += fasta_record.sequence.upper().count("N")
total_bases_not_covered += fasta_record.sequence.count("-")
total_bases = float(len(msa) * msa.seqlen())
frac_covered = 1.0 - total_bases_not_covered / total_bases
return frac_covered >= min_coverage
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 _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_msa_from_file__compressed_bz2():
expected = MSA([FASTA("This_is_BZ_FASTA!", None, "CGTNA"),
FASTA("This_is_ALSO_BZ_FASTA!", None, "ACGTN")])
results = MSA.from_file("tests/data/fasta_file.fasta.bz2")
assert_equal(results, expected)
