def test_write_genbank_sequence(self, tmpdir, genbank_reference):
output_filename = Path(tmpdir) / Path("new_sequences.fasta")
reference = SeqIO.read(genbank_reference, "genbank")
sequences_written = write_sequences([reference], output_filename,
"genbank")
assert sequences_written == 1
def test_write_single_set_of_sequences_to_lzma_file(
self, tmpdir, sequences):
output_filename = Path(tmpdir) / Path("new_sequences.fasta.xz")
sequences_written = write_sequences(sequences, output_filename,
"fasta")
assert sequences_written == len(sequences)
with lzma.open(output_filename, "rt") as handle:
assert sequences_written == len(
[line for line in handle if line.startswith(">")])
def test_write_sequences_by_external_handle(self, tmpdir, sequences):
output_filename = Path(tmpdir) / Path("new_sequences.fasta")
with open_file(output_filename, "w") as handle:
total_sequences_written = 0
for sequence in sequences:
sequences_written = write_sequences(sequence, handle)
total_sequences_written += sequences_written
with open(output_filename, "r") as handle:
assert total_sequences_written == len(
[line for line in handle if line.startswith(">")])
prefixes = "|".join(args.strip_prefixes)
pattern = f"^({prefixes})|{pattern}"
with open_file(args.output, "w") as output_handle:
# In order to prefer the latter files, we have to reverse the order of
# the files.
sequences = read_sequences(*reversed(sequence_files))
renamed_sequences = rename_sequences(sequences, pattern)
deduplicated_sequences = drop_duplicate_sequences(
renamed_sequences,
args.error_on_duplicate_strains
)
try:
for sequence in deduplicated_sequences:
write_sequences(sequence, output_handle)
except DuplicateSequenceError as error:
print(
f"ERROR: The following strains have duplicate sequences: {error}",
file=sys.stderr
)
sys.exit(1)
# Clean up any open sequence files.
for sequence_file in sequence_files:
if hasattr(sequence_file, "close"):
sequence_file.close()
# Clean up any open tarballs.
for tar_handle in tar_handles:
tar_handle.close()
nargs='+',
type=int,
help="list of sites to mask")
parser.add_argument("--output",
required=True,
help="FASTA file of output alignment")
args = parser.parse_args()
begin_length = 0
if args.mask_from_beginning:
begin_length = args.mask_from_beginning
end_length = 0
if args.mask_from_end:
end_length = args.mask_from_end
with open_file(args.output, 'w') as outfile:
for record in read_sequences(args.alignment):
seq = str(record.seq)
if args.mask_terminal_gaps:
seq = mask_terminal_gaps(seq)
start = "N" * begin_length
middle = seq[begin_length:-end_length]
end = "N" * end_length
seq_list = list(start + middle + end)
if args.mask_sites:
for site in args.mask_sites:
seq_list[site - 1] = "N"
record.seq = Seq("".join(seq_list))
write_sequences(record, outfile)
def test_write_sequences_from_generator(self, tmpdir, sequences_generator):
output_filename = Path(tmpdir) / Path("new_sequences.fasta")
sequences_written = write_sequences(sequences_generator,
output_filename, "fasta")
assert sequences_written == 3
def test_write_sequences(self, tmpdir, sequences):
output_filename = Path(tmpdir) / Path("new_sequences.fasta")
sequences_written = write_sequences(sequences, output_filename,
"fasta")
assert sequences_written == len(sequences)
# same name already exists and if the hash is different.
sequence_hash = hashlib.sha256(str(record.seq).encode("utf-8")).hexdigest()
if record.name in sequence_hash_by_name:
# If the hashes differ (multiple entries with the same
# strain name but different sequences), we keep the first
# sequence and add the strain to a list of duplicates to
# report at the end.
if sequence_hash_by_name.get(record.name) != sequence_hash:
duplicate_strains.add(record.name)
# If the current strain has been seen before, don't write
# out its sequence again.
continue
sequence_hash_by_name[record.name] = sequence_hash
write_sequences(record, output_handle)
if len(duplicate_strains) > 0:
error_mode = "ERROR"
exit_code = 1
if args.warn_about_duplicates:
error_mode = "WARNING"
exit_code = 0
print(
f"{error_mode}: Detected the following duplicate input strains with different sequences:",
file=sys.stderr
)
for strain in duplicate_strains:
print(textwrap.indent(strain, " "), file=sys.stderr)