def parse_basic_args(parser):
'It parses the command line and it returns a dict with the arguments.'
parsed_args = parser.parse_args()
# we have to wrap the file in a BufferedReader to allow peeking into stdin
wrapped_fhands = []
# if input is stdin it will be a fhand not a list of fhands.
# we have to convert to a list
in_fhands = parsed_args.input
if not isinstance(in_fhands, list):
in_fhands = [in_fhands]
for fhand in in_fhands:
fhand = wrap_in_buffered_reader(fhand)
fhand = uncompress_if_required(fhand)
wrapped_fhands.append(fhand)
# We have to add the one_line to the fastq files in order to get the
# speed improvements of the seqitems
in_format = parsed_args.in_format
if in_format == GUESS_FORMAT:
for wrapped_fhand in wrapped_fhands:
get_format(wrapped_fhand)
else:
if in_format != get_format(wrapped_fhands[0]):
msg = 'The given input format does not correspond to the input'
msg += ' file'
raise WrongFormatError(msg)
if 'fastq' in in_format:
for wrapped_fhand in wrapped_fhands:
get_format(wrapped_fhand)
else:
# we dont set the first one because already did in the previous
# checking
for wrapped_fhand in wrapped_fhands[1:]:
set_format(wrapped_fhand, in_format)
out_fhand = getattr(parsed_args, OUTFILE)
comp_kind = get_requested_compression(parsed_args)
if isinstance(out_fhand, list):
new_out_fhands = []
for out_f in out_fhand:
try:
out_f = compress_fhand(out_f, compression_kind=comp_kind)
except RuntimeError, error:
parser.error(error)
new_out_fhands.append(out_f)
out_fhand = new_out_fhands
def _sorted_mapped_reads(ref_fpath, paired_fpaths=None,
unpaired_fpaths=None, directory=None,
file_format=None, min_seed_len=None):
fhand = open(paired_fpaths[0]) if paired_fpaths else open(unpaired_fpaths[0])
if file_format is not None:
set_format(fhand, file_format)
else:
file_format = get_format(fhand)
index_fpath = get_or_create_bwa_index(ref_fpath, directory)
extra_params = ['-a', '-M']
if min_seed_len is not None:
extra_params.extend(['-k', min_seed_len])
bwa = map_with_bwamem(index_fpath, paired_fpaths=paired_fpaths,
unpaired_fpath=unpaired_fpaths,
extra_params=extra_params)
bam_fhand = NamedTemporaryFile(dir='/home/carlos/tmp')
sort_mapped_reads(bwa, bam_fhand.name, key='queryname')
bamfile = pysam.Samfile(bam_fhand.name)
return bamfile
def test_get_format_fhand(self):
"It checks the get/set format functions"
# file fhand
fhand = NamedTemporaryFile()
fhand.write(">seq\natgctacgacta\n")
fhand.flush()
name = fhand.name
id_ = id(fhand)
file_format = get_format(fhand)
assert FILEFORMAT_INVENTORY[(id_, name)] == file_format
num_keys = len(FILEFORMAT_INVENTORY)
file_format = get_format(fhand)
assert FILEFORMAT_INVENTORY[(id_, name)] == file_format
assert len(FILEFORMAT_INVENTORY) == num_keys
fhand = NamedTemporaryFile()
set_format(fhand, "fasta")
assert "fasta" == get_format(fhand)
def test_get_format_fhand(self):
"It checks the get/set format functions"
#file fhand
fhand = NamedTemporaryFile()
fhand.write('>seq\natgctacgacta\n')
fhand.flush()
name = fhand.name
id_ = id(fhand)
file_format = get_format(fhand)
assert FILEFORMAT_INVENTORY[(id_, name)] == file_format
num_keys = len(FILEFORMAT_INVENTORY)
file_format = get_format(fhand)
assert FILEFORMAT_INVENTORY[(id_, name)] == file_format
assert len(FILEFORMAT_INVENTORY) == num_keys
fhand = NamedTemporaryFile()
set_format(fhand, 'fasta')
assert 'fasta' == get_format(fhand)
def parse_basic_args(parser):
'It parses the command line and it returns a dict with the arguments.'
parsed_args = parser.parse_args()
# we have to wrap the file in a BufferedReader to allow peeking into stdin
wrapped_fhands = []
# if input is stdin it will be a fhand not a list of fhands.
# we have to convert to a list
in_fhands = parsed_args.input
if not isinstance(in_fhands, list):
in_fhands = [in_fhands]
for fhand in in_fhands:
fhand = wrap_in_buffered_reader(fhand)
fhand = uncompress_if_required(fhand)
wrapped_fhands.append(fhand)
# We have to add the one_line to the fastq files in order to get the
# speed improvements of the seqitems
in_format = parsed_args.in_format
if in_format == GUESS_FORMAT:
for wrapped_fhand in wrapped_fhands:
get_format(wrapped_fhand)
else:
for wrapped_fhand in wrapped_fhands:
set_format(wrapped_fhand, in_format)
out_fhand = getattr(parsed_args, OUTFILE)
comp_kind = get_requested_compression(parsed_args)
if isinstance(out_fhand, list):
new_out_fhands = []
for out_f in out_fhand:
try:
out_f = compress_fhand(out_f, compression_kind=comp_kind)
except RuntimeError, error:
parser.error(error)
new_out_fhands.append(out_f)
out_fhand = new_out_fhands
def parse_basic_args(parser):
'It parses the command line and it returns a dict with the arguments.'
parsed_args = parser.parse_args()
# we have to wrap the file in a BufferedReader to allow peeking into stdin
wrapped_fhands = []
# if input is stdin it will be a fhand not a list of fhands.
# we have to convert to a list
in_fhands = parsed_args.input
if not isinstance(in_fhands, list):
in_fhands = [in_fhands]
for fhand in in_fhands:
fhand = wrap_in_buffered_reader(fhand)
fhand = uncompress_if_required(fhand)
wrapped_fhands.append(fhand)
# We have to add the one_line to the fastq files in order to get the
# speed improvements of the seqitems
in_format = parsed_args.in_format
if in_format == GUESS_FORMAT:
for wrapped_fhand in wrapped_fhands:
get_format(wrapped_fhand)
else:
for wrapped_fhand in wrapped_fhands:
set_format(wrapped_fhand, in_format)
out_fhand = getattr(parsed_args, OUTFILE)
comp_kind = get_requested_compression(parsed_args)
if isinstance(out_fhand, list):
new_out_fhands = []
for out_f in out_fhand:
try:
out_f = compress_fhand(out_f, compression_kind=comp_kind)
except RuntimeError, error:
parser.error(error)
new_out_fhands.append(out_f)
out_fhand = new_out_fhands
def test_pair_matcher(self):
'It test the pair matcher function'
# with equal seqs but the last ones
file1 = os.path.join(TEST_DATA_DIR, 'pairend1.sfastq')
file2 = os.path.join(TEST_DATA_DIR, 'pairend2.sfastq')
fwd_seqs = read_seqs([open(file1)])
rev_seqs = read_seqs([open(file2)])
out_fhand = StringIO()
orphan_out_fhand = StringIO()
out_format = 'fastq'
seqs = flat_zip_longest(fwd_seqs, rev_seqs)
match_pairs(seqs, out_fhand, orphan_out_fhand, out_format)
output = out_fhand.getvalue()
assert '@seq1:136:FC706VJ:2:2104:15343:197393 1:Y:18:ATCACG' in output
assert '@seq2:136:FC706VJ:2:2104:15343:197393 2:Y:18:ATCACG' in output
orp = orphan_out_fhand.getvalue()
assert '@seq8:136:FC706VJ:2:2104:15343:197393 2:Y:18:ATCACG' in orp
# with the firsts seqs different
file1 = os.path.join(TEST_DATA_DIR, 'pairend1.sfastq')
file2 = os.path.join(TEST_DATA_DIR, 'pairend3.sfastq')
fwd_seqs = read_seqs([open(file1)])
rev_seqs = read_seqs([open(file2)])
out_fhand = StringIO()
orphan_out_fhand = StringIO()
out_format = 'fastq'
seqs = flat_zip_longest(fwd_seqs, rev_seqs)
match_pairs(seqs, out_fhand, orphan_out_fhand, out_format)
output = out_fhand.getvalue()
assert '@seq4:136:FC706VJ:2:2104:15343:197393 1:Y:18:ATCACG' in output
assert '@seq5:136:FC706VJ:2:2104:15343:197393 2:Y:18:ATCACG' in output
orp = orphan_out_fhand.getvalue()
assert '@seq1:136:FC706VJ:2:2104:15343:197393 1:Y:18:ATCACG' in orp
assert '@seq3:136:FC706VJ:2:2104:15343:197393 2:Y:18:ATCACG' in orp
assert '@seq6:136:FC706VJ:2:2104:15343:197393 2:Y:18:ATCACG' in orp
file1 = os.path.join(TEST_DATA_DIR, 'pairend4.sfastq')
file2 = os.path.join(TEST_DATA_DIR, 'pairend2.sfastq')
fwd_seqs = read_seqs([open(file1)])
rev_seqs = read_seqs([open(file2)])
out_fhand = StringIO()
orphan_out_fhand = StringIO()
out_format = 'fastq'
seqs = flat_zip_longest(fwd_seqs, rev_seqs)
match_pairs(seqs, out_fhand, orphan_out_fhand, out_format)
output = out_fhand.getvalue()
assert '@seq8:136:FC706VJ:2:2104:15343:197393 1:Y:18:ATCACG' in output
assert '@seq8:136:FC706VJ:2:2104:15343:197393 2:Y:18:ATCACG' in output
orp = orphan_out_fhand.getvalue()
assert '@seq1:136:FC706VJ:2:2104:15343:197393 2:Y:18:ATCACG' in orp
assert '@seq2:136:FC706VJ:2:2104:15343:197393 2:Y:18:ATCACG' in orp
# with reads with no direcction
file1 = os.path.join(TEST_DATA_DIR, 'pairend7.sfastq')
file2 = os.path.join(TEST_DATA_DIR, 'pairend2.sfastq')
fwd_seqs = read_seqs([open(file1)])
rev_seqs = read_seqs([open(file2)])
out_fhand = StringIO()
orphan_out_fhand = StringIO()
out_format = 'fastq'
seqs = flat_zip_longest(fwd_seqs, rev_seqs)
match_pairs(seqs, out_fhand, orphan_out_fhand, out_format)
output = out_fhand.getvalue()
assert '@seq8:136:FC706VJ:2:2104:15343:197393 1:Y:18:ATCACG' in output
assert '@seq8:136:FC706VJ:2:2104:15343:197393 2:Y:18:ATCACG' in output
assert '@seq1:136:FC706VJ:2:2104:15343:197393 2:Y:18:ATCACG' in output
assert '@seq1:136:FC706VJ:2:2104:15343:197393 2:Y:18:ATCACG' in output
orp = orphan_out_fhand.getvalue()
assert '@seq6:136:FC706VJ:2:2104:15343:197393.mpl_1' in orp
assert '@seq7:136:FC706VJ:2:2104:15343:197393.hhhh' in orp
assert '@seq2:136:FC706VJ:2:2104:15343:197393 2:Y:18:ATCAC' in orp
# File is not sorted
file1 = '''@s1.f
AACCAGTCAAC
+
CCCFFFFFGHH
@s2.f
AACCAGTCAAC
+
CCCFFFFFGHH
@s1.r
AACCAGTCAAC
+
CCCFFFFFGHH
'''
file1 = StringIO(file1)
set_format(file1, 'fastq')
seqs = read_seqs([file1])
out_fhand = StringIO()
orphan_out_fhand = StringIO()
out_format = 'fastq'
try:
match_pairs(seqs, out_fhand, orphan_out_fhand, out_format,
check_order_buffer_size=10)
output = out_fhand.getvalue()
self.fail('ItemsNotSortedError error expected')
except ItemsNotSortedError:
pass
def test_pair_matcher(self):
'It test the pair matcher function'
# with equal seqs but the last ones
file1 = os.path.join(TEST_DATA_DIR, 'pairend1.sfastq')
file2 = os.path.join(TEST_DATA_DIR, 'pairend2.sfastq')
fwd_seqs = read_seqs([open(file1)])
rev_seqs = read_seqs([open(file2)])
out_fhand = StringIO()
orphan_out_fhand = StringIO()
out_format = 'fastq'
seqs = flat_zip_longest(fwd_seqs, rev_seqs)
match_pairs(seqs, out_fhand, orphan_out_fhand, out_format)
output = out_fhand.getvalue()
assert '@seq1:136:FC706VJ:2:2104:15343:197393 1:Y:18:ATCACG' in output
assert '@seq2:136:FC706VJ:2:2104:15343:197393 2:Y:18:ATCACG' in output
orp = orphan_out_fhand.getvalue()
assert '@seq8:136:FC706VJ:2:2104:15343:197393 2:Y:18:ATCACG' in orp
# with the firsts seqs different
file1 = os.path.join(TEST_DATA_DIR, 'pairend1.sfastq')
file2 = os.path.join(TEST_DATA_DIR, 'pairend3.sfastq')
fwd_seqs = read_seqs([open(file1)])
rev_seqs = read_seqs([open(file2)])
out_fhand = StringIO()
orphan_out_fhand = StringIO()
out_format = 'fastq'
seqs = flat_zip_longest(fwd_seqs, rev_seqs)
match_pairs(seqs, out_fhand, orphan_out_fhand, out_format)
output = out_fhand.getvalue()
assert '@seq4:136:FC706VJ:2:2104:15343:197393 1:Y:18:ATCACG' in output
assert '@seq5:136:FC706VJ:2:2104:15343:197393 2:Y:18:ATCACG' in output
orp = orphan_out_fhand.getvalue()
assert '@seq1:136:FC706VJ:2:2104:15343:197393 1:Y:18:ATCACG' in orp
assert '@seq3:136:FC706VJ:2:2104:15343:197393 2:Y:18:ATCACG' in orp
assert '@seq6:136:FC706VJ:2:2104:15343:197393 2:Y:18:ATCACG' in orp
file1 = os.path.join(TEST_DATA_DIR, 'pairend4.sfastq')
file2 = os.path.join(TEST_DATA_DIR, 'pairend2.sfastq')
fwd_seqs = read_seqs([open(file1)])
rev_seqs = read_seqs([open(file2)])
out_fhand = StringIO()
orphan_out_fhand = StringIO()
out_format = 'fastq'
seqs = flat_zip_longest(fwd_seqs, rev_seqs)
match_pairs(seqs, out_fhand, orphan_out_fhand, out_format)
output = out_fhand.getvalue()
assert '@seq8:136:FC706VJ:2:2104:15343:197393 1:Y:18:ATCACG' in output
assert '@seq8:136:FC706VJ:2:2104:15343:197393 2:Y:18:ATCACG' in output
orp = orphan_out_fhand.getvalue()
assert '@seq1:136:FC706VJ:2:2104:15343:197393 2:Y:18:ATCACG' in orp
assert '@seq2:136:FC706VJ:2:2104:15343:197393 2:Y:18:ATCACG' in orp
# with reads with no direcction
file1 = os.path.join(TEST_DATA_DIR, 'pairend7.sfastq')
file2 = os.path.join(TEST_DATA_DIR, 'pairend2.sfastq')
fwd_seqs = read_seqs([open(file1)])
rev_seqs = read_seqs([open(file2)])
out_fhand = StringIO()
orphan_out_fhand = StringIO()
out_format = 'fastq'
seqs = flat_zip_longest(fwd_seqs, rev_seqs)
match_pairs(seqs, out_fhand, orphan_out_fhand, out_format)
output = out_fhand.getvalue()
assert '@seq8:136:FC706VJ:2:2104:15343:197393 1:Y:18:ATCACG' in output
assert '@seq8:136:FC706VJ:2:2104:15343:197393 2:Y:18:ATCACG' in output
assert '@seq1:136:FC706VJ:2:2104:15343:197393 2:Y:18:ATCACG' in output
assert '@seq1:136:FC706VJ:2:2104:15343:197393 2:Y:18:ATCACG' in output
orp = orphan_out_fhand.getvalue()
assert '@seq6:136:FC706VJ:2:2104:15343:197393.mpl_1' in orp
assert '@seq7:136:FC706VJ:2:2104:15343:197393.hhhh' in orp
assert '@seq2:136:FC706VJ:2:2104:15343:197393 2:Y:18:ATCAC' in orp
# File is not sorted
file1 = '''@s1.f
AACCAGTCAAC
+
CCCFFFFFGHH
@s2.f
AACCAGTCAAC
+
CCCFFFFFGHH
@s1.r
AACCAGTCAAC
+
CCCFFFFFGHH
'''
file1 = StringIO(file1)
set_format(file1, 'fastq')
seqs = read_seqs([file1])
out_fhand = StringIO()
orphan_out_fhand = StringIO()
out_format = 'fastq'
try:
match_pairs(seqs,
out_fhand,
orphan_out_fhand,
out_format,
check_order_buffer_size=10)
output = out_fhand.getvalue()
self.fail('ItemsNotSortedError error expected')
except ItemsNotSortedError:
pass