def test_chanj_with_sambamba():
bed_lines = ["# chrom\tchromStart\tchromEnd\treadCount\tmeanCoverage"
"\tsampleName",
"1\t69089\t70007\t232\t25.4946\tADM992A10\t"]
with pytest.raises(BedFormattingError):
list(bed.chanjo(bed_lines))
def test_chanj_with_sambamba():
bed_lines = [
"# chrom\tchromStart\tchromEnd\treadCount\tmeanCoverage"
"\tsampleName", "1\t69089\t70007\t232\t25.4946\tADM992A10\t"
]
with pytest.raises(BedFormattingError):
list(bed.chanjo(bed_lines))
def test_chanjo():
with open(TEST_OUTPUT, 'r') as handle:
data_rows = [data for data in bed.chanjo(handle)]
data = data_rows[0]
assert data['name'] == '1-69090-70007'
assert data['score'] == 0
assert data['strand'] == '+'
assert list(data['elements']) == [('CCDS30547.1', 'OR4F5')]
def test_chanjo():
with open(TEST_OUTPUT, 'r') as handle:
data_rows = [data for data in bed.chanjo(handle)]
data = data_rows[0]
assert data['name'] == '1-69090-70007'
assert data['score'] == 0
assert data['strand'] == '+'
assert list(data['elements']) == [('CCDS30547.1', 'OR4F5')]
def link_elements(chanjo_db, bed_iterable, batch_size=10000):
"""Load Sambamba BED output from a stream."""
rows = bed.chanjo(bed_iterable)
stats = link_mod.rows(chanjo_db.session, rows)
for index, stat in enumerate(stats):
chanjo_db.add(stat)
if index % batch_size == 0:
chanjo_db.save()
logger.debug('processed %s exons...', index)
chanjo_db.save()
def link_elements(chanjo_db, bed_iterable, batch_size=10000):
"""Load Sambamba BED output from a stream."""
rows = bed.chanjo(bed_iterable)
stats = link_mod.rows(chanjo_db.session, rows)
for index, stat in enumerate(stats):
chanjo_db.add(stat)
if index % batch_size == 0:
chanjo_db.save()
logger.debug('processed %s exons...', index)
chanjo_db.save()
def process(sequence):
"""Process a sequence of exon lines.
Args:
sequence (sequence): list of chanjo bed lines
Returns:
Result: iterators of transcript models, number of transcripts processed
"""
exons = bed.chanjo(sequence)
transcripts = groupby_tx(exons)
models = (make_model(tx_id, exons)
for tx_id, exons in iteritems(transcripts))
return Result(models=models, count=len(transcripts))
