def process(sequence,
sample_id=None,
group_id=None,
source=None,
threshold=None):
"""Process a sequence of exon lines.
Args:
sequence (sequence): list of chanjo bed lines
sample_id (Optional[str]): unique sample id, else auto-guessed
grouip_id (Optional[str]): id to group samples
source (Optional[str]): path to coverage source (BAM/Sambamba)
threshold (Optional[int]): completeness level to disqualify exons
Returns:
Result: iterators of `Transcript`, transcripts processed, sample model
"""
exons = sambamba.depth_output(sequence)
transcripts = groupby_tx(exons, sambamba=True)
raw_stats = ((tx_id, tx_stat(tx_id, exons, threshold=threshold))
for tx_id, exons in iteritems(transcripts))
if sample_id is None:
sample_id = next(itervalues(transcripts))[0]['sampleName']
sample_obj = Sample(id=sample_id, group_id=group_id, source=source)
models = (make_model(sample_obj, tx_id, raw_stat)
for tx_id, raw_stat in raw_stats)
return Result(models=models, count=len(transcripts), sample=sample_obj)
def test_depth_output_exon():
bed_lines = ["# chrom\tchromStart\tchromEnd\tF3\tF4\tF5\tF6\tF7\t"
"readCount\tmeanCoverage\tpercentage10\tpercentage20"
"\tpercentage100\tsampleName",
"1\t69089\t70007\t1-69090-70007\t0\t+\tCCDS30547.1\tOR4F5\t"
"232\t25.4946\t57.9521\t36.0566\t5.55556\tADM992A10\t"]
row_data = sambamba.depth_output(bed_lines)
results = [data for data in row_data]
assert len(results) == 1
assert results[0]['sampleName'] == 'ADM992A10'
assert results[0]['chromStart'] == 69089
def test_depth_output_exon():
bed_lines = [
"# chrom\tchromStart\tchromEnd\tF3\tF4\tF5\tF6\tF7\t"
"readCount\tmeanCoverage\tpercentage10\tpercentage20"
"\tpercentage100\tsampleName",
"1\t69089\t70007\t1-69090-70007\t0\t+\tCCDS30547.1\tOR4F5\t"
"232\t25.4946\t57.9521\t36.0566\t5.55556\tADM992A10\t",
]
row_data = sambamba.depth_output(bed_lines)
results = [data for data in row_data]
assert len(results) == 1
assert results[0]["sampleName"] == "ADM992A10"
assert results[0]["chromStart"] == 69089
def load_sambamba(chanjo_db, bed_iterable, sample_id=None, group_id=None):
"""Load Sambamba BED output from a stream."""
rows = sambamba.depth_output(bed_iterable)
stats = sambamba_rows(chanjo_db.session,
rows,
sample_id=sample_id,
group_id=group_id)
for index, stat in enumerate(stats):
chanjo_db.add(stat)
if index % 10000 == 0:
chanjo_db.save()
logger.info("processed %s annotations", index)
chanjo_db.save()
logger.info("processed %s annotations", index)
def test_depth_output_gene():
bed_lines = ["# chrom\tchromStart\tchromEnd\tF3\treadCount\tmeanCoverage\t"
"percentage10\tpercentage20\tpercentage100\tsampleName",
"1\t69089\t70007\tOR4F5\t232\t25.4946\t57.9521\t36.0566\t"
"5.55556\tADM992A10\t"]
row_data = sambamba.depth_output(bed_lines)
results = [data for data in row_data]
assert len(results) == 1
assert results[0]['chrom'] == '1'
assert results[0]['chromStart'] == 69089
assert results[0]['chromEnd'] == 70007
assert results[0]['extraFields'] == ['OR4F5']
assert results[0]['readCount'] == 232
assert results[0]['meanCoverage'] == 25.4946
assert results[0]['thresholds'][20] == 36.0566
assert results[0]['sampleName'] == 'ADM992A10'
def test_depth_output_gene():
bed_lines = [
"# chrom\tchromStart\tchromEnd\tF3\treadCount\tmeanCoverage\t"
"percentage10\tpercentage20\tpercentage100\tsampleName",
"1\t69089\t70007\tOR4F5\t232\t25.4946\t57.9521\t36.0566\t" "5.55556\tADM992A10\t",
]
row_data = sambamba.depth_output(bed_lines)
results = [data for data in row_data]
assert len(results) == 1
assert results[0]["chrom"] == "1"
assert results[0]["chromStart"] == 69089
assert results[0]["chromEnd"] == 70007
assert results[0]["extraFields"] == ["OR4F5"]
assert results[0]["readCount"] == 232
assert results[0]["meanCoverage"] == 25.4946
assert results[0]["thresholds"][20] == 36.0566
assert results[0]["sampleName"] == "ADM992A10"
def setup(self):
self.store = Store('sqlite://')
self.store.set_up()
self.row_data = parse_sambamba.depth_output(bed_lines)
