def test_antitarget(self):
"""The 'antitarget' command."""
baits = tabio.read_auto('formats/nv2_baits.interval_list')
access = tabio.read_auto('../data/access-5k-mappable.hg19.bed')
self.assertLess(0, len(commands.do_antitarget(baits)))
self.assertLess(0, len(commands.do_antitarget(baits, access)))
self.assertLess(0, len(commands.do_antitarget(baits, access, 200000)))
self.assertLess(0, len(commands.do_antitarget(baits, access, 10000,
5000)))
def test_read_auto(self):
for fname, nrows in (("formats/empty", 0),
("formats/amplicon.bed", 1433),
("formats/amplicon.text", 1433),
("formats/nv2_baits.interval_list", 6809),
("formats/refflat-mini.txt", 100),
("formats/example.gff", 6),
):
self.assertEqual(len(tabio.read_auto(fname)), nrows)
with open(fname) as handle:
self.assertEqual(len(tabio.read_auto(handle)), nrows)
def test_target(self):
"""The 'target' command."""
annot_fname = "formats/refflat-mini.txt"
for bait_fname in ("formats/nv2_baits.interval_list",
"formats/amplicon.bed"):
baits = tabio.read_auto(bait_fname)
bait_len = len(baits)
# No splitting: w/ and w/o re-annotation
r1 = commands.do_target(baits)
self.assertEqual(len(r1), bait_len)
r1a = commands.do_target(baits,
do_short_names=True,
annotate=annot_fname)
self.assertEqual(len(r1a), len(r1))
# Splitting
r2 = commands.do_target(baits,
do_short_names=True,
do_split=True,
avg_size=100)
self.assertGreater(len(r2), len(r1))
r2a = commands.do_target(baits,
do_short_names=True,
do_split=True,
avg_size=100,
annotate=annot_fname)
self.assertEqual(len(r2a), len(r2))
# Original regions object should be unmodified
self.assertEqual(len(baits), bait_len)
def read_regions(bed_fname):
if bed_fname:
regions = tabio.read_auto(bed_fname)
if len(regions):
return regions
else:
logging.warn("No regions to estimate depth from %s",
regions.meta.get('filename', ''))
return None
def test_total_range_size(self):
"""Test total region coverage calculation."""
for fname, area in (
('formats/empty', 0),
('formats/duke-my.bed', 103),
('formats/dac-my.bed', 148),
('formats/example.gff', 7951),
('formats/refflat-mini.txt', 695404),
):
regions = tabio.read_auto(fname)
self.assertEqual(regions.total_range_size(), area)
def filter_targets(target_bed, sample_bams, procs):
"""Check if each potential target has significant coverage."""
baits = tabio.read_auto(target_bed)
# Loop over BAMs to calculate weighted averages of bin coverage depths
total_depths = np.zeros(len(baits), dtype=np.float_)
for bam_fname in sample_bams:
logging.info("Evaluating targets in %s", bam_fname)
sample = cnvlib.do_coverage(target_bed, bam_fname, processes=procs)
total_depths += sample['depth'].values
baits['depth'] = total_depths / len(sample_bams)
return baits
