def test_batch(self):
"""The 'batch' command."""
target_bed = "formats/my-targets.bed"
fasta = "formats/chrM-Y-trunc.hg19.fa"
bam = "formats/na12878-chrM-Y-trunc.bam"
annot = "formats/my-refflat.bed"
# Build a single-sample WGS reference
ref_fname, tgt_bed_fname, _ = batch.batch_make_reference(
[bam], None, None, True, fasta, annot, True, 500, None, None,
None, None, 'build', 1, False, "wgs")
self.assertEqual(ref_fname, 'build/reference.cnn')
refarr = cnvlib.read(ref_fname, 'bed')
tgt_regions = tabio.read(tgt_bed_fname, 'bed')
self.assertEqual(len(refarr), len(tgt_regions))
# Build a single-sample hybrid-capture reference
ref_fname, tgt_bed_fname, anti_bed_fname = batch.batch_make_reference(
[bam], target_bed, None, True, fasta, None, True, 10, None, 1000,
100, None, 'build', 1, False, "hybrid")
self.assertEqual(ref_fname, 'build/reference.cnn')
refarr = cnvlib.read(ref_fname, 'bed')
tgt_regions = tabio.read(tgt_bed_fname, 'bed')
anti_regions = tabio.read(anti_bed_fname, 'bed')
self.assertEqual(len(refarr), len(tgt_regions) + len(anti_regions))
# Run the same sample
batch.batch_run_sample(
bam, tgt_bed_fname, anti_bed_fname, ref_fname, 'build', True,
True, True, None, False, False, "hybrid", 1)
cns = cnvlib.read("build/na12878-chrM-Y-trunc.cns")
self.assertGreater(len(cns), 0)
def test_read_vcf(self):
"""Read the VCF format."""
# Paired VCF with full info
fname = "formats/na12878_na12882_mix.vcf"
v1 = tabio.read(fname, "vcf")
self.assertLess(len(v1), linecount(fname))
self.assertLess(0, len(v1))
for sid in ("NA12882", "NA12878"):
v2 = tabio.read(fname, "vcf", sample_id=sid)
self.assertEqual(v2.sample_id, sid)
self.assertEqual(len(v1), len(v2))
for kwarg in ({'min_depth': 100},
{'skip_somatic': True},
{'skip_reject': True}):
v3 = tabio.read(fname, "vcf", **kwarg)
self.assertLess(len(v3), len(v1))
self.assertLess(0, len(v3),
"%d variants left after filter %r"
% (len(v3), list(kwarg)[0]))
# VCF header, no samples, no records
v4 = tabio.read('formats/nosample.vcf', 'vcf')
self.assertEqual(len(v4), 0)
self.assertEqual(v4.sample_id, 'nosample')
# VCF with 1 sample, no records
v5 = tabio.read('formats/blank.vcf', 'vcf', sample_id='Blank')
self.assertEqual(len(v5), 0)
self.assertEqual(v5.sample_id, 'Blank')
def test_autobin(self):
"""The 'autobin' command."""
bam_fname = "formats/na12878-chrM-Y-trunc.bam"
target_bed = "formats/my-targets.bed"
targets = tabio.read(target_bed, 'bed')
access_bed = "../data/access-5k-mappable.hg19.bed"
accessible = tabio.read(access_bed, 'bed').filter(chromosome='chrY')
for method in ('amplicon', 'wgs', 'hybrid'):
(cov, bs), _ = autobin.do_autobin(bam_fname, method,
targets=targets,
access=accessible)
self.assertGreater(cov, 0)
self.assertGreater(bs, 0)
def test_resize_ranges(self):
"""Test resizing bins."""
baits_fname = 'formats/nv2_baits.interval_list'
chrom_sizes = {
'chr1': 249250621,
'chr2': 243199373,
'chr3': 198022430,
'chr4': 191154276,
'chr5': 180915260,
'chr6': 171115067,
'chr7': 159138663,
'chr8': 146364022,
'chr9': 141213431,
'chr10': 135534747,
'chr11': 135006516,
'chr12': 133851895,
'chr13': 115169878,
'chr14': 107349540,
'chr15': 102531392,
'chr16': 90354753,
'chr17': 81195210,
'chr18': 78077248,
'chr19': 59128983,
'chr20': 63025520,
'chr21': 48129895,
'chr22': 51304566,
'chrX': 155270560,
'chrY': 59373566
}
bins = tabio.read(baits_fname, 'interval')
for chrom, arr in bins.resize_ranges(1e7, chrom_sizes).by_chromosome():
self.assertLessEqual(0, arr.start.min())
self.assertLessEqual(arr.end.max(), chrom_sizes[chrom])
def test_read_vcf(self):
"""Read the VCF format."""
fname = "formats/na12878_na12882_mix.vcf"
v1 = tabio.read(fname, "vcf")
self.assertLess(len(v1), linecount(fname))
self.assertLess(0, len(v1))
for sid in ("NA12882", "NA12878"):
v2 = tabio.read(fname, "vcf", sample_id=sid)
self.assertEqual(v2.sample_id, sid)
self.assertEqual(len(v1), len(v2))
for kwarg in ({
'min_depth': 100
}, {
'skip_somatic': True
}, {
'skip_reject': True
}):
v3 = tabio.read(fname, "vcf", **kwarg)
self.assertLess(len(v3), len(v1))
self.assertLess(0, len(v3))
def test_segment(self):
"""The 'segment' command."""
cnarr = cnvlib.read("formats/amplicon.cnr")
# NB: R methods are in another script; haar is pure-Python
segments = segmentation.do_segmentation(cnarr, "haar")
self.assertGreater(len(segments), 0)
segments = segmentation.do_segmentation(cnarr, "haar", threshold=.0001,
skip_low=True)
self.assertGreater(len(segments), 0)
varr = tabio.read("formats/na12878_na12882_mix.vcf", "vcf")
segments = segmentation.do_segmentation(cnarr, "haar", variants=varr)
self.assertGreater(len(segments), 0)
def test_call_filter(self):
segments = cnvlib.read("formats/tr95t.segmetrics.cns")
variants = tabio.read("formats/na12878_na12882_mix.vcf", "vcf")
# Each filter individually, then all filters together
for filters in (['ampdel'], ['cn'], ['ci'], ['sem'],
['sem', 'cn', 'ampdel'],
['ci', 'cn', 'ampdel']):
result = commands.do_call(segments, variants, method="threshold",
purity=.9, is_reference_male=True,
is_sample_female=True, filters=filters)
self.assertLessEqual(len(result), len(segments))
self.assertLessEqual(len(segments.chromosome.unique()), len(result))
for colname in 'baf', 'cn', 'cn1', 'cn2':
self.assertIn(colname, result)
def test_empty(self):
"""Instantiate from an empty file."""
garr = tabio.read("formats/empty")
self.assertEqual(len(garr), 0)
AP = argparse.ArgumentParser(description=__doc__)
AP.add_argument('refflat', help="UCSC refFlat.txt for the reference genome.")
AP.add_argument('-e',
'--exons',
action='store_true',
help="""Emit each exon instead of the whole gene regions.""")
AP.add_argument('-f',
'--flatten',
action='store_true',
help="""Flatten overlapping regions, keeping original
boundaries. Not recommended with --exons.""")
AP.add_argument('-m',
'--merge',
metavar='BASEPAIRS',
nargs='?',
type=int,
const=1,
help="""Merge overlapping regions with different names.
Recommended with --exons. Optional argument value is the
number of overlapping bases between two regions to trigger a
merge. [Default: %(const)s]""")
AP.add_argument('-o', '--output', help="Output filename.")
args = AP.parse_args()
regions = tabio.read(args.refflat, 'refflat', exons=args.exons)
if args.flatten:
regions = regions.flatten()
elif args.merge:
regions = regions.merge(bp=args.merge)
tabio.write(regions, args.output, 'bed4')
def test_read_text(self):
"""Read the text region format."""
fname = "formats/amplicon.text"
regions = tabio.read(fname, "text")
self.assertEqual(len(regions), linecount(fname))
self.assertEqual(regions.sample_id, "amplicon")
def test_read_picardhs(self):
"""Read Picard CalculateHsMetrics PER_TARGET_COVERAGE format."""
fname = "picard/p2-5_5.antitargetcoverage.csv"
cna = tabio.read(fname, "picardhs")
self.assertEqual(len(cna), linecount(fname) - 1)
self.assertEqual(cna.sample_id, "p2-5_5")
def test_read_ilist(self):
"""Read the interval list format."""
regions = tabio.read("formats/nv2_baits.interval_list", "interval")
self.assertEqual(len(regions), 6809)
self.assertEqual(regions.sample_id, "nv2_baits")
def test_read_bed(self):
"""Read the BED format."""
fname = "formats/amplicon.bed"
regions = tabio.read(fname, "bed")
self.assertEqual(len(regions), linecount(fname))
self.assertEqual(regions.sample_id, "amplicon")
def test_empty(self):
"""Instantiate from an empty file."""
for fmt in ("auto", "tab", "bed", "interval", "text"):
regions = tabio.read("formats/empty", fmt=fmt)
self.assertEqual(len(regions), 0)
def test_read_refflat(self):
"""Read the UCSC 'refFlat' format."""
fname = "formats/refflat-mini.txt"
regions = tabio.read(fname, 'refflat')
self.assertEqual(len(regions), linecount(fname))
self.assertEqual(13, regions.chromosome.nunique())
def test_read_gff(self):
"""Read the GFF format."""
fname = 'formats/example.gff'
regions = tabio.read(fname, 'gff')
self.assertEqual(len(regions), linecount(fname) - 2)
self.assertEqual(regions.sample_id, 'example')
