def test_export(self):
"""Run the 'export' command with each format."""
# SEG
seg_rows = export.export_seg(["formats/tr95t.cns"])
self.assertGreater(len(seg_rows), 0)
seg2_rows = export.export_seg(["formats/tr95t.cns",
"formats/cl_seq.cns"])
self.assertGreater(len(seg2_rows), len(seg_rows))
# THetA2
cnr = tabio.read_cna("formats/tr95t.cns")
theta_rows = export.export_theta(cnr, None)
self.assertGreater(len(theta_rows), 0)
ref = tabio.read_cna("formats/reference-tr.cnn")
theta_rows = export.export_theta(cnr, ref)
self.assertGreater(len(theta_rows), 0)
# Formats that calculate absolute copy number
for fname, ploidy, is_f in [("tr95t.cns", 2, True),
("cl_seq.cns", 6, True),
("amplicon.cns", 2, False)]:
cns = tabio.read_cna("formats/" + fname)
# BED
self.assertLess(len(export.export_bed(cns, ploidy, True, is_f,
cns.sample_id, "ploidy")),
len(cns))
self.assertLess(len(export.export_bed(cns, ploidy, True, is_f,
cns.sample_id, "variant")),
len(cns))
self.assertEqual(len(export.export_bed(cns, ploidy, True, is_f,
cns.sample_id, "all")),
len(cns))
# VCF
_vheader, vcf_body = export.export_vcf(cns, ploidy, True, is_f)
self.assertTrue(0 < len(vcf_body.splitlines()) < len(cns))
def test_ranges(self):
"""Test range methods: by_ranges, in_range, in_ranges."""
cnarr = tabio.read_cna("formats/amplicon.cnr")
segarr = tabio.read_cna("formats/amplicon.cns")
chrom_segarr = dict(segarr.by_chromosome())
for chrom, subarr in cnarr.by_chromosome():
count_segs = 0
count_bins = 0
subsegarr = chrom_segarr[chrom]
for count_segs, (seg, bins) in enumerate(subarr.by_ranges(subsegarr)):
count_bins += len(bins)
self.assertEqual(seg.probes, len(bins))
self.assertEqual(len(bins), len(
cnarr.in_range(seg.chromosome, seg.start, seg.end,
mode='outer')))
self.assertEqual(len(bins), len(
cnarr.in_range(seg.chromosome, seg.start, seg.end,
mode='trim')))
self.assertEqual(len(subsegarr), count_segs + 1)
self.assertEqual(len(subarr), count_bins)
self.assertEqual(len(subarr), len(
cnarr.in_ranges(chrom, subsegarr['start'], subsegarr['end'],
mode="outer")))
self.assertEqual(len(subarr), len(
subarr.in_ranges(starts=subsegarr['start'],
ends=subsegarr['end'], mode="outer")))
self.assertEqual(len(subarr), len(
cnarr.in_ranges(chrom, subsegarr['start'], subsegarr['end'],
mode="trim")))
self.assertEqual(len(subarr), len(
subarr.in_ranges(starts=subsegarr['start'],
ends=subsegarr['end'], mode="trim")))
def test_gainloss(self):
"""The 'gainloss' command."""
probes = tabio.read_cna("formats/amplicon.cnr")
rows = commands.do_gainloss(probes, male_reference=True)
self.assertGreater(len(rows), 0)
segs = tabio.read_cna("formats/amplicon.cns")
rows = commands.do_gainloss(probes, segs, 0.3, 4, male_reference=True)
self.assertGreater(len(rows), 0)
def test_metrics(self):
"""The 'metrics' command."""
cnarr = tabio.read_cna("formats/amplicon.cnr")
segments = tabio.read_cna("formats/amplicon.cns")
resids = cnarr.residuals(segments)
self.assertLessEqual(len(resids), len(cnarr))
values = metrics.ests_of_scale(resids)
for val in values:
self.assertGreater(val, 0)
def test_residuals(self):
cnarr = tabio.read_cna("formats/amplicon.cnr")
segments = tabio.read_cna("formats/amplicon.cns")
regions = gary.GenomicArray(segments.data).drop_extra_columns()
for arg in (None, segments, regions):
resid = cnarr.residuals(arg)
self.assertAlmostEqual(0, resid.mean(), delta=.3)
self.assertAlmostEqual(1, np.percentile(resid, 80), delta=.2)
self.assertAlmostEqual(2, resid.std(), delta=.5)
def test_drop_extra_columns(self):
"""Test removal of optional 'gc' column."""
cna = tabio.read_cna('formats/reference-tr.cnn')
self.assertIn('gc', cna)
cleaned = cna.drop_extra_columns()
self.assertNotIn('gc', cleaned)
self.assertTrue((cleaned['log2'] == cna['log2']).all())
def test_segment_parallel(self):
"""The 'segment' command, in parallel."""
cnarr = tabio.read_cna("formats/amplicon.cnr")
psegments = segmentation.do_segmentation(cnarr, "haar", processes=2)
ssegments = segmentation.do_segmentation(cnarr, "haar", processes=1)
self.assertEqual(psegments.data.shape, ssegments.data.shape)
self.assertEqual(len(psegments.meta), len(ssegments.meta))
def test_by_chromosome(self):
for fname in ("formats/amplicon.cnr", "formats/cl_seq.cns"):
cnarr = tabio.read_cna(fname)
row_count = 0
for _chrom, rows in cnarr.by_chromosome():
row_count += len(rows)
self.assertEqual(row_count, len(cnarr))
def test_basic(self):
"""Test basic container functionality and magic methods."""
cna = tabio.read_cna('formats/reference-tr.cnn')
# Length
self.assertEqual(len(cna),
linecount('formats/reference-tr.cnn') - 1)
# Equality
same = tabio.read_cna('formats/reference-tr.cnn')
self.assertEqual(cna, same)
# Item access
orig = cna[0]
cna[0] = orig
cna[3:4] = cna[3:4]
cna[6:10] = cna[6:10]
self.assertEqual(tuple(cna[0]), tuple(same[0]))
self.assertEqual(cna[3:6], same[3:6])
def test_segmetrics(self):
"""The 'segmetrics' command."""
cnarr = tabio.read_cna("formats/amplicon.cnr")
segarr = tabio.read_cna("formats/amplicon.cns")
for func in (
lambda x: metrics.confidence_interval_bootstrap(x, 0.05, 100),
lambda x: metrics.prediction_interval(x, 0.05),
):
lo, hi = commands._segmetric_interval(segarr, cnarr, func)
self.assertEqual(len(lo), len(segarr))
self.assertEqual(len(hi), len(segarr))
sensible_segs_mask = (np.asarray(segarr['probes']) > 3)
means = segarr[sensible_segs_mask, 'log2']
los = lo[sensible_segs_mask]
his = hi[sensible_segs_mask]
self.assertTrue((los < means).all())
self.assertTrue((means < his).all())
def test_call_gender(self):
"""Test each 'call' method on allosomes."""
for (
fname,
sample_is_f,
ref_is_m,
chr1_expect,
chrx_expect,
chry_expect,
chr1_cn,
chrx_cn,
chry_cn,
) in (
("formats/f-on-f.cns", True, False, 0, 0, None, 2, 2, None),
("formats/f-on-m.cns", True, True, 0.585, 1, None, 3, 2, None),
("formats/m-on-f.cns", False, False, 0, -1, 0, 2, 1, 1),
("formats/m-on-m.cns", False, True, 0, 0, 0, 2, 1, 1),
):
cns = tabio.read_cna(fname)
chr1_idx = (cns.chromosome == 'chr1')
chrx_idx = (cns.chromosome == 'chrX')
chry_idx = (cns.chromosome == 'chrY')
def test_chrom_means(segments):
self.assertEqual(chr1_cn, segments['cn'][chr1_idx].mean())
self.assertAlmostEqual(chr1_expect,
segments['log2'][chr1_idx].mean(), 0)
self.assertEqual(chrx_cn, segments['cn'][chrx_idx].mean())
self.assertAlmostEqual(chrx_expect,
segments['log2'][chrx_idx].mean(), 0)
if not sample_is_f:
self.assertEqual(chry_cn, segments['cn'][chry_idx].mean())
self.assertAlmostEqual(chry_expect,
segments['log2'][chry_idx].mean(),
0)
# Call threshold
cns_thresh = commands.do_call(cns,
None,
"threshold",
is_reference_male=ref_is_m,
is_sample_female=sample_is_f)
test_chrom_means(cns_thresh)
# Call clonal pure
cns_clone = commands.do_call(cns,
None,
"clonal",
is_reference_male=ref_is_m,
is_sample_female=sample_is_f)
test_chrom_means(cns_clone)
# Call clonal barely-mixed
cns_p99 = commands.do_call(cns,
None,
"clonal",
purity=0.99,
is_reference_male=ref_is_m,
is_sample_female=sample_is_f)
test_chrom_means(cns_p99)
def test_call(self):
"""The 'call' command."""
# Methods: clonal, threshold, none
tr_cns = tabio.read_cna("formats/tr95t.cns")
tr_thresh = commands.do_call(tr_cns,
None,
"threshold",
is_reference_male=True,
is_sample_female=True)
self.assertEqual(len(tr_cns), len(tr_thresh))
tr_clonal = commands.do_call(tr_cns,
None,
"clonal",
purity=.65,
is_reference_male=True,
is_sample_female=True)
self.assertEqual(len(tr_cns), len(tr_clonal))
cl_cns = tabio.read_cna("formats/cl_seq.cns")
cl_thresh = commands.do_call(cl_cns,
None,
"threshold",
thresholds=np.log2(
(np.arange(12) + .5) / 6.),
is_reference_male=True,
is_sample_female=True)
self.assertEqual(len(cl_cns), len(cl_thresh))
cl_clonal = commands.do_call(cl_cns,
None,
"clonal",
ploidy=6,
purity=.99,
is_reference_male=True,
is_sample_female=True)
self.assertEqual(len(cl_cns), len(cl_clonal))
cl_none = commands.do_call(cl_cns,
None,
"none",
ploidy=6,
purity=.99,
is_reference_male=True,
is_sample_female=True)
self.assertEqual(len(cl_cns), len(cl_none))
def test_segment(self):
"""The 'segment' command."""
cnarr = tabio.read_cna("formats/amplicon.cnr")
# R methods are in another script
segments = segmentation.do_segmentation(cnarr, "haar")
self.assertGreater(len(segments), 0)
segments = segmentation.do_segmentation(cnarr,
"haar",
threshold=.001,
skip_low=True)
self.assertGreater(len(segments), 0)
def test_segment(self):
"""The 'segment' command."""
cnarr = tabio.read_cna("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_fix(self):
"""The 'fix' command."""
# Extract fake target/antitarget bins from a combined file
ref = tabio.read_cna('formats/reference-tr.cnn')
is_bg = (ref["gene"] == "Background")
tgt_bins = ref[~is_bg]
tgt_bins.log2 += np.random.randn(len(tgt_bins)) / 5
anti_bins = ref[is_bg]
anti_bins.log2 += np.random.randn(len(anti_bins)) / 5
blank_bins = cnary.CopyNumArray([])
# Typical usage (hybrid capture)
cnr = commands.do_fix(tgt_bins, anti_bins, ref)
self.assertTrue(0 < len(cnr) <= len(ref))
# Blank antitargets (WGS or amplicon)
cnr = commands.do_fix(tgt_bins, blank_bins, ref[~is_bg])
self.assertTrue(0 < len(cnr) <= len(tgt_bins))
def test_guess_xx(self):
"""Guess chromosomal sex from chrX log2 ratio value."""
for (fname, sample_is_f, ref_is_m) in (
("formats/f-on-f.cns", True, False),
("formats/f-on-m.cns", True, True),
("formats/m-on-f.cns", False, False),
("formats/m-on-m.cns", False, True),
("formats/amplicon.cnr", False, True),
("formats/cl_seq.cns", True, True),
("formats/tr95t.cns", True, True),
("formats/reference-tr.cnn", False, False),
):
guess = tabio.read_cna(fname).guess_xx(ref_is_m)
self.assertEqual(guess, sample_is_f,
"%s: guessed XX %s but is %s"
% (fname, guess, sample_is_f))
def test_gender(self):
"""Guess chromosomal gender from chrX log2 ratio value."""
for (fname, sample_is_f, ref_is_m) in (
("formats/f-on-f.cns", True, False),
("formats/f-on-m.cns", True, True),
("formats/m-on-f.cns", False, False),
("formats/m-on-m.cns", False, True),
("formats/amplicon.cnr", False, True),
("formats/cl_seq.cns", True, True),
("formats/tr95t.cns", True, True),
("formats/reference-tr.cnn", False, False),
):
cnarr = tabio.read_cna(fname)
if sample_is_f != cnarr.guess_xx(ref_is_m):
print("Gender issue:", fname, sample_is_f, ref_is_m)
self.assertEqual(sample_is_f, cnarr.guess_xx(ref_is_m))
def test_center_all(self):
"""Test recentering."""
cna = tabio.read_cna('formats/reference-tr.cnn')
# Median-centering an already median-centered array -> no change
chr1 = cna.in_range('chr1')
self.assertAlmostEqual(0, np.median(chr1['log2']), places=1)
chr1.center_all()
orig_chr1_cvg = np.median(chr1['log2'])
self.assertAlmostEqual(0, orig_chr1_cvg)
# Median-centering resets a shift away from the median
chr1plus2 = chr1.copy()
chr1plus2['log2'] += 2.0
chr1plus2.center_all()
self.assertAlmostEqual(np.median(chr1plus2['log2']), orig_chr1_cvg)
# Other methods for centering are similar for a CN-neutral chromosome
for method in ("mean", "mode", "biweight"):
cp = chr1.copy()
cp.center_all(method)
self.assertLess(abs(cp['log2'].median() - orig_chr1_cvg), 0.1)
def test_breaks(self):
"""The 'breaks' command."""
probes = tabio.read_cna("formats/amplicon.cnr")
segs = tabio.read_cna("formats/amplicon.cns")
rows = commands.do_breaks(probes, segs, 4)
self.assertGreater(len(rows), 0)
def setUp(self):
self.ex_cnr = tabio.read_cna('formats/reference-tr.cnn')
def test_import_theta(self):
"""The 'import-theta' command."""
cns = tabio.read_cna("formats/nv3.cns")
theta_fname = "formats/nv3.n3.results"
for new_cns in commands.do_import_theta(cns, theta_fname):
self.assertTrue(0 < len(new_cns) <= len(cns))
def test_empty(self):
"""Instantiate from an empty file."""
cnarr = tabio.read_cna("formats/empty")
self.assertEqual(len(cnarr), 0)