def test_split_zmws_targetsize(self):
N_RECORDS = 117
N_ZMWS = 48
test_file = upstreamdata.getUnalignedBam()
ds1 = openDataFile(test_file)
assert len([r for r in ds1]) == N_RECORDS
assert len(ds1) == N_RECORDS
assert len(set(ds1.index.holeNumber)) == N_ZMWS
# with no split
dss = list(ds1.split(targetSize=1000, zmws=True))
assert len(dss) == 1
assert sum([len([r for r in ds_]) for ds_ in dss]) == N_RECORDS
assert sum([len(ds_) for ds_ in dss]) == N_RECORDS
exp = [48]
obs = sorted([len(set(ds.index.holeNumber)) for ds in dss])
assert exp == obs
# with a split
dss = list(ds1.split(targetSize=25, zmws=True))
assert len(dss) == 2
assert sum([len([r for r in ds_]) for ds_ in dss]) == N_RECORDS
assert sum([len(ds_) for ds_ in dss]) == N_RECORDS
exp = [24, 24]
obs = sorted([len(set(ds.index.holeNumber)) for ds in dss])
assert exp == obs
# with a split
dss = list(ds1.split(targetSize=5, zmws=True))
assert len(dss) == 10
assert sum([len([r for r in ds_]) for ds_ in dss]) == N_RECORDS
assert sum([len(ds_) for ds_ in dss]) == N_RECORDS
exp = [4, 4, 5, 5, 5, 5, 5, 5, 5, 5]
obs = sorted([len(set(ds.index.holeNumber)) for ds in dss])
assert exp == obs
def test_subreadset_from_bam(self):
# DONE control experiment for bug 28698
bam = upstreamData.getUnalignedBam()
ds1 = SubreadSet(bam, strict=False)
fn = tempfile.NamedTemporaryFile(suffix=".subreadset.xml").name
log.debug(fn)
ds1.write(fn)
def test_subreadset_from_bam(self):
# DONE control experiment for bug 28698
bam = upstreamData.getUnalignedBam()
ds1 = SubreadSet(bam, strict=False)
fn = tempfile.NamedTemporaryFile(suffix=".subreadset.xml").name
log.debug(fn)
ds1.write(fn)
def test_get_dataset_uuid(self):
ds = SubreadSet(upstreamdata.getUnalignedBam(), strict=True)
ds_file = tempfile.NamedTemporaryFile(suffix=".subreadset.xml").name
ds.write(ds_file)
uuid = getDataSetUuid(ds_file)
self.assertEqual(uuid, ds.uuid)
with open(ds_file, "w") as out:
out.write("hello world!")
uuid = getDataSetUuid(ds_file)
self.assertEqual(uuid, None)
def test_get_dataset_uuid(self):
ds = SubreadSet(upstreamdata.getUnalignedBam(), strict=True)
ds_file = tempfile.NamedTemporaryFile(suffix=".subreadset.xml").name
ds.write(ds_file)
uuid = getDataSetUuid(ds_file)
assert uuid == ds.uuid
with open(ds_file, "w") as out:
out.write("hello world!")
uuid = getDataSetUuid(ds_file)
assert uuid is None
def test_split_zmws_targetsize(self):
N_RECORDS = 117
N_ZMWS = 48
test_file = upstreamdata.getUnalignedBam()
ds1 = openDataFile(test_file)
self.assertEqual(len([r for r in ds1]), N_RECORDS)
self.assertEqual(len(ds1), N_RECORDS)
self.assertEqual(len(set(ds1.index.holeNumber)), N_ZMWS)
# with no split
dss = ds1.split(targetSize=1000, zmws=True)
self.assertEqual(len(dss), 1)
self.assertEqual(sum([len([r for r in ds_]) for ds_ in dss]),
N_RECORDS)
self.assertEqual(sum([len(ds_) for ds_ in dss]),
N_RECORDS)
exp = [48]
obs = sorted([len(set(ds.index.holeNumber)) for ds in dss])
self.assertListEqual(exp, obs)
# with a split
dss = ds1.split(targetSize=25, zmws=True)
self.assertEqual(len(dss), 2)
self.assertEqual(sum([len([r for r in ds_]) for ds_ in dss]),
N_RECORDS)
self.assertEqual(sum([len(ds_) for ds_ in dss]),
N_RECORDS)
exp = [24, 24]
obs = sorted([len(set(ds.index.holeNumber)) for ds in dss])
self.assertListEqual(exp, obs)
# with a split
dss = ds1.split(targetSize=5, zmws=True)
self.assertEqual(len(dss), 10)
self.assertEqual(sum([len([r for r in ds_]) for ds_ in dss]),
N_RECORDS)
self.assertEqual(sum([len(ds_) for ds_ in dss]),
N_RECORDS)
exp = [4, 4, 5, 5, 5, 5, 5, 5, 5, 5]
obs = sorted([len(set(ds.index.holeNumber)) for ds in dss])
self.assertListEqual(exp, obs)
def test_split_zmws(self):
N_RECORDS = 117
test_file = upstreamdata.getUnalignedBam()
ds1 = openDataFile(test_file)
self.assertEqual(len([r for r in ds1]), N_RECORDS)
self.assertEqual(len(ds1), N_RECORDS)
dss = ds1.split(chunks=1, zmws=True)
self.assertEqual(len(dss), 1)
self.assertEqual(sum([len([r for r in ds_]) for ds_ in dss]),
N_RECORDS)
self.assertEqual(sum([len(ds_) for ds_ in dss]), N_RECORDS)
# We have a lower limit on the number of zmws, now
dss = ds1.split(chunks=12, zmws=True)
self.assertEqual(len(dss), 2)
self.assertEqual(sum([len([r for r in ds_]) for ds_ in dss]),
N_RECORDS)
self.assertEqual(sum([len(ds_) for ds_ in dss]), N_RECORDS)
self.assertEqual(
dss[0].zmwRanges,
[('m140905_042212_sidney_c100564852550000001823085912221377_s1_X0',
1650, 32328)])
self.assertEqual(
dss[-1].zmwRanges,
[('m140905_042212_sidney_c100564852550000001823085912221377_s1_X0',
32560, 54396)])
ranges = sorted([c.zmwRanges[0][1:] for c in dss])
interspans = []
last = None
for rg in ranges:
if not last is None:
interspans.append((last, rg[0]))
self.assertFalse(last == rg[0])
last = rg[1]
for rg in interspans:
self.assertEqual(
len(
np.nonzero(
np.logical_and(ds1.index.holeNumber < rg[1],
ds1.index.holeNumber > rg[0]))[0]), 0)
def test_split_zmws(self):
N_RECORDS = 117
test_file = upstreamdata.getUnalignedBam()
ds1 = openDataFile(test_file)
self.assertEqual(len([r for r in ds1]), N_RECORDS)
self.assertEqual(len(ds1), N_RECORDS)
dss = ds1.split(chunks=1, zmws=True)
self.assertEqual(len(dss), 1)
self.assertEqual(sum([len([r for r in ds_]) for ds_ in dss]),
N_RECORDS)
self.assertEqual(sum([len(ds_) for ds_ in dss]),
N_RECORDS)
# We have a lower limit on the number of zmws, now
dss = ds1.split(chunks=12, zmws=True)
self.assertEqual(len(dss), 2)
self.assertEqual(sum([len([r for r in ds_]) for ds_ in dss]),
N_RECORDS)
self.assertEqual(sum([len(ds_) for ds_ in dss]),
N_RECORDS)
self.assertEqual(
dss[0].zmwRanges,
[('m140905_042212_sidney_c100564852550000001823085912221377_s1_X0',
1650, 32328)])
self.assertEqual(
dss[-1].zmwRanges,
[('m140905_042212_sidney_c100564852550000001823085912221377_s1_X0',
32560, 54396)])
ranges = sorted([c.zmwRanges[0][1:] for c in dss])
interspans = []
last = None
for rg in ranges:
if not last is None:
interspans.append((last, rg[0]))
self.assertFalse(last == rg[0])
last = rg[1]
for rg in interspans:
self.assertEqual(len(np.nonzero(np.logical_and(
ds1.index.holeNumber < rg[1],
ds1.index.holeNumber > rg[0]))[0]), 0)
def test_split_zmws_targetsize(self):
N_RECORDS = 117
N_ZMWS = 48
test_file = upstreamdata.getUnalignedBam()
ds1 = openDataFile(test_file)
self.assertEqual(len([r for r in ds1]), N_RECORDS)
self.assertEqual(len(ds1), N_RECORDS)
self.assertEqual(len(set(ds1.index.holeNumber)), N_ZMWS)
# with no split
dss = ds1.split(targetSize=1000, zmws=True)
self.assertEqual(len(dss), 1)
self.assertEqual(sum([len([r for r in ds_]) for ds_ in dss]),
N_RECORDS)
self.assertEqual(sum([len(ds_) for ds_ in dss]), N_RECORDS)
exp = [48]
obs = sorted([len(set(ds.index.holeNumber)) for ds in dss])
self.assertListEqual(exp, obs)
# with a split
dss = ds1.split(targetSize=25, zmws=True)
self.assertEqual(len(dss), 2)
self.assertEqual(sum([len([r for r in ds_]) for ds_ in dss]),
N_RECORDS)
self.assertEqual(sum([len(ds_) for ds_ in dss]), N_RECORDS)
exp = [24, 24]
obs = sorted([len(set(ds.index.holeNumber)) for ds in dss])
self.assertListEqual(exp, obs)
# with a split
dss = ds1.split(targetSize=5, zmws=True)
self.assertEqual(len(dss), 10)
self.assertEqual(sum([len([r for r in ds_]) for ds_ in dss]),
N_RECORDS)
self.assertEqual(sum([len(ds_) for ds_ in dss]), N_RECORDS)
exp = [4, 4, 5, 5, 5, 5, 5, 5, 5, 5]
obs = sorted([len(set(ds.index.holeNumber)) for ds in dss])
self.assertListEqual(exp, obs)
def __init__(self):
self.bam = BamReader(data.getUnalignedBam())
self.bax = BaxH5Reader(data.getBaxForBam())
self.baxRead0 = next(self.bax.subreads())
self.bamRead0 = next(iter(self.bam))
def test_get_dataset_metatype(self):
ds = SubreadSet(upstreamdata.getUnalignedBam(), strict=True)
ds_file = tempfile.NamedTemporaryFile(suffix=".subreadset.xml").name
ds.write(ds_file)
meta_type = getDataSetMetaType(ds_file)
assert meta_type == "PacBio.DataSet.SubreadSet"
def test_context_filters(self):
ss = SubreadSet(upstreamdata.getUnalignedBam())
self.assertEqual(set(ss.index.contextFlag), {0, 1, 2, 3})
self.assertEqual([
len(np.flatnonzero(ss.index.contextFlag == cx))
for cx in sorted(set(ss.index.contextFlag))
], [15, 33, 32, 37])
self.assertEqual(len(ss.index), 117)
# no adapters/barcodes
ss.filters.addRequirement(cx=[('=', 0)])
self.assertEqual(len(ss.index), 15)
ss.filters.removeRequirement('cx')
self.assertEqual(len(ss.index), 117)
# no adapters/barcodes
ss.filters.addRequirement(cx=[('=', 'NO_LOCAL_CONTEXT')])
self.assertEqual(len(ss.index), 15)
ss.filters.removeRequirement('cx')
self.assertEqual(len(ss.index), 117)
# some adapters/barcodes
ss.filters.addRequirement(cx=[('!=', 0)])
self.assertEqual(len(ss.index), 102)
ss.filters.removeRequirement('cx')
self.assertEqual(len(ss.index), 117)
# adapter before
ss.filters.addRequirement(cx=[('&', 1)])
self.assertEqual(len(ss.index), 70)
ss.filters.removeRequirement('cx')
self.assertEqual(len(ss.index), 117)
# adapter before
ss.filters.addRequirement(cx=[('&', 'ADAPTER_BEFORE')])
self.assertEqual(len(ss.index), 70)
ss.filters.removeRequirement('cx')
self.assertEqual(len(ss.index), 117)
# adapter after
ss.filters.addRequirement(cx=[('&', 2)])
self.assertEqual(len(ss.index), 69)
ss.filters.removeRequirement('cx')
self.assertEqual(len(ss.index), 117)
# adapter before or after
ss.filters.addRequirement(cx=[('&', 3)])
self.assertEqual(len(ss.index), 102)
ss.filters.removeRequirement('cx')
self.assertEqual(len(ss.index), 117)
# adapter before or after
ss.filters.addRequirement(cx=[('&', 'ADAPTER_BEFORE | ADAPTER_AFTER')])
self.assertEqual(len(ss.index), 102)
ss.filters.removeRequirement('cx')
self.assertEqual(len(ss.index), 117)
# adapter before or after but not both
ss.filters.addRequirement(cx=[('!=', 0)])
ss.filters.addRequirement(cx=[('~', 1), ('~', 2)])
self.assertEqual(len(ss.index), 65)
ss.filters.removeRequirement('cx')
self.assertEqual(len(ss.index), 117)
# adapter before or after
ss.filters.addRequirement(cx=[('&', 1), ('&', 2)])
self.assertEqual(len(ss.index), 102)
ss.filters.removeRequirement('cx')
self.assertEqual(len(ss.index), 117)
# adapter before and after
ss.filters.addRequirement(cx=[('&', 1)])
ss.filters.addRequirement(cx=[('&', 2)])
self.assertEqual(len(ss.index), 37)
ss.filters.removeRequirement('cx')
self.assertEqual(len(ss.index), 117)
# adapter before but not after
ss.filters.addRequirement(cx=[('&', 1)])
ss.filters.addRequirement(cx=[('~', 2)])
self.assertEqual(len(ss.index), 33)
ss.filters.removeRequirement('cx')
self.assertEqual(len(ss.index), 117)
# no adapter before
ss.filters.addRequirement(cx=[('~', 1)])
self.assertEqual(len(ss.index), 47)
ss.filters.removeRequirement('cx')
self.assertEqual(len(ss.index), 117)
# no adapter before or after
ss.filters.addRequirement(cx=[('~', 1)])
ss.filters.addRequirement(cx=[('~', 2)])
self.assertEqual(len(ss.index), 15)
ss.filters.removeRequirement('cx')
self.assertEqual(len(ss.index), 117)
# no adapter before or after
ss.filters.addRequirement(cx=[('~', 3)])
self.assertEqual(len(ss.index), 15)
ss.filters.removeRequirement('cx')
self.assertEqual(len(ss.index), 117)
def test_context_filters(self):
ss = SubreadSet(upstreamdata.getUnalignedBam())
assert set(ss.index.contextFlag) == {0, 1, 2, 3}
assert [
len(np.flatnonzero(ss.index.contextFlag == cx))
for cx in sorted(set(ss.index.contextFlag))
] == [15, 33, 32, 37]
assert len(ss.index) == 117
# no adapters/barcodes
ss.filters.addRequirement(cx=[('=', 0)])
assert len(ss.index) == 15
ss.filters.removeRequirement('cx')
assert len(ss.index) == 117
# no adapters/barcodes
ss.filters.addRequirement(cx=[('=', 'NO_LOCAL_CONTEXT')])
assert len(ss.index) == 15
ss.filters.removeRequirement('cx')
assert len(ss.index) == 117
# some adapters/barcodes
ss.filters.addRequirement(cx=[('!=', 0)])
assert len(ss.index) == 102
ss.filters.removeRequirement('cx')
assert len(ss.index) == 117
# adapter before
ss.filters.addRequirement(cx=[('&', 1)])
assert len(ss.index) == 70
ss.filters.removeRequirement('cx')
assert len(ss.index) == 117
# adapter before
ss.filters.addRequirement(cx=[('&', 'ADAPTER_BEFORE')])
assert len(ss.index) == 70
ss.filters.removeRequirement('cx')
assert len(ss.index) == 117
# adapter after
ss.filters.addRequirement(cx=[('&', 2)])
assert len(ss.index) == 69
ss.filters.removeRequirement('cx')
assert len(ss.index) == 117
# adapter before or after
ss.filters.addRequirement(cx=[('&', 3)])
assert len(ss.index) == 102
ss.filters.removeRequirement('cx')
assert len(ss.index) == 117
# adapter before or after
ss.filters.addRequirement(cx=[('&', 'ADAPTER_BEFORE | ADAPTER_AFTER')])
assert len(ss.index) == 102
ss.filters.removeRequirement('cx')
assert len(ss.index) == 117
# adapter before or after but not both
ss.filters.addRequirement(cx=[('!=', 0)])
ss.filters.addRequirement(cx=[('~', 1), ('~', 2)])
assert len(ss.index) == 65
ss.filters.removeRequirement('cx')
assert len(ss.index) == 117
# adapter before or after
ss.filters.addRequirement(cx=[('&', 1), ('&', 2)])
assert len(ss.index) == 102
ss.filters.removeRequirement('cx')
assert len(ss.index) == 117
# adapter before and after
ss.filters.addRequirement(cx=[('&', 1)])
ss.filters.addRequirement(cx=[('&', 2)])
assert len(ss.index) == 37
ss.filters.removeRequirement('cx')
assert len(ss.index) == 117
# adapter before but not after
ss.filters.addRequirement(cx=[('&', 1)])
ss.filters.addRequirement(cx=[('~', 2)])
assert len(ss.index) == 33
ss.filters.removeRequirement('cx')
assert len(ss.index) == 117
# no adapter before
ss.filters.addRequirement(cx=[('~', 1)])
assert len(ss.index) == 47
ss.filters.removeRequirement('cx')
assert len(ss.index) == 117
# no adapter before or after
ss.filters.addRequirement(cx=[('~', 1)])
ss.filters.addRequirement(cx=[('~', 2)])
assert len(ss.index) == 15
ss.filters.removeRequirement('cx')
assert len(ss.index) == 117
# no adapter before or after
ss.filters.addRequirement(cx=[('~', 3)])
assert len(ss.index) == 15
ss.filters.removeRequirement('cx')
assert len(ss.index) == 117
def setup_class(cls):
cls.bam = BamReader(data.getUnalignedBam())
cls.bamRead0 = next(iter(cls.bam))
def test_get_dataset_metatype(self):
ds = SubreadSet(upstreamdata.getUnalignedBam(), strict=True)
ds_file = tempfile.NamedTemporaryFile(suffix=".subreadset.xml").name
ds.write(ds_file)
meta_type = getDataSetMetaType(ds_file)
self.assertEqual(meta_type, "PacBio.DataSet.SubreadSet")
def __init__(self):
self.V = ZmwReadStitcher(getUnalignedBam())
self.B = BasH5Reader(getBaxForBam())
self.VZ = self.V[1650]
self.BZ = self.B[1650]
def test_context_filters(self):
ss = SubreadSet(upstreamdata.getUnalignedBam())
self.assertEqual(set(ss.index.contextFlag), {0, 1, 2, 3})
self.assertEqual(
[len(np.flatnonzero(ss.index.contextFlag == cx))
for cx in sorted(set(ss.index.contextFlag))],
[15, 33, 32, 37])
self.assertEqual(len(ss.index), 117)
# no adapters/barcodes
ss.filters.addRequirement(cx=[('=', 0)])
self.assertEqual(len(ss.index), 15)
ss.filters.removeRequirement('cx')
self.assertEqual(len(ss.index), 117)
# no adapters/barcodes
ss.filters.addRequirement(cx=[('=', 'NO_LOCAL_CONTEXT')])
self.assertEqual(len(ss.index), 15)
ss.filters.removeRequirement('cx')
self.assertEqual(len(ss.index), 117)
# some adapters/barcodes
ss.filters.addRequirement(cx=[('!=', 0)])
self.assertEqual(len(ss.index), 102)
ss.filters.removeRequirement('cx')
self.assertEqual(len(ss.index), 117)
# adapter before
ss.filters.addRequirement(cx=[('&', 1)])
self.assertEqual(len(ss.index), 70)
ss.filters.removeRequirement('cx')
self.assertEqual(len(ss.index), 117)
# adapter before
ss.filters.addRequirement(cx=[('&', 'ADAPTER_BEFORE')])
self.assertEqual(len(ss.index), 70)
ss.filters.removeRequirement('cx')
self.assertEqual(len(ss.index), 117)
# adapter after
ss.filters.addRequirement(cx=[('&', 2)])
self.assertEqual(len(ss.index), 69)
ss.filters.removeRequirement('cx')
self.assertEqual(len(ss.index), 117)
# adapter before or after
ss.filters.addRequirement(cx=[('&', 3)])
self.assertEqual(len(ss.index), 102)
ss.filters.removeRequirement('cx')
self.assertEqual(len(ss.index), 117)
# adapter before or after
ss.filters.addRequirement(cx=[('&', 'ADAPTER_BEFORE | ADAPTER_AFTER')])
self.assertEqual(len(ss.index), 102)
ss.filters.removeRequirement('cx')
self.assertEqual(len(ss.index), 117)
# adapter before or after but not both
ss.filters.addRequirement(cx=[('!=', 0)])
ss.filters.addRequirement(cx=[('~', 1),
('~', 2)])
self.assertEqual(len(ss.index), 65)
ss.filters.removeRequirement('cx')
self.assertEqual(len(ss.index), 117)
# adapter before or after
ss.filters.addRequirement(cx=[('&', 1),
('&', 2)])
self.assertEqual(len(ss.index), 102)
ss.filters.removeRequirement('cx')
self.assertEqual(len(ss.index), 117)
# adapter before and after
ss.filters.addRequirement(cx=[('&', 1)])
ss.filters.addRequirement(cx=[('&', 2)])
self.assertEqual(len(ss.index), 37)
ss.filters.removeRequirement('cx')
self.assertEqual(len(ss.index), 117)
# adapter before but not after
ss.filters.addRequirement(cx=[('&', 1)])
ss.filters.addRequirement(cx=[('~', 2)])
self.assertEqual(len(ss.index), 33)
ss.filters.removeRequirement('cx')
self.assertEqual(len(ss.index), 117)
# no adapter before
ss.filters.addRequirement(cx=[('~', 1)])
self.assertEqual(len(ss.index), 47)
ss.filters.removeRequirement('cx')
self.assertEqual(len(ss.index), 117)
# no adapter before or after
ss.filters.addRequirement(cx=[('~', 1)])
ss.filters.addRequirement(cx=[('~', 2)])
self.assertEqual(len(ss.index), 15)
ss.filters.removeRequirement('cx')
self.assertEqual(len(ss.index), 117)
# no adapter before or after
ss.filters.addRequirement(cx=[('~', 3)])
self.assertEqual(len(ss.index), 15)
ss.filters.removeRequirement('cx')
self.assertEqual(len(ss.index), 117)
def __init__(self):
self.V = ZmwReadStitcher(getUnalignedBam())
self.B = BasH5Reader(getBaxForBam())
self.VZ = self.V[1650]
self.BZ = self.B[1650]
def __init__(self):
self.bam = BamReader (data.getUnalignedBam())
self.bax = BaxH5Reader(data.getBaxForBam())
self.baxRead0 = next(self.bax.subreads())
self.bamRead0 = next(iter(self.bam))
def setup_class(self):
self.bam = BamReader (data.getUnalignedBam())
self.bax = BaxH5Reader(data.getBaxForBam())
self.baxRead0 = next(self.bax.subreads())
self.bamRead0 = next(iter(self.bam))
