def test_invalid_access():
ga = create_genomic_array(GenomicIndexer.create_from_genomesize(
{'chr10': 300}),
stranded=False,
typecode='int8',
storage='ndarray')
with pytest.raises(Exception):
# access only via genomic interval
ga[1]
with pytest.raises(Exception):
# access only via genomic interval and condition
ga[1] = 1
ga = create_genomic_array(GenomicIndexer.create_from_genomesize(
{'chr10': 300}),
stranded=False,
typecode='int8',
storage='sparse')
with pytest.raises(Exception):
# access only via genomic interval
ga[1]
with pytest.raises(Exception):
# access only via genomic interval and condition
ga[1] = 1
def test_gindexer_short_interval():
data_path = pkg_resources.resource_filename('janggu', 'resources/')
gi = GenomicIndexer.create_from_file(os.path.join(data_path,
'sample_equalsize.bed'),
binsize=200,
stepsize=200)
assert len(gi) == 4
gi = GenomicIndexer.create_from_file(os.path.join(data_path,
'sample_equalsize.bed'),
binsize=180,
stepsize=20)
assert len(gi) == 8
gi = GenomicIndexer.create_from_file(os.path.join(data_path,
'sample_equalsize.bed'),
binsize=210,
stepsize=20,
zero_padding=False)
assert len(gi) == 0
gi = GenomicIndexer.create_from_file(os.path.join(data_path,
'sample_equalsize.bed'),
binsize=210,
stepsize=20,
zero_padding=True)
assert len(gi) == 4
def test_gindexer_merged_variable_length_ranges():
data_path = pkg_resources.resource_filename('janggu', 'resources/')
# with fixed size
gi = GenomicIndexer.create_from_file(os.path.join(data_path, 'sample.bed'),
binsize=3000,
stepsize=3000,
zero_padding=False)
np.testing.assert_equal(len(gi), 6)
iv = gi[0]
np.testing.assert_equal((iv.chrom, iv.start, iv.end, iv.strand),
('chr1', 15000, 18000, '+'))
iv = gi[-1]
np.testing.assert_equal((iv.chrom, iv.start, iv.end, iv.strand),
('chr2', 21000, 24000, '-'))
# with variable size regions
gi = GenomicIndexer.create_from_file(os.path.join(data_path, 'sample.bed'),
binsize=3000,
stepsize=3000,
zero_padding=True)
np.testing.assert_equal(len(gi), 8)
iv = gi[0]
np.testing.assert_equal((iv.chrom, iv.start, iv.end, iv.strand),
('chr1', 15000, 18000, '+'))
iv = gi[-1]
np.testing.assert_equal((iv.chrom, iv.start, iv.end, iv.strand),
('chr2', 24000, 25000, '-'))
def test_gindexer_errors():
data_path = pkg_resources.resource_filename('janggu', 'resources/')
with pytest.raises(ValueError):
GenomicIndexer.create_from_file(os.path.join(data_path, 'sample.bed'),
binsize=0,
stepsize=50)
with pytest.raises(ValueError):
GenomicIndexer.create_from_file(os.path.join(data_path, 'sample.bed'),
binsize=10,
stepsize=0)
with pytest.raises(ValueError):
# due to flank < 0
GenomicIndexer.create_from_file(os.path.join(data_path, 'sample.bed'),
binsize=200,
stepsize=50,
flank=-1)
# due to unequal intervals
gi = GenomicIndexer.create_from_file(os.path.join(data_path, 'scores.bed'),
binsize=None,
stepsize=None,
flank=0)
#print(len(gi))
#for reg in gi:
# print(reg)
GenomicIndexer.create_from_file(os.path.join(data_path, 'scores.bed'),
binsize=200,
stepsize=200,
flank=0)
def test_tmp_normalization(tmpdir):
os.environ['JANGGU_OUTPUT'] = tmpdir.strpath
def loading(garray):
garray[Interval('chr1', 0, 150), 0] = np.repeat(10, 150).reshape(-1, 1)
garray[Interval('chr2', 0, 300), 0] = np.repeat(1, 300).reshape(-1, 1)
return garray
for store in ['ndarray', 'hdf5']:
ga = create_genomic_array(GenomicIndexer.create_from_genomesize({
'chr1':
150,
'chr2':
300
}),
stranded=False,
typecode='float32',
storage=store,
cache="cache_file",
resolution=50,
loader=loading,
collapser='sum',
normalizer=['tpm'])
np.testing.assert_allclose(
ga[Interval('chr1', 100, 101)],
np.asarray([[[10 * 1000 / 50 * 1e6 / (720.)]]]))
np.testing.assert_allclose(
ga[Interval('chr2', 100, 101)],
np.asarray([[[1 * 1000 / 50 * 1e6 / (720.)]]]))
def test_bwga_instance_unstranded_taged(tmpdir):
os.environ['JANGGU_OUTPUT'] = tmpdir.strpath
iv = Interval('chr10', 100, 120, strand='.')
ga = create_genomic_array(GenomicIndexer.create_from_genomesize(
{'chr10': 300}),
stranded=False,
typecode='int8',
storage='ndarray',
datatags='test_bwga_instance_unstranded')
with pytest.raises(Exception):
# access only via genomic interval
ga[1]
with pytest.raises(Exception):
# access only via genomic interval and condition
ga[1] = 1
np.testing.assert_equal(ga[iv].shape, (20, 1, 1))
np.testing.assert_equal(ga[iv], np.zeros((20, 1, 1)))
ga[iv, 0] = np.ones((20, 1))
np.testing.assert_equal(ga[iv], np.ones((20, 1, 1)))
np.testing.assert_equal(ga[iv].sum(), 20)
iv = Interval('chr10', 0, 300, strand='.')
np.testing.assert_equal(ga[iv].sum(), 20)
def test_output_bigwig_loss_resolution_unequal_stepsize(tmpdir):
os.environ['JANGGU_OUTPUT'] = tmpdir.strpath
# generate loss
#
# resolution < stepsize
inputs = Array("x", numpy.random.random((7, 4, 1, 10)))
outputs = Array('y', numpy.random.random((7, 4, 1, 4)),
conditions=['c1', 'c2', 'c3', 'c4'])
bwm = get_janggu(inputs, outputs)
data_path = pkg_resources.resource_filename('janggu',
'resources/10regions.bed')
gi = GenomicIndexer.create_from_file(data_path,
binsize=200,
stepsize=50)
dummy_eval = Scorer('loss', lambda t, p: [0.2] * len(t),
exporter=ExportBigwig(gindexer=gi))
bwm.evaluate(inputs, outputs, callbacks=[dummy_eval])
file_ = os.path.join(tmpdir.strpath, 'evaluation', bwm.name,
'loss.{}.bigwig')
for cond in ['c1', 'c2', 'c3', 'c4']:
assert os.path.exists(file_.format(cond))
bw = pyBigWig.open(file_.format('c1'))
co = bw.values('chr1', 600, 2000-150)
numpy.testing.assert_allclose(numpy.mean(co), 0.2, rtol=1e-5)
def test_janggu_variant_prediction(tmpdir):
os.environ['JANGGU_OUTPUT'] = tmpdir.strpath
"""Test Janggu creation by shape and name. """
data_path = pkg_resources.resource_filename('janggu', 'resources/')
for order in [1, 2, 3]:
refgenome = os.path.join(data_path, 'sample_genome.fa')
vcffile = os.path.join(data_path, 'sample.vcf')
dna = Bioseq.create_from_refgenome('dna',
refgenome=refgenome,
storage='ndarray',
binsize=50,
store_whole_genome=True,
order=order)
def _cnn_model(inputs, inp, oup, params):
inputs = Input(
(50 - params['order'] + 1, 1, pow(4, params['order'])))
layer = Flatten()(inputs)
layer = Dense(params['hiddenunits'])(layer)
output = Dense(4, activation='sigmoid')(layer)
return inputs, output
model = Janggu.create(_cnn_model,
modelparams={
'hiddenunits': 2,
'order': order
},
name='dna_ctcf_HepG2-cnn')
model.predict_variant_effect(
dna,
vcffile,
conditions=['m' + str(i) for i in range(4)],
output_folder=os.path.join(os.environ['JANGGU_OUTPUT']))
assert os.path.exists(
os.path.join(os.environ['JANGGU_OUTPUT'], 'scores.hdf5'))
assert os.path.exists(
os.path.join(os.environ['JANGGU_OUTPUT'], 'snps.bed.gz'))
f = h5py.File(os.path.join(os.environ['JANGGU_OUTPUT'], 'scores.hdf5'),
'r')
gindexer = GenomicIndexer.create_from_file(
os.path.join(os.environ['JANGGU_OUTPUT'], 'snps.bed.gz'), None,
None)
cov = Cover.create_from_array('snps',
f['diffscore'],
gindexer,
store_whole_genome=True)
print(cov['chr2', 55, 65].shape)
print(cov['chr2', 55, 65])
assert np.abs(cov['chr2', 59, 60]).sum() > 0.0
assert np.abs(cov['chr2', 54, 55]).sum() == 0.0
f.close()
def test_resolution_negative():
with pytest.raises(Exception):
ga = create_genomic_array(GenomicIndexer.create_from_genomesize(
{'chr10': 300}),
stranded=True,
typecode='int8',
storage='ndarray',
cache=False,
resolution=-1)
def test_invalid_storage():
with pytest.raises(Exception):
ga = create_genomic_array(GenomicIndexer.create_from_genomesize(
{'chr10': 300}),
stranded=True,
typecode='int8',
storage='storgae',
resolution=1,
cache=False)
def test_create_from_array(tmpdir):
inbed = resource_filename('janggu', 'resources/bed_test.bed')
outbed = os.path.join(tmpdir.strpath, 'out.bed')
trim_bed(inbed, outbed, 5)
# original file
gindexer = GenomicIndexer.create_from_file(inbed, None, None)
reg = gindexer[0]
assert (reg.start % 5) == 0
assert (reg.end % 5) > 0
# trimmed file
gindexer = GenomicIndexer.create_from_file(outbed, None, None)
gindexer = GenomicIndexer.create_from_file(outbed, None, None)
reg = gindexer[0]
assert (reg.start % 5) == 0
assert (reg.end % 5) == 0
def test_dna_dims_order_1_from_reference(tmpdir):
os.environ['JANGGU_OUTPUT'] = tmpdir.strpath
order = 1
data_path = pkg_resources.resource_filename('janggu', 'resources/')
bed_merged = os.path.join(data_path, 'sample.gtf')
refgenome = os.path.join(data_path, 'sample_genome.fa')
gindexer = GenomicIndexer.create_from_file(bed_merged, 200, 200)
data = Bioseq.create_from_refgenome('train', refgenome=refgenome,
storage='ndarray',
order=order,
store_whole_genome=True)
data.gindexer = gindexer
assert len(data.garray.handle) == 2
assert 'chr1' in data.garray.handle
assert 'chr2' in data.garray.handle
# for order 1
assert len(data) == 100
assert data.shape == (100, 200, 1, 4)
# the correctness of the sequence extraction was also
# validated using:
# bedtools getfasta -fi sample_genome.fa -bed sample.bed
# >chr1:15000-25000
# ATTGTGGTGA...
# this sequence is read from the forward strand
np.testing.assert_equal(data[0][0, :10, 0, :],
np.asarray([[1, 0, 0, 0], # A
[0, 0, 0, 1], # T
[0, 0, 0, 1], # T
[0, 0, 1, 0], # C
[0, 0, 0, 1], # T
[0, 0, 1, 0], # G
[0, 0, 1, 0], # G
[0, 0, 0, 1], # T
[0, 0, 1, 0], # G
[1, 0, 0, 0]], # A
dtype='int8'))
# bedtools getfasta -fi sample_genome.fa -bed sample.bed
# >chr2:15000-25000
# ggggaagcaa...
# this sequence is read from the reverse strand
# so we have ...ttgcttcccc
np.testing.assert_equal(data[50][0, -10:, 0, :],
np.asarray([[0, 0, 0, 1], # T
[0, 0, 0, 1], # T
[0, 0, 1, 0], # G
[0, 1, 0, 0], # C
[0, 0, 0, 1], # T
[0, 0, 0, 1], # T
[0, 1, 0, 0], # C
[0, 1, 0, 0], # C
[0, 1, 0, 0], # C
[0, 1, 0, 0]], # C
dtype='int8'))
def test_hdf5_no_cache():
with pytest.raises(Exception):
# cache must be True
ga = create_genomic_array(GenomicIndexer.create_from_genomesize(
{'chr10': 300}),
stranded=True,
typecode='int8',
storage='hdf5',
cache=None)
def test_gindexer_short_interval_with_dataframe():
data_path = pkg_resources.resource_filename('janggu', 'resources/')
df = pd.read_csv(os.path.join(data_path, 'sample_equalsize.bed'),
sep='\t',
header=None,
names=['chrom', 'start', 'end'])
gi = GenomicIndexer.create_from_file(df, binsize=200, stepsize=200)
assert len(gi) == 4
gi = GenomicIndexer.create_from_file(df, binsize=180, stepsize=20)
assert len(gi) == 8
gi = GenomicIndexer.create_from_file(df,
binsize=210,
stepsize=20,
zero_padding=False)
assert len(gi) == 0
gi = GenomicIndexer.create_from_file(df,
binsize=210,
stepsize=20,
zero_padding=True)
assert len(gi) == 4
def test_bwga_instance_unstranded(tmpdir):
iv = Interval('chr10', 100, 120, strand='.')
ga = create_genomic_array(GenomicIndexer.create_from_genomesize(
{'chr10': 300}),
stranded=False,
typecode='int8',
storage='ndarray',
cache=False)
np.testing.assert_equal(ga[iv].shape, (20, 1, 1))
np.testing.assert_equal(ga[iv], np.zeros((20, 1, 1)))
ga[iv, 0] = np.ones((20, 1))
np.testing.assert_equal(ga[iv], np.ones((20, 1, 1)))
np.testing.assert_equal(ga[iv].sum(), 20)
iv = Interval('chr10', 0, 300, strand='.')
np.testing.assert_equal(ga[iv].sum(), 20)
def test_gindexer_merged():
data_path = pkg_resources.resource_filename('janggu', 'resources/')
gi = GenomicIndexer.create_from_file(os.path.join(data_path, 'sample.bed'),
binsize=200,
stepsize=200)
np.testing.assert_equal(len(gi), 100)
gi2 = gi.filter_by_region(include='chr1')
gi3 = gi.filter_by_region(include='chr10')
gi4 = gi.filter_by_region(exclude='chr2')
gi5 = gi.filter_by_region(exclude='chr10')
np.testing.assert_equal(len(gi2), 50)
np.testing.assert_equal(len(gi3), 0)
np.testing.assert_equal(len(gi4), 50)
np.testing.assert_equal(len(gi5), 100)
def test_output_bed_loss_resolution_equal_stepsize(tmpdir):
os.environ['JANGGU_OUTPUT'] = tmpdir.strpath
# generate loss
#
# resolution < stepsize
inputs = Array("x", numpy.random.random((7, 1, 1, 10)))
outputs = Array('y',
numpy.random.random((7, 1, 1, 4)),
conditions=['c1', 'c2', 'c3', 'c4'])
bwm = get_janggu_conv(inputs, outputs)
data_path = pkg_resources.resource_filename('janggu',
'resources/10regions.bed')
gi = GenomicIndexer.create_from_file(data_path, binsize=200, stepsize=200)
dummy_eval = Scorer('loss',
lambda t, p: [0.1] * len(t),
exporter=export_bed)
bwm.evaluate(inputs,
outputs,
callbacks=[dummy_eval],
exporter_kwargs={
'gindexer': gi,
'resolution': 200
})
file_ = os.path.join(tmpdir.strpath, 'evaluation', bwm.name,
'loss.nptest.y.{}.bed')
for cond in ['c1', 'c2', 'c3', 'c4']:
assert os.path.exists(file_.format(cond))
bed = iter(HTSeq.BED_Reader(file_.format('c1')))
nreg = 0
for reg in bed:
numpy.testing.assert_equal(reg.score, 0.1)
nreg += 1
# numpy.testing.assert_equal(breg.score, value)
assert nreg == 7, 'There should be 7 regions in the bed file.'
def test_bwga_instance_stranded(tmpdir):
os.environ['JANGGU_OUTPUT'] = tmpdir.strpath
iv = Interval('chr10', 100, 120, strand='+')
ga = create_genomic_array(GenomicIndexer.create_from_genomesize(
{'chr10': 300}),
stranded=True,
typecode='int8',
storage='ndarray')
np.testing.assert_equal(ga[iv].shape, (20, 2, 1))
np.testing.assert_equal(ga[iv], np.zeros((20, 2, 1)))
x = np.zeros((20, 2, 1))
x[:, :1, :] = 1
ga[iv, 0] = x[:, :, 0]
np.testing.assert_equal(ga[iv], x)
np.testing.assert_equal(ga[iv].sum(), 20)
iv = Interval('chr10', 0, 300)
np.testing.assert_equal(ga[iv].sum(), 20)
def test_output_bed_loss_resolution_unequal_stepsize(tmpdir):
os.environ['JANGGU_OUTPUT'] = tmpdir.strpath
# generate loss
#
# resolution < stepsize
inputs = Array("x", numpy.random.random((7, 4, 1, 10)))
outputs = Array('y', numpy.random.random((7, 4, 1, 4)),
conditions=['c1', 'c2', 'c3', 'c4'])
bwm = get_janggu(inputs, outputs)
data_path = pkg_resources.resource_filename('janggu',
'resources/10regions.bed')
gi = GenomicIndexer.create_from_file(data_path,
binsize=200,
stepsize=200)
# dummy_eval = Scorer('loss', lambda t, p: -t * numpy.log(p),
# exporter=export_bed, export_args={'gindexer': gi})
dummy_eval = Scorer('loss', lambda t, p: [0.1] * len(t),
exporter=ExportBed(gindexer=gi, resolution=50))
bwm.evaluate(inputs, outputs, callbacks=[dummy_eval])
file_ = os.path.join(tmpdir.strpath, 'evaluation', bwm.name,
'loss.{}.bed')
for cond in ['c1', 'c2', 'c3', 'c4']:
assert os.path.exists(file_.format(cond))
bed = BedTool(file_.format('c1'))
nreg = 0
for reg in bed:
numpy.testing.assert_equal(float(reg.score), 0.1)
nreg += 1
assert nreg == 28, 'There should be 28 regions in the bed file.'
def test_perctrim(tmpdir):
os.environ['JANGGU_OUTPUT'] = tmpdir.strpath
def loading(garray):
garray[Interval('chr1', 0, 150),
0] = np.random.normal(loc=10, size=150).reshape(-1, 1)
garray[Interval('chr2', 0, 300),
0] = np.random.normal(loc=100, size=300).reshape(-1, 1)
return garray
for store in ['ndarray', 'hdf5']:
ga = create_genomic_array(GenomicIndexer.create_from_genomesize({
'chr1':
150,
'chr2':
300
}),
stranded=False,
typecode='float32',
storage=store,
cache="cache_file",
loader=loading,
normalizer=['binsizenorm', 'perctrim'])
def test_zscore_normalization(tmpdir):
os.environ['JANGGU_OUTPUT'] = tmpdir.strpath
def loading(garray):
garray[Interval('chr1', 0, 150), 0] = np.repeat(1, 150).reshape(-1, 1)
garray[Interval('chr2', 0, 300), 0] = np.repeat(-1, 300).reshape(-1, 1)
return garray
for store in ['ndarray', 'hdf5']:
ga = create_genomic_array(GenomicIndexer.create_from_genomesize({
'chr1':
150,
'chr2':
300
}),
stranded=False,
typecode='float32',
storage=store,
cache=True,
loader=loading,
normalizer=['zscore'])
np.testing.assert_allclose(ga.weighted_mean(),
np.asarray([0.0]),
rtol=1e-5,
atol=1e-5)
np.testing.assert_allclose(ga.weighted_sd(),
np.asarray([1.]),
rtol=1e-5,
atol=1e-5)
np.testing.assert_allclose(ga[Interval('chr1', 100, 101)],
np.asarray([[[1.412641340027806]]]),
rtol=1e-5,
atol=1e-5)
np.testing.assert_allclose(ga[Interval('chr2', 100, 101)],
np.asarray([[[-0.706320670013903]]]),
rtol=1e-5,
atol=1e-5)
def test_output_bed_predict_denseout(tmpdir):
os.environ['JANGGU_OUTPUT'] = tmpdir.strpath
# generate loss
#
# resolution < stepsize
inputs = Array("x", numpy.random.random((7, 10)))
outputs = Array('y',
numpy.random.random((7, 4)),
conditions=['c1', 'c2', 'c3', 'c4'])
bwm = get_janggu(inputs, outputs)
data_path = pkg_resources.resource_filename('janggu',
'resources/10regions.bed')
gi = GenomicIndexer.create_from_file(data_path, binsize=200, stepsize=200)
dummy_eval = Scorer('pred',
lambda p: [0.1] * len(p),
exporter=ExportBed(gindexer=gi, resolution=200),
conditions=['c1', 'c2', 'c3', 'c4'])
bwm.predict(inputs, callbacks=[dummy_eval])
file_ = os.path.join(tmpdir.strpath, 'evaluation', bwm.name,
'pred.nptest.y.{}.bed')
for cond in ['c1', 'c2', 'c3', 'c4']:
assert os.path.exists(file_.format(cond))
bed = iter(HTSeq.BED_Reader(file_.format('c1')))
nreg = 0
for reg in bed:
numpy.testing.assert_equal(reg.score, 0.1)
nreg += 1
assert nreg == 7, 'There should be 7 regions in the bed file.'
def test_output_bigwig_predict_denseout(tmpdir):
os.environ['JANGGU_OUTPUT'] = tmpdir.strpath
# generate loss
#
# resolution < stepsize
inputs = Array("x", numpy.random.random((7, 10)))
outputs = Array('y',
numpy.random.random((7, 4)),
conditions=['c1', 'c2', 'c3', 'c4'])
bwm = get_janggu(inputs, outputs)
data_path = pkg_resources.resource_filename('janggu',
'resources/10regions.bed')
gi = GenomicIndexer.create_from_file(data_path, binsize=200, stepsize=200)
dummy_eval = Scorer('pred',
lambda p: [0.1] * len(p),
exporter=export_bigwig,
conditions=['c1', 'c2', 'c3', 'c4'])
bwm.predict(inputs,
callbacks=[dummy_eval],
exporter_kwargs={'gindexer': gi})
file_ = os.path.join(tmpdir.strpath, 'evaluation', bwm.name,
'pred.nptest.y.{}.bigwig')
for cond in ['c1', 'c2', 'c3', 'c4']:
assert os.path.exists(file_.format(cond))
bw = pyBigWig.open(file_.format('c1'))
co = bw.values('chr1', 600, 2000)
numpy.testing.assert_allclose(numpy.mean(co), 0.1, rtol=1e-5)
def test_check_resolution_collapse_compatibility(tmpdir):
os.environ['JANGGU_OUTPUT'] = tmpdir.strpath
def loading(garray):
garray[Interval('chr1', 0, 150), 0] = np.repeat(10, 150).reshape(-1, 1)
garray[Interval('chr2', 0, 300), 0] = np.repeat(1, 300).reshape(-1, 1)
return garray
with pytest.raises(Exception):
# Error because resolution=50 but no collapser defined
ga = create_genomic_array(GenomicIndexer.create_from_genomesize({
'chr1':
150,
'chr2':
300
}),
stranded=False,
typecode='float32',
storage="ndarray",
cache=None,
resolution=50,
loader=loading,
collapser=None,
normalizer=['tpm'])
with pytest.raises(Exception):
# Error because resolution=None but no collapser defined
ga = create_genomic_array(GenomicIndexer.create_from_genomesize({
'chr1':
150,
'chr2':
300
}),
stranded=False,
typecode='float32',
storage="ndarray",
cache=None,
resolution=None,
loader=loading,
collapser=None,
normalizer=['tpm'])
ga = create_genomic_array(GenomicIndexer.create_from_file(
[
Interval('chr1', 0, 150),
Interval('chr2', 0, 150),
Interval('chr2', 150, 300)
],
binsize=150,
stepsize=None,
),
stranded=False,
typecode='float32',
storage="ndarray",
cache=None,
resolution=1,
loader=loading)
ga = create_genomic_array(GenomicIndexer.create_from_file(
[Interval('chr1', 0, 150),
Interval('chr2', 0, 300)],
binsize=None,
stepsize=None,
collapse=True),
stranded=False,
typecode='float32',
storage="ndarray",
cache='test',
resolution=None,
loader=loading,
store_whole_genome=None,
collapser='sum')
ga = create_genomic_array(GenomicIndexer.create_from_file(
[Interval('chr1', 0, 150),
Interval('chr2', 0, 300)],
binsize=None,
stepsize=None,
collapse=True),
stranded=False,
typecode='float32',
storage="ndarray",
cache=None,
resolution=None,
loader=loading,
collapser='sum',
normalizer=['tpm'])
os.makedirs(vcfoutput, exist_ok=True)
# perform variant effect prediction using Bioseq object and
# a VCF file
scoresfile, variantsfile = model.predict_variant_effect(
DNA, VCFFILE, conditions=['feature'], output_folder=vcfoutput)
scoresfile = os.path.join(vcfoutput, 'scores.hdf5')
variantsfile = os.path.join(vcfoutput, 'snps.bed.gz')
# parse the variant effect predictions (difference between
# reference and alternative variant) into a Cover object
# for the purpose of visualization
f = h5py.File(scoresfile, 'r')
gindexer = GenomicIndexer.create_from_file(variantsfile, None, None)
snpcov = Cover.create_from_array('snps',
f['diffscore'],
gindexer,
store_whole_genome=True,
padding_value=np.nan)
snpcov = Cover.create_from_array('snps',
f['diffscore'],
gindexer,
store_whole_genome=False,
padding_value=np.nan)
gi = DNA.gindexer[3]
chrom = gi.chrom
start = gi.start
def test_filter_by_region():
roi_file = pkg_resources.resource_filename('janggu',
'resources/bed_test.bed')
f1 = GenomicIndexer.create_from_file(regions=roi_file,
binsize=2,
stepsize=2)
np.testing.assert_equal(len(f1), 9)
j = ""
for i in f1:
j += str(i) + "\n"
prv = "chr1:[0,2)/+\n" \
"chr1:[2,4)/+\n" \
"chr1:[4,6)/+\n" \
"chr1:[6,8)/+\n" \
"chr1:[8,10)/+\n" \
"chr1:[10,12)/+\n" \
"chr1:[12,14)/+\n" \
"chr1:[14,16)/+\n" \
"chr1:[16,18)/+\n"
np.testing.assert_equal(j, prv)
test1 = f1.filter_by_region(include='chr1', start=0, end=18)
k = ""
for i in test1:
k += str(i) + "\n"
np.testing.assert_equal(j, k)
test2 = f1.filter_by_region(include='chr1', start=5, end=10)
z = ""
for i in test2:
z += str(i) + "\n"
prv2 = "chr1:[4,6)/+\n" \
"chr1:[6,8)/+\n" \
"chr1:[8,10)/+\n"
np.testing.assert_equal(z, prv2)
test3 = f1.filter_by_region(include='chr1', start=5, end=11)
q = ""
for i in test3:
q += str(i) + "\n"
prv3 = "chr1:[4,6)/+\n" \
"chr1:[6,8)/+\n" \
"chr1:[8,10)/+\n" \
"chr1:[10,12)/+\n"
np.testing.assert_equal(q, prv3)
test4 = f1.filter_by_region(include='chr1', start=6, end=10)
z1 = ""
for i in test4:
z1 += str(i) + "\n"
prv4 = "chr1:[6,8)/+\n" \
"chr1:[8,10)/+\n"
np.testing.assert_equal(z1, prv4)
test5 = f1.filter_by_region(include='chr1', start=6, end=11)
q1 = ""
for i in test5:
q1 += str(i) + "\n"
prv5 = "chr1:[6,8)/+\n" \
"chr1:[8,10)/+\n" \
"chr1:[10,12)/+\n"
np.testing.assert_equal(q1, prv5)
test6 = f1.filter_by_region(include='chr1', start=20, end=30)
np.testing.assert_equal(len(test6), 0)
