def test_add(self):
bedpe1 = [ '1', '200', '300', '2', '300', '400', '777_1', '57', '+', '-', 'BND', 'PASS', 'MISSING', 'SVTYPE=BND;AF=0.2' ]
b1 = Bedpe(bedpe1)
bedpe2= [ '1', '195', '305', '2', '295', '405', '777_1', '57', '+', '-', 'BND', 'PASS', 'MISSING', 'SVTYPE=BND;AF=0.3' ]
b2 = Bedpe(bedpe2)
c = Cluster()
c.add(b1, None)
self.assertEqual(c.size, 1)
self.assertEqual(c.sv_event, 'BND')
self.assertEqual(c.filter, '0.2')
self.assertEqual(c.chrom_a, '1')
self.assertEqual(c.min_a, 200)
self.assertEqual(c.max_a, 300)
self.assertEqual(c.chrom_b, '2')
self.assertEqual(c.min_b, 300)
self.assertEqual(c.max_b, 400)
self.assertEqual(c.strand_a, '+')
self.assertEqual(c.strand_b, '-')
c.add(b2, None)
self.assertEqual(c.size, 2)
self.assertEqual(c.sv_event, 'BND')
self.assertEqual(c.filter, '0.3')
self.assertEqual(c.chrom_a, '1')
self.assertEqual(c.min_a, 195)
self.assertEqual(c.max_a, 305)
self.assertEqual(c.chrom_b, '2')
self.assertEqual(c.min_b, 295)
self.assertEqual(c.max_b, 405)
self.assertEqual(c.strand_a, '+')
self.assertEqual(c.strand_b, '-')
def cluster_bedpe(self, in_file, bedpe_out, is_sorted):
# Locally alias instance variables
max_distance = self.max_distance
eval_param = self.eval_param
in_header = True
for line in in_file:
if line.startswith('#') and in_header:
if line.startswith('#CHROM'):
bedpe_out.write('##INFO=<ID=RETAINED,Number=0,Type=Flag,Description="Variants clustering with this call were pruned">\n')
bedpe_out.write(line)
continue
in_header = False
self.bedpe_lines += 1
bedpe = Bedpe(line.rstrip().split('\t'))
if bedpe.af is None:
sys.stderr.write('No allele frequency for variant found. This tool requires allele frequency information to function. Please add with svtools afreq and rerun\n')
sys.exit(1)
if bedpe.af == '.':
self.skipped_lines += 1
continue
matched_clusters = []
for cluster in self.cluster_list:
if cluster.can_add(bedpe, max_distance):
cluster.add(bedpe, eval_param)
matched_clusters.append(cluster)
if not matched_clusters:
new_cluster = Cluster()
new_cluster.add(bedpe, eval_param)
self.cluster_list.append(new_cluster)
else:
if len(matched_clusters) > 1:
i = 0
pruned_clusters = []
while i < (len(matched_clusters) - 1):
j = i + 1
to_delete = set()
while j < len(matched_clusters):
if matched_clusters[i].can_add(matched_clusters[j].elements[0], max_distance):
matched_clusters[i].add(matched_clusters[j].elements[0], eval_param)
pruned_clusters.append(matched_clusters[j])
to_delete.add(j)
j += 1
for index in sorted(to_delete, reverse=True):
del matched_clusters[index]
i += 1
if pruned_clusters:
self.cluster_list = [cluster for cluster in self.cluster_list if cluster not in pruned_clusters]
#prune and print eligible clusters
if self.bedpe_lines % 1000 == 0 and is_sorted:
self.cluster_list = self.prune(bedpe,
False,
bedpe_out)
self.cluster_list = self.prune(None,
True,
bedpe_out)
sys.stderr.write(self.stats_report_string())
return
def cluster_bedpe(self, in_file, bedpe_out, is_sorted):
# Locally alias instance variables
max_distance = self.max_distance
eval_param = self.eval_param
in_header = True
for line in in_file:
if line.startswith('#') and in_header:
if line.startswith('#CHROM'):
bedpe_out.write('##INFO=<ID=RETAINED,Number=0,Type=Flag,Description="Variants clustering with this call were pruned">\n')
bedpe_out.write(line)
continue
in_header = False
self.bedpe_lines += 1
bedpe = Bedpe(line.rstrip().split('\t'))
if bedpe.af is None:
sys.stderr.write('No allele frequency for variant found. This tool requires allele frequency information to function. Please add with svtools afreq and rerun\n')
sys.exit(1)
if bedpe.af == '.':
self.skipped_lines += 1
continue
matched_clusters = []
for cluster in self.cluster_list:
if cluster.can_add(bedpe, max_distance):
cluster.add(bedpe, eval_param)
matched_clusters.append(cluster)
if not matched_clusters:
new_cluster = Cluster()
new_cluster.add(bedpe, eval_param)
self.cluster_list.append(new_cluster)
else:
if len(matched_clusters) > 1:
i = 0
pruned_clusters = []
while i < (len(matched_clusters) - 1):
j = i + 1
to_delete = set()
while j < len(matched_clusters):
if matched_clusters[i].can_add(matched_clusters[j].elements[0], max_distance):
matched_clusters[i].add(matched_clusters[j].elements[0], eval_param)
pruned_clusters.append(matched_clusters[j])
to_delete.add(j)
j += 1
for index in sorted(to_delete, reverse=True):
del matched_clusters[index]
i += 1
if pruned_clusters:
self.cluster_list = [cluster for cluster in self.cluster_list if cluster not in pruned_clusters]
#prune and print eligible clusters
if self.bedpe_lines % 1000 == 0 and is_sorted:
self.cluster_list = self.prune(bedpe,
False,
bedpe_out)
self.cluster_list = self.prune(None,
True,
bedpe_out)
sys.stderr.write(self.stats_report_string())
return
def cluster_bedpe(self, in_file, bedpe_out, is_sorted):
# Locally alias instance variables
max_distance = self.max_distance
eval_param = self.eval_param
in_header = True
for line in in_file:
if line.startswith('#') and in_header:
bedpe_out.write(line)
continue
in_header = False
self.bedpe_lines += 1
bedpe = Bedpe(line.rstrip().split('\t'))
if bedpe.af is None:
sys.stderr.write('No allele frequency for variant found. This tool requires allele frequency information to function. Please add with svtools afreq and rerun\n')
sys.exit(1)
if bedpe.af == '.':
self.skipped_lines += 1
continue
matched_clusters = []
for cluster in self.cluster_list:
if cluster.can_add(bedpe, max_distance):
cluster.add(bedpe, eval_param)
matched_clusters.append(cluster)
if not matched_clusters:
new_cluster = Cluster()
new_cluster.add(bedpe, eval_param)
self.cluster_list.append(new_cluster)
else:
if len(matched_clusters) > 1:
i = 0
matched_cluster_pruned = False
while i < (len(matched_clusters) - 1):
j = i + 1
while j < len(matched_clusters):
if matched_clusters[i].can_add(matched_clusters[j].elements[0], max_distance):
matched_clusters[i].add(matched_clusters[j].elements[0], eval_param)
matched_cluster_pruned = True
del matched_clusters[j]
j += 1
i += 1
if matched_cluster_pruned:
self.cluster_list = [cluster for cluster in self.cluster_list if cluster not in matched_clusters]
#prune and print eligible clusters
if self.bedpe_lines % 1000 == 0 and is_sorted:
self.cluster_list = self.prune(bedpe,
False,
bedpe_out)
self.cluster_list = self.prune(None,
True,
bedpe_out)
sys.stderr.write(self.stats_report_string())
return
def test_get_cluster_string(self):
bedpe = [ '1', '200', '300', '2', '300', '400', '777_1', '57', '+', '-', 'BND', 'PASS', 'MISSING', 'SVTYPE=BND;AF=0.2' ]
b = Bedpe(bedpe)
c = Cluster()
with self.assertRaises(ValueError):
c.get_cluster_string()
c.add(b, None)
self.assertEqual(c.get_cluster_string(), str(b))
def test_get_cluster_string(self):
bedpe = [
'1', '200', '300', '2', '300', '400', '777_1', '57', '+', '-',
'BND', 'PASS', '.', '.', '.', '.', '.', '.', 'MISSING',
'SVTYPE=BND;AF=0.2'
]
b = Bedpe(bedpe)
c = Cluster()
with self.assertRaises(ValueError):
c.get_cluster_string()
c.add(b, None)
self.assertEqual(c.get_cluster_string(), str(b))
def test_add(self):
bedpe1 = [
'1', '200', '300', '2', '300', '400', '777_1', '57', '+', '-',
'BND', 'PASS', '.', '.', '.', '.', '.', '.', 'MISSING',
'SVTYPE=BND;AF=0.2'
]
b1 = Bedpe(bedpe1)
bedpe2 = [
'1', '195', '305', '2', '295', '405', '777_1', '57', '+', '-',
'BND', 'PASS', '.', '.', '.', '.', '.', '.', 'MISSING',
'SVTYPE=BND;AF=0.3'
]
b2 = Bedpe(bedpe2)
c = Cluster()
c.add(b1, None)
self.assertEqual(c.size, 1)
self.assertEqual(c.sv_event, 'BND')
self.assertEqual(c.filter, '0.2')
self.assertEqual(c.chrom_a, '1')
self.assertEqual(c.min_a, 200)
self.assertEqual(c.max_a, 300)
self.assertEqual(c.chrom_b, '2')
self.assertEqual(c.min_b, 300)
self.assertEqual(c.max_b, 400)
self.assertEqual(c.strand_a, '+')
self.assertEqual(c.strand_b, '-')
c.add(b2, None)
self.assertEqual(c.size, 2)
self.assertEqual(c.sv_event, 'BND')
self.assertEqual(c.filter, '0.3')
self.assertEqual(c.chrom_a, '1')
self.assertEqual(c.min_a, 195)
self.assertEqual(c.max_a, 305)
self.assertEqual(c.chrom_b, '2')
self.assertEqual(c.min_b, 295)
self.assertEqual(c.max_b, 405)
self.assertEqual(c.strand_a, '+')
self.assertEqual(c.strand_b, '-')
def test_can_add(self):
bedpe = [ '1', '200', '300', '2', '300', '400', '777_1', '57', '+', '-', 'BND', 'PASS', 'MISSING', 'SVTYPE=BND;AF=0.2' ]
b = Bedpe(bedpe)
c = Cluster()
c.chrom_a = b.c1
c.chrom_b = b.c2
c.min_a = b.s1
c.max_a = b.e1
c.min_b = b.s2
c.max_b = b.e2
c.strand_a = b.o1
c.strand_b = b.o2
self.assertTrue(c.can_add(b, 1))
c.size = 1
c.sv_event = 'DEL'
self.assertFalse(c.can_add(b, 1))
c.sv_event = 'BND'
self.assertTrue(c.can_add(b, 1))
c.chrom_a = 'X'
self.assertFalse(c.can_add(b, 1))
c.chrom_a = b.c1
c.chrom_b = 'X'
self.assertFalse(c.can_add(b, 1))
c.chrom_b = b.c2
c.min_a = 305
self.assertFalse(c.can_add(b, 1))
c.min_a = b.s1
c.max_a = 150
self.assertFalse(c.can_add(b, 1))
c.max_a = b.e1
c.min_b = 405
self.assertFalse(c.can_add(b, 1))
c.min_b = b.s1
c.max_b = 150
self.assertFalse(c.can_add(b, 1))
def test_can_add(self):
bedpe = [
'1', '200', '300', '2', '300', '400', '777_1', '57', '+', '-',
'BND', 'PASS', '.', '.', '.', '.', '.', '.', 'MISSING',
'SVTYPE=BND;AF=0.2'
]
b = Bedpe(bedpe)
c = Cluster()
c.chrom_a = b.c1
c.chrom_b = b.c2
c.min_a = b.s1
c.max_a = b.e1
c.min_b = b.s2
c.max_b = b.e2
c.strand_a = b.o1
c.strand_b = b.o2
self.assertTrue(c.can_add(b, 1))
c.size = 1
c.sv_event = 'DEL'
self.assertFalse(c.can_add(b, 1))
c.sv_event = 'BND'
self.assertTrue(c.can_add(b, 1))
c.chrom_a = 'X'
self.assertFalse(c.can_add(b, 1))
c.chrom_a = b.c1
c.chrom_b = 'X'
self.assertFalse(c.can_add(b, 1))
c.chrom_b = b.c2
c.min_a = 305
self.assertFalse(c.can_add(b, 1))
c.min_a = b.s1
c.max_a = 150
self.assertFalse(c.can_add(b, 1))
c.max_a = b.e1
c.min_b = 405
self.assertFalse(c.can_add(b, 1))
c.min_b = b.s1
c.max_b = 150
self.assertFalse(c.can_add(b, 1))