def aligned_segment(self):
s = pysam.AlignedSegment()
s.query_name = str(self.filename)
s.query_sequence = self.seq
s.flag = self.flag
s.reference_start = self.pos
s.mapping_quality = self.mapq
s.cigar = self.cigar
s.next_reference_start = self.pnext
s.template_length = self.tlen
s.query_qualities = pysam.fromQualityString(self.qual)
s.tags = (("ES", self.es), ("RP", self.path_to_read))
return s
def aligned_segment(self):
s = pysam.AlignedSegment()
s.query_name = str(self.filename)
s.query_sequence= self.seq
s.flag = self.flag
s.reference_start = self.pos
s.mapping_quality = self.mapq
s.cigar = self.cigar
s.next_reference_start = self.pnext
s.template_length=self.tlen
s.query_qualities = pysam.fromQualityString(self.qual)
s.tags = (("ES", self.es),
("RP", self.path_to_read))
return s
def test_get_aligned_pairs_padding(self):
a = pysam.AlignedSegment()
a.query_name = "read_12345"
a.query_sequence = "ACGT" * 10
a.flag = 0
a.reference_id = 0
a.reference_start = 20
a.mapping_quality = 20
a.cigartuples = ((7, 20), (6, 1), (8, 19))
a.query_qualities = pysam.fromQualityString("1234") * 10
def inner():
a.get_aligned_pairs()
# padding is not bein handled right now
self.assertRaises(NotImplementedError, inner)
def test_get_aligned_pairs_match_mismatch(self):
a = pysam.AlignedSegment()
a.query_name = "read_12345"
a.query_sequence = "ACGT" * 10
a.flag = 0
a.reference_id = 0
a.reference_start = 20
a.mapping_quality = 20
a.cigartuples = ((7, 20), (8, 20))
a.query_qualities = pysam.fromQualityString("1234") * 10
self.assertEqual(a.get_aligned_pairs(),
[(qpos, refpos) for (qpos, refpos) in zip(
range(0, 0 + 40), range(20, 20 + 40))])
self.assertEqual(a.get_aligned_pairs(True),
[(qpos, refpos) for (qpos, refpos) in zip(
range(0, 0 + 40), range(20, 20 + 40))])
def testUpdate2(self):
'''issue 135: inplace update of sequence and quality score.
This does not work as setting the sequence will erase
the quality scores.
'''
a = self.buildRead()
a.query_sequence = a.query_sequence[5:10]
self.assertEqual(pysam.toQualityString(a.query_qualities), None)
a = self.buildRead()
s = pysam.toQualityString(a.query_qualities)
a.query_sequence = a.query_sequence[5:10]
a.query_qualities = pysam.fromQualityString(s[5:10])
self.assertEqual(pysam.toQualityString(a.query_qualities), s[5:10])
def test_get_aligned_pairs_hard_clipping(self):
a = pysam.AlignedSegment()
a.query_name = "read_12345"
a.query_sequence = "ACGT" * 10
a.flag = 0
a.reference_id = 0
a.reference_start = 20
a.mapping_quality = 20
a.cigartuples = ((5, 2), (0, 35), (5, 3))
a.query_qualities = pysam.fromQualityString("1234") * 10
self.assertEqual(a.get_aligned_pairs(),
# No seq, no seq pos
[(qpos, refpos) for (qpos, refpos) in zip(
range(0, 0 + 35), range(20, 20 + 35))])
self.assertEqual(a.get_aligned_pairs(True),
[(qpos, refpos) for (qpos, refpos) in zip(
range(0, 0 + 35), range(20, 20 + 35))])
def testLargeRead(self):
'''build an example read.'''
a = pysam.AlignedSegment()
a.query_name = "read_12345"
a.query_sequence = "ACGT" * 200
a.flag = 0
a.reference_id = 0
a.reference_start = 20
a.mapping_quality = 20
a.cigartuples = ((0, 4 * 200), )
a.next_reference_id = 0
a.next_reference_start = 200
a.template_length = 167
a.query_qualities = pysam.fromQualityString("1234") * 200
return a
def buildRead(self):
'''build an example read.'''
a = pysam.AlignedSegment()
a.query_name = "read_12345"
a.query_sequence = "ACGT" * 10
a.flag = 0
a.reference_id = 0
a.reference_start = 20
a.mapping_quality = 20
a.cigartuples = ((0, 10), (2, 1), (0, 9), (1, 1), (0, 20))
a.next_reference_id = 0
a.next_reference_start = 200
a.template_length = 167
a.query_qualities = pysam.fromQualityString("1234") * 10
# todo: create tags
return a
def test_get_aligned_pairs_skip(self):
a = pysam.AlignedSegment()
a.query_name = "read_12345"
a.query_sequence = "ACGT" * 10
a.flag = 0
a.reference_id = 0
a.reference_start = 20
a.mapping_quality = 20
a.cigartuples = ((0, 2), (3, 100), (0, 38))
a.query_qualities = pysam.fromQualityString("1234") * 10
self.assertEqual(a.get_aligned_pairs(),
[(0, 20), (1, 21)] +
[(None, refpos) for refpos in range(22, 22 + 100)] +
[(qpos, refpos) for (qpos, refpos) in zip(
range(2, 2 + 38),
range(20 + 2 + 100, 20 + 2 + 100 + 38))])
self.assertEqual(a.get_aligned_pairs(True),
[(0, 20), (1, 21)] +
# [(None, refpos) for refpos in range(21, 21+100)] +
[(qpos, refpos) for (qpos, refpos) in zip(
range(2, 2 + 38),
range(20 + 2 + 100, 20 + 2 + 100 + 38))])
def test_get_aligned_pairs_soft_clipping(self):
a = pysam.AlignedSegment()
a.query_name = "read_12345"
a.query_sequence = "ACGT" * 10
a.flag = 0
a.reference_id = 0
a.reference_start = 20
a.mapping_quality = 20
a.cigartuples = ((4, 2), (0, 35), (4, 3))
a.query_qualities = pysam.fromQualityString("1234") * 10
self.assertEqual(a.get_aligned_pairs(),
[(0, None), (1, None)] +
[(qpos, refpos) for (qpos, refpos) in zip(
range(2, 2 + 35), range(20, 20 + 35))] +
[(37, None), (38, None), (39, None)]
)
self.assertEqual(a.get_aligned_pairs(True),
# [(0, None), (1, None)] +
[(qpos, refpos) for (qpos, refpos) in zip(
range(2, 2 + 35), range(20, 20 + 35))]
# [(37, None), (38, None), (39, None)]
)
def parse_line (self, line):
self.count["total"] += 1
# Try bloc to skip to the next line in case a non standard line is found
try:
# Split the line and verify the number of fields
split_line = line.strip().split("\t")
assert len (split_line) >= 11, "Invalid number of field in bam aligned sequence"
# Init an AlignedSegment
read = Read(
qname = split_line[0],
flag = int(split_line[1]),
rname = self.header.rname_to_refid(split_line[2]),
pos = int(split_line[3])-1,
mapq = int(split_line[4]),
cigar = self._cigarstring_to_tuple(split_line[5]),
rnext = self.header.rname_to_refid(split_line[6]),
pnext = int(split_line[7])-1,
seq = split_line[9],
qual = pysam.fromQualityString(split_line[10]),
tags = self._parse_tags(split_line [11:]) if len (split_line) >= 12 else tuple())
# skip the read if secondary and required
if read.is_secondary:
self.count["secondary"] += 1
if self.skip_secondary:
return None
# finally return the read
self.count["primary"] += 1
return read
except Exception as E:
print E
print "Invalid sequence line in bam: {}".format(line)
self.count["invalid"] += 1
return None
import pysam
from mergedups.pileup import PileupElement, Pileup
__author__ = 'dankle'
my_read = pysam.AlignedSegment()
my_read.query_sequence="AGCT"
my_read.query_qualities = pysam.fromQualityString("FGHI")
my_read.reference_id = 0
my_read.reference_start = 32
my_read.mpos = 250
my_read.is_reverse = True
my_read.tags = (("NM", 1), ("RG", "L1"))
# my_read2 is truncated by one base
my_read2 = pysam.AlignedSegment()
my_read2.query_sequence="GGC"
my_read2.query_qualities = pysam.fromQualityString("FGH")
my_read3 = pysam.AlignedSegment()
my_read3.query_sequence="AACT"
my_read3.query_qualities = pysam.fromQualityString("FGHI")
my_read4 = pysam.AlignedSegment()
my_read4.query_sequence="GGCT"
my_read4.query_qualities = pysam.fromQualityString("FGHI")
def test_pileup_element():
pe = PileupElement('A', 40)
assert pe.phredqual() == 'I'
