def chipcount(bamfile,
bwfile,
maxinsert=180,
mininsert=130,
paired=False,
extend=150):
"""
:param bamfile:
:param chromosome:
:param start:
:param end:
:param paired:
:return:
"""
samfile = openBam.openBam(bamfile)
readscount = dict()
if paired:
pass
else:
pass
return readscount
def dhcutcount(bamfile, chromosome, start, end, library='Duke'):
"""
:param bamfile: bamfile
:param chromosome:
:param start:
:param end:
:param library: Duke or Washington
Duke: |=====>
<=====|
Washington: |===========|
Out put cutting site '|'
:return: dictionary of cutting site count
"""
samfile = openBam.openBam(bamfile)
readscount = dict()
if library == 'Duke':
for aligned_read in samfile.fetch(reference=str(chromosome),
start=start,
end=end):
if aligned_read.is_reverse:
site = aligned_read.aend
else:
site = aligned_read.pos
site = site + 1
if site in readscount:
readscount[site] = readscount[site] + 1
else:
readscount[site] = 1
elif library == 'Washington':
pass
else:
pass
return readscount
def chipcoverage(bamfile, chromosome, start, end, maxinsert=180, mininsert=130, paired=False, extend=150):
"""
:param bamfile:
:param chromosome:
:param start:
:param end:
:param paired:
:return:
"""
samfile = openBam.openBam(bamfile)
readscount = dict()
if paired:
for aligened_read in samfile.fetch(reference=str(chromosome), start=start, end=end):
if aligened_read.is_proper_pair:
if not aligened_read.is_reverse:
if mininsert <= aligened_read.isize <= maxinsert:
pair_start = aligened_read.pos
for i in range(pair_start, pair_start + aligened_read.isize):
if start <= i <= end:
if i in readscount:
readscount[i] += 1
else:
readscount[i] = 1
else:
for alignend_read in samfile.fetch(reference=str(chromosome), start=start, end=end):
for i in range(alignend_read.pos, alignend_read.pos + extend):
if start <= i <= end:
if i in readscount:
readscount[i] += 1
else:
readscount[i] = 1
return readscount
def coveragecount(bamfile, chromosome, start, end, maxinsert=80, mininsert=1, paired=False):
"""
:param bamfile:
:param chromosome:
:param start:
:param end:
:param paired:
:return: dictionary of mhs middle site count
"""
samfile = openBam.openBam(bamfile)
readscount = dict()
if paired:
for aligened_read in samfile.fetch(reference=str(chromosome), start=start, end=end):
if aligened_read.is_proper_pair:
if not aligened_read.is_reverse:
if mininsert <= aligened_read.isize <= maxinsert:
pair_start = aligened_read.pos
for site in range(pair_start, pair_start + aligened_read.isize):
if site in readscount:
readscount[site] += 1
else:
readscount[site] = 1
else:
for alignend_read in samfile.fetch(reference=str(chromosome), start=start, end=end):
if mininsert <= alignend_read.alen <= maxinsert:
for site in range(alignend_read.pos, alignend_read.pos + alignend_read.alen):
if site in readscount:
readscount[site] = readscount[site] + 1
else:
readscount[site] = 1
return readscount
def dhcutcount(bamfile, chromosome, start, end, library='Duke'):
"""
:param bamfile: bamfile
:param chromosome:
:param start:
:param end:
:param library: Duke or Washington
Duke: |=====>
<=====|
Washington: |===========|
Out put cutting site '|'
:return: dictionary of cutting site count
"""
samfile = openBam.openBam(bamfile)
readscount = dict()
if library == 'Duke':
for aligned_read in samfile.fetch(reference=str(chromosome), start=start, end=end):
if aligned_read.is_reverse:
site = aligned_read.aend
else:
site = aligned_read.pos
site = site + 1
if site in readscount:
readscount[site] = readscount[site] + 1
else:
readscount[site] = 1
elif library == 'Washington':
pass
else:
pass
return readscount
def chipcount(bamfile, bwfile, maxinsert=180, mininsert=130, paired=False, extend=150):
"""
:param bamfile:
:param chromosome:
:param start:
:param end:
:param paired:
:return:
"""
samfile = openBam.openBam(bamfile)
readscount = dict()
if paired:
pass
else:
pass
return readscount
def mhsmidcount(bamfile, chromosome, start, end, maxinsert=80, mininsert=1, paired=False):
"""
:param bamfile:
:param chromosome:
:param start:
:param end:
:param paired:
:return: dictionary of mhs middle site count
"""
samfile = openBam.openBam(bamfile)
readscount = dict()
if paired:
for aligened_read in samfile.fetch(reference=str(chromosome), start=start, end=end):
if aligened_read.is_proper_pair:
if not aligened_read.is_reverse:
if mininsert <= aligened_read.isize <= maxinsert:
pair_start = aligened_read.pos
if aligened_read.isize % 2 == 0:
middle1 = pair_start + aligened_read.isize / 2
middle2 = pair_start + aligened_read.isize / 2 - 1
else:
middle1 = pair_start + int(aligened_read.isize / 2)
middle2 = pair_start + int(aligened_read.isize / 2)
middleint1 = int(middle1)
middleint2 = int(middle2)
if start <= middleint1 <= end:
if middleint1 in readscount:
readscount[middleint1] = readscount[middleint1] + 1
else:
readscount[middleint1] = 1
if start <= middleint2 <= end:
if middleint2 in readscount:
readscount[middleint2] = readscount[middleint2] + 1
else:
readscount[middleint2] = 1
else:
for alignend_read in samfile.fetch(reference=str(chromosome), start=start, end=end):
if mininsert <= alignend_read.alen <= maxinsert:
if alignend_read.alen % 2 == 0:
middle1 = alignend_read.pos + alignend_read.alen / 2
middle2 = alignend_read.pos + alignend_read.alen / 2 + 1
else:
middle1 = alignend_read.pos + int(alignend_read.alen / 2)
middle2 = alignend_read.pos + int(alignend_read.alen / 2)
middleint1 = int(middle1)
middleint2 = int(middle2)
if (start <= middleint1 <= end):
if middleint1 in readscount:
readscount[middleint1] = readscount[middleint1] + 1
else:
readscount[middleint1] = 1
if (start <= middleint2 <= end):
if middleint2 in readscount:
readscount[middleint2] = readscount[middleint2] + 1
else:
readscount[middleint2] = 1
return readscount
def chipcoverage(bamfile,
chromosome,
start,
end,
maxinsert=180,
mininsert=130,
paired=False,
extend=150):
"""
:param bamfile:
:param chromosome:
:param start:
:param end:
:param paired:
:return:
"""
samfile = openBam.openBam(bamfile)
readscount = dict()
if paired:
for aligened_read in samfile.fetch(reference=str(chromosome),
start=start,
end=end):
if aligened_read.is_proper_pair:
if not aligened_read.is_reverse:
if mininsert <= aligened_read.isize <= maxinsert:
pair_start = aligened_read.pos
for i in range(pair_start,
pair_start + aligened_read.isize):
if start <= i <= end:
if i in readscount:
readscount[i] += 1
else:
readscount[i] = 1
else:
for alignend_read in samfile.fetch(reference=str(chromosome),
start=start,
end=end):
for i in range(alignend_read.pos, alignend_read.pos + extend):
if start <= i <= end:
if i in readscount:
readscount[i] += 1
else:
readscount[i] = 1
return readscount
def __init__(self, bamfile):
self.bamfile = bamfile
self.samfile = openBam.openBam(self.bamfile)
self.chrlen = self.getchrlen()
def __init__(self, bamfile):
self.bamfile = bamfile
self.samfile = openBam.openBam(self.bamfile)
self.chrlen = self.getchrlen()
def mhsmidcount(bamfile,
chromosome,
start,
end,
maxinsert=80,
mininsert=1,
paired=False):
"""
:param bamfile:
:param chromosome:
:param start:
:param end:
:param paired:
:return: dictionary of mhs middle site count
"""
samfile = openBam.openBam(bamfile)
readscount = dict()
if paired:
for aligened_read in samfile.fetch(reference=str(chromosome),
start=start,
end=end):
if aligened_read.is_proper_pair:
if not aligened_read.is_reverse:
if mininsert <= aligened_read.isize <= maxinsert:
pair_start = aligened_read.pos
if aligened_read.isize % 2 == 0:
middle1 = pair_start + aligened_read.isize / 2
middle2 = pair_start + aligened_read.isize / 2 - 1
else:
middle1 = pair_start + int(aligened_read.isize / 2)
middle2 = pair_start + int(aligened_read.isize / 2)
middleint1 = int(middle1)
middleint2 = int(middle2)
if start <= middleint1 <= end:
if middleint1 in readscount:
readscount[
middleint1] = readscount[middleint1] + 1
else:
readscount[middleint1] = 1
if start <= middleint2 <= end:
if middleint2 in readscount:
readscount[
middleint2] = readscount[middleint2] + 1
else:
readscount[middleint2] = 1
else:
for alignend_read in samfile.fetch(reference=str(chromosome),
start=start,
end=end):
if mininsert <= alignend_read.alen <= maxinsert:
if alignend_read.alen % 2 == 0:
middle1 = alignend_read.pos + alignend_read.alen / 2
middle2 = alignend_read.pos + alignend_read.alen / 2 + 1
else:
middle1 = alignend_read.pos + int(alignend_read.alen / 2)
middle2 = alignend_read.pos + int(alignend_read.alen / 2)
middleint1 = int(middle1)
middleint2 = int(middle2)
if (start <= middleint1 <= end):
if middleint1 in readscount:
readscount[middleint1] = readscount[middleint1] + 1
else:
readscount[middleint1] = 1
if (start <= middleint2 <= end):
if middleint2 in readscount:
readscount[middleint2] = readscount[middleint2] + 1
else:
readscount[middleint2] = 1
return readscount
def coveragecount(bamfile,
chromosome,
start,
end,
maxinsert=80,
mininsert=1,
paired=False):
"""
:param bamfile:
:param chromosome:
:param start:
:param end:
:param paired:
:return: dictionary of mhs middle site count
"""
samfile = openBam.openBam(bamfile)
readscount = dict()
if paired:
for aligened_read in samfile.fetch(reference=str(chromosome),
start=start,
end=end):
if aligened_read.is_proper_pair:
if not aligened_read.is_reverse:
if mininsert <= aligened_read.isize <= maxinsert:
pair_start = aligened_read.pos
for site in range(pair_start,
pair_start + aligened_read.isize):
if site in readscount:
readscount[site] += 1
else:
readscount[site] = 1
else:
for alignend_read in samfile.fetch(reference=str(chromosome),
start=start,
end=end):
if mininsert <= alignend_read.alen <= maxinsert:
for site in range(alignend_read.pos,
alignend_read.pos + alignend_read.alen):
if site in readscount:
readscount[site] = readscount[site] + 1
else:
readscount[site] = 1
return readscount