def procress_emit(qinput, qoutput, lock, pileup_prefix, parser_parameters, n,
p_neutral, f_sel1, f_sel2, ancestral):
qualityEncoding = parser_parameters[0]
minQual = parser_parameters[1]
minCount = parser_parameters[2]
minCoverage = parser_parameters[3]
maxCoverage = parser_parameters[4]
#creation of the parser object
if ancestral == "provided":
parser = pp.Pileup_parser_provided(qualityEncoding, minQual, minCount,
minCoverage, maxCoverage)
elif ancestral == "unknown":
parser = pp.Pileup_parser_folded(qualityEncoding, minQual, minCount,
minCoverage, maxCoverage)
else:
parser = pp.Pileup_parser_ref(qualityEncoding, minQual, minCount,
minCoverage, maxCoverage)
f = pp.Format()
pileup = pp.openPileup(pileup_prefix, 'r')
for item in iter(qinput.get, 'STOP'):
l = []
pileup.seek(item[0])
for i in range(item[1]):
l.append(pileup.readline())
#...
p = A()
for l_item in l:
parsed = parser.get_pileup_parser(l_item)
if parsed['valid'] == 1:
info = f.format('info', parsed)
if info.split()[5] != "N":
unfolded = int(info.split()[7])
votemp = np.fromstring(f.format('freq', parsed),
dtype=int,
sep=' ')
SE = np.fromstring(f.format('qual', parsed),
dtype=float,
sep=' ')
SEtemp = 10**(-SE / 10)
pseg = prob_cond_true_freq(n, votemp, SEtemp, unfolded)
votemp = np.zeros(len(votemp))
p0 = prob_cond_true_freq(n, votemp, SEtemp, unfolded)
E = comp_emit_BF_3_SEG(n, pseg, p0, p_neutral, f_sel1,
f_sel2, unfolded)
if E[0] > 0 and E[1] > 0 and E[2] > 0:
p.list_chro.append(info.split()[0])
p.list_pos.append(int(info.split()[1]))
p.list_E.append(E)
#...
#...
#...
if len(p.list_E
) != 0: #in case that all the lines parsed are not valid
qoutput.put(p)
#...
#...
pileup.close()
def process_probCond(qinput, qoutput, lock, pileup_prefix, parser_parameters,
ratio, n, ancestral):
pileup = pp.openPileup(pileup_prefix, 'r')
qualityEncoding = parser_parameters[0]
minQual = parser_parameters[1]
minCount = parser_parameters[2]
minCoverage = parser_parameters[3]
maxCoverage = parser_parameters[4]
#creation of the parser object
if ancestral == "provided":
parser = pp.Pileup_parser_provided(qualityEncoding, minQual, minCount,
minCoverage, maxCoverage)
elif ancestral == "unknown":
parser = pp.Pileup_parser_folded(qualityEncoding, minQual, minCount,
minCoverage, maxCoverage)
else:
parser = pp.Pileup_parser_ref(qualityEncoding, minQual, minCount,
minCoverage, maxCoverage)
f = pp.Format()
for item in iter(qinput.get, 'STOP'):
l = []
lock.acquire()
pileup.seek(item[0])
for i in range(item[1]):
l.append(pileup.readline())
#...
lock.release()
p_list = []
for l_item in l:
parsed = parser.get_pileup_parser(l_item)
if parsed['valid'] == 1:
if bernoulli.rvs(1. / ratio) == 1:
info = f.format('info', parsed)
unfolded = int(info.split()[7])
SE = np.fromstring(f.format('qual', parsed),
dtype=float,
sep=' ')
#print SE
votemp = np.fromstring(f.format('freq', parsed),
dtype=int,
sep=' ')
SEtemp = 10**(-SE / 10)
p = prob_cond_true_freq(n, votemp, SEtemp, unfolded)
if np.sum(p) > 0:
p_list.append(p)
#....
#...
#...
if len(p_list) != 0: #in case that all the lines parsed are not valid
qoutput.put(p_list)
#...
#...
pileup.close()
'Error : --k option can\'t be used with the --estim option without the --pred option'
)
sys.exit()
#...
if spectrum_file and theta:
print(
'ERROR : --theta option can\'t be used with the --spectrum-file option.'
)
sys.exit()
if not ancestral == "reference" and not ancestral == "provided" and not ancestral == "unknown":
print('ERROR : invalid argument for -a')
sys.exit()
#pileup file loading
pileup = openPileup(pileup_prefix, 'r', True)
#...
# management of the region if it is specified with the --region option
if region:
chro = region.split(':')
#if only the chromosome is specified in the region ex: --region 2L
if len(chro) == 1:
chro = chro[0]
prefix += '_' + chro
# region's parameters. 'start' end 'end' are set to 'None
region = [chro, start, end]
#chromosome, start and end are specified in the region ex: --region 2L:1000..2000
else:
zone = chro[1].split('..')
#...
def comp_emit_seg_direct(parser_parameters, region, nProcess, n, prefix,
p_neutral, pileup_prefix, ancestral):
emit = open(prefix + '.segemit', 'w')
lock = Lock()
task_queue = Queue()
done_queue = Queue()
block = 10000
pileup = pp.openPileup(pileup_prefix, 'rb')
# computation of cond prob for segsites
if region:
chro = region[0]
start = region[1]
end = region[2]
offset_default = pileup.tell()
pileup_line = pileup.readline()
a = pileup_line.split()[0]
while (a != chro):
offset_default = pileup.tell()
pileup_line = pileup.readline()
try:
a = pileup_line.split()[0]
except IndexError:
#if the pileup_line can't be splited, that's the end of the file
print('ERROR : chro %s not found' % (chro))
sys.exit()
#...
#...
if start:
a = int(pileup_line.split()[1])
b = pileup_line.split()[0]
if a > end:
print('ERROR : interval\'s positions not found.')
sys.exit()
#...
while a < start and b == chro:
offset_default = pileup.tell()
pileup_line = pileup.readline()
try:
a = int(pileup_line.split()[1])
b = pileup_line.split()[0]
except IndexError:
#if the pileup_line can't be splited, that's the end of the file
print('ERROR : interval\'s positions not found.')
#...
#...
if b != chro:
print b
print('ERROR : interval\'s positions not found.')
sys.exit()
#...
offset_table = [offset_default]
nbLine = 0
split_pileup = pileup_line.split()
while split_pileup[0] == chro:
if start:
if int(split_pileup[1]) > end:
break
#...
#...
nbLine += 1
if nbLine % block == 0:
offset_table.append(pileup.tell())
#...
pileup_line = pileup.readline()
split_pileup = pileup_line.split()
if len(split_pileup) == 0:
break
#...
#...
#...
else:
offset_table = [0]
nbLine = 0
pileup_line = pileup.readline()
while (pileup_line !=
''): #if pileup_line == '', that's the end of the file
nbLine += 1
if nbLine % block == 0:
offset_table.append(pileup.tell())
#...
pileup_line = pileup.readline()
#...
#...
pileup.close()
coeff1 = 0.7
coeff2 = 0.2
f_sel1 = proba_nielsen(n, p_neutral, coeff1)
print('f_sel1 loaded')
f_sel2 = proba_nielsen(n, p_neutral, coeff2)
print('f_sel2 loaded')
for i in range(nProcess):
p = Process(target=procress_emit,
args=(task_queue, done_queue, lock, pileup_prefix,
parser_parameters, n, p_neutral, f_sel1, f_sel2,
ancestral)).start()
#...
#for each offset expept the last one
for offset in offset_table[:-1]:
task_queue.put([offset, block])
#...
#management of the last line_block
if nbLine % block != 0:
task_queue.put([offset_table[-1], nbLine % block])
#...
del offset_table
del f_sel1
del f_sel2
for i in range(nProcess):
task_queue.put('STOP')
#...
while task_queue.qsize() != 0:
pass
#...
mat = []
for i in range(done_queue.qsize()):
mat.append(done_queue.get())
#...
if len(mat) > 1:
quickSort(mat)
#...
for item in mat:
for i in range(len(item.list_pos)):
emit.write(item.list_chro[i] + ' ' + str(item.list_pos[i]) + ' ' +
str(item.list_E[i][0]) + ' ' + str(item.list_E[i][1]) +
' ' + str(item.list_E[i][2]) + '\n')
#...
#...
emit.close()
def prob_cond(parser_parameters, region, theta, nProcess, ratio, n, prefix,
pileup_prefix, ancestral):
lock = Lock()
task_queue = Queue()
done_queue = Queue()
block = 10000
pileup = pp.openPileup(pileup_prefix, 'rb')
if region:
chro = region[0]
start = region[1]
end = region[2]
offset_default = pileup.tell()
pileup_line = pileup.readline()
a = pileup_line.split()[0]
while (a != chro):
offset_default = pileup.tell()
pileup_line = pileup.readline()
try:
a = pileup_line.split()[0]
except IndexError:
#if the pileup_line can't be splited, that's the end of the file
print('ERROR : chro %s not found' % (chro))
sys.exit()
#...
#...
if start:
a = int(pileup_line.split()[1])
b = pileup_line.split()[0]
if a > end:
print('ERROR : interval\'s positions not found.')
sys.exit()
#...
while a < start and b == chro:
offset_default = pileup.tell()
pileup_line = pileup.readline()
try:
a = int(pileup_line.split()[1])
b = pileup_line.split()[0]
except IndexError:
#if the pileup_line can't be splited, that's the end of the file
print('ERROR : interval\'s positions not found.')
#...
#...
if b != chro:
print('ERROR : interval\'s positions not found.')
sys.exit()
#...
offset_table = [offset_default]
nbLine = 0
split_pileup = pileup_line.split()
while split_pileup[0] == chro:
if start:
if int(split_pileup[1]) > end:
break
#...
#...
nbLine += 1
if nbLine % block == 0:
offset_table.append(pileup.tell())
#...
pileup_line = pileup.readline()
split_pileup = pileup_line.split()
if len(split_pileup) == 0:
break
#...
#...
#...
else:
offset_table = [0]
nbLine = 0
pileup_line = pileup.readline()
while (pileup_line !=
''): #if pileup_line == '', that's the end of the file
nbLine += 1
if nbLine % block == 0:
offset_table.append(pileup.tell())
#...
pileup_line = pileup.readline()
#...
#...
pileup.close()
#for each offset except the last one
for offset in offset_table[:-1]:
task_queue.put([offset, block])
#...
#management of the last line_block
if nbLine % block != 0:
task_queue.put([offset_table[-1], nbLine % block])
#...
del offset_table
for i in range(nProcess):
task_queue.put('STOP')
#...
for i in range(nProcess):
p = Process(target=process_probCond,
args=(task_queue, done_queue, lock, pileup_prefix,
parser_parameters, ratio, n, ancestral)).start()
#...
while task_queue.qsize() != 0:
pass
#...
p_neutral = []
for i in range(done_queue.qsize()):
p_neutral += done_queue.get()
#...
p_neutral = np.array(p_neutral)
p_neutral = comp_spectrum(p_neutral, n, theta, ancestral)
np.savetxt(prefix + '.spectrum',
np.array([p_neutral]),
delimiter=' ',
fmt='%.6e')
return p_neutral
def process_estim(qinput, qoutput, lock, parser_parameters, pileup_prefix, n,
p_neutral, ancestral):
print 'process starts'
pileup = pp.openPileup(pileup_prefix, 'r')
qualityEncoding = parser_parameters[0]
minQual = parser_parameters[1]
minCount = parser_parameters[2]
minCoverage = parser_parameters[3]
maxCoverage = parser_parameters[4]
#creation of the parser object
if ancestral == "provided":
parser = pp.Pileup_parser_provided(qualityEncoding, minQual, minCount,
minCoverage, maxCoverage)
elif ancestral == "unknown":
parser = pp.Pileup_parser_folded(qualityEncoding, minQual, minCount,
minCoverage, maxCoverage)
else:
parser = pp.Pileup_parser_ref(qualityEncoding, minQual, minCount,
minCoverage, maxCoverage)
f = pp.Format()
for item in iter(qinput.get, 'STOP'):
l = []
lock.acquire()
pileup.seek(item[0])
for i in range(item[1]):
l.append(pileup.readline())
#...
lock.release()
estim_tab = A()
for l_item in l:
parsed = parser.get_pileup_parser(l_item)
if parsed['valid'] == 1:
info = f.format('info', parsed)
unfolded = int(info.split()[7])
SE = np.fromstring(f.format('qual', parsed),
dtype=float,
sep=' ')
votemp = np.fromstring(f.format('freq', parsed),
dtype=int,
sep=' ')
SEtemp = 10**(-SE / 10)
estim_tab.list_chro.append(info.split()[0])
estim_tab.list_pos.append(int(info.split()[1]))
estim_tab.list_anc.append(info.split()[4])
estim_tab.list_der.append(info.split()[5])
if unfolded == 1:
estim_tab.list_u.append(
np.argmax(p_neutral *
prob_cond_true_freq(n, votemp, SEtemp, 1)))
else:
estim_tab.list_u.append(
np.argmax((p_neutral + p_neutral[::-1]) *
prob_cond_true_freq(n, votemp, SEtemp, 1)))
Ltemp = len(estim_tab.list_u) - 1
if estim_tab.list_u[Ltemp] > (n / 2):
estim_tab.list_u[Ltemp] = n - estim_tab.list_u[Ltemp]
estim_tab.list_anc[Ltemp] = info.split()[5]
estim_tab.list_der[Ltemp] = info.split()[4]
#...
#...
#print '+1'
if len(estim_tab.list_u
) != 0: #in case that all the lines parsed are not valid
qoutput.put(estim_tab)
#...
#...
print 'process stops'
pileup.close()
def estimation(parser_parameters, region, nProcess, n, prefix, p_neutral,
pileup_prefix, ancestral):
lock = Lock()
task_queue = Queue()
done_queue = Queue()
block = 10000
pileup = pp.openPileup(pileup_prefix, 'r')
if region:
chro = region[0]
start = region[1]
end = region[2]
offset_default = pileup.tell()
pileup_line = pileup.readline()
a = pileup_line.split()[0]
while (a != chro):
offset_default = pileup.tell()
pileup_line = pileup.readline()
try:
a = pileup_line.split()[0]
except IndexError:
#if the pileup_line can't be splited, that's the end of the file
print('ERROR : chro %s not found' % (chro))
sys.exit()
#...
#...
if start:
a = int(pileup_line.split()[1])
b = pileup_line.split()[0]
if a > end:
print('ERROR : interval\'s positions not found.')
sys.exit()
#...
while a < start and b == chro:
offset_default = pileup.tell()
pileup_line = pileup.readline()
try:
a = int(pileup_line.split()[1])
b = pileup_line.split()[0]
except IndexError:
#if the pileup_line can't be splited, that's the end of the file
print('ERROR : interval\'s positions not found.')
#...
#...
if b != chro:
print('ERROR : interval\'s positions not found.')
sys.exit()
#...
offset_table = [offset_default]
nbLine = 0
split_pileup = pileup_line.split()
while split_pileup[0] == chro:
if start:
if int(split_pileup[1]) > end:
break
#...
#...
nbLine += 1
if nbLine % block == 0:
offset_table.append(pileup.tell())
#...
pileup_line = pileup.readline()
split_pileup = pileup_line.split()
if len(split_pileup) == 0:
break
#...
#...
#...
else:
offset_table = [0]
nbLine = 0
pileup_line = pileup.readline()
while (pileup_line !=
''): #if pileup_line == '', that's the end of the file
nbLine += 1
if nbLine % block == 0:
offset_table.append(pileup.tell())
#...
pileup_line = pileup.readline()
#...
#...
#for each offset expept the last one
for offset in offset_table[:-1]:
task_queue.put([offset, block])
#...
#management of the last line_block
if nbLine % block != 0:
task_queue.put([offset_table[-1], nbLine % block])
#...
for i in range(nProcess):
task_queue.put('STOP')
#...
for i in range(nProcess):
p = Process(target=process_estim,
args=(task_queue, done_queue, lock, parser_parameters,
pileup_prefix, n, p_neutral, ancestral)).start()
#...
while task_queue.qsize() != 0:
pass
#...
estim = []
for i in range(done_queue.qsize()):
estim.append(done_queue.get())
#...
if len(estim) > 1:
quickSort(estim)
#...
fic_estim = open(prefix + '.estim', 'w')
for item in estim:
for i in range(len(item.list_pos)):
fic_estim.write(item.list_chro[i] + ' ' + str(item.list_pos[i]) +
' ' + item.list_anc[i] + ' ' + item.list_der[i] +
' ' + str(item.list_u[i]) + '\n')
#...
#...
fic_estim.close()