def main(trioFileN,
projectN,
tidL=[],
clean=False,
pbs=False,
server='smc1',
genome='hg19'):
storageBase = os.path.dirname(mypipe.prepare_baseDir(projectN,
mkdir=False)) + '/'
apacheBase = storageBase
if glob(storageBase + projectN):
print('File directory: already exists')
else:
os.system('mkdir %s/%s; \
chmod a+w %s/%s' % (storageBase, projectN, storageBase, projectN))
print('File directory: created')
if glob(apacheBase + projectN):
print('Log directory: already exists')
else:
os.system('mkdir %s/%s; \
chmod a+w %s/%s' % (apacheBase, projectN, apacheBase, projectN))
print('Log directory: created')
bamDirL = mysetting.wxsBamDirL
trioH = mypipe.read_trio(trioFileN, bamDirL, tidL)
## assume 1 primary & normal per trio
for tid in trioH:
if tidL != [] and tid not in tidL:
continue
if trioH[tid]['Normal'] == [] or trioH[tid]['prim_id'] == []:
continue
bamS = set()
if trioH[tid]['prim_id'] != []: ##primary
bamS.add(trioH[tid]['Normal'][0])
bamS.add(trioH[tid]['Primary'][0])
if trioH[tid]['recur_id'] != []: ##recurrent
for recur in range(len(trioH[tid]['Recurrent'])):
bamS.add(trioH[tid]['Recurrent'][recur])
sampN = trioH[tid]['prim_id'][0]
cmd = '/usr/bin/python %s/NGS/pipeline/pipe_s_xsq2phylotree.py -i %s -n %s -p %s -c %s -s %s -g %s' % (
mysetting.SRC_HOME, ','.join(
list(bamS)), sampN, projectN, False, server, genome)
print cmd
if pbs:
log = '%s/%s.Xsq2phylotree.qlog' % (storageBase + projectN + '/' +
sampN, sampN)
os.system('echo "%s" | qsub -q %s -N x2phylotree_%s -o %s -j oe' %
(cmd, server, sampN, log))
else:
log = '%s/%s.Xsq2phylotree.qlog' % (storageBase + projectN, sampN)
os.system('(%s) 2> %s' % (cmd, log))
def main(trioFileN, projectN, tidL=[], clean=False, pbs=False, server='smc1', genome='hg19'):
storageBase = os.path.dirname(mypipe.prepare_baseDir(projectN, mkdir=False)) + '/'
apacheBase = storageBase
if glob(storageBase+projectN):
print ('File directory: already exists')
else:
os.system('mkdir %s/%s; \
chmod a+w %s/%s' % (storageBase,projectN, storageBase,projectN))
print ('File directory: created')
if glob(apacheBase+projectN):
print ('Log directory: already exists')
else:
os.system('mkdir %s/%s; \
chmod a+w %s/%s' % (apacheBase,projectN, apacheBase,projectN))
print ('Log directory: created')
bamDirL = mysetting.wxsBamDirL
trioH = mypipe.read_trio(trioFileN, bamDirL, tidL)
## assume 1 primary & normal per trio
for tid in trioH:
if tidL != [] and tid not in tidL:
continue
if trioH[tid]['Normal'] == []:
continue
if trioH[tid]['prim_id'] != []: ##primary
sampN = trioH[tid]['prim_id'][0]
print tid, trioH[tid]['Primary']
tumor = trioH[tid]['Primary'][0]
normal = trioH[tid]['Normal'][0]
cmd = '/usr/bin/python %s/NGS/pipeline/pipe_s_xsq2somatic.py -i %s -j %s -n %s -p %s -c %s -s %s -g %s' % (mysetting.SRC_HOME, tumor, normal, sampN, projectN, False, server, genome)
print cmd
if pbs:
log = '%s/%s.Xsq2somatic.qlog' % (storageBase+projectN+'/'+sampN,sampN)
os.system('echo "%s" | qsub -q %s -N x2somatic_%s -o %s -j oe' % (cmd, server, sampN, log))
else:
log = '%s/%s.Xsq2somatic.qlog' % (storageBase+projectN, sampN)
os.system('(%s) 2> %s' % (cmd, log))
if trioH[tid]['recur_id'] != []: ##recurrent
for recur in range(len(trioH[tid]['Recurrent'])):
sampN = trioH[tid]['recur_id'][recur]
tumor = trioH[tid]['Recurrent'][recur]
normal = trioH[tid]['Normal'][0]
cmd = '/usr/bin/python %s/NGS/pipeline/pipe_s_xsq2somatic.py -i %s -j %s -n %s -p %s -c %s -s %s -g %s' % (mysetting.SRC_HOME, tumor, normal, sampN, projectN, False, server, genome)
print cmd
if pbs:
log = '%s/%s.Xsq2somatic.qlog' % (storageBase+projectN+'/'+sampN,sampN)
os.system('echo "%s" | qsub -q %s -N x2somatic_%s -o %s -j oe' % (cmd, server, sampN, log))
else:
log = '%s/%s.Xsq2somatic.qlog' % (storageBase+projectN, sampN)
os.system('(%s) 2> %s' % (cmd, log))
def main(trioFileN, projectN, clean=False, pbs=False, server='smc1', genome='hg19', sampL=[]):
storageBase = os.path.dirname(mypipe.prepare_baseDir(projectN, mkdir=False)) + '/'
apacheBase = storageBase
if glob(storageBase+projectN):
print ('File directory: already exists')
else:
os.system('mkdir %s/%s; \
chmod a+w %s/%s' % (storageBase,projectN, storageBase,projectN))
print('File directory: created')
if glob(apacheBase+projectN):
print ('Log directory: already exists')
else:
os.system('mkdir %s/%s; \
chmod a+w %s/%s' % (apacheBase,projectN, apacheBase,projectN))
print('Log directory: created')
bamDirL = mysetting.wxsBamDirL
trioH = mypipe.read_trio(trioFileN, bamDirL)
## assume 1 primary & normal per trio
for tid in trioH:
## must have normal sample
if trioH[tid]['norm_id'] == []:
continue
norm_id = trioH[tid]['norm_id'][0]
# if norm_id == 'S567_B_SS': ## id flip for mutscan(B)
# norm_id = 'S567_T_SS'
mutscanN = ''
for dir in mysetting.wxsMutscanDirL:
mutscanL = os.popen('find %s -name %s*.mutscan' % (dir, norm_id)).readlines()
if len(mutscanL) > 0:
mutscanN = mutscanL[0].rstrip()
break
if mutscanN == '': ## .mutscan not found
print norm_id
sys.stderr.write('Can\'t find .mutscan\n')
# sys.exit(1)
continue
if trioH[tid]['prim_id'] != []:
sampN = trioH[tid]['prim_id'][0]
if sampL == [] or (sampL != [] and sampN in sampL):
procN = ''
for dir in mysetting.wxsPileupProcDirL:
id = sampN
# if sampN == 'S567_T_SS': ## id flip for pileup_proc
# id = 'S567_B_SS'
fileL = os.popen('find %s -name %s*chr*.pileup_proc' % (dir, id)).readlines()
if len(fileL) > 0:
procDir = list(set(map(lambda x: os.path.dirname(x.rstrip()), fileL)))[0]
procN = '%s/%s*chr*.pileup_proc' % (procDir,id)
break
if procN == '': ## .pileup_proc not found
sys.stderr.write('Can\'t find .pileup_proc\n')
sys.exit(1)
cnN = os.popen('find %s -name %s*.ngCGH.seg' % (mysetting.wxsCNADir,sampN)).readlines()[0].rstrip()
cmd = '/usr/bin/python %s/NGS/pipeline/pipe_s_xsq2purity.py -i \'%s\' -j %s -k %s -n %s -p %s -c %s -s %s -g %s' % (mysetting.SRC_HOME, procN, mutscanN, cnN, sampN, projectN, clean, server, genome)
print sampN
print procN, mutscanN, cnN
if pbs:
log = '%s/%s.Xsq2purity.qlog' % (storageBase+projectN+'/'+sampN,sampN)
os.system('echo "%s" | qsub -q %s -N x2purity_%s -o %s -j oe' % (cmd, server, sampN, log))
else:
log = '%s/%s.Xsq2purity.qlog' % (storageBase+projectN, sampN)
os.system('(%s) 2> %s' % (cmd, log))
## primary of pair
if trioH[tid]['recur_id'] != []:
for recur in range(len(trioH[tid]['Recurrent'])):
sampN = trioH[tid]['recur_id'][recur]
if sampL == [] or (sampL != [] and sampN in sampL):
procN = ''
for dir in mysetting.wxsPileupProcDirL:
fileL = os.popen('find %s -name %s*chr*.pileup_proc' % (dir, sampN)).readlines()
if len(fileL) > 0:
procDir = list(set(map(lambda x: os.path.dirname(x.rstrip()), fileL)))[0]
procN = '%s/%s*chr*.pileup_proc' % (procDir,sampN)
break
if procN == '': ## .pileup_proc not found
sys.stderr.write('Can\'t find .pileup_proc\n')
sys.exit(1)
cnN = os.popen('find %s -name %s*.ngCGH.seg' % (mysetting.wxsCNADir,sampN)).readlines()[0].rstrip()
cmd = '/usr/bin/python %s/NGS/pipeline/pipe_s_xsq2purity.py -i \'%s\' -j %s -k %s -n %s -p %s -c %s -s %s -g %s' % (mysetting.SRC_HOME, procN, mutscanN, cnN, sampN, projectN, clean, server, genome)
print sampN
print procN, mutscanN, cnN
if pbs:
log = '%s/%s.Xsq2purity.qlog' % (storageBase+projectN+'/'+sampN,sampN)
os.system('echo "%s" | qsub -q %s -N x2purity_%s -o %s -j oe' % (cmd, server, sampN, log))
else:
log = '%s/%s.Xsq2purity.qlog' % (storageBase+projectN, sampN)
os.system('(%s) 2> %s' % (cmd, log))
#!/usr/bin/python
import sys, os, re
import mysetting, mybasic
mybasic.add_module_path(['NGS/pipeline','NGS/mutation'])
import mutect_batch, somaticindeldetector_batch
import mypipe
bamDirL = mysetting.wxsBamDirL
trioH = mypipe.read_trio('/EQL1/NSL/clinical/trio_info.txt', bamDirL)
#for tid in sorted(trioH.keys()):
# if tid not in ['59','60','61']:
# continue
# print tid, trioH[tid]['prim_id'], trioH[tid]['recur_id']
# for role in ['Normal','Primary','Recurrent']:
# print role,trioH[tid][role]
#sys.exit(1)
outDir='/EQL3/pipeline/somatic_mutect'
## assume 1 primary & normal per trio
for tid in trioH:
if trioH[tid]['norm_id'] == []:
continue
if tid not in ['63']:
continue
norm = trioH[tid]['norm_id'][0]
colL = line.rstrip().split('\t')
rm = re.match('(chr[^:]*):([0-9]*)~([0-9]*)', colL[idxH['locus']])
(chr,chrSta,chrEnd) = rm.groups()
ref = colL[idxH['ref']]
alt = colL[idxH['alt']]
if (chr,chrSta,chrEnd,ref,alt) not in annotH:
annotH[(chr,chrSta,chrEnd,ref,alt)] = {}
for col in ['gene_symL','ch_dna','ch_aa','ch_type','cosmic','mutsig']:
annotH[(chr,chrSta,chrEnd,ref,alt)][col] = colL[idxH[col]]
return annotH
### until it is merged into pipeline
import mybasic
mybasic.add_module_path(['NGS/pipeline'])
import mypipe
trioH = mypipe.read_trio(bamDirL=mysetting.wxsBamDirL)
pairH = {}
for tid in trioH:
if trioH[tid]['recur_id'] != []:
pid = trioH[tid]['prim_id'][0][:-5]
pairH[pid] = map(lambda x: x[:-5], trioH[tid]['recur_id'])
####
#(con,cursor) = mymysql.connectDB(db='ircr1')
#tag = 'pair_R:%'
#cursor.execute('select distinct samp_id from sample_tag where tag like "%s"' % tag)
#sIdL_p = [x for (x,) in cursor.fetchall()]
#
#tag = 'XSeq%%,N'
#cursor.execute('select distinct samp_id from sample_tag where tag like "%s"' % tag)
#wxsL = [x for (x,) in cursor.fetchall()]
#
def diff_batch(trioFileN, tidL=[]):
bamDirL = mysetting.wxsBamDirL
trioH = mypipe.read_trio(trioFileN, bamDirL, tidL)
for tid in trioH:
if tidL != [] and tid not in tidL:
continue
if trioH[tid]['Normal'] == [] or trioH[tid]['prim_id'] == [] or trioH[tid]['recur_id'] == []:
continue
datH = {}
for ref in ['C','T']:
for alt in ['A','C','G','T']:
if alt == ref:
continue
mut = '%s>%s' % (ref, alt)
for a in ['A','C','G','T']:
for b in ['A','C','G','T']:
context = a + ref + b
datH[(mut, context)] = {'prim':0.0, 'recur':0.0, 'delta':0.0}
#for b
#for a
#for alt
#for ref
print tid, trioH[tid]['prim_id'], trioH[tid]['recur_id']
for rid in trioH[tid]['recur_id']:
pid = trioH[tid]['prim_id'][0]
p_file = '/EQL3/pipeline/somatic_mutation/%s/%s.mutation_signature.txt' % (pid,pid)
r_file = '/EQL3/pipeline/somatic_mutation/%s/%s.mutation_signature.txt' % (rid,rid)
if os.path.isfile(p_file) and os.path.isfile(r_file):
print p_file
inFile = open(p_file, 'r')
inFile.readline()
for line in inFile:
colL = line.rstrip().split('\t')
mut = colL[1]
context = colL[2]
frac = float(colL[3])/float(colL[5])
datH[(mut,context)]['prim'] = frac
#for line
inFile.close()
print r_file
inFile = open(r_file, 'r')
inFile.readline()
for line in inFile:
colL = line.rstrip().split('\t')
mut = colL[1]
context = colL[2]
frac = float(colL[3])/float(colL[5])
datH[(mut,context)]['recur'] = frac
#for line
inFile.close()
# ofileN = '/EQL3/pipeline/somatic_mutation/%s/%s.mutation_signature_diff.txt' % (rid,rid)
# outFile = open(ofileN, 'w')
# outFile.write('prim_id\trecur_id\tmutation\tcontext\tp_frac\tr_frac\tdelta\n')
# for key in datH:
# (mut, context) = key
# datH[key]['delta'] = datH[key]['recur'] - datH[key]['prim']
# outFile.write('%s\t%s\t%s\t%s\t%s\t%s\t%s\n' % (pid, rid, mut, context, datH[key]['prim'], datH[key]['recur'], datH[key]['delta']))
# outFile.flush()
# outFile.close()
os.system('Rscript %s/NGS/mutation/mutect_mutation_signature_diff_plot.R %s %s' % (mysetting.SRC_HOME, pid, rid))