def sort_bdg(self, core_num=4):
sh_file =\
"%s/s10.sortbdg.sh" % (self.scripts)
sh_work_repPeak_file =\
"%s/s10.1.sortbdg.repPeak_work.sh" % (self.scripts)
sh_work_mrgPeak_file =\
"%s/s10.2.sortbdg.mrgPeak_work.sh" % (self.scripts)
sh_work_repBroadPeak_file =\
"%s/s10.3.sortbdg.repBroadPeak_work.sh" % (self.scripts)
sh_work_mrgBroadPeak_file =\
"%s/s10.4.sortbdg.mrgBroadPeak_work.sh" % (self.scripts)
l_sh_info = self.s10_sortbdg()
l_sh_work_repPeak = []
l_sh_work_mrgPeak = []
l_sh_work_repBroadPeak = []
l_sh_work_mrgBroadPeak = []
for merge_name in set(self.samInfo_pd_ChIP['merge_name']):
idx = (self.samInfo_pd_ChIP['merge_name'] == merge_name)
if self.__is_input(idx):
continue
l_brief = list(self.samInfo_pd_ChIP[idx]['brief_name'])
for brief in l_brief:
l_sh_work_repBroadPeak.append("sh %s %s %s" %\
(sh_file, brief, self.dir_BroadPeak_rep))
l_sh_work_mrgBroadPeak.append("sh %s %s %s" %\
(sh_file, merge_name, self.dir_BroadPeak_mrg))
for brief in l_brief:
l_sh_work_repPeak.append("sh %s %s %s" %\
(sh_file, brief, self.dir_Peak_rep))
l_sh_work_mrgPeak.append("sh %s %s %s" %\
(sh_file, merge_name, self.dir_Peak_mrg))
my_job_repPeak = m_jobs.run_jobs(sh_file, \
sh_work_repPeak_file, l_sh_info, l_sh_work_repPeak)
my_job_mrgPeak = m_jobs.run_jobs(sh_file, \
sh_work_mrgPeak_file, l_sh_info, l_sh_work_mrgPeak)
my_job_repBroadPeak = m_jobs.run_jobs(sh_file, \
sh_work_repBroadPeak_file, l_sh_info, l_sh_work_repBroadPeak)
my_job_mrgBroadPeak = m_jobs.run_jobs(sh_file, \
sh_work_mrgBroadPeak_file, l_sh_info, l_sh_work_mrgBroadPeak)
my_job_repPeak.running_multi(cpu=core_num, is_debug=self.is_debug)
my_job_mrgPeak.running_multi(cpu=core_num, is_debug=self.is_debug)
my_job_repBroadPeak.running_multi(cpu=core_num, is_debug=self.is_debug)
my_job_mrgBroadPeak.running_multi(cpu=core_num, is_debug=self.is_debug)
def density_baseLevel( self ):
sh_file = "%s/s16.densityBaseLv.sh" % (self.scripts)
sh_rep_work_file = "%s/s16.densityBaseLvRep_work.sh" % (self.scripts)
sh_mrg_work_file = "%s/s16.densityBaseLvMrg_work.sh" % (self.scripts)
l_brief = self.samInfo_pd_ChIP['brief_name']
l_merge = set(self.samInfo_pd_ChIP['merge_name'])
l_sh_info = self.s16_densityBaselv()
l_sh_rep_work = []
l_sh_mrg_work = []
for brief_name in l_brief:
idx =(self.samInfo_pd_ChIP['brief_name'] == brief_name)
if self.__is_input(idx):
continue
l_sh_rep_work.append("sh %s %s %s %s" %
(sh_file, brief_name, self.ref, self.dir_Peak_rep)
)
for merge_name in l_merge:
idx =(self.samInfo_pd_ChIP['merge_name'] == merge_name)
if self.__is_input(idx):
continue
l_sh_mrg_work.append("sh %s %s %s %s" %
(sh_file, merge_name, self.ref, self.dir_Peak_mrg)
)
my_job_rep = m_jobs.run_jobs(sh_file, sh_rep_work_file, l_sh_info, l_sh_rep_work)
my_job_rep.running_multi(cpu=8, is_debug = self.is_debug)
my_job_mrg = m_jobs.run_jobs(sh_file, sh_mrg_work_file, l_sh_info, l_sh_mrg_work)
my_job_mrg.running_multi(cpu=8, is_debug = self.is_debug)
def make_igv_broad(self, core_num=4):
sh_file = "%s/s11.makeIGV_broad.sh" %\
(self.scripts)
sh_work_repPeak_file = "%s/s11.3.makeIGV.repBroadPeak_work.sh" %\
(self.scripts)
sh_work_mrgPeak_file = "%s/s11.4.makeIGV.mrgBroadPeak_work.sh" %\
(self.scripts)
l_sh_info = self.s11_makeIGV_broad()
l_sh_work_rep = []
l_sh_work_mrg = []
for merge_name in set(self.samInfo_pd_ChIP['merge_name']):
idx = (self.samInfo_pd_ChIP['merge_name'] == merge_name)
if self.__is_input(idx):
continue
m01.make_dir([self.dir_BroadPeak_TDF, merge_name])
l_brief = list(self.samInfo_pd_ChIP[idx]['brief_name'])
for brief in l_brief:
l_sh_work_rep.append("sh %s %s %s %s" %\
(sh_file, brief, merge_name, self.dir_BroadPeak_rep))
l_sh_work_mrg.append("sh %s %s %s %s" %\
(sh_file, merge_name, merge_name, self.dir_BroadPeak_mrg))
my_job_rep = m_jobs.run_jobs(sh_file, sh_work_repPeak_file, \
l_sh_info, l_sh_work_rep)
my_job_mrg = m_jobs.run_jobs(sh_file, sh_work_mrgPeak_file, \
l_sh_info, l_sh_work_mrg)
my_job_rep.running_multi(cpu=core_num, is_debug=self.is_debug)
my_job_mrg.running_multi(cpu=core_num, is_debug=self.is_debug)
def make_igv_broad(self):
sh_file = "%s/s11.makeIGV_broad.sh" %\
(self.scripts)
sh_work_repPeak_file = "%s/s11.3.makeIGV.repBroadPeak_work.sh" %\
(self.scripts)
sh_work_mrgPeak_file = "%s/s11.4.makeIGV.mrgBroadPeak_work.sh" %\
(self.scripts)
l_sh_info = self.s11_makeIGV_broad()
l_sh_work_rep = []
l_sh_work_mrg = []
for merge_name in set(self.samInfo_pd_ChIP['merge_name']):
idx = (self.samInfo_pd_ChIP['merge_name'] == merge_name)
if self.__is_input(idx):
continue
m01.make_dir([self.dir_BroadPeak_TDF, merge_name])
l_brief = list(self.samInfo_pd_ChIP[idx]['brief_name'])
for brief in l_brief:
l_sh_work_rep.append("sh %s %s %s %s" %\
(sh_file, brief, merge_name, self.dir_BroadPeak_rep))
l_sh_work_mrg.append("sh %s %s %s %s" %\
(sh_file, merge_name, merge_name, self.dir_BroadPeak_mrg))
my_job_rep = m_jobs.run_jobs(sh_file, sh_work_repPeak_file, \
l_sh_info, l_sh_work_rep)
my_job_mrg = m_jobs.run_jobs(sh_file, sh_work_mrgPeak_file, \
l_sh_info, l_sh_work_mrg)
my_job_rep.running_multi(cpu=8, is_debug=self.is_debug)
my_job_mrg.running_multi(cpu=8, is_debug=self.is_debug)
def run_anno_peak(self,
TSS_genebody_up,
TSS_genebody_down,
TSS_promoter_up,
TSS_promoter_down,
ext_binlen=50,
body_bincnt=100,
tss_binlen=1):
sh_file = "%s/s12.PeakGeneRegion.sh" % (self.scripts)
sh_work_file = "%s/s12.PeakGeneRegion_work.sh" % (self.scripts)
l_sh_info = self.s12_PeakGeneRegion(TSS_genebody_up,
TSS_genebody_down,
TSS_promoter_up,
TSS_promoter_down,
ext_binlen=50,
body_bincnt=100,
tss_binlen=1)
l_sh_work = []
for merge_name in set(self.samInfo_pd_ChIP['merge_name']):
m01.make_dir([self.dir_Peak_mrg_TSS, merge_name])
m01.make_dir([self.dir_Peak_mrg_Gene, merge_name])
l_sh_work.append("sh %s %s" % (sh_file, merge_name))
my_job = m_jobs.run_jobs(sh_file, sh_work_file, l_sh_info, l_sh_work)
my_job.running_multi(cpu=8, is_debug=self.is_debug)
def merge_RPKM_uniq( self ):
m01.make_dir([ self.dir_RPM_mrg ])
sh_file = "%s/s15.MergeRPKM.sh" % (self.scripts)
sh_work_file = "%s/s15.1.MergeRPKM_work.sh" % (self.scripts)
l_brief = self.samInfo_pd_ChIP['brief_name']
l_merge = set(self.samInfo_pd_ChIP['merge_name'])
l_sh_info = self.s15_merge_RPKM()
l_sh_work = []
for window in [ "100","1kb" ]:
for ltype in ["rep","mrg"]:
l_sam = l_brief
RPKM_dir = self.dir_RPM_bins_rep
if ltype == "mrg":
l_sam = l_merge
RPKM_dir = self.dir_RPM_bins_mrg
header = "\"#chr\\tbeg\\tend\\t%s\"" % ("\\t".join(l_sam))
l_RPKM_file = [
"%s/%s/%s.RPKM.uniq.%s" %\
(RPKM_dir,sam,sam,window) for sam in l_sam
]
l_sh_work.append(
"sh %s %s %s %s %s" %\
(sh_file, header, window, ltype, " ".join(l_RPKM_file))
)
my_job = m_jobs.run_jobs(sh_file, sh_work_file, l_sh_info, l_sh_work)
my_job.running_multi(cpu=8, is_debug = self.is_debug)
def run_macs_rep( self, pvalue=0.001, ref="hs" ):
sh_file = "%s/s06.1.macs2PeakRep.sh" % (self.scripts)
sh_work_file = "%s/s06.1.macs2PeakRep_work.sh" % (self.scripts)
l_sh_info = self.s06_1_macs2PeakRep( ref )
l_sh_work = []
for brief_name in self.samInfo_pd_ChIP['brief_name']:
idx =(self.samInfo_pd_ChIP['brief_name'] == brief_name)
if self.__is_input(idx):
continue
m01.make_dir([self.dir_Peak_rep, brief_name])
ctrl_name = self.samInfo_pd_ChIP[ idx ]['control'].values[0]
shift_size = 300
f_shiftSize = "%s/%s/out/out.tab" %\
(self.dir_spp_rep_shiftSize, brief_name )
if os.path.isfile( f_shiftSize ):
val = get_shiftSize( f_shiftSize )
if val > 0:
shift_size = val
l_sh_work.append("sh %s %s %s %f %d" %\
(sh_file, brief_name, ctrl_name, pvalue, shift_size))
my_job = m_jobs.run_jobs(sh_file, sh_work_file, l_sh_info, l_sh_work)
my_job.running_multi(cpu=8, is_debug=self.is_debug)
def run_macs_rep(self, pvalue=0.001, ref="hs", core_num=4):
sh_file = "%s/s06.1.macs2PeakRep.sh" % (self.scripts)
sh_work_file = "%s/s06.1.macs2PeakRep_work.sh" % (self.scripts)
l_sh_info = self.s06_1_macs2PeakRep(ref)
l_sh_work = []
for brief_name in self.samInfo_pd_ChIP['brief_name']:
idx = (self.samInfo_pd_ChIP['brief_name'] == brief_name)
if self.__is_input(idx):
continue
m01.make_dir([self.dir_Peak_rep, brief_name])
ctrl_name = self.samInfo_pd_ChIP[idx]['control'].values[0]
shift_size = 300
f_shiftSize = "%s/%s/out/out.tab" %\
(self.dir_spp_rep_shiftSize, brief_name )
if os.path.isfile(f_shiftSize):
val = get_shiftSize(f_shiftSize)
if val > 0:
shift_size = val
l_sh_work.append("sh %s %s %s %f %d" %\
(sh_file, brief_name, ctrl_name, pvalue, shift_size))
my_job = m_jobs.run_jobs(sh_file, sh_work_file, l_sh_info, l_sh_work)
my_job.running_multi(cpu=core_num, is_debug=self.is_debug)
def merge_RPKM_uniq(self):
m01.make_dir([self.dir_RPM_mrg])
sh_file = "%s/s15.MergeRPKM.sh" % (self.scripts)
sh_work_file = "%s/s15.1.MergeRPKM_work.sh" % (self.scripts)
l_brief = self.samInfo_pd_ChIP['brief_name']
l_merge = set(self.samInfo_pd_ChIP['merge_name'])
l_sh_info = self.s15_merge_RPKM()
l_sh_work = []
for window in ["100", "1kb"]:
for ltype in ["rep", "mrg"]:
l_sam = l_brief
RPKM_dir = self.dir_RPM_bins_rep
if ltype == "mrg":
l_sam = l_merge
RPKM_dir = self.dir_RPM_bins_mrg
header = "\"#chr\\tbeg\\tend\\t%s\"" % ("\\t".join(l_sam))
l_RPKM_file = [
"%s/%s/%s.RPKM.uniq.%s" %\
(RPKM_dir,sam,sam,window) for sam in l_sam
]
l_sh_work.append(
"sh %s %s %s %s %s" %\
(sh_file, header, window, ltype, " ".join(l_RPKM_file))
)
my_job = m_jobs.run_jobs(sh_file, sh_work_file, l_sh_info, l_sh_work)
my_job.running_multi(cpu=8, is_debug=self.is_debug)
def __get_rmsk(self):
sh_file = "%s/db04.rmsk.sh" % (self.scripts)
sh_work_file = "%s/db04.rmsk_work.sh" % (self.scripts)
l_sh_info = self.db_04_rmsk()
l_sh_work = []
l_sh_work.append("sh %s %s" % (sh_file,self.ref))
my_job = m_jobs.run_jobs(sh_file, sh_work_file, l_sh_info, l_sh_work)
my_job.running_multi(cpu=8, is_debug = self.is_debug)
def __get_ref_fasta(self):
sh_file = "%s/db01.DownloadRef.sh" % (self.scripts)
sh_work_file = "%s/db01.DownloadRef_work.sh" % (self.scripts)
l_sh_info = self.db_01_DownloadRef()
l_sh_work = []
l_sh_work.append("sh %s %s" % (sh_file,self.ref))
my_job = m_jobs.run_jobs(sh_file, sh_work_file, l_sh_info, l_sh_work)
my_job.running_multi(cpu=8, is_debug = self.is_debug)
def __get_ref_index(self):
sh_file = "%s/db02.RefIndex.sh" % (self.scripts)
sh_work_file = "%s/db02.RefIndex_work.sh" % (self.scripts)
l_sh_info = self.db_02_BuildRefIndex()
l_sh_work = []
l_sh_work.append("sh %s %s" % (sh_file,self.ref))
my_job = m_jobs.run_jobs(sh_file, sh_work_file, l_sh_info, l_sh_work)
my_job.running_multi(cpu=8, is_debug = self.is_debug)
def __get_rmsk(self):
sh_file = "%s/db04.rmsk.sh" % (self.scripts)
sh_work_file = "%s/db04.rmsk_work.sh" % (self.scripts)
l_sh_info = self.db_04_rmsk()
l_sh_work = []
l_sh_work.append("sh %s %s" % (sh_file, self.ref))
my_job = m_jobs.run_jobs(sh_file, sh_work_file, l_sh_info, l_sh_work)
my_job.running_multi(cpu=8, is_debug=self.is_debug)
def __get_ref_fasta(self):
sh_file = "%s/db01.DownloadRef.sh" % (self.scripts)
sh_work_file = "%s/db01.DownloadRef_work.sh" % (self.scripts)
l_sh_info = self.db_01_DownloadRef()
l_sh_work = []
l_sh_work.append("sh %s %s" % (sh_file, self.ref))
my_job = m_jobs.run_jobs(sh_file, sh_work_file, l_sh_info, l_sh_work)
my_job.running_multi(cpu=8, is_debug=self.is_debug)
def __get_ref_index(self):
sh_file = "%s/db02.RefIndex.sh" % (self.scripts)
sh_work_file = "%s/db02.RefIndex_work.sh" % (self.scripts)
l_sh_info = self.db_02_BuildRefIndex()
l_sh_work = []
l_sh_work.append("sh %s %s" % (sh_file, self.ref))
my_job = m_jobs.run_jobs(sh_file, sh_work_file, l_sh_info, l_sh_work)
my_job.running_multi(cpu=8, is_debug=self.is_debug)
def __get_region(sefl, query):
sh_file = "%s/db05.repeat.sh" % (self.scripts)
sh_work_file = "%s/db05.repeat_work.sh" % (self.scripts)
l_sh_info = self.db_05_Region(query)
l_sh_work = []
l_sh_work.append("sh %s %s" % (sh_file, self.ref))
my_job = m_jobs.run_jobs(sh_file, sh_work_file, l_sh_info, l_sh_work)
my_job.running_multi(cpu=8, is_debug=self.is_debug)
# my_job.running_SGE(vf="400m", maxjob=100, is_debug = self.is_debug)
def merge_density_100bp(self, core_num=4):
m01.make_dir([self.dir_RPM_mrg])
sh_file = "%s/s17.MergeDensity.sh" % (self.scripts)
sh_work_file = "%s/s17.MergeDensity_work.sh" % (self.scripts)
l_brief = self.samInfo_pd_ChIP['brief_name']
l_merge = set(self.samInfo_pd_ChIP['merge_name'])
l_brief2 = []
for brief_name in l_brief:
idx = (self.samInfo_pd_ChIP['brief_name'] == brief_name)
if self.__is_input(idx):
continue
l_brief2.append(brief_name)
l_merge2 = []
for merge_name in l_merge:
idx = (self.samInfo_pd_ChIP['merge_name'] == merge_name)
if self.__is_input(idx):
continue
l_merge2.append(merge_name)
l_brief = l_brief2
l_merge = l_merge2
l_sh_info = self.s17_merge_RPKM()
l_sh_work = []
for ltype in ["rep", "mrg"]:
l_sam = l_brief
RPKM_dir = self.dir_Peak_rep
if ltype == "mrg":
l_sam = l_merge
RPKM_dir = self.dir_Peak_mrg
header = "\"#chr\\tbeg\\tend\\t%s\"" % ("\\t".join(l_sam))
l_RPKM_file = [
"%s/%s/%s.1kb.norm_avg.xls" %\
(RPKM_dir, sam, sam) for sam in l_sam
]
l_sh_work.append(
"sh %s %s %s %s %s" %\
(sh_file, header, "1kb", ltype, " ".join(l_RPKM_file))
)
my_job = m_jobs.run_jobs(sh_file, sh_work_file, l_sh_info, l_sh_work)
my_job.running_multi(cpu=core_num, is_debug=self.is_debug)
def merge_density_100bp(self):
m01.make_dir([ self.dir_RPM_mrg ])
sh_file = "%s/s17.MergeDensity.sh" % (self.scripts)
sh_work_file = "%s/s17.MergeDensity_work.sh" % (self.scripts)
l_brief = self.samInfo_pd_ChIP['brief_name']
l_merge = set(self.samInfo_pd_ChIP['merge_name'])
l_brief2 = []
for brief_name in l_brief:
idx =(self.samInfo_pd_ChIP['brief_name'] == brief_name)
if self.__is_input(idx):
continue
l_brief2.append(brief_name)
l_merge2 = []
for merge_name in l_merge:
idx =(self.samInfo_pd_ChIP['merge_name'] == merge_name)
if self.__is_input(idx):
continue
l_merge2.append(merge_name)
l_brief = l_brief2
l_merge = l_merge2
l_sh_info = self.s17_merge_RPKM()
l_sh_work = []
for ltype in ["rep","mrg"]:
l_sam = l_brief
RPKM_dir = self.dir_Peak_rep
if ltype == "mrg":
l_sam = l_merge
RPKM_dir = self.dir_Peak_mrg
header = "\"#chr\\tbeg\\tend\\t%s\"" % ("\\t".join(l_sam))
l_RPKM_file = [
"%s/%s/%s.1kb.norm_avg.xls" %\
(RPKM_dir, sam, sam) for sam in l_sam
]
l_sh_work.append(
"sh %s %s %s %s %s" %\
(sh_file, header, "1kb", ltype, " ".join(l_RPKM_file))
)
my_job = m_jobs.run_jobs(sh_file, sh_work_file, l_sh_info, l_sh_work)
my_job.running_multi(cpu=8, is_debug = self.is_debug)
def density_baseLevel(self, core_num=4):
sh_file = "%s/s16.densityBaseLv.sh" % (self.scripts)
sh_rep_work_file = "%s/s16.densityBaseLvRep_work.sh" % (self.scripts)
sh_mrg_work_file = "%s/s16.densityBaseLvMrg_work.sh" % (self.scripts)
l_brief = self.samInfo_pd_ChIP['brief_name']
l_merge = set(self.samInfo_pd_ChIP['merge_name'])
l_sh_info = self.s16_densityBaselv()
l_sh_rep_work = []
l_sh_mrg_work = []
for brief_name in l_brief:
idx = (self.samInfo_pd_ChIP['brief_name'] == brief_name)
if self.__is_input(idx):
continue
l_sh_rep_work.append(
"sh %s %s %s %s" %
(sh_file, brief_name, self.ref, self.dir_Peak_rep))
for merge_name in l_merge:
idx = (self.samInfo_pd_ChIP['merge_name'] == merge_name)
if self.__is_input(idx):
continue
l_sh_mrg_work.append(
"sh %s %s %s %s" %
(sh_file, merge_name, self.ref, self.dir_Peak_mrg))
my_job_rep = m_jobs.run_jobs(sh_file, sh_rep_work_file, l_sh_info,
l_sh_rep_work)
my_job_rep.running_multi(cpu=core_num, is_debug=self.is_debug)
my_job_mrg = m_jobs.run_jobs(sh_file, sh_mrg_work_file, l_sh_info,
l_sh_mrg_work)
my_job_mrg.running_multi(cpu=core_num, is_debug=self.is_debug)
def run_QC(self):
sh_file = "%s/s01.QC.sh" % (self.scripts)
sh_work_file = "%s/s01.QC_work.sh" % (self.scripts)
l_sh_info = self.s01_QC()
l_sh_work = []
for samp in self.samInfo_pd_ChIP['sample']:
make_dir( [ self.dir_clean_data, samp ] )
idx = (self.samInfo_pd_ChIP['sample'] == samp)
end = self.samInfo_pd_ChIP[ idx ]['end_type'].values[0]
data_dype = self.M_CvtEnd[ end ]
l_sh_work.append("sh %s %s %d" % (sh_file, samp, data_dype) )
my_job = m_jobs.run_jobs(sh_file, sh_work_file, l_sh_info, l_sh_work)
my_job.running_multi(cpu=8, is_debug = self.is_debug)
def div_bed_to_bins_unique_mrg(self):
sh_file = "%s/s14.RPM_density_rep.sh" % (self.scripts)
sh_work_file = "%s/s14.RPM_density_rep_work.sh" % (self.scripts)
l_sh_info = self.s14_RPM_density_mrg()
l_sh_work = []
for merge_name in set(self.samInfo_pd_ChIP['merge_name']):
m01.make_dir([ self.dir_RPM_bins_mrg, merge_name])
mapped_reads = np.sum(self.stat_Info.StatInfo[merge_name]['q30'])
l_sh_work.append("sh %s %s %d" % (sh_file,merge_name, mapped_reads))
my_job = m_jobs.run_jobs(sh_file, sh_work_file, l_sh_info, l_sh_work)
my_job.running_multi(cpu=8, is_debug = self.is_debug)
def run_QC(self, core_num=4):
sh_file = "%s/s01.QC.sh" % (self.scripts)
sh_work_file = "%s/s01.QC_work.sh" % (self.scripts)
l_sh_info = self.s01_QC()
l_sh_work = []
for samp in self.samInfo_pd_ChIP['sample']:
make_dir( [ self.dir_clean_data, samp ] )
idx = (self.samInfo_pd_ChIP['sample'] == samp)
end = self.samInfo_pd_ChIP[ idx ]['end_type'].values[0]
data_dype = self.M_CvtEnd[ end ]
l_sh_work.append("sh %s %s %d" % (sh_file, samp, data_dype) )
my_job = m_jobs.run_jobs(sh_file, sh_work_file, l_sh_info, l_sh_work)
my_job.running_multi(cpu=core_num, is_debug = self.is_debug)
def div_bed_to_bins_unique_mrg(self):
sh_file = "%s/s14.RPM_density_rep.sh" % (self.scripts)
sh_work_file = "%s/s14.RPM_density_rep_work.sh" % (self.scripts)
l_sh_info = self.s14_RPM_density_mrg()
l_sh_work = []
for merge_name in set(self.samInfo_pd_ChIP['merge_name']):
m01.make_dir([self.dir_RPM_bins_mrg, merge_name])
mapped_reads = np.sum(self.stat_Info.StatInfo[merge_name]['q30'])
l_sh_work.append("sh %s %s %d" %
(sh_file, merge_name, mapped_reads))
my_job = m_jobs.run_jobs(sh_file, sh_work_file, l_sh_info, l_sh_work)
my_job.running_multi(cpu=8, is_debug=self.is_debug)
def get_shift_size_mrg(self, core_num=4):
sh_file = "%s/s05.2.spp_mrg_shiftSize.sh" % (self.scripts)
sh_work_file = "%s/s05.2.spp_mrg_shiftSize_work.sh" % (self.scripts)
l_sh_info = self.s05_2_spp_mrg_shiftSize()
l_sh_work = []
for merge_name in set(self.samInfo_pd_ChIP['merge_name']):
idx = (self.samInfo_pd_ChIP['merge_name'] == merge_name)
if self.__is_input(idx):
continue
m01.make_dir([self.dir_spp_mrg_shiftSize, merge_name, "test"])
m01.make_dir([self.dir_spp_mrg_shiftSize, merge_name, "out"])
l_sh_work.append("sh %s %s" % (sh_file, merge_name))
my_job = m_jobs.run_jobs(sh_file, sh_work_file, l_sh_info, l_sh_work)
my_job.running_multi(cpu=core_num, is_debug=self.is_debug)
def get_shift_size_mrg(self):
sh_file = "%s/s05.2.spp_mrg_shiftSize.sh" % (self.scripts)
sh_work_file = "%s/s05.2.spp_mrg_shiftSize_work.sh" % (self.scripts)
l_sh_info = self.s05_2_spp_mrg_shiftSize()
l_sh_work = []
for merge_name in set(self.samInfo_pd_ChIP['merge_name']):
idx =(self.samInfo_pd_ChIP['merge_name'] == merge_name)
if self.__is_input(idx):
continue
m01.make_dir([self.dir_spp_mrg_shiftSize, merge_name, "test"])
m01.make_dir([self.dir_spp_mrg_shiftSize, merge_name, "out" ])
l_sh_work.append("sh %s %s" % ( sh_file, merge_name ))
my_job = m_jobs.run_jobs(sh_file, sh_work_file, l_sh_info, l_sh_work)
my_job.running_multi(cpu=8, is_debug=self.is_debug)
def run_bwa(self, core_num=2):
sh_file = "%s/s02.bwa.sh" % (self.scripts)
sh_work_file = "%s/s02.bwa_work.sh" % (self.scripts)
l_sh_info = self.s02_bwa()
l_sh_work = []
for samp in self.samInfo_pd_ChIP['sample']:
idx =(self.samInfo_pd_ChIP['sample'] == samp)
brief_name = self.samInfo_pd_ChIP[ idx ]['brief_name'].values[0]
end = self.samInfo_pd_ChIP[ idx ]['end_type'].values[0]
data_dype = self.M_CvtEnd[ end ]
make_dir( [ self.dir_bam, brief_name ] )
l_sh_work.append(
"sh %s %s %s %d" % (sh_file, samp, brief_name, data_dype)
)
my_job = m_jobs.run_jobs(sh_file, sh_work_file, l_sh_info, l_sh_work)
my_job.running_multi(cpu=core_num, is_debug = self.is_debug)
def run_bwa(self):
sh_file = "%s/s02.bwa.sh" % (self.scripts)
sh_work_file = "%s/s02.bwa_work.sh" % (self.scripts)
l_sh_info = self.s02_bwa()
l_sh_work = []
for samp in self.samInfo_pd_ChIP['sample']:
idx =(self.samInfo_pd_ChIP['sample'] == samp)
brief_name = self.samInfo_pd_ChIP[ idx ]['brief_name'].values[0]
end = self.samInfo_pd_ChIP[ idx ]['end_type'].values[0]
data_dype = self.M_CvtEnd[ end ]
make_dir( [ self.dir_bam, brief_name ] )
l_sh_work.append(
"sh %s %s %s %d" % (sh_file, samp, brief_name, data_dype)
)
my_job = m_jobs.run_jobs(sh_file, sh_work_file, l_sh_info, l_sh_work)
my_job.running_multi(cpu=8, is_debug = self.is_debug)
def bam2repbed(self,ext_len=300):
sh_file = "%s/s03.bam2bedrep.sh" % (self.scripts)
sh_work_file = "%s/s03.bam2bedrep_work.sh" % (self.scripts)
l_sh_info = self.s03_bam2bedrep()
l_sh_work = []
make_dir( [ self.dir_bed_rep ] )
for samp in self.samInfo_pd_ChIP['sample']:
idx =(self.samInfo_pd_ChIP['sample'] == samp)
brief_name = self.samInfo_pd_ChIP[ idx ]['brief_name'].values[0]
end = self.samInfo_pd_ChIP[ idx ]['end_type'].values[0]
data_dype = self.M_CvtEnd[ end ]
l_sh_work.append("sh %s %s %s %d" % \
(sh_file, brief_name, data_dype, ext_len))
my_job = m_jobs.run_jobs(sh_file, sh_work_file, l_sh_info, l_sh_work)
my_job.running_multi(cpu=8, is_debug = self.is_debug)
def bam2repbed(self, ext_len=300, core_num=4):
sh_file = "%s/s03.bam2bedrep.sh" % (self.scripts)
sh_work_file = "%s/s03.bam2bedrep_work.sh" % (self.scripts)
l_sh_info = self.s03_bam2bedrep()
l_sh_work = []
make_dir( [ self.dir_bed_rep ] )
for samp in self.samInfo_pd_ChIP['sample']:
idx =(self.samInfo_pd_ChIP['sample'] == samp)
brief_name = self.samInfo_pd_ChIP[ idx ]['brief_name'].values[0]
end = self.samInfo_pd_ChIP[ idx ]['end_type'].values[0]
data_dype = self.M_CvtEnd[ end ]
l_sh_work.append("sh %s %s %s %d" % \
(sh_file, brief_name, data_dype, ext_len))
my_job = m_jobs.run_jobs(sh_file, sh_work_file, l_sh_info, l_sh_work)
my_job.running_multi(cpu=core_num, is_debug = self.is_debug)
def run_macs_rep_broad(self, pvalue=0.05, ref="hs", core_num=4):
sh_file = "%s/s08.macs2BroadPeakRep.sh" % (self.scripts)
sh_work_file = "%s/s08.macs2BroadPeakRep_work.sh" % (self.scripts)
l_sh_info = self.s08_macs2BroadPeakRep(ref)
l_sh_work = []
for brief_name in self.samInfo_pd_ChIP['brief_name']:
idx = (self.samInfo_pd_ChIP['brief_name'] == brief_name)
if self.__is_input(idx):
continue
m01.make_dir([self.dir_BroadPeak_rep, brief_name])
ctrl_name = self.samInfo_pd_ChIP[idx]['control'].values[0]
l_sh_work.append("sh %s %s %s %f" %\
( sh_file, brief_name, ctrl_name, pvalue ))
my_job = m_jobs.run_jobs(sh_file, sh_work_file, l_sh_info, l_sh_work)
my_job.running_multi(cpu=core_num, is_debug=self.is_debug)
def prepare_idr_input(self, top_peak=100000, core_num=4):
sh_file = "%s/s07.1.IDR_prepare.sh" % (self.scripts)
sh_work_file = "%s/s07.1.IDR_prepare_work.sh" % (self.scripts)
l_sh_info = self.s07_1_IDR_prepare()
l_sh_work = []
for merge_name in set(self.samInfo_pd_ChIP['merge_name']):
idx = (self.samInfo_pd_ChIP['merge_name'] == merge_name)
if self.__is_input(idx):
continue
m01.make_dir([self.dir_Peak_idr, merge_name])
l_brief = list(self.samInfo_pd_ChIP[idx]['brief_name'])
list_brief = " ".join(l_brief)
l_sh_work.append("sh %s %s %d %s" %
(sh_file, merge_name, top_peak, list_brief))
my_job = m_jobs.run_jobs(sh_file, sh_work_file, l_sh_info, l_sh_work)
my_job.running_multi(cpu=core_num, is_debug=self.is_debug)
def div_bed_to_bins_unique_rep(self):
sh_file = "%s/s13.RPM_density_rep.sh" % (self.scripts)
sh_work_file = "%s/s13.RPM_density_rep_work.sh" % (self.scripts)
l_sh_info = self.s13_RPM_density_rep()
l_sh_work = []
for brief_name in self.samInfo_pd_ChIP['brief_name']:
m01.make_dir([ self.dir_RPM_bins_rep, brief_name])
idx = (self.samInfo_pd_ChIP['brief_name'] == brief_name)
merge_name = self.samInfo_pd_ChIP[ idx ]['merge_name'].values[0]
l_brief = self.stat_Info.StatInfo[merge_name]['l_brief']
idx2 = l_brief.index(brief_name)
mapped_reads = self.stat_Info.StatInfo[merge_name]['q30'][idx2]
l_sh_work.append("sh %s %s %d" % (sh_file, brief_name, mapped_reads))
my_job = m_jobs.run_jobs(sh_file, sh_work_file, l_sh_info, l_sh_work)
my_job.running_multi(cpu=8, is_debug = self.is_debug)
def run_macs_rep_broad(self, pvalue=0.05, ref="hs"):
sh_file = "%s/s08.macs2BroadPeakRep.sh" % (self.scripts)
sh_work_file = "%s/s08.macs2BroadPeakRep_work.sh" % (self.scripts)
l_sh_info = self.s08_macs2BroadPeakRep( ref )
l_sh_work = []
for brief_name in self.samInfo_pd_ChIP['brief_name']:
idx =(self.samInfo_pd_ChIP['brief_name'] == brief_name)
if self.__is_input(idx):
continue
m01.make_dir([self.dir_BroadPeak_rep, brief_name])
ctrl_name = self.samInfo_pd_ChIP[idx]['control'].values[0]
l_sh_work.append("sh %s %s %s %f" %\
( sh_file, brief_name, ctrl_name, pvalue ))
my_job = m_jobs.run_jobs(sh_file, sh_work_file, l_sh_info, l_sh_work)
my_job.running_multi(cpu=8,is_debug=self.is_debug)
def mrgbed_multi(self, core_num=4):
sh_file = "%s/s04.2.bedmrg.multi.sh" % (self.scripts)
sh_work_file = "%s/s04.2.bedmrg.multi_work.sh" % (self.scripts)
l_sh_info = self.s04_2_bedmrg_multi()
l_sh_work = []
for merge_name in set(self.samInfo_pd_ChIP['merge_name']):
idx =(self.samInfo_pd_ChIP['merge_name'] == merge_name)
merged = "%s/%s" % (self.dir_bed_mrg, merge_name)
l_brief = self.samInfo_pd_ChIP[ idx ]['brief_name']
l_bed_rep = [ "%s/%s" % (self.dir_bed_rep,brief_name) \
for brief_name in l_brief ]
l_sh_work.append(
"sh %s %s %s" % ( sh_file, merged, " ".join(l_bed_rep) )
)
my_job = m_jobs.run_jobs(sh_file, sh_work_file, l_sh_info, l_sh_work)
my_job.running_multi(cpu=core_num, is_debug = self.is_debug)
def mrgbed_multi(self):
sh_file = "%s/s04.2.bedmrg.multi.sh" % (self.scripts)
sh_work_file = "%s/s04.2.bedmrg.multi_work.sh" % (self.scripts)
l_sh_info = self.s04_2_bedmrg_multi()
l_sh_work = []
for merge_name in set(self.samInfo_pd_ChIP['merge_name']):
idx =(self.samInfo_pd_ChIP['merge_name'] == merge_name)
merged = "%s/%s" % (self.dir_bed_mrg, merge_name)
l_brief = self.samInfo_pd_ChIP[ idx ]['brief_name']
l_bed_rep = [ "%s/%s" % (self.dir_bed_rep,brief_name) \
for brief_name in l_brief ]
l_sh_work.append(
"sh %s %s %s" % ( sh_file, merged, " ".join(l_bed_rep) )
)
my_job = m_jobs.run_jobs(sh_file, sh_work_file, l_sh_info, l_sh_work)
my_job.running_multi(cpu=8, is_debug = self.is_debug)
def prepare_idr_input(self, top_peak = 100000):
sh_file = "%s/s07.1.IDR_prepare.sh" % (self.scripts)
sh_work_file = "%s/s07.1.IDR_prepare_work.sh" % (self.scripts)
l_sh_info = self.s07_1_IDR_prepare()
l_sh_work = []
for merge_name in set(self.samInfo_pd_ChIP['merge_name']):
idx =(self.samInfo_pd_ChIP['merge_name'] == merge_name)
if self.__is_input(idx):
continue
m01.make_dir( [ self.dir_Peak_idr, merge_name ] )
l_brief = list(self.samInfo_pd_ChIP[ idx ]['brief_name'])
list_brief = " ".join(l_brief)
l_sh_work.append(
"sh %s %s %d %s" % (sh_file, merge_name, top_peak,list_brief)
)
my_job = m_jobs.run_jobs(sh_file, sh_work_file, l_sh_info, l_sh_work)
my_job.running_multi(cpu=8, is_debug=self.is_debug)
def div_bed_to_bins_unique_rep(self):
sh_file = "%s/s13.RPM_density_rep.sh" % (self.scripts)
sh_work_file = "%s/s13.RPM_density_rep_work.sh" % (self.scripts)
l_sh_info = self.s13_RPM_density_rep()
l_sh_work = []
for brief_name in self.samInfo_pd_ChIP['brief_name']:
m01.make_dir([self.dir_RPM_bins_rep, brief_name])
idx = (self.samInfo_pd_ChIP['brief_name'] == brief_name)
merge_name = self.samInfo_pd_ChIP[idx]['merge_name'].values[0]
l_brief = self.stat_Info.StatInfo[merge_name]['l_brief']
idx2 = l_brief.index(brief_name)
mapped_reads = self.stat_Info.StatInfo[merge_name]['q30'][idx2]
l_sh_work.append("sh %s %s %d" %
(sh_file, brief_name, mapped_reads))
my_job = m_jobs.run_jobs(sh_file, sh_work_file, l_sh_info, l_sh_work)
my_job.running_multi(cpu=8, is_debug=self.is_debug)
def run_macs_mrg_broad(self, pvalue=0.05, ref="hs", core_num=4):
sh_file = "%s/s09.macs2BroadPeakMrg.sh" % (self.scripts)
sh_work_file = "%s/s09.macs2BroadPeakMrg_work.sh" % (self.scripts)
l_sh_info = self.s09_macs2BroadPeakMrg(ref)
l_sh_work = []
for merge_name in set(self.samInfo_pd_ChIP['merge_name']):
idx = (self.samInfo_pd_ChIP['merge_name'] == merge_name)
if self.__is_input(idx):
continue
m01.make_dir([self.dir_Peak_mrg, merge_name])
ctrl_name = self.samInfo_pd_ChIP[idx]['control'].values[0]
l_sh_work.append("sh %s %s %s %f" % \
(sh_file, merge_name, ctrl_name, pvalue))
my_job = m_jobs.run_jobs(sh_file, sh_work_file, l_sh_info, l_sh_work)
my_job.running_multi(cpu=core_num, is_debug=self.is_debug)
def run_macs_mrg_broad(self, pvalue=0.05, ref="hs"):
sh_file = "%s/s09.macs2BroadPeakMrg.sh" % (self.scripts)
sh_work_file = "%s/s09.macs2BroadPeakMrg_work.sh" % (self.scripts)
l_sh_info = self.s09_macs2BroadPeakMrg(ref)
l_sh_work = []
for merge_name in set(self.samInfo_pd_ChIP['merge_name']):
idx = (self.samInfo_pd_ChIP['merge_name'] == merge_name)
if self.__is_input(idx):
continue
m01.make_dir([self.dir_Peak_mrg, merge_name])
ctrl_name = self.samInfo_pd_ChIP[idx]['control'].values[0]
l_sh_work.append("sh %s %s %s %f" % \
(sh_file, merge_name, ctrl_name, pvalue))
my_job = m_jobs.run_jobs(sh_file, sh_work_file, l_sh_info, l_sh_work)
my_job.running_multi(cpu=8, is_debug=self.is_debug)
def run_anno_peak(self,
TSS_genebody_up,TSS_genebody_down,TSS_promoter_up,
TSS_promoter_down,ext_binlen=50,body_bincnt=100,
tss_binlen=1):
sh_file = "%s/s12.PeakGeneRegion.sh" % (self.scripts)
sh_work_file = "%s/s12.PeakGeneRegion_work.sh" % (self.scripts)
l_sh_info = self.s12_PeakGeneRegion(
TSS_genebody_up,TSS_genebody_down,TSS_promoter_up,
TSS_promoter_down,ext_binlen=50,body_bincnt=100,
tss_binlen=1)
l_sh_work = []
for merge_name in set(self.samInfo_pd_ChIP['merge_name']):
m01.make_dir([ self.dir_Peak_mrg_TSS, merge_name ])
m01.make_dir([ self.dir_Peak_mrg_Gene, merge_name ])
l_sh_work.append("sh %s %s" % ( sh_file, merge_name ))
my_job = m_jobs.run_jobs(sh_file, sh_work_file, l_sh_info, l_sh_work)
my_job.running_multi(cpu=8, is_debug = self.is_debug)
def get_idr_Peak(self, core_num=4):
prefix = ".".join(self.sam_ChIPinfo.split(".")[:-1])
file_idr_out = "%s/IDR_result.%s.xls" % (self.dir_StatInfo, prefix)
f_idr_out = open(file_idr_out, "r")
sh_file = "%s/s07.3.IDR_pass_Peaks.sh" % (self.scripts)
sh_work_file = "%s/s07.3.IDR_pass_Peaks_work.sh" % (self.scripts)
l_sh_info = self.s07_3_IDR_passPeaks()
l_sh_work = []
h = f_idr_out.readline()
for line in f_idr_out:
line = line.strip()
f = line.split()
merge_name = f[0]
peak_cnt = int(f[1])
l_sh_work.append("sh %s %s %d" % (sh_file, merge_name, peak_cnt))
my_job = m_jobs.run_jobs(sh_file, sh_work_file, l_sh_info, l_sh_work)
my_job.running_multi(cpu=core_num, is_debug=self.is_debug)
def get_idr_Peak(self):
prefix = ".".join( self.sam_ChIPinfo.split(".")[:-1] )
file_idr_out= "%s/IDR_result.%s.xls" % (self.dir_StatInfo, prefix)
f_idr_out = open(file_idr_out,"r")
sh_file = "%s/s07.3.IDR_pass_Peaks.sh" % (self.scripts)
sh_work_file = "%s/s07.3.IDR_pass_Peaks_work.sh" % (self.scripts)
l_sh_info = self.s07_3_IDR_passPeaks()
l_sh_work = []
h = f_idr_out.readline()
for line in f_idr_out:
line = line.strip()
f = line.split()
merge_name= f[0]
peak_cnt = int(f[1])
l_sh_work.append("sh %s %s %d" % (sh_file, merge_name,peak_cnt))
my_job = m_jobs.run_jobs(sh_file, sh_work_file, l_sh_info, l_sh_work)
my_job.running_multi( cpu=8, is_debug = self.is_debug )
def run_idr(self, core_num=4):
sh_file = \
"%s/s07.2.IDR_usingMacs2Peak.sh" % (self.scripts)
sh_work_file_rep = \
"%s/s07.2.IDR_usingMacs2Peak_rep_work.sh" % (self.scripts)
sh_work_file_self = \
"%s/s07.2.IDR_usingMacs2Peak_selfReps_work.sh" % (self.scripts)
sh_work_file_pool = \
"%s/s07.2.IDR_usingMacs2Peak_poolReps_work.sh" % (self.scripts)
l_sh_info = self.s07_2_usingMacs2Peak()
l_sh_work_rep = []
l_sh_work_self = []
l_sh_work_pool = []
for merge_name in set(self.samInfo_pd_ChIP['merge_name']):
idx = (self.samInfo_pd_ChIP['merge_name'] == merge_name)
if self.__is_input(idx):
continue
m01.make_dir([self.dir_Peak_idr, merge_name])
l_brief = list(self.samInfo_pd_ChIP[idx]['brief_name'])
# print merge_name,l_brief,list(l_brief)
### IDR ANALYSIS ON ORIGINAL REPLICATES
subtype = "rep"
m01.make_dir([self.dir_Peak_idr, merge_name, subtype])
if len(l_brief) > 1:
for i in range(0, len(l_brief) - 1):
for j in range(i + 1, len(l_brief)):
in_sam1 = "%s" % (l_brief[i])
in_sam2 = "%s" % (l_brief[j])
l_sh_work_rep.append("sh %s %s %s %s %s" %\
(sh_file,in_sam1,in_sam2,merge_name,subtype))
### IDR ANALYSIS ON SELF-PSEUDOREPLICATES
subtype = "selfPseudoReps"
m01.make_dir([self.dir_Peak_idr, merge_name, subtype])
for sam in l_brief:
in_sam1 = "%s.pr1" % (sam)
in_sam2 = "%s.pr2" % (sam)
l_sh_work_self.append("sh %s %s %s %s %s" %\
(sh_file, in_sam1, in_sam2, merge_name, subtype))
### IDR ANALYSIS ON POOLED-PSEUDOREPLICATES
subtype = "pooledPseudoReps"
m01.make_dir([self.dir_Peak_idr, merge_name, subtype])
in_sam1 = "%s.pr1" % (merge_name)
in_sam2 = "%s.pr2" % (merge_name)
l_sh_work_pool.append("sh %s %s %s %s %s" %\
(sh_file, in_sam1, in_sam2, merge_name, subtype))
my_job_rep = m_jobs.run_jobs( \
sh_file, sh_work_file_rep, l_sh_info, l_sh_work_rep)
my_job_self = m_jobs.run_jobs( \
sh_file, sh_work_file_self, l_sh_info, l_sh_work_self)
my_job_pool = m_jobs.run_jobs( \
sh_file, sh_work_file_pool, l_sh_info, l_sh_work_pool)
my_job_rep.running_multi(cpu=core_num, is_debug=self.is_debug)
my_job_self.running_multi(cpu=core_num, is_debug=self.is_debug)
my_job_pool.running_multi(cpu=core_num, is_debug=self.is_debug)
def sort_bdg(self):
sh_file =\
"%s/s10.sortbdg.sh" % (self.scripts)
sh_work_repPeak_file =\
"%s/s10.1.sortbdg.repPeak_work.sh" % (self.scripts)
sh_work_mrgPeak_file =\
"%s/s10.2.sortbdg.mrgPeak_work.sh" % (self.scripts)
sh_work_repBroadPeak_file =\
"%s/s10.3.sortbdg.repBroadPeak_work.sh" % (self.scripts)
sh_work_mrgBroadPeak_file =\
"%s/s10.4.sortbdg.mrgBroadPeak_work.sh" % (self.scripts)
l_sh_info = self.s10_sortbdg()
l_sh_work_repPeak = []
l_sh_work_mrgPeak = []
l_sh_work_repBroadPeak = []
l_sh_work_mrgBroadPeak = []
for merge_name in set(self.samInfo_pd_ChIP['merge_name']):
idx = (self.samInfo_pd_ChIP['merge_name'] == merge_name)
if self.__is_input(idx):
continue
l_brief = list(self.samInfo_pd_ChIP[idx]['brief_name'])
for brief in l_brief:
l_sh_work_repBroadPeak.append("sh %s %s %s" %\
(sh_file, brief, self.dir_BroadPeak_rep))
l_sh_work_mrgBroadPeak.append("sh %s %s %s" %\
(sh_file, merge_name, self.dir_BroadPeak_mrg))
for brief in l_brief:
l_sh_work_repPeak.append("sh %s %s %s" %\
(sh_file, brief, self.dir_Peak_rep))
l_sh_work_mrgPeak.append("sh %s %s %s" %\
(sh_file, merge_name, self.dir_Peak_mrg))
my_job_repPeak = m_jobs.run_jobs(sh_file, \
sh_work_repPeak_file, l_sh_info, l_sh_work_repPeak)
my_job_mrgPeak = m_jobs.run_jobs(sh_file, \
sh_work_mrgPeak_file, l_sh_info, l_sh_work_mrgPeak)
my_job_repBroadPeak = m_jobs.run_jobs(sh_file, \
sh_work_repBroadPeak_file, l_sh_info, l_sh_work_repBroadPeak)
my_job_mrgBroadPeak = m_jobs.run_jobs(sh_file, \
sh_work_mrgBroadPeak_file, l_sh_info, l_sh_work_mrgBroadPeak)
my_job_repPeak.running_multi(cpu=8, is_debug=self.is_debug)
my_job_mrgPeak.running_multi(cpu=8, is_debug=self.is_debug)
my_job_repBroadPeak.running_multi(cpu=8, is_debug=self.is_debug)
my_job_mrgBroadPeak.running_multi(cpu=8, is_debug=self.is_debug)
def run_idr(self):
sh_file = \
"%s/s07.2.IDR_usingMacs2Peak.sh" % (self.scripts)
sh_work_file_rep = \
"%s/s07.2.IDR_usingMacs2Peak_rep_work.sh" % (self.scripts)
sh_work_file_self = \
"%s/s07.2.IDR_usingMacs2Peak_selfReps_work.sh" % (self.scripts)
sh_work_file_pool = \
"%s/s07.2.IDR_usingMacs2Peak_poolReps_work.sh" % (self.scripts)
l_sh_info = self.s07_2_usingMacs2Peak()
l_sh_work_rep = []
l_sh_work_self = []
l_sh_work_pool = []
for merge_name in set(self.samInfo_pd_ChIP['merge_name']):
idx =(self.samInfo_pd_ChIP['merge_name'] == merge_name)
if self.__is_input(idx):
continue
m01.make_dir([self.dir_Peak_idr, merge_name])
l_brief = list(self.samInfo_pd_ChIP[idx]['brief_name'])
# print merge_name,l_brief,list(l_brief)
### IDR ANALYSIS ON ORIGINAL REPLICATES
subtype = "rep"
m01.make_dir([self.dir_Peak_idr, merge_name, subtype])
if len(l_brief) > 1:
for i in range( 0,len(l_brief)-1 ):
for j in range( i+1,len(l_brief) ):
in_sam1 = "%s" % (l_brief[i])
in_sam2 = "%s" % (l_brief[j])
l_sh_work_rep.append("sh %s %s %s %s %s" %\
(sh_file,in_sam1,in_sam2,merge_name,subtype))
### IDR ANALYSIS ON SELF-PSEUDOREPLICATES
subtype = "selfPseudoReps"
m01.make_dir([self.dir_Peak_idr, merge_name, subtype])
for sam in l_brief:
in_sam1 = "%s.pr1" % (sam)
in_sam2 = "%s.pr2" % (sam)
l_sh_work_self.append("sh %s %s %s %s %s" %\
(sh_file, in_sam1, in_sam2, merge_name, subtype))
### IDR ANALYSIS ON POOLED-PSEUDOREPLICATES
subtype = "pooledPseudoReps"
m01.make_dir([ self.dir_Peak_idr, merge_name, subtype ])
in_sam1 = "%s.pr1" % (merge_name)
in_sam2 = "%s.pr2" % (merge_name)
l_sh_work_pool.append("sh %s %s %s %s %s" %\
(sh_file, in_sam1, in_sam2, merge_name, subtype))
my_job_rep = m_jobs.run_jobs( \
sh_file, sh_work_file_rep, l_sh_info, l_sh_work_rep)
my_job_self = m_jobs.run_jobs( \
sh_file, sh_work_file_self, l_sh_info, l_sh_work_self)
my_job_pool = m_jobs.run_jobs( \
sh_file, sh_work_file_pool, l_sh_info, l_sh_work_pool)
my_job_rep.running_multi(cpu=8, is_debug=self.is_debug)
my_job_self.running_multi(cpu=8,is_debug=self.is_debug)
my_job_pool.running_multi(cpu=8,is_debug=self.is_debug)
