def initialize_pipeline(phase_path, haplotype_path, cnv_path):
exons_path = bamhelp.GetExons()
event, extension = os.path.splitext(os.path.basename(cnv_path))
phased_bed = "/".join([phase_path, "PHASED.BED"])
bedtools_path = bamhelp.GetBedtoolsPath()
try:
logger.debug(' --- Initializing input files --- ')
exonsinroibed = "/".join(
[haplotype_path, "exons_in_roi" + str(event) + ".bed"])
nonhetbed = "/".join([haplotype_path, "non_het" + str(event) + ".bed"])
hetbed = "/".join([haplotype_path, "het" + str(event) + ".bed"])
hetsnpbed = "/".join([haplotype_path, "het_snp" + str(event) + ".bed"])
tmp = "/".join([haplotype_path, str(event) + "_tmp.bed"])
command = " ".join([
bedtools_path, "intersect -a", exons_path, "-b", cnv_path,
"-wa -wb > ", tmp
])
runCommand(command)
cmd = "".join([
"""awk '{print $1"\t"$2"\t"$3"\t"$NF}' """, tmp, " > ",
exonsinroibed
])
runCommand(cmd)
splitBed(exonsinroibed, '_exons_in_roi' + str(event))
command = " ".join([
bedtools_path, "intersect -a", phased_bed, "-b", exonsinroibed,
"-wa -wb >", tmp
])
runCommand(command)
cmd = "".join([
"""awk '{print $1"\t"$2"\t"$3"\t"$4"\t"$5"\t"$6"\t"$NF}' """, tmp,
" > ", hetsnpbed
])
runCommand(cmd)
splitBed(hetsnpbed, '_het_snp' + str(event))
os.remove(tmp)
except:
logger.exception("Initialization error !")
raise
logger.debug("--- initialization complete ---")
return
def initialize0(results_path, cancer_dir_path):
try:
vcf_path = bamhelp.GetVCF()
exons_path = bamhelp.GetExons()
reference_path = bamhelp.GetRef()
bedtools_path = bamhelp.GetBedtoolsPath()
vpath, vcf = os.path.split(vcf_path)
if (params.GetPhase()):
phasedvcf = "/".join(
[results_path,
sub('.vcf$', '_phased.vcf.gz', vcf)])
vcftobed = "/".join([results_path, sub('.vcf$', '.bed', vcf)])
hap1vcf = "/".join([results_path, "hap1_het.vcf"])
hap2vcf = "/".join([results_path, "hap2_het.vcf"])
hap1vcffiltered = "/".join([results_path, "hap1_het_filtered"])
hap2vcffiltered = "/".join([results_path, "hap2_het_filtered"])
hap1vcffilteredtobed = "/".join(
[results_path, "hap1_het_filtered.bed"])
hap2vcffilteredtobed = "/".join(
[results_path, "hap2_het_filtered.bed"])
phased_bed = "/".join([results_path, "PHASED.BED"])
phaseVCF(vcf_path, phasedvcf)
getVCFHaplotypes(phasedvcf, hap1vcf, hap2vcf)
thinVCF(hap1vcf, hap1vcffiltered)
thinVCF(hap2vcf, hap2vcffiltered)
convertvcftobed(hap1vcffiltered + ".recode.vcf",
hap1vcffilteredtobed)
convertvcftobed(hap2vcffiltered + ".recode.vcf",
hap2vcffilteredtobed)
cmd1 = """sed -i 's/$/\thap1/' """ + hap1vcffilteredtobed
cmd2 = """sed -i 's/$/\thap2/' """ + hap2vcffilteredtobed
cmd3 = "cat " + hap1vcffilteredtobed + " " + hap2vcffilteredtobed + " > " + 'tmp.bed'
cmd4 = "sort -V -k1,1 -k2,2 tmp.bed > " + phased_bed
runCommand(cmd1)
runCommand(cmd2)
runCommand(cmd3)
runCommand(cmd4)
os.remove('tmp.bed')
except:
raise
return
def initialize_pipeline(phase_path, haplotype_path, cnv_path):
"""
Intersect CNV region with exons and then intersect with phased VCF bed.
"""
exons_path = params.GetExonsPath()
cnv_bed = params.GetCNV()
event, extension = os.path.splitext(os.path.basename(cnv_path))
phased_bed = "/".join([phase_path, "PHASED.BED"])
nonroibedfn = "/".join([haplotype_path, "non_roi.bed"])
bedtools_path = bamhelp.GetBedtoolsPath()
try:
logger.debug(' --- Initializing input files --- ')
exonsinroibed = "/".join([haplotype_path, "exons_in_roi" + str(event) + ".bed"])
nonhetbed = "/".join([haplotype_path, "non_het" + str(event) + ".bed"])
hetbed = "/".join([haplotype_path, "het" + str(event) + ".bed"])
hetsnpbed = "/".join([haplotype_path, "het_snp" + str(event) + ".bed"])
tmp1 = "/".join([haplotype_path, str(event) + "_tmp1.bed"])
tmp2 = "/".join([haplotype_path, str(event) + "_tmp2.bed"])
command = " ".join([bedtools_path, "intersect -a", cnv_path, "-b", exons_path, " > ", exonsinroibed])
runCommand(command)
splitBed(exonsinroibed, '_exons_in_roi' + str(event))
command = " ".join([bedtools_path, "intersect -a", phased_bed, "-b", exonsinroibed, "-wa -wb >", tmp2])
runCommand(command)
removeIfEmptyBed(tmp2)
if os.path.isfile(tmp2):
filterColumns(tmp2, hetsnpbed, [0,1,2,3,4,5,9])#[i for i in range(0, 8)])
splitBed(hetsnpbed, '_het_snp' + str(event))
# non-roi bed:
if not os.path.isfile(nonroibedfn):
command = " ".join([bedtools_path, "subtract -a", exons_path, "-b", cnv_bed, ">", nonroibedfn])
runCommand(command)
removeIfEmptyBed(nonroibedfn)
if os.path.isfile(nonroibedfn):
splitBedByChr(nonroibedfn, haplotype_path)
except:
logger.exception("Initialization error !")
raise
logger.debug("--- initialization complete ---")
return
def initialize0(results_path, cancer_dir_path):
try:
vcf_path = bamhelp.GetVCF()
exons_path = bamhelp.GetExons()
reference_path = bamhelp.GetRef()
bedtools_path = bamhelp.GetBedtoolsPath()
vpath, vcf = os.path.split(vcf_path)
if params.GetPhase():
phasedvcf = "/".join(
[results_path,
sub('.vcf$', '_phased.vcf.gz', vcf)])
vcftobed = "/".join([results_path, sub('.vcf$', '.bed', vcf)])
hap1vcf = "/".join([results_path, "hap1_het.vcf"])
hap2vcf = "/".join([results_path, "hap2_het.vcf"])
hap1vcffiltered = "/".join([results_path, "hap1_het_filtered"])
hap2vcffiltered = "/".join([results_path, "hap2_het_filtered"])
hap1vcffilteredtobed = "/".join(
[results_path, "hap1_het_filtered.bed"])
hap2vcffilteredtobed = "/".join(
[results_path, "hap2_het_filtered.bed"])
phased_bed = "/".join([results_path, "PHASED.BED"])
phaseVCF(vcf_path, phasedvcf)
getVCFHaplotypes(phasedvcf, hap1vcf, hap2vcf)
thinVCF(hap1vcf, hap1vcffiltered)
thinVCF(hap2vcf, hap2vcffiltered)
convertvcftobed(hap1vcffiltered + ".recode.vcf",
hap1vcffilteredtobed)
convertvcftobed(hap2vcffiltered + ".recode.vcf",
hap2vcffilteredtobed)
generatePhasedBed(hap1vcffilteredtobed, hap2vcffilteredtobed,
phased_bed)
except:
logger.exception("Initialization error !")
raise
return
def initialize0(results_path, cancer_dir_path):
"""
Initialize paths for files provided by user.
Phasing is also performed if requested by user.
"""
try:
vcf_path = params.GetVCFPath()
exons_path = params.GetExonsPath()
#reference_path = bamhelp.GetRef()
bedtools_path = bamhelp.GetBedtoolsPath()
vpath, vcf = os.path.split(vcf_path)
phasedvcf = "/".join([results_path, sub('.vcf$', '_phased.vcf.gz', vcf)])
vcftobed = "/".join([results_path, sub('.vcf$', '.bed', vcf)])
hap1vcf = "/".join([results_path, "hap1_het.vcf"])
hap2vcf = "/".join([results_path, "hap2_het.vcf"])
hap1vcffiltered = "/".join([results_path, "hap1_het_filtered"])
hap2vcffiltered = "/".join([results_path, "hap2_het_filtered"])
hap1vcffilteredtobed = "/".join([results_path, "hap1_het_filtered.bed"])
hap2vcffilteredtobed = "/".join([results_path, "hap2_het_filtered.bed"])
phased_bed = "/".join([results_path, "PHASED.BED"])
if params.GetPhase():
phaseVCF(vcf_path, phasedvcf)
getVCFHaplotypes(phasedvcf, hap1vcf, hap2vcf)
else:
getVCFHaplotypes(vcf_path, hap1vcf, hap2vcf)
convertvcftobed(hap1vcf, hap1vcffilteredtobed)
convertvcftobed(hap2vcf, hap2vcffilteredtobed)
generatePhasedBed(hap1vcffilteredtobed, hap2vcffilteredtobed, phased_bed)
except:
logger.exception("Initialization error!")
raise
return