def filter_vcf(pileup, outfile=None, chr_col=0, ref_col=3, alt_col=4, sep='\t'):
""" Removes lines where ALT==REF and chromosomes other than 1 - 22, X, Y and MT"""
fh = open(pileup, "r")
if outfile is None:
outfile=pileup+'.filt'
fu.delete(outfile)
fh_out = open(outfile, "w")
for line in fh:
line = line.strip()
if line.startswith('#'):
fh_out.write(str(line)+'\n')
else:
fields=line.split(sep)
if(len(fields)>=8):
chr=str(fields[chr_col])
ref=str(fields[ref_col])
alt=str(fields[alt_col])
if (alt != ref) and (fu.find_first_index(ACCEPTED_CHR, chr.strip()) > -1):
fh_out.write(str(line)+'\n')
def filter_vcf(pileup,
outfile=None,
chr_col=0,
ref_col=3,
alt_col=4,
sep='\t'):
""" Removes lines where ALT==REF and chromosomes other than 1 - 22, X, Y and MT"""
fh = open(pileup, "r")
if outfile is None:
outfile = pileup + '.filt'
fu.delete(outfile)
fh_out = open(outfile, "w")
for line in fh:
line = line.strip()
if line.startswith('#'):
fh_out.write(str(line) + '\n')
else:
fields = line.split(sep)
if (len(fields) >= 8):
chr = str(fields[chr_col])
ref = str(fields[ref_col])
alt = str(fields[alt_col])
if (alt != ref) and (fu.find_first_index(
ACCEPTED_CHR, chr.strip()) > -1):
fh_out.write(str(line) + '\n')
def filter_pileup(pileup,
outfile=None,
chr_col=0,
ref_col=2,
alt_col=3,
sep='\t'):
fh = open(pileup, "r")
if outfile is None:
outfile = pileup + '.vcf'
fu.delete(outfile)
fh_out = open(outfile, "w")
fh_out.write(vcfheader(pileup) + '\n')
for line in fh:
line = line.strip()
fields = line.split(sep)
chr = str(fields[chr_col])
ref = str(fields[ref_col])
alt = str(fields[alt_col])
if (alt != ref) and (fu.find_first_index(ACCEPTED_CHR, chr.strip()) >
-1):
fh_out.write(varpileup_line2vcf_line(fields[0:9]) + '\n')
def filter_vcf(pileup,
outfile=None,
chr_col=0,
ref_col=3,
alt_col=4,
sep='\t'):
fh = open(pileup, "r")
if (outfile is None):
outfile = pileup + '.filt'
fu.delete(outfile)
fh_out = open(outfile, "w")
for line in fh:
line = line.strip()
if line.startswith('#'):
fh_out.write(str(line) + '\n')
else:
fields = line.split(sep)
if (len(fields) >= 8):
chr = str(fields[chr_col])
ref = str(fields[ref_col])
alt = str(fields[alt_col])
if ((alt != ref) and \
(fu.find_first_index(ACCEPTED_CHR, chr.strip()) > -1)):
fh_out.write(str(line) + '\n')
### EOF
def filter_pileup(pileup, outfile=None, chr_col=0, ref_col=2, alt_col=3, sep='\t'):
fh = open(pileup, "r")
if outfile is None:
outfile=pileup+'.vcf'
fu.delete(outfile)
fh_out = open(outfile, "w")
fh_out.write(vcfheader(pileup)+'\n')
for line in fh:
line = line.strip()
fields=line.split(sep)
chr=str(fields[chr_col])
ref=str(fields[ref_col])
alt=str(fields[alt_col])
if (alt != ref) and (fu.find_first_index(ACCEPTED_CHR, chr.strip()) > -1):
fh_out.write(varpileup_line2vcf_line(fields[0:9]) +'\n' )
def run(infile, format):
print("Running . . .")
ann.getSnpsFromDbSnp(vcf=infile, format='vcf', tmpextin='', tmpextout='.1' )
#print("Done dbSNP")
# Set numbering
tmpextin=1
tmpextout=2
ann.getBigRefGene(vcf=infile, format='vcf', tmpextin='.'+str(tmpextin), tmpextout='.'+str(tmpextout))
#print("Done BigRefGene ")
tmpextin=tmpextin+1
tmpextout=tmpextout+1
ann.getGenes(vcf=infile, format='vcf', table='refGene', promoter_offset=500, tmpextin='.'+str(tmpextin), tmpextout='.'+str(tmpextout))
#print("Done RefGene")
tmpextin=tmpextin+1
tmpextout=tmpextout+1
ann.addOverlapWithCytoband(vcf=infile, format='vcf', table='cytoBand', tmpextin='.'+str(tmpextin), tmpextout='.'+str(tmpextout))
#print("cytoband ")
tmpextin=tmpextin+1
tmpextout=tmpextout+1
ann.addOverlapWithGadAll(vcf=infile, format='vcf', table='gadAll', tmpextin='.'+str(tmpextin), tmpextout='.'+str(tmpextout))
#print("gadAll ")
tmpextin=tmpextin+1
tmpextout=tmpextout+1
ann.addOverlapWithGwasCatalog(vcf=infile, format='vcf', table='gwasCatalog', tmpextin='.'+str(tmpextin), tmpextout='.'+str(tmpextout))
#print("GwasCatalog ")
tmpextin=tmpextin+1
tmpextout=tmpextout+1
ann.addOverlapWithMiRNA(vcf=infile, format='vcf', table='targetScanS', tmpextin='.'+str(tmpextin), tmpextout='.'+str(tmpextout))
#print("miRNA")
tmpextin=tmpextin+1
tmpextout=tmpextout+1
ann.addOverlapWitHUGOGeneNomenclature(vcf=infile, format='vcf', table='hugo', tmpextin='.'+str(tmpextin), tmpextout='.'+str(tmpextout))
#print("HUGO Gene Nomenclature Committee (HGNC) ")
tmpextin=tmpextin+1
tmpextout=tmpextout+1
ann.addOverlapWithCnvDatabase(vcf=infile, format='vcf', table='dgv_Cnv', tmpextin='.'+str(tmpextin), tmpextout='.'+str(tmpextout))
#print("dgv_Cnv")
tmpextin=tmpextin+1
tmpextout=tmpextout+1
ann.addOverlapWithCnvDatabase(vcf=infile, format='vcf', table='abParts_IG_T_CelReceptors', tmpextin='.'+str(tmpextin), tmpextout='.'+str(tmpextout))
#print("abParts_IG_T_CelReceptors")
tmpextin=tmpextin+1
tmpextout=tmpextout+1
ann.addOverlapWithCnvDatabase(vcf=infile, format='vcf', table='mcCarroll_Cnv', tmpextin='.'+str(tmpextin), tmpextout='.'+str(tmpextout))
#print("mcCarroll_Cnv")
tmpextin=tmpextin+1
tmpextout=tmpextout+1
ann.addOverlapWithCnvDatabase(vcf=infile, format='vcf', table='conrad_Cnv', tmpextin='.'+str(tmpextin), tmpextout='.'+str(tmpextout))
#print("conrad_Cnv")
tmpextin=tmpextin+1
tmpextout=tmpextout+1
ann.addOverlapWithGenomicSuperDups(vcf=infile, format='vcf', table='genomicSuperDups', tmpextin='.'+str(tmpextin), tmpextout='.'+str(tmpextout))
#print("genomicSuperDups")
tmpextin=tmpextin+1
tmpextout=tmpextout+1
ann.addOverlapWithTfbsConsSites(vcf=infile, table='tfbsConsSites',tmpextin='.'+str(tmpextin), tmpextout='.'+str(tmpextout))
#print("addOverlapWithTfbsConsSites")
tmpextin=tmpextin+1
tmpextout=tmpextout+1
## Cleanup
for i in range(1, tmpextin):
fu.delete(infile+'.'+ str(i))
os.rename(infile+'.'+str(tmpextin), infile+'.annot')
finalout=(infile+'.annot').replace('.vcf.annot', '.annot.vcf')
os.rename(infile+'.annot', finalout)
