def main():
usage = "usage: %prog [options] file.vcf \n output format values from genotype data field in a VCF for suitabale plotting/dataviz"
parser = OptionParser(usage)
parser.add_option("--includeRef", action="store_true", dest="includeRef", help="include sites in the set ReferenceInAll", default=False)
parser.add_option("--includeFilter", action="store_true", dest="includeFilter", help="include site filtered or not!", default=False)
parser.add_option("--formatTag", dest="format", default="GT", help="format tag to compare (default GT)")
(options, args)=parser.parse_args()
vcfilename=args[0]
#vcfilename='/Users/indapa/software/Pgmsnp/PythonNotebook/child5x.nrs.sites.calledWith20x_bam.child5x.nrs.sites.calledWith5x_bam.combineVariants.vcf'
basename=os.path.splitext(vcfilename)[0]
vcfobj=VcfFile(vcfilename)
vcfh=open(vcfilename,'r')
vcfobj.parseMetaAndHeaderLines(vcfh)
header=vcfobj.returnHeader() +"\n"
samples=vcfobj.getSampleList()
print "\t".join(samples)
for vrec in vcfobj.yieldVcfRecordwithGenotypes(vcfh):
vrec_ziptuple=vrec.zipGenotypes(samples)
outputs=[]
for (sample, geno_obj) in vrec_ziptuple:
outputs.append( "\t".join( [geno_obj.getFormatVal(options.format) ] ) )
print "\t".join(outputs)
def main():
""" This program adds non-reference positions to a VCF file with variant positions.
It does this by the following. Given a bed file of non-variant intervals and a 2bit file of the reference genome,
it retrieves the refernce alllele, and prints out the VCF data line with the ref/ref genotypes. Then
it prints a single line from the segregating VCF file, and then start the loop again.
It assumes that the input vcf is position sorted.
To generate the non-segrgating bed interval file, run the following program from bx-python:
bed_subtract_basewise.py reference_genome.bed segregating.sites.bed
bed_subtract_basewise.py ~/software/Pgmsnp/PythonNotebook/simref.1.bed Simulation1.segregating.bed """
usage = "usage: %prog [options] file.vcf"
parser = OptionParser(usage)
parser.add_option("--bed", type="string", dest="bed", help="bed file with non-variant intervals")
parser.add_option("--tbf", type="string", dest="tbf", help="2bit file of reference genome", default='/Users/amit/data/MySimulations/Simulation1/Reference/simref.1.2bit')
(options, args)=parser.parse_args()
try:
sys.stderr.write("opening twobitfile...\n")
twobit=bx.seq.twobit.TwoBitFile( open( options.tbf ) )
except:
sys.stderr.write("unable to open twobit file!\n")
segregatingVcf=args[0]
bedfh=open(options.bed,'r')
vcfh=open(segregatingVcf,'r')
vcfobj=VcfFile(segregatingVcf)
vcfobj.parseMetaAndHeaderLines(vcfh)
header=vcfobj.returnHeader()
formatstring="GT"
print header
for (chrom,start,end) in yield_bedcoordinate(bedfh):
start=int(start)
end=int(end)
for i in range(start,end):
begin=i
end=i+1
refseq=twobit[chrom][begin:end]
vrec=VcfRecord(chrom,str(end),'.',refseq,'.','.','.','NS=3')
vrec.addGenotype( VcfGenotype(formatstring,'0/0') )
vrec.addGenotype( VcfGenotype(formatstring,'0/0') )
vrec.addGenotype( VcfGenotype(formatstring,'0/0') )
print vrec.toStringwithGenotypes()
vcf_gen=vcfobj.yieldVcfRecordwithGenotypes(vcfh)
print vcf_gen.next().toStringwithGenotypes()
def main():
""" This program extracts out records matching the set=(\S+). Typically, the VCF is derived
from GATK CombineVariants, but any vcf with set=(\S+) can be examined with this program """
usage = "usage: %prog [options] file.vcf.gz "
#parser = OptionParser(usage)
parser = argparse.ArgumentParser(description=' extract records with matching set=(\S+) tag')
parser.add_argument('vcfile', metavar='vcfile', type=str, help='file.vcf.gz')
#parser.add_argument('-filter', dest='filter', type=str, default=".", help='filter value')
parser.add_argument('-set', dest='set', type=str, default=None, help="name of set to extract")
args = parser.parse_args()
if args.set == None:
sys.stderr.write("please provide value to -set option!\n")
sys.exit(1)
(path, vcfile)=os.path.split(args.vcfile )
basename=return_file_basename( return_file_basename(vcfile) )
sys.stderr.write( basename +"\n")
outvcf=".".join([basename, args.set, 'vcf'])
sys.stderr.write( outvcf +"\n")
outfh=open(outvcf, 'w')
if args.vcfile.endswith(".gz"):
vcfh=gzip.open(args.vcfile,'r')
else:
vcfh=open(args.vcfile,'r')
vcfobj=VcfFile(args.vcfile)
pattern=';set=(\S+)'
vcfobj.parseMetaAndHeaderLines(vcfh)
header=vcfobj.returnHeader()
outfh.write( header +"\n")
for vrec in vcfobj.yieldVcfRecordwithGenotypes(vcfh):
searchresult=re.search(pattern, vrec.getInfo() )
if re.search(pattern, vrec.getInfo() ) == None:
continue
value=re.search(pattern, vrec.getInfo() ).groups()[0]
#print value
if value == args.set:
outfh.write( vrec.toStringwithGenotypes() +"\n" )
def main():
usage = "usage: %prog [options] "
parser = argparse.ArgumentParser(description='Given a gzipped vcf file and pedigree file, generate a new vcf with only those samples present in the pedigree (ped file) ')
parser.add_argument('-ped', dest='pedfile', type=str, help="*.ped file")
parser.add_argument('vcfile', type=str,help='*.vcf.gz file')
args=parser.parse_args()
""" parse the pedfile and return the list of iids to keep from the VCF file """
pedobj=Pedfile(args.pedfile)
pedobj.parsePedfile()
keeplist= pedobj.returnIndivids()
#open the VCFfile
vcfh=gzip.open(args.vcfile,'r')
vcfobj=VcfFile(args.vcfile)
vcfobj.parseMetaAndHeaderLines(vcfh)
samples=vcfobj.getSampleList()
newsamples= [ s for s in samples if s in keeplist]
print newsamples
vcfobj.setSampleList(newsamples)
header=vcfobj.returnHeader()
print header
for vrec in vcfobj.yieldVcfRecordwithGenotypes(vcfh):
keepGenotypes=[]
vrec_ziptuple=vrec.zipGenotypes(samples)
for (s, genObj) in vrec_ziptuple:
if s in keeplist:
keepGenotypes.append( genObj )
vrec.addGenotypeList( keepGenotypes )
print vrec.toStringwithGenotypes()
def main():
""" remove samples from a vcf file """
usage = "usage: %prog [options] file.vcf.gz "
# parser = OptionParser(usage)
parser = argparse.ArgumentParser(description="remove samples from vcf file")
parser.add_argument("removesamples", metavar="sample", type=str, nargs="+", help="sample names to remove")
parser.add_argument("-vcf", dest="vcfile", type=str, help="vcf file to remove samples from")
# parser.add_argument("vcf", help="vcf file to analyze")
args = parser.parse_args()
# print 'remove these samples: ', args.samples
# print args.vcfile
vcfh = gzip.open(args.vcfile, "r")
vcfobj = VcfFile(args.vcfile)
vcfobj.parseMetaAndHeaderLines(vcfh)
# print header
samples = vcfobj.getSampleList()
newsamples = [s for s in samples if s not in args.removesamples]
# print 'keep these samples: ', newsamples
vcfobj.setSampleList(newsamples)
header = vcfobj.returnHeader()
print header
for vrec in vcfobj.yieldVcfRecordwithGenotypes(vcfh):
keepGenotypes = []
vrec_ziptuple = vrec.zipGenotypes(samples)
for (s, genObj) in vrec_ziptuple:
if s not in args.removesamples:
# print s
keepGenotypes.append(genObj)
# print keepGenotypes
vrec.addGenotypeList(keepGenotypes)
print vrec.toStringwithGenotypes()
def main():
usage = "usage: %prog [options] file.vcf.gz \n calcuate NRS and NRD on a vcf generated from CombineVariants --genotypemergeoption UNIQUIFY\n"
parser = OptionParser(usage)
parser.add_option("--matrixonly", action="store_true", dest="matrixonly", help="only print concordance matrixe", default=False)
parser.add_option("--includeRef", action="store_true", dest="includeRef", help="include sites in the set ReferenceInAll", default=False)
parser.add_option("--includeFilter", action="store_true", dest="includeFilter", help="include site filtered or not!", default=False)
(options, args)=parser.parse_args()
vcfilename=args[0]
basename=os.path.splitext(os.path.splitext(vcfilename)[0])[0]
""" row is eval, column is comparison
make a numpy matrix to represent genotype concordance matrix """
concordancetable= np.matrix( [ [ 0,0,0,0 ], [ 0,0,0,0 ], [ 0,0,0,0 ], [ 0,0,0,0 ] ] )
calledtable = np.matrix ( [ [0 ,0] , [0,0] ] )
#outputfile is the the basename of the VCF to be analyzed replaced with a variantEval.txt suffix
outputfile=".".join([basename, 'variantEval','txt'])
outputfh=open(outputfile, 'w')
#log file of sites that contribute to NRS penalty; hom-ref and no-calls at variant sites in comparison set
nrslog=".".join([basename, 'nrs','log'])
nrdlog=".".join([basename, 'nrd','log'])
filterlog=".".join([basename, 'filtered','log'])
multialleliclog=".".join([basename, 'multiallelic','log'])
concordancelog=".".join([basename, 'concordance','log'])
fieldslog=".".join([basename, 'fields', 'log'])
nrsfh=open(nrslog, 'w')
nrdfh=open(nrdlog, 'w')
filteredfh=open(filterlog, 'w')
multifh=open(multialleliclog, 'w')
concordancefh=open(concordancelog, 'w')
fieldsfh=open(fieldslog, 'w')
fieldsfh.write('set'+"\n")
vcfobj=VcfFile(vcfilename)
vcfh=gzip.open(vcfilename,'r')
vcfobj.parseMetaAndHeaderLines(vcfh)
header=vcfobj.returnHeader() +"\n"
nrsfh.write(header)
nrdfh.write(header)
filteredfh.write(header)
concordancefh.write(header)
multifh.write(header)
#outputfh.write(header)
#multifh.write(header)
samples=vcfobj.getSampleList()
#for (comparename, evalname) in grouper(2,samples):
# print comparename, evalname
vcf_sample_eval_objects = [ VcfSampleEval(compare,eval,basename) for (compare,eval) in grouper(2,samples) ]
for evalObj in vcf_sample_eval_objects:
evalObj.writeHeaders(header)
totalrecords=0
pattern=';set=(\S+)'
for vrec in vcfobj.yieldVcfRecordwithGenotypes(vcfh):
if ',' in vrec.getAlt() > 1:
outstring=vrec.toStringwithGenotypes() + "\n"
multifh.write(outstring)
#continue
""" skip homoz reference calls unless you want to include them! """
if 'ReferenceInAll' in vrec.getInfo() and options.includeRef == False:
continue
""" if variant is filtered, skip it! """
if 'filterIn' in vrec.getInfo() and options.includeFilter == False:
outstring=vrec.toStringwithGenotypes() + "\n"
filteredfh.write(outstring)
continue
if 'FilteredInAll' in vrec.getInfo():
outstring=vrec.toStringwithGenotypes() + "\n"
filteredfh.write(outstring)
continue
#returns a list [ (samplename, vcfgenotype) , ... () ]
vrec_ziptuple=vrec.zipGenotypes(samples)
""" we make a hack and make a list like so:
[(sample.variant, compare_genotype, sample.variant2, eval_genotype) ... ]
basically it halves the length of vrec_ziptuple and gives it the same structure
as the list of VcfSampleEval objects"""
compare_eval =[ compare+evalu for (compare,evalu) in grouper(2,vrec_ziptuple) ]
#what set are you in?
field=re.search(pattern, vrec.getInfo()).groups()[0]
fieldsfh.write(field+"\n")
totalrecords+=1
""" we take records two at a time, assuming the first is the comparison genotype the second is the evaluation genotype """
for (genotype_tuple, evalObj) in izip(compare_eval, vcf_sample_eval_objects):
#print genotype_tuple
compare=genotype_tuple[0:2]
eval=genotype_tuple[2::]
#print compare
#print eval
(comp_allele1, comp_allele2)=compare[1].getAlleles()
(eval_allele1, eval_allele2)=eval[1].getAlleles()
eval_alleletype=typeofGenotype(eval_allele1, eval_allele2)
comp_alleletype=typeofGenotype(comp_allele1, comp_allele2)
""" increment the cell count """
concordancetable[eval_alleletype, comp_alleletype]+=1
evalObj.incrementcellcount(eval_alleletype,comp_alleletype)
"""write gentoype record to log appropriate log file """
#print records that contirubut the NRS penalty
if eval_alleletype == 3:
if comp_alleletype == 1 or comp_alleletype==2:
outstring=vrec.toStringwithGenotypes() + "\n"
nrsfh.write( outstring)
evalObj.writeNrs(outstring)
if eval_alleletype==0:
if comp_alleletype == 1 or comp_alleletype == 2:
outstring=vrec.toStringwithGenotypes() + "\n"
nrsfh.write( outstring )
evalObj.writeNrs(outstring)
#print records that contribute to NRD penalty
if eval_alleletype==0:
if comp_alleletype == 1 or comp_alleletype == 2:
outstring=vrec.toStringwithGenotypes() + "\n"
nrdfh.write( outstring )
evalObj.writeNrd(outstring)
if comp_alleletype == 0:
outstring=vrec.toStringwithGenotypes() + "\n"
concordancefh.write( outstring )
evalObj.writeConcordance( outstring)
if eval_alleletype == 1:
if comp_alleletype == 0 or comp_alleletype == 2:
outstring=vrec.toStringwithGenotypes() + "\n"
nrdfh.write( outstring )
evalObj.writeNrd(outstring)
if comp_alleletype == 1:
outstring=vrec.toStringwithGenotypes() + "\n"
concordancefh.write( outstring )
evalObj.writeConcordance( outstring)
if eval_alleletype == 2:
if comp_alleletype == 0 or comp_alleletype ==1:
outstring=vrec.toStringwithGenotypes() + "\n"
nrdfh.write( outstring )
evalObj.writeNrd(outstring)
if comp_alleletype == 2:
outstring=vrec.toStringwithGenotypes() + "\n"
concordancefh.write( outstring )
evalObj.writeConcordance( outstring)
for evalObj in vcf_sample_eval_objects:
evalObj.writeEvalOutput()
outputfh.write("total records analyzed: " + str(totalrecords) + "\n" )
outputfh.write( "rows are eval genotypes columns comparison genotypes\n")
outputfh.write("\t".join(['','AA','AB','BB', './.' ]) +"\n")
rownames=[0,'AA', 1,'AB', 2,'BB', 3,'./.']
for (i, gt) in grouper(2,rownames):
row=concordancetable[i,:].tolist()
for r in row:
outstr="\t".join(map(str,r))
outputfh.write( gt +"\t"+outstr+"\n")
outputfh.write( "matrix sum: \n")
sum=np.sum(concordancetable)
outputfh.write( str(sum) +"\n")
#now we figure out how many sites were called or not called
calledtable[0,0]=concordancetable[0:3,0:3].sum()
calledtable[0,1]=concordancetable[0:3,3].sum()
calledtable[1,0]=concordancetable[3,0:3].sum()
calledtable[1,1]=concordancetable[3,3]
outputfh.write("\n")
rownames=[ 0,'called', 1,'./.' ]
outputfh.write( "rows are eval genotypes columns comparison genotypes\n")
outputfh.write( "\t".join(['','called','./.' ]) +"\n" )
for (i, gt) in grouper(2,rownames):
row=calledtable[i,:].tolist()
for r in row:
outstr="\t".join(map(str,r))
outputfh.write( gt +"\t"+outstr+"\n")
outputfh.write( "matrix sum: \n")
sum=np.sum(calledtable)
outputfh.write( str(sum) +"\n")
outputfh.write("\n")
if options.matrixonly == False:
discordance=concordancetable[0,1]+concordancetable[0,2]+concordancetable[1,0]+concordancetable[1,2]+concordancetable[2,0]+concordancetable[2,1]
total=concordancetable[0,1]+concordancetable[0,2]+concordancetable[1,0]+concordancetable[1,1]+ concordancetable[1,2]+concordancetable[2,0]+concordancetable[2,1] +concordancetable[2,2]
nrd=round( (float(discordance)/float(total)) * 100, 2)
variant_count_evaluation= concordancetable[1,1]+ concordancetable[1,2]+ concordancetable[2,1]+ concordancetable[2,2]
variant_count_comparison= concordancetable[0,1]+concordancetable[0,2]+concordancetable[1,1]+concordancetable[1,2]+concordancetable[2,1]+concordancetable[2,2]+concordancetable[3,1]+concordancetable[3,2]
nrs=round( float(variant_count_evaluation)/float(variant_count_comparison) * 100 , 2)
outputfh.write( "NRD: " + str(nrd) +" \n")
outputfh.write( "NRS " + str(nrs) +" \n")
def main():
usage = "usage: %prog [options] vcf_file_one vcf|bed_file_two\n\nFind regions in the first vcf file that overlap regions of the second vcf or bed file\n"
parser = OptionParser(usage)
parser.add_option("--minCols", type="int", dest="mincols", default=1, help="mininum basepair overlap (default is one)")
parser.add_option("--v", action="store_true", dest="reverse", help="Print regions in first vcf that DO NOT overlap second vcf|bed file")
parser.add_option("--filter", type="string", dest="filter", default=None, help="intersect records only set with filter (default is None")
parser.add_option("--info", type="string", dest="infotag", help="INFO tag id that annotates what type of variant the VCF record is", default="TYPE")
parser.add_option("--type", type="string", dest="variantype", help="type of variant (SNP INS DEL)", default=None)
parser.add_option("--noheader", action="store_true", dest="noheader", help="VCF file one has no header line", default=False)
parser.add_option("--nochrprefix", action="store_false", dest="chrprefix", help="use if the bed doesn't have chr prefix in chrom column", default=True)
(options, args)=parser.parse_args()
sys.stderr.write("intersecting two files ...\n")
vcf_file_one=args[0]
in2_fname=args[1]
in2_fname_ext= os.path.splitext(in2_fname)[1][1:]
if "bed" == in2_fname_ext:
bitsets = binned_bitsets_from_file( open( in2_fname ) )
if "vcf" == in2_fname_ext:
bitsets = binned_bitsets_from_vcffile( in2_fname , options.filter)
vcfobj=VcfFile(vcf_file_one)
vcfh=open(vcf_file_one,'r')
if options.noheader == False:
vcfobj.parseMetaAndHeaderLines(vcfh)
header=vcfobj.returnHeader()
#print header
#vcfobj.parseMetaAndHeaderLines(vcfh)
#descriptors = vcfobj.getMetaInfoDescription()
#infoids=[]
#for (tag, description) in descriptors:
# infoids.append(tag)
#if options.infotag not in infoids and options.infotag != 'QUAL' and options.infotag != "" and options.noheader == False:
# sys.stderr.write(options.infotag + " tag not in ##INFO headers!\n")
# exit(1)
print header
for dataline in vcfobj.yieldVcfDataLine(vcfh):
fields=dataline.strip().split('\t')
(chrom,pos,id,ref,alt,qual,filtercode,info)=fields[0:8]
(start,end) = (int(pos)-1, int(pos))
#pass the filter code
if filtercode != options.filter and options.filter != None:
continue
#check to see if record is the correct variant TYPE
if options.variantype != None:
pattern=options.infotag+'=('+options.variantype+')'
if re.search(pattern, info ) == None:
continue
if options.chrprefix == True:
chrom="chr"+chrom
if chrom in bitsets and bitsets[chrom].count_range( start, end-start ) >= options.mincols:
if not options.reverse:
print dataline
else:
if options.reverse == True:
print dataline
def main():
usage = "usage: %prog [options] file.vcf.gz "
parser = argparse.ArgumentParser(description='filter records based on genotypes')
parser.add_argument('vcf', metavar='vcf', type=str,
help='vcf.gz file')
""" http://stackoverflow.com/a/15008806/1735942 """
parser.add_argument('--no-header',dest='header',action='store_false')
parser.add_argument('-gt', metavar='gt', type=str, nargs='*', action='append',
help='sample 0/0')
args = parser.parse_args()
""" http://stackoverflow.com/q/12460989/1735942 """
args.gt = [el for elements in args.gt for el in elements]
#print args.gq
gt_filter=[ tuple(x.split(' ')) for x in args.gt ]
gt_dict=defaultdict(list)
for (k,v) in gt_filter:
gt_dict[k].append(v)
#print gt_dict
vcfh=gzip.open(args.vcf,'r')
vcfobj=VcfFile(args.vcf)
vcfobj.parseMetaAndHeaderLines(vcfh)
header=vcfobj.returnHeader()
if args.header == True:
print header
samplelist=vcfobj.getSampleList()
for s in gt_dict.keys():
if s not in samplelist:
print s ," not in samples!\n"
sys.exit(1)
#print header
#print header
#print gt_dict.keys()
for vrec in vcfobj.yieldVcfRecordwithGenotypes(vcfh ):
genotypes_toFilter=[] #list [ (sample,genoObj) ] to be filtered
genotype_tuple= vrec.zipGenotypes(samplelist) ## get a list of tuples [ (sample, VcfGenotype object) ... ]
for (s,g) in genotype_tuple:
if s in gt_dict.keys():
#print s
if len(gt_dict[s]) > 1: # logical or
if any( [ g.getFormatVal('GT') == v for v in gt_dict[s] ] ):
genotypes_toFilter.append(True)
else: genotypes_toFilter.append(False)
else:
if all( [ g.getFormatVal('GT') == v for v in gt_dict[s] ] ):
genotypes_toFilter.append(True)
else:genotypes_toFilter.append(False)
# all gt filters need to evaluate to True in order for record to print
if all(item == True for item in genotypes_toFilter):
print vrec.toStringwithGenotypes()
def main():
""" given a VCF file and bam file containing the sample(s) in the VCF this will add INFO and FORMAT tags
to indicate the count of reference and alt alleles observed in total and per-sample and print out a new VCF"""
usage = "usage: %prog [option] file.vcf.gz"
parser = OptionParser(usage)
parser.add_option("--bam", type="string", dest="bam", default=None, help="bam file to perform pileup on")
parser.add_option(
"--mapq",
type="float",
dest="mapq",
default=0.0,
help="Exclude alignments from analysis if they have a mapping less than mapq (default is 0)",
)
parser.add_option(
"--bq",
type="float",
dest="bq",
default=0.0,
help="Exclude bases from analysis if their supporting base quality is less that --bq (default is 0)",
)
parser.add_option(
"--includeDuplicates",
action="store_false",
dest="duplicate",
help="include duplicate marked reads in analysis (turned off by default) ",
)
(options, args) = parser.parse_args()
if options.bam == None:
sys.stderr.write("please provide a value to --bam option\n")
sys.exit(1)
vcfilename = args[0]
bamfilename = options.bam
ra_formatline = FormatLine("RA", number="1", type="Integer", description="number of reference alleles observed")
aa_formatline = FormatLine("AA", number="1", type="Integer", description="number of alternate alleles observed")
if os.path.exists(bamfilename + ".bai") == False:
sys.stderr.write("please check for existence of bam index file (*.bai)\n")
exit(1)
vcfobj = VcfFile(vcfilename)
vcfh = gzip.open(vcfilename, "r")
vcfobj.parseMetaAndHeaderLines(vcfh)
vcfobj.addMetaFormatHeader(ra_formatline)
vcfobj.addMetaFormatHeader(aa_formatline)
vcfobj.addMetaInfoHeader("RA", "Integer", "1", "total number of reference alleles observed")
vcfobj.addMetaInfoHeader("AA", "Integer", "1", "total number of alternate alleles observed")
header = vcfobj.returnHeader()
print header
readgroupdict = {}
pybamfile = pysam.Samfile(bamfilename, "rb")
rgdictlist = pybamfile.header["RG"]
for dictionary in rgdictlist:
readgroupdict[dictionary["ID"]] = dictionary["SM"]
# print readgroupdict
samples = vcfobj.getSampleList()
# print samples
for vrec in vcfobj.yieldVcfRecordwithGenotypes(vcfh):
(chrom, start, end) = vrec.getChrom(), int(vrec.getPos()) - 1, int(vrec.getPos())
# print chrom, str(start), str(end)
# print vrec.getRef()
# print vrec.toStringwithGenotypes()
for pileupcolumn in pybamfile.pileup(chrom, start, end):
if pileupcolumn.pos != end:
continue
# sys.stdout.write('chr'+chrom+ " " + str(start) + " " + str(end) + " " + str(pileupcolumn.pos) + " ")
# print 'coverage at base %s = %s' % (pileupcolumn.pos , pileupcolumn.n)
seqdict = {}
sampledict = {}
for s in samples:
sampledict[s] = []
# print sampledict
for (base, count) in (("A", 0), ("C", 0), ("G", 0), ("T", 0), ("N", 0)):
seqdict[base] = count
for pileupread in pileupcolumn.pileups:
if pileupread.alignment.is_duplicate == True and options.duplicate == False:
continue
if pileupread.alignment.mapq < options.mapq:
continue
if (ord(pileupread.alignment.qual[pileupread.qpos - 1]) - 33) < options.bq:
continue
seqdict[pileupread.alignment.seq[pileupread.qpos - 1]] += 1
readgroup = dict(pileupread.alignment.tags)["RG"]
sample = readgroupdict[readgroup]
# print readgroup,sample, pileupread.alignment.seq[pileupread.qpos-1]
sampledict[sample].append(pileupread.alignment.seq[pileupread.qpos - 1])
# print pileupread.alignment.seq, len(pileupread.alignment.seq), pileupread.qpos
vrec.addInfo("RA=" + str(seqdict[vrec.getRef()]))
if vrec.getAlt() != ".":
vrec.addInfo("AA=" + str(seqdict[vrec.getAlt()]))
zip_genos = vrec.zipGenotypes(samples)
for (sample, vcfgenobj) in zip_genos:
if len(sampledict[sample]) == 0:
vcfgenobj.addFormat("RA")
vcfgenobj.addFormat("AA")
continue
else:
ra = 0
aa = 0
c = dict(Counter(sampledict[sample]))
if vrec.getRef() in c.keys():
ra = c[vrec.getRef()]
if vrec.getAlt() in c.keys():
aa = c[vrec.getAlt()]
vcfgenobj.addFormatVal("RA", str(ra))
vcfgenobj.addFormatVal("AA", str(aa))
# for nt in ('A', 'C', 'G', 'T', 'N'):
# sys.stdout.write( str(seqdict[nt]) + " ")
# sys.stdout.write("\n")
print vrec.toStringwithGenotypes()
pybamfile.close()
def main():
""" This program bins the records of a VCF file according to a user defined range and number of bins.
For example if -start 10 and -end 100 and -num of 10 it would make 10 bins:
10, 20, 30, 40,50,60,70,80,90,100
Then for each record if the QUAL is >=x, then that record is written to *.qual_x.vcf file
"""
usage = "usage: %prog [options] file.vcf.gz "
#parser = OptionParser(usage)
parser = argparse.ArgumentParser(description=' bin vcf records according to QUAL')
parser.add_argument('vcfile', metavar='vcfile', type=str, help='file.vcf.gz')
parser.add_argument('-filter', dest='filter', type=str, default=".", help='filter value')
parser.add_argument('-start', dest='start', type=int, help="starting point for QUAL range")
parser.add_argument('-end', dest='end', type=int, help="ending pint for QUAL range")
parser.add_argument('-num', dest='num', type=int, help='number of bins')
#parser.add_argument("vcf", help="vcf file to analyze")
args = parser.parse_args()
#print args
(path, vcfile)=os.path.split(args.vcfile )
basename=return_file_basename( return_file_basename(vcfile) )
print basename
if args.start == None or args.end == None or args.num == None:
sys.stderr.write("please give start stop and number of bins for QUAL")
sys.exit(1)
bins=np.linspace(args.start, args.end, args.num)
binstring=bins
binstring=binstring.astype(int).tolist()
print binstring
binned_vcfilenames=[ ".".join( [ basename, "qual_"+ str(s), "vcf"]) for s in binstring ]
print binned_vcfilenames
#binned_fh = itertools.chain(*(open(f, "w") for f in binned_vcfilenames))
""" we create a list of filehandles for the binned VCFs """
binned_fh=list(itertools.imap(lambda x:open(x,'w'), binned_vcfilenames))
if args.vcfile.endswith(".gz"):
vcfh=gzip.open(args.vcfile,'r')
else:
vcfh=open(args.vcfile,'r')
vcfobj=VcfFile(args.vcfile)
#vcf_reader = vcf.Reader(open(args.vcfile, 'r'))
#print vcf_reader.metadata
vcfobj.parseMetaAndHeaderLines(vcfh)
header=vcfobj.returnHeader()
map(lambda x: x.write(header+"\n"),binned_fh)
#vcfrecord_bins= [ [] for i in xrange(len(bins)) ]
sys.stderr.write("binning vcf records based on quality ....\n")
#for vrec in vcf_reader:
for vrec in vcfobj.yieldVcfRecordwithGenotypes(vcfh):
""" skip records that do not have PASS in filter column """
if vrec.getFilter() != args.filter:
continue
QUAL=float(vrec.getQual())
vcfstring=vrec.toStringwithGenotypes()
for i in xrange(len(bins)):
if QUAL >= bins[i]:
binned_fh[i].write(vcfstring+"\n")
#vcfrecord_bins[i].append(vrec)
else: break
map(lambda x: x.close(),binned_fh)
def main():
usage = "usage: %prog [options] file.vcf.gz"
parser = OptionParser(usage)
parser.add_option("--model", type="string", dest="model", default = "dominant", help=" inheritance model [dominant|recessive], default is dominant ")
parser.add_option("--ped", type="string", dest="pedfile", default=None, help="ped file of samples with phenotype (disease) status")
parser.add_option("--filter", type="string", dest="filter", help="analyze only those records matching filter (default is PASS)", default='PASS')
(options, args)=parser.parse_args()
if options.pedfile==None:
sys.stderr.write("please provide a value to --ped parameter!\n")
exit(1)
affecteds=[] # list of affected samples
unaffecteds=[] # list of unaffected samples
pedobjects=[] #list of pedobjects, represents lines in a pedfile
pedfh=open(options.pedfile, 'r')
for line in pedfh:
fields=line.strip().split('\t')
(fid,iid,pid,mid,sex,phenotype)=fields[0:6]
phenotype=int(phenotype)
pedobjects.append( Ped(fid,iid,pid,mid,sex,phenotype) )
#the phenotype status is set to 2 if the sample is affected: http://pngu.mgh.harvard.edu/~purcell/plink/data.shtml#ped
affecteds=[ pedobj.getid() for pedobj in pedobjects if pedobj.getpheno() == 2 ]
unaffecteds=[ pedobj.getid() for pedobj in pedobjects if pedobj.getpheno() == 1 ]
#check if any overlapping samples between unaffected and affected
if len( list( set(unaffecteds).intersection( set(affecteds) ) ) ) != 0:
sys.stderr.write("check list of affected and unaffecteds for overlapping samples!\n")
exit(1)
# sys.stderr.write("check list of affected and unaffected for overlapping samples!\n")
# exit(1)
vcfilename=args[0]
vcfh=gzip.open(vcfilename,'r')
#instantiate a VcfFile object
vcfobj=VcfFile(vcfilename)
vcfobj.parseMetaAndHeaderLines(vcfh)
header=vcfobj.returnHeader()
samplelist=vcfobj.getSampleList()
print header
for vrec in vcfobj.yieldVcfRecordwithGenotypes(vcfh ):
affected_genotypes=[] #list of tuples (sample, VcfGenotype object) with samples that are affected
unaffected_genotypes=[] # list of tuples (sample, VcfGenotype object) with samples that are unaffected
if vrec.getFilter() != options.filter and options.filter != None : continue
genotype_tuple= vrec.zipGenotypes(samplelist) # get a list of tuples [ (sample, VcfGenotype object) ... ]
for (sample, genotype) in genotype_tuple: #iterate thru and see if they are in affected or unaffected list
if options.model == 'dominant':
if sample in affecteds: # if so ...
affected_genotypes.append( ( sample, genotype.toString(), genotype.isSegregating() ) ) # are they segregating for a non-ref allele?
if sample in unaffecteds:
unaffected_genotypes.append( (sample, genotype.toString(), genotype.isSegregating() ) ) # are they segregating for a non-ref allele?
elif options.model == 'recessive':
if sample in affecteds:
affected_genotypes.append( ( sample, genotype.toString(), genotype.isNonRefHomz() ) ) # are they segregating for a non-ref homoz?
if sample in unaffecteds:
unaffected_genotypes.append( (sample, genotype.toString(), genotype.isNonRefHomz() ) ) # are they segregating for a non-ref non-refhomoz?
else:
sys.stderr.write(options.model + " not supported for genotype discrete filtering ...\n")
if options.model == 'dominant':
#under dominant model, all affecteds should be
#segrgating for non-ref allele and all UN-affecteds should *NOT* be segregating for non-ref allele
#how many affected individuals are segregating for non-ref allele?
count_segregating_affected = [ tpl[2] == True for tpl in affected_genotypes ].count(True)
#how many UN-affected individuals are *NOT* segregating for non-ref allele?
count_segregating_unaffected = [ tpl[2] == False for tpl in unaffected_genotypes ].count(True)
#now if all affects are segregating for the site
# and all the un-affecteds are *not* segregating for the site
# it is a candidate
if count_segregating_affected == len(affecteds):
if count_segregating_unaffected == len(unaffecteds):
print vrec.toStringwithGenotypes()
elif options.model == 'recessive':
#how many affected individuals are segregating for non-ref allele?
#http://stackoverflow.com/a/5684324/1735942
count_homoz_nonref_affected = [ tpl[2] == True for tpl in affected_genotypes ].count(True)
#how many UN-affected individuals are *NOT* segregating for non-ref allele?
count_homoz_ref_unaffected = [ tpl[2] == False for tpl in unaffected_genotypes ].count(True)
#now if all affects are homoz nonref for the site
# and all the un-affecteds are homoz ref for the site
# it is a candidate
if count_homoz_nonref_affected == len(affecteds):
if count_homoz_ref_unaffected == len(unaffecteds):
print vrec.toStringwithGenotypes()
else:
sys.stderr.write(options.model + " not supported for genotype discrete filtering ...\n")