def main():
usage = "usage: %prog [options] arg"
parser = OptionParser(usage)
usage = "usage: %prog [options] file.vcf \n print summary information about site depth in records of a VCF file\n"
parser = OptionParser(usage)
parser.add_option("--max", type="int", dest="max", help="skip records that are greater than or equal to max (default sys.maxint)", default=sys.maxint)
#parser.add_option("--v", action="store_true", dest="snp", help="restrict analysis to SNPs (must have INFO ID SNP in header")
(options, args)=parser.parse_args()
vcfilename=args[0]
fileName, fileExtension = os.path.splitext(vcfilename)
#nuller.12:80717441..80717681.vcf
regionpattern='nuller.(\d+):(\d+)..(\d+)'
results=re.search(regionpattern,fileName ).groups()
regionstr="\t".join(list(results))
vcfh=open(vcfilename,'r')
#instantiate a VcfFile object
vcfobj=VcfFile(vcfilename)
#parse its metainfo lines (ones that begin with ##)
vcfobj.parseMetaLines(vcfh)
descriptors = vcfobj.getMetaInfoDescription()
infoids=[]
for (tag, description) in descriptors:
infoids.append(tag)
if 'DP' not in infoids:
sys.stderr.write("DP tag not in ##INFO headers!")
exit(1)
vcfh.seek(0)
vcfobj.parseHeaderLine(vcfh)
pattern='DP=(\d+)'
depth_list=[]
for vrec in vcfobj.yieldVcfRecord(vcfh):
dp=re.search(pattern, vrec.getInfo() ).groups()[0]
if dp == None:
sys.stderr.write("unable to parse DP value from INFO field\n")
continue
else:
if int(dp) >= options.max: continue
depth_list.append(int(dp))
maxDP=max( array (depth_list))
minDP= min (array (depth_list))
medianDP=median (array (depth_list))
meanDP=mean( array(depth_list))
length=len(depth_list)
outstr="\t".join([regionstr, str(maxDP), str(minDP), str(medianDP), str(meanDP), str(length)])
print outstr
def main():
usage = "usage: %prog [options] file.vcf"
parser = OptionParser(usage)
parser.add_option("--filter", type="string", dest="filter", help="analyze only those records matching filter (default is None)", default=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)
(options, args)=parser.parse_args()
vcfilename=args[0]
vcfh=open(vcfilename,'r')
#instantiate a VcfFile object
vcfobj=VcfFile(vcfilename)
#parse its metainfo lines (ones that begin with ##)
vcfobj.parseMetaLines(vcfh)
vcfobj.addMetaInfoHeader("CR", "D", 1, "site call rate")
vcfobj.printMetaLines()
vcfh.seek(0)
vcfobj.parseHeaderLine(vcfh)
vcfobj.printHeaderLine()
samplelist = vcfobj.getSampleList()
sampleCalls={} #key sample name value #called genotypes
for s in samplelist: sampleCalls[s]=0
totalrecords=0
for vrec in vcfobj.yieldVcfRecordwithGenotypes(vcfh ):
if vrec.getFilter() != options.filter and options.filter != None : continue
totalrecords+=1
sitecallrate=vrec.siteCallrate()
vrec.appendInfoString("CR="+str(sitecallrate))
vrec.sampleCallrate(samplelist,sampleCalls)
#print vrec.toStringwithGenotypes()
for s in samplelist:
callrate=float(sampleCalls[s])/float(totalrecords)
print s, sampleCalls[s], totalrecords, callrate
def main():
usage = "usage: %prog [options] maf file.vcf"
parser = OptionParser(usage)
parser.add_option("--maftag", type="string", dest="maftag", help="INFO tag id that annotates the allele freq of the record", default="AF")
parser.add_option("--variantag", type="string", dest="vtag", help="INFO tag that annotates the type of variant type", default="VT")
parser.add_option("--variantype", type="string", dest="variantype", help="type of variant (SNP INS DEL)", default=None)
parser.add_option("--filter", type="string", dest="filter", help="extract records matching filter (default is None)", default=None)
parser.add_option("--noheader", action="store_true", dest="noheader", help="VCF file has no header file", default=False)
parser.add_option("--quiet", action="store_true", dest="quiet", help="don't print vcf output to stdout", default=False)
parser.add_option("--leq", type="float", dest="leq", default=1.0, help="keep variants with AF <= (default 1)")
parser.add_option("--geq", type="float", dest="geq", default=0.0, help="keep variants with AF >= (default 0)")
(options, args)=parser.parse_args()
if len(args)!=1:
sys.stderr.write(usage+"\n")
exit(1)
vcfilename=args[0]
#maf=float(args[0])
freqfh=open('freq.log', 'w')
vcfh=open(vcfilename,'r')
#instantiate a VcfFile object
vcfobj=VcfFile(vcfilename)
#parse its metainfo lines (ones that begin with ##)
if options.noheader == False:
vcfobj.parseMetaLines(vcfh)
#vcfobj.printMetaLines()
descriptors = vcfobj.getMetaInfoDescription()
infoids=[]
for (tag, description) in descriptors:
infoids.append(tag)
if options.maftag not in infoids and options.maftag != 'QUAL' and options.noheader == False:
sys.stderr.write(options.maftag + " tag not in ##INFO headers!\n")
exit(1)
if options.vtag not in infoids and options.vtag != 'QUAL' and options.noheader==False:
sys.stderr.write(options.vtag + " tag not in ##INFO headers!\n")
exit(1)
#vcfh.seek(0)
if options.noheader == False:
vcfobj.parseHeaderLine(vcfh)
if options.variantype==None:
variantpattern=options.vtag+'=(\w+);'
else:
variantpattern=options.vtag+'=('+options.variantype+');'
mafpattern=options.maftag+'=(0.\d+)'
#print mafpattern, variantpattern
for dataline in vcfobj.yieldVcfDataLine(vcfh):
#print dataline
fields=dataline.strip().split('\t')
(chrom,pos,id,ref,alt,qual,filtercode,info)=fields[0:8]
#if filtercode != options.filter and options.filter != None : continue
if re.search(variantpattern, info ) == None:
#sys.stderr.write("no variant pattern\n")
continue
variant_type=re.search(variantpattern, info ).groups()[0]
if re.search(mafpattern, info ) == None:
#sys.stderr.write("No mafpattern!\n")
#sys.stderr.write(dataline+"\n")
continue
maf_value=re.search(mafpattern, info ).groups()[0]
if float(maf_value) <= options.leq and float(maf_value) >= options.geq:
if options.quiet == False:
print dataline
logstring="\t".join([chrom,pos,id,ref,alt,variant_type, options.maftag, maf_value])
freqfh.write(logstring+'\n')
