def writeEvalOutput(self):
self.outputfh.write( "rows are eval genotypes columns comparison genotypes\n")
self.outputfh.write("\t".join(['','AA','AB','BB', './.' ]) +"\n")
rownames=[0,'AA', 1,'AB', 2,'BB', 3,'./.']
for (i, gt) in grouper(2,rownames):
row=self.concordancetable[i,:].tolist()
for r in row:
outstr="\t".join(map(str,r))
self.outputfh.write( gt +"\t"+outstr+"\n")
self.outputfh.write( "matrix sum: \n")
summy=np.sum(self.concordancetable)
self.outputfh.write( str(summy) +"\n")
#now we figure out how many sites were called or not called
self.calledtable[0,0]=self.concordancetable[0:3,0:3].sum()
self.calledtable[0,1]=self.concordancetable[0:3,3].sum()
self.calledtable[1,0]=self.concordancetable[3,0:3].sum()
self.calledtable[1,1]=self.concordancetable[3,3]
self.outputfh.write("\n")
rownames=[ 0,'called', 1,'./.' ]
self.outputfh.write( "rows are eval genotypes columns comparison genotypes\n")
self.outputfh.write( "\t".join(['','called','./.' ]) +"\n" )
for (i, gt) in grouper(2,rownames):
row=self.calledtable[i,:].tolist()
for r in row:
outstr="\t".join(map(str,r))
self.outputfh.write( gt +"\t"+outstr+"\n")
self.outputfh.write( "matrix sum: \n")
summy=np.sum(self.calledtable)
self.outputfh.write( str(summy) +"\n")
self.outputfh.write("\n")
discordance=self.concordancetable[0,1]+self.concordancetable[0,2]+self.concordancetable[1,0]+self.concordancetable[1,2]+self.concordancetable[2,0]+self.concordancetable[2,1]
total=self.concordancetable[0,1]+self.concordancetable[0,2]+self.concordancetable[1,0]+self.concordancetable[1,1]+ self.concordancetable[1,2]+self.concordancetable[2,0]+self.concordancetable[2,1] +self.concordancetable[2,2]
nrd=round( (float(discordance)/float(total)) * 100, 2)
variant_count_evaluation= self.concordancetable[1,1]+ self.concordancetable[1,2]+ self.concordancetable[2,1]+ self.concordancetable[2,2]
variant_count_comparison= self.concordancetable[0,1]+self.concordancetable[0,2]+self.concordancetable[1,1]+self.concordancetable[1,2]+self.concordancetable[2,1]+self.concordancetable[2,2]+self.concordancetable[3,1]+self.concordancetable[3,2]
nrs=round( float(variant_count_evaluation)/float(variant_count_comparison) * 100 , 2)
self.outputfh.write( "NRD: " + str(nrd) +" \n")
self.outputfh.write( "NRS " + str(nrs) +" \n")
outstring=",".join( map(str,melt_lol(self.concordancetable.tolist())) )
self.genotypematrixfh.write(outstring+"\n")
def main():
usage = "usage: %prog [options] nrd.log.vcf\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)
(options, args) = parser.parse_args()
vcfilename = args[0]
basename = os.path.splitext(vcfilename)[0]
vcfobj = VcfFile(vcfilename)
vcfh = open(vcfilename, "r")
nrdallfh = open(basename + ".allgenos.nrd.txt", "w")
nrdtwofh = open(basename + ".twogenos.nrd.txt", "w")
nrdonefh = open(basename + ".onegenos.nrd.txt", "w")
vcfobj.parseMetaAndHeaderLines(vcfh)
samples = vcfobj.getSampleList()
# print samples
# print "#setname\t" + "\t".join(samples)
for vrec in vcfobj.yieldVcfRecordwithGenotypes(vcfh):
outputline = [[vrec.getPos()]]
setname = vrec.returnInfoDict()["set"] # which callset does the site belong to?
outputline.append([setname]) # we aggregate genotypes per sample heere
vrec_ziptuple = vrec.zipGenotypes(samples)
# print vrec_ziptuple
""" Since I'm testing against trio, NRD count can be 1 2 or 3
We keep track of the nrd count and print those records to the appropriate file:
nrdallfh, nrdtwofh, nrdonefh """
nrd_count = 0
for (compare, eval) in grouper(2, vrec_ziptuple):
(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)
if eval_alleletype == comp_alleletype:
continue
outputline.append([eval[0], str(eval_alleletype), compare[0], str(comp_alleletype)])
nrd_count += 1
output = "\t".join(melt_lol(outputline))
""" depending on the nrd count, print the records to appropirate file(s) """
if nrd_count == 3:
nrdallfh.write(output + "\n")
if nrd_count == 2:
nrdtwofh.write(output + "\n")
if nrd_count == 1:
nrdonefh.write(output + "\n")
def main():
usage = "usage: %prog [options] "
parser = argparse.ArgumentParser(description='Calculate non-reference sensitivity (NRS) and non-reference discrepancy (NRD) of VCF files with the same records')
parser.add_argument("-goldvcf", dest='gold', help="VCF with gold standard genotypes you want to compare to")
parser.add_argument("-evalvcf", dest='eval', help="VCF you want to evaluate against the gold standard")
args=parser.parse_args()
nrsfh=open('NRS.log', 'w')
nrdfh=open('NRD.log', 'w')
#matrixfh=open('overall.wes.array.genotype.matrix.csv', 'w')
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] ] )
vcf_readerOne = vcf.Reader(open(args.eval, 'r'),compressed=True)
vcf_readerTwo = vcf.Reader(open(args.gold, 'r'),compressed=True)
vcf_gen1=py_recordgen(vcf_readerOne)
vcf_gen2=py_recordgen(vcf_readerTwo)
FLAG=True
vcf_sample_eval_objects=[]
common_samples=[]
sys.stderr.write("computing per-sample concordance ....\n")
for vrec1, vrec2 in itertools.izip(vcf_gen1, vcf_gen2):
vrec1_samples=[elem.sample for elem in vrec1.samples ]
vrec2_samples=[elem.sample for elem in vrec2.samples ]
if vrec1.CHROM != vrec2.CHROM:
sys.stderr.write("chromosome number does not match!\n")
sys.stderr.write(vrec1.CHROM + " " + vrec2.CHROM + "\n")
sys.exit(1)
if vrec1.POS != vrec2.POS:
sys.stderr.write("chromosome POS does not match!\n")
sys.stderr.write(vrec1.POS + " " + vrec2.POS + "\n")
sys.exit(1)
if vrec1.ID == None: vrec1.ID='.'
if vrec2.ID == None: vrec2.ID='.'
common_samples= [x for x in vrec1_samples if x in vrec2_samples ]
#print len(common_samples)
if FLAG == True:
#vcf_sample_eval_objects = [ VcfSampleEval ('array', 'wes', x) for x in common_samples ]
vcf_sample_eval_objects = [ VcfSampleEval ('gold', 'eval', x) for x in common_samples ]
FLAG=False
gold_eval_genotypes=[] # list of tuples where (sample_name, eval_gt, compare(gold).gt is the order
for s in common_samples:
gold_eval_genotypes.append( [s, vrec1.genotype(s).gt_type, vrec2.genotype(s).gt_type] )
#print gold_eval_genotypes
for eval_obj, eval_genotypes in itertools.izip(vcf_sample_eval_objects, gold_eval_genotypes):
if eval_genotypes[1] == None:
eval_genotypes[1]=3
if eval_genotypes[2] == None:
eval_genotypes[2] = 3
eval_obj.incrementcellcount(eval_genotypes[1],eval_genotypes[2])
concordancetable[eval_genotypes[1], eval_genotypes[2] ]+=1
if eval_genotypes[1] != eval_genotypes[2]:
if (eval_genotypes[1] == 0 or eval_genotypes[1] == 3) and (eval_genotypes[2] == 1 or eval_genotypes[2] == 2):
nrsout="\t".join( [str(vrec1.CHROM), str(vrec1.POS),eval_genotypes[0], vrec1.ID, eval_genotypes[0], str(eval_genotypes[1]), str(eval_genotypes[2]) ] )
nrsfh.write(nrsout+"\n")
if eval_genotypes[1] != 3:
nrdout="\t".join([str(vrec1.CHROM), str(vrec1.POS),eval_genotypes[0], vrec1.ID, eval_genotypes[0], str(eval_genotypes[1]), str(eval_genotypes[2]) ])
nrdfh.write(nrdout+"\n")
#print
concordancefh=open("concordance.txt", 'w')
matrixfh=open("genotype.matrix.csv", 'w')
print "Sample\tNRS\tNRD"
for (eval_obj, sample) in itertools.izip(vcf_sample_eval_objects, common_samples):
(NRS, NRD)=eval_obj.returnNRS_NRD()
outstring="\t".join( [sample, str(NRS), str(NRD)])
print outstring
eval_obj.write_genotype_matrix()
outstring=",".join( map(str,melt_lol(concordancetable.tolist())) )
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(vcfilename)[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'])
genotypematrix=".".join([basename, 'genotype.matrix', 'csv'])
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')
genotypematrixfh=open(genotypematrix, '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) ]
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)
#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 (compare, eval) in grouper(2,vrec_ziptuple):
(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
"""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)
if eval_alleletype==0:
if comp_alleletype == 1 or comp_alleletype == 2:
outstring=vrec.toStringwithGenotypes() + "\n"
nrsfh.write( 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 )
if comp_alleletype == 0:
outstring=vrec.toStringwithGenotypes() + "\n"
concordancefh.write( outstring )
if eval_alleletype == 1:
if comp_alleletype == 0 or comp_alleletype == 2:
outstring=vrec.toStringwithGenotypes() + "\n"
nrdfh.write( outstring )
if comp_alleletype == 1:
outstring=vrec.toStringwithGenotypes() + "\n"
concordancefh.write( outstring )
if eval_alleletype == 2:
if comp_alleletype == 0 or comp_alleletype ==1:
outstring=vrec.toStringwithGenotypes() + "\n"
nrdfh.write( outstring )
if comp_alleletype == 2:
outstring=vrec.toStringwithGenotypes() + "\n"
concordancefh.write( outstring )
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")
outstring=",".join( map(str,melt_lol(concordancetable.tolist())) )
genotypematrixfh.write(outstring+"\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 write_genotype_matrix(self):
""" melt the genotypematrix into a CSV of numbers """
outstring=",".join( map(str,melt_lol(self.concordancetable.tolist())) )
self.genotypematrixfh.write(outstring+"\n")
