def parseFile(ifile):
#o = open(ifile+'.burttii_filtered','w')
first_line = True
global HEADER
count = 0
#print 'Marksers used: ',count
HEADER='CHROM\tPOS\t'
string='Burtii_20130605 Gifu_20130609 MG20_genomic_20130609 mg004 mg010 mg012 mg019 \
mg023 mg036 mg049 mg051 mg062 mg072 mg073 mg077 mg080 mg082 mg083 mg086 mg089\
mg093 mg095 mg097 mg101 mg107 mg109 mg112 mg113 mg118 mg123 mg128'
for i in string.split():
HEADER += i+'_GC\t' + i+'_GQ\t' + i+'_DP\t'
print HEADER
for line in open(ifile,'r'):
if len(line) > 1 and not line.startswith('#'):
obj = classVCF.VCF(line)
genotypes = obj.genotypes()
### check if the MG20 is 0/0 reference Homozygous
if obj.genotype(2) != '0/1' and len(obj.alts())==1 and len(obj.refs())==1:
#o.write(line+'\n')
count += 1
genotypes = obj.genotypes()
string = obj.chroms()+'\t'+str(obj.poss()) + '\t'
for i in range(len(genotypes)):
if obj.genotype(i) != 'NONE':
string += obj.genotype(i) + '\t' + str(obj.genotypeQual(i)) + '\t' + str(obj.genotypeDepth(i)) + '\t'
else:
string += obj.genotype(i) + '\t' + '0' + '\t' + '0' + '\t'
print string
def parse():
count = 0
then = time.time()
for line in open(ifile, 'r'):
if len(line) > 0 and not line.startswith('##'):
line = line.strip()
obj = classVCF.VCF(line)
count += 1
if count % 10000 == 0:
diff = time.time() - then
minutes, seconds = int(diff) / 60, diff % 60
print 'Number of markers processed: ', '{:9,.0f}'.format(count)
print('Time taken Min:Sec ==> ' + str(minutes) + ':' +
str(round(seconds, 2)))
if line.startswith('#'):
genotypes = obj.genotypes()
g_count = len(genotypes)
dist_mat = {}
for i in range(g_count):
for j in range(g_count):
dist_mat[i, j] = 0
else:
for i in range(g_count):
for j in range(g_count):
geno1 = obj.genotype(i)
geno2 = obj.genotype(j)
dist_mat[i, j] += calc_dist(geno1, geno2)
printOut(dist_mat, genotypes)
def parseFile(ifile):
o = open(ifile + '.MG20filtered', 'w')
global HEADER
count = 0
for line in open(ifile, 'r'):
if len(line) > 1 and not line.startswith('#'):
line = line.strip('\n')
obj = classVCF.VCF(line)
genotypes = obj.genotypes()
### check if the MG20 is 0/0 reference Homozygous
if obj.genotype(2) == '0/0':
o.write(line + '\n')
o.close()
def makeFasta():
seqs = {}
count = 0
for line in open(ifile, 'r'):
if line.startswith('#CHROM'):
line = line.strip('\n')
obj = classVCF.VCF(line)
genotypes_names = obj.genotypes()
if len(line) > 1 and not line.startswith('#'):
line = line.strip('\n')
obj = classVCF.VCF(line)
genotypes = obj.genotypes()
count += 1
if count % 100000 == 0:
print 'Number of markers processed: ', '{:9,.0f}'.format(count)
### check if the burttii is not 0/1 heterogyzous
for i in range(len(genotypes)):
if i in seqs:
if obj.genotype(i) == '0/0':
seqs[i] += obj.refs()
elif obj.genotype(i) == '1/1':
seqs[i] += obj.alts()
else:
seqs[i] += 'N'
else:
if obj.genotype(i) == '0/0':
seqs[i] = obj.refs()
elif obj.genotype(i) == '1/1':
seqs[i] = obj.alts()
else:
seqs[i] = 'N'
printFasta(seqs, genotypes_names)
def parseFile(ifile):
o = open(ifile+'MoreThanMG20coverage','w')
global HEADER
count = 0
for line in open(ifile,'r'):
if len(line) > 1 and not line.startswith('#'):
line = line.strip('\n')
obj = classVCF.VCF(line)
genotypes = obj.genotypes()
### check if the MG20 is 0/0 reference Homozygous
if int(obj.genotypeDepthSUM()) > int(obj.genotypeDepth(2)): ### check if its not only MG20 coverage
if obj.genotype(2) == '0/0':
o.write(line+'\n')
count += 1
print 'Total positions printed:', count
o.close()
def parse_call(chromosome, callable_file):
hash = {}
count = 0
for line in open(callable_file, 'r'):
if len(line) > 1 and not line.startswith('#'):
count += 1
### print the lines processed
if count % 100000 == 0:
print 'Lines processed in callable fraction file: ', chromosome, '{:9,.0f}'.format(
count)
if tokens[0] == chromosome:
line = line.strip()
tokens = line.split('\t')
obj = classVCF.VCF(line)
pos = int(tokens[1])
hash[pos] = str(obj.depth())
return hash
def parseFile(ifile):
o = open(ifile + '.MG20filtered', 'w')
global HEADER
count = 0
for line in open(ifile, 'r'):
if len(line) > 1 and not line.startswith('##'):
line = line.strip('\n')
if line.startswith('#CHROM'):
o.write(line + '\n')
HEADER = line
samples_het = []
samples_homo = []
sample_names = line.split('\t')[9:]
samples_len = len(line.split('\t')) - 9
for i in range(samples_len):
samples_het.append(0)
samples_homo.append(0)
else:
obj = classVCF.VCF(line)
genotypes = obj.genotypes()
### check if the MG20 is 0/0 reference Homozygous
if obj.genotype(2) == '0/0':
o.write(line + '\n')
count += 1
genotypes = obj.genotypes()
for i in range(len(genotypes)):
if obj.genotype(i) == '0/1' or obj.genotype(
i) == '1/0':
samples_het[i] += 1
elif obj.genotype(i) == '0/0' or obj.genotype(
i) == '1/1':
samples_homo[i] += 1
print 'Marksers used: ', count
print 'Sample\tHetCount\tHomoCount\tHetPer\tHomoPer'
for i in range(len(sample_names)):
total = int(samples_het[i]) + int(samples_homo[i])
Het_per = float(samples_het[i]) / total
Homo_per = float(samples_homo[i]) / total
print sample_names[i] + '\t' + str(samples_het[i]) + '\t' + str(
samples_homo[i]) + '\t' + str(Het_per) + '\t' + str(Homo_per)
o.close()
def parseFile(ifile):
o = open(ifile+'.NoBurttiiGifu','w')
global HEADER
count = 0
for line in open(ifile,'r'):
if len(line) > 1 and not line.startswith('#'):
line = line.strip('\n')
obj = classVCF.VCF(line)
genotypes = obj.genotypes()
write_flag = False
### check if the burttii is not 0/1 heterogyzous
for i in range(3,len(genotypes)):
if obj.genotype(i) == '0/1':
write_flag = True
if write_flag == True:
o.write(line+'\n')
count += 1
print 'Total positions printed:', count
o.close()
def parseFile(ifile):
o = open(ifile + '.tbl', 'w')
global HEADER
HEADER = '#Chromosome\tPosition\tCallable\tSNP\tDepth\tgenotypeCalls\tgenotypeCallsHete\tgenotypeCallsHomo\tInbreedingCoeffs\tHaplotypeScores'
count = 0
o.write(HEADER + '\n')
for line in open(ifile, 'r'):
if len(line) > 1 and not line.startswith('#'):
line = line.strip('\n')
obj = classVCF.VCF(line)
genotypes = obj.genotypes()
'''
### check if the MG20 is 0/0 reference Homozygous
if int(obj.genotypeDepthSUM()) > int(obj.genotypeDepth(2)): ### check if its not only MG20 coverage
if obj.genotype(2) == '0/0':
o.write(line+'\n')
count += 1
'''
line = str(obj.chroms())+'\t'+str(obj.poss())+'\t'+ '1' + '\t' + str(obj.variants()) + '\t' + str(obj.depth()) + '\t'+\
str(obj.genotypeCalls()) + '\t' + str(obj.genotypeCallsHete()) + '\t' + str(obj.genotypeCallsHomo()) + '\t' +\
str(obj.InbreedingCoeffs()) + '\t' + str(obj.HaplotypeScores())
o.write(line + '\n')
o.close()