############################# program #############################
counter = 0
# read the header
ances = open(args.ancestral, 'r')
ances_words = ances.readline()
output = open(args.output, 'w')
print('Opening the file...')
with open(args.input) as datafile:
header_words = datafile.readline().split()
sampCol = calls.indexSamples(sampleNames, header_words)
print('Creating the output file...')
samples_head = calls.selectSamples(sampCol, header_words)
samples_headP = '\t'.join(str(e) for e in samples_head)
output.write('%s\t%s\t%s\t%s\t%s\n' % ('CHROM', 'POS', 'ANC',
'DER', samples_headP))
# read the second line of the ancestral file
ances_words = ances.readline().split()
if '_' in ances_words[0]:
ances_ch = int(ances_words[0].split('_')[1])
else:
ances_ch = int(ances_words[0].split('chr')[1])
ances_pos = int(ances_words[1])
ances_gt = splitAncestral(ances_words[2])
sampleNames = calls.checkSampleNames(args.samples, args.input)
############################# program #############################
counter = 0
siteNumber = 1
chrPrev = str(1)
print('Opening the file...')
with open(args.input) as datafile:
header_line = datafile.readline()
header_words = header_line.split()
# index samples
sampCol = calls.indexSamples(sampleNames, header_words)
print('Creating the output file...')
fileoutput = open(chrPrev+'_'+args.output, 'w')
for line in datafile:
words = line.split()
chr = str(words[0].split('_')[1])
pos = words[1]
# split chromosomes into separate files
if chr != chrPrev:
fileoutput.close()
fileoutput = open(chr+'_'+args.output, 'w')
chrPrev = chr
siteNumber = 1
counter = 0
print('Opening the file...')
with open(args.input) as datafile:
header_words = datafile.readline().split()
# make output header
print('Creating the output file...')
fileoutput = open(args.output, 'w')
popsP = '\t'.join(str(w) for w in pops)
fileoutput.write("%s\n" % popsP)
for popName in pops:
# index samples
vars()[popName + "Index"] = calls.indexSamples(
vars()[popName + "samples"], header_words)
for line in datafile:
words = line.split()
GT = words[2:]
GTpair = [i for i in list(set(GT))
if i != 'N'] # get the set of alleles, skip missing alleles
popNum = 0
#if ("N" not in GT) and (len(GTpair) == 2) : # skip missing data or non-biallelic
if (len(GTpair) == 2): # skip non-biallelic
for popName in pops:
popNum += 1 # to make correct output. See below
# select genotypes
sGT = calls.selectSamples(vars()[popName + "Index"], words)
############################# program #############################
def all_same(items):
return all(x == items[0] for x in items[1:])
counter = 0
output = open(args.output, 'w')
output.write("#CHR\tPOS\tCommon_alleles\tRare_alleles\n")
print('Opening the file...')
with open(args.input) as datafile:
header_words = datafile.readline().split()
# index samples
sIndex = calls.indexSamples(sNames, header_words)
# create lists for output
sNames = calls.selectSamples(sIndex, header_words)
for line in datafile:
words = line.split()
chr_pos = words[0:2]
chr_posP = '\t'.join(str(e) for e in chr_pos)
# select samples
sGT = calls.selectSamples(sIndex, words)
# define two or one character code
if all(len(i) == 1 for i in sGT):
alleles = calls.OneToTwo(sGT)
parser.add_argument('-s', '--samples', help = 'column names of the samples to process (optional)', type=str, required=False)
args = parser.parse_args()
# check if samples names are given and if all sample names are present in a header
sampleNames = calls.checkSampleNames(args.samples, args.tab)
############################# program #############################
print('Opening the file...')
counter = 0
siftFile = open(args.annotation, 'r')
annotOptions = siftFile.readline().split()
fieldsNames = args.fields.split(',')
fieldsIndex = calls.indexSamples(fieldsNames, annotOptions)
sift_words = siftFile.readline().split()
sift_chr = int(sift_words[0].split('_')[1])
sift_pos = int(sift_words[1])
with open(args.tab) as datafile:
header_words = datafile.readline().split()
# index samples
sampCol = calls.indexSamples(sampleNames, header_words)
# make output header
print('Creating the output file...')
output = open(args.output, 'w')
ouput_header = header_words[0:2] + calls.selectSamples(sampCol, header_words)
outputPhy.write(' %s %s\n' % (NumberSamp, NumberPos))
# process one sample per time to reduce RAM usage
for sample in sampleNames:
# write sample name into file
outputFasta.write(">%s\n" % sample)
outputPhy.write("%s " % sample)
fastaLim = 0 # counter to split sequence in multi-line fasta
with open(args.input) as datafile:
header_words = datafile.readline().split()
# index a sample
sampCol = calls.indexSamples([sample], header_words)
for line in datafile:
words = line.split()
genotype = calls.selectSamples(sampCol, words)
# output only single nucleotide genotypes, insertions are replaced with N.
if len(genotype) == 1:
outputFasta.write(genotype[0])
outputPhy.write(genotype[0])
else:
outputFasta.write('N')
outputPhy.write('N')
# to split sequence in multi-line fasta
for i in familyNames.strip("\"").split(";"):
famName = i.split("[")[0]
famSample = re.split("\[|\]|", i)[1]
Fsamples.append(famSample.split(","))
familySamples[famName] = calls.checkSampleNames(famSample, args.input)
samples = calls.flattenList(Fsamples)
calls.checkSampleNames('ANC', args.input)
calls.checkSampleNames('DER', args.input)
############################# program #############################
outputSNPs = open(args.output + '.snps', 'w')
with open(args.input) as datafile:
header_words = datafile.readline().split()
sampleIndex = calls.indexSamples(samples, header_words)
ANCindex = calls.indexSamples(['ANC'], header_words)
DERindex = calls.indexSamples(['DER'], header_words)
FamilyIndex = {}
phasedLines = {}
for family in familySamples:
FamilyIndex[family] = calls.indexSamples(familySamples[family],
header_words)
phasedLines[family] = []
for line in datafile:
words = line.split()
CHR = words[0]
POS = words[1]
chr_pos = CHR + '_' + POS
