def loadDataFromVCF():
'constructs list of sample objects, each with a genotype dictionary'
vcfFN = Sample.args.dataFN
vcfFile, vcfReader = utils.getCSVreader(vcfFN, delimiter='\t')
Sample.setSampleListFromVCFheader(vcfReader)
Sample.errAndLog('%sReading genotype data...\n %s\n\n' % \
(utils.DASHES, vcfFN))
for lineList in vcfReader:
position = int(lineList[1])
if position in Sample.tree.snpPosSet:
genoList = lineList[Sample.config.vcfStartCol:]
for sample in Sample.sampleList:
genotype = genoList[sample.sampleIndex].split(':')[0]
if genotype == Sample.config.missingGenotype:
continue
elif Sample.config.runFromVCF: # as opposed to .vcf4
ref, alt = lineList[3:5]
if genotype == '0':
genotype = ref
elif genotype == '1':
genotype = alt
sample.addGeno(position, genotype)
vcfFile.close()
def processSampleMajorTxtandCallHaplogroups():
'''
reads in sample major data, calling haplogroup for each line.
returns list of sample objects with genotype data purged.
assumed format:
row 1 = physical coordinates
column 1 = sample ID
'''
genoFN = Sample.args.dataFN
genoFile, genoReader = utils.getCSVreader(genoFN, delimiter='\t')
Sample.errAndLog('%sReading genotype data:\n %s\n\n' % \
(utils.DASHES, genoFN))
# determine relevant physical coordinates and corresponding columns
allPositionsList = [
int(position) for position in genoReader.next()[1:]
]
columnPositionTupleList = list()
for column, position in enumerate(allPositionsList):
if position in Sample.tree.snpPosSet:
columnPositionTupleList.append((column, position))
# read genotypes, call haplogroups
for genoList in genoReader:
ID, genoList = genoList[0], genoList[1:]
if Sample.args.singleSampleID and ID != Sample.args.singleSampleID:
continue
sample = Sample(ID)
for column, position in columnPositionTupleList:
genotype = genoList[column]
if genotype != Sample.config.missingGenotype:
sample.addGeno(position, genotype)
sample.callHaplogroup()
Sample.sampleList.append(sample)
genoFile.close()