def processhapmap(): print "parsing hapmap genotypes chrom files" parsegenotypes.parsehapmap() print "now filtering SNPs" b = parsegenotypes.filterSNPs('../genotypes/hapmap') print "{0} SNPs filtered out".format(len(b)) [flips, errors] = parsegenotypes.checkRef('../genotypes/hapmap') print "{0} flips and {1} errors".format(len(flips),len(errors)) #flips = glob.json('../genotypes/hapmapflips') #errors = glob.json('../genotypes/hapmaperrors') parsegenotypes.flipGeno('hapmapGeno', flips, errors)
def processgenotypes(): """parse genotype files and flip them around according to hg19 """ for i, n in enumerate(homedirnames): parsegenotypes.parse1KGvcf(vcffiles[i], names1KG[i]) b = parsegenotypes.filterSNPs(names1KG[i]) print "{0} SNPs filtered out".format(len(b)) c = parsegenotypes.checkRef(n) print "{0} errors and {1} flipped".format(len(c[1]),len(c[0])) #parsegenotypes.corrRef(c[0], n) parsegenotypes.flipGeno(n+'Geno', c[0], c[1])