'''
# snps
reader = TsvReader(snpfile, cnames=False)
snplist = list(set(r[snpcol] for r in reader))
reader.close()
from cruzdb import Genome
g = Genome(genome)
outfiletmp = outfile + '.tmp'
writer = TsvWriter(outfiletmp)
for i in range(0, len(snplist), 1000):
chunk = snplist[i:i + 1000]
sql = 'SELECT chrom, chromStart, chromEnd, name, score, strand, refUCSC, alleles, alleleFreqs FROM snp{dbsnpver} WHERE name in ({snps})'.format(
dbsnpver=dbsnpver, snps=', '.join("'{}'".format(s) for s in chunk))
result = g.sql(sql)
for r in result:
allfreqs = dict(zip(r.alleles.split(','),
r.alleleFreqs.split(',')))
reffreq = allfreqs.get(r.refUCSC, '0')
if r.refUCSC in allfreqs:
del allfreqs[r.refUCSC]
if '' in allfreqs:
del allfreqs['']
writer.write([
r.chrom, r.chromStart, r.chromEnd, r.name, r.score, r.strand,
r.refUCSC, ','.join(allfreqs.keys()),
','.join([reffreq] + list(allfreqs.values()))
])
writer.close()
