def get_sex_info():
from short_read_analysis import preprocess_radtag_lane
db = preprocess_radtag_lane.get_table_as_dict('DB_library_data')
sex = dict([(l['sampleid'],l['sex']) for l in db if l.has_key('sex')])
hyb_parent_sex = {}
for l in db:
if l.has_key('sire') and l.has_key('dam'):
if l['sire'].startswith('F1') and l['dam'].startswith('BW'):
hyb_parent_sex[l['sampleid']] = 'M'
elif l['dam'].startswith('F1') and l['sire'].startswith('BW'):
hyb_parent_sex[l['sampleid']] = 'F'
return hyb_parent_sex, sex
def write_spagedi_genotypes(vcf_data,
outfile,
keys_to_write=None,
indiv_to_write=None):
'''generates output intended for SPAGeDi
currently treats all individuals as originating from a single population;
this will need to be elaborated upon
'''
from short_read_analysis import preprocess_radtag_lane
lookup = dict([
(l['sampleid'], l['population'])
for l in preprocess_radtag_lane.get_table_as_dict('DB_library_data')
if l.has_key('population')
])
if keys_to_write is None:
keys_to_write = vcf_data.keys()
keys_to_write.sort(key=lambda x: (x[0], int(x[1])))
if indiv_to_write is None:
indiv_to_write = set()
for k in keys_to_write:
v = vcf_data[k]
indiv_to_write = indiv_to_write.union(set(v['indiv_gt'].keys()))
indiv_to_write = sorted(list(indiv_to_write))
ofh = open(outfile, 'w')
#write header
ofh.write('%s\t1\t0\t%s\t1\t2\n0\nInd\tPop\t%s\n' % \
(len(indiv_to_write),len(keys_to_write), '\t'.join(['%s.%s' % (c,p) for c,p in keys_to_write])))
#write genotypes
for ind in indiv_to_write:
ofh.write('%s\t%s' % (ind, lookup.get(ind, 'pop1')))
for k in keys_to_write:
try:
gt = '/'.join([
str(int(i) + 1)
for i in vcf_data[k]['indiv_gt'][ind]['GT'].split('/')
])
ofh.write('\t' + gt)
except KeyError:
ofh.write('\t0/0')
ofh.write('\n')
ofh.write('END\n')
ofh.close()
def write_spagedi_genotypes(vcf_data, outfile, keys_to_write = None, indiv_to_write = None):
'''generates output intended for SPAGeDi
currently treats all individuals as originating from a single population;
this will need to be elaborated upon
'''
from short_read_analysis import preprocess_radtag_lane
lookup = dict([(l['sampleid'],l['population']) for l in preprocess_radtag_lane.get_table_as_dict('DB_library_data') if l.has_key('population')])
if keys_to_write is None:
keys_to_write = vcf_data.keys()
keys_to_write.sort(key = lambda x: (x[0],int(x[1])))
if indiv_to_write is None:
indiv_to_write = set()
for k in keys_to_write:
v = vcf_data[k]
indiv_to_write = indiv_to_write.union(set(v['indiv_gt'].keys()))
indiv_to_write = sorted(list(indiv_to_write))
ofh = open(outfile,'w')
#write header
ofh.write('%s\t1\t0\t%s\t1\t2\n0\nInd\tPop\t%s\n' % \
(len(indiv_to_write),len(keys_to_write), '\t'.join(['%s.%s' % (c,p) for c,p in keys_to_write])))
#write genotypes
for ind in indiv_to_write:
ofh.write('%s\t%s' % (ind,lookup.get(ind,'pop1')))
for k in keys_to_write:
try:
gt = '/'.join([str(int(i)+1) for i in vcf_data[k]['indiv_gt'][ind]['GT'].split('/')])
ofh.write('\t'+gt)
except KeyError:
ofh.write('\t0/0')
ofh.write('\n')
ofh.write('END\n')
ofh.close()
else:
print >> sys.stderr, 'no matching genotypes for pheno line %s' % pd['id']
else:
print >> sys.stderr, 'no id in %s' % pd
return phenomaploci,phenomap
if __name__ == '__main__':
db,mapfile,outfile = sys.argv[1:4]
if ',' in mapfile:
mapf,mIDf = m.split(',')
else:
mapf = mapfile
mIDf = False
if ',' in db:
phenotypes = []
for db_i in db.split(','):
phenotypes.extend(preprocess_radtag_lane.get_table_as_dict(db_i,suppress_fc_check=True))
else:
phenotypes = preprocess_radtag_lane.get_table_as_dict(db,suppress_fc_check=True)
maploci,genotypes = extract_genotypes_from_mclgr.load_cross_radtag_genotypes(mapf,mIDf)
phenomaploci,phenomap = add_pheno_to_map(phenotypes,maploci,genotypes)
print >> sys.stderr, '%s pheno+map loci, %s lines' % (len(phenomaploci),len(phenomap))
og,mID = extract_genotypes_from_mclgr.output_cross_radtag_genotypes(phenomaploci,phenomap,outfile)
