Skip to content

Commit

Permalink
Merge pull request #266 from sambrightman/called-definition
Browse files Browse the repository at this point in the history
Allow partially-called genotypes to be considered called
  • Loading branch information
martijnvermaat committed Feb 15, 2017
2 parents 0711a91 + d91ec5e commit 476169c
Show file tree
Hide file tree
Showing 3 changed files with 13 additions and 2 deletions.
4 changes: 2 additions & 2 deletions vcf/model.py
Expand Up @@ -26,7 +26,7 @@ def __init__(self, site, sample, data):
if getattr(self.data, 'GT', None) is not None:
self.gt_alleles = [(al if al != '.' else None) for al in allele_delimiter.split(self.data.GT)]
self.ploidity = len(self.gt_alleles)
self.called = all([al != None for al in self.gt_alleles])
self.called = any(al is not None for al in self.gt_alleles)
self.gt_nums = self.data.GT if self.called else None
else:
#62 a call without a genotype is not defined as called or not
Expand Down Expand Up @@ -65,7 +65,7 @@ def gt_bases(self):
if self.called:
# lookup and return the actual DNA alleles
try:
return self.gt_phase_char().join(str(self.site.alleles[int(X)]) for X in self.gt_alleles)
return self.gt_phase_char().join(str(self.site.alleles[int(X)] if X is not None else '.') for X in self.gt_alleles)
except:
sys.stderr.write("Allele number not found in list of alleles\n")
else:
Expand Down
10 changes: 10 additions & 0 deletions vcf/test/test_vcf.py
Expand Up @@ -1657,22 +1657,32 @@ def test_read_uncalled(self):
gt_nums = [s.gt_nums for s in var.samples]
ploidity = [s.ploidity for s in var.samples]
gt_alleles = [s.gt_alleles for s in var.samples]
gt_type = [s.gt_type for s in var.samples]

if var.POS == 14370:
self.assertEqual(['0|0', None, '1/1'], gt_nums)
self.assertEqual(['G|G', None, 'A/A'], gt_bases)
self.assertEqual([2,2,2], ploidity)
self.assertEqual([['0','0'], [None,None], ['1','1']], gt_alleles)
self.assertEqual([0, None, 2], gt_type)
elif var.POS == 17330:
self.assertEqual([None, '0|1', '0/0'], gt_nums)
self.assertEqual([None, 'T|A', 'T/T'], gt_bases)
self.assertEqual([3,2,2], ploidity)
self.assertEqual([[None,None,None], ['0','1'], ['0','0']], gt_alleles)
self.assertEqual([None, 1, 0], gt_type)
elif var.POS == 1234567:
self.assertEqual(['0/1', '0/2', None], gt_nums)
self.assertEqual(['GTC/G', 'GTC/GTCT', None], gt_bases)
self.assertEqual([2,2,1], ploidity)
self.assertEqual([['0','1'], ['0','2'], [None]], gt_alleles)
self.assertEqual([1, 1, None], gt_type)
elif var.POS == 1234568:
self.assertEqual(['./1', '0/.', None], gt_nums)
self.assertEqual(['./G', 'GTC/.', None], gt_bases)
self.assertEqual([2,2,1], ploidity)
self.assertEqual([[None,'1'], ['0',None], [None]], gt_alleles)
self.assertEqual([1, 1, None], gt_type)
reader._reader.close()


Expand Down
1 change: 1 addition & 0 deletions vcf/test/uncalled_genotypes.vcf
Expand Up @@ -5,3 +5,4 @@
20 14370 rs6054257 G A 29 PASS NS=3 GT 0|0 ./. 1/1
20 17330 . T A 3 q10 NS=3 GT ././. 0|1 0/0
20 1234567 microsat1 GTC G,GTCT 50 PASS NS=3 GT 0/1 0/2 .
20 1234568 . GTC G,GTCT 50 PASS NS=3 GT ./1 0/. .

0 comments on commit 476169c

Please sign in to comment.