def compare_test_vcf(self, raw_orig_vcf, raw_test_vcf):
raw_orig_vcf = os.path.abspath(raw_orig_vcf)
raw_test_vcf = os.path.abspath(raw_test_vcf)
orig_vars = list(pysam.VariantFile(raw_orig_vcf))
tmp_dirname = util.strip_extensions(raw_test_vcf, ['gz','vcf']) + "-vcomp-" + util.randstr()
with util.TempDir(dirname=tmp_dirname):
orig_vcf = util.bgz_tabix(raw_orig_vcf, self.conf)
test_vcf = util.remove_halfcalls(raw_test_vcf)
test_vcf = util.bgz_tabix(test_vcf, self.conf)
caller_name = util.strip_extensions(test_vcf, ['gz','vcf'])
bed = util.vars_to_bed(orig_vars)
var_results = defaultdict(dict)
var_quals = self.collect_var_quals({caller_name: test_vcf}, bed, orig_vcf)
bamstats = defaultdict(dict)
for normalizer_name, normalizer in self.normalizers.iteritems():
logging.info("--> Running normalizer " + normalizer_name)
normed_orig_vcf = normalizer(orig_vcf, self.conf)
normed_caller_vcf = normalizer(test_vcf, self.conf)
for comparator_name, comparator in self.comparators.iteritems():
logging.info("--> Running comparator " + comparator_name + " (normalizer " + normalizer_name + ")")
all_results = comparator(normed_orig_vcf, normed_caller_vcf, None, self.conf)
single_results = split_results(all_results, bed)
for region, result in zip(util.read_regions(bed), single_results):
match_vars = util.find_matching_var(orig_vcf, region)
if not match_vars:
raise ValueError('Unable to find original variant from region ' + str(region))
result = compare_single_var(result,
region,
normed_orig_vcf,
normed_caller_vcf,
comparator,
"/".join(str(i) for i in match_vars[0].samples[0]['GT']),
self.conf)
key = var_key(match_vars)
if caller_name not in var_results[key]:
var_results[key][caller_name] = defaultdict(dict)
var_results[key][caller_name][normalizer_name][comparator_name] = result
bamstats[key] = {}
# Iterate over all results and write to standard output. We do this here instead of within the loops above
# because it keeps results organized by variant, which makes them easier to look at
self.reporter.write_output(var_results, var_quals, bamstats)
def test_rm_halfcalls(self):
input_vcf = os.path.join(TestUtils.DATA_PATH, TestUtils.HALFCALL_VCF)
try:
no_halfcalls = util.remove_halfcalls(input_vcf)
calls = {}
with open(no_halfcalls) as fh:
for line in fh:
if line[0] == "#":
continue
toks = line.split()
calls[toks[1]] = toks[9]
self.assertTrue(len(calls) == 3)
for pos, gt in calls.iteritems():
self.assertTrue("." not in gt.split(":")[0])
except Exception as ex:
print str(ex)
finally:
os.remove(no_halfcalls)