def test_vcf_round_trip(self):
testFile = self.resourceFile("small.vcf")
ac = ADAMContext(self.ss)
genotypes = ac.loadGenotypes(testFile)
tmpPath = self.tmpFile() + ".vcf"
genotypes.toVariantContexts().saveAsVcf(tmpPath)
savedGenotypes = ac.loadGenotypes(testFile)
self.assertEquals(genotypes._jvmRdd.jrdd().count(),
savedGenotypes._jvmRdd.jrdd().count())
def test_vcf_round_trip(self):
testFile = self.resourceFile("small.vcf")
ac = ADAMContext(self.sc)
genotypes = ac.loadGenotypes(testFile)
tmpPath = self.tmpFile() + ".vcf"
genotypes.toVariantContexts().saveAsVcf(tmpPath)
savedGenotypes = ac.loadGenotypes(testFile)
self.assertEquals(genotypes._jvmRdd.jrdd().count(),
savedGenotypes._jvmRdd.jrdd().count())
def test_transform(self):
testFile = self.resourceFile("random.vcf")
ac = ADAMContext(self.ss)
genotypes = ac.loadGenotypes(testFile)
transformedGenotypes = genotypes.transform(lambda x: x.filter(x.contigName == '1'))
self.assertEquals(transformedGenotypes.toDF().count(), 9)
def test_VariantsPerSampleDistribution(self):
ac = ADAMContext(self.ss)
testFile = self.resourceFile("genodata.v3.test.vcf")
genotypes = ac.loadGenotypes(testFile)
_, data = VariantsPerSampleDistribution(self.ss, genotypes).plotDistributions(testMode= True)
expected = [6, 8, 8, 1, 7, 8]
assert(sum(data) == sum(expected))
def test_load_genotypes(self):
testFile = self.resourceFile("small.vcf")
ac = ADAMContext(self.sc)
reads = ac.loadGenotypes(testFile)
self.assertEqual(reads.toDF().count(), 18)
self.assertEqual(reads._jvmRdd.jrdd().count(), 18)
def test_transform(self):
testFile = self.resourceFile("random.vcf")
ac = ADAMContext(self.sc)
genotypes = ac.loadGenotypes(testFile)
transformedGenotypes = genotypes.transform(lambda x: x.filter(x.contigName == '1'))
self.assertEquals(transformedGenotypes.toDF().count(), 9)
def test_load_genotypes(self):
testFile = self.resourceFile("small.vcf")
ac = ADAMContext(self.ss)
reads = ac.loadGenotypes(testFile)
self.assertEqual(reads.toDF().count(), 18)
self.assertEqual(reads._jvmRdd.jrdd().count(), 18)
def test_HetHomRatioDistribution(self):
ac = ADAMContext(self.ss)
testFile = self.resourceFile("genodata.v3.test.vcf")
genotypes = ac.loadGenotypes(testFile)
_, data = HetHomRatioDistribution(self.ss, genotypes, sample=1.0).plot(testMode= True)
expected = sorted([5.0, 0.6, 0.14, 0.17, 1.67])
sorted_data = sorted(data)
assert( expected == [ round(x,2) for x in sorted_data ])
def test_GenotypeCallRatesDistribution(self):
ac = ADAMContext(self.ss)
testFile = self.resourceFile("genodata.v3.test.vcf")
genotypes = ac.loadGenotypes(testFile)
_, data = GenotypeCallRatesDistribution(self.ss, genotypes, sample=1.0).plot(testMode= True)
expected = sorted([0.95, 0.88, 0.89, 0.94, 0.93, 0.90])
sorted_data = sorted(data)
assert( expected == [ round(x,2) for x in sorted_data] )
def test_vcf_add_filter(self):
testFile = self.resourceFile("small.vcf")
ac = ADAMContext(self.ss)
genotypes = ac.loadGenotypes(testFile)
tmpPath = self.tmpFile() + ".vcf"
genotypes.toVariantContexts().addFilterHeaderLine("BAD",
"Bad variant.").saveAsVcf(tmpPath)
self.check_for_line_in_file(tmpPath, '##FILTER=<ID=BAD,Description="Bad variant.">')
def test_vcf_sort(self):
testFile = self.resourceFile("random.vcf")
ac = ADAMContext(self.ss)
genotypes = ac.loadGenotypes(testFile)
tmpPath = self.tmpFile() + ".vcf"
genotypes.toVariantContexts().sort().saveAsVcf(tmpPath,
asSingleFile=True)
self.checkFiles(tmpPath, self.resourceFile("sorted.vcf", module='adam-cli'))
def test_VariantsPerSampleDistributionSampling(self):
ac = ADAMContext(self.ss)
testFile = self.resourceFile("genodata.v3.test.vcf")
genotypes = ac.loadGenotypes(testFile)
_, data = VariantsPerSampleDistribution(self.ss, genotypes, sample=0.9).plotDistributions(testMode= True)
expected = [6, 8, 8, 1, 7, 8]
# estimated counts should be around real counts
dev = 8
assert(sum(expected) > sum(data) - dev and sum(expected) < sum(data) + dev)
def test_vcf_add_filter(self):
testFile = self.resourceFile("small.vcf")
ac = ADAMContext(self.ss)
genotypes = ac.loadGenotypes(testFile)
tmpPath = self.tmpFile() + ".vcf"
genotypes.toVariantContexts().addFilterHeaderLine("BAD",
"Bad variant.").saveAsVcf(tmpPath)
self.check_for_line_in_file(tmpPath, '##FILTER=<ID=BAD,Description="Bad variant.">')
def test_vcf_sort_lex(self):
testFile = self.resourceFile("random.vcf")
ac = ADAMContext(self.ss)
genotypes = ac.loadGenotypes(testFile)
tmpPath = self.tmpFile() + ".vcf"
genotypes.toVariantContexts().sortLexicographically().saveAsVcf(tmpPath,
asSingleFile=True)
self.checkFiles(tmpPath, self.resourceFile("sorted.lex.vcf", module='adam-cli'))
def test_vcf_sort_lex(self):
testFile = self.resourceFile("random.vcf")
ac = ADAMContext(self.sc)
genotypes = ac.loadGenotypes(testFile)
tmpPath = self.tmpFile() + ".vcf"
genotypes.toVariantContexts().sortLexicographically().saveAsVcf(tmpPath,
asSingleFile=True)
self.checkFiles(tmpPath, self.resourceFile("sorted.lex.vcf"))
def test_vcf_sort(self):
testFile = self.resourceFile("random.vcf")
ac = ADAMContext(self.sc)
genotypes = ac.loadGenotypes(testFile)
tmpPath = self.tmpFile() + ".vcf"
genotypes.toVariantContextRDD().sort().saveAsVcf(tmpPath,
asSingleFile=True)
self.checkFiles(tmpPath, self.resourceFile("sorted.vcf"))
def test_to_variants(self):
testFile = self.resourceFile("small.vcf")
ac = ADAMContext(self.ss)
genotypes = ac.loadGenotypes(testFile)
variants = genotypes.toVariants()
self.assertEqual(variants.toDF().count(), 18)
variants = genotypes.toVariants(dedupe=True)
self.assertEqual(variants.toDF().count(), 6)
def test_vcf_add_info_scalar(self):
testFile = self.resourceFile("small.vcf")
ac = ADAMContext(self.ss)
genotypes = ac.loadGenotypes(testFile)
tmpPath = self.tmpFile() + ".vcf"
genotypes.toVariantContexts().addScalarInfoHeaderLine(
"SC", "Scalar.", bool).saveAsVcf(tmpPath)
self.check_for_line_in_file(
tmpPath, '##INFO=<ID=SC,Number=0,Type=Flag,Description="Scalar.">')
def test_to_variants(self):
testFile = self.resourceFile("small.vcf")
ac = ADAMContext(self.ss)
genotypes = ac.loadGenotypes(testFile)
variants = genotypes.toVariants()
self.assertEquals(variants.toDF().count(), 18)
variants = genotypes.toVariants(dedupe=True)
self.assertEquals(variants.toDF().count(), 6)
def test_vcf_add_info_all_array(self):
testFile = self.resourceFile("small.vcf")
ac = ADAMContext(self.ss)
genotypes = ac.loadGenotypes(testFile)
tmpPath = self.tmpFile() + ".vcf"
genotypes.toVariantContexts().addAllAlleleArrayInfoHeaderLine("RA",
"Array with # alleles.",
float).saveAsVcf(tmpPath)
self.check_for_line_in_file(tmpPath,
'##INFO=<ID=RA,Number=R,Type=Float,Description="Array with # alleles.">')
def test_vcf_add_info_scalar(self):
testFile = self.resourceFile("small.vcf")
ac = ADAMContext(self.ss)
genotypes = ac.loadGenotypes(testFile)
tmpPath = self.tmpFile() + ".vcf"
genotypes.toVariantContexts().addScalarInfoHeaderLine("SC",
"Scalar.",
bool).saveAsVcf(tmpPath)
self.check_for_line_in_file(tmpPath,
'##INFO=<ID=SC,Number=0,Type=Flag,Description="Scalar.">')
def test_vcf_add_format_alts_array(self):
testFile = self.resourceFile("small.vcf")
ac = ADAMContext(self.ss)
genotypes = ac.loadGenotypes(testFile)
tmpPath = self.tmpFile() + ".vcf"
genotypes.toVariantContexts().addAlternateAlleleArrayFormatHeaderLine("AA",
"Array with # alts.",
chr).saveAsVcf(tmpPath)
self.check_for_line_in_file(tmpPath,
'##FORMAT=<ID=AA,Number=A,Type=Character,Description="Array with # alts.">')
def test_vcf_add_format_genotype_array(self):
testFile = self.resourceFile("small.vcf")
ac = ADAMContext(self.ss)
genotypes = ac.loadGenotypes(testFile)
tmpPath = self.tmpFile() + ".vcf"
genotypes.toVariantContexts().addGenotypeArrayFormatHeaderLine("GA",
"Array with # genotypes.",
float).saveAsVcf(tmpPath)
self.check_for_line_in_file(tmpPath,
'##FORMAT=<ID=GA,Number=G,Type=Float,Description="Array with # genotypes.">')
def test_vcf_add_format_genotype_array(self):
testFile = self.resourceFile("small.vcf")
ac = ADAMContext(self.ss)
genotypes = ac.loadGenotypes(testFile)
tmpPath = self.tmpFile() + ".vcf"
genotypes.toVariantContexts().addGenotypeArrayFormatHeaderLine("GA",
"Array with # genotypes.",
float).saveAsVcf(tmpPath)
self.check_for_line_in_file(tmpPath,
'##FORMAT=<ID=GA,Number=G,Type=Float,Description="Array with # genotypes.">')
def test_vcf_add_format_alts_array(self):
testFile = self.resourceFile("small.vcf")
ac = ADAMContext(self.ss)
genotypes = ac.loadGenotypes(testFile)
tmpPath = self.tmpFile() + ".vcf"
genotypes.toVariantContexts().addAlternateAlleleArrayFormatHeaderLine("AA",
"Array with # alts.",
chr).saveAsVcf(tmpPath)
self.check_for_line_in_file(tmpPath,
'##FORMAT=<ID=AA,Number=A,Type=Character,Description="Array with # alts.">')
def test_vcf_add_info_all_array(self):
testFile = self.resourceFile("small.vcf")
ac = ADAMContext(self.ss)
genotypes = ac.loadGenotypes(testFile)
tmpPath = self.tmpFile() + ".vcf"
genotypes.toVariantContexts().addAllAlleleArrayInfoHeaderLine("RA",
"Array with # alleles.",
float).saveAsVcf(tmpPath)
self.check_for_line_in_file(tmpPath,
'##INFO=<ID=RA,Number=R,Type=Float,Description="Array with # alleles.">')
def test_vcf_add_format_scalar(self):
testFile = self.resourceFile("small.vcf")
ac = ADAMContext(self.ss)
genotypes = ac.loadGenotypes(testFile)
tmpPath = self.tmpFile() + ".vcf"
genotypes.toVariantContexts().addScalarFormatHeaderLine("SC",
"Scalar.",
str).saveAsVcf(tmpPath)
self.check_for_line_in_file(tmpPath,
'##FORMAT=<ID=SC,Number=1,Type=String,Description="Scalar.">')
def test_vcf_add_format_scalar(self):
testFile = self.resourceFile("small.vcf")
ac = ADAMContext(self.ss)
genotypes = ac.loadGenotypes(testFile)
tmpPath = self.tmpFile() + ".vcf"
genotypes.toVariantContexts().addScalarFormatHeaderLine(
"SC", "Scalar.", str).saveAsVcf(tmpPath)
self.check_for_line_in_file(
tmpPath,
'##FORMAT=<ID=SC,Number=1,Type=String,Description="Scalar.">')
def test_vcf_add_format_array(self):
testFile = self.resourceFile("small.vcf")
ac = ADAMContext(self.ss)
genotypes = ac.loadGenotypes(testFile)
tmpPath = self.tmpFile() + ".vcf"
genotypes.toVariantContexts().addFixedArrayFormatHeaderLine("FA4",
4,
"Fixed array of 4 elements.",
int).saveAsVcf(tmpPath)
self.check_for_line_in_file(tmpPath,
'##FORMAT=<ID=FA4,Number=4,Type=Integer,Description="Fixed array of 4 elements.">')
def test_vcf_add_format_array(self):
testFile = self.resourceFile("small.vcf")
ac = ADAMContext(self.ss)
genotypes = ac.loadGenotypes(testFile)
tmpPath = self.tmpFile() + ".vcf"
genotypes.toVariantContexts().addFixedArrayFormatHeaderLine(
"FA4", 4, "Fixed array of 4 elements.", int).saveAsVcf(tmpPath)
self.check_for_line_in_file(
tmpPath,
'##FORMAT=<ID=FA4,Number=4,Type=Integer,Description="Fixed array of 4 elements.">'
)
def test_visualize_genotypes(self):
# load file
ac = ADAMContext(self.ss)
testFile = self.resourceFile("genodata.v3.test.vcf")
# read features
genotypes = ac.loadGenotypes(testFile)
gs = GenotypeSummary(self.ss, ac, genotypes)
contig = "chr22"
start = 21079600
end = 21079700
x = gs.viewPileup(contig, start, end)
assert(x != None)
