def test_tajima():
with Capturing() as out:
tajima.main([
"tajima", "--no-header", "100000", "1000", "test_data/test.vcf.gz"
])
assert out[0] == 'I\t6000\t106000\t2\t1\t-0.740993868265'
assert out[-1] == 'X\t17567000\t17667000\t2\t1\t-0.740993868265'
def test_sanger():
if not os.path.exists(os.path.expanduser("~/.genome/WBcel235/WBcel235.fa.gz")):
genome.main(["genome","ncbi","--ref=WBcel235"])
with Capturing() as out:
primer.main(["primer", "sanger", "--ref=WBcel235","--region=I:542216-543215", "test_data/test.vcf.gz"])
t = eval(str(out))[1].split("\t")[8:10]
assert t == ['GAGAAGGACGGGACCCTTTG', 'aGGCCAGAACCTCGTGAAAC']
def test_template():
if not os.path.exists(os.path.expanduser("~/.genome/WBcel235/WBcel235.fa.gz")):
genome.main(["genome","ncbi","--ref=WBcel235"])
with Capturing() as out:
primer.main(["primer", "template", "--size=500", "--ref=WBcel235","--region=I:1-100000", "test_data/test.vcf.gz"])
t = eval(str(out))[1].split("\t")[6][0:20]
assert t == "ATTTCCCTCTCCGGGAAATG"
def test_snip():
if not os.path.exists(os.path.expanduser("~/.genome/WBcel235/WBcel235.fa.gz")):
genome.main(["genome","ncbi","--ref=WBcel235"])
with Capturing() as out:
primer.main(["primer", "snip", "--size=500", "--ref=WBcel235","--region=I:542216-543215", "test_data/test.vcf.gz"])
t = eval(str(out))[1].split("\t")[7:9]
assert t == ['496:496,184', '429,496:429,67,184']
def test_compare_vcftools():
"""
Compare the Tajima's D Calculation with vcftools output.
"""
comm = ["vcftools", "--TajimaD", "100000", "--gzvcf", "test_data/test.vcf.gz"]
out, err = Popen(comm, stdout=PIPE, stderr=PIPE).communicate()
vcftools_tajima = open("out.Tajima.D", 'r').read().splitlines()
vcftools_tajima = [x.split("\t")[0:4] for x in vcftools_tajima]
with Capturing() as out:
tajima.main(["tajima","--no-header","100000", "100000", "test_data/test.vcf.gz"])
vcftools_tajima = dict([(x[0] + ":" + x[1], autoconvert(x[3])) for x in vcftools_tajima if x[3] != "nan"])
out = [x.split("\t") for x in out]
vcfkit_tajima = dict([(x[0] + ":" + x[1], autoconvert(x[5])) for x in out])
for k in list(vcfkit_tajima.keys()):
assert nearly_equal(vcftools_tajima[k], vcfkit_tajima[k], sig_fig = 3) is True
def test_call_DL238():
if not os.path.exists(
os.path.expanduser("~/.genome/WBcel235/WBcel235.fa.gz")):
genome.main(["genome", "ncbi", "--ref=WBcel235"])
with Capturing() as out:
call.main([
"call", "test_data/DL238.ab1", "--ref=WBcel235", "--vcf-sites",
"test_data/DL238.vcf.gz"
])
out = eval(str(out))
assert len(out) == 5
out = out[1].split("\t")
assert out[0] == "X"
assert int(out[1]) == 14557228
assert out[2] == out[3]
assert out[5] == out[6]
assert out[9] == "TN"
def test_sample_hom_gt():
with Capturing() as out:
calc.main(["calc", "sample_hom_gt", "test_data/test.vcf.gz"])
assert out[0] == 'sample\tfreq_of_gt\tn_gt_at_freq'
assert out[10] == 'AB1\t10\t8'
def test_tajima():
with Capturing() as out:
tajima.main(["tajima","--no-header","100000", "1000", "test_data/test.vcf.gz"])
assert round(float(out[0].split("\t")[5]), 3) == -0.741
def test_spectrum_genotypes_frequency():
with Capturing() as out:
calc.main(["calc", "genotypes", "test_data/test.vcf.gz"])
assert out[-1] == '1\t0\t0\t12\t2'
def test_spectrum_alleles_count():
with Capturing() as out:
calc.main(["calc", "spectrum", "test_data/test.vcf.gz"])
assert round(float(out[-2].split("\t")[1]), 5) == 0.03571
def test_phylo_upgma():
with Capturing() as out:
comm = ["phylo", "tree", "upgma", "test_data/test.vcf.gz"]
phylo.main(comm)
h = hashlib.sha224(str(out)).hexdigest()
assert h == "e3ef017c77bca5fd3feef7ed6215a37a5f0bb41101c125b3e493049e"
def test_spectrum_genotypes_count():
with Capturing() as out:
calc.main(["calc", "genotypes", "test_data/test.vcf.gz"])
assert out[0] == 'n\tref\thet\talt\tmis'
assert out[-1] == '1\t0\t0\t12\t2'
def test_phylo_nj():
with Capturing() as out:
phylo.main(["phylo", "tree", "nj", "data/test.vcf.gz"])
h = hashlib.sha224(str(out)).hexdigest()
assert h == "6c21e0508729c604d403a29cb40dca810455009fec793a9a99da9927"
def test_phylo_fasta():
with Capturing() as out:
phylo.main(["phylo", "fasta", "test_data/test.vcf.gz"])
h = hashlib.sha224(str(out)).hexdigest()
assert h == "81eda4b80e96eed31749e0a28d1acbd345fcd216023d17735978e999"
def test_vars():
with Capturing() as out:
result = command.main(['--flag'])
assert True
def test_phylo_nj():
with Capturing() as out:
phylo.main(["phylo", "tree", "nj", "test_data/test.vcf.gz"])
h = hashlib.sha224(str(out)).hexdigest()
assert h == "96cdd2d7221bcbea8d86e099fdc1af02594d9dcad4daf8a5f85d0557"
def test_phylo_fasta():
with Capturing() as out:
phylo.main(["phylo", "fasta", "test_data/test.vcf.gz"])
last_line = out[-1]
assert 2958 == len(last_line)
assert last_line.startswith("AANNCTC")
def test_phylo_upgma():
with Capturing() as out:
phylo.main(["phylo", "tree", "upgma", "test_data/test.vcf.gz"])
line = out[25]
assert line.startswith("RC301:0.085")
def test_phylo_nj():
with Capturing() as out:
phylo.main(["phylo", "tree", "nj", "test_data/test.vcf.gz"])
line = out[24]
assert line.startswith("DL200:0.1324")
def test_phylo_fasta():
with Capturing() as out:
phylo.main(["phylo", "fasta", "data/test.vcf.gz"])
h = hashlib.sha224(str(out)).hexdigest()
assert h == "610ba5d2b533d730b6e9fb3005453d3d94710c9021fa5ca46fb5d7d8"
def test_phylo_upgma():
with Capturing() as out:
comm = ["phylo", "tree", "upgma", "data/test.vcf.gz"]
phylo.main(comm)
h = hashlib.sha224(str(out)).hexdigest()
assert h == "cd58f6912c40715ef5b2b1d8a381743454eb42cc6d0ba8a6c847ea83"
def test_square():
with Capturing() as out:
result = command.main(['--square', '20'])
assert int(out[0]) == 400
def test_spectrum_alleles_count():
with Capturing() as out:
calc.main(["calc", "spectrum", "data/test.vcf.gz"])
assert out[-2] == '23\t0.0357142857143'