def test_gaps():
hg19 = Genome("hg19", chromosomes=["chr1"])
assert "chr1" in hg19
assert "chr2" not in hg19
filled = hg19.filled(chromosomes=["chr1"])
hg19.bed_to_sequence(filled)
hg19.delete()
def test_tessellate():
hg19 = Genome("hg19", chromosomes=["chrM"])
filled = hg19.filled(chromosomes=["chrM"])
tessellate_bed(filled, window_size=200, alignment="left")
tessellate_bed(filled, window_size=200, alignment="right")
tessellate_bed(filled, window_size=200, alignment="center")
hg19.delete()
def test_simulated_download_failure():
for _ in Genome("sacCer3", chromosomes=sacCer3_chromosomes).items():
pass
sacCer3 = Genome("sacCer3", chromosomes=sacCer3_chromosomes)
path = sacCer3._chromosome_path("chrI")
with open(path, "w") as f:
f.write("Totally not JSON")
with pytest.raises(Exception):
sacCer3 = Genome("sacCer3", chromosomes=sacCer3_chromosomes)
sacCer3.delete()
def test_create_new_genome_object():
sacCer3 = Genome(
"sacCer3",
chromosomes=sacCer3_chromosomes,
)
for path in glob("{path}/*.json".format(path=sacCer3.path)):
os.remove(path)
with pytest.warns(RuntimeWarning):
sacCer3 = Genome("sacCer3", chromosomes=sacCer3_chromosomes)
sacCer3 = Genome("sacCer3", chromosomes=sacCer3_chromosomes)
sacCer3.gaps()
sacCer3.filled()
str(sacCer3)
sacCer3.delete()
def test_wiggle():
hg19 = Genome("hg19", chromosomes=["chr17"])
filled = hg19.filled(chromosomes=["chr17"])
wiggles = wiggle_bed_regions(
filled,
max_wiggle_size=100,
wiggles=10,
seed=42
)
path = "{pwd}/expected_wiggles.csv".format(
pwd=os.path.dirname(os.path.abspath(__file__))
)
if not os.path.exists(path):
wiggles.to_csv(path, index=False)
pd.testing.assert_frame_equal(
wiggles,
pd.read_csv(path),
check_dtype=False
)
hg19.delete()
def test_gaps():
hg19 = Genome("hg19", chromosomes=["chr1"])
assert "chr1" in hg19
assert "chr2" not in hg19
# Check that no gap is with 0 length
gaps = hg19.gaps(["chr1"])
assert (gaps.chromEnd - gaps.chromStart != 0).all()
# Converting gaps to sequences: should all be Nns
gaps_tesselate = tessellate_bed(gaps, 200, verbose=False)
gaps_sequences = hg19.bed_to_sequence(gaps_tesselate)
for gap in gaps_sequences:
assert set(gap.lower()) == set(["n"])
filled = hg19.filled(["chr1"])
assert (filled.chromEnd - filled.chromStart != 0).all()
filled_tesselate = tessellate_bed(filled, 200, verbose=False)
filled_sequences = hg19.bed_to_sequence(filled_tesselate)
for fl in filled_sequences:
assert "n" not in fl.lower()
filled_tesselate["strand"] = "."
filled_sequences = hg19.bed_to_sequence(filled_tesselate)
for fl in filled_sequences:
assert "n" not in fl.lower()
hg19.delete()