def test_conversion_highlevel(path):
"""
Test whether the high-level GFF3 interface can properly read
the features from a GFF3 file and write these properties to a file
without data changing.
The 'phase' is tested additionally, since it is not part of a
`Feature` object.
"""
gff_file = gff.GFFFile.read(join(data_dir("sequence"), path))
ref_annot = gff.get_annotation(gff_file)
ref_phases = []
for _, _, type, _, _, _, _, phase, _ in gff_file:
if type == "CDS":
ref_phases.append(phase)
gff_file = gff.GFFFile()
gff.set_annotation(gff_file, ref_annot)
temp = TemporaryFile("w+")
gff_file.write(temp)
temp.seek(0)
gff_file = gff.GFFFile.read(temp)
temp.close()
test_annot = gff.get_annotation(gff_file)
test_phases = []
for _, _, type, _, _, _, _, phase, _ in gff_file:
if type == "CDS":
test_phases.append(phase)
assert ref_annot == test_annot
assert test_phases == ref_phases
def test_conversion_highlevel(path):
"""
Test whether the high-level GFF3 interface can properly read
the features from a GFF3 file and write these properties to a file
without data changing.
The 'phase' is tested additionally, since it is not part of a
`Feature` object.
"""
file = gff.GFFFile()
file.read(join(data_dir, path))
ref_annot = gff.get_annotation(file)
ref_phases = []
for _, _, type, _, _, _, _, phase, _ in file:
if type == "CDS":
ref_phases.append(phase)
file = gff.GFFFile()
gff.set_annotation(file, ref_annot)
temp_file_name = biotite.temp_file("gff3")
file.write(temp_file_name)
file = gff.GFFFile()
file.read(temp_file_name)
test_annot = gff.get_annotation(file)
test_phases = []
for _, _, type, _, _, _, _, phase, _ in file:
if type == "CDS":
test_phases.append(phase)
assert ref_annot == test_annot
assert test_phases == ref_phases
def test_genbank_consistency(path):
"""
Test whether the same annotation (if reasonable) can be read from a
GFF3 file and a GenBank file.
"""
gb_file = gb.GenBankFile.read(join(data_dir("sequence"), path))
ref_annot = gb.get_annotation(gb_file)
gff_file = gff.GFFFile.read(join(data_dir("sequence"), path[:-3] + ".gff3"))
test_annot = gff.get_annotation(gff_file)
# Remove qualifiers, since they will be different
# in GFF3 and GenBank
ref_annot = seq.Annotation(
[seq.Feature(feature.key, feature.locs) for feature in ref_annot]
)
test_annot = seq.Annotation(
[seq.Feature(feature.key, feature.locs) for feature in test_annot]
)
for feature in test_annot:
# Only CDS, gene, intron and exon should be equal
# in GenBank and GFF3
if feature.key in ["CDS", "gene", "intron", "exon"]:
try:
assert feature in test_annot
except AssertionError:
print(feature.key)
for loc in feature.locs:
print(loc)
raise