def test_genbank(self):
dummy_record = Record(Seq("A" * 100, generic_dna))
clusters = [
create_cluster(3, 20, "prodA"),
create_cluster(25, 41, "prodB")
]
for cluster in clusters:
dummy_record.add_cluster(cluster)
subregion = SubRegion(FeatureLocation(35, 71), "test", 0.7)
dummy_record.add_subregion(subregion)
supercluster = SuperCluster(SuperCluster.kinds.NEIGHBOURING, clusters)
dummy_record.add_supercluster(supercluster)
region = Region(superclusters=[supercluster], subregions=[subregion])
dummy_record.add_region(region)
with NamedTemporaryFile(suffix=".gbk") as output:
region.write_to_genbank(output.name)
bio = list(seqio.parse(output.name))
assert len(bio) == 1
rec = Record.from_biopython(bio[0], taxon="bacteria")
assert len(rec.get_regions()) == 1
new = rec.get_region(0)
assert new.location.start == 3 - region.location.start
assert new.location.end == 71 - region.location.start
assert new.products == region.products
assert new.probabilities == region.probabilities
def test_prepeptide_adjustment(self):
dummy_record = Record(Seq("A"*400, generic_dna))
subregion = DummySubRegion(start=100, end=300)
dummy_record.add_subregion(subregion)
region = Region(subregions=[subregion])
dummy_record.add_region(region)
dummy_prepeptide = DummyFeature(200, 230, 1, "CDS_motif")
# ensure both FeatureLocation and CompoundLocations are handled appropriately
leader_loc = FeatureLocation(200, 210, 1)
tail_loc = CompoundLocation([FeatureLocation(220, 223, -1), FeatureLocation(227, 230, -1)])
dummy_prepeptide._qualifiers["leader_location"] = [str(leader_loc)]
dummy_prepeptide._qualifiers["tail_location"] = [str(tail_loc)]
dummy_record.add_feature(dummy_prepeptide)
# and add a CDS_motif without either qualifier (e.g. NRPS/PKS motif) to ensure that doesn't break
dummy_record.add_feature(DummyFeature(250, 280, 1, "CDS_motif"))
with NamedTemporaryFile(suffix=".gbk") as output:
region.write_to_genbank(output.name)
bio = list(seqio.parse(output.name))[0]
assert len(bio.features) == 4
found = False
for feature in bio.features:
tail = feature.qualifiers.get("tail_location")
leader = feature.qualifiers.get("leader_location")
if tail and leader:
# the part locations should now be adjusted backwards 100 bases
assert leader == ["[100:110](+)"]
assert tail == ["join{[120:123](-), [127:130](-)}"]
found = True
assert found, "prepeptide feature missing in conversion"
