def test_genbank(self):
dummy_record = Record(Seq("A"*100, generic_dna))
clusters = [create_protocluster(3, 20, "prodA"),
create_protocluster(25, 41, "prodB")]
for cluster in clusters:
dummy_record.add_protocluster(cluster)
subregion = SubRegion(FeatureLocation(35, 71), "test", 0.7)
dummy_record.add_subregion(subregion)
candidate = CandidateCluster(CandidateCluster.kinds.NEIGHBOURING, clusters)
dummy_record.add_candidate_cluster(candidate)
region = Region(candidate_clusters=[candidate],
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
print(bio[0].features)
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_rules(self):
cluster = CandidateCluster(CandidateCluster.kinds.INTERLEAVED,
self.record.get_protoclusters())
assert cluster.detection_rules == [
cluster.detection_rule
for cluster in self.record.get_protoclusters()
]
def test_comparison(self):
candidate = CandidateCluster(CandidateClusterKind.NEIGHBOURING,
[create_cluster(5, 10, 20, 25, "a")])
longer = CandidateCluster(CandidateClusterKind.NEIGHBOURING,
[create_cluster(5, 10, 40, 45, "a")])
after = CandidateCluster(CandidateClusterKind.NEIGHBOURING,
[create_cluster(10, 20, 40, 45, "a")])
def check(first, second):
assert first < second
assert first < second.location
assert sorted([second, first]) == [first, second]
check(candidate, after)
check(longer, candidate)
check(longer, after)
assert sorted([after, candidate, longer]) == [longer, candidate, after]
def test_conversion(self):
kind = CandidateClusterKind.INTERLEAVED
original = CandidateCluster(kind,
self.record.get_protoclusters(),
smiles="dummy smiles",
polymer="dummy polymer")
self.record.add_candidate_cluster(original)
assert original.products == ["a"]
assert len(original.protoclusters) == 1
bios = original.to_biopython()
assert len(bios) == 1
bio = bios[0]
assert bio.qualifiers["product"] == ["a"]
assert bio.qualifiers["kind"] == [str(kind)]
assert bio.qualifiers["candidate_cluster_number"] == [
str(original.get_candidate_cluster_number())
]
assert bio.qualifiers["SMILES"] == ["dummy smiles"]
assert bio.qualifiers["polymer"] == ["dummy polymer"]
assert bio.qualifiers["contig_edge"] == ["True"]
regenerated = CandidateCluster.from_biopython(bio)
assert isinstance(regenerated, TemporaryCandidateCluster)
assert regenerated.products == original.products
assert regenerated.location == original.location
assert regenerated.smiles_structure == original.smiles_structure
assert regenerated.polymer == original.polymer
proto_numbers = [
cluster.get_protocluster_number()
for cluster in self.record.get_protoclusters()
]
assert regenerated.protoclusters == proto_numbers
assert regenerated.kind == original.kind
real = regenerated.convert_to_real_feature(self.record)
assert isinstance(real, CandidateCluster)
assert len(real.protoclusters) == len(self.record.get_protoclusters())
for reference, record_cluster in zip(real.protoclusters,
self.record.get_protoclusters()):
assert reference is record_cluster
# attempt a conversion with a record missing the cluster
self.record.clear_protoclusters()
with self.assertRaisesRegex(ValueError,
"Not all referenced clusters are present"):
regenerated.convert_to_real_feature(self.record)
def test_unique_clusters(self):
protoclusters = [
create_protocluster(i, 10, product=prod)
for i, prod in enumerate("ABC")
]
candidates = [
CandidateCluster(CandidateCluster.kinds.INTERLEAVED,
protoclusters[:2]),
CandidateCluster(CandidateCluster.kinds.INTERLEAVED,
protoclusters[1:])
]
assert protoclusters[1] in candidates[
0].protoclusters and protoclusters[1] in candidates[1].protoclusters
region = Region(candidate_clusters=candidates)
unique_clusters = region.get_unique_protoclusters()
# if the protocluster in both candidates is repeated, there'll be an extra
assert len(unique_clusters) == 3
assert unique_clusters == protoclusters
def test_core(self):
protos = [
create_cluster(5, 10, 20, 25, "a"),
create_cluster(30, 40, 50, 60, "b")
]
cluster = CandidateCluster(CandidateClusterKind.NEIGHBOURING,
protos,
smiles="dummy",
polymer="dummy")
assert cluster.core_location == FeatureLocation(10, 50)
def test_conversion(self):
kind = CandidateClusterKind.INTERLEAVED
original = CandidateCluster(kind,
self.record.get_protoclusters(),
smiles="dummy smiles",
polymer="dummy polymer")
self.record.add_candidate_cluster(original)
assert original.products == ["a"]
assert len(original.protoclusters) == 1
bios = original.to_biopython()
assert len(bios) == 1
bio = bios[0]
assert bio.qualifiers["product"] == ["a"]
assert bio.qualifiers["kind"] == [str(kind)]
assert bio.qualifiers["candidate_cluster_number"] == [
str(original.get_candidate_cluster_number())
]
assert bio.qualifiers["SMILES"] == ["dummy smiles"]
assert bio.qualifiers["polymer"] == ["dummy polymer"]
assert bio.qualifiers["contig_edge"] == ["True"]
real = CandidateCluster.from_biopython(bio, record=self.record)
assert isinstance(real, CandidateCluster)
assert len(real.protoclusters) == len(self.record.get_protoclusters())
for reference, record_cluster in zip(real.protoclusters,
self.record.get_protoclusters()):
assert reference is record_cluster
# attempt a conversion with a record missing the cluster
self.record.clear_protoclusters()
with self.assertRaisesRegex(
ValueError,
"record does not contain all expected protoclusters"):
CandidateCluster.from_biopython(bio, record=self.record)
# and with no record
with self.assertRaisesRegex(ValueError, "record instance required"):
CandidateCluster.from_biopython(bio)
def test_sideloaded(self):
clusters = [
create_protocluster(3, 20, "prodA"),
SideloadedProtocluster(FeatureLocation(25, 41),
FeatureLocation(25, 41), "external",
"prodB")
]
candidate = CandidateCluster(CandidateCluster.kinds.NEIGHBOURING,
clusters)
subregions = [
SubRegion(FeatureLocation(35, 71), "test", 0.7),
SideloadedSubRegion(FeatureLocation(45, 61), "external")
]
region = Region(candidate_clusters=[candidate], subregions=subregions)
sideloaded = region.get_sideloaded_areas()
assert len(sideloaded) == 2
assert sideloaded[0] is clusters[1]
assert sideloaded[1] is subregions[1]
def test_smiles_and_polymer(self):
cluster = CandidateCluster(CandidateCluster.kinds.INTERLEAVED,
self.record.get_protoclusters())
assert cluster.smiles_structure is None
assert cluster.polymer is None
def test_no_clusters(self):
with self.assertRaisesRegex(ValueError,
"cannot exist without at least one"):
CandidateCluster(CandidateCluster.kinds.INTERLEAVED, [])
def test_bad_kind(self):
with self.assertRaisesRegex(TypeError,
"should be CandidateClusterKind"):
CandidateCluster("berf", self.record.get_protoclusters())