def test_bridge_in_linear_record(self):
self.seqrec.annotations["topology"] = "linear"
self.seqrec.features.append(self.seqcds)
with self.assertRaisesRegex(ValueError, "Features that bridge"):
Record.from_biopython(self.seqrec, taxon='bacteria')
self.seqrec.features[0] = self.seqgene
with self.assertRaisesRegex(ValueError, "Features that bridge"):
Record.from_biopython(self.seqrec, taxon='bacteria')
def test_bridge_in_linear_record(self):
self.seqrec.annotations["topology"] = "linear"
self.seqrec.features.append(self.seqcds)
with self.assertRaisesRegex(SecmetInvalidInputError,
"cannot determine correct exon ordering"):
Record.from_biopython(self.seqrec, taxon='fungi')
self.seqrec.features[0] = self.seqgene
with self.assertRaisesRegex(SecmetInvalidInputError,
"cannot determine correct exon ordering"):
Record.from_biopython(self.seqrec, taxon='fungi')
def test_record_conversion_from_biopython(self):
before = list(Bio.SeqIO.parse(helpers.get_path_to_nisin_genbank(), "genbank"))[0]
# sort notes, because direct comparisons otherwise are awful
for feature in before.features:
if "note" in feature.qualifiers:
feature.qualifiers["note"] = sorted(feature.qualifiers["note"])
before_features = sorted(map(str, before.features))
type_counts = defaultdict(lambda: 0)
for feature in before.features:
type_counts[feature.type] += 1
record = Record.from_biopython(before, taxon="bacteria")
after = record.to_biopython()
# ensure new features are correct
assert len(before_features) == len(after.features)
for bef, aft in zip(before_features, sorted(map(str, after.features))):
assert bef == aft
# ensure we haven't changed the original record or feature list
assert id(before) != id(after)
assert id(before.features) != id(after.features)
for i in range(len(before.features)):
assert id(before.features[i]) != id(after.features[i])
for bef, aft in zip(before_features, sorted(map(str, before.features))):
assert bef == aft
# ensure that the counts of each match
assert type_counts["CDS"] == len(record.get_cds_features())
assert type_counts["PFAM_domain"] == len(record.get_pfam_domains())
assert type_counts["cluster"] == len(record.get_clusters())
assert type_counts["aSDomain"] == len(record.get_antismash_domains())
def test_cds_with_no_id(self):
self.seqrec.features.append(self.seqcds)
rec = Record.from_biopython(self.seqrec, taxon="bacteria")
cdses = rec.get_cds_features()
assert len(cdses) == 2
assert cdses[0].location.start == 0
assert cdses[0].location.end == 9
assert cdses[0].get_name() == "bridge_LOWER"
assert cdses[1].location.start == 12
assert cdses[1].location.end == 21
assert cdses[1].get_name() == "bridge_UPPER"
def test_cds_split(self):
self.seqrec.features.append(self.seqcds)
print(self.seqcds)
for id_name in ["locus_tag", "gene"]:
self.seqcds.qualifiers[id_name] = ["test"]
rec = Record.from_biopython(self.seqrec, taxon="bacteria")
cdses = rec.get_cds_features()
assert len(cdses) == 2
assert cdses[0].location.start == 0
assert cdses[0].location.end == 9
assert getattr(cdses[0], id_name) == "test_LOWER"
assert cdses[0].get_name() == "test_LOWER"
assert cdses[1].location.start == 12
assert cdses[1].location.end == 21
assert getattr(cdses[1], id_name) == "test_UPPER"
assert cdses[1].get_name() == "test_UPPER"
self.seqcds.qualifiers.pop(id_name)
def test_gene_split(self):
self.seqrec.features.append(self.seqgene)
for id_name in ["locus_tag", "gene"]:
self.seqgene.qualifiers[id_name] = [id_name + "_test"]
expected = id_name + "_test"
rec = Record.from_biopython(self.seqrec, taxon="bacteria")
self.seqgene.qualifiers.pop(id_name)
genes = rec.get_genes()
assert len(genes) == 2
if id_name == "gene":
id_name = "gene_name" # since a Gene doesn't have a gene member
assert genes[0].location.start == 12
assert genes[0].location.end == 21
assert getattr(genes[0], id_name) == expected + "_UPPER"
assert genes[0].get_name() == expected + "_UPPER"
assert genes[1].location.start == 0
assert genes[1].location.end == 9
assert getattr(genes[1], id_name) == expected + "_LOWER"
assert genes[1].get_name() == expected + "_LOWER"
