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"
def add_to_record(self, record: Record) -> None:
""" Adds the found TTA features to the record """
if record.id != self.record_id:
raise ValueError(
"Record to store in and record analysed don't match")
for feature in self.features:
record.add_feature(feature)
def add_to_record(self, record: Record) -> None:
""" Adds the hits as TIGRDomains to the given record """
if record.id != self.record_id:
raise ValueError("Record to store in and record analysed don't match")
for i, hit in enumerate(self.hits):
protein_location = FeatureLocation(hit.protein_start, hit.protein_end)
tigr_feature = TIGRDomain(location_from_string(hit.location),
description=hit.description, protein_location=protein_location,
identifier=hit.identifier, locus_tag=hit.locus_tag)
for key in ["label", "locus_tag", "domain", "evalue",
"score", "translation"]:
setattr(tigr_feature, key, getattr(hit, key))
tigr_feature.detection = "hmmscan"
tigr_feature.domain_id = "{}_{}_{:04d}".format(self.tool, tigr_feature.locus_tag, i + 1)
record.add_feature(tigr_feature)
def store_promoters(promoters: Iterable[Promoter], record: Record) -> None:
"""Store information about promoter sequences to a SeqRecord"""
for promoter in promoters:
# remember to account for 0-indexed start location
new_feature = SeqFeature(FeatureLocation(max(0, promoter.start - 1),
promoter.end),
type="promoter")
new_feature.qualifiers = {
"locus_tag": promoter.get_gene_names(
), # already a list with one or two elements
"seq": [str(promoter.seq)],
}
if isinstance(promoter, CombinedPromoter):
new_feature.qualifiers["note"] = ["bidirectional promoter"]
secmet_version = Feature.from_biopython(new_feature)
secmet_version.created_by_antismash = True
record.add_feature(secmet_version)
