def run_detection(record: Record, options: ConfigType,
module_results: Dict[str, Union[ModuleResults, Dict[str, Any]]]) -> Dict[str, float]:
""" Detect different secondary metabolite clusters, PFAMs, and domains.
Arguments:
record: the Record to run detection over
options: antiSMASH config
module_results: a dictionary mapping a module's name to results from
a previous run on this module, as a ModuleResults subclass
or in JSON form
Returns:
the time taken by each detection module as a dictionary
"""
timings = {} # type: Dict[str, float]
# run full genome detections
for module in [full_hmmer]:
run_module(record, cast(AntismashModule, module), options, module_results, timings)
results = module_results.get(module.__name__)
if results:
assert isinstance(results, ModuleResults)
logging.debug("Adding detection results from %s to record", module.__name__)
results.add_to_record(record)
# generate cluster predictions
logging.info("Detecting secondary metabolite clusters")
for module in [hmm_detection, cassis, clusterfinder_probabilistic]:
run_module(record, cast(AntismashModule, module), options, module_results, timings)
results = module_results.get(module.__name__)
if results:
assert isinstance(results, DetectionResults)
for protocluster in results.get_predicted_protoclusters():
record.add_protocluster(protocluster)
for region in results.get_predicted_subregions():
record.add_subregion(region)
logging.debug("%d protoclusters found", len(record.get_protoclusters()))
logging.debug("%d subregions found", len(record.get_subregions()))
record.create_candidate_clusters()
record.create_regions()
if not record.get_regions():
logging.info("No regions detected, skipping record")
record.skip = "No regions detected"
return timings
logging.info("%d region(s) detected in record", len(record.get_regions()))
# finally, run any detection limited to genes in clusters
for module in [nrps_pks_domains, cluster_hmmer, genefunctions]:
run_module(record, cast(AntismashModule, module), options, module_results, timings)
results = module_results.get(module.__name__)
if results:
assert isinstance(results, ModuleResults)
logging.debug("Adding detection results from %s to record", module.__name__)
results.add_to_record(record)
return timings
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"
def generate_results(record: Record,
options: ConfigType) -> ClusterFinderResults:
""" Find and construct probabilistic cluster areas """
predictions = find_probabilistic_clusters(record, options)
new_areas = []
for prediction in predictions:
new_areas.append(
SubRegion(prediction.location,
tool="clusterfinder",
probability=prediction.probability))
if options.cf_create_clusters:
for area in new_areas:
record.add_subregion(area)
return ClusterFinderResults(record.id,
new_areas,
create=options.cf_create_clusters)
def add_to_record(self, record: Record) -> None:
store_promoters(self.promoters, record)
for cluster in self.subregions:
record.add_subregion(cluster)
def add_to_record(self, record: Record) -> None:
if self.create_new_clusters: # then get_predicted_subregions covered it already
return
for area in self.areas:
record.add_subregion(area)