def test_overlaps_but_not_contains(self):
# should get gene2 and gene3
rules = rule_parser.Parser(
"\n".join([
"RULE Overlap CUTOFF 25 NEIGHBOURHOOD 5 CONDITIONS modelB and modelF "
"RULE OverlapImpossible CUTOFF 25 NEIGHBOURHOOD 5 CONDITIONS modelA and modelF"
]), self.test_names).rules
detected_types, cluster_type_hits = hmm_detection.apply_cluster_rules(
self.record, self.results_by_id, rules)
assert detected_types == {
"GENE_2": {
"Overlap": {"modelB"}
},
"GENE_3": {
"Overlap": {"modelF"}
}
}
assert cluster_type_hits == {"Overlap": {"GENE_2", "GENE_3"}}
# only 1 cluster should be found, since it requires both genes
# if forming clusters by .is_contained_by(), 2 clusters will be formed
# if finding rule hits uses .is_contained_by(), no clusters will be formed
rules_by_name = {rule.name: rule for rule in rules}
clusters = hmm_detection.find_protoclusters(self.record,
cluster_type_hits,
rules_by_name)
assert len(clusters) == 1
assert clusters[0].product == "Overlap"
assert clusters[0].core_location.start == 30000
assert clusters[0].core_location.end == 90000
def test_apply_cluster_rules(self):
detected_types, cluster_type_hits = hmm_detection.apply_cluster_rules(
self.record, self.results_by_id, self.rules)
for gid in detected_types:
detected_types[gid] = set(detected_types[gid])
expected_types = {
"GENE_1":
set(["MetaboliteA", "MetaboliteB", "MetaboliteC", "MetaboliteD"]),
"GENE_2":
set(["MetaboliteC", "MetaboliteD"]),
"GENE_3":
set(["Metabolite0"]),
"GENE_4":
set(["MetaboliteA"]),
"GENE_5":
set(["Metabolite1", "MetaboliteA"])
}
assert detected_types == expected_types
assert cluster_type_hits == {
"MetaboliteA": {"GENE_1", "GENE_4", "GENE_5"},
"MetaboliteB": {"GENE_1"},
"MetaboliteC": {"GENE_1", "GENE_2"},
'MetaboliteD': {'GENE_1', 'GENE_2'},
'Metabolite0': {'GENE_3'},
'Metabolite1': {'GENE_5'}
}
