def setUp(self):
self.func = domain_identification.filter_nonterminal_docking_domains
self.cds = DummyCDS(0, 200)
self.cds.translation = "A" * 200
self.record = DummyRecord(features=[self.cds])
def __init__(self, pid=.5, cds=None, ref_name="ref_cds_name"):
super().__init__("ref_rec", ref_name, cds or DummyCDS(), pid, 1234.,
105., 1e-8)
def run_ranking_as_genes(self, n_terms, c_terms, orders):
genes = {name: DummyCDS(locus_tag=name) for name in orders[0]}
gene_orders = [[genes[k] for k in order] for order in orders]
res = orderfinder.rank_biosynthetic_orders(n_terms, c_terms, gene_orders)
return "".join(gene.locus_tag for gene in res)
def setUp(self):
self.gene_mapping = {"a": DummyCDS(1, 2, locus_tag="a"),
"b": DummyCDS(3, 4, locus_tag="b"),
"c": DummyCDS(5, 6, locus_tag="c"),
"e": DummyCDS(7, 8, locus_tag="e")}
self.genes = list(self.gene_mapping.values())
def test_order_finding_size(self):
cdss = [DummyCDS() for i in range(11)]
with self.assertRaisesRegex(AssertionError, "input too large"):
orderfinder.find_possible_orders(cdss, None, None)
def setUp(self):
# used by parse_subject, every sequence will be 100 long
mock('Record.get_cds_by_name', returns=DummyCDS(1, 101))
mock('core.get_cds_lengths', returns={})
self.sample_data = self.read_sample_data()
self.sample_data_as_lists = self.file_data_to_lists(self.sample_data)
def setUp(self):
self.config = build_config([])
self.rules_file = path.get_full_path(__file__, "..", "cluster_rules",
"strict.txt")
self.signature_file = path.get_full_path(__file__, "..", "data",
"hmmdetails.txt")
self.signature_names = {
sig.name
for sig in core.get_signature_profiles()
}
self.filter_file = path.get_full_path(__file__, "..",
"filterhmmdetails.txt")
self.results_by_id = {
"GENE_1": [
FakeHSPHit("modelA", "GENE_1", 0, 10, 50, 0),
FakeHSPHit("modelB", "GENE_1", 0, 10, 50, 0)
],
"GENE_2": [
FakeHSPHit("modelC", "GENE_2", 0, 10, 50, 0),
FakeHSPHit("modelB", "GENE_2", 0, 10, 50, 0)
],
"GENE_3": [
FakeHSPHit("modelC", "GENE_3", 0, 10, 50, 0),
FakeHSPHit("modelF", "GENE_3", 0, 10, 50, 0)
],
"GENE_4": [
FakeHSPHit("modelA", "GENE_4", 0, 10, 50, 0),
FakeHSPHit("modelE", "GENE_4", 0, 10, 50, 0)
],
"GENE_5": [
FakeHSPHit("modelA", "GENE_5", 0, 10, 50, 0),
FakeHSPHit("modelG", "GENE_5", 0, 10, 50, 0)
]
}
self.feature_by_id = {
"GENE_1": DummyCDS(0, 30000, locus_tag="GENE_1"),
"GENE_2": DummyCDS(30000, 50000, locus_tag="GENE_2"),
"GENE_3": DummyCDS(70000, 90000, locus_tag="GENE_3"),
"GENE_X": DummyCDS(95000, 100000, locus_tag="GENE_X"), # no hits
"GENE_4": DummyCDS(125000, 140000, locus_tag="GENE_4"),
"GENE_5": DummyCDS(130000, 150000, locus_tag="GENE_5")
}
self.test_names = {
"modelA", "modelB", "modelC", "modelF", "modelG", "a", "b", "c",
"d"
}
self.rules = rule_parser.Parser(
"\n".join([
"RULE MetaboliteA CUTOFF 10 NEIGHBOURHOOD 5 CONDITIONS modelA",
"RULE MetaboliteB CUTOFF 10 NEIGHBOURHOOD 5 CONDITIONS cds(modelA and modelB)",
"RULE MetaboliteC CUTOFF 10 NEIGHBOURHOOD 5 CONDITIONS (modelA and modelB)",
"RULE MetaboliteD CUTOFF 20 NEIGHBOURHOOD 5 CONDITIONS minimum(2,[modelC,modelB]) and modelA",
"RULE Metabolite0 CUTOFF 1 NEIGHBOURHOOD 3 CONDITIONS modelF",
"RULE Metabolite1 CUTOFF 1 NEIGHBOURHOOD 3 CONDITIONS modelG"
]), self.test_names).rules
self.features = []
for gene_id in self.feature_by_id:
self.features.append(self.feature_by_id[gene_id])
self.features.sort(
key=lambda x: x.location.start) # vital for py3 < 3.5
self.record = Record()
self.record._record.seq = Seq("A" * 150000)
for feature in self.features:
self.record.add_cds_feature(feature)
