def test_items(self):
db = RepliconDB(self.cfg)
ESCO030p01 = RepliconInfo(self.cfg.replicon_topology, 1, 67, self.ESCO030p01_genes)
PSAE001c01 = RepliconInfo(self.cfg.replicon_topology, 68, 133, self.PSAE001c01_genes)
NCXX = RepliconInfo("circular", 134, 141, self.NCDB_genes)
self.assertItemsEqual(db.items(), [('ESCO030p01',ESCO030p01), ('NC_xxxxx_xx',NCXX),
('PSAE001c01',PSAE001c01)])
def test_getitem(self):
db = RepliconDB(self.cfg)
ESCO030p01 = RepliconInfo(self.cfg.replicon_topology, 1, 67,
self.ESCO030p01_genes)
PSAE001c01 = RepliconInfo(self.cfg.replicon_topology, 68, 133,
self.PSAE001c01_genes)
self.assertEqual(ESCO030p01, db['ESCO030p01'])
self.assertEqual(PSAE001c01, db['PSAE001c01'])
self.assertRaises(KeyError, db.__getitem__, 'foo')
def test_getitem(self):
db = RepliconDB(self.cfg)
ESCO030p01 = RepliconInfo(self.cfg.replicon_topology, 1, 67, self.ESCO030p01_genes)
PSAE001c01 = RepliconInfo(self.cfg.replicon_topology, 68, 133, self.PSAE001c01_genes)
NCXX = RepliconInfo("circular", 134, 141, self.NCDB_genes)
self.assertEqual(ESCO030p01, db['ESCO030p01'])
self.assertEqual(PSAE001c01, db['PSAE001c01'])
self.assertEqual(NCXX, db['NC_xxxxx_xx'])
self.assertRaises(KeyError, db.__getitem__, 'foo')
def test_replicon_infos(self):
db = RepliconDB(self.cfg)
ESCO030p01 = RepliconInfo(self.cfg.replicon_topology(), 1, 67,
self.ESCO030p01_genes)
PSAE001c01 = RepliconInfo(self.cfg.replicon_topology(), 68, 133,
self.PSAE001c01_genes)
NCXX = RepliconInfo("circular", 134, 141, self.NCDB_genes)
values = db.replicon_infos()
self.assertCountEqual(values, [ESCO030p01, NCXX, PSAE001c01])
def test_get(self):
db = RepliconDB(self.cfg)
ESCO030p01 = RepliconInfo(self.cfg.replicon_topology, 1, 67,
self.ESCO030p01_genes)
PSAE001c01 = RepliconInfo(self.cfg.replicon_topology, 68, 133,
self.PSAE001c01_genes)
self.assertEqual(ESCO030p01, db.get('ESCO030p01'))
self.assertEqual(PSAE001c01, db.get('PSAE001c01'))
self.assertIsNone(db.get('foo'))
self.assertEqual('bar', db.get('foo', 'bar'))
def test_get(self):
db = RepliconDB(self.cfg)
ESCO030p01 = RepliconInfo(self.cfg.replicon_topology, 1, 67, self.ESCO030p01_genes)
PSAE001c01 = RepliconInfo(self.cfg.replicon_topology, 68, 133, self.PSAE001c01_genes)
NCXX = RepliconInfo("circular", 134, 141, self.NCDB_genes)
self.assertEqual(ESCO030p01, db.get('ESCO030p01'))
self.assertEqual(PSAE001c01, db.get('PSAE001c01'))
self.assertEqual(NCXX, db.get('NC_xxxxx_xx', 'foo'))
self.assertIsNone(db.get('foo'))
self.assertEqual('bar', db.get('foo', 'bar'))
def test_iteritems(self):
db = RepliconDB(self.cfg)
ESCO030p01 = RepliconInfo(self.cfg.replicon_topology(), 1, 67,
self.ESCO030p01_genes)
PSAE001c01 = RepliconInfo(self.cfg.replicon_topology(), 68, 133,
self.PSAE001c01_genes)
NCXX = RepliconInfo("circular", 134, 141, self.NCDB_genes)
iter_items = db.iteritems()
for item in [('ESCO030p01', ESCO030p01), ('PSAE001c01', PSAE001c01),
('NC_xxxxx_xx', NCXX)]:
with self.subTest(item=item):
self.assertEqual(next(iter_items), item)
def test_items(self):
db = RepliconDB(self.cfg)
ESCO030p01 = RepliconInfo(self.cfg.replicon_topology, 1, 67,
self.ESCO030p01_genes)
PSAE001c01 = RepliconInfo(self.cfg.replicon_topology, 68, 133,
self.PSAE001c01_genes)
self.assertItemsEqual(db.items(), [('ESCO030p01', ESCO030p01),
('PSAE001c01', PSAE001c01)])
db = RepliconDB(self.cfg)
PRRU001c01 = RepliconInfo(self.cfg.replicon_topology, 1, 67,
self.ESCO030p01_genes)
PSAE001c01 = RepliconInfo(self.cfg.replicon_topology, 68, 133,
self.PSAE001c01_genes)
def test_get_loners(self):
model = Model("foo/T2SS", 11)
# handle name, topology type, and min/max positions in the sequence dataset for a replicon and list of genes.
# each genes is representing by a tuple (seq_id, length)"""
rep_info = RepliconInfo('linear', 1, 60, [(f"g_{i}", i * 10) for i in range(1, 7)])
core_genes = []
model_genes = []
for g_name in ('gspD', 'sctC', 'sctJ', 'sctN', 'abc'):
core_gene = CoreGene(self.model_location, g_name, self.profile_factory)
core_genes.append(core_gene)
model_genes.append(ModelGene(core_gene, model))
model_genes[3]._loner = True
model_genes[4]._loner = True
model.add_mandatory_gene(model_genes[0])
model.add_mandatory_gene(model_genes[1])
model.add_accessory_gene(model_genes[2])
model.add_accessory_gene(model_genes[3])
model.add_neutral_gene(model_genes[4])
# Hit(gene, model, hit_id, hit_seq_length, replicon_name, position, i_eval, score,
# profile_coverage, sequence_coverage, begin_match, end_match
h10 = Hit(core_genes[0], "h10", 10, "replicon_1", 10, 1.0, 10.0, 1.0, 1.0, 10, 20)
h20 = Hit(core_genes[1], "h20", 10, "replicon_1", 20, 1.0, 20.0, 1.0, 1.0, 10, 20)
h30 = Hit(core_genes[2], "h30", 10, "replicon_1", 30, 1.0, 30.0, 1.0, 1.0, 10, 20)
h61 = Hit(core_genes[3], "h61", 10, "replicon_1", 60, 1.0, 61.0, 1.0, 1.0, 10, 20)
h80 = Hit(core_genes[4], "h80", 10, "replicon_1", 80, 1.0, 80.0, 1.0, 1.0, 10, 20)
# loners are clusters of one hit
loners = get_loners([h10, h20, h30, h61, h80], model, self.hit_weights)
hit_from_clusters = [h.hits[0] for h in loners]
self.assertListEqual(hit_from_clusters, [h61, h80])
def test_build_clusters(self):
# handle name, topology type, and min/max positions in the sequence dataset for a replicon and list of genes.
# each genes is representing by a tuple (seq_id, length)"""
rep_info = RepliconInfo('linear', 1, 60, [(f"g_{i}", i * 10) for i in range(1, 7)])
model = Model("foo/T2SS", 11)
core_genes = []
model_genes = []
for g_name in ('gspD', 'sctC', 'sctJ', 'sctN', 'abc'):
core_gene = CoreGene(self.model_location, g_name, self.profile_factory)
core_genes.append(core_gene)
model_genes.append(ModelGene(core_gene, model))
model_genes[4]._loner = True
model.add_mandatory_gene(model_genes[0])
model.add_mandatory_gene(model_genes[1])
model.add_accessory_gene(model_genes[2])
model.add_accessory_gene(model_genes[3])
model.add_neutral_gene(model_genes[4])
# Hit(gene, hit_id, hit_seq_length, replicon_name, position, i_eval, score,
# profile_coverage, sequence_coverage, begin_match, end_match
h10 = Hit(core_genes[0], "h10", 10, "replicon_1", 10, 1.0, 10.0, 1.0, 1.0, 10, 20)
h11 = Hit(core_genes[0], "h11", 10, "replicon_1", 10, 1.0, 11.0, 1.0, 1.0, 10, 20)
h20 = Hit(core_genes[1], "h20", 10, "replicon_1", 20, 1.0, 20.0, 1.0, 1.0, 10, 20)
h21 = Hit(core_genes[2], "h21", 10, "replicon_1", 20, 1.0, 21.0, 1.0, 1.0, 10, 20)
h30 = Hit(core_genes[2], "h30", 10, "replicon_1", 30, 1.0, 30.0, 1.0, 1.0, 10, 20)
h31 = Hit(core_genes[1], "h31", 10, "replicon_1", 30, 1.0, 31.0, 1.0, 1.0, 10, 20)
h50 = Hit(core_genes[2], "h50", 10, "replicon_1", 50, 1.0, 50.0, 1.0, 1.0, 10, 20)
h51 = Hit(core_genes[2], "h51", 10, "replicon_1", 50, 1.0, 51.0, 1.0, 1.0, 10, 20)
h60 = Hit(core_genes[2], "h60", 10, "replicon_1", 60, 1.0, 60.0, 1.0, 1.0, 10, 20)
h61 = Hit(core_genes[3], "h61", 10, "replicon_1", 60, 1.0, 61.0, 1.0, 1.0, 10, 20)
# case replicon is linear, 2 clusters
hits = [h10, h11, h20, h21, h30, h31, h50, h51, h60, h61]
random.shuffle(hits)
clusters = build_clusters(hits, rep_info, model, self.hit_weights)
self.assertEqual(len(clusters), 2)
self.assertListEqual(clusters[0].hits, [h11, h21, h31])
self.assertListEqual(clusters[1].hits, [h51, h61])
# case replicon is linear with a single hit (not loner) between 2 clusters
h70 = Hit(core_genes[3], "h70", 10, "replicon_1", 70, 1.0, 80.0, 1.0, 1.0, 10, 20)
h80 = Hit(core_genes[4], "h80", 10, "replicon_1", 80, 1.0, 80.0, 1.0, 1.0, 10, 20)
hits = [h10, h11, h20, h21, h50, h51, h70, h80]
random.shuffle(hits)
clusters = build_clusters(hits, rep_info, model, self.hit_weights)
self.assertEqual(len(clusters), 2)
self.assertListEqual(clusters[0].hits, [h11, h21])
self.assertListEqual(clusters[1].hits, [h70, h80])
# replicon is linear, 3 clusters, the last one contains only one hit (loner)
rep_info = RepliconInfo('linear', 1, 100, [(f"g_{i}", i*10) for i in range(1, 101)])
h80 = Hit(core_genes[4], "h80", 10, "replicon_1", 80, 1.0, 80.0, 1.0, 1.0, 10, 20)
hits = [h10, h11, h20, h21, h30, h31, h50, h51, h60, h61, h80]
random.shuffle(hits)
clusters = build_clusters(hits, rep_info, model, self.hit_weights)
self.assertEqual(len(clusters), 3)
self.assertListEqual(clusters[0].hits, [h11, h21, h31])
self.assertListEqual(clusters[1].hits, [h51, h61])
self.assertListEqual(clusters[2].hits, [h80])
# replicon is circular contains only one cluster
rep_info = RepliconInfo('circular', 1, 60, [(f"g_{i}", i*10) for i in range(1, 7)])
hits = [h10, h20, h30]
clusters = build_clusters(hits, rep_info, model, self.hit_weights)
self.assertEqual(len(clusters), 1)
self.assertListEqual(clusters[0].hits, [h10, h20, h30])
# replicon is circular the last cluster is merge with the first So we have only one cluster
rep_info = RepliconInfo('circular', 1, 60, [(f"g_{i}", i*10) for i in range(1, 7)])
hits = [h10, h11, h20, h21, h30, h31, h50, h51, h60, h61]
clusters = build_clusters(hits, rep_info, model, self.hit_weights)
self.assertEqual(len(clusters), 1)
self.assertListEqual(clusters[0].hits, [h51, h61, h11, h21, h31])
# replicon is circular the last hit is incorporate to the first cluster
rep_info = RepliconInfo('circular', 1, 80, [(f"g_{i}", i*10) for i in range(1, 9)])
h80 = Hit(core_genes[3], "h80", 10, "replicon_1", 80, 1.0, 80.0, 1.0, 1.0, 10, 20)
hits = [h10, h11, h20, h21, h30, h31, h50, h51, h60, h61, h80]
random.shuffle(hits)
clusters = build_clusters(hits, rep_info, model, self.hit_weights)
self.assertEqual(len(clusters), 2)
self.assertListEqual(clusters[0].hits, [h80, h11, h21, h31])
self.assertListEqual(clusters[1].hits, [h51, h61])
# replicon is circular the last hit is not merged with the first cluster
rep_info = RepliconInfo('linear', 1, 80, [(f"g_{i}", i*10) for i in range(1, 9)])
hits = [h10, h11, h20, h21, h30, h31, h50, h51, h60, h61, h80]
random.shuffle(hits)
clusters = build_clusters(hits, rep_info, model, self.hit_weights)
self.assertEqual(len(clusters), 2)
self.assertEqual(len(clusters), 2)
self.assertListEqual(clusters[0].hits, [h11, h21, h31])
self.assertListEqual(clusters[1].hits, [h51, h61])
# case replicon is linear, 2 clusters, the hits 11,21,31 and 51,61 are contiguous
h10 = Hit(core_genes[0], "h10", 10, "replicon_1", 10, 1.0, 11.0, 1.0, 1.0, 10, 20)
h11 = Hit(core_genes[2], "h11", 10, "replicon_1", 11, 1.0, 21.0, 1.0, 1.0, 10, 20)
h12 = Hit(core_genes[1], "h12", 10, "replicon_1", 12, 1.0, 31.0, 1.0, 1.0, 10, 20)
h50 = Hit(core_genes[2], "h50", 10, "replicon_1", 50, 1.0, 51.0, 1.0, 1.0, 10, 20)
h51 = Hit(core_genes[3], "h51", 10, "replicon_1", 51, 1.0, 61.0, 1.0, 1.0, 10, 20)
hits = [h10, h11, h12, h50, h51]
random.shuffle(hits)
clusters = build_clusters(hits, rep_info, model, self.hit_weights)
self.assertEqual(len(clusters), 2)
self.assertListEqual(clusters[0].hits, [h10, h11, h12])
self.assertListEqual(clusters[1].hits, [h50, h51])
# case replicon is linear
# one cluster with one hit loner
h80 = Hit(core_genes[4], "h80", 10, "replicon_1", 80, 1.0, 80.0, 1.0, 1.0, 10, 20)
hits = [h80]
random.shuffle(hits)
clusters = build_clusters(hits, rep_info, model, self.hit_weights)
self.assertEqual(len(clusters), 1)
self.assertListEqual(clusters[0].hits, [h80])
# case replicon is linear, no hits
clusters = build_clusters([], rep_info, model, self.hit_weights)
self.assertListEqual(clusters, [])