def test_contains(self):
model = Model("foo/T2SS", 11)
c_gene_1 = CoreGene(self.model_location, "gspD", self.profile_factory)
c_gene_2 = CoreGene(self.model_location, "sctC", self.profile_factory)
c_gene_3 = CoreGene(self.model_location, "sctJ", self.profile_factory)
gene_1 = ModelGene(c_gene_1, model)
gene_2 = ModelGene(c_gene_2, model)
gene_3 = ModelGene(c_gene_3, model)
# Hit(gene, model, hit_id, hit_seq_length, replicon_name, position, i_eval, score,
# profile_coverage, sequence_coverage, begin_match, end_match
h10 = Hit(c_gene_1, "h10", 10, "replicon_1", 10, 1.0, 10.0, 1.0, 1.0, 10, 20)
v_h10 = ValidHit(h10, gene_1, GeneStatus.MANDATORY)
h20 = Hit(c_gene_2, "h20", 10, "replicon_1", 20, 1.0, 20.0, 1.0, 1.0, 10, 20)
v_h20 = ValidHit(h20, gene_2, GeneStatus.MANDATORY)
h30 = Hit(c_gene_3, "h30", 10, "replicon_1", 30, 1.0, 30.0, 1.0, 1.0, 10, 20)
v_h30 = ValidHit(h30, gene_3, GeneStatus.ACCESSORY)
h50 = Hit(c_gene_3, "h50", 10, "replicon_1", 50, 1.0, 50.0, 1.0, 1.0, 10, 20)
v_h50 = ValidHit(h50, gene_3, GeneStatus.ACCESSORY)
c1 = Cluster([v_h10, v_h20, v_h50], model, self.hit_weights)
self.assertTrue(v_h10 in c1)
self.assertFalse(v_h30 in c1)
def test_hits(self):
model = Model("foo/T2SS", 10)
c_gene_gspd = CoreGene(self.model_location, "gspD",
self.profile_factory)
gene_gspd = ModelGene(c_gene_gspd, model)
model.add_mandatory_gene(gene_gspd)
c_gene_sctj = CoreGene(self.model_location, "sctJ",
self.profile_factory)
gene_sctj = ModelGene(c_gene_sctj, model)
model.add_accessory_gene(gene_sctj)
c_gene_sctn = CoreGene(self.model_location, "sctN",
self.profile_factory)
gene_sctn = ModelGene(c_gene_sctn, model)
model.add_accessory_gene(gene_sctn)
hit_1 = Hit(c_gene_gspd, "hit_1", 803, "replicon_id", 1, 1.0, 1.0, 1.0,
1.0, 10, 20)
v_hit_1 = ValidHit(hit_1, gene_gspd, GeneStatus.MANDATORY)
hit_2 = Hit(c_gene_sctj, "hit_2", 803, "replicon_id", 1, 1.0, 1.0, 1.0,
1.0, 10, 20)
v_hit_2 = ValidHit(hit_2, gene_sctj, GeneStatus.ACCESSORY)
hit_3 = Hit(c_gene_sctn, "hit_3", 803, "replicon_id", 1, 1.0, 1.0, 1.0,
1.0, 10, 20)
v_hit_3 = ValidHit(hit_3, gene_sctn, GeneStatus.ACCESSORY)
ls_1 = LikelySystem(model, [v_hit_1], [v_hit_2, v_hit_3], [], [])
self.assertListEqual(ls_1.hits, [v_hit_1, v_hit_2, v_hit_3])
def test_fulfilled_function(self):
model = Model("foo/T2SS", 11)
c_gene_1 = CoreGene(self.model_location, "gspD", self.profile_factory)
c_gene_2 = CoreGene(self.model_location, "sctC", self.profile_factory)
c_gene_3 = CoreGene(self.model_location, "sctJ", self.profile_factory)
c_gene_4 = CoreGene(self.model_location, "sctJ_FLG", self.profile_factory)
gene_1 = ModelGene(c_gene_1, model)
gene_2 = ModelGene(c_gene_2, model)
gene_3 = ModelGene(c_gene_3, model)
gene_4 = Exchangeable(c_gene_4, gene_3)
gene_3.add_exchangeable(gene_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(c_gene_1, "h10", 10, "replicon_1", 10, 1.0, 10.0, 1.0, 1.0, 10, 20)
v_h10 = ValidHit(h10, gene_1, GeneStatus.MANDATORY)
h20 = Hit(c_gene_2, "h20", 10, "replicon_1", 20, 1.0, 20.0, 1.0, 1.0, 10, 20)
v_h20 = ValidHit(h20, gene_2, GeneStatus.MANDATORY)
c = Cluster([v_h10, v_h20], model, self.hit_weights)
self.assertTrue(c.fulfilled_function(gene_1))
self.assertFalse(c.fulfilled_function(gene_3))
h50 = Hit(c_gene_4, "h50", 10, "replicon_1", 50, 1.0, 50.0, 1.0, 1.0, 10, 20)
v_h50 = ValidHit(h50, gene_4, GeneStatus.ACCESSORY)
c = Cluster([v_h10, v_h50], model, self.hit_weights)
self.assertTrue(c.fulfilled_function(gene_3))
def test_hits(self):
model = Model("foo/T2SS", 10)
c_gene_gspd = CoreGene(self.model_location, "gspD",
self.profile_factory)
gene_gspd = ModelGene(c_gene_gspd, model)
model.add_mandatory_gene(gene_gspd)
c_gene_sctj = CoreGene(self.model_location, "sctJ",
self.profile_factory)
gene_sctj = ModelGene(c_gene_sctj, model)
model.add_accessory_gene(gene_sctj)
c_gene_sctn = CoreGene(self.model_location, "sctN",
self.profile_factory)
gene_sctn = ModelGene(c_gene_sctn, model)
model.add_accessory_gene(gene_sctn)
hit_1 = Hit(c_gene_gspd, "hit_1", 803, "replicon_id", 1, 1.0, 1.0, 1.0,
1.0, 10, 20)
v_hit_1 = ValidHit(hit_1, gene_gspd, GeneStatus.MANDATORY)
hit_2 = Hit(c_gene_sctj, "hit_2", 803, "replicon_id", 1, 1.0, 1.0, 1.0,
1.0, 10, 20)
v_hit_2 = ValidHit(hit_2, gene_sctj, GeneStatus.ACCESSORY)
hit_3 = Hit(c_gene_sctn, "hit_3", 803, "replicon_id", 1, 1.0, 1.0, 1.0,
1.0, 10, 20)
v_hit_3 = ValidHit(hit_3, gene_sctn, GeneStatus.ACCESSORY)
rc = RejectedClusters(model, [
Cluster([v_hit_1, v_hit_2], model, self.hit_weights),
Cluster([v_hit_3], model, self.hit_weights)
], ["bla bla"])
self.assertEqual(rc.hits, [v_hit_1, v_hit_2, v_hit_3])
self.assertEqual(rc.reasons, ["bla bla"])
def test_init(self):
model = Model("foo/model_A", 10)
# test if id is well incremented
c_gene_gspd = CoreGene(self.model_location, "gspD",
self.profile_factory)
gene_gspd = ModelGene(c_gene_gspd, model)
model.add_mandatory_gene(gene_gspd)
c_gene_sctj = CoreGene(self.model_location, "sctJ",
self.profile_factory)
gene_sctj = ModelGene(c_gene_sctj, model)
model.add_accessory_gene(gene_sctj)
hit_1 = Hit(c_gene_gspd, "hit_1", 803, "replicon_id", 1, 1.0, 1.0, 1.0,
1.0, 10, 20)
v_hit_1 = ValidHit(hit_1, gene_gspd, GeneStatus.MANDATORY)
hit_2 = Hit(c_gene_sctj, "hit_2", 803, "replicon_id", 1, 1.0, 1.0, 1.0,
1.0, 10, 20)
v_hit_2 = ValidHit(hit_2, gene_sctj, GeneStatus.ACCESSORY)
ls_1 = LikelySystem(model, [v_hit_1], [v_hit_2], [], [])
self.assertTrue(ls_1.id.startswith('replicon_id_model_A_'))
ls_2 = LikelySystem(model, [v_hit_1, v_hit_2], [], [], [])
# check if the id of the second likelysystem is well increased
self.assertEqual(int(ls_2.id.split('_')[-1]),
int(ls_1.id.split('_')[-1]) + 1)
def setUp(self) -> None:
args = argparse.Namespace()
args.sequence_db = self.find_data("base", "test_1.fasta")
args.db_type = 'gembase'
args.models_dir = self.find_data('models')
cfg = Config(MacsyDefaults(), args)
model_name = 'foo'
models_location = ModelLocation(path=os.path.join(args.models_dir, model_name))
model = Model("foo/T2SS", 10)
profile_factory = ProfileFactory(cfg)
gene_name = "gspD"
self.c_gene_gspd = CoreGene(models_location, gene_name, profile_factory)
self.gene_gspd = ModelGene(self.c_gene_gspd, model)
gene_name = "sctJ"
self.c_gene_sctj = CoreGene(models_location, gene_name, profile_factory)
self.gene_sctj = ModelGene(self.c_gene_sctj, model)
model.add_mandatory_gene(self.gene_gspd)
model.add_accessory_gene(self.gene_sctj)
self.hit_1 = Hit(self.c_gene_gspd, "hit_1", 803, "replicon_id", 2, 1.0, 1.0, 1.0, 1.0, 10, 20)
self.hit_2 = Hit(self.c_gene_sctj, "hit_2", 803, "replicon_id", 3, 1.0, 1.0, 1.0, 1.0, 10, 20)
def test_str(self):
model = Model("foo/T2SS", 10)
c_gene_gspd = CoreGene(self.model_location, "gspD",
self.profile_factory)
gene_gspd = ModelGene(c_gene_gspd, model)
model.add_mandatory_gene(gene_gspd)
c_gene_sctj = CoreGene(self.model_location, "sctJ",
self.profile_factory)
gene_sctj = ModelGene(c_gene_sctj, model)
model.add_accessory_gene(gene_sctj)
c_gene_sctn = CoreGene(self.model_location, "sctN",
self.profile_factory)
gene_sctn = ModelGene(c_gene_sctn, model)
model.add_accessory_gene(gene_sctn)
hit_1 = Hit(c_gene_gspd, "hit_1", 803, "replicon_id", 1, 1.0, 1.0, 1.0,
1.0, 10, 20)
v_hit_1 = ValidHit(hit_1, gene_gspd, GeneStatus.MANDATORY)
hit_2 = Hit(c_gene_sctj, "hit_2", 803, "replicon_id", 2, 1.0, 1.0, 1.0,
1.0, 10, 20)
v_hit_2 = ValidHit(hit_2, gene_sctj, GeneStatus.ACCESSORY)
hit_3 = Hit(c_gene_sctn, "hit_3", 803, "replicon_id", 3, 1.0, 1.0, 1.0,
1.0, 10, 20)
v_hit_3 = ValidHit(hit_3, gene_sctn, GeneStatus.ACCESSORY)
uls_1 = UnlikelySystem(model, [v_hit_1], [v_hit_2, v_hit_3], [], [],
["reason"])
expected_str = """(hit_1, gspD, 1), (hit_2, sctJ, 2), (hit_3, sctN, 3): These hits does not probably constitute a system because:
reason"""
self.assertEqual(str(uls_1), expected_str)
def test_str(self):
model = Model("foo/T2SS", 10)
c_gene_gspd = CoreGene(self.model_location, "gspD",
self.profile_factory)
gene_gspd = ModelGene(c_gene_gspd, model)
model.add_mandatory_gene(gene_gspd)
c_gene_sctj = CoreGene(self.model_location, "sctJ",
self.profile_factory)
gene_sctj = ModelGene(c_gene_sctj, model)
model.add_accessory_gene(gene_sctj)
c_gene_sctn = CoreGene(self.model_location, "sctN",
self.profile_factory)
gene_sctn = ModelGene(c_gene_sctn, model)
model.add_accessory_gene(gene_sctn)
hit_1 = Hit(c_gene_gspd, "hit_1", 803, "replicon_id", 1, 1.0, 1.0, 1.0,
1.0, 10, 20)
v_hit_1 = ValidHit(hit_1, gene_gspd, GeneStatus.MANDATORY)
hit_2 = Hit(c_gene_sctj, "hit_2", 803, "replicon_id", 1, 1.0, 1.0, 1.0,
1.0, 10, 20)
v_hit_2 = ValidHit(hit_2, gene_sctj, GeneStatus.ACCESSORY)
hit_3 = Hit(c_gene_sctn, "hit_3", 803, "replicon_id", 1, 1.0, 1.0, 1.0,
1.0, 10, 20)
v_hit_3 = ValidHit(hit_3, gene_sctn, GeneStatus.ACCESSORY)
ls_1 = LikelySystem(model, [v_hit_1], [v_hit_2, v_hit_3], [], [])
expected_str = ', '.join([
f"({h.id}, {h.gene.name}, {h.position})"
for h in (v_hit_1, v_hit_2, v_hit_3)
])
self.assertEqual(str(ls_1), expected_str)
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_get_position(self):
gene_name = "gspD"
gene = CoreGene(self.model_location, gene_name, self.profile_factory)
h0 = Hit(gene, "PSAE001c01_006940", 803, "PSAE001c01", 3450, float(1.2e-234), float(779.2),
float(1.000000), (741.0 - 104.0 + 1) / 803, 104, 741)
self.assertEqual(h0.get_position(), 3450)
def test_UnlikelySystemSerializer_txt(self):
model = Model("foo/FOO", 10)
c_gene_gspd = CoreGene(self.model_location, "gspD",
self.profile_factory)
gene_gspd = ModelGene(c_gene_gspd, model)
model.add_mandatory_gene(gene_gspd)
c_gene_sctj = CoreGene(self.model_location, "sctJ",
self.profile_factory)
gene_sctj = ModelGene(c_gene_sctj, model)
model.add_accessory_gene(gene_sctj)
c_gene_sctn = CoreGene(self.model_location, "sctN",
self.profile_factory)
gene_sctn = ModelGene(c_gene_sctn, model)
model.add_accessory_gene(gene_sctn)
c_gene_abc = CoreGene(self.model_location, "abc", self.profile_factory)
gene_abc = ModelGene(c_gene_abc, model)
model.add_forbidden_gene(gene_abc)
hit_1 = Hit(c_gene_gspd, "hit_1", 803, "replicon_id", 1, 1.0, 1.0, 1.0,
1.0, 10, 20)
v_hit_1 = ValidHit(hit_1, gene_gspd, GeneStatus.MANDATORY)
hit_2 = Hit(c_gene_sctj, "hit_2", 803, "replicon_id", 2, 1.0, 1.0, 1.0,
1.0, 10, 20)
v_hit_2 = ValidHit(hit_2, gene_sctj, GeneStatus.ACCESSORY)
hit_3 = Hit(c_gene_sctn, "hit_3", 803, "replicon_id", 3, 1.0, 1.0, 1.0,
1.0, 10, 20)
v_hit_3 = ValidHit(hit_3, gene_sctn, GeneStatus.ACCESSORY)
hit_4 = Hit(c_gene_abc, "hit_4", 803, "replicon_id", 4, 1.0, 1.0, 1.0,
1.0, 10, 20)
v_hit_4 = ValidHit(hit_4, gene_abc, GeneStatus.FORBIDDEN)
ser = TxtUnikelySystemSerializer()
ls_1 = UnlikelySystem(model, [v_hit_1], [v_hit_2, v_hit_3], [],
[v_hit_4], ["the reason why"])
txt = ser.serialize(ls_1)
expected_txt = """This replicon probably not contains a system foo/FOO:
the reason why
system id = replicon_id_FOO_1
model = foo/FOO
replicon = replicon_id
hits = [('hit_1', 'gspD', 1), ('hit_2', 'sctJ', 2), ('hit_3', 'sctN', 3), ('hit_4', 'abc', 4)]
wholeness = 1.000
mandatory genes:
\t- gspD: 1 (gspD)
accessory genes:
\t- sctJ: 1 (sctJ)
\t- sctN: 1 (sctN)
neutral genes:
forbidden genes:
\t- abc: 1 (abc)
Use ordered replicon to have better prediction.
"""
self.assertEqual(txt, expected_txt)
def test_SystemSerializer_tsv(self):
model = Model("foo/T2SS", 10)
c_gene_gspd = CoreGene(self.model_location, "gspD",
self.profile_factory)
gene_gspd = ModelGene(c_gene_gspd, model)
model.add_mandatory_gene(gene_gspd)
c_gene_sctj = CoreGene(self.model_location, "sctJ",
self.profile_factory)
gene_sctj = ModelGene(c_gene_sctj, model)
model.add_accessory_gene(gene_sctj)
c_gene_sctn = CoreGene(self.model_location, "sctN",
self.profile_factory)
gene_sctn = ModelGene(c_gene_sctn, model)
c_gene_sctn_flg = CoreGene(self.model_location, "sctN_FLG",
self.profile_factory)
gene_sctn_flg = Exchangeable(c_gene_sctn_flg, gene_sctn)
gene_sctn.add_exchangeable(gene_sctn_flg)
model.add_accessory_gene(gene_sctn)
h_gspd = Hit(c_gene_gspd, "h_gspd", 803, "replicon_id", 10, 1.0, 1.0,
1.0, 1.0, 10, 20)
v_h_gspd = ValidHit(h_gspd, gene_gspd, GeneStatus.MANDATORY)
h_sctj = Hit(c_gene_sctj, "h_sctj", 803, "replicon_id", 20, 1.0, 1.0,
1.0, 1.0, 20, 30)
v_h_sctj = ValidHit(h_sctj, gene_sctj, GeneStatus.ACCESSORY)
h_sctn_flg = Hit(c_gene_sctn_flg, "h_sctn_flg", 803, "replicon_id", 30,
1.0, 1.0, 1.0, 1.0, 30, 40)
v_h_sctn_flg = ValidHit(h_sctn_flg, gene_sctn_flg,
GeneStatus.ACCESSORY)
c1 = Cluster([v_h_gspd, v_h_sctj], model, self.hit_weights)
c2 = Cluster([v_h_sctn_flg], model, self.hit_weights)
sys_multi_loci = System(model, [c1, c2], self.cfg.redundancy_penalty())
hit_multi_sys_tracker = HitSystemTracker([sys_multi_loci])
system_serializer = TsvSystemSerializer()
sys_tsv = "\t".join([
"replicon_id", "h_gspd", "gspD", "10", "foo/T2SS",
sys_multi_loci.id, "1", "1.000", "1.900", "1", "gspD", "mandatory",
"803", "1.0", "1.000", "1.000", "1.000", "10", "20", ""
])
sys_tsv += "\n"
sys_tsv += "\t".join([
"replicon_id", "h_sctj", "sctJ", "20", "foo/T2SS",
sys_multi_loci.id, "1", "1.000", "1.900", "1", "sctJ", "accessory",
"803", "1.0", "1.000", "1.000", "1.000", "20", "30", ""
])
sys_tsv += "\n"
sys_tsv += "\t".join([
"replicon_id", "h_sctn_flg", "sctN_FLG", "30", "foo/T2SS",
sys_multi_loci.id, "1", "1.000", "1.900", "1", "sctN", "accessory",
"803", "1.0", "1.000", "1.000", "1.000", "30", "40", ""
])
sys_tsv += "\n"
self.assertEqual(
sys_tsv,
system_serializer.serialize(sys_multi_loci, hit_multi_sys_tracker))
def test_eq(self):
gene_name = "gspD"
gene = CoreGene(self.model_location, gene_name, self.profile_factory)
h0 = Hit(gene, "PSAE001c01_006940", 803, "PSAE001c01", 3450, float(1.2e-234), float(779.2),
float(1.000000), (741.0 - 104.0 + 1) / 803, 104, 741)
h1 = Hit(gene, "PSAE001c01_006940", 803, "PSAE001c01", 3450, float(1.2e-234), float(779.2),
float(1.000000), (741.0 - 104.0 + 1) / 803, 104, 741)
h2 = Hit(gene, "PSAE001c01_013980", 759, "PSAE001c01", 4146, float(3.7e-76), float(255.8),
float(1.000000), (736.0 - 105.0 + 1) / 759, 105, 736)
self.assertEqual(h0, h1)
self.assertNotEqual(h0, h2)
def test_hash(self):
gene_name = "gspD"
gene = CoreGene(self.model_location, gene_name, self.profile_factory)
h0 = Hit(gene, "PSAE001c01_006940", 803, "PSAE001c01", 3450, float(1.2e-234), float(779.2),
float(1.000000), (741.0 - 104.0 + 1) / 803, 104, 741)
h1 = Hit(gene, "PSAE001c01_006940", 803, "PSAE001c01", 3450, float(1.2e-234), float(779.2),
float(1.000000), (741.0 - 104.0 + 1) / 803, 104, 741)
h2 = Hit(gene, "PSAE001c01_006941", 803, "PSAE001c01", 3450, float(1.2e-234), float(779.2),
float(1.000000), (741.0 - 104.0 + 1) / 803, 104, 741)
self.assertTrue(isinstance(hash(h0), int))
self.assertEqual(hash(h0), hash(h1))
self.assertNotEqual(hash(h0), hash(h2))
def test_search_recover(self):
# first job searching using hmmsearch
gene_name = "abc"
c_gene_abc = CoreGene(self.model_location, gene_name,
self.profile_factory)
report = search_genes([c_gene_abc], self.cfg)
expected_hit = [
Hit(c_gene_abc, "ESCO030p01_000260", 706, "ESCO030p01", 26,
float(1.000e-200), float(660.800), float(1.000), float(0.714),
160, 663)
]
# second job using recover
# disable hmmer to be sure that test use the recover inner function
self.cfg.hmmer = lambda: "hmmer_disable"
# and create a new dir for the second job
previous_job_path = self.cfg.working_dir()
self.cfg.previous_run = lambda: previous_job_path
self.cfg.out_dir = lambda: os.path.join(self.tmp_dir, 'job_2')
os.mkdir(self.cfg.out_dir())
# rerun with previous run
# but we have to reset the profile attached to the gene gene._profile._report
self.profile_factory = ProfileFactory(self.cfg)
c_gene_abc = CoreGene(self.model_location, gene_name,
self.profile_factory)
report = search_genes([c_gene_abc], self.cfg)
self.assertEqual(len(report), 1)
self.assertEqual(expected_hit[0], report[0].hits[0])
def test_len(self):
model = Model("foo/T2SS", 11)
c_gene_1 = CoreGene(self.model_location, "gspD", self.profile_factory)
c_gene_2 = CoreGene(self.model_location, "sctC", self.profile_factory)
gene_1 = ModelGene(c_gene_1, model)
gene_2 = ModelGene(c_gene_2, model)
# Hit(gene, model, hit_id, hit_seq_length, replicon_name, position, i_eval, score,
# profile_coverage, sequence_coverage, begin_match, end_match
h10 = Hit(c_gene_1, "h10", 10, "replicon_1", 10, 1.0, 10.0, 1.0, 1.0, 10, 20)
v_h10 = ValidHit(h10, gene_1, GeneStatus.MANDATORY)
h20 = Hit(c_gene_2, "h20", 10, "replicon_1", 20, 1.0, 20.0, 1.0, 1.0, 10, 20)
v_h20 = ValidHit(h20, gene_2, GeneStatus.MANDATORY)
c1 = Cluster([v_h10, v_h20], model, self.hit_weights)
self.assertEqual(len(c1), 2)
def test_cmp(self):
gene_name = "gspD"
gene = CoreGene(self.model_location, gene_name, self.profile_factory)
# compare hit with different id (comparison based on seq identifier)
h0 = Hit(gene, "PSAE001c01_006940", 803, "PSAE001c01", 3450, float(1.2e-234),
float(779.2), float(1.000000), (741.0 - 104.0 + 1) / 803, 104, 741)
h1 = Hit(gene, "PSAE001c01_013980", 759, "PSAE001c01", 4146, float(3.7e-76),
float(255.8), float(1.000000), (736.0 - 105.0 + 1) / 759, 105, 736)
self.assertGreater(h1, h0)
self.assertLess(h0, h1)
# compare hit with different same id (comparison based on score)
# score = 779.2
h0 = Hit(gene, "PSAE001c01_006940", 803, "PSAE001c01", 3450, float(1.2e-234),
float(779.2), float(1.000000), (741.0 - 104.0 + 1) / 803, 104, 741)
# score = 255.8
h1 = Hit(gene, "PSAE001c01_006940", 759, "PSAE001c01", 4146, float(3.7e-76),
float(255.8), float(1.000000), (736.0 - 105.0 + 1) / 759, 105, 736)
self.assertGreater(h0, h1)
self.assertLess(h1, h0)
def test_search(self):
gene_name = "abc"
c_gene_abc = CoreGene(self.model_location, gene_name,
self.profile_factory)
report = search_genes([c_gene_abc], self.cfg)
expected_hit = [
Hit(c_gene_abc, "ESCO030p01_000260", 706, "ESCO030p01", 26,
float(1.000e-200), float(660.800), float(1.000), float(0.714),
160, 663)
]
self.assertEqual(len(report), 1)
self.assertEqual(expected_hit[0], report[0].hits[0])
def test_reason(self):
model = Model("foo/model_A", 10)
# test if id is well incremented
c_gene_gspd = CoreGene(self.model_location, "gspD",
self.profile_factory)
gene_gspd = ModelGene(c_gene_gspd, model)
model.add_mandatory_gene(gene_gspd)
c_gene_sctj = CoreGene(self.model_location, "sctJ",
self.profile_factory)
gene_sctj = ModelGene(c_gene_sctj, model)
model.add_forbidden_gene(gene_sctj)
hit_1 = Hit(c_gene_gspd, "hit_1", 803, "replicon_id", 1, 1.0, 1.0, 1.0,
1.0, 10, 20)
v_hit_1 = ValidHit(hit_1, gene_gspd, GeneStatus.MANDATORY)
hit_2 = Hit(c_gene_sctj, "hit_2", 803, "replicon_id", 1, 1.0, 1.0, 1.0,
1.0, 10, 20)
v_hit_2 = ValidHit(hit_2, gene_sctj, GeneStatus.FORBIDDEN)
reason_2 = ["forbidden gene"]
uls_2 = UnlikelySystem(model, [v_hit_1], [], [], [v_hit_2], reason_2)
self.assertEqual(uls_2.reasons, reason_2)
def test_str(self):
model = Model("foo/T2SS", 11)
c_gene_1 = CoreGene(self.model_location, "gspD", self.profile_factory)
gene_1 = ModelGene(c_gene_1, model)
model.add_mandatory_gene(gene_1)
c_gene_2 = CoreGene(self.model_location, "sctC", self.profile_factory)
gene_2 = ModelGene(c_gene_2, model)
model.add_accessory_gene(gene_2)
# Hit(gene, model, hit_id, hit_seq_length, replicon_name, position, i_eval, score,
# profile_coverage, sequence_coverage, begin_match, end_match
h10 = Hit(c_gene_1, "h10", 10, "replicon_1", 10, 1.0, 10.0, 1.0, 1.0,
10, 20)
v_h10 = ValidHit(h10, gene_1, GeneStatus.MANDATORY)
h20 = Hit(c_gene_2, "h20", 10, "replicon_1", 20, 1.0, 20.0, 1.0, 1.0,
10, 20)
v_h20 = ValidHit(h20, gene_2, GeneStatus.ACCESSORY)
h40 = Hit(c_gene_1, "h40", 10, "replicon_1", 40, 1.0, 10.0, 1.0, 1.0,
10, 20)
v_h40 = ValidHit(h40, gene_1, GeneStatus.MANDATORY)
h50 = Hit(c_gene_2, "h50", 10, "replicon_1", 50, 1.0, 20.0, 1.0, 1.0,
10, 20)
v_h50 = ValidHit(h50, gene_2, GeneStatus.ACCESSORY)
c1 = Cluster([v_h10, v_h20], model, self.hit_weights)
c2 = Cluster([v_h40, v_h50], model, self.hit_weights)
r_c = RejectedClusters(model, [c1, c2], ["bla"])
expected_str = """Cluster:
- model = T2SS
- replicon = replicon_1
- hits = (h10, gspD, 10), (h20, sctC, 20)
Cluster:
- model = T2SS
- replicon = replicon_1
- hits = (h40, gspD, 40), (h50, sctC, 50)
These clusters have been rejected because:
\t- bla
"""
self.assertEqual(expected_str, str(r_c))
def test_extract_concurent(self):
gene_name = "gspD"
c_gene = CoreGene(self.model_location, gene_name, self.profile_factory)
shutil.copy(
self.find_data("hmm", gene_name + self.cfg.res_search_suffix()),
self.cfg.working_dir())
report_path = os.path.join(self.cfg.working_dir(),
gene_name + self.cfg.res_search_suffix())
reports = []
for i in range(5):
report = OrderedHMMReport(c_gene, report_path, self.cfg)
reports.append(report)
import threading
def worker(report):
report.extract()
for report in reports:
t = threading.Thread(target=worker, args=(report, ))
t.start()
main_thread = threading.currentThread()
for t in threading.enumerate():
if t is main_thread:
continue
t.join()
# gene, model, hit_id, hit_seq_length replicon_name, pos_hit, i_eval, score,
# profile_coverage, sequence_coverage, begin_match, end_match
hits = [
Hit(c_gene, "NC_xxxxx_xx_056141", 803,
RepliconDB.ordered_replicon_name, 141, float(2e-236),
float(779.2), float(1.000000), (741.0 - 104.0 + 1) / 803, 104,
741),
Hit(c_gene, "PSAE001c01_006940", 803,
RepliconDB.ordered_replicon_name, 68, float(1.2e-234),
float(779.2), float(1.000000), (741.0 - 104.0 + 1) / 803, 104,
741),
Hit(c_gene, "PSAE001c01_013980", 759,
RepliconDB.ordered_replicon_name, 69, float(3.7e-76),
float(255.8), float(1.000000), (736.0 - 105.0 + 1) / 759, 105,
736),
Hit(c_gene, "PSAE001c01_017350", 600,
RepliconDB.ordered_replicon_name, 70, float(3.2e-27),
float(94.2), float(0.500000), (506.0 - 226.0 + 1) / 600, 226,
506),
Hit(c_gene, "PSAE001c01_018920", 776,
RepliconDB.ordered_replicon_name, 71, float(6.1e-183),
float(608.4), float(1.000000), (606.0 - 48.0 + 1) / 776, 48,
606),
Hit(c_gene, "PSAE001c01_031420", 658,
RepliconDB.ordered_replicon_name, 73, float(1.8e-210),
float(699.3), float(1.000000), (614.0 - 55.0 + 1) / 658, 55,
614)
]
for report in reports:
report.save_extract()
self.assertEqual(len(report.hits), len(hits))
self.assertListEqual(report.hits, hits)
def test_filter_loners(self):
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[2]._loner = True
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)
h40 = Hit(core_genes[3], "h40", 10, "replicon_1", 40, 1.0, 61.0, 1.0, 1.0, 10, 20)
h50 = Hit(core_genes[4], "h50", 10, "replicon_1", 50, 1.0, 80.0, 1.0, 1.0, 10, 20)
c1 = Cluster([h10, h20, h30, h40, h50], model, self.hit_weights)
filtered_loners = filter_loners(c1, [Cluster([h30], model, self.hit_weights),
Cluster([h40], model, self.hit_weights),
Cluster([h50], model, self.hit_weights)]
)
self.assertListEqual(filtered_loners, [])
c1 = Cluster([h10, h20, h40], model, self.hit_weights)
c30 = Cluster([h30], model, self.hit_weights)
c40 = Cluster([h40], model, self.hit_weights)
c50 = Cluster([h50], model, self.hit_weights)
filtered_loners = filter_loners(c1, [c30, c40, c50])
self.assertListEqual(filtered_loners, [c30, c50])
def test_init(self):
model = Model("foo/T2SS", 11)
c_gene_1 = CoreGene(self.model_location, "gspD", self.profile_factory)
gene_1 = ModelGene(c_gene_1, model)
model.add_mandatory_gene(gene_1)
c_gene_2 = CoreGene(self.model_location, "sctC", self.profile_factory)
gene_2 = ModelGene(c_gene_2, model)
model.add_accessory_gene(gene_2)
# Hit(gene, model, hit_id, hit_seq_length, replicon_name, position, i_eval, score,
# profile_coverage, sequence_coverage, begin_match, end_match
h10 = Hit(c_gene_1, "h10", 10, "replicon_1", 10, 1.0, 10.0, 1.0, 1.0,
10, 20)
v_h10 = ValidHit(h10, gene_1, GeneStatus.MANDATORY)
h20 = Hit(c_gene_2, "h20", 10, "replicon_1", 20, 1.0, 20.0, 1.0, 1.0,
10, 20)
v_h20 = ValidHit(h20, gene_2, GeneStatus.ACCESSORY)
c1 = Cluster([v_h10, v_h20], model, self.hit_weights)
r_c = RejectedClusters(model, c1, ["bla"])
self.assertListEqual(r_c.clusters, [c1])
self.assertEqual(r_c.reasons, ['bla'])
def test_init(self):
model_1 = Model("foo/T2SS", 11)
c_gene_1 = CoreGene(self.model_location, "gspD", self.profile_factory)
c_gene_2 = CoreGene(self.model_location, "sctC", self.profile_factory)
c_gene_3 = CoreGene(self.model_location, "sctJ", self.profile_factory)
gene_1 = ModelGene(c_gene_1, model_1)
h10 = Hit(c_gene_1, "h10", 10, "replicon_1", 10, 1.0, 10.0, 1.0, 1.0, 10, 20)
v_h10 = ValidHit(h10, gene_1, GeneStatus.MANDATORY)
h20 = Hit(c_gene_2, "h20", 10, "replicon_1", 20, 1.0, 20.0, 1.0, 1.0, 10, 20)
v_h20 = ValidHit(h20, gene_1, GeneStatus.MANDATORY)
h30 = Hit(c_gene_3, "h30", 10, "replicon_2", 30, 1.0, 30.0, 1.0, 1.0, 10, 20)
v_h30 = ValidHit(h30, gene_1, GeneStatus.ACCESSORY)
h50 = Hit(c_gene_3, "h50", 10, "replicon_2", 50, 1.0, 50.0, 1.0, 1.0, 10, 20)
v_h50 = ValidHit(h50, gene_1, GeneStatus.ACCESSORY)
with self.assertRaises(MacsypyError) as ctx:
with self.catch_log():
Cluster([v_h10, v_h20, v_h30, v_h50], model_1, self.hit_weights)
msg = "Cannot build a cluster from hits coming from different replicons"
self.assertEqual(str(ctx.exception), msg)
def test_save_extract(self):
gene_name = "gspD"
gene = CoreGene(self.model_location, gene_name, self.profile_factory)
shutil.copy(
self.find_data("hmm", gene_name + self.cfg.res_search_suffix()),
self.cfg.working_dir())
report_path = os.path.join(self.cfg.working_dir(),
gene_name + self.cfg.res_search_suffix())
report = GembaseHMMReport(gene, report_path, self.cfg)
report.extract()
report.save_extract()
extract_filename = gene_name + self.cfg.res_extract_suffix()
extract_path = os.path.join(self.cfg.working_dir(),
self.cfg.hmmer_dir(), extract_filename)
self.assertTrue(os.path.exists(extract_path))
self.assertTrue(os.path.isfile(extract_path))
hits = [
Hit(gene, "NC_xxxxx_xx_056141", 803, "NC_xxxxx_xx", 141,
float(2e-236), float(779.2), float(1.000000),
(741.0 - 104.0 + 1) / 803, 104, 741),
Hit(gene, "PSAE001c01_006940", 803, "PSAE001c01", 68,
float(1.2e-234), float(779.2), float(1.000000),
(741.0 - 104.0 + 1) / 803, 104, 741),
Hit(gene, "PSAE001c01_013980",
759, "PSAE001c01", 69, float(3.7e-76), float(255.8),
float(1.000000), (736.0 - 105.0 + 1) / 759, 105, 736),
Hit(gene, "PSAE001c01_017350",
600, "PSAE001c01", 70, float(3.2e-27), float(94.2),
float(0.500000), (506.0 - 226.0 + 1) / 600, 226, 506),
Hit(gene, "PSAE001c01_018920", 776, "PSAE001c01", 71,
float(6.1e-183), float(608.4), float(1.000000),
(606.0 - 48.0 + 1) / 776, 48, 606),
Hit(gene, "PSAE001c01_031420", 658, "PSAE001c01", 73,
float(1.8e-210), float(699.3), float(1.000000),
(614.0 - 55.0 + 1) / 658, 55, 614)
]
expected_extract_path = os.path.join(self.cfg.working_dir(),
'expected_extract')
with open(expected_extract_path, 'w') as expected_extract:
extract = """# gene: {name} extract from {path} hmm output
# profile length= {len_profile:d}
# i_evalue threshold= {i_evalue:.3f}
# coverage threshold= {cov:.3f}
# hit_id replicon_name position_hit hit_sequence_length gene_name gene_system i_eval score profile_coverage sequence_coverage begin end
""".format(name=gene.name,
path=report_path,
len_profile=len(gene.profile),
i_evalue=self.cfg.i_evalue_sel(),
cov=self.cfg.coverage_profile())
expected_extract.write(extract)
for h in hits:
expected_extract.write(str(h))
self.assertFileEqual(extract_path, expected_extract_path)
def test_best_hit(self):
gene_name = 'gspD'
c_gene = CoreGene(self.model_location, gene_name, self.profile_factory)
shutil.copy(
self.find_data("hmm", gene_name + self.cfg.res_search_suffix()),
self.cfg.working_dir())
report_path = os.path.join(self.cfg.working_dir(),
gene_name + self.cfg.res_search_suffix())
report = GembaseHMMReport(c_gene, report_path, self.cfg)
self.assertIsNone(report.best_hit())
report.extract()
best_hit = report.best_hit()
hit_expected = Hit(c_gene, "NC_xxxxx_xx_056141", 803,
"NC_xxxxx_xx", 141, float(2e-236), float(779.2),
float(1.000000), (741.0 - 104.0 + 1) / 803, 104,
741)
self.assertEqual(hit_expected, best_hit)
def test_merge(self):
model = Model("foo/T2SS", 11)
c_gene_1 = CoreGene(self.model_location, "gspD", self.profile_factory)
c_gene_2 = CoreGene(self.model_location, "sctC", self.profile_factory)
c_gene_3 = CoreGene(self.model_location, "sctJ", self.profile_factory)
gene_1 = ModelGene(c_gene_1, model)
gene_2 = ModelGene(c_gene_2, model)
gene_3 = ModelGene(c_gene_3, model)
# Hit(gene, model, hit_id, hit_seq_length, replicon_name, position, i_eval, score,
# profile_coverage, sequence_coverage, begin_match, end_match
h10 = Hit(c_gene_1, "h10", 10, "replicon_1", 10, 1.0, 10.0, 1.0, 1.0, 10, 20)
v_h10 = ValidHit(h10, gene_1, GeneStatus.MANDATORY)
h20 = Hit(c_gene_2, "h20", 10, "replicon_1", 20, 1.0, 20.0, 1.0, 1.0, 10, 20)
v_h20 = ValidHit(h20, gene_2, GeneStatus.MANDATORY)
h30 = Hit(c_gene_3, "h30", 10, "replicon_1", 30, 1.0, 30.0, 1.0, 1.0, 10, 20)
v_h30 = ValidHit(h30, gene_3, GeneStatus.ACCESSORY)
h50 = Hit(c_gene_3, "h50", 10, "replicon_1", 50, 1.0, 50.0, 1.0, 1.0, 10, 20)
v_h50 = ValidHit(h50, gene_3, GeneStatus.ACCESSORY)
c1 = Cluster([v_h10, v_h20], model, self.hit_weights)
c2 = Cluster([v_h30, v_h50], model, self.hit_weights)
c1.merge(c2)
self.assertListEqual(c1.hits, [v_h10, v_h20, v_h30, v_h50])
c1 = Cluster([v_h10, v_h20], model, self.hit_weights)
c2 = Cluster([v_h30, v_h50], model, self.hit_weights)
c2.merge(c1)
self.assertListEqual(c2.hits, [v_h30, v_h50, v_h10, v_h20])
c1 = Cluster([v_h10, v_h20], model, self.hit_weights)
c2 = Cluster([v_h30, v_h50], model, self.hit_weights)
c1.merge(c2, before=True)
self.assertListEqual(c1.hits, [v_h30, v_h50, v_h10, v_h20])
model_2 = Model("foo/T3SS", 11)
c_gene_3 = CoreGene(self.model_location, "sctJ", self.profile_factory)
gene_3 = ModelGene(c_gene_3, model)
h30 = Hit(c_gene_3, "h30", 10, "replicon_2", 30, 1.0, 30.0, 1.0, 1.0, 10, 20)
v_h30 = ValidHit(h30, gene_3, GeneStatus.ACCESSORY)
h50 = Hit(c_gene_3, "h50", 10, "replicon_2", 50, 1.0, 50.0, 1.0, 1.0, 10, 20)
v_h50 = ValidHit(h50, gene_3, GeneStatus.ACCESSORY)
c3 = Cluster([v_h30, v_h50], model_2, self.hit_weights)
with self.assertRaises(MacsypyError) as ctx:
c1.merge(c3)
self.assertEqual(str(ctx.exception), "Try to merge Clusters from different model")
def test_get_best_hits(self):
model = Model("foo/T2SS", 10)
gene_name = "gspD"
c_gene_gspd = CoreGene(self.models_location, gene_name, self.profile_factory)
gene_gspd = ModelGene(c_gene_gspd, model)
# gene, model, id, hit_seq_len, replicon_name, position, i_eval,
# score, profil_coverage, sequence_coverage, begin,end
######################
# based on the score #
######################
h0 = Hit(gene_gspd, "PSAE001c01_006940", 803, "PSAE001c01", 3450, float(1.2e-234),
10, float(1.000000), (741.0 - 104.0 + 1) / 803, 104, 741)
h1 = Hit(gene_gspd, "PSAE001c01_013980", 759, "PSAE001c01", 3450, float(3.7e-76),
11, float(1.000000), (736.0 - 105.0 + 1) / 759, 105, 736)
h = get_best_hits([h0, h1])
self.assertEqual(h[0], h1)
#######################
# based on the i_eval #
#######################
h0 = Hit(gene_gspd, "PSAE001c01_006940", 803, "PSAE001c01", 3450, 10,
10, float(1.000000), (741.0 - 104.0 + 1) / 803, 104, 741)
h1 = Hit(gene_gspd, "PSAE001c01_013980", 759, "PSAE001c01", 3450, 11,
10, float(1.000000), (736.0 - 105.0 + 1) / 759, 105, 736)
h = get_best_hits([h0, h1], key='i_eval')
self.assertEqual(h[0], h0)
#################################
# based on the profile_coverage #
#################################
h0 = Hit(gene_gspd, "PSAE001c01_006940", 803, "PSAE001c01", 3450, 10,
10, 10, (741.0 - 104.0 + 1) / 803, 104, 741)
h1 = Hit(gene_gspd, "PSAE001c01_013980", 759, "PSAE001c01", 3450, 10,
10, 11, (736.0 - 105.0 + 1) / 759, 105, 736)
h = get_best_hits([h0, h1], key='profile_coverage')
self.assertEqual(h[0], h1)
# bad criterion
with self.assertRaises(MacsypyError) as ctx:
get_best_hits([h0, h1], key='nimportnaoik')
self.assertEqual('The criterion for Hits comparison nimportnaoik does not exist or is not available.\n'
'It must be either "score", "i_eval" or "profile_coverage".', str(ctx.exception))
def test_str(self):
gene_name = "gspD"
gene = CoreGene(self.model_location, gene_name, self.profile_factory)
hit_prop = {'id': "PSAE001c01_006940",
'hit_seq_len': 803,
'replicon_name': "PSAE001c01",
'position': 694,
'i_eval': float(1.2e-234),
'score': float(779.2),
'gene_name': gene.name,
'profil_coverage': float(1.0),
'sequence_coverage': float(638.000000),
'begin': 104,
'end': 741
}
hit = Hit(gene, hit_prop['id'], hit_prop['hit_seq_len'], hit_prop['replicon_name'],
hit_prop['position'], hit_prop['i_eval'], hit_prop['score'],
hit_prop['profil_coverage'], hit_prop['sequence_coverage'], hit_prop['begin'],hit_prop['end'])
s = "{id}\t{replicon_name}\t{position:d}\t{hit_seq_len:d}\t{gene_name}\t{i_eval:.3e}" \
"\t{score:.3f}\t{profil_coverage:.3f}\t{sequence_coverage:.3f}\t{begin:d}\t{end:d}\n".format(**hit_prop)
self.assertEqual(s, str(hit))
def test_extract(self):
gene_name = "gspD"
c_gene = CoreGene(self.model_location, gene_name, self.profile_factory)
shutil.copy(
self.find_data("hmm", gene_name + self.cfg.res_search_suffix()),
self.cfg.working_dir())
report_path = os.path.join(self.cfg.working_dir(),
gene_name + self.cfg.res_search_suffix())
report = OrderedHMMReport(c_gene, report_path, self.cfg)
report.extract()
self.assertEqual(len(report.hits), 6)
# gene, model, hit_id, hit_seq_ length replicon_name, pos_hit, i_eval,
# score, profile_coverage, sequence_coverage, begin_match, end_match
hits = [
Hit(c_gene, "NC_xxxxx_xx_056141", 803,
RepliconDB.ordered_replicon_name, 141, float(2e-236),
float(779.2), float(1.000000), (741.0 - 104.0 + 1) / 803, 104,
741),
Hit(c_gene, "PSAE001c01_006940", 803,
RepliconDB.ordered_replicon_name, 68, float(1.2e-234),
float(779.2), float(1.000000), (741.0 - 104.0 + 1) / 803, 104,
741),
Hit(c_gene, "PSAE001c01_013980", 759,
RepliconDB.ordered_replicon_name, 69, float(3.7e-76),
float(255.8), float(1.000000), (736.0 - 105.0 + 1) / 759, 105,
736),
Hit(c_gene, "PSAE001c01_017350", 600,
RepliconDB.ordered_replicon_name, 70, float(3.2e-27),
float(94.2), float(0.500000), (506.0 - 226.0 + 1) / 600, 226,
506),
Hit(c_gene, "PSAE001c01_018920", 776,
RepliconDB.ordered_replicon_name, 71, float(6.1e-183),
float(608.4), float(1.000000), (606.0 - 48.0 + 1) / 776, 48,
606),
Hit(c_gene, "PSAE001c01_031420", 658,
RepliconDB.ordered_replicon_name, 73, float(1.8e-210),
float(699.3), float(1.000000), (614.0 - 55.0 + 1) / 658, 55,
614)
]
self.assertListEqual(hits, report.hits)
report = OrderedHMMReport(c_gene, report_path, self.cfg)
report.hits = hits
self.assertIsNone(report.extract())