def test_get_best_hits_4_func(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, loner=True)
# gene, model, id, hit_seq_len, replicon_name, position, i_eval,
# score, profil_coverage, sequence_coverage, begin,end
######################
# based on the score #
######################
h0 = CoreHit(gene_gspd, "PSAE001c01_006940", 803, "PSAE001c01", 3450, float(1.2e-234),
10, float(1.000000), (741.0 - 104.0 + 1) / 803, 104, 741)
h1 = CoreHit(gene_gspd, "PSAE001c01_013980", 759, "PSAE001c01", 3450, float(3.7e-76),
11, float(1.000000), (736.0 - 105.0 + 1) / 759, 105, 736)
m0 = ModelHit(h0, gene_gspd, GeneStatus.ACCESSORY)
m1 = ModelHit(h1, gene_gspd, GeneStatus.ACCESSORY)
l0 = Loner(h0, gene_ref=gene_gspd, gene_status=GeneStatus.ACCESSORY, counterpart=[m1])
l1 = Loner(h1, gene_ref=gene_gspd, gene_status=GeneStatus.ACCESSORY, counterpart=[m0])
l = get_best_hit_4_func(gene_name, [l0, l1])
self.assertEqual(l, l1)
#######################
# based on the i_eval #
#######################
h0 = CoreHit(gene_gspd, "PSAE001c01_006940", 803, "PSAE001c01", 3450, 10,
10, float(1.000000), (741.0 - 104.0 + 1) / 803, 104, 741)
h1 = CoreHit(gene_gspd, "PSAE001c01_013980", 759, "PSAE001c01", 3450, 11,
10, float(1.000000), (736.0 - 105.0 + 1) / 759, 105, 736)
m0 = ModelHit(h0, gene_gspd, GeneStatus.ACCESSORY)
m1 = ModelHit(h1, gene_gspd, GeneStatus.ACCESSORY)
l0 = Loner(h0, gene_ref=gene_gspd, gene_status=GeneStatus.ACCESSORY, counterpart=[m1])
l1 = Loner(h1, gene_ref=gene_gspd, gene_status=GeneStatus.ACCESSORY, counterpart=[m0])
l = get_best_hit_4_func(gene_name, [l0, l1], key='i_eval')
self.assertEqual(l, l0)
#################################
# based on the profile_coverage #
#################################
h0 = CoreHit(gene_gspd, "PSAE001c01_006940", 803, "PSAE001c01", 3450, 10,
10, 10, (741.0 - 104.0 + 1) / 803, 104, 741)
h1 = CoreHit(gene_gspd, "PSAE001c01_013980", 759, "PSAE001c01", 3450, 10,
10, 11, (736.0 - 105.0 + 1) / 759, 105, 736)
m0 = ModelHit(h0, gene_gspd, GeneStatus.ACCESSORY)
m1 = ModelHit(h1, gene_gspd, GeneStatus.ACCESSORY)
l0 = Loner(h0, gene_ref=gene_gspd, gene_status=GeneStatus.ACCESSORY, counterpart=[m1])
l1 = Loner(h1, gene_ref=gene_gspd, gene_status=GeneStatus.ACCESSORY, counterpart=[m0])
l = get_best_hit_4_func(gene_name, [l0, l1], key='profile_coverage')
self.assertEqual(l, l1)
# bad criterion
with self.assertRaises(MacsypyError) as ctx:
get_best_hits([l0, l1], 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_init(self):
# create loner from a CoreHit
l1 = Loner(self.chit_1, gene_ref=self.mg_gspd, gene_status=GeneStatus.MANDATORY)
self.assertEqual(l1.gene_ref, self.mg_gspd)
self.assertEqual(l1.status, GeneStatus.MANDATORY)
# create loner from a CoreHit with counterpart
_ = Loner(self.chit_1, gene_ref=self.mg_gspd, gene_status=GeneStatus.MANDATORY, counterpart=[self.mhit_3])
# try to create Loner from cCoreHit but without gene_ref nor gene_status
with self.assertRaises(MacsypyError) as ctx:
Loner(self.chit_1, gene_ref=self.mg_gspd)
self.assertEqual(str(ctx.exception),
"Cannot Create a Loner hit from CoreHit (gspD, 2) "
"without specifying 'gene_ref' and 'gene_status'")
with self.assertRaises(MacsypyError) as ctx:
Loner(self.chit_1, gene_status=GeneStatus.MANDATORY)
self.assertEqual(str(ctx.exception),
"Cannot Create a Loner hit from CoreHit (gspD, 2) "
"without specifying 'gene_ref' and 'gene_status'")
# create loner from a ModelHit
mh1 = ModelHit(self.chit_1, self.mg_gspd, GeneStatus.MANDATORY)
l3 = Loner(mh1)
self.assertEqual(l3.gene_ref, self.mg_gspd)
self.assertEqual(l3.status, GeneStatus.MANDATORY)
with self.catch_log(log_name='macsypy') as log:
with self.assertRaises(MacsypyError) as ctx:
Loner(self.chit_2, gene_ref=self.mg_sctj, gene_status=GeneStatus.ACCESSORY)
self.assertEqual(str(ctx.exception),
"hit_2 cannot be a loner gene_ref 'sctJ' not tag as loner")
with self.assertRaises(MacsypyError) as ctx:
Loner(self.chit_1, self.cg_gspd, GeneStatus.MANDATORY)
self.assertEqual(str(ctx.exception),
"The Loner 'gene_ref' argument must be a ModelGene not <class 'macsypy.gene.CoreGene'>.")
def test_SpecialHitSerializer_tsv(self):
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))
# we need to reset the ProfileFactory
# because it's a like a singleton
# so other tests are influenced by ProfileFactory and it's configuration
# for instance search_genes get profile without hmmer_exe
profile_factory = ProfileFactory(cfg)
model = Model("foo/T2SS", 10)
gene_name = "gspD"
cg_gspd = CoreGene(models_location, gene_name, profile_factory)
mg_gspd = ModelGene(cg_gspd, model, loner=True)
gene_name = "sctJ"
cg_sctj = CoreGene(models_location, gene_name, profile_factory)
mg_sctj = ModelGene(cg_sctj, model)
gene_name = "abc"
cg_abc = CoreGene(models_location, gene_name, profile_factory)
mg_abc = ModelGene(cg_abc, model)
model.add_mandatory_gene(mg_gspd)
model.add_accessory_gene(mg_sctj)
model.add_accessory_gene(mg_abc)
chit_abc = CoreHit(cg_abc, "hit_abc", 803, "replicon_id", 3, 1.0, 1.0,
1.0, 1.0, 10, 20)
chit_sctj = CoreHit(cg_sctj, "hit_sctj", 803, "replicon_id", 4, 1.0,
1.0, 1.0, 1.0, 10, 20)
chit_gspd1 = CoreHit(cg_gspd, "hit_gspd1", 803, "replicon_id", 20, 1.0,
2.0, 1.0, 1.0, 10, 20)
chit_gspd2 = CoreHit(cg_gspd, "hit_gspd2", 803, "replicon_id", 30, 1.0,
3.0, 1.0, 1.0, 10, 20)
mhit_abc = ModelHit(chit_abc, mg_abc, GeneStatus.ACCESSORY)
mhit_sctj = ModelHit(chit_sctj, mg_sctj, GeneStatus.ACCESSORY)
mhit_gspd1 = ModelHit(chit_gspd1, mg_gspd, GeneStatus.MANDATORY)
mhit_gspd2 = ModelHit(chit_gspd2, mg_gspd, GeneStatus.MANDATORY)
l_gspd1 = Loner(mhit_gspd1, counterpart=[mhit_gspd2])
l_gspd2 = Loner(mhit_gspd2, counterpart=[mhit_gspd1])
ser = TsvSpecialHitSerializer()
txt = ser.serialize([l_gspd1, l_gspd2])
expected_txt = "\t".join([
'replicon', 'model_fqn', 'function', 'gene_name', 'hit_id',
'hit_pos', 'hit_status', 'hit_seq_len', 'hit_i_eval', 'hit_score',
'hit_profile_cov', 'hit_seq_cov', 'hit_begin_match',
'hit_end_match'
])
expected_txt += "\n"
expected_txt += "\t".join([
'replicon_id', 'foo/T2SS', 'gspD', 'gspD', 'hit_gspd1', '20',
'mandatory', '803', '1.000e+00', '2.000', '1.000', '1.000', '10',
'20'
])
expected_txt += "\n"
expected_txt += "\t".join([
'replicon_id', 'foo/T2SS', 'gspD', 'gspD', 'hit_gspd2', '30',
'mandatory', '803', '1.000e+00', '3.000', '1.000', '1.000', '10',
'20'
])
expected_txt += "\n"
self.maxDiff = None
self.assertEqual(txt, expected_txt)
def test_SolutionSerializer_tsv(self):
model_name = 'foo'
model_location = ModelLocation(
path=os.path.join(self.cfg.models_dir()[0], model_name))
###########
# Model B #
###########
model_B = Model("foo/B", 10)
c_gene_sctn_flg = CoreGene(model_location, "sctN_FLG",
self.profile_factory)
gene_sctn_flg = ModelGene(c_gene_sctn_flg, model_B)
c_gene_sctj_flg = CoreGene(model_location, "sctJ_FLG",
self.profile_factory)
gene_sctj_flg = ModelGene(c_gene_sctj_flg, model_B)
c_gene_flgB = CoreGene(model_location, "flgB", self.profile_factory)
gene_flgB = ModelGene(c_gene_flgB, model_B)
c_gene_tadZ = CoreGene(model_location, "tadZ", self.profile_factory)
gene_tadZ = ModelGene(c_gene_tadZ, model_B)
model_B.add_mandatory_gene(gene_sctn_flg)
model_B.add_mandatory_gene(gene_sctj_flg)
model_B.add_accessory_gene(gene_flgB)
model_B.add_accessory_gene(gene_tadZ)
###########
# Model A #
###########
model_A = Model("foo/A", 10)
c_gene_sctn = CoreGene(model_location, "sctN", self.profile_factory)
gene_sctn = ModelGene(c_gene_sctn, model_A)
gene_sctn_hom = Exchangeable(c_gene_sctn_flg, gene_sctn)
gene_sctn.add_exchangeable(gene_sctn_hom)
c_gene_sctj = CoreGene(model_location, "sctJ", self.profile_factory)
gene_sctj = ModelGene(c_gene_sctj, model_A)
gene_sctj_an = Exchangeable(c_gene_sctj_flg, gene_sctj)
gene_sctj.add_exchangeable(gene_sctj_an)
c_gene_gspd = CoreGene(model_location, "gspD", self.profile_factory)
gene_gspd = ModelGene(c_gene_gspd, model_A)
gene_gspd_an = Exchangeable(c_gene_flgB, gene_gspd)
gene_gspd.add_exchangeable(gene_gspd_an)
c_gene_abc = CoreGene(model_location, "abc", self.profile_factory)
gene_abc = ModelGene(c_gene_abc, model_A, loner=True)
gene_abc_ho = Exchangeable(c_gene_tadZ, gene_abc)
gene_abc.add_exchangeable(gene_abc_ho)
model_A.add_mandatory_gene(gene_sctn)
model_A.add_mandatory_gene(gene_sctj)
model_A.add_accessory_gene(gene_gspd)
model_A.add_accessory_gene(gene_abc)
# CoreHit(gene, hit_id, hit_seq_length, replicon_name, position, i_eval, score,
# profile_coverage, sequence_coverage, begin_match, end_match
# pos score
h_sctj = CoreHit(c_gene_sctj, "hit_sctj", 803, "replicon_id", 1, 1.0,
1.0, 1.0, 1.0, 10, 20)
mh_sctj = ModelHit(h_sctj, gene_sctj, GeneStatus.MANDATORY)
h_sctn = CoreHit(c_gene_sctn, "hit_sctn", 803, "replicon_id", 2, 1.0,
1.0, 1.0, 1.0, 10, 20)
mh_sctn = ModelHit(h_sctn, gene_sctn, GeneStatus.MANDATORY)
h_gspd = CoreHit(c_gene_gspd, "hit_gspd", 803, "replicon_id", 3, 1.0,
1.0, 1.0, 1.0, 10, 20)
mh_gspd = ModelHit(h_gspd, gene_gspd, GeneStatus.ACCESSORY)
h_sctj_flg = CoreHit(c_gene_sctj_flg, "hit_sctj_flg", 803,
"replicon_id", 10, 1.0, 1.0, 1.0, 1.0, 10, 20)
h_flgB = CoreHit(c_gene_flgB, "hit_flgB", 803, "replicon_id", 11, 1.0,
1.0, 1.0, 1.0, 10, 20)
h_abc = CoreHit(c_gene_abc, "hit_abc", 803, "replicon_id", 20, 1.0,
1.0, 1.0, 1.0, 10, 20)
h_abc2 = CoreHit(c_gene_abc, "hit_abc2", 803, "replicon_id", 50, 1.0,
1.0, 1.0, 1.0, 10, 20)
h_tadZ = CoreHit(c_gene_tadZ, "hit_tadZ", 803, "replicon_id", 40, 1.0,
1.0, 1.0, 1.0, 10, 20)
mh_sctj_flg = ModelHit(h_sctj_flg, gene_sctj_flg, GeneStatus.MANDATORY)
mh_flgB = ModelHit(h_flgB, gene_flgB, GeneStatus.ACCESSORY)
mh_abc = ModelHit(h_abc, gene_abc, GeneStatus.ACCESSORY)
mh_abc2 = ModelHit(h_abc2, gene_abc, GeneStatus.ACCESSORY)
mh_tadZ = ModelHit(h_tadZ, gene_tadZ, GeneStatus.ACCESSORY)
model_A._min_mandatory_genes_required = 2
model_A._min_genes_required = 2
c1 = Cluster([mh_sctj, mh_sctn, mh_gspd], model_A, self.hit_weights)
c2 = Cluster([mh_sctj, mh_sctn], model_A, self.hit_weights)
c3 = Cluster([
Loner(h_abc,
gene_ref=gene_abc,
gene_status=GeneStatus.ACCESSORY,
counterpart=[mh_abc2])
], model_A, self.hit_weights)
model_B._min_mandatory_genes_required = 1
model_B._min_genes_required = 2
c5 = Cluster([mh_sctj_flg, mh_tadZ, mh_flgB], model_B,
self.hit_weights)
sys_A = System(model_A, [c1, c2, c3], self.cfg.redundancy_penalty())
# score = 2.5, 2 , 0.35 = 4.85 - (2 * 1.5) = 1.85
sys_A.id = "sys_id_A"
sys_B = System(model_B, [c5], self.cfg.redundancy_penalty())
# score = 2.0
sys_B.id = "sys_id_B"
sol = Solution([sys_A, sys_B])
sol_id = '12'
hit_multi_sys_tracker = HitSystemTracker([sys_A, sys_B])
sol_serializer = TsvSolutionSerializer()
sol_tsv = '\t'.join([
sol_id, 'replicon_id', 'hit_sctj', 'sctJ', '1', 'foo/A',
'sys_id_A', '2', '1', '1.000', '1.850', '2', 'sctJ', 'mandatory',
'803', '1.0', '1.000', '1.000', '1.000', '10', '20', '', ''
])
sol_tsv += "\n"
sol_tsv += '\t'.join([
sol_id, 'replicon_id', 'hit_sctn', 'sctN', '2', 'foo/A',
'sys_id_A', '2', '1', '1.000', '1.850', '2', 'sctN', 'mandatory',
'803', '1.0', '1.000', '1.000', '1.000', '10', '20', '', ''
])
sol_tsv += "\n"
sol_tsv += '\t'.join([
sol_id, 'replicon_id', 'hit_gspd', 'gspD', '3', 'foo/A',
'sys_id_A', '2', '1', '1.000', '1.850', '2', 'gspD', 'accessory',
'803', '1.0', '1.000', '1.000', '1.000', '10', '20', '', ''
])
sol_tsv += "\n"
sol_tsv += '\t'.join([
sol_id, 'replicon_id', 'hit_sctj', 'sctJ', '1', 'foo/A',
'sys_id_A', '2', '2', '1.000', '1.850', '2', 'sctJ', 'mandatory',
'803', '1.0', '1.000', '1.000', '1.000', '10', '20', '', ''
])
sol_tsv += "\n"
sol_tsv += '\t'.join([
sol_id, 'replicon_id', 'hit_sctn', 'sctN', '2', 'foo/A',
'sys_id_A', '2', '2', '1.000', '1.850', '2', 'sctN', 'mandatory',
'803', '1.0', '1.000', '1.000', '1.000', '10', '20', '', ''
])
sol_tsv += "\n"
sol_tsv += '\t'.join([
sol_id, 'replicon_id', 'hit_abc', 'abc', '20', 'foo/A', 'sys_id_A',
'2', '-1', '1.000', '1.850', '2', 'abc', 'accessory', '803', '1.0',
'1.000', '1.000', '1.000', '10', '20', 'hit_abc2', ''
])
sol_tsv += "\n"
sol_tsv += "\n"
sol_tsv += '\t'.join([
sol_id, 'replicon_id', 'hit_sctj_flg', 'sctJ_FLG', '10', 'foo/B',
'sys_id_B', '1', '1', '0.750', '2.000', '1', 'sctJ_FLG',
'mandatory', '803', '1.0', '1.000', '1.000', '1.000', '10', '20',
'', ''
])
sol_tsv += "\n"
sol_tsv += '\t'.join([
sol_id, 'replicon_id', 'hit_flgB', 'flgB', '11', 'foo/B',
'sys_id_B', '1', '1', '0.750', '2.000', '1', 'flgB', 'accessory',
'803', '1.0', '1.000', '1.000', '1.000', '10', '20', '', ''
])
sol_tsv += "\n"
sol_tsv += '\t'.join([
sol_id, 'replicon_id', 'hit_tadZ', 'tadZ', '40', 'foo/B',
'sys_id_B', '1', '1', '0.750', '2.000', '1', 'tadZ', 'accessory',
'803', '1.0', '1.000', '1.000', '1.000', '10', '20', '', ''
])
sol_tsv += "\n"
sol_tsv += "\n"
ser = sol_serializer.serialize(sol, sol_id, hit_multi_sys_tracker)
self.maxDiff = None
self.assertEqual(ser, sol_tsv)
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, loner=True)
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)
#CoreHit(gene, hit_id, hit_seq_length, replicon_name, position, i_eval, score,
# profile_coverage, sequence_coverage, begin_match, end_match
# pos score
ch_gspd = CoreHit(c_gene_gspd, "h_gspd", 803, "replicon_id", 10, 1.0,
1.0, 1.0, 1.0, 10, 20)
mh_gspd = ModelHit(ch_gspd,
gene_ref=gene_gspd,
gene_status=GeneStatus.MANDATORY)
ch_sctj = CoreHit(c_gene_sctj, "h_sctj", 803, "replicon_id", 20, 1.0,
1.0, 1.0, 1.0, 20, 30)
mh_sctj = ModelHit(ch_sctj,
gene_ref=gene_sctj,
gene_status=GeneStatus.ACCESSORY)
ch_sctn_flg = CoreHit(c_gene_sctn_flg, "h_sctn_flg", 803,
"replicon_id", 40, 1.0, 1.0, 1.0, 1.0, 30, 40)
mh_sctn_flg = ModelHit(ch_sctn_flg,
gene_ref=gene_sctn_flg,
gene_status=GeneStatus.ACCESSORY)
ch_sctn = CoreHit(c_gene_sctn, "h_sctn", 803, "replicon_id", 80, 1.0,
1.0, 1.0, 1.0, 30, 40)
mh_sctn = Loner(ch_sctn,
gene_ref=gene_sctn,
gene_status=GeneStatus.ACCESSORY,
counterpart=[mh_sctn_flg])
c1 = Cluster([mh_gspd, mh_sctj], model, self.hit_weights)
c2 = Cluster([mh_sctn], model, self.hit_weights)
sys_multi_loci = System(model, [c1, c2], self.cfg.redundancy_penalty())
# score 1.5 .35 = 1.85
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", "1.000", "1.850", "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", "1.000", "1.850", "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", "sctN", "80", "foo/T2SS",
sys_multi_loci.id, "1", "-1", "1.000", "1.850", "1", "sctN",
"accessory", "803", "1.0", "1.000", "1.000", "1.000", "30", "40",
"h_sctn_flg", ""
])
sys_tsv += "\n"
self.maxDiff = None
self.assertEqual(
sys_tsv,
system_serializer.serialize(sys_multi_loci, hit_multi_sys_tracker))
def test_str(self):
l2 = Loner(self.chit_1, gene_ref=self.mg_gspd, gene_status=GeneStatus.MANDATORY, counterpart=[self.mhit_3])
self.assertEqual(str(l2),
'\t'.join(['hit_1', 'replicon_id', '2', '803', 'gspD', '1.000e+00',
'1.000', '1.000', '1.000', '10', '20', 'hit_3'])
)
def test_multi_system(self):
l1 = Loner(self.chit_1, gene_ref=self.mg_gspd, gene_status=GeneStatus.MANDATORY)
self.assertFalse(l1.multi_system)
def test_loner(self):
l1 = Loner(self.chit_1, gene_ref=self.mg_gspd, gene_status=GeneStatus.MANDATORY)
self.assertTrue(l1.loner)
def test_len(self):
l1 = Loner(self.chit_1, gene_ref=self.mg_gspd, gene_status=GeneStatus.MANDATORY)
self.assertEqual(len(l1), 1)
l2 = Loner(self.chit_1, gene_ref=self.mg_gspd, gene_status=GeneStatus.MANDATORY, counterpart=[self.mhit_3])
self.assertEqual(len(l2), 2)
def test_counterpart(self):
l1 = Loner(self.chit_1, gene_ref=self.mg_gspd, gene_status=GeneStatus.MANDATORY)
self.assertSetEqual(l1.counterpart, set())
l2 = Loner(self.chit_1, gene_ref=self.mg_gspd, gene_status=GeneStatus.MANDATORY, counterpart=[self.mhit_3])
self.assertSetEqual(l2.counterpart, set([self.mhit_3]))
def _build_clusters(cfg, profile_factory):
model_name = 'foo'
model_location = ModelLocation(
path=os.path.join(cfg.models_dir()[0], model_name))
models = {}
cg_sctn_flg = CoreGene(model_location, "sctN_FLG", profile_factory)
cg_sctj_flg = CoreGene(model_location, "sctJ_FLG", profile_factory)
cg_flgB = CoreGene(model_location, "flgB", profile_factory)
cg_tadZ = CoreGene(model_location, "tadZ", profile_factory)
cg_sctn = CoreGene(model_location, "sctN", profile_factory)
cg_sctj = CoreGene(model_location, "sctJ", profile_factory)
cg_gspd = CoreGene(model_location, "gspD", profile_factory)
cg_abc = CoreGene(model_location, "abc", profile_factory)
cg_sctc = CoreGene(model_location, "sctC", profile_factory)
###########
# Model A #
###########
models['A'] = Model("foo/A", 10)
mgA_sctn = ModelGene(cg_sctn, models['A'])
mgA_sctn_hom = Exchangeable(cg_sctn_flg, mgA_sctn)
mgA_sctn.add_exchangeable(mgA_sctn_hom)
mgA_sctj = ModelGene(cg_sctj, models['A'])
mgA_sctj_an = Exchangeable(cg_sctj_flg, mgA_sctj)
mgA_sctj.add_exchangeable(mgA_sctj_an)
mgA_gspd = ModelGene(cg_gspd, models['A'])
mgA_gspd_an = Exchangeable(cg_flgB, mgA_gspd)
mgA_gspd.add_exchangeable(mgA_gspd_an)
mgA_abc = ModelGene(cg_abc, models['A'])
mgA_abc_ho = Exchangeable(cg_tadZ, mgA_abc)
mgA_abc.add_exchangeable(mgA_abc_ho)
models['A'].add_mandatory_gene(mgA_sctn)
models['A'].add_mandatory_gene(mgA_sctj)
models['A'].add_accessory_gene(mgA_gspd)
models['A'].add_forbidden_gene(mgA_abc)
models['A']._min_mandatory_genes_required = 2
models['A']._min_genes_required = 2
###########
# Model B #
###########
models['B'] = Model("foo/B", 10)
mgB_sctn_flg = ModelGene(cg_sctn_flg, models['B'])
mgB_sctj_flg = ModelGene(cg_sctj_flg, models['B'])
mgB_flgB = ModelGene(cg_flgB, models['B'])
mgB_tadZ = ModelGene(cg_tadZ, models['B'])
models['B'].add_mandatory_gene(mgB_sctn_flg)
models['B'].add_mandatory_gene(mgB_sctj_flg)
models['B'].add_accessory_gene(mgB_flgB)
models['B'].add_accessory_gene(mgB_tadZ)
models['B']._min_mandatory_genes_required = 1
models['B']._min_genes_required = 2
###########
# Model C #
###########
models['C'] = Model("foo/C", 10)
mgC_sctn_flg = ModelGene(cg_sctn_flg, models['C'])
mgC_sctj_flg = ModelGene(cg_sctj_flg, models['C'])
mgC_flgB = ModelGene(cg_flgB, models['C'])
mgC_tadZ = ModelGene(cg_tadZ, models['C'])
mgC_gspd = ModelGene(cg_gspd, models['C'])
models['C'].add_mandatory_gene(mgC_sctn_flg)
models['C'].add_mandatory_gene(mgC_sctj_flg)
models['C'].add_mandatory_gene(mgC_flgB)
models['C'].add_accessory_gene(mgC_tadZ)
models['C'].add_accessory_gene(mgC_gspd)
models['C']._min_mandatory_genes_required = 1
models['C']._min_genes_required = 2
###########
# Model D #
###########
models['D'] = Model("foo/D", 10)
mgD_abc = ModelGene(cg_abc, models['D'])
mgD_sctn = ModelGene(cg_sctn, models['D'])
models['D'].add_mandatory_gene(mgD_abc)
models['D'].add_accessory_gene(mgD_sctn)
models['D']._min_mandatory_genes_required = 1
models['D']._min_genes_required = 1
###########
# Model E #
###########
models['E'] = Model("foo/E", 10)
mgE_gspd = ModelGene(cg_gspd, models['E'])
models['E'].add_accessory_gene(mgE_gspd)
models['E']._min_mandatory_genes_required = 0
models['E']._min_genes_required = 1
###########
# Model F #
###########
models['F'] = Model("foo/F", 10)
mgF_abc = ModelGene(cg_abc, models['F'])
models['F'].add_mandatory_gene(mgF_abc)
models['F']._min_mandatory_genes_required = 1
models['F']._min_genes_required = 1
#####################
# Model G idem as C #
#####################
models['G'] = Model("foo/G", 10)
mgG_sctn_flg = ModelGene(cg_sctn_flg, models['G'])
mgG_sctj_flg = ModelGene(cg_sctj_flg, models['G'])
mgG_flgB = ModelGene(cg_flgB, models['G'])
mgG_tadZ = ModelGene(cg_tadZ, models['G'])
mgG_gspd = ModelGene(cg_gspd, models['G'])
models['G'].add_mandatory_gene(mgG_sctn_flg)
models['G'].add_mandatory_gene(mgG_sctj_flg)
models['G'].add_mandatory_gene(mgG_flgB)
models['G'].add_accessory_gene(mgG_tadZ)
models['G'].add_accessory_gene(mgG_gspd)
#####################
# Model H idem as D #
#####################
models['H'] = Model("foo/H", 10)
mgH_abc = ModelGene(cg_abc, models['H'])
mgH_sctn = ModelGene(cg_sctn, models['H'])
models['H'].add_mandatory_gene(mgH_abc)
models['H'].add_accessory_gene(mgH_sctn)
models['H']._min_mandatory_genes_required = 1
models['H']._min_genes_required = 1
###########
# Model I #
###########
models['I'] = Model("foo/I", 10)
mgI_abc = ModelGene(cg_abc, models['I'])
mgI_flgB = ModelGene(cg_flgB, models['I'])
mgI_tadZ = ModelGene(cg_tadZ, models['I'])
models['I'].add_mandatory_gene(mgI_abc)
models['I'].add_mandatory_gene(mgI_flgB)
models['I'].add_accessory_gene(mgI_tadZ)
models['I']._min_mandatory_genes_required = 1
models['I']._min_genes_required = 1
###########
# model J #
###########
models['J'] = Model("foo/J", 10)
mgJ_abc = ModelGene(cg_abc, models['J'])
mgJ_gspd = ModelGene(cg_gspd, models['J'])
mgJ_tadZ = ModelGene(cg_tadZ, models['J'])
mgJ_sctc = ModelGene(cg_sctc, models['J'])
models['J'].add_mandatory_gene(mgJ_abc)
models['J'].add_mandatory_gene(mgJ_gspd)
models['J'].add_accessory_gene(mgJ_tadZ)
models['J'].add_accessory_gene(mgJ_sctc)
models['J']._min_mandatory_genes_required = 1
models['J']._min_genes_required = 1
###########
# model K #
###########
models['K'] = Model("foo/K", 10)
mgK_flgB = ModelGene(cg_flgB, models['K'])
mgK_sctn_flg = ModelGene(cg_sctn_flg, models['K'])
mgK_sctj_flg = ModelGene(cg_sctj_flg, models['K'])
mgK_sctn = ModelGene(cg_sctn, models['K'])
models['K'].add_mandatory_gene(mgK_flgB)
models['K'].add_mandatory_gene(mgK_sctn_flg)
models['K'].add_accessory_gene(mgK_sctj_flg)
models['K'].add_accessory_gene(mgK_sctn)
models['K']._min_mandatory_genes_required = 1
models['K']._min_genes_required = 1
###########
# model L #
###########
models['L'] = Model("foo/L", 10)
mgL_flgB = ModelGene(cg_flgB, models['L'])
mgL_sctn_flg = ModelGene(cg_sctn_flg, models['L'])
mgL_sctj_flg = ModelGene(cg_sctj_flg, models['L'])
mgL_sctn = ModelGene(cg_sctn, models['L'], loner=True)
models['L'].add_mandatory_gene(mgL_flgB)
models['L'].add_mandatory_gene(mgL_sctn_flg)
models['L'].add_accessory_gene(mgL_sctj_flg)
models['L'].add_accessory_gene(mgL_sctn)
###########
# model M #
###########
models['M'] = Model("foo/L", 10)
mgM_sctj = ModelGene(cg_sctj, models['M'])
mgM_gspd = ModelGene(cg_gspd, models['M'])
mgM_sctn = ModelGene(cg_sctn, models['M'], multi_system=True)
mgM_tadZ = ModelGene(cg_tadZ, models['M'])
mgM_abc = ModelGene(cg_abc, models['M'])
models['M'].add_mandatory_gene(mgM_sctj)
models['M'].add_mandatory_gene(mgM_gspd)
models['M'].add_accessory_gene(mgM_sctn)
models['M'].add_accessory_gene(mgM_tadZ)
models['M'].add_accessory_gene(mgM_abc)
###########
# model N #
###########
models['N'] = Model("foo/N", 10)
mgN_flgB = ModelGene(cg_flgB, models['N'])
mgN_sctn_flg = ModelGene(cg_sctn_flg, models['N'])
mgN_sctj = ModelGene(cg_sctj, models['N'])
mgN_sctj_flg = ModelGene(cg_sctj_flg, models['N'])
mgN_sctn = ModelGene(cg_sctn, models['N'], loner=True)
mgN_tadZ = ModelGene(cg_tadZ, models['N'], loner=True)
models['N'].add_mandatory_gene(mgN_flgB)
models['N'].add_mandatory_gene(mgN_sctn_flg)
models['N'].add_accessory_gene(mgN_sctj)
models['N'].add_accessory_gene(mgN_sctj_flg)
models['N'].add_accessory_gene(mgN_sctn)
models['N'].add_accessory_gene(mgN_tadZ)
###########
# model O #
###########
models['O'] = Model("foo/O", 10)
mgO_sctj = ModelGene(cg_sctj, models['O'], multi_system=True)
mgO_sctj_flg = Exchangeable(cg_sctj_flg, mgO_sctj)
mgO_sctj.add_exchangeable(mgO_sctj_flg)
mgO_gspd = ModelGene(cg_gspd, models['O'], loner=True, multi_system=True)
mgO_sctn = ModelGene(cg_sctn, models['O'], multi_system=True)
mgO_sctn_flg = Exchangeable(cg_sctn_flg, mgO_sctn)
mgO_sctn.add_exchangeable(mgO_sctn_flg)
mgO_tadZ = ModelGene(cg_tadZ, models['O'], loner=True)
mgO_abc = ModelGene(cg_abc, models['O'])
models['O'].add_mandatory_gene(mgO_sctj)
models['O'].add_mandatory_gene(mgO_gspd)
models['O'].add_accessory_gene(mgO_sctn)
models['O'].add_accessory_gene(mgO_tadZ)
models['O'].add_neutral_gene(mgO_abc)
ch_sctj = CoreHit(cg_sctj, "hit_sctj", 803, "replicon_id", 1, 1.0, 1.0,
1.0, 1.0, 10, 20)
ch_sctn = CoreHit(cg_sctn, "hit_sctn", 803, "replicon_id", 2, 1.0, 1.0,
1.0, 1.0, 10, 20)
ch_gspd = CoreHit(cg_gspd, "hit_gspd", 803, "replicon_id", 3, 1.0, 1.0,
1.0, 1.0, 10, 20)
ch_sctn_flg = CoreHit(cg_sctn_flg, "hit_sctn_flg", 803, "replicon_id", 4,
1.0, 1.0, 1.0, 1.0, 10, 20)
ch_sctj = CoreHit(cg_sctj, "hit_sctj", 803, "replicon_id", 5, 1.0, 1.0,
1.0, 1.0, 10, 20)
ch_sctj_flg = CoreHit(cg_sctj_flg, "hit_sctj_flg", 803, "replicon_id", 6,
1.0, 1.0, 1.0, 1.0, 10, 20)
ch_flgB = CoreHit(cg_flgB, "hit_flgB", 803, "replicon_id", 7, 1.0, 1.0,
1.0, 1.0, 10, 20)
ch_tadZ = CoreHit(cg_tadZ, "hit_tadZ", 803, "replicon_id", 8, 1.0, 1.0,
1.0, 1.0, 10, 20)
ch_abc = CoreHit(cg_abc, "hit_abc", 803, "replicon_id", 9, 1.0, 1.0, 1.0,
1.0, 10, 20)
hit_weights = HitWeight(**cfg.hit_weights())
clusters = {}
clusters['c1'] = Cluster([
ModelHit(ch_sctj, gene_ref=mgA_sctj, gene_status=GeneStatus.MANDATORY),
ModelHit(ch_sctn, gene_ref=mgA_sctn, gene_status=GeneStatus.MANDATORY),
ModelHit(ch_gspd, gene_ref=mgA_gspd, gene_status=GeneStatus.ACCESSORY)
], models['A'], hit_weights)
clusters['c2'] = Cluster([
ModelHit(ch_sctj, gene_ref=mgA_sctj, gene_status=GeneStatus.MANDATORY),
ModelHit(ch_sctn, gene_ref=mgA_sctn, gene_status=GeneStatus.MANDATORY)
], models['A'], hit_weights)
clusters['c3'] = Cluster([
ModelHit(ch_sctj_flg,
gene_ref=mgB_sctj_flg,
gene_status=GeneStatus.MANDATORY),
ModelHit(ch_tadZ, gene_ref=mgB_tadZ, gene_status=GeneStatus.ACCESSORY),
ModelHit(ch_flgB, gene_ref=mgB_flgB, gene_status=GeneStatus.ACCESSORY)
], models['B'], hit_weights)
clusters['c4'] = Cluster([
ModelHit(ch_sctj_flg,
gene_ref=mgC_sctj_flg,
gene_status=GeneStatus.MANDATORY),
ModelHit(ch_tadZ, gene_ref=mgC_tadZ, gene_status=GeneStatus.ACCESSORY),
ModelHit(ch_flgB, gene_ref=mgC_flgB, gene_status=GeneStatus.MANDATORY),
ModelHit(ch_gspd, gene_ref=mgC_gspd, gene_status=GeneStatus.ACCESSORY)
], models['C'], hit_weights)
clusters['c5'] = Cluster([
ModelHit(ch_abc, gene_ref=mgD_abc, gene_status=GeneStatus.MANDATORY),
ModelHit(ch_sctn, gene_ref=mgD_sctn, gene_status=GeneStatus.ACCESSORY)
], models['D'], hit_weights)
clusters['c6'] = Cluster([
ModelHit(ch_gspd, gene_ref=mgE_gspd, gene_status=GeneStatus.ACCESSORY)
], models['E'], hit_weights)
clusters['c7'] = Cluster(
[ModelHit(ch_abc, gene_ref=mgF_abc, gene_status=GeneStatus.MANDATORY)],
models['F'], hit_weights)
clusters['c8'] = Cluster([
ModelHit(ch_flgB, gene_ref=mgI_flgB, gene_status=GeneStatus.MANDATORY),
ModelHit(ch_tadZ, gene_ref=mgI_tadZ, gene_status=GeneStatus.ACCESSORY)
], models['I'], hit_weights)
clusters['c9'] = Cluster([
ModelHit(ch_abc, gene_ref=mgJ_abc, gene_status=GeneStatus.MANDATORY),
ModelHit(ch_tadZ, gene_ref=mgJ_tadZ, gene_status=GeneStatus.ACCESSORY)
], models['J'], hit_weights)
clusters['c10'] = Cluster([
ModelHit(ch_flgB, gene_ref=mgK_flgB, gene_status=GeneStatus.MANDATORY),
ModelHit(ch_sctn, gene_ref=mgK_sctn, gene_status=GeneStatus.ACCESSORY)
], models['K'], hit_weights)
clusters['c11'] = Cluster([
ModelHit(ch_flgB, gene_ref=mgL_flgB, gene_status=GeneStatus.MANDATORY),
ModelHit(ch_sctn_flg,
gene_ref=mgL_sctn_flg,
gene_status=GeneStatus.MANDATORY)
], models['L'], hit_weights)
clusters['c12'] = Cluster([
ModelHit(ch_sctj_flg,
gene_ref=mgL_sctj_flg,
gene_status=GeneStatus.ACCESSORY),
ModelHit(ch_sctn, gene_ref=mgL_sctn, gene_status=GeneStatus.ACCESSORY)
], models['L'], hit_weights)
clusters['c13'] = Cluster(
[Loner(ch_sctn, gene_ref=mgL_sctn, gene_status=GeneStatus.ACCESSORY)],
models['L'], hit_weights)
clusters['c14'] = Cluster([
ModelHit(ch_sctj, mgM_sctj, gene_status=GeneStatus.MANDATORY),
MultiSystem(
ch_sctn, gene_ref=mgM_sctn, gene_status=GeneStatus.ACCESSORY),
ModelHit(ch_gspd, gene_ref=mgM_gspd, gene_status=GeneStatus.ACCESSORY)
], models['M'], hit_weights)
clusters['c15'] = Cluster([
ModelHit(ch_tadZ, gene_ref=mgM_tadZ, gene_status=GeneStatus.ACCESSORY),
ModelHit(ch_abc, gene_ref=mgM_abc, gene_status=GeneStatus.ACCESSORY)
], models['M'], hit_weights)
clusters['c16'] = Cluster([
MultiSystem(
ch_sctn, gene_ref=mgM_sctn, gene_status=GeneStatus.ACCESSORY)
], models['M'], hit_weights)
clusters['c17'] = Cluster([
ModelHit(ch_flgB, mgL_flgB, GeneStatus.MANDATORY),
ModelHit(ch_sctn_flg, mgL_sctn_flg, GeneStatus.MANDATORY)
], models['N'], hit_weights)
clusters['c18'] = Cluster([
ModelHit(ch_sctj, mgN_sctj, GeneStatus.MANDATORY),
ModelHit(ch_sctj_flg, mgL_sctj_flg, GeneStatus.MANDATORY)
], models['N'], hit_weights)
clusters['c19'] = Cluster([Loner(ch_sctn, mgL_sctn, GeneStatus.ACCESSORY)],
models['N'], hit_weights)
clusters['c20'] = Cluster([Loner(ch_tadZ, mgN_tadZ, GeneStatus.ACCESSORY)],
models['N'], hit_weights)
clusters['c21'] = Cluster([
ModelHit(ch_sctj, mgO_sctj, GeneStatus.MANDATORY),
ModelHit(ch_abc, mgO_abc, GeneStatus.NEUTRAL),
ModelHit(ch_tadZ, mgO_tadZ, GeneStatus.ACCESSORY)
], models['O'], hit_weights)
clusters['c22'] = Cluster([
ModelHit(ch_sctn_flg, mgO_sctn_flg, GeneStatus.ACCESSORY),
ModelHit(ch_gspd, mgO_gspd, GeneStatus.MANDATORY),
ModelHit(ch_tadZ, mgO_tadZ, GeneStatus.ACCESSORY)
], models['O'], hit_weights)
clusters['c23'] = Cluster(
[Loner(ch_gspd, mgO_gspd, gene_status=GeneStatus.MANDATORY)],
models['O'], hit_weights)
clusters['c24'] = Cluster(
[MultiSystem(ch_gspd, mgO_gspd, gene_status=GeneStatus.MANDATORY)],
models['O'], hit_weights)
clusters['c25'] = Cluster(
[MultiSystem(ch_sctn, mgO_sctn, gene_status=GeneStatus.ACCESSORY)],
models['O'], hit_weights)
clusters['c26'] = Cluster([
MultiSystem(
ch_sctj_flg, mgO_sctj_flg, gene_status=GeneStatus.MANDATORY)
], models['O'], hit_weights)
return models, clusters