def _search_in_ordered_replicon(hits_by_replicon, models_to_detect, config,
logger):
systems = []
rejected_clusters = []
rep_db = RepliconDB(config)
for rep_name in hits_by_replicon:
logger.info(
"\n{:#^60}".format(f" Hits analysis for replicon {rep_name} "))
rep_info = rep_db[rep_name]
for model in models_to_detect:
logger.info(f"Check model {model.fqn}")
hits_related_one_model = model.filter(hits_by_replicon[rep_name])
logger.debug("{:#^80}".format(" hits related to {} ".format(
model.name)))
logger.debug("".join([str(h) for h in hits_related_one_model]))
logger.debug("#" * 80)
logger.info("Building clusters")
hit_weights = HitWeight(**config.hit_weights())
clusters = cluster.build_clusters(hits_related_one_model, rep_info,
model, hit_weights)
logger.debug("{:#^80}".format("CLUSTERS"))
logger.debug("\n" + "\n".join([str(c) for c in clusters]))
logger.debug("#" * 80)
logger.info("Searching systems")
if model.multi_loci:
# The loners are already in clusters lists with their context
# so they are take in account
clusters_combination = [
itertools.combinations(clusters, i)
for i in range(1,
len(clusters) + 1)
]
else:
# we must add loners manually
# but only if the cluster does not already contains them
loners = cluster.get_loners(hits_related_one_model, model,
hit_weights)
clusters_combination = []
for one_cluster in clusters:
one_clust_combination = [one_cluster]
filtered_loners = cluster.filter_loners(
one_cluster, loners)
one_clust_combination.extend(filtered_loners)
clusters_combination.append([one_clust_combination])
for one_combination_set in clusters_combination:
for one_clust_combination in one_combination_set:
ordered_matcher = OrderedMatchMaker(
model, redundancy_penalty=config.redundancy_penalty())
res = ordered_matcher.match(one_clust_combination)
if isinstance(res, System):
systems.append(res)
else:
rejected_clusters.append(res)
if systems:
systems.sort(key=lambda syst: (syst.replicon_name, syst.position[0],
syst.model.fqn, -syst.score))
return systems, rejected_clusters
def test_hit_weight_default(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)
hit_weight = HitWeight(**cfg.hit_weights())
self.assertEqual(hit_weight.mandatory, 1)
self.assertEqual(hit_weight.accessory, 0.5)
self.assertEqual(hit_weight.itself, 1)
self.assertEqual(hit_weight.exchangeable, 0.8)
self.assertEqual(hit_weight.loner_multi_system, 0.7)
def setUp(self) -> None:
self.args = argparse.Namespace()
self.args.sequence_db = self.find_data("base", "test_1.fasta")
self.args.db_type = 'gembase'
self.args.models_dir = self.find_data('models')
self.args.res_search_dir = "blabla"
self.cfg = Config(MacsyDefaults(), self.args)
self.model_name = 'foo'
self.model_location = ModelLocation(path=os.path.join(self.args.models_dir, self.model_name))
self.profile_factory = ProfileFactory(self.cfg)
self.hit_weights = HitWeight(**self.cfg.hit_weights())
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')
self.cfg = Config(MacsyDefaults(), args)
self.model_name = 'foo'
self.model_location = ModelLocation(
path=os.path.join(args.models_dir, self.model_name))
self.profile_factory = ProfileFactory(self.cfg)
self.hit_weights = HitWeight(**self.cfg.hit_weights())
# reset the uniq id number for AbstractSetOfHits
# to have predictable results
AbstractSetOfHits._id = itertools.count(1)
def test_hit_weight_not_default(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')
args.mandatory_weight = 2.0
args.accessory_weight = 3.0
args.neutral_weight = 4.0
args.exchangeable_weight = 5.0
args.itself_weight = 6.0
args.loner_multi_system_weight = 12
cfg = Config(MacsyDefaults(), args)
hit_weight = HitWeight(**cfg.hit_weights())
self.assertEqual(hit_weight.mandatory, 2.0)
self.assertEqual(hit_weight.accessory, 3.0)
self.assertEqual(hit_weight.neutral, 4.0)
self.assertEqual(hit_weight.exchangeable, 5.0)
self.assertEqual(hit_weight.itself, 6.0)
self.assertEqual(hit_weight.loner_multi_system, 12.0)
def test_systems_to_txt(self):
system_str = f"""# macsyfinder {macsypy.__version__}
# {' '.join(sys.argv)}
# No Systems found
"""
f_out = StringIO()
track_multi_systems_hit = HitSystemTracker([])
systems_to_txt([], track_multi_systems_hit, f_out)
self.assertMultiLineEqual(system_str, f_out.getvalue())
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)
# test if id is well incremented
gene_name = "gspD"
c_gene_gspd = CoreGene(models_location, gene_name, profile_factory)
gene_gspd = ModelGene(c_gene_gspd, model)
model.add_mandatory_gene(gene_gspd)
gene_name = "sctJ"
c_gene_sctj = CoreGene(models_location, gene_name, 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)
system_1 = System(model, [
Cluster([v_hit_1, v_hit_2], model, HitWeight(**cfg.hit_weights()))
], cfg.redundancy_penalty())
system_str = f"""# macsyfinder {macsypy.__version__}
# {' '.join(sys.argv)}
# Systems found:
system id = replicon_id_T2SS_{next(System._id) - 1}
model = foo/T2SS
replicon = replicon_id
clusters = [('hit_1', 'gspD', 1), ('hit_2', 'sctJ', 1)]
occ = 1
wholeness = 1.000
loci nb = 1
score = 1.500
mandatory genes:
\t- gspD: 1 (gspD)
accessory genes:
\t- sctJ: 1 (sctJ)
neutral genes:
============================================================
"""
f_out = StringIO()
track_multi_systems_hit = HitSystemTracker([system_1])
systems_to_txt([system_1], track_multi_systems_hit, f_out)
self.assertMultiLineEqual(system_str, f_out.getvalue())
def test_rejected_clst_to_txt(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')
args.res_search_dir = "blabla"
cfg = Config(MacsyDefaults(), args)
model_name = 'foo'
models_location = ModelLocation(
path=os.path.join(args.models_dir, model_name))
profile_factory = ProfileFactory(cfg)
model = Model("foo/T2SS", 11)
gene_name = "gspD"
c_gene_gspd = CoreGene(models_location, gene_name, profile_factory)
gene_1 = ModelGene(c_gene_gspd, model)
gene_name = "sctC"
c_gene_sctc = CoreGene(models_location, gene_name, profile_factory)
gene_2 = ModelGene(c_gene_sctc, model)
model.add_mandatory_gene(gene_1)
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_gspd, "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_sctc, "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_gspd, "h10", 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_sctc, "h20", 10, "replicon_1", 50, 1.0, 20.0, 1.0,
1.0, 10, 20)
v_h50 = ValidHit(h50, gene_2, GeneStatus.ACCESSORY)
hit_weights = HitWeight(**cfg.hit_weights())
c1 = Cluster([v_h10, v_h20], model, hit_weights)
c2 = Cluster([v_h40, v_h50], model, hit_weights)
r_c = RejectedClusters(model, [c1, c2],
["The reasons to reject this clusters"])
rej_clst_str = f"""# macsyfinder {macsypy.__version__}
# {' '.join(sys.argv)}
# Rejected clusters:
Cluster:
- model = T2SS
- replicon = replicon_1
- hits = (h10, gspD, 10), (h20, sctC, 20)
Cluster:
- model = T2SS
- replicon = replicon_1
- hits = (h10, gspD, 40), (h20, sctC, 50)
These clusters have been rejected because:
\t- The reasons to reject this clusters
============================================================
"""
f_out = StringIO()
rejected_clst_to_txt([r_c], f_out)
self.maxDiff = None
self.assertMultiLineEqual(rej_clst_str, f_out.getvalue())
rej_clst_str = f"""# macsyfinder {macsypy.__version__}
# {' '.join(sys.argv)}
# No Rejected clusters
"""
f_out = StringIO()
rejected_clst_to_txt([], f_out)
self.assertMultiLineEqual(rej_clst_str, f_out.getvalue())
def test_solutions_to_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_A = Model("foo/A", 10)
model_B = Model("foo/B", 10)
model_C = Model("foo/C", 10)
c_gene_sctn_flg = CoreGene(models_location, "sctN_FLG",
profile_factory)
gene_sctn_flg = ModelGene(c_gene_sctn_flg, model_B)
c_gene_sctj_flg = CoreGene(models_location, "sctJ_FLG",
profile_factory)
gene_sctj_flg = ModelGene(c_gene_sctj_flg, model_B)
c_gene_flgB = CoreGene(models_location, "flgB", profile_factory)
gene_flgB = ModelGene(c_gene_flgB, model_B)
c_gene_tadZ = CoreGene(models_location, "tadZ", profile_factory)
gene_tadZ = ModelGene(c_gene_tadZ, model_B)
c_gene_sctn = CoreGene(models_location, "sctN", 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(models_location, "sctJ", 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(models_location, "gspD", 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(models_location, "abc", profile_factory)
gene_abc = ModelGene(c_gene_abc, model_A)
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_forbidden_gene(gene_abc)
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_C.add_mandatory_gene(gene_sctn_flg)
model_C.add_mandatory_gene(gene_sctj_flg)
model_C.add_mandatory_gene(gene_flgB)
model_C.add_accessory_gene(gene_tadZ)
model_C.add_accessory_gene(gene_gspd)
h_sctj = Hit(c_gene_sctj, "hit_sctj", 803, "replicon_id", 1, 1.0, 1.0,
1.0, 1.0, 10, 20)
h_sctn = Hit(c_gene_sctn, "hit_sctn", 803, "replicon_id", 1, 1.0, 1.0,
1.0, 1.0, 10, 20)
h_gspd = Hit(c_gene_gspd, "hit_gspd", 803, "replicon_id", 1, 1.0, 1.0,
1.0, 1.0, 10, 20)
h_sctj_flg = Hit(c_gene_sctj_flg, "hit_sctj_flg", 803, "replicon_id",
1, 1.0, 1.0, 1.0, 1.0, 10, 20)
h_flgB = Hit(c_gene_flgB, "hit_flgB", 803, "replicon_id", 1, 1.0, 1.0,
1.0, 1.0, 10, 20)
h_tadZ = Hit(c_gene_tadZ, "hit_tadZ", 803, "replicon_id", 1, 1.0, 1.0,
1.0, 1.0, 10, 20)
model_A._min_mandatory_genes_required = 2
model_A._min_genes_required = 2
hit_weights = HitWeight(**cfg.hit_weights())
c1 = Cluster([
ValidHit(h_sctj, gene_sctj, GeneStatus.MANDATORY),
ValidHit(h_sctn, gene_sctn, GeneStatus.MANDATORY),
ValidHit(h_gspd, gene_gspd, GeneStatus.ACCESSORY)
], model_A, hit_weights)
c2 = Cluster([
ValidHit(h_sctj, gene_sctj, GeneStatus.MANDATORY),
ValidHit(h_sctn, gene_sctn, GeneStatus.MANDATORY)
], model_A, hit_weights)
model_B._min_mandatory_genes_required = 1
model_B._min_genes_required = 2
c3 = Cluster([
ValidHit(h_sctj_flg, gene_sctj_flg, GeneStatus.MANDATORY),
ValidHit(h_tadZ, gene_tadZ, GeneStatus.ACCESSORY),
ValidHit(h_flgB, gene_flgB, GeneStatus.ACCESSORY)
], model_B, hit_weights)
model_C._min_mandatory_genes_required = 1
model_C._min_genes_required = 2
c4 = Cluster([
ValidHit(h_sctj_flg, gene_sctj_flg, GeneStatus.MANDATORY),
ValidHit(h_tadZ, gene_tadZ, GeneStatus.ACCESSORY),
ValidHit(h_flgB, gene_flgB, GeneStatus.MANDATORY),
ValidHit(h_gspd, gene_gspd, GeneStatus.ACCESSORY)
], model_C, hit_weights)
sys_A = System(model_A, [c1, c2], cfg.redundancy_penalty())
sys_A.id = "sys_id_A"
sys_B = System(model_B, [c3], cfg.redundancy_penalty())
sys_B.id = "sys_id_B"
sys_C = System(model_C, [c4], cfg.redundancy_penalty())
sys_C.id = "sys_id_C"
sol_1 = [sys_A, sys_B]
sol_2 = [sys_A, sys_C]
sol_id_1 = '1'
sol_id_2 = '2'
sol_tsv = f"""# macsyfinder {macsypy.__version__}
# {' '.join(sys.argv)}
# Systems found:
"""
sol_tsv += "\t".join([
"sol_id", "replicon", "hit_id", "gene_name", "hit_pos",
"model_fqn", "sys_id", "sys_loci", "sys_wholeness", "sys_score",
"sys_occ", "hit_gene_ref", "hit_status", "hit_seq_len",
"hit_i_eval", "hit_score", "hit_profile_cov", "hit_seq_cov",
"hit_begin_match", "hit_end_match", "used_in"
])
sol_tsv += "\n"
sol_tsv += '\t'.join([
sol_id_1, 'replicon_id', 'hit_sctj', 'sctJ', '1', 'foo/A',
'sys_id_A', '2', '1.000', '1.500', '2', 'sctJ', 'mandatory', '803',
'1.0', '1.000', '1.000', '1.000', '10', '20', ''
])
sol_tsv += "\n"
sol_tsv += '\t'.join([
sol_id_1, 'replicon_id', 'hit_sctn', 'sctN', '1', 'foo/A',
'sys_id_A', '2', '1.000', '1.500', '2', 'sctN', 'mandatory', '803',
'1.0', '1.000', '1.000', '1.000', '10', '20', ''
])
sol_tsv += "\n"
sol_tsv += '\t'.join([
sol_id_1, 'replicon_id', 'hit_gspd', 'gspD', '1', 'foo/A',
'sys_id_A', '2', '1.000', '1.500', '2', 'gspD', 'accessory', '803',
'1.0', '1.000', '1.000', '1.000', '10', '20', ''
])
sol_tsv += "\n"
sol_tsv += '\t'.join([
sol_id_1, 'replicon_id', 'hit_sctj', 'sctJ', '1', 'foo/A',
'sys_id_A', '2', '1.000', '1.500', '2', 'sctJ', 'mandatory', '803',
'1.0', '1.000', '1.000', '1.000', '10', '20', ''
])
sol_tsv += "\n"
sol_tsv += '\t'.join([
sol_id_1, 'replicon_id', 'hit_sctn', 'sctN', '1', 'foo/A',
'sys_id_A', '2', '1.000', '1.500', '2', 'sctN', 'mandatory', '803',
'1.0', '1.000', '1.000', '1.000', '10', '20', ''
])
sol_tsv += "\n"
sol_tsv += "\n"
sol_tsv += '\t'.join([
sol_id_1, 'replicon_id', 'hit_sctj_flg', 'sctJ_FLG', '1', 'foo/B',
'sys_id_B', '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_1, 'replicon_id', 'hit_tadZ', 'tadZ', '1', 'foo/B',
'sys_id_B', '1', '0.750', '2.000', '1', 'tadZ', 'accessory', '803',
'1.0', '1.000', '1.000', '1.000', '10', '20', ''
])
sol_tsv += "\n"
sol_tsv += '\t'.join([
sol_id_1, 'replicon_id', 'hit_flgB', 'flgB', '1', 'foo/B',
'sys_id_B', '1', '0.750', '2.000', '1', 'flgB', 'accessory', '803',
'1.0', '1.000', '1.000', '1.000', '10', '20', ''
])
sol_tsv += "\n"
sol_tsv += "\n"
sol_tsv += '\t'.join([
sol_id_2, 'replicon_id', 'hit_sctj', 'sctJ', '1', 'foo/A',
'sys_id_A', '2', '1.000', '1.500', '2', 'sctJ', 'mandatory', '803',
'1.0', '1.000', '1.000', '1.000', '10', '20', ''
])
sol_tsv += "\n"
sol_tsv += '\t'.join([
sol_id_2, 'replicon_id', 'hit_sctn', 'sctN', '1', 'foo/A',
'sys_id_A', '2', '1.000', '1.500', '2', 'sctN', 'mandatory', '803',
'1.0', '1.000', '1.000', '1.000', '10', '20', ''
])
sol_tsv += "\n"
sol_tsv += '\t'.join([
sol_id_2, 'replicon_id', 'hit_gspd', 'gspD', '1', 'foo/A',
'sys_id_A', '2', '1.000', '1.500', '2', 'gspD', 'accessory', '803',
'1.0', '1.000', '1.000', '1.000', '10', '20', ''
])
sol_tsv += "\n"
sol_tsv += '\t'.join([
sol_id_2, 'replicon_id', 'hit_sctj', 'sctJ', '1', 'foo/A',
'sys_id_A', '2', '1.000', '1.500', '2', 'sctJ', 'mandatory', '803',
'1.0', '1.000', '1.000', '1.000', '10', '20', ''
])
sol_tsv += "\n"
sol_tsv += '\t'.join([
sol_id_2, 'replicon_id', 'hit_sctn', 'sctN', '1', 'foo/A',
'sys_id_A', '2', '1.000', '1.500', '2', 'sctN', 'mandatory', '803',
'1.0', '1.000', '1.000', '1.000', '10', '20', ''
])
sol_tsv += "\n"
sol_tsv += "\n"
sol_tsv += '\t'.join([
sol_id_2, 'replicon_id', 'hit_sctj_flg', 'sctJ_FLG', '1', 'foo/C',
'sys_id_C', '1', '0.800', '3.000', '1', 'sctJ_FLG', 'mandatory',
'803', '1.0', '1.000', '1.000', '1.000', '10', '20', 'sys_id_B'
])
sol_tsv += "\n"
sol_tsv += '\t'.join([
sol_id_2, 'replicon_id', 'hit_tadZ', 'tadZ', '1', 'foo/C',
'sys_id_C', '1', '0.800', '3.000', '1', 'tadZ', 'accessory', '803',
'1.0', '1.000', '1.000', '1.000', '10', '20', 'sys_id_B'
])
sol_tsv += "\n"
sol_tsv += '\t'.join([
sol_id_2, 'replicon_id', 'hit_flgB', 'flgB', '1', 'foo/C',
'sys_id_C', '1', '0.800', '3.000', '1', 'flgB', 'mandatory', '803',
'1.0', '1.000', '1.000', '1.000', '10', '20', 'sys_id_B'
])
sol_tsv += "\n"
sol_tsv += '\t'.join([
sol_id_2, 'replicon_id', 'hit_gspd', 'gspD', '1', 'foo/C',
'sys_id_C', '1', '0.800', '3.000', '1', 'gspD', 'accessory', '803',
'1.0', '1.000', '1.000', '1.000', '10', '20', 'sys_id_A'
])
sol_tsv += "\n"
sol_tsv += "\n"
f_out = StringIO()
hit_multi_sys_tracker = HitSystemTracker([sys_A, sys_B])
solutions_to_tsv([sol_1, sol_2], hit_multi_sys_tracker, f_out)
self.assertMultiLineEqual(sol_tsv, f_out.getvalue())
def test_systems_to_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"
c_gene_gspd = CoreGene(models_location, gene_name, profile_factory)
gene_gspd = ModelGene(c_gene_gspd, model)
model.add_mandatory_gene(gene_gspd)
gene_name = "sctJ"
c_gene_sctj = CoreGene(models_location, gene_name, 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)
system_1 = System(model, [
Cluster([v_hit_1, v_hit_2], model, HitWeight(**cfg.hit_weights()))
], cfg.redundancy_penalty())
system_tsv = f"""# macsyfinder {macsypy.__version__}
# {' '.join(sys.argv)}
# Systems found:
"""
system_tsv += "\t".join([
"replicon", "hit_id", "gene_name", "hit_pos", "model_fqn",
"sys_id", "sys_loci", "sys_wholeness", "sys_score", "sys_occ",
"hit_gene_ref", "hit_status", "hit_seq_len", "hit_i_eval",
"hit_score", "hit_profile_cov", "hit_seq_cov", "hit_begin_match",
"hit_end_match", "used_in"
])
system_tsv += "\n"
system_tsv += "\t".join([
"replicon_id", "hit_1", "gspD", "1", "foo/T2SS", system_1.id, "1",
"1.000", "1.500", "1", "gspD", "mandatory", "803", "1.0", "1.000",
"1.000", "1.000", "10", "20", ""
])
system_tsv += "\n"
system_tsv += "\t".join([
"replicon_id", "hit_2", "sctJ", "1", "foo/T2SS", system_1.id, "1",
"1.000", "1.500", "1", "sctJ", "accessory", "803", "1.0", "1.000",
"1.000", "1.000", "10", "20", ""
])
system_tsv += "\n\n"
f_out = StringIO()
track_multi_systems_hit = HitSystemTracker([system_1])
systems_to_tsv([system_1], track_multi_systems_hit, f_out)
self.assertMultiLineEqual(system_tsv, f_out.getvalue())
# test No system found
system_str = f"""# macsyfinder {macsypy.__version__}
# {' '.join(sys.argv)}
# No Systems found
"""
f_out = StringIO()
track_multi_systems_hit = HitSystemTracker([])
systems_to_tsv([], track_multi_systems_hit, f_out)
self.assertMultiLineEqual(system_str, f_out.getvalue())
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
def _build_systems(cfg, profile_factory):
model_name = 'foo'
model_location = ModelLocation(
path=os.path.join(cfg.models_dir(), model_name))
model_A = Model("foo/A", 10)
model_B = Model("foo/B", 10)
model_C = Model("foo/C", 10)
model_D = Model("foo/D", 10)
model_E = Model("foo/E", 10)
model_F = Model("foo/F", 10)
model_G = Model("foo/G", 10)
model_H = Model("foo/H", 10)
c_gene_sctn_flg = CoreGene(model_location, "sctN_FLG", profile_factory)
gene_sctn_flg = ModelGene(c_gene_sctn_flg, model_B)
c_gene_sctj_flg = CoreGene(model_location, "sctJ_FLG", profile_factory)
gene_sctj_flg = ModelGene(c_gene_sctj_flg, model_B)
c_gene_flgB = CoreGene(model_location, "flgB", profile_factory)
gene_flgB = ModelGene(c_gene_flgB, model_B)
c_gene_tadZ = CoreGene(model_location, "tadZ", profile_factory)
gene_tadZ = ModelGene(c_gene_tadZ, model_B)
c_gene_sctn = CoreGene(model_location, "sctN", 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", 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", 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", profile_factory)
gene_abc = ModelGene(c_gene_abc, model_A)
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_forbidden_gene(gene_abc)
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_C.add_mandatory_gene(gene_sctn_flg)
model_C.add_mandatory_gene(gene_sctj_flg)
model_C.add_mandatory_gene(gene_flgB)
model_C.add_accessory_gene(gene_tadZ)
model_C.add_accessory_gene(gene_gspd)
model_D.add_mandatory_gene(gene_abc)
model_D.add_accessory_gene(gene_sctn)
model_E.add_accessory_gene(gene_gspd)
model_F.add_mandatory_gene(gene_abc)
# idem as C
model_G.add_mandatory_gene(gene_sctn_flg)
model_G.add_mandatory_gene(gene_sctj_flg)
model_G.add_mandatory_gene(gene_flgB)
model_G.add_accessory_gene(gene_tadZ)
model_G.add_accessory_gene(gene_gspd)
# idem as D
model_H.add_mandatory_gene(gene_abc)
model_H.add_accessory_gene(gene_sctn)
h_sctj = Hit(c_gene_sctj, "hit_sctj", 803, "replicon_id", 1, 1.0, 1.0, 1.0,
1.0, 10, 20)
h_sctn = Hit(c_gene_sctn, "hit_sctn", 803, "replicon_id", 2, 1.0, 1.0, 1.0,
1.0, 10, 20)
h_gspd = Hit(c_gene_gspd, "hit_gspd", 803, "replicon_id", 3, 1.0, 1.0, 1.0,
1.0, 10, 20)
h_sctj_flg = Hit(c_gene_sctj_flg, "hit_sctj_flg", 803, "replicon_id", 4,
1.0, 1.0, 1.0, 1.0, 10, 20)
h_flgB = Hit(c_gene_flgB, "hit_flgB", 803, "replicon_id", 5, 1.0, 1.0, 1.0,
1.0, 10, 20)
h_tadZ = Hit(c_gene_tadZ, "hit_tadZ", 803, "replicon_id", 6, 1.0, 1.0, 1.0,
1.0, 10, 20)
h_abc = Hit(c_gene_abc, "hit_abc", 803, "replicon_id", 7, 1.0, 1.0, 1.0,
1.0, 10, 20)
model_A._min_mandatory_genes_required = 2
model_A._min_genes_required = 2
hit_weights = HitWeight(**cfg.hit_weights())
c1 = Cluster([
ValidHit(h_sctj, gene_sctj, GeneStatus.MANDATORY),
ValidHit(h_sctn, gene_sctn, GeneStatus.MANDATORY),
ValidHit(h_gspd, gene_gspd, GeneStatus.ACCESSORY)
], model_A, hit_weights)
c2 = Cluster([
ValidHit(h_sctj, gene_sctj, GeneStatus.MANDATORY),
ValidHit(h_sctn, gene_sctn, GeneStatus.MANDATORY)
], model_A, hit_weights)
model_B._min_mandatory_genes_required = 1
model_B._min_genes_required = 2
c3 = Cluster([
ValidHit(h_sctj_flg, gene_sctj_flg, GeneStatus.MANDATORY),
ValidHit(h_tadZ, gene_tadZ, GeneStatus.ACCESSORY),
ValidHit(h_flgB, gene_flgB, GeneStatus.ACCESSORY)
], model_B, hit_weights)
model_C._min_mandatory_genes_required = 1
model_C._min_genes_required = 2
c4 = Cluster([
ValidHit(h_sctj_flg, gene_sctj_flg, GeneStatus.MANDATORY),
ValidHit(h_tadZ, gene_tadZ, GeneStatus.ACCESSORY),
ValidHit(h_flgB, gene_flgB, GeneStatus.MANDATORY),
ValidHit(h_gspd, gene_gspd, GeneStatus.ACCESSORY)
], model_C, hit_weights)
model_D._min_mandatory_genes_required = 1
model_D._min_genes_required = 1
c5 = Cluster([
ValidHit(h_abc, gene_abc, GeneStatus.MANDATORY),
ValidHit(h_sctn, gene_sctn, GeneStatus.ACCESSORY)
], model_D, hit_weights)
model_E._min_mandatory_genes_required = 0
model_E._min_genes_required = 1
c6 = Cluster([ValidHit(h_gspd, gene_gspd, GeneStatus.ACCESSORY)], model_E,
hit_weights)
model_F._min_mandatory_genes_required = 1
model_F._min_genes_required = 1
c7 = Cluster([ValidHit(h_abc, gene_abc, GeneStatus.MANDATORY)], model_F,
hit_weights)
systems = {}
systems['A'] = System(model_A, [c1, c2],
cfg.redundancy_penalty()) # 5 hits
# we need to tweek the replicon_id to have stable ressults
# whatever the number of tests ran
# or the tests order
systems['A'].id = "replicon_id_A"
systems['B'] = System(model_B, [c3], cfg.redundancy_penalty()) # 3 hits
systems['B'].id = "replicon_id_B"
systems['C'] = System(model_C, [c4], cfg.redundancy_penalty()) # 4 hits
systems['C'].id = "replicon_id_C"
systems['D'] = System(model_D, [c5], cfg.redundancy_penalty()) # 2 hits
systems['D'].id = "replicon_id_D"
systems['E'] = System(model_E, [c6], cfg.redundancy_penalty()) # 1 hit
systems['E'].id = "replicon_id_E"
systems['F'] = System(model_F, [c7], cfg.redundancy_penalty()) # 1 hit
systems['F'].id = "replicon_id_F"
systems['G'] = System(model_G, [c4], cfg.redundancy_penalty()) # 4 hits
systems['G'].id = "replicon_id_G"
systems['H'] = System(model_H, [c5], cfg.redundancy_penalty()) # 2 hits
systems['H'].id = "replicon_id_H"
return systems