def test_touch(self):
Cache.clean()
self.assertDictEqual(Cache.get_objects(), {})
Cache.touch(self.__d, 'd')
self.assertDictEqual(Cache.get('d'), self.__d)
Cache.touch(None, 'd')
self.assertDictEqual(Cache.get('d'), self.__d)
Cache.touch({}, 'd')
self.assertDictEqual(Cache.get('d'), self.__d)
def __build_all_pathways(
pathways: Dict,
transfos: Dict,
sink_molecules: List,
rr_reactions: Dict,
compounds_cache: Dict,
max_subpaths_filter: int,
lower_flux_bound: float,
upper_flux_bound: float,
logger: Logger = getLogger(__name__)
) -> Dict:
"""Builds pathways based on all combinations over
reaction rules and template reactions (see
`build_pathway_combinatorics` documentation).
Parameters
----------
pathways: Dict
Metabolic pathways as list of chemical
reactions where each reaction is defined by:
- transformation ID,
- reaction rule ID, and
- template reaction ID
transfos: Dict
Full chemical transformations
sink_molecules: List
Sink chemical species IDs
rr_reactions: Dict
Reaction rules cache
compounds_cache: Dict
Compounds cache
max_subpaths_filter: int
Number of pathways (best) kept per master pathway
lower_flux_bound: float
Lower flux bound for all new reactions created
upper_flux_bound: float
Upper flux bound for all new reactions created
logger: Logger, optional
Returns
-------
Set of ranked rpPathway objects
"""
res_pathways = {}
nb_pathways = 0
nb_unique_pathways = 0
## PATHWAYS
for path_idx, transfos_lst in pathways.items():
# Combine over multiple template reactions
sub_pathways = list(itertools_product(*transfos_lst))
## SUB-PATHWAYS
# # Keep only topX best sub_pathways
# # within a same master pathway
res_pathways[path_idx] = []
for sub_path_idx in range(len(sub_pathways)):
pathway = rpPathway(
id=str(path_idx).zfill(3)+'_'+str(sub_path_idx+1).zfill(4),
logger=logger
)
logger.debug(pathway.get_id())
## ITERATE OVER REACTIONS
nb_reactions = len(sub_pathways[sub_path_idx])
for rxn_idx in range(nb_reactions):
rxn = sub_pathways[sub_path_idx][rxn_idx]
transfo_id = rxn['rp2_transfo_id']
transfo = transfos[transfo_id]
rule_ids = rxn['rule_ids']
tmpl_rxn_id = rxn['tmpl_rxn_ids']
## COMPOUNDS
# Template reaction compounds
added_cmpds = transfo['complement'][rule_ids][tmpl_rxn_id]['added_cmpds']
# Add missing compounds to the cache
for side in added_cmpds.keys():
for spe_id in added_cmpds[side].keys():
logger.debug(f'Add missing compound {spe_id}')
if spe_id not in Cache.get_objects():
try:
rpCompound(
id=spe_id,
smiles=compounds_cache[spe_id]['smiles'],
inchi=compounds_cache[spe_id]['inchi'],
inchikey=compounds_cache[spe_id]['inchikey'],
formula=compounds_cache[spe_id]['formula'],
name=compounds_cache[spe_id]['name']
)
except KeyError:
rpCompound(
id=spe_id
)
## REACTION
# Compounds from original transformation
core_species = {
'right': deepcopy(transfo['right']),
'left': deepcopy(transfo['left'])
}
compounds = __add_compounds(core_species, added_cmpds)
# revert reaction index (forward)
rxn_idx_forward = nb_reactions - rxn_idx
rxn = rpReaction(
id='rxn_'+str(rxn_idx_forward),
ec_numbers=transfo['ec'],
reactants=dict(compounds['left']),
products=dict(compounds['right']),
lower_flux_bound=lower_flux_bound,
upper_flux_bound=upper_flux_bound
)
# write infos
for info_id, info in sub_pathways[sub_path_idx][rxn_idx].items():
getattr(rxn, 'set_'+info_id)(info)
rxn.set_rule_score(rr_reactions[rule_ids][tmpl_rxn_id]['rule_score'])
rxn.set_idx_in_path(rxn_idx_forward)
# Add at the beginning of the pathway
# to have the pathway in forward direction
# Search for the target in the current reaction
target_id = [spe_id for spe_id in rxn.get_products_ids() if 'TARGET' in spe_id]
if target_id != []:
target_id = target_id[0]
else:
target_id = None
logger.debug(f'rxn: {rxn._to_dict()}')
pathway.add_reaction(
rxn=rxn,
target_id=target_id
)
## TRUNK SPECIES
pathway.add_species_group(
'trunk',
[
spe_id
for value
in core_species.values()
for spe_id in value.keys()
]
)
## COMPLETED SPECIES
pathway.add_species_group(
'completed',
[
spe_id
for value
in added_cmpds.values()
for spe_id in value.keys()
]
)
## SINK
pathway.set_sink_species(
list(
set(pathway.get_species_ids()) & set(sink_molecules)
)
)
nb_pathways += 1
## RANK AMONG ALL SUB-PATHWAYS OF THE CURRENT MASTER PATHWAY
res_pathways[path_idx] = __keep_unique_pathways(
res_pathways[path_idx],
pathway,
logger
)
nb_unique_pathways += len(res_pathways[path_idx])
# Flatten lists of pathways
pathways = sum(
[
pathways
for pathways in res_pathways.values()
], [])
# Globally sort pathways
pathways = sorted(pathways)[-max_subpaths_filter:]
logger.info(f'Pathways statistics')
logger.info(f'-------------------')
logger.info(f' pathways: {nb_pathways}')
logger.info(f' unique pathways: {nb_unique_pathways}')
logger.info(f' selected pathways: {len(pathways)} (topX filter = {max_subpaths_filter})')
# Return topX pathway objects
return [
pathway.object
for pathway in pathways
]
# Transform the list of Item into a list of Pathway
results = {}
nb_sel_pathways = 0
for res_pathway_idx, res_pathway in res_pathways.items():
results[res_pathway_idx] = [pathway.object for pathway in res_pathway]
nb_sel_pathways += len(results[res_pathway_idx])
logger.info(f'Pathways selected: {nb_sel_pathways}/{nb_pathways}')
return results
def test_get_objects(self):
Cache.clean()
Cache.add(self.__d, 'd')
self.assertDictEqual(Cache.get_objects(), {'d': self.__d})