def test_add_reaction(self):
rxn = rpReaction(id='rxn')
self.pathway.add_reaction(rxn)
self.assertListEqual(
self.pathway.get_list_of_reactions(),
self.reactions + [rxn]
)
def setUp(self):
self.logger = create_logger(__name__, 'ERROR')
self.rxn_1 = rpReaction(
id='rxn_1',
reactants={
'MNXM188': 1,
'MNXM4': 1,
'MNXM6': 1,
'MNXM1': 3
},
products={
'CMPD_0000000004': 1,
'CMPD_0000000003': 1,
'MNXM13': 1,
'MNXM15': 3,
'MNXM5': 1
},
)
self.rxn_2 = rpReaction(
id='rxn_2',
reactants={
'MNXM4': 1,
'CMPD_0000000003': 2
},
products={
'MNXM1': 1,
'TARGET_0000000001': 1
},
)
self.rxn_3 = rpReaction(
id='rxn_3',
reactants={
'CMPD_0000000004': 3,
'MNXM4': 1,
'MNXM6': 1
},
products={
'MNXM13': 1,
'MNXM5': 1
},
)
self.reactions = [self.rxn_1, self.rxn_2, self.rxn_3]
self.sto_mat_1 = [[-3.0, 1.0, 0.0], [-1.0, -1.0, -1.0],
[1.0, 0.0, 1.0], [3.0, 0.0, 0.0], [1.0, 0.0, -3.0],
[1.0, 0.0, 1.0], [0.0, 1.0, 0.0], [1.0, -2.0, 0.0],
[-1.0, 0.0, 0.0], [-1.0, 0.0, -1.0]]
def setUp(self):
self.reactants = {
"CMPD_0000000010": 1,
"MNXM1": 1
}
self.products = {
"CMPD_0000000003": 1,
"MNXM13": 1
}
self.ec_numbers = [
"4.1.1.63"
]
self.id = "rxn"
self.miriam = {'ec-code': ['4.1.1.63']}
self.rxn = rpReaction(
id=self.id,
miriam=self.miriam,
reactants=self.reactants,
products=self.products
)
self.rp2_transfo_id = 'TRS_0_0_0'
self.rule_ids = ['RR-02-a0cc0be463ff412f-16-F']
self.tmpl_rxn_ids = ['MNXR96458']
self.rule_score = 0.5982208769718989
self.selenzy = {
'UniProtID_1': 65.65,
'UniProtID_2': 77.77,
}
self.inherited_dict = {
'id': self.id,
'reactants': self.reactants,
'products': self.products,
'ec_numbers': self.ec_numbers,
}
self.specific_dict = {
'idx_in_path': -1,
'rp2_transfo_id': self.rp2_transfo_id,
'rule_ids': self.rule_ids,
'tmpl_rxn_ids': self.tmpl_rxn_ids,
'rule_score': self.rule_score,
**{
'selenzy_'+id: self.selenzy[id]
for id in self.selenzy
}
}
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 setUp(self):
self.target = rpCompound(
id='TARGET_0000000001',
smiles='[H]OC(=O)C([H])=C([H])C([H])=C([H])C(=O)O[H]'
)
species = {
# "TARGET_0000000001": rpCompound(
# id="TARGET_0000000001",
# smiles="[H]OC(=O)C([H])=C([H])C([H])=C([H])C(=O)O[H]",
# inchi="InChI=1S/C6H6O4/c7-5(8)3-1-2-4-6(9)10/h1-4H,(H,7,8)(H,9,10)",
# inchikey="TXXHDPDFNKHHGW-UHFFFAOYSA-N"
# ),
"TARGET_0000000001": self.target,
"CMPD_0000000010": rpCompound(
id="CMPD_0000000010",
smiles="[H]OC(=O)c1c([H])c([H])c(O[H])c(O[H])c1[H]",
inchi="InChI=1S/C7H6O4/c8-5-2-1-4(7(10)11)3-6(5)9/h1-3,8-9H,(H,10,11)",
inchikey="YQUVCSBJEUQKSH-UHFFFAOYSA-N"
),
"MNXM23": rpCompound(
id="MNXM23",
formula="C3H3O3",
smiles="CC(=O)C(=O)O]",
inchi="InChI=1S/C3H4O3/c1-2(4)3(5)6/h1H3,(H,5,6)",
inchikey="LCTONWCANYUPML-UHFFFAOYSA-N",
name="pyruvate"
),
"CMPD_0000000025": rpCompound(
id="CMPD_0000000025",
smiles="[H]OC(=O)c1c([H])c([H])c([H])c(O[H])c1[H]",
inchi="InChI=1S/C7H6O3/c8-6-3-1-2-5(4-6)7(9)10/h1-4,8H,(H,9,10)",
inchikey="IJFXRHURBJZNAO-UHFFFAOYSA-N"
),
"CMPD_0000000003": rpCompound(
id="CMPD_0000000003",
smiles="[H]Oc1c([H])c([H])c([H])c([H])c1O[H]",
inchi="InChI=1S/C6H6O2/c7-5-3-1-2-4-6(5)8/h1-4,7-8H",
inchikey="YCIMNLLNPGFGHC-UHFFFAOYSA-N"
),
"MNXM337": rpCompound(
id="MNXM337",
smiles="[H]OC(=O)C(OC1([H])C([H])=C(C(=O)O[H])C([H])=C([H])C1([H])O[H])=C([H])[H]",
inchi="InChI=1S/C10H10O6/c1-5(9(12)13)16-8-4-6(10(14)15)2-3-7(8)11/h2-4,7-8,11H,1H2,(H,12,13)(H,14,15)",
inchikey="WTFXTQVDAKGDEY-UHFFFAOYSA-N"
),
"MNXM2": rpCompound(
id="MNXM2",
smiles="[H]O[H]",
inchi="InChI=1S/H2O/h1H2",
inchikey="XLYOFNOQVPJJNP-UHFFFAOYSA-N"
),
"MNXM13": rpCompound(
id="MNXM13",
smiles="O=C=O",
inchi="InChI=1S/CO2/c2-1-3",
inchikey="CURLTUGMZLYLDI-UHFFFAOYSA-N",
formula="CO2",
name="CO2"
),
"MNXM5": rpCompound(
id="MNXM5",
smiles="N=C(O)c1ccc[n+](C2OC(COP(=O)(O)OP(=O)(O)OCC3OC(n4cnc5c(N)ncnc54)C(OP(=O)(O)O)C3O)C(O)C2O)c1",
inchi="InChI=1S/C21H28N7O17P3/c22-17-12-19(25-7-24-17)28(8-26-12)21-16(44-46(33,34)35)14(30)11(43-21)6-41-48(38,39)45-47(36,37)40-5-10-13(29)15(31)20(42-10)27-3-1-2-9(4-27)18(23)32/h1-4,7-8,10-11,13-16,20-21,29-31H,5-6H2,(H7-,22,23,24,25,32,33,34,35,36,37,38,39)/p+1",
inchikey="XJLXINKUBYWONI-UHFFFAOYSA-O",
formula="C21H25N7O17P3",
name="NADP(+)"
),
"MNXM4": rpCompound(
id="MNXM4",
smiles="O=O",
inchi="InChI=1S/O2/c1-2",
inchikey="MYMOFIZGZYHOMD-UHFFFAOYSA-N"
),
"MNXM1": rpCompound(
id="MNXM1",
smiles="[H+]",
inchi="InChI=1S/p+1",
inchikey="GPRLSGONYQIRFK-UHFFFAOYSA-N"
),
"MNXM6": rpCompound(
id="MNXM6",
smiles="[H]N=C(O[H])C1=C([H])N(C2([H])OC([H])(C([H])([H])OP(=O)(O[H])OP(=O)(O[H])OC([H])([H])C3([H])OC([H])(n4c([H])nc5c(N([H])[H])nc([H])nc54)C([H])(OP(=O)(O[H])O[H])C3([H])O[H])C([H])(O[H])C2([H])O[H])C([H])=C([H])C1([H])[H]",
inchi="InChI=1S/C21H30N7O17P3/c22-17-12-19(25-7-24-17)28(8-26-12)21-16(44-46(33,34)35)14(30)11(43-21)6-41-48(38,39)45-47(36,37)40-5-10-13(29)15(31)20(42-10)27-3-1-2-9(4-27)18(23)32/h1,3-4,7-8,10-11,13-16,20-21,29-31H,2,5-6H2,(H2,23,32)(H,36,37)(H,38,39)(H2,22,24,25)(H2,33,34,35)",
inchikey="ACFIXJIJDZMPPO-UHFFFAOYSA-N"
)
}
self.reactants = {
"CMPD_0000000003": 1,
"MNXM4": 1
}
self.products = {
self.target.get_id(): 1,
"MNXM1": 2
}
self.rxn = rpReaction(
id="rxn_4",
ec_numbers=[
"1.13.11.1"
],
reactants=self.reactants,
products=self.products
)
self.reactions = [
self.rxn,
rpReaction(
id="rxn_3",
ec_numbers=[
"4.1.1.63"
],
reactants={
"CMPD_0000000010": 1,
"MNXM1": 1
},
products={
"CMPD_0000000003": 1,
"MNXM13": 1
}
),
rpReaction(
id="rxn_2",
ec_numbers=[
"1.14.13.23"
],
reactants={
"CMPD_0000000025": 1,
"MNXM4": 1,
"MNXM6": 1,
"MNXM1": 1
},
products={
"CMPD_0000000010": 1,
"MNXM2": 1,
"MNXM5": 1
}
),
rpReaction(
id="rxn_1",
ec_numbers=[
"4.1.3.45"
],
reactants={
"MNXM337": 1
},
products={
"CMPD_0000000025": 1,
"MNXM23": 1
}
)
]
self.fba = 0.57290585662576
self.thermo = {
"dG0_prime": {
"value": -884.6296371353768,
"error": 9.819227446307337,
"units": "kilojoule / mole"
},
"dGm_prime": {
"value": -884.6296371353768,
"error": 9.819227446307337,
"units": "kilojoule / mole"
},
"dG_prime": {
"value": -884.6296371353768,
"error": 9.819227446307337,
"units": "kilojoule / mole"
}
}
self.rp2_transfo_id = 'TRS_0_0_0'
self.rule_ids = ['RR-02-a0cc0be463ff412f-16-F']
self.tmpl_rxn_ids = ['MNXR96458']
self.idx_in_path = 1
self.rule_score = 0.5982208769718989
self.id = 'pathway'
cache = rrCache(
attrs=[
'comp_xref',
'deprecatedCompID_compid',
]
)
self.compartments = [
{
'id': 'MNXC3',
'name': 'cytosol',
'annot': cache.get('comp_xref')[
cache.get('deprecatedCompID_compid')[
'MNXC3'
]
]
}
]
self.parameters = {
"upper_flux_bound": {
"value": 999999.0,
"units": "mmol_per_gDW_per_hr"
},
"lower_flux_bound": {
"value": 0.0,
"units": "mmol_per_gDW_per_hr"
}
}
self.unit_def = {
"mmol_per_gDW_per_hr": [
{
"kind": 23,
"exponent": 1,
"scale": -3,
"multiplier": 1.0
},
{
"kind": 8,
"exponent": 1,
"scale": 0,
"multiplier": 1.0
},
{
"kind": 28,
"exponent": 1,
"scale": 0,
"multiplier": 3600.0
}
],
"kj_per_mol": [
{
"kind": 13,
"exponent": 1,
"scale": 3,
"multiplier": 1.0
},
{
"kind": 13,
"exponent": -1,
"scale": 1,
"multiplier": 1.0
}
]
}
self.pathway = rpPathway(
id=self.id,
)
self.pathway.set_parameters(self.parameters)
self.pathway.set_unit_defs(self.unit_def)
self.rxn.set_rp2_transfo_id(self.rp2_transfo_id)
self.rxn.set_rule_ids(self.rule_ids)
self.rxn.set_tmpl_rxn_ids(self.tmpl_rxn_ids)
self.rxn.set_idx_in_path(self.idx_in_path)
self.rxn.set_rule_score(self.rule_score)
self.pathway.add_reaction(rxn=self.rxn, target_id=self.target.get_id())
for rxn in self.reactions[1:]:
self.pathway.add_reaction(rxn)
self.sink = ['MNXM23', 'MNXM6', 'MNXM13']
self.pathway.set_sink(self.sink)
for key, value in self.thermo.items():
self.pathway.add_thermo_info(key, value)
self.pathway.set_fba_fraction(self.fba)