def create_folded_model(S, model):
r_id2new_r_id = {}
initial_r_ids = {r_id for r_id in S.r_id2i.keys() if r_id not in S.gr_id2r_id2c}
r_ids_to_remove = [r.getId() for r in model.getListOfReactions() if r.getId() not in S.r_ids]
def map2new_id(r_id, new_id):
if r_id not in S.gr_id2r_id2c:
r_id2new_r_id[r_id] = new_id
else:
for sub_r_id in S.gr_id2r_id2c[r_id].keys():
map2new_id(sub_r_id, new_id)
for mr_id in S.r_ids - initial_r_ids:
cl_id2c = S.gr_id2r_id2c[mr_id]
name = 'lumped reaction %s' % mr_id
id_ = mr_id
r_id2st, p_id2st = S.st_matrix.get_inputs_outputs(mr_id)
new_r_id = create_reaction(model, r_id2st, p_id2st, reversible=True, id_=id_, name=name).getId()
for r_id in cl_id2c:
map2new_id(r_id, new_r_id)
for r_id in r_ids_to_remove:
model.removeReaction(r_id)
for r in model.getListOfReactions():
for i in range(0, r.getNumModifiers()):
r.removeModifier(0)
remove_unused_species(model)
return r_id2new_r_id
def simple_merge_models(S, model_id2c_id2group, model_id2dfs, out_sbml):
doc = libsbml.SBMLDocument(2, 4)
model = doc.createModel()
model.setId('merged_model')
model_id2id2id = defaultdict(dict)
common_ids = set()
c_group2id = {}
new_m_id2i, new_r_id2i, new_efm_id2i, new_boundary_m_ids = {}, {}, {}, []
for model_id, [_, _, df] in model_id2dfs.items():
for index, row in df.iterrows():
c_id, name = row['Id'], row['Name']
if model_id in model_id2c_id2group and c_id in model_id2c_id2group[model_id]:
group = model_id2c_id2group[model_id][c_id]
if group in c_group2id:
new_id = c_group2id[group]
else:
new_id = create_compartment(model, name=name, id_='merged_%s_%s' % (model_id, c_id)).getId()
c_group2id[group] = new_id
common_ids.add(new_id)
else:
new_id = create_compartment(model, name=name, id_='%s_%s' % (model_id, c_id)).getId()
model_id2id2id[model_id][c_id] = new_id
id2id = {}
m_id_group_ids = set(S.m_id2gr_id.values())
for (model_id, m_id), i in ((it, i) for (it, i) in S.m_id2i.items() if it not in m_id_group_ids):
c_id = model_id2dfs[model_id][0].at[m_id, 'Compartment']
c_id = model_id2id2id[model_id][c_id]
name = model_id2dfs[model_id][0].at[m_id, 'Name']
is_boundary = (model_id, m_id) in S.boundary_m_ids
new_id = create_species(model, compartment_id=c_id, name=name, bound=is_boundary,
id_='%s_%s' % (model_id, m_id)).getId()
model_id2id2id[model_id][m_id] = new_id
id2id[(model_id, m_id)] = new_id
new_m_id2i[new_id] = i
if is_boundary:
new_boundary_m_ids.append(new_id)
for it in m_id_group_ids:
model_id, m_ids = next(iter(it))
m_id = next(iter(m_ids))
is_boundary = it in S.boundary_m_ids
new_id = \
create_species(model,
compartment_id=model_id2id2id[model_id][model_id2dfs[model_id][0].at[m_id, 'Compartment']],
name=model_id2dfs[model_id][0].at[m_id, 'Name'], bound=is_boundary,
id_='merged_%s_%s' % (model_id, m_id)).getId()
for model_id, m_ids in it:
model_id2id2id[model_id].update({m_id: new_id for m_id in m_ids})
id2id[it] = new_id
new_m_id2i[new_id] = S.m_id2i[it]
if is_boundary:
new_boundary_m_ids.append(new_id)
common_ids.add(new_id)
for ((model_id, r_id), i) in ((it, i) for (it, i) in S.r_id2i.items() if it not in S.gr_id2r_id2c.keys()):
r_id2st, p_id2st = S.st_matrix.get_inputs_outputs((model_id, r_id))
new_id = create_reaction(model, {id2id[m_id]: st for (m_id, st) in r_id2st.items()},
{id2id[m_id]: st for (m_id, st) in p_id2st.items()},
model_id2dfs[model_id][1].at[r_id, 'Name'], reversible=True,
id_='%s_%s' % (model_id, r_id)).getId()
model_id2id2id[model_id][r_id] = new_id
new_r_id2i[new_id] = i
for gr, it2c in S.gr_id2r_id2c.items():
model_id, r_id = next(iter(it2c.keys()))
r_id2st, p_id2st = S.st_matrix.get_inputs_outputs(gr)
new_id = \
create_reaction(model, {id2id[m_id]: st for (m_id, st) in r_id2st.items()},
{id2id[m_id]: st for (m_id, st) in p_id2st.items()},
model_id2dfs[model_id][1].at[r_id, 'Name'], reversible=True,
id_='merged_%s_%s' % (model_id, r_id)).getId()
for model_id, r_id in it2c.keys():
model_id2id2id[model_id][r_id] = new_id
new_r_id2i[new_id] = S.r_id2i[gr]
common_ids.add(new_id)
for ((model_id, efm_id), i) in ((it, i) for (it, i) in S.efm_id2i.items() if it not in S.gr_id2efm_ids.keys()):
new_id = '%s_%s' % (model_id, efm_id)
new_efm_id2i[new_id] = i
model_id2id2id[model_id][efm_id] = new_id
for gr, efm_ids in S.gr_id2efm_ids.items():
model_id, efm_id = next(efm_ids)
new_id = 'merged_%s_%s' % (model_id, efm_id)
new_efm_id2i[new_id] = S.r_id2i[gr]
for model_id, efm_id in efm_ids:
model_id2id2id[model_id][efm_id] = new_id
libsbml.writeSBMLToFile(doc, out_sbml)
return model_id2id2id, common_ids, System(m_id2i=new_m_id2i, r_id2i=new_r_id2i, efm_id2i=new_efm_id2i, N=S.N, V=S.V,
boundary_m_ids=new_boundary_m_ids)
def save_as_comp_generalized_sbml(input_model, out_sbml, groups_sbml, r_id2clu, clu2s_ids, ub_sps, onto):
logging.info("serializing generalization")
s_id_increment, r_id_increment = 0, 0
if groups_sbml:
doc = convert_to_lev3_v1(input_model)
groups_model = doc.getModel()
groups_plugin = groups_model.getPlugin("groups")
if groups_plugin:
logging.info(" saving ubiquitous species annotations")
s_group = groups_plugin.createGroup()
s_group.setId("g_ubiquitous_sps")
s_group.setKind(libsbml.GROUP_KIND_COLLECTION)
s_group.setSBOTerm(SBO_CHEMICAL_MACROMOLECULE)
s_group.setName("ubiquitous species")
for s_id in ub_sps:
member = s_group.createMember()
member.setIdRef(s_id)
add_annotation(s_group, libsbml.BQB_IS_DESCRIBED_BY, GROUP_TYPE_UBIQUITOUS)
if out_sbml:
# generalized model
generalized_doc = libsbml.SBMLDocument(input_model.getSBMLNamespaces())
generalized_model = generalized_doc.createModel()
copy_elements(input_model, generalized_model)
r_id2g_eq, s_id2gr_id = {}, {}
if not clu2s_ids:
logging.info(" nothing to serialize")
else:
clu2r_ids = invert_map(r_id2clu)
logging.info(" creating species groups")
for ((c_id, t), s_ids) in clu2s_ids.items():
comp = input_model.getCompartment(c_id)
if len(s_ids) > 1:
t = onto.get_term(t)
t_name, t_id = (t.get_name(), t.get_id()) if t \
else (' or '.join(input_model.getSpecies(s_id).getName() for s_id in s_ids), None)
if not t_id:
t = t_name
if out_sbml:
new_species = create_species(model=generalized_model, compartment_id=comp.getId(), type_id=None,
name="{0} ({1}) [{2}]".format(t_name, len(s_ids), comp.getName()))
add_annotation(new_species, libsbml.BQB_IS, t_id, CHEBI_PREFIX)
new_s_id = new_species.getId()
else:
s_id_increment += 1
new_s_id = generate_unique_id(input_model, "s_g_", s_id_increment)
for s_id in s_ids:
s_id2gr_id[s_id] = new_s_id, t
if groups_sbml and groups_plugin:
# save as a group
s_group = groups_plugin.createGroup()
s_group.setId(new_s_id)
s_group.setKind(libsbml.GROUP_KIND_CLASSIFICATION)
s_group.setSBOTerm(SBO_CHEMICAL_MACROMOLECULE)
g_name = "{0} [{1}]".format(t_name, comp.getName())
s_group.setName(g_name)
# logging.info("%s: %d" % (g_name, len(s_ids)))
if t_id:
add_annotation(s_group, libsbml.BQB_IS, t_id, CHEBI_PREFIX)
for s_id in s_ids:
member = s_group.createMember()
member.setIdRef(s_id)
add_annotation(s_group, libsbml.BQB_IS_DESCRIBED_BY, GROUP_TYPE_EQUIV)
generalize_species = lambda species_id: s_id2gr_id[species_id][0] if (species_id in s_id2gr_id) else species_id
s_id_to_generalize = set(s_id2gr_id.keys())
logging.info(" creating reaction groups")
for clu, r_ids in clu2r_ids.items():
representative = input_model.getReaction(list(r_ids)[0])
r_name = "generalized %s" % representative.getName()
if out_sbml:
reactants = dict(get_reactants(representative, stoichiometry=True))
products = dict(get_products(representative, stoichiometry=True))
if (len(r_ids) == 1) and \
not ((set(reactants.keys()) | set(products.keys())) & s_id_to_generalize):
generalized_model.addReaction(representative)
continue
r_id2st = {generalize_species(it): st for (it, st) in reactants.items()}
p_id2st = {generalize_species(it): st for (it, st) in products.items()}
reversible = next((False for r_id in r_ids if not input_model.getReaction(r_id).getReversible()), True)
new_r_id = create_reaction(generalized_model, r_id2st, p_id2st, name=r_name, reversible=reversible,
id_=representative.getId() if len(r_ids) == 1 else None).getId()
elif len(r_ids) > 1:
r_id_increment += 1
new_r_id = generate_unique_id(input_model, "r_g_", r_id_increment)
if len(r_ids) > 1:
for r_id in r_ids:
r_id2g_eq[r_id] = new_r_id, r_name
if groups_sbml and groups_plugin:
# save as a group
r_group = groups_plugin.createGroup()
r_group.setId(new_r_id)
r_group.setKind(libsbml.GROUP_KIND_COLLECTION)
r_group.setSBOTerm(SBO_BIOCHEMICAL_REACTION)
r_group.setName(r_name)
for r_id in r_ids:
member = r_group.createMember()
member.setIdRef(r_id)
add_annotation(r_group, libsbml.BQB_IS_DESCRIBED_BY, GROUP_TYPE_EQUIV)
if out_sbml:
remove_unused_elements(generalized_model)
save_as_sbml(generalized_model, out_sbml)
if groups_sbml and groups_model:
save_as_sbml(groups_model, groups_sbml)
logging.info("serialized to " + groups_sbml)
return r_id2g_eq, s_id2gr_id
def save_as_comp_generalized_sbml(input_model, out_sbml, groups_sbml, r_id2clu, clu2s_ids, ub_sps, onto):
logging.info("serializing generalization")
s_id_increment, r_id_increment = 0, 0
if groups_sbml:
doc = convert_to_lev3_v1(input_model)
groups_model = doc.getModel()
groups_plugin = groups_model.getPlugin("groups")
if groups_plugin:
logging.info(" saving ubiquitous species annotations")
s_group = groups_plugin.createGroup()
s_group.setId("g_ubiquitous_sps")
s_group.setKind(libsbml.GROUP_KIND_COLLECTION)
s_group.setSBOTerm(SBO_CHEMICAL_MACROMOLECULE)
s_group.setName("ubiquitous species")
for s_id in ub_sps:
member = s_group.createMember()
member.setIdRef(s_id)
add_annotation(s_group, libsbml.BQB_IS_DESCRIBED_BY, GROUP_TYPE_UBIQUITOUS)
if out_sbml:
# generalized model
generalized_doc = convert_to_lev3_v1(input_model)
generalized_model = generalized_doc.getModel()
for _ in range(0, generalized_model.getNumReactions()):
generalized_model.removeReaction(0)
r_id2g_eq, s_id2gr_id = {}, {}
if not clu2s_ids:
logging.info(" nothing to serialize")
else:
clu2r_ids = invert_map(r_id2clu)
logging.info(" creating species groups")
for ((c_id, t), s_ids) in clu2s_ids.items():
comp = input_model.getCompartment(c_id)
if len(s_ids) > 1:
t = onto.get_term(t)
t_name, t_id = (t.get_name(), t.get_id()) if t \
else (' or '.join(input_model.getSpecies(s_id).getName() for s_id in s_ids), None)
if not t_id:
t = t_name
if out_sbml:
new_species = create_species(model=generalized_model, compartment_id=comp.getId(), type_id=None,
name="{0} ({1}) [{2}]".format(t_name, len(s_ids), comp.getName()))
add_annotation(new_species, libsbml.BQB_IS, t_id, CHEBI_PREFIX)
new_s_id = new_species.getId()
else:
s_id_increment += 1
new_s_id = generate_unique_id(input_model, "s_g_", s_id_increment)
for s_id in s_ids:
s_id2gr_id[s_id] = new_s_id, t
if groups_sbml and groups_plugin:
# save as a group
s_group = groups_plugin.createGroup()
s_group.setId(new_s_id)
s_group.setKind(libsbml.GROUP_KIND_CLASSIFICATION)
s_group.setSBOTerm(SBO_CHEMICAL_MACROMOLECULE)
g_name = "{0} [{1}]".format(t_name, comp.getName())
s_group.setName(g_name)
# logging.info("%s: %d" % (g_name, len(s_ids)))
if t_id:
add_annotation(s_group, libsbml.BQB_IS, t_id, CHEBI_PREFIX)
for s_id in s_ids:
member = s_group.createMember()
member.setIdRef(s_id)
add_annotation(s_group, libsbml.BQB_IS_DESCRIBED_BY, GROUP_TYPE_EQUIV)
generalize_species = lambda species_id: s_id2gr_id[species_id][0] if (species_id in s_id2gr_id) else species_id
s_id_to_generalize = set(s_id2gr_id.keys())
logging.info(" creating reaction groups")
for clu, r_ids in clu2r_ids.items():
representative = input_model.getReaction(list(r_ids)[0])
r_name = "generalized %s" % representative.getName()
if out_sbml:
reactants = dict(get_reactants(representative, stoichiometry=True))
products = dict(get_products(representative, stoichiometry=True))
if (len(r_ids) == 1) and \
not ((set(reactants.keys()) | set(products.keys())) & s_id_to_generalize):
create_reaction(generalized_model, reactants, products, name=representative.getName(),
reversible=representative.getReversible(), id_=representative.getId())
continue
r_id2st = {generalize_species(it): st for (it, st) in reactants.items()}
p_id2st = {generalize_species(it): st for (it, st) in products.items()}
reversible = next((False for r_id in r_ids if not input_model.getReaction(r_id).getReversible()), True)
new_r_id = create_reaction(generalized_model, r_id2st, p_id2st, name=r_name, reversible=reversible,
id_=representative.getId() if len(r_ids) == 1 else None).getId()
elif len(r_ids) > 1:
r_id_increment += 1
new_r_id = generate_unique_id(input_model, "r_g_", r_id_increment)
if len(r_ids) > 1:
for r_id in r_ids:
r_id2g_eq[r_id] = new_r_id, r_name
if groups_sbml and groups_plugin:
# save as a group
r_group = groups_plugin.createGroup()
r_group.setId(new_r_id)
r_group.setKind(libsbml.GROUP_KIND_COLLECTION)
r_group.setSBOTerm(SBO_BIOCHEMICAL_REACTION)
r_group.setName(r_name)
for r_id in r_ids:
member = r_group.createMember()
member.setIdRef(r_id)
add_annotation(r_group, libsbml.BQB_IS_DESCRIBED_BY, GROUP_TYPE_EQUIV)
if out_sbml:
remove_unused_elements(generalized_model)
save_as_sbml(generalized_model, out_sbml)
if groups_sbml and groups_model:
save_as_sbml(groups_model, groups_sbml)
logging.info("serialized to " + groups_sbml)
return r_id2g_eq, s_id2gr_id