def find_gene_knockout_reactions_fast(cobra_model, gene_list):
compiled_rules = delete.get_compiled_gene_reaction_rules(
cobra_model)
return find_gene_knockout_reactions(
cobra_model,
gene_list,
compiled_gene_reaction_rules=compiled_rules)
def escape_ID(cobra_model):
"""makes all ids SBML compliant"""
for x in chain([cobra_model], cobra_model.metabolites,
cobra_model.reactions, cobra_model.genes):
x.id = _escape_str_id(x.id)
cobra_model.repair()
gene_renamer = _GeneEscaper()
for rxn, rule in get_compiled_gene_reaction_rules(cobra_model).items():
if rule is not None:
rxn._gene_reaction_rule = ast2str(gene_renamer.visit(rule))
def escape_ID(cobra_model):
"""makes all ids SBML compliant"""
for x in chain([cobra_model],
cobra_model.metabolites,
cobra_model.reactions,
cobra_model.genes):
x.id = _escape_str_id(x.id)
cobra_model.repair()
gene_renamer = _GeneEscaper()
for rxn, rule in iteritems(get_compiled_gene_reaction_rules(cobra_model)):
if rule is not None:
rxn._gene_reaction_rule = ast2str(gene_renamer.visit(rule))
def rename_genes(cobra_model, rename_dict):
"""renames genes in a model from the rename_dict"""
recompute_reactions = set() # need to recomptue related genes
remove_genes = []
for old_name, new_name in rename_dict.items():
# undefined if there a value matches a different key
# because dict is unordered
try:
gene_index = cobra_model.genes.index(old_name)
except ValueError:
gene_index = None
old_gene_present = gene_index is not None
new_gene_present = new_name in cobra_model.genes
if old_gene_present and new_gene_present:
old_gene = cobra_model.genes.get_by_id(old_name)
# Added in case not renaming some genes:
if old_gene is not cobra_model.genes.get_by_id(new_name):
remove_genes.append(old_gene)
recompute_reactions.update(old_gene._reaction)
elif old_gene_present and not new_gene_present:
# rename old gene to new gene
gene = cobra_model.genes[gene_index]
# trick DictList into updating index
cobra_model.genes._dict.pop(gene.id) # ugh
gene.id = new_name
cobra_model.genes[gene_index] = gene
elif not old_gene_present and new_gene_present:
pass
else: # if not old gene_present and not new_gene_present
# the new gene's _model will be set by repair
# This would add genes from rename_dict
# that are not associated with a rxn
# cobra_model.genes.append(Gene(new_name))
pass
cobra_model.repair()
class Renamer(NodeTransformer):
def visit_Name(self, node):
node.id = rename_dict.get(node.id, node.id)
return node
gene_renamer = Renamer()
for rxn, rule in get_compiled_gene_reaction_rules(cobra_model).items():
if rule is not None:
rxn._gene_reaction_rule = ast2str(gene_renamer.visit(rule))
for rxn in recompute_reactions:
rxn.gene_reaction_rule = rxn._gene_reaction_rule
for i in remove_genes:
cobra_model.genes.remove(i)
def rename_genes(cobra_model, rename_dict):
"""renames genes in a model from the rename_dict"""
recompute_reactions = set() # need to recomptue related genes
remove_genes = []
for old_name, new_name in iteritems(rename_dict):
# undefined if there a value matches a different key
# because dict is unordered
try:
gene_index = cobra_model.genes.index(old_name)
except ValueError:
gene_index = None
old_gene_present = gene_index is not None
new_gene_present = new_name in cobra_model.genes
if old_gene_present and new_gene_present:
old_gene = cobra_model.genes.get_by_id(old_name)
remove_genes.append(old_gene)
recompute_reactions.update(old_gene._reaction)
elif old_gene_present and not new_gene_present:
# rename old gene to new gene
gene = cobra_model.genes[gene_index]
# trick DictList into updating index
cobra_model.genes._dict.pop(gene.id) # ugh
gene.id = new_name
cobra_model.genes[gene_index] = gene
elif not old_gene_present and new_gene_present:
pass
else: # not old gene_present and not new_gene_present
# the new gene's _model will be set by repair
cobra_model.genes.append(Gene(new_name))
cobra_model.repair()
class Renamer(NodeTransformer):
def visit_Name(self, node):
node.id = rename_dict.get(node.id, node.id)
return node
gene_renamer = Renamer()
for rxn, rule in iteritems(get_compiled_gene_reaction_rules(cobra_model)):
if rule is not None:
rxn._gene_reaction_rule = ast2str(gene_renamer.visit(rule))
for rxn in recompute_reactions:
rxn.gene_reaction_rule = rxn._gene_reaction_rule
for i in remove_genes:
cobra_model.genes.remove(i)
def find_gene_knockout_reactions_fast(cobra_model, gene_list):
compiled_rules = delete.get_compiled_gene_reaction_rules(
cobra_model)
return find_gene_knockout_reactions(
cobra_model, gene_list,
compiled_gene_reaction_rules=compiled_rules)
def _double_gene_deletion_moma(cobra_model,
gene_ids1,
gene_ids2,
gene_id_to_result,
solver,
number_of_processes=1,
zero_cutoff=1e-12,
wt_growth_rate=None,
no_flux_reaction_indexes=set(),
**kwargs):
"""compute double gene deletions using moma
cobra_model: model
gene_ids1, gene_ids2: lists of id's to be knocked out
gene_id_to_result: maps each gene identifier to the entry in
the result matrix
number_of_processes: must be 1. Parallel MOMA not yet implemented
no_flux_reaction_indexes: set of indexes for reactions in the model
which carry no flux in an optimal solution. For deletions only in
this set, the result will beset to wt_growth_rate.
returns an upper triangular square matrix
"""
if number_of_processes > 1:
raise NotImplementedError("parallel MOMA not implemented")
if moma is None:
raise RuntimeError("scipy required for MOMA")
# Because each gene reaction rule will be evaluated multiple times
# the reaction has multiple associated genes being deleted, compiling
# the gene reaction rules ahead of time increases efficiency greatly.
compiled_rules = get_compiled_gene_reaction_rules(cobra_model)
# function to compute reaction knockouts with moma
moma_model, moma_obj = moma.create_euclidian_moma_model(cobra_model)
def run(gene_ids):
ko_reactions = find_gene_knockout_reactions(cobra_model, gene_ids)
ko_indexes = map(cobra_model.reactions.index, ko_reactions)
# If all the reactions carry no flux, deletion will have no effect.
if no_flux_reaction_indexes.issuperset(gene_ids):
return wt_growth_rate
return moma.moma_knockout(moma_model,
moma_obj,
ko_indexes,
solver=solver,
**kwargs).f
n_results = len(gene_id_to_result)
results = numpy.empty((n_results, n_results))
results.fill(numpy.nan)
# precompute all single deletions and store them along the diagonal
for gene_id, result_index in iteritems(gene_id_to_result):
value = run((gene_id, ))
value = value if abs(value) > zero_cutoff else 0.
results[result_index, result_index] = value
# If singly lethal, the entire row and column are set to 0.
if value == 0.:
results[result_index, :] = 0.
results[:, result_index] = 0.
# Run double knockouts in the upper triangle
index_selector = yield_upper_tria_indexes(gene_ids1, gene_ids2,
gene_id_to_result)
for result_index, (gene1, gene2) in index_selector:
# if singly lethal the results have already been set
if results[result_index] == 0:
continue
results[result_index] = run((gene1, gene2))
return results
def _double_gene_deletion_fba(cobra_model,
gene_ids1,
gene_ids2,
gene_id_to_result,
solver,
number_of_processes=None,
zero_cutoff=1e-12,
wt_growth_rate=None,
no_flux_reaction_indexes=set(),
**kwargs):
"""compute double gene deletions using fba
cobra_model: model
gene_ids1, gene_ids2: lists of id's to be knocked out
gene_id_to_result: maps each gene identifier to the entry in
the result matrix
no_flux_reaction_indexes: set of indexes for reactions in the model
which carry no flux in an optimal solution. For deletions only in
this set, the result will beset to wt_growth_rate.
returns an upper triangular square matrix
"""
# Because each gene reaction rule will be evaluated multiple times
# the reaction has multiple associated genes being deleted, compiling
# the gene reaction rules ahead of time increases efficiency greatly.
compiled_rules = get_compiled_gene_reaction_rules(cobra_model)
n_results = len(gene_id_to_result)
results = numpy.empty((n_results, n_results))
results.fill(numpy.nan)
if number_of_processes == 1: # explicitly disable multiprocessing
PoolClass = CobraDeletionMockPool
else:
PoolClass = CobraDeletionPool
with PoolClass(cobra_model,
n_processes=number_of_processes,
solver=solver,
**kwargs) as pool:
# precompute all single deletions in the pool and store them along
# the diagonal
for gene_id, gene_result_index in iteritems(gene_id_to_result):
ko_reactions = find_gene_knockout_reactions(
cobra_model, (cobra_model.genes.get_by_id(gene_id), ))
ko_indexes = [cobra_model.reactions.index(i) for i in ko_reactions]
pool.submit(ko_indexes, label=gene_result_index)
for result_index, value in pool.receive_all():
# if singly lethal, set everything in row and column to 0
value = value if abs(value) > zero_cutoff else 0.
if value == 0.:
results[result_index, :] = 0.
results[:, result_index] = 0.
else: # only the diagonal needs to be set
results[result_index, result_index] = value
# Run double knockouts in the upper triangle
index_selector = yield_upper_tria_indexes(gene_ids1, gene_ids2,
gene_id_to_result)
for result_index, (gene1, gene2) in index_selector:
# if singly lethal the results have already been set
if results[result_index] == 0:
continue
ko_reactions = find_gene_knockout_reactions(
cobra_model, (gene1, gene2), compiled_rules)
ko_indexes = [cobra_model.reactions.index(i) for i in ko_reactions]
# if all removed gene indexes carry no flux
if len(set(ko_indexes) - no_flux_reaction_indexes) == 0:
results[result_index] = wt_growth_rate
continue
pool.submit(ko_indexes, label=result_index)
for result in pool.receive_all():
value = result[1]
if value < zero_cutoff:
value = 0
results[result[0]] = value
return results