def assemble_pysb(stmts, data_genes, out_file):
"""Return an assembled PySB model."""
base_file, _ = os.path.splitext(out_file)
#stmts = ac.load_statements('%s.pkl' % base_file)
stmts = preprocess_stmts(stmts, data_genes)
# Make a SIF model equivalent to the PySB model
# Useful for making direct comparisons in pathfinding
sa = SifAssembler(stmts)
sa.make_model(use_name_as_key=True,
include_mods=True,
include_complexes=True)
sif_str = sa.print_model(include_unsigned_edges=True)
with open('%s_pysb.sif' % base_file, 'wt') as f:
f.write(sif_str)
# This is the "final" set of statements going into the assembler so it
# makes sense to cache these.
# This is also the point where index cards can be generated
ac.dump_statements(stmts, '%s_before_pa.pkl' % base_file)
assemble_index_cards(stmts, 'output/index_cards')
# Save a version of statements with no evidence for faster loading
for s in stmts:
s.evidence = []
for ss in s.supports + s.supported_by:
ss.evidence = []
ac.dump_statements(stmts, '%s_no_evidence.pkl' % base_file)
# Assemble model
pa = PysbAssembler()
pa.add_statements(stmts)
pa.make_model(reverse_effects=False)
#ac.dump_statements(pa.statements, '%s_after_pa.pkl' % base_file)
# Set context
set_context(pa)
# Add observables
add_observables(pa.model)
pa.save_model(out_file)
with open('korkut_pysb.pkl', 'wb') as fh:
pickle.dump(pa.model, fh)
#pa.export_model('kappa', '%s.ka' % base_file)
return pa.model
def assemble_sif(stmts, data, out_file):
"""Return an assembled SIF."""
# Filter for high-belief statements
stmts = ac.filter_belief(stmts, 0.99)
stmts = ac.filter_top_level(stmts)
# Filter for Activation / Inhibition
stmts_act = ac.filter_by_type(stmts, Activation)
stmts_inact = ac.filter_by_type(stmts, Inhibition)
stmts = stmts_act + stmts_inact
# Get Ras227 and filter statments
ras_genes = process_data.get_ras227_genes()
ras_genes = [x for x in ras_genes if x not in ['YAP1']]
stmts = ac.filter_gene_list(stmts, ras_genes, 'all')
# Get the drugs inhibiting their targets as INDRA
# statements
def get_drug_statements():
drug_targets = process_data.get_drug_targets()
drug_stmts = []
for dn, tns in drug_targets.items():
da = Agent(dn + ':Drugs')
for tn in tns:
ta = Agent(tn)
drug_stmt = Inhibition(da, ta)
drug_stmts.append(drug_stmt)
return drug_stmts
drug_stmts = get_drug_statements()
stmts = stmts + drug_stmts
# Because of a bug in CNO, node names containing AND
# need to be replaced
def rename_and_nodes(st):
for s in st:
for a in s.agent_list():
if a is not None:
if a.name.find('AND') != -1:
a.name = a.name.replace('AND', 'A_ND')
rename_and_nodes(stmts)
# Rewrite statements to replace genes with their corresponding
# antibodies when possible
stmts = rewrite_ab_stmts(stmts, data)
def filter_ab_edges(st, policy='all'):
st_out = []
for s in st:
if policy == 'all':
all_ab = True
for a in s.agent_list():
if a is not None:
if a.name.find('_p') == -1 and \
a.name.find('Drugs') == -1:
all_ab = False
break
if all_ab:
st_out.append(s)
elif policy == 'one':
any_ab = False
for a in s.agent_list():
if a is not None and a.name.find('_p') != -1:
any_ab = True
break
if any_ab:
st_out.append(s)
return st_out
stmts = filter_ab_edges(stmts, 'all')
# Get a list of the AB names that end up being covered in the prior network
# This is important because other ABs will need to be taken out of the
# MIDAS file to work.
def get_ab_names(st):
prior_abs = set()
for s in st:
for a in s.agent_list():
if a is not None:
if a.name.find('_p') != -1:
prior_abs.add(a.name)
return sorted(list(prior_abs))
pkn_abs = get_ab_names(stmts)
print('Boolean PKN contains these antibodies: %s' % ', '.join(pkn_abs))
# Make the SIF model
sa = SifAssembler(stmts)
sa.make_model(use_name_as_key=True)
sif_str = sa.print_model()
with open(out_file, 'wb') as fh:
fh.write(sif_str.encode('utf-8'))
# Make the MIDAS data file used for training the model
midas_data = process_data.get_midas_data(data, pkn_abs)
return sif_str
