def test_set_context():
cxa = CxAssembler()
cxa.add_statements([st_phos, st_dephos])
cxa.make_model()
cxa.set_context('BT20_BREAST')
print(cxa.cx['nodeAttributes'])
assert(len(cxa.cx['nodeAttributes']) == 10)
def test_cited():
cxa = CxAssembler()
cxa.add_statements([st_cited])
cxa.make_model()
assert(len(cxa.cx['citations']) == 1)
assert(len(cxa.cx['edgeCitations']) == 1)
citation = cxa.cx['citations'][0]
assert(citation.get('dc:identifier') == 'pmid:12345')
cid = citation.get('@id')
assert(cxa.cx['edgeCitations'][0]['citations'][0] == cid)
def assemble_cx(stmts, out_file):
"""Return a CX assembler."""
stmts = ac.filter_belief(stmts, 0.95)
stmts = ac.filter_top_level(stmts)
stmts = ac.strip_agent_context(stmts)
ca = CxAssembler()
ca.add_statements(stmts)
model = ca.make_model()
ca.save_model(out_file)
return ca
def test_rasgef():
cxa = CxAssembler()
cxa.add_statements([st_rasgef])
cxa.make_model()
assert (len(cxa.cx['nodes']) == 2)
assert (len(cxa.cx['edges']) == 1)
def test_edge_attributes():
cxa = CxAssembler()
cxa.add_statements([st_phos, st_dephos])
cxa.make_model()
assert(len(cxa.cx['edgeAttributes']) == 8)
def test_rasgap():
cxa = CxAssembler()
cxa.add_statements([st_rasgap])
cxa.make_model()
assert(len(cxa.cx['nodes']) == 2)
assert(len(cxa.cx['edges']) == 1)
def test_act():
cxa = CxAssembler()
cxa.add_statements([st_act, st_act2])
cxa.make_model()
assert(len(cxa.cx['nodes']) == 3)
assert(len(cxa.cx['edges']) == 2)
def test_complex():
cxa = CxAssembler()
cxa.add_statements([st_complex])
cxa.make_model()
assert(len(cxa.cx['nodes']) == 3)
assert(len(cxa.cx['edges']) == 3)
def test_dephos():
cxa = CxAssembler()
cxa.add_statements([st_phos, st_dephos])
cxa.make_model()
assert(len(cxa.cx['nodes']) == 3)
assert(len(cxa.cx['edges']) == 2)
def test_make_print_model():
cxa = CxAssembler()
cxa.add_statements([st_phos])
cx_str = cxa.make_model()
assert(cx_str)
def test_invalid_cited():
cxa = CxAssembler()
cxa.add_statements([st_invalid_cited])
cxa.make_model()
assert(not cxa.cx['citations'])
assert(not cxa.cx['edgeCitations'])
def test_complex():
cxa = CxAssembler()
cxa.add_statements([st_complex])
cxa.make_model()
assert (len(cxa.cx['nodes']) == 3)
assert (len(cxa.cx['edges']) == 3)
def test_act():
cxa = CxAssembler()
cxa.add_statements([st_act, st_act2])
cxa.make_model()
assert (len(cxa.cx['nodes']) == 3)
assert (len(cxa.cx['edges']) == 2)
def test_dephos():
cxa = CxAssembler()
cxa.add_statements([st_phos, st_dephos])
cxa.make_model()
assert (len(cxa.cx['nodes']) == 3)
assert (len(cxa.cx['edges']) == 2)
def test_make_print_model():
cxa = CxAssembler()
cxa.add_statements([st_phos])
cx_str = cxa.make_model()
assert (cx_str)
def test_supports():
cxa = CxAssembler()
cxa.add_statements([st_cited])
cxa.make_model()
assert (len(cxa.cx['supports']) == 1)
assert (len(cxa.cx['edgeSupports']) == 1)
def test_invalid_cited():
cxa = CxAssembler()
cxa.add_statements([st_invalid_cited])
cxa.make_model()
assert (not cxa.cx['citations'])
assert (not cxa.cx['edgeCitations'])
def test_edge_attributes():
cxa = CxAssembler()
cxa.add_statements([st_phos, st_dephos])
cxa.make_model()
assert (len(cxa.cx['edgeAttributes']) == 14)
def test_supports():
cxa = CxAssembler()
cxa.add_statements([st_cited])
cxa.make_model()
assert(len(cxa.cx['supports']) == 1)
assert(len(cxa.cx['edgeSupports']) == 1)
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
# 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)
def get_drug_names(st):
prior_drugs = set()
for s in st:
for a in s.agent_list():
if a is not None:
if a.name.find('Drugs') != -1:
prior_drugs.add(a.name.split(':')[0])
return sorted(list(prior_drugs))
pkn_drugs = get_drug_names(stmts)
print('Boolean PKN contains these antibodies: %s' % ', '.join(pkn_abs))
# Because of a bug in CNO,
# node names containing AND need to be replaced
# node names containing - need to be replaced
# node names starting in a digit need to be replaced
# must happen before SIF assembly, but not sooner as that will drop
# names from the MIDAS file
def rename_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')
if a.name.find('-') != -1:
a.name = a.name.replace('-', '_')
if a.name[0].isdigit():
a.name = 'abc_' + a.name
rename_nodes(stmts)
# Make the SIF model
sa = SifAssembler(stmts)
sa.make_model(use_name_as_key=True)
sif_str = sa.print_model()
# assemble and dump a cx of the sif
ca = CxAssembler()
ca.add_statements(stmts)
model = ca.make_model()
ca.save_model('sif.cx')
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, pkn_drugs)
return sif_str
