def generate_model(model_name):
"""Generate a simple model for end-to-end testing using natural language."""
tp = trips.process_text('BRAF activates MAP2K1. '
'Active MAP2K1 activates MAPK1.')
indra_stmts = tp.statements
emmaa_stmts = [
EmmaaStatement(stmt, datetime.datetime.now(), 'MAPK1')
for stmt in indra_stmts
]
# Create a CXAssembled model, upload to NDEx and retrieve key
#cxa = CxAssembler(indra_stmts)
#cxa.make_model()
#ndex_id = cxa.upload_model(private=False)
config_dict = {
'ndex': {
'network': 'a08479d1-24ce-11e9-bb6a-0ac135e8bacf'
},
'search_terms': [{
'db_refs': {
'HGNC': '20974'
},
'name': 'MAPK1',
'search_term': 'MAPK1',
'type': 'gene'
}]
}
emmaa_model = EmmaaModel(model_name, config_dict)
emmaa_model.add_statements(emmaa_stmts)
return emmaa_model, config_dict
def test_model_json():
"""Test the json structure and content of EmmaaModel.to_json() output"""
indra_stmts = \
[Activation(Agent('BRAF', db_refs={'HGNC': '20974'}),
Agent('MAP2K1'),
evidence=[Evidence(text='BRAF activates MAP2K1.')]),
Activation(Agent('MAP2K1',
activity=ActivityCondition('activity', True)),
Agent('MAPK1'),
evidence=[Evidence(text='Active MAP2K1 activates MAPK1.')])
]
st = SearchTerm('gene', 'MAP2K1', db_refs={}, search_term='MAP2K1')
emmaa_stmts = [
EmmaaStatement(stmt, datetime.datetime.now(), [st])
for stmt in indra_stmts
]
config_dict = {
'ndex': {
'network': 'a08479d1-24ce-11e9-bb6a-0ac135e8bacf'
},
'search_terms': [{
'db_refs': {
'HGNC': '20974'
},
'name': 'MAPK1',
'search_term': 'MAPK1',
'type': 'gene'
}]
}
emmaa_model = EmmaaModel('test', config_dict)
emmaa_model.add_statements(emmaa_stmts)
emmaa_model_json = emmaa_model.to_json()
# Test json structure
assert emmaa_model_json['name'] == 'test'
assert isinstance(emmaa_model_json['stmts'], list)
assert emmaa_model_json['ndex_network'] == \
'a08479d1-24ce-11e9-bb6a-0ac135e8bacf'
# Test config
assert emmaa_model_json['search_terms'][0]['type'] == 'gene'
assert emmaa_model_json['search_terms'][0]['db_refs'] == {'HGNC': '20974'}
# Test json statements
assert 'BRAF activates MAP2K1.' == \
emmaa_model_json['stmts'][0]['stmt']['evidence'][0]['text']
assert 'BRAF activates MAP2K1.' == \
emmaa_model_json['stmts'][0]['stmt']['evidence'][0]['text']
assert 'Active MAP2K1 activates MAPK1.' == \
emmaa_model_json['stmts'][1]['stmt']['evidence'][0]['text']
assert emmaa_model_json['stmts'][0]['stmt']['subj']['name'] == 'BRAF'
assert emmaa_model_json['stmts'][1]['stmt']['subj']['name'] == 'MAP2K1'
assert emmaa_model_json['stmts'][1]['stmt']['obj']['name'] == 'MAPK1'
# Need hashes to be strings so that javascript can read them
assert isinstance(
emmaa_model_json['stmts'][0]['stmt']['evidence'][0]['source_hash'],
str)
def upload_prior(ctype, config, gene_names):
fname = f'../models/{ctype}/prior_stmts.pkl'
with open(fname, 'rb') as fh:
stmts = pickle.load(fh)
estmts = get_emmaa_statements(stmts, gene_names)
model = EmmaaModel(ctype, config)
model.add_statements(estmts)
model.update_to_ndex()
def upload_prior(ctype, config):
fname = f'models/{ctype}/prior_stmts.pkl'
with open(fname, 'rb') as fh:
stmts = pickle.load(fh)
estmts = [
EmmaaStatement(stmt, datetime.datetime.now(), []) for stmt in stmts
]
model = EmmaaModel(ctype, config)
model.add_statements(estmts)
model.upload_to_ndex()
def test_model_extend():
ev1 = Evidence(pmid='1234', text='abcd', source_api='x')
ev2 = Evidence(pmid='1234', text='abcde', source_api='x')
ev3 = Evidence(pmid='1234', text='abcd', source_api='x')
indra_sts = [Phosphorylation(None, Agent('a'), evidence=ev) for ev in
[ev1, ev2, ev3]]
emmaa_sts = [EmmaaStatement(st, datetime.datetime.now(), []) for st in
indra_sts]
em = EmmaaModel('x', {'search_terms': [], 'ndex': {'network': None}})
em.add_statements([emmaa_sts[0]])
em.extend_unique(emmaa_sts[1:])
assert len(em.stmts) == 2
stmt = EmmaaStatement(Phosphorylation(None, Agent('b'), evidence=ev1),
datetime.datetime.now(), [])
em.extend_unique([stmt])
assert len(em.stmts) == 3
def create_model(relevance=None, paper_ids=None):
indra_stmts = [
Activation(Agent('BRAF', db_refs={'HGNC': '1097'}),
Agent('MAP2K1', db_refs={'HGNC': '6840'}),
evidence=[Evidence(text='BRAF activates MAP2K1.',
source_api='assertion',
text_refs={'TRID': '1234'})]),
Activation(Agent('MAP2K1', db_refs={'HGNC': '6840'},
activity=ActivityCondition('activity', True)),
Agent('MAPK1', db_refs={'HGNC': '6871'}),
evidence=[Evidence(text='Active MAP2K1 activates MAPK1.',
source_api='assertion',
text_refs={'TRID': '2345'})])
]
st = SearchTerm('gene', 'MAP2K1', db_refs={}, search_term='MAP2K1')
emmaa_stmts = [
EmmaaStatement(
indra_stmts[0], datetime.datetime.now(), [st],
{'internal': True, 'curated': False}),
EmmaaStatement(
indra_stmts[1], datetime.datetime.now(), [st],
{'internal': True, 'curated': True})
]
config_dict = {
'ndex': {'network': 'a08479d1-24ce-11e9-bb6a-0ac135e8bacf'},
'search_terms': [{'db_refs': {'HGNC': '20974'}, 'name': 'MAPK1',
'search_term': 'MAPK1', 'type': 'gene'}],
'human_readable_name': 'Test Model',
'test': {
'statement_checking': {'max_path_length': 5, 'max_paths': 1},
'test_corpus': 'simple_tests',
'mc_types': ['pysb', 'pybel', 'signed_graph', 'unsigned_graph']},
'assembly': [
{'function': 'filter_no_hypothesis'},
{'function': 'map_grounding'},
{'function': 'filter_grounded_only'},
{'function': 'filter_human_only'},
{'function': 'map_sequence'},
{'function': 'run_preassembly', 'kwargs': {
'return_toplevel': False}}]}
if relevance:
config_dict['assembly'].append(
{'function': 'filter_relevance', 'kwargs': {'policy': relevance}})
emmaa_model = EmmaaModel('test', config_dict, paper_ids)
emmaa_model.add_statements(emmaa_stmts)
return emmaa_model
def create_upload_model(model_name, full_name, indra_stmts, ndex_id=None):
"""Make and upload an EMMAA model from a list of INDRA Statements.
Parameters
----------
short_name : str
Short name of the model to use on S3.
full_name : str
Human-readable model name to use in EMMAA dashboard.
indra_stmts : list of indra.statement
INDRA Statements to be used to populate the EMMAA model.
ndex_id : str
UUID of the network corresponding to the model on NDex. If provided,
the NDex network will be updated with the latest model content.
If None (default), a new network will be created and the UUID stored
in the model config files on S3.
"""
emmaa_stmts = to_emmaa_stmts(indra_stmts, datetime.datetime.now(), [])
# Get updated CX content for the INDRA Statements
cxa = CxAssembler(indra_stmts)
cx_str = cxa.make_model()
# If we don't have an NDex ID, create network and upload to Ndex
if ndex_id is None:
ndex_id = cxa.upload_model(private=False)
print(f'NDex ID for {model_name} is {ndex_id}.')
# If the NDEx ID is provided, update the existing network
else:
ndex_client.update_network(cx_str, ndex_id)
# Create the config dictionary
config_dict = {'ndex': {'network': ndex_id}, 'search_terms': []}
# Create EMMAA model
emmaa_model = EmmaaModel(model_name, config_dict)
emmaa_model.add_statements(emmaa_stmts)
# Upload model to S3 with config as YAML and JSON
emmaa_model.save_to_s3()
s3_client = boto3.client('s3')
config_json = json.dumps(config_dict)
s3_client.put_object(Body=config_json.encode('utf8'),
Key='models/%s/config.json' % model_name,
Bucket='emmaa')
config_json = json.dumps(config_dict)
s3_client.put_object(Body=config_json.encode('utf8'),
Key='models/%s/config.json' % model_name,
Bucket='emmaa')
def update_cancer(cancer_type):
"""Update the model for the given cancer.
A JSON config file must be present for the given cancer type, located in
the models/<cancer_type>/config.json.
Parameters
----------
cancer_type : str
A short string which is the name of the cancer, and corresponds to a
directory in the models directory, as described above.
"""
print(cancer_type)
with open(f'models/{cancer_type}/prior_stmts.pkl', 'rb') as fh:
stmts = pickle.load(fh)
config = json.load(open(f'models/{cancer_type}/config.json', 'r'))
em = EmmaaModel(cancer_type, config)
ess = [EmmaaStatement(st, datetime.datetime.now(), []) for st in stmts]
em.add_statements(ess)
em.save_to_s3()
return
def create_upload_model(model_name, indra_stmts, config_file):
"""Make and upload an EMMAA model from a list of INDRA Statements.
Parameters
----------
model_name : str
Name of the model to use on S3.
indra_stmts : list of indra.statement
INDRA Statements to be used to populate the EMMAA model.
config_file : str
Path to the local config.json file.
"""
emmaa_stmts = to_emmaa_stmts(indra_stmts, datetime.datetime.now(), [],
{'internal': True})
# Load config information
with open(config_file, 'rt') as f:
config_json = json.load(f)
# If there is no ndex entry in the config, create a new network and update
# the config file with the NDex network ID
if 'ndex' not in config_json:
cxa = CxAssembler(indra_stmts)
cx_str = cxa.make_model()
ndex_id = cxa.upload_model(private=False)
print(f'NDex ID for {model_name} is {ndex_id}.')
config_json['ndex'] = {'network': ndex_id}
updated_config_file = f'{config_file}.updated'
with open(updated_config_file, 'wt') as f:
json.dump(config_json, f, indent=2)
# If the NDEx ID is provided we don't need to update the existing network
# because this will occur as part of the model assembly/update procedure
# on EMMAA itself.
# Create the config dictionary
# Create EMMAA model
emmaa_model = EmmaaModel(model_name, config_json)
emmaa_model.add_statements(emmaa_stmts)
# Upload model to S3
emmaa_model.save_to_s3()
# Upload config JSON
s3_client = boto3.client('s3')
save_config_to_s3(model_name, config_json)
def make_model(self, estmts, upload_to_s3=False):
"""Return, and optionally upload to S3 an initial EMMAA Model.
Parameters
----------
estmts : list of emmaa.statement.EmmaaStatement
A list of prior EMMAA Statements to initialize the model with.
upload_to_s3 : Optional[bool]
If True, the model and the config are uploaded to S3, otherwise
the model object is just returned without upload. Default: False
Returns
-------
emmaa.model.EmmaaModel
The EMMAA Model object constructed from the generated config
and the given EMMAA Statements.
"""
from emmaa.model import EmmaaModel
config = self.make_config(upload_to_s3=upload_to_s3)
model = EmmaaModel(name=self.name, config=config)
model.add_statements(estmts)
if upload_to_s3:
model.save_to_s3()
return model