def run_assembly(self):
"""Run INDRA's assembly pipeline on the Statements."""
self.eliminate_copies()
stmts = self.get_indra_stmts()
stmts = self.filter_event_association(stmts)
stmts = ac.filter_no_hypothesis(stmts)
if not self.assembly_config.get('skip_map_grounding'):
stmts = ac.map_grounding(stmts)
if self.assembly_config.get('standardize_names'):
ac.standardize_names_groundings(stmts)
if self.assembly_config.get('filter_ungrounded'):
score_threshold = self.assembly_config.get('score_threshold')
stmts = ac.filter_grounded_only(stmts,
score_threshold=score_threshold)
if self.assembly_config.get('merge_groundings'):
stmts = ac.merge_groundings(stmts)
if self.assembly_config.get('merge_deltas'):
stmts = ac.merge_deltas(stmts)
relevance_policy = self.assembly_config.get('filter_relevance')
if relevance_policy:
stmts = self.filter_relevance(stmts, relevance_policy)
if not self.assembly_config.get('skip_filter_human'):
stmts = ac.filter_human_only(stmts)
if not self.assembly_config.get('skip_map_sequence'):
stmts = ac.map_sequence(stmts)
# Use WM hierarchies and belief scorer for WM preassembly
preassembly_mode = self.assembly_config.get('preassembly_mode')
if preassembly_mode == 'wm':
hierarchies = get_wm_hierarchies()
belief_scorer = get_eidos_scorer()
stmts = ac.run_preassembly(stmts,
return_toplevel=False,
belief_scorer=belief_scorer,
hierarchies=hierarchies)
else:
stmts = ac.run_preassembly(stmts, return_toplevel=False)
belief_cutoff = self.assembly_config.get('belief_cutoff')
if belief_cutoff is not None:
stmts = ac.filter_belief(stmts, belief_cutoff)
stmts = ac.filter_top_level(stmts)
if self.assembly_config.get('filter_direct'):
stmts = ac.filter_direct(stmts)
stmts = ac.filter_enzyme_kinase(stmts)
stmts = ac.filter_mod_nokinase(stmts)
stmts = ac.filter_transcription_factor(stmts)
if self.assembly_config.get('mechanism_linking'):
ml = MechLinker(stmts)
ml.gather_explicit_activities()
ml.reduce_activities()
ml.gather_modifications()
ml.reduce_modifications()
ml.gather_explicit_activities()
ml.replace_activations()
ml.require_active_forms()
stmts = ml.statements
self.assembled_stmts = stmts
def default_assembly(stmts):
from indra.belief.wm_scorer import get_eidos_scorer
from indra.preassembler.hierarchy_manager import get_wm_hierarchies
hm = get_wm_hierarchies()
scorer = get_eidos_scorer()
stmts = ac.run_preassembly(stmts, belief_scorer=scorer,
return_toplevel=True,
flatten_evidence=True,
flatten_evidence_collect_from='supported_by',
poolsize=4)
stmts = ac.merge_groundings(stmts)
stmts = ac.merge_deltas(stmts)
stmts = ac.standardize_names_groundings(stmts)
return stmts
def default_assembly(stmts):
from indra.belief.wm_scorer import get_eidos_scorer
from indra.preassembler.hierarchy_manager import get_wm_hierarchies
hm = get_wm_hierarchies()
scorer = get_eidos_scorer()
stmts = ac.run_preassembly(stmts, belief_scorer=scorer,
return_toplevel=True,
flatten_evidence=True,
flatten_evidence_collect_from='supported_by',
poolsize=4)
stmts = ac.merge_groundings(stmts)
stmts = ac.merge_deltas(stmts)
stmts = ac.standardize_names_groundings(stmts)
return stmts
def test_merge_groundings():
refs1 = {'UN': [('x', 0.8), ('y', 0.7)], 'B': 'x', 'C': 'y'}
refs2 = {'UN': [('x', 0.9), ('y', 0.6), ('z', 0.5)], 'B': 'x', 'D': 'z'}
stmts = [
Influence(Concept('a', db_refs=refs1),
Concept('b', db_refs=refs2),
evidence=[Evidence(source_api='eidos', text='1')]),
Influence(Concept('a', db_refs=refs2),
Concept('b', db_refs=refs1),
evidence=[Evidence(source_api='eidos', text='2')])
]
stmts = ac.run_preassembly(stmts)
assert len(stmts) == 1
stmts = ac.merge_groundings(stmts)
assert stmts[0].subj.db_refs == \
{'UN': [('x', 0.9), ('y', 0.7), ('z', 0.5)],
'B': 'x', 'C': 'y', 'D': 'z'}, \
stmts[0].subj.db_refs
assert stmts[0].obj.db_refs == stmts[0].subj.db_refs
def test_merge_groundings():
refs1 = {'UN': [('x', 0.8), ('y', 0.7)],
'B': 'x',
'C': 'y'}
refs2 = {'UN': [('x', 0.9), ('y', 0.6), ('z', 0.5)],
'B': 'x',
'D': 'z'}
stmts = [Influence(Event(Concept('a', db_refs=refs1)),
Event(Concept('b', db_refs=refs2)),
evidence=[Evidence(source_api='eidos', text='1')]),
Influence(Event(Concept('a', db_refs=refs2)),
Event(Concept('b', db_refs=refs1)),
evidence=[Evidence(source_api='eidos', text='2')])]
stmts = ac.run_preassembly(stmts)
assert len(stmts) == 1
stmts = ac.merge_groundings(stmts)
assert stmts[0].subj.concept.db_refs == \
{'UN': [('x', 0.9), ('y', 0.7), ('z', 0.5)],
'B': 'x', 'C': 'y', 'D': 'z'}, \
stmts[0].subj.db_refs
assert stmts[0].obj.concept.db_refs == stmts[0].subj.concept.db_refs
def surface_details(stmts):
stmts = ac.merge_groundings(stmts)
stmts = ac.merge_deltas(stmts)
return stmts
from indra.statements import stmts_to_json_file
import indra.tools.assemble_corpus as ac
from assemble_model import process_eidos, assemble_stmts
if __name__ == '__main__':
stmts = process_eidos()
stmts_to_json_file(stmts, 'eidos_500m_raw.json')
stmts = assemble_stmts(stmts)
stmts = ac.merge_groundings(stmts)
stmts = ac.merge_deltas(stmts)
stmts = ac.standardize_names_groundings(stmts)
stmts_to_json_file(stmts, 'eidos_500m_assembled.json')
