def get_eidos_scorer() -> SimpleScorer:
"""Return a SimpleScorer based on Eidos curated precision estimates.
Returns
-------
scorer :
A SimpleScorer instance loaded with default prior probabilities as
well as prior probabilities derived from curation-based counts.
"""
with open(get_resource_file('default_belief_probs.json'), 'r') as fh:
prior_probs = json.load(fh)
table = load_eidos_curation_table()
# Get the overall precision
total_num = table['COUNT of RULE'].sum()
weighted_sum = table['COUNT of RULE'].dot(table['% correct'])
precision = weighted_sum / total_num
# We have to divide this into a random and systematic component, for now
# in an ad-hoc manner
syst_error = 0.05
rand_error = 1 - precision - syst_error
prior_probs['rand']['eidos'] = rand_error
prior_probs['syst']['eidos'] = syst_error
# Get a dict of rule-specific errors.
subtype_probs = {
'eidos': {
k: 1.0 - min(v, 0.95) - syst_error
for k, v in zip(table['RULE'], table['% correct'])
}
}
scorer = SimpleScorer(prior_probs, subtype_probs)
return scorer
def calculate_belief(stmts):
scorer = SimpleScorer(subtype_probs={
'biopax': {'pc11': 0.2, 'phosphosite': 0.01},
})
be = BeliefEngine(scorer=scorer)
be.set_prior_probs(stmts)
be.set_hierarchy_probs(stmts)
return {str(s.get_hash()): s.belief for s in stmts}
def test_evidence_random_noise_prior():
type_probs = {'biopax': 0.9, 'geneways': 0.2}
biopax_subtype_probs = {'reactome': 0.4, 'biogrid': 0.2}
geneways_subtype_probs = {'phosphorylate': 0.5, 'bind': 0.7}
subtype_probs = {
'biopax': biopax_subtype_probs,
'geneways': geneways_subtype_probs
}
ev_geneways_bind = Evidence(source_api='geneways',
source_id=0,
pmid=0,
text=None,
epistemics={},
annotations={'actiontype': 'bind'})
ev_biopax_reactome = Evidence(source_api='biopax',
source_id=0,
pmid=0,
text=None,
epistemics={},
annotations={'source_sub_id': 'reactome'})
ev_biopax_pid = Evidence(source_api='biopax',
source_id=0,
pmid=0,
text=None,
epistemics={},
annotations={'source_sub_id': 'pid'})
# Random noise prior for geneways bind evidence is the subtype prior,
# since we specified it
assert evidence_random_noise_prior(ev_geneways_bind, \
type_probs, subtype_probs) == 0.7
# Random noise prior for reactome biopax evidence is the subtype prior,
# since we specified it
assert evidence_random_noise_prior(ev_biopax_reactome, \
type_probs, subtype_probs) == 0.4
# Random noise prior for pid evidence is the subtype prior,
# since we specified it
assert evidence_random_noise_prior(ev_biopax_pid, type_probs,
subtype_probs) == 0.9
# Make sure this all still works when we go through the belief engine
statements = []
members = [Agent('a'), Agent('b')]
statements.append(Complex(members, evidence=ev_geneways_bind))
statements.append(Complex(members, evidence=ev_biopax_reactome))
statements.append(Complex(members, evidence=ev_biopax_pid))
p = {'rand': type_probs, 'syst': {'biopax': 0, 'geneways': 0}}
scorer = SimpleScorer(p, subtype_probs)
engine = BeliefEngine(scorer)
engine.set_prior_probs(statements)
assert statements[0].belief == 1 - 0.7
assert statements[1].belief == 1 - 0.4
assert statements[2].belief == 1 - 0.9
def test_default_probs_override():
"""Make sure default probs are overriden by constructor argument."""
prior_probs = {'rand': {'assertion': 0.5}}
scorer = SimpleScorer(prior_probs)
be = BeliefEngine(scorer)
for err_type in ('rand', 'syst'):
for k, v in scorer.prior_probs[err_type].items():
if err_type == 'rand' and k == 'assertion':
assert v == 0.5
else:
assert default_probs[err_type][k] == v
def test_default_probs_extend():
"""Make sure default probs are extended by constructor argument."""
prior_probs = {'rand': {'new_source': 0.1}, 'syst': {'new_source': 0.05}}
scorer = SimpleScorer(prior_probs)
be = BeliefEngine(scorer)
for err_type in ('rand', 'syst'):
assert 'new_source' in scorer.prior_probs[err_type]
for k, v in scorer.prior_probs[err_type].items():
if err_type == 'rand' and k == 'new_source':
assert v == 0.1
elif err_type == 'syst' and k == 'new_source':
assert v == 0.05
else:
assert default_probs[err_type][k] == v
def test_score_statement():
"""Check that we can correctly score a single statement."""
prior_probs = {'rand': {'reach': 0.1, 'trips': 0.2},
'syst': {'reach': 0, 'trips': 0}}
scorer = SimpleScorer(prior_probs)
# ev1 is from "reach"
st1 = Phosphorylation(None, Agent('a'), evidence=[ev1])
belief = scorer.score_statement(st1)
assert belief == 0.9
# try extra_evidence empty list:
belief = scorer.score_statement(st1, extra_evidence=[])
assert belief == 0.9
# Now we try extra_evidence from trips.
# Expected result is 1 - (0.1 * 0.2) = 0.98
belief = scorer.score_statement(st1, extra_evidence=[ev2])
assert belief == 0.98
def test_negative_evidence():
prior_probs = {'rand': {'new_source': 0.1},
'syst': {'new_source': 0.05}}
getev = lambda x: Evidence(source_api='new_source',
epistemics={'negated': x})
evs1 = [getev(x) for x in [True, True, False]]
evs2 = [getev(x) for x in [False, False, False]]
evs3 = [getev(x) for x in [True, True, True]]
stmts = [Phosphorylation(None, Agent('a'), evidence=e)
for e in [evs1, evs2, evs3]]
scorer = SimpleScorer(prior_probs)
engine = BeliefEngine(scorer)
engine.set_prior_probs(stmts)
pr = prior_probs['rand']['new_source']
ps = prior_probs['syst']['new_source']
assert_close_enough(stmts[0].belief, ((1-pr)-ps)*(1-((1-pr*pr)-ps)))
assert_close_enough(stmts[1].belief, (1-pr*pr*pr)-ps)
assert stmts[2].belief == 0
import json
import logging
from os import path
import numpy as np
import pandas as pd
import networkx as nx
from decimal import Decimal
import indra
from indra.belief import SimpleScorer
from indra.statements import Evidence
from indra.statements import Statement
logger = logging.getLogger(__name__)
simple_scorer = SimpleScorer()
np.seterr(all='raise')
NP_PRECISION = 10 ** -np.finfo(np.longfloat).precision # Numpy precision
default_sign_dict = {'Activation': 0,
'Inhibition': 1,
'IncreaseAmount': 0,
'DecreaseAmount': 1}
INDRA_ROOT = path.abspath(path.dirname(path.abspath(indra.__file__)))
INDRA_RESOURCES = path.join(INDRA_ROOT, 'resources')
with open(path.join(INDRA_RESOURCES, 'source_mapping.json'), 'r') as f:
db_source_mapping = json.load(f)
class IndraNet(nx.MultiDiGraph):