def test_combine_duplicates():
raf = Agent('RAF1')
mek = Agent('MEK1')
erk = Agent('ERK2')
p1 = Phosphorylation(raf, mek,
evidence=Evidence(text='foo'))
p2 = Phosphorylation(raf, mek,
evidence=Evidence(text='bar'))
p3 = Phosphorylation(raf, mek,
evidence=Evidence(text='baz'))
p4 = Phosphorylation(raf, mek,
evidence=Evidence(text='beep'))
p5 = Phosphorylation(mek, erk,
evidence=Evidence(text='foo'))
p6 = Dephosphorylation(mek, erk,
evidence=Evidence(text='bar'))
p7 = Dephosphorylation(mek, erk,
evidence=Evidence(text='baz'))
p8 = Dephosphorylation(mek, erk,
evidence=Evidence(text='beep'))
p9 = Dephosphorylation(Agent('SRC'), Agent('KRAS'),
evidence=Evidence(text='beep'))
stmts = [p1, p2, p3, p4, p5, p6, p7, p8, p9]
pa = Preassembler(hierarchies, stmts=stmts)
pa.combine_duplicates()
# The statements come out sorted by their matches_key
assert(len(pa.unique_stmts) == 4)
assert(pa.unique_stmts[0].matches(p6)) # MEK dephos ERK
assert(len(pa.unique_stmts[0].evidence) == 3)
assert(pa.unique_stmts[1].matches(p9)) # SRC dephos KRAS
assert(len(pa.unique_stmts[1].evidence) == 1)
assert(pa.unique_stmts[2].matches(p5)) # MEK phos ERK
assert(len(pa.unique_stmts[2].evidence) == 1)
assert(pa.unique_stmts[3].matches(p1)) # RAF phos MEK
assert(len(pa.unique_stmts[3].evidence) == 4)
def test_complex_refinement_order():
st1 = Complex([Agent('MED23'), Agent('ELK1')])
st2 = Complex([Agent('ELK1', mods=[ModCondition('phosphorylation')]),
Agent('MED23')])
pa = Preassembler(hierarchies, stmts=[st1, st2])
pa.combine_duplicates()
pa.combine_related()
assert len(pa.related_stmts) == 1
def test_duplicates():
src = Agent('SRC', db_refs = {'HGNC': '11283'})
ras = Agent('RAS', db_refs = {'FA': '03663'})
st1 = Phosphorylation(src, ras)
st2 = Phosphorylation(src, ras)
pa = Preassembler(hierarchies, stmts=[st1, st2])
pa.combine_duplicates()
assert len(pa.unique_stmts) == 1
def analyze(filename, plot=False):
# Load the file
results = load_file(filename)
# Put together a list of all statements
all_stmts = [stmt for paper_stmts in results.values()
for stmt in paper_stmts]
# Map grounding
logger.info('Mapping grounding...')
gmap = gm.GroundingMapper(gm.default_grounding_map)
map_stmts = gmap.map_agents(all_stmts)
map_stmts = gmap.rename_agents(map_stmts)
# Combine duplicates
logger.info('Removing duplicates...')
pa = Preassembler(hierarchies, map_stmts)
pa.combine_duplicates()
# Map GO IDs to genes and associated statements
logger.info('Building map from GO IDs to stmts')
go_gene_map = {}
go_name_map = {}
for stmt in pa.unique_stmts:
(bp_name, go, gene) = go_gene_pair(stmt)
if bp_name is None and go is None and gene is None:
continue
go_gene_list = go_gene_map.get(go, [])
go_gene_list.append((gene, stmt))
go_gene_map[go] = go_gene_list
go_name_set = go_name_map.get(go, set([]))
go_name_set.add(bp_name)
go_name_map[go] = go_name_set
# Iterate over all of the GO IDs and compare the annotated genes in GO
# to the ones from the given statements
go_stmt_map = {}
for ix, go_id in enumerate(go_gene_map.keys()):
logger.info('Getting genes for %s (%s) from GO (%d of %d)' %
(go_id, ','.join(list(go_name_map[go_id])),
ix+1, len(go_gene_map.keys())))
genes_from_go = get_genes_for_go_id(go_id)
gene_stmt_list = go_gene_map[go_id]
in_go = []
not_in_go = []
for (gene, stmt) in gene_stmt_list:
if gene in genes_from_go:
in_go.append(stmt)
else:
not_in_go.append(stmt)
go_stmt_map[go_id] = {'names': list(go_name_map[go_id]),
'in_go': in_go, 'not_in_go': not_in_go}
with open('go_stmt_map.pkl', 'wb') as f:
pickle.dump(go_stmt_map, f, protocol=2)
if plot:
plot_stmt_counts(go_stmt_map, 'go_stmts.pdf')
def test_agent_text_storage():
A1 = Agent('A', db_refs={'TEXT': 'A'})
A2 = Agent('A', db_refs={'TEXT': 'alpha'})
B1 = Agent('B', db_refs={'TEXT': 'bag'})
B2 = Agent('B', db_refs={'TEXT': 'bug'})
C = Agent('C')
D = Agent('D')
inp = [
Complex([A1, B1], evidence=Evidence(text='A complex bag.')),
Complex([B2, A2], evidence=Evidence(text='bug complex alpha once.')),
Complex([B2, A2], evidence=Evidence(text='bug complex alpha again.')),
Complex([A1, C, B2], evidence=Evidence(text='A complex C bug.')),
Phosphorylation(A1, B1, evidence=Evidence(text='A phospo bags.')),
Phosphorylation(A2, B2, evidence=Evidence(text='alpha phospho bugs.')),
Conversion(D, [A1, B1], [C, D],
evidence=Evidence(text='D: A bag -> C D')),
Conversion(D, [B1, A2], [C, D],
evidence=Evidence(text='D: bag a -> C D')),
Conversion(D, [B2, A2], [D, C],
evidence=Evidence(text='D: bug a -> D C')),
Conversion(D, [B1, A1], [C, D],
evidence=Evidence(text='D: bag A -> C D')),
Conversion(D, [A1], [A1, C],
evidence=Evidence(text='D: A -> A C'))
]
pa = Preassembler(hierarchies, inp)
unq1 = pa.combine_duplicates()
assert len(unq1) == 5, len(unq1)
assert all([len(ev.annotations['prior_uuids']) == 1
for s in unq1 for ev in s.evidence
if len(s.evidence) > 1]),\
'There can only be one prior evidence per uuid at this stage.'
ev_uuid_dict = {ev.annotations['prior_uuids'][0]: ev.annotations['agents']
for s in unq1 for ev in s.evidence}
for s in inp:
raw_text = [ag.db_refs.get('TEXT')
for ag in s.agent_list(deep_sorted=True)]
assert raw_text == ev_uuid_dict[s.uuid]['raw_text'],\
str(raw_text) + '!=' + str(ev_uuid_dict[s.uuid]['raw_text'])
# Now run pa on the above corpus plus another statement.
inp2 = unq1 + [
Complex([A1, C, B1], evidence=Evidence(text='A complex C bag.'))
]
pa2 = Preassembler(hierarchies, inp2)
unq2 = pa2.combine_duplicates()
assert len(unq2) == 5, len(unq2)
old_ev_list = []
new_ev = None
for s in unq2:
for ev in s.evidence:
if ev.text == inp2[-1].evidence[0].text:
new_ev = ev
else:
old_ev_list.append(ev)
assert all([len(ev.annotations['prior_uuids']) == 2 for ev in old_ev_list])
assert new_ev
assert len(new_ev.annotations['prior_uuids']) == 1
def test_homodimer_refinement():
egfr = Agent('EGFR')
erbb = Agent('ERBB2')
st1 = Complex([erbb, erbb])
st2 = Complex([erbb, egfr])
pa = Preassembler(hierarchies, stmts=[st1, st2])
pa.combine_duplicates()
assert len(pa.unique_stmts) == 2
pa.combine_related()
assert len(pa.related_stmts) == 2
def test_duplicates_copy():
src = Agent('SRC', db_refs = {'HGNC': '11283'})
ras = Agent('RAS', db_refs = {'FA': '03663'})
st1 = Phosphorylation(src, ras, evidence=[Evidence(text='Text 1')])
st2 = Phosphorylation(src, ras, evidence=[Evidence(text='Text 2')])
stmts = [st1, st2]
pa = Preassembler(hierarchies, stmts=stmts)
pa.combine_duplicates()
assert len(pa.unique_stmts) == 1
assert len(stmts) == 2
assert len(stmts[0].evidence) == 1
assert len(stmts[1].evidence) == 1
def test_flatten_stmts():
st1 = Phosphorylation(Agent('MAP3K5'), Agent('RAF1'), 'S', '338')
st2 = Phosphorylation(None, Agent('RAF1'), 'S', '338')
st3 = Phosphorylation(None, Agent('RAF1'))
st4 = Phosphorylation(Agent('PAK1'), Agent('RAF1'), 'S', '338')
st5 = Phosphorylation(None, Agent('RAF1'), evidence=Evidence(text='foo'))
pa = Preassembler(hierarchies, stmts=[st1, st2, st3, st4, st5])
pa.combine_duplicates()
pa.combine_related()
assert len(pa.related_stmts) == 2
assert len(flatten_stmts(pa.unique_stmts)) == 4
assert len(flatten_stmts(pa.related_stmts)) == 4
def test_duplicates_copy():
src = Agent('SRC', db_refs={'HGNC': '11283'})
ras = Agent('RAS', db_refs={'FA': '03663'})
st1 = Phosphorylation(src, ras, evidence=[Evidence(text='Text 1')])
st2 = Phosphorylation(src, ras, evidence=[Evidence(text='Text 2')])
stmts = [st1, st2]
pa = Preassembler(bio_ontology, stmts=stmts)
pa.combine_duplicates()
assert len(pa.unique_stmts) == 1
assert len(stmts) == 2
assert len(stmts[0].evidence) == 1
assert len(stmts[1].evidence) == 1
def test_flatten_stmts():
st1 = Phosphorylation(Agent('MAP3K5'), Agent('RAF1'), 'S', '338')
st2 = Phosphorylation(None, Agent('RAF1'), 'S', '338')
st3 = Phosphorylation(None, Agent('RAF1'))
st4 = Phosphorylation(Agent('PAK1'), Agent('RAF1'), 'S', '338')
st5 = Phosphorylation(None, Agent('RAF1'), evidence=Evidence(text='foo'))
pa = Preassembler(hierarchies, stmts=[st1, st2, st3, st4, st5])
pa.combine_duplicates()
pa.combine_related()
assert (len(pa.related_stmts) == 2)
assert (len(flatten_stmts(pa.unique_stmts)) == 4)
assert (len(flatten_stmts(pa.related_stmts)) == 4)
def test_activation_refinement():
subj = Agent('alcohol', db_refs={'CHEBI': 'CHEBI:16236',
'HMDB': 'HMDB00108',
'PUBCHEM': '702',
'TEXT': 'alcohol'})
obj = Agent('endotoxin', db_refs={'TEXT': 'endotoxin'})
st1 = Inhibition(subj, obj)
st2 = Activation(subj, obj)
pa = Preassembler(hierarchies, stmts=[st1, st2])
pa.combine_duplicates()
assert len(pa.unique_stmts) == 2
pa.combine_related()
assert len(pa.related_stmts) == 2
def test_combine_evidence_exact_duplicates():
raf = Agent('RAF1')
mek = Agent('MEK1')
p1 = Phosphorylation(raf, mek, evidence=Evidence(text='foo'))
p2 = Phosphorylation(raf, mek, evidence=Evidence(text='bar'))
p3 = Phosphorylation(raf, mek, evidence=Evidence(text='bar'))
stmts = [p1, p2, p3]
pa = Preassembler(bio_ontology, stmts=stmts)
pa.combine_duplicates()
# The statements come out sorted by their matches_key
assert len(pa.unique_stmts) == 1
assert len(pa.unique_stmts[0].evidence) == 2
assert set(ev.text for ev in pa.unique_stmts[0].evidence) == \
set(['foo', 'bar'])
def test_combine_evidence_exact_duplicates_different_raw_text():
raf1 = Agent('RAF1', db_refs={'TEXT': 'Raf'})
raf2 = Agent('RAF1', db_refs={'TEXT': 'RAF'})
mek = Agent('MEK1')
p1 = Phosphorylation(raf1, mek, evidence=Evidence(text='foo'))
p2 = Phosphorylation(raf1, mek, evidence=Evidence(text='bar'))
p3 = Phosphorylation(raf2, mek, evidence=Evidence(text='bar'))
stmts = [p1, p2, p3]
pa = Preassembler(hierarchies, stmts=stmts)
pa.combine_duplicates()
# The statements come out sorted by their matches_key
assert len(pa.unique_stmts) == 1
assert len(pa.unique_stmts[0].evidence) == 3
assert set(ev.text for ev in pa.unique_stmts[0].evidence) == \
set(['foo', 'bar', 'bar'])
def test_duplicates_sorting():
mc = ModCondition('phosphorylation')
map2k1_1 = Agent('MAP2K1', mods=[mc])
mc1 = ModCondition('phosphorylation', 'serine', '218')
mc2 = ModCondition('phosphorylation', 'serine', '222')
mc3 = ModCondition('phosphorylation', 'serine', '298')
map2k1_2 = Agent('MAP2K1', mods=[mc1, mc2, mc3])
mapk3 = Agent('MAPK3')
st1 = Phosphorylation(map2k1_1, mapk3, position='218')
st2 = Phosphorylation(map2k1_2, mapk3)
st3 = Phosphorylation(map2k1_1, mapk3, position='218')
stmts = [st1, st2, st3]
pa = Preassembler(bio_ontology, stmts=stmts)
pa.combine_duplicates()
assert len(pa.unique_stmts) == 2
def test_event_assemble_location():
rainfall = Concept('rainfall')
loc1 = RefContext(name='x', db_refs={'GEOID': '1'})
loc2 = RefContext(name='x', db_refs={'GEOID': '2'})
ev1 = Event(rainfall, context=WorldContext(geo_location=loc1))
ev2 = Event(rainfall, context=WorldContext(geo_location=loc2))
pa = Preassembler(hierarchies=hierarchies, stmts=[ev1, ev2],
matches_fun=None)
unique_stmts = pa.combine_duplicates()
assert len(unique_stmts) == 1
pa = Preassembler(hierarchies=hierarchies, stmts=[ev1, ev2],
matches_fun=location_matches)
unique_stmts = pa.combine_duplicates()
assert len(unique_stmts) == 2
def test_association_refinement():
health = 'UN/entities/human/health'
food = 'UN/entities/human/food'
food_security = 'UN/entities/human/food/food_security'
eh = Event(Concept('health', db_refs={'UN': [(health, 1.0)]}))
ef = Event(Concept('food', db_refs={'UN': [(food, 1.0)]}))
efs = Event(Concept('food security', db_refs={'UN': [(food_security, 1.0)]}))
st1 = Association([eh, ef], evidence=[Evidence(source_api='eidos1')])
st2 = Association([ef, eh], evidence=[Evidence(source_api='eidos2')])
st3 = Association([eh, efs], evidence=[Evidence(source_api='eidos3')])
st4 = Association([ef, efs], evidence=[Evidence(source_api='eidos4')])
eidos_ont = os.path.join(os.path.dirname(os.path.abspath(__file__)),
'../sources/eidos/eidos_ontology.rdf')
hm = HierarchyManager(eidos_ont, True, True)
hierarchies = {'entity': hm}
pa = Preassembler(hierarchies, [st1, st2, st3, st4])
unique_stmts = pa.combine_duplicates() # debugging
assert len(unique_stmts) == 3
rel_stmts = pa.combine_related()
assert len(rel_stmts) == 2
eh_efs_stmt = [st for st in rel_stmts if (st.members[0].concept.name in
{'health', 'food security'} and st.members[1].concept.name
in {'health', 'food security'})][0]
assert len(eh_efs_stmt.supported_by) == 1
assert (eh_efs_stmt.supported_by[0].members[0].concept.name
in {'food', 'health'})
assert (eh_efs_stmt.supported_by[0].members[1].concept.name
in {'food', 'health'})
def test_activation_refinement():
subj = Agent('alcohol',
db_refs={
'CHEBI': 'CHEBI:16236',
'HMDB': 'HMDB00108',
'PUBCHEM': '702',
'TEXT': 'alcohol'
})
obj = Agent('endotoxin', db_refs={'TEXT': 'endotoxin'})
st1 = Inhibition(subj, obj)
st2 = Activation(subj, obj)
pa = Preassembler(bio_ontology, stmts=[st1, st2])
pa.combine_duplicates()
assert len(pa.unique_stmts) == 2
pa.combine_related()
assert len(pa.related_stmts) == 2
def test_association_refinement():
health = 'UN/entities/human/health'
food = 'UN/entities/human/food'
food_security = 'UN/entities/human/food/food_security'
eh = Event(Concept('health', db_refs={'UN': [(health, 1.0)]}))
ef = Event(Concept('food', db_refs={'UN': [(food, 1.0)]}))
efs = Event(
Concept('food security', db_refs={'UN': [(food_security, 1.0)]}))
st1 = Association([eh, ef], evidence=[Evidence(source_api='eidos1')])
st2 = Association([ef, eh], evidence=[Evidence(source_api='eidos2')])
st3 = Association([eh, efs], evidence=[Evidence(source_api='eidos3')])
st4 = Association([ef, efs], evidence=[Evidence(source_api='eidos4')])
eidos_ont = os.path.join(os.path.dirname(os.path.abspath(__file__)),
'../sources/eidos/eidos_ontology.rdf')
hm = HierarchyManager(eidos_ont, True, True)
hierarchies = {'entity': hm}
pa = Preassembler(hierarchies, [st1, st2, st3, st4])
unique_stmts = pa.combine_duplicates() # debugging
assert len(unique_stmts) == 3
rel_stmts = pa.combine_related()
assert len(rel_stmts) == 2
eh_efs_stmt = [
st for st in rel_stmts
if (st.members[0].concept.name in {'health', 'food security'}
and st.members[1].concept.name in {'health', 'food security'})
][0]
assert len(eh_efs_stmt.supported_by) == 1
assert (eh_efs_stmt.supported_by[0].members[0].concept.name
in {'food', 'health'})
assert (eh_efs_stmt.supported_by[0].members[1].concept.name
in {'food', 'health'})
def test_association_refinement():
unrelated = 'wm/concept/causal_factor/wild_food_sources'
parent = 'wm/concept/causal_factor/health_and_life'
child = 'wm/concept/causal_factor/health_and_life/' \
'living_condition/food_safety'
parent_event = Event(Concept('parent', db_refs={'WM': [(parent, 1.0)]}))
unrelated_event = \
Event(Concept('unrelated', db_refs={'WM': [(unrelated, 1.0)]}))
child_event = Event(Concept('child', db_refs={'WM': [(child, 1.0)]}))
st1 = Association([parent_event, unrelated_event],
evidence=[Evidence(source_api='eidos1')])
st2 = Association([unrelated_event, parent_event],
evidence=[Evidence(source_api='eidos2')])
st3 = Association([parent_event, child_event],
evidence=[Evidence(source_api='eidos3')])
st4 = Association([unrelated_event, child_event],
evidence=[Evidence(source_api='eidos4')])
pa = Preassembler(world_ontology, [st1, st2, st3, st4])
unique_stmts = pa.combine_duplicates()
assert len(unique_stmts) == 3
top_level_stmts = pa.combine_related()
assert len(top_level_stmts) == 2, top_level_stmts
names = {
tuple(sorted(e.concept.name for e in stmt.members)): stmt
for stmt in top_level_stmts
}
stmt = names[('child', 'unrelated')]
assert len(stmt.supported_by) == 1
assert {e.concept.name for e in stmt.supported_by[0].members} == \
{'parent', 'unrelated'}
def test_uppro_assembly():
ag1 = Agent('x', db_refs={'UP': 'P01019', 'UPPRO': 'PRO_0000032457'})
ag2 = Agent('y', db_refs={'UP': 'P01019', 'UPPRO': 'PRO_0000032458'})
assert ag1.get_grounding() == ('UPPRO', ag1.db_refs['UPPRO'])
assert ag2.get_grounding() == ('UPPRO', ag2.db_refs['UPPRO'])
stmt1 = Phosphorylation(None, ag1)
stmt2 = Phosphorylation(None, ag2)
assert stmt1.matches_key() != stmt2.matches_key()
pa = Preassembler(bio_ontology, [stmt1, stmt2])
unique_stmts = pa.combine_duplicates()
assert len(unique_stmts) == 2, unique_stmts
from indra.tools import assemble_corpus as ac
stmts = ac.map_grounding([stmt1, stmt2])
pa = Preassembler(bio_ontology, stmts)
unique_stmts = pa.combine_duplicates()
assert len(unique_stmts) == 2
def test_combine_evidence_exact_duplicates():
raf = Agent('RAF1')
mek = Agent('MEK1')
p1 = Phosphorylation(raf, mek,
evidence=Evidence(text='foo'))
p2 = Phosphorylation(raf, mek,
evidence=Evidence(text='bar'))
p3 = Phosphorylation(raf, mek,
evidence=Evidence(text='bar'))
stmts = [p1, p2, p3]
pa = Preassembler(hierarchies, stmts=stmts)
pa.combine_duplicates()
# The statements come out sorted by their matches_key
assert len(pa.unique_stmts) == 1
assert len(pa.unique_stmts[0].evidence) == 2
assert set(ev.text for ev in pa.unique_stmts[0].evidence) == \
set(['foo', 'bar'])
def test_duplicates_sorting():
mc = ModCondition('phosphorylation')
map2k1_1 = Agent('MAP2K1', mods=[mc])
mc1 = ModCondition('phosphorylation', 'serine', '218')
mc2 = ModCondition('phosphorylation', 'serine', '222')
mc3 = ModCondition('phosphorylation', 'serine', '298')
map2k1_2 = Agent('MAP2K1', mods=[mc1, mc2, mc3])
mapk3 = Agent('MAPK3')
#ras = Agent('MAPK3', db_refs = {'FA': '03663'})
#nras = Agent('NRAS', db_refs = {'FA': '03663'})
st1 = Phosphorylation(map2k1_1, mapk3, position='218')
st2 = Phosphorylation(map2k1_2, mapk3)
st3 = Phosphorylation(map2k1_1, mapk3, position='218')
stmts = [st1, st2, st3]
pa = Preassembler(hierarchies, stmts=stmts)
pa.combine_duplicates()
assert len(pa.unique_stmts) == 2
def test_duplicates_sorting():
mc = ModCondition('phosphorylation')
map2k1_1 = Agent('MAP2K1', mods=[mc])
mc1 = ModCondition('phosphorylation', 'serine', '218')
mc2 = ModCondition('phosphorylation', 'serine', '222')
mc3 = ModCondition('phosphorylation', 'serine', '298')
map2k1_2 = Agent('MAP2K1', mods=[mc1, mc2, mc3])
mapk3 = Agent('MAPK3')
#ras = Agent('MAPK3', db_refs = {'FA': '03663'})
#nras = Agent('NRAS', db_refs = {'FA': '03663'})
st1 = Phosphorylation(map2k1_1, mapk3, position='218')
st2 = Phosphorylation(map2k1_2, mapk3)
st3 = Phosphorylation(map2k1_1, mapk3, position='218')
stmts = [st1, st2, st3]
pa = Preassembler(hierarchies, stmts=stmts)
pa.combine_duplicates()
assert len(pa.unique_stmts) == 2
def test_agent_coordinates():
path = os.path.join(os.path.dirname(os.path.abspath(__file__)),
'reach_coordinates.json')
stmts = reach.process_json_file(path).statements
pa = Preassembler(bio_ontology, stmts)
unique_stmt = pa.combine_duplicates()[0]
agent_annots = [ev.annotations['agents'] for ev in unique_stmt.evidence]
assert all(a['raw_text'] == ['MEK1', 'ERK2'] for a in agent_annots)
assert {tuple(a['coords'])
for a in agent_annots} == {((21, 25), (0, 4)), ((0, 4), (15, 19))}
def test_grounding_aggregation():
braf1 = Agent('BRAF', db_refs={'TEXT': 'braf', 'HGNC': '1097'})
braf2 = Agent('BRAF', db_refs={'TEXT': 'BRAF'})
braf3 = Agent('BRAF', db_refs={'TEXT': 'Braf', 'UP': 'P15056'})
st1 = Phosphorylation(None, braf1)
st2 = Phosphorylation(None, braf2)
st3 = Phosphorylation(None, braf3)
pa = Preassembler(hierarchies, stmts=[st1, st2, st3])
unique_stmts = pa.combine_duplicates()
assert len(unique_stmts) == 3
def test_grounding_aggregation():
braf1 = Agent('BRAF', db_refs={'TEXT': 'braf', 'HGNC': '1097'})
braf2 = Agent('BRAF', db_refs={'TEXT': 'BRAF'})
braf3 = Agent('BRAF', db_refs={'TEXT': 'Braf', 'UP': 'P15056'})
st1 = Phosphorylation(None, braf1)
st2 = Phosphorylation(None, braf2)
st3 = Phosphorylation(None, braf3)
pa = Preassembler(hierarchies, stmts=[st1, st2, st3])
unique_stmts = pa.combine_duplicates()
assert len(unique_stmts) == 3
def test_grounding_aggregation_complex():
mek = Agent('MEK')
braf1 = Agent('BRAF', db_refs={'TEXT': 'braf', 'HGNC': '1097'})
braf2 = Agent('BRAF', db_refs={'TEXT': 'BRAF', 'dummy': 'dummy'})
braf3 = Agent('BRAF', db_refs={'TEXT': 'Braf', 'UP': 'P15056'})
st1 = Complex([mek, braf1])
st2 = Complex([braf2, mek])
st3 = Complex([mek, braf3])
pa = Preassembler(hierarchies, stmts=[st1, st2, st3])
unique_stmts = pa.combine_duplicates()
assert len(unique_stmts) == 3
def test_grounding_aggregation_complex():
mek = Agent('MEK')
braf1 = Agent('BRAF', db_refs={'TEXT': 'braf', 'HGNC': '1097'})
braf2 = Agent('BRAF', db_refs={'TEXT': 'BRAF', 'dummy': 'dummy'})
braf3 = Agent('BRAF', db_refs={'TEXT': 'Braf', 'UP': 'P15056'})
st1 = Complex([mek, braf1])
st2 = Complex([braf2, mek])
st3 = Complex([mek, braf3])
pa = Preassembler(bio_ontology, stmts=[st1, st2, st3])
unique_stmts = pa.combine_duplicates()
assert len(unique_stmts) == 3, unique_stmts
def test_agent_coordinates():
path = os.path.join(os.path.dirname(os.path.abspath(__file__)),
'reach_coordinates.json')
stmts = reach.process_json_file(path).statements
pa = Preassembler(hierarchies, stmts)
unique_stmt = pa.combine_duplicates()[0]
evidence_list = unique_stmt.evidence
agent_annots = [ev.annotations['agents'] for ev in unique_stmt.evidence]
assert all(a['raw_text'] == ['MEK1', 'ERK2'] for a in agent_annots)
assert {tuple(a['coords']) for a in agent_annots} == {((21, 25), (0, 4)),
((0, 4), (15, 19))}
def test_preassemble_related_complex():
ras = Agent('RAS', db_refs={'FPLX': 'RAS'})
kras = Agent('KRAS', db_refs={'HGNC': '6407'})
hras = Agent('HRAS', db_refs={'HGNC': '5173'})
st1 = Complex([kras, hras])
st2 = Complex([kras, ras])
st3 = Complex([hras, kras])
st4 = Complex([ras, kras])
pa = Preassembler(hierarchies, [st1, st2, st3, st4])
uniq = pa.combine_duplicates()
assert len(uniq) == 2
top = pa.combine_related()
assert len(top) == 1
def test_preassemble_related_complex():
ras = Agent('RAS', db_refs={'FPLX': 'RAS'})
kras = Agent('KRAS', db_refs={'HGNC': '6407'})
hras = Agent('HRAS', db_refs={'HGNC': '5173'})
st1 = Complex([kras, hras])
st2 = Complex([kras, ras])
st3 = Complex([hras, kras])
st4 = Complex([ras, kras])
pa = Preassembler(bio_ontology, [st1, st2, st3, st4])
uniq = pa.combine_duplicates()
assert len(uniq) == 2
top = pa.combine_related()
assert len(top) == 1
def extract_phos():
with open(stmts_fname, 'rb') as fh:
model = pickle.load(fh)
stmts = []
for pmid, pmid_stmts in model.items():
for stmt in pmid_stmts:
if isinstance(stmt, Phosphorylation):
stmts.append(stmt)
logger.info('%d phosphorylations in RAS Machine' % len(stmts))
stmts = [s for s in stmts if s.enz is not None]
logger.info('%d phosphorylations with enzyme in RAS Machine' % len(stmts))
stmts_grounded = filter_grounded(stmts)
logger.info('%d grounded phosphorylations in RAS Machine' %
len(stmts_grounded))
stmts_enzkinase = filter_enzkinase(stmts_grounded)
logger.info('%d phosphorylations with kinase enzyme in RAS Machine' %
len(stmts_enzkinase))
sm = SiteMapper(default_site_map)
stmts_valid, _ = sm.map_sites(stmts_enzkinase)
logger.info('%d valid-sequence phosphorylations in RAS Machine' %
len(stmts_valid))
pa = Preassembler(hierarchies, stmts_valid)
stmts_unique = pa.combine_duplicates()
logger.info('%d unique phosphorylations in RAS Machine' %
len(stmts_unique))
stmts_unique = pa.combine_related()
logger.info('%d top-level phosphorylations in RAS Machine' %
len(stmts_unique))
with open('mapped_unique_phos.pkl', 'wb') as fh:
pickle.dump(stmts_unique, fh, protocol=2)
# Filter RAS Machine statements for direct and not hypothesis
stmts = filter_direct(stmts_unique)
logger.info('%d direct phosphorylations in RAS Machine' % len(stmts))
stmts = filter_non_hypothesis(stmts)
logger.info('%d non-hypothesis phosphorylations in RAS Machine' %
len(stmts))
with open('filtered_phos.pkl', 'wb') as fh:
pickle.dump(stmts, fh, protocol=2)
return stmts
def test_influence_duplicate():
gov = 'wm/concept/causal_factor/social_and_political/government'
agr = 'wm/concept/causal_factor/agriculture/crop_production'
cgov = Event(Concept('government', db_refs={'WM': [(gov, 1.0)]}))
cagr = Event(Concept('agriculture', db_refs={'WM': [(agr, 1.0)]}))
print(cgov.matches_key())
stmt1 = Influence(cgov, cagr, evidence=[Evidence(source_api='eidos1')])
stmt2 = Influence(cagr, cgov, evidence=[Evidence(source_api='eidos2')])
stmt3 = Influence(cgov, cagr, evidence=[Evidence(source_api='eidos3')])
pa = Preassembler(world_ontology, [stmt1, stmt2, stmt3])
unique_stmts = pa.combine_duplicates()
unique_stmts = sorted(unique_stmts, key=lambda x: len(x.evidence))
assert len(unique_stmts) == 2
assert len(unique_stmts[0].evidence) == 1
assert len(unique_stmts[1].evidence) == 2, unique_stmts
sources = [e.source_api for e in unique_stmts[1].evidence]
assert set(sources) == {'eidos1', 'eidos3'}
def run_preassembly(statements, hierarchies):
print('%d total statements' % len(statements))
# Filter to grounded only
statements = ac.filter_grounded_only(statements, score_threshold=0.4)
# Make a Preassembler with the Eidos and TRIPS ontology
pa = Preassembler(hierarchies, statements)
# Make a BeliefEngine and run combine duplicates
be = BeliefEngine()
unique_stmts = pa.combine_duplicates()
print('%d unique statements' % len(unique_stmts))
be.set_prior_probs(unique_stmts)
# Run combine related
related_stmts = pa.combine_related(return_toplevel=False)
be.set_hierarchy_probs(related_stmts)
# Filter to top-level Statements
top_stmts = ac.filter_top_level(related_stmts)
print('%d top-level statements' % len(top_stmts))
return top_stmts
def run_preassembly(statements, hierarchies):
print('%d total statements' % len(statements))
# Filter to grounded only
statements = map_onto(statements)
ac.dump_statements(statements, 'pi_mtg_demo_unfiltered.pkl')
statements = ac.filter_grounded_only(statements, score_threshold=0.7)
#statements = ac.filter_by_db_refs(statements, 'UN',
# ['conflict', 'food_security', 'precipitation'], policy='one',
# match_suffix=True)
statements = ac.filter_by_db_refs(
statements,
'UN', [
'conflict', 'food_security', 'flooding', 'food_production',
'human_migration', 'drought', 'food_availability', 'market',
'food_insecurity'
],
policy='all',
match_suffix=True)
assume_polarity(statements)
statements = filter_has_polarity(statements)
# Make a Preassembler with the Eidos and TRIPS ontology
pa = Preassembler(hierarchies, statements)
# Make a BeliefEngine and run combine duplicates
be = BeliefEngine()
unique_stmts = pa.combine_duplicates()
print('%d unique statements' % len(unique_stmts))
be.set_prior_probs(unique_stmts)
# Run combine related
related_stmts = pa.combine_related(return_toplevel=False)
be.set_hierarchy_probs(related_stmts)
#related_stmts = ac.filter_belief(related_stmts, 0.8)
# Filter to top-level Statements
top_stmts = ac.filter_top_level(related_stmts)
pa.stmts = top_stmts
print('%d top-level statements' % len(top_stmts))
conflicts = pa.find_contradicts()
top_stmts = remove_contradicts(top_stmts, conflicts)
ac.dump_statements(top_stmts, 'pi_mtg_demo.pkl')
return top_stmts
def extract_phos():
with open(stmts_fname, 'rb') as fh:
model = pickle.load(fh)
stmts = []
for pmid, pmid_stmts in model.items():
for stmt in pmid_stmts:
if isinstance(stmt, Phosphorylation):
stmts.append(stmt)
logger.info('%d phosphorylations in RAS Machine' % len(stmts))
stmts = [s for s in stmts if s.enz is not None]
logger.info('%d phosphorylations with enzyme in RAS Machine' % len(stmts))
stmts_grounded = filter_grounded(stmts)
logger.info('%d grounded phosphorylations in RAS Machine' % len(stmts_grounded))
stmts_enzkinase = filter_enzkinase(stmts_grounded)
logger.info('%d phosphorylations with kinase enzyme in RAS Machine' % len(stmts_enzkinase))
sm = SiteMapper(default_site_map)
stmts_valid, _ = sm.map_sites(stmts_enzkinase)
logger.info('%d valid-sequence phosphorylations in RAS Machine' % len(stmts_valid))
pa = Preassembler(hierarchies, stmts_valid)
stmts_unique = pa.combine_duplicates()
logger.info('%d unique phosphorylations in RAS Machine' % len(stmts_unique))
stmts_unique = pa.combine_related()
logger.info('%d top-level phosphorylations in RAS Machine' % len(stmts_unique))
with open('mapped_unique_phos.pkl', 'wb') as fh:
pickle.dump(stmts_unique, fh, protocol=2)
# Filter RAS Machine statements for direct and not hypothesis
stmts = filter_direct(stmts_unique)
logger.info('%d direct phosphorylations in RAS Machine' % len(stmts))
stmts = filter_non_hypothesis(stmts)
logger.info('%d non-hypothesis phosphorylations in RAS Machine' % len(stmts))
with open('filtered_phos.pkl', 'wb') as fh:
pickle.dump(stmts, fh, protocol=2)
return stmts
def test_influence_duplicate():
gov = 'UN/entities/human/government/government_entity'
agr = 'UN/entities/natural/crop_technology'
cgov = Event(Concept('government', db_refs={'UN': [(gov, 1.0)]}))
cagr = Event(Concept('agriculture', db_refs={'UN': [(agr, 1.0)]}))
stmt1 = Influence(cgov, cagr, evidence=[Evidence(source_api='eidos1')])
stmt2 = Influence(cagr, cgov, evidence=[Evidence(source_api='eidos2')])
stmt3 = Influence(cgov, cagr, evidence=[Evidence(source_api='eidos3')])
eidos_ont = os.path.join(os.path.dirname(os.path.abspath(__file__)),
'../sources/eidos/eidos_ontology.rdf')
hm = HierarchyManager(eidos_ont, True, True)
hierarchies = {'entity': hm}
pa = Preassembler(hierarchies, [stmt1, stmt2, stmt3])
unique_stmts = pa.combine_duplicates()
assert len(unique_stmts) == 2
assert len(unique_stmts[0].evidence) == 2
assert len(unique_stmts[1].evidence) == 1
sources = [e.source_api for e in unique_stmts[0].evidence]
assert set(sources) == set(['eidos1', 'eidos3'])
def test_influence_duplicate():
gov = 'UN/entities/human/government/government_entity'
agr = 'UN/entities/natural/crop_technology'
cgov = Event(Concept('government', db_refs={'UN': [(gov, 1.0)]}))
cagr = Event(Concept('agriculture', db_refs={'UN': [(agr, 1.0)]}))
stmt1 = Influence(cgov, cagr, evidence=[Evidence(source_api='eidos1')])
stmt2 = Influence(cagr, cgov, evidence=[Evidence(source_api='eidos2')])
stmt3 = Influence(cgov, cagr, evidence=[Evidence(source_api='eidos3')])
eidos_ont = os.path.join(os.path.dirname(os.path.abspath(__file__)),
'../sources/eidos/eidos_ontology.rdf')
hm = HierarchyManager(eidos_ont, True, True)
hierarchies = {'entity': hm}
pa = Preassembler(hierarchies, [stmt1, stmt2, stmt3])
unique_stmts = pa.combine_duplicates()
assert len(unique_stmts) == 2
assert len(unique_stmts[0].evidence) == 2
assert len(unique_stmts[1].evidence) == 1
sources = [e.source_api for e in unique_stmts[0].evidence]
assert set(sources) == set(['eidos1', 'eidos3'])
def test_association_duplicate():
ev1 = Event(Concept('a'))
ev2 = Event(Concept('b'))
ev3 = Event(Concept('c'))
# Order of members does not matter
st1 = Association([ev1, ev2], evidence=[Evidence(source_api='eidos1')])
st2 = Association([ev1, ev3], evidence=[Evidence(source_api='eidos2')])
st3 = Association([ev2, ev1], evidence=[Evidence(source_api='eidos3')])
st4 = Association([ev2, ev3], evidence=[Evidence(source_api='eidos4')])
st5 = Association([ev2, ev3], evidence=[Evidence(source_api='eidos5')])
eidos_ont = os.path.join(os.path.dirname(os.path.abspath(__file__)),
'../sources/eidos/eidos_ontology.rdf')
pa = Preassembler(world_ontology, [st1, st2, st3, st4, st5])
unique_stmts = pa.combine_duplicates()
assert len(unique_stmts) == 3
assert len(unique_stmts[0].evidence) == 2
assert len(unique_stmts[1].evidence) == 1
assert len(unique_stmts[2].evidence) == 2
sources = [e.source_api for e in unique_stmts[0].evidence]
assert set(sources) == {'eidos1', 'eidos3'}
def test_association_duplicate():
ev1 = Event(Concept('a'))
ev2 = Event(Concept('b'))
ev3 = Event(Concept('c'))
# Order of members does not matter
st1 = Association([ev1, ev2], evidence=[Evidence(source_api='eidos1')])
st2 = Association([ev1, ev3], evidence=[Evidence(source_api='eidos2')])
st3 = Association([ev2, ev1], evidence=[Evidence(source_api='eidos3')])
st4 = Association([ev2, ev3], evidence=[Evidence(source_api='eidos4')])
st5 = Association([ev2, ev3], evidence=[Evidence(source_api='eidos5')])
eidos_ont = os.path.join(os.path.dirname(os.path.abspath(__file__)),
'../sources/eidos/eidos_ontology.rdf')
hm = HierarchyManager(eidos_ont, True, True)
hierarchies = {'entity': hm}
pa = Preassembler(hierarchies, [st1, st2, st3, st4, st5])
unique_stmts = pa.combine_duplicates()
assert len(unique_stmts) == 3
assert len(unique_stmts[0].evidence) == 2
assert len(unique_stmts[1].evidence) == 1
assert len(unique_stmts[2].evidence) == 2
sources = [e.source_api for e in unique_stmts[0].evidence]
assert set(sources) == set(['eidos1', 'eidos3'])
def preassemble(self, filters=None):
"""Preassemble the Statements collected in the model.
Use INDRA's GroundingMapper, Preassembler and BeliefEngine
on the IncrementalModel and save the unique statements and
the top level statements in class attributes.
Currently the following filter options are implemented:
- grounding: require that all Agents in statements are grounded
- model_one: require that at least one Agent is in the incremental model
- model_all: require that all Agents are in the incremental model
- prior_one: require that at least one Agent is in the prior model
- prior_all: require that all Agents are in the prior model
Note that model_one -> prior_all are increasingly more restrictive
options.
Parameters
----------
filters : Optional[list[str]]
A list of filter options to apply when choosing the statements.
See description above for more details. Default: None
"""
stmts = self.get_statements()
logger.info("%d raw Statements in total" % len(stmts))
# Fix grounding
logger.info("Running grounding map")
twg = gm.agent_texts_with_grounding(stmts)
prot_map = gm.protein_map_from_twg(twg)
gm.default_grounding_map.update(prot_map)
gmap = gm.GroundingMapper(gm.default_grounding_map)
stmts = gmap.map_agents(stmts, do_rename=True)
logger.info("%d Statements after grounding map" % len(stmts))
# Fix sites
sm = SiteMapper(default_site_map)
stmts, _ = sm.map_sites(stmts)
logger.info("%d Statements with valid sequence" % len(stmts))
if filters:
if "grounding" in filters:
# Filter out ungrounded statements
logger.info("Running grounding filter")
stmts = self._relevance_filter(stmts, ["grounding"])
logger.info("%s Statements after filter" % len(stmts))
if "human_only" in filters:
# Filter out non-human proteins
logger.info("Running non-human protein filter")
stmts = self._relevance_filter(stmts, ["human_only"])
logger.info("%s Statements after filter" % len(stmts))
for rel_key in ("prior_one", "model_one", "prior_all", "model_all"):
if rel_key in filters:
logger.info("Running %s relevance filter" % rel_key)
stmts = self._relevance_filter(stmts, [rel_key])
logger.info("%s Statements after filter" % len(stmts))
# Combine duplicates
logger.info("Preassembling %d Statements" % len(stmts))
pa = Preassembler(hierarchies, stmts)
self.unique_stmts = pa.combine_duplicates()
logger.info("%d unique Statements" % len(self.unique_stmts))
# Run BeliefEngine on unique statements
be = BeliefEngine()
be.set_prior_probs(self.unique_stmts)
# Build statement hierarchy
self.unique_stmts = pa.combine_related(return_toplevel=False)
self.toplevel_stmts = [st for st in self.unique_stmts if not st.supports]
logger.info("%d top-level Statements" % len(self.toplevel_stmts))
# Run BeliefEngine on hierarchy
be.set_hierarchy_probs(self.unique_stmts)
def analyze(filename):
results = load_file(filename)
all_stmts = [stmt for paper_stmts in results.values()
for stmt in paper_stmts]
# Map grounding
logger.info('Mapping grounding...')
gmap = gm.GroundingMapper(gm.default_grounding_map)
map_stmts = gmap.map_agents(all_stmts)
map_stmts = gmap.rename_agents(map_stmts)
# Combine duplicates
logger.info('Removing duplicates...')
pa = Preassembler(hierarchies, map_stmts)
pa.combine_duplicates()
# Get complexes
complexes = [s for s in pa.unique_stmts if isinstance(s, Complex)]
# Get HGNC grounding
protein_complexes = [s for s in complexes
if all([True if 'HGNC' in ag.db_refs.keys()
else False
for ag in s.agent_list()])]
logger.info('Mapping gene IDs to gene symbols')
gene_ids = list(set([ag.db_refs['HGNC'] for stmt in protein_complexes
for ag in stmt.members]))
genes = [hgnc_client.get_hgnc_name(id) for id in gene_ids]
# Get complexes from BioGrid and combine duplicates
num_genes_per_query = 50
start_indices = range(0, len(genes), num_genes_per_query)
end_indices = [i + num_genes_per_query
if i + num_genes_per_query < len(genes) else len(genes)
for i in start_indices]
bg_complexes = []
for i in range(len(start_indices)):
logger.info("Querying biogrid for %s" %
str(genes[start_indices[i]:end_indices[i]]))
bg_complexes += (bg.get_statements(
genes[start_indices[i]:end_indices[i]]))
# Filter out Biogrid statements not involving genes in the gene list
# (this will make duplicate removal more efficient
bg_filt = []
for stmt in bg_complexes:
if stmt.members[0].name in genes and \
stmt.members[1].name in genes:
bg_filt.append(stmt)
# Might as well free up some memory
del bg_complexes
logger.info("Combining duplicates with biogrid...")
pa = Preassembler(hierarchies, bg_filt + protein_complexes)
pa.combine_duplicates()
indra_only = []
bg_only = []
indra_and_bg = []
for stmt in pa.unique_stmts:
evidence_source_list = set([])
for e in stmt.evidence:
evidence_source_list.add(e.source_api)
if 'reach' in evidence_source_list and \
'biogrid' in evidence_source_list:
indra_and_bg.append(stmt)
elif 'reach' in evidence_source_list and \
'biogrid' not in evidence_source_list:
indra_only.append(stmt)
elif 'reach' not in evidence_source_list and \
'biogrid' in evidence_source_list:
bg_only.append(stmt)
rows = []
for stmt in indra_only:
rows.append([stmt.members[0].name, stmt.members[1].name,
str(len(stmt.evidence))])
write_unicode_csv('unmatched_complexes.tsv', rows, delimiter='\t')
return {'indra_only': indra_only,
'bg_only': bg_only,
'indra_and_bg': indra_and_bg}
help='Basename for output files.',
required=True)
args = parser.parse_args()
# Load statements and filter to grounded only
stmts = ac.load_statements(args.input_file)
stmts = ac.filter_grounded_only(stmts)
# Sort by TextRefs
by_tr, no_tr = stmts_by_text_refs(stmts)
# Combine duplicates in each statement list
by_tr_pa = {}
for tr, stmt_list in by_tr.items():
pa = Preassembler(bio_ontology, stmt_list)
uniq_stmts = pa.combine_duplicates()
by_tr_pa[tr] = uniq_stmts
# Filter to MESH term for "Coronavirus"
mesh_id = 'D017934'
mesh_children = get_mesh_children(mesh_id)
# Include parent term in list
mesh_children.append(mesh_id)
mesh_pmids = get_pmids_for_mesh_terms(mesh_children) # SLOW!
# Get the subset of statements from these PMIDs
mesh_stmts = filter_stmts_to_pmids(by_tr_pa, mesh_pmids)
# Sort text refs by numbers of statements
all_stmts_sorted = sort_by_uniq_stmts(by_tr_pa)
mesh_stmts_sorted = sort_by_uniq_stmts(mesh_stmts)
def run_preassembly(self, stmts, print_summary=True):
"""Run complete preassembly procedure on the given statements.
Results are returned as a dict and stored in the attribute
:py:attr:`results`. They are also saved in the pickle file
`<basename>_results.pkl`.
Parameters
----------
stmts : list of :py:class:`indra.statements.Statement`
Statements to preassemble.
print_summary : bool
If True (default), prints a summary of the preassembly process to
the console.
Returns
-------
dict
A dict containing the following entries:
- `raw`: the starting set of statements before preassembly.
- `duplicates1`: statements after initial de-duplication.
- `valid`: statements found to have valid modification sites.
- `mapped`: mapped statements (list of
:py:class:`indra.preassembler.sitemapper.MappedStatement`).
- `mapped_stmts`: combined list of valid statements and statements
after mapping.
- `duplicates2`: statements resulting from de-duplication of the
statements in `mapped_stmts`.
- `related2`: top-level statements after combining the statements
in `duplicates2`.
"""
# First round of preassembly: remove duplicates before sitemapping
pa1 = Preassembler(hierarchies, stmts)
logger.info("Combining duplicates")
pa1.combine_duplicates()
# Map sites
logger.info("Mapping sites")
(valid, mapped) = sm.map_sites(pa1.unique_stmts)
# Combine valid and successfully mapped statements into single list
correctly_mapped_stmts = []
for ms in mapped:
if all([
True if mm[1] is not None else False
for mm in ms.mapped_mods
]):
correctly_mapped_stmts.append(ms.mapped_stmt)
mapped_stmts = valid + correctly_mapped_stmts
# Second round of preassembly: de-duplicate and combine related
pa2 = Preassembler(hierarchies, mapped_stmts)
logger.info("Combining duplicates again")
pa2.combine_duplicates()
pa2.combine_related()
# Fill out the results dict
self.results = {}
self.results['raw'] = stmts
self.results['duplicates1'] = pa1.unique_stmts
self.results['valid'] = valid
self.results['mapped'] = mapped
self.results['mapped_stmts'] = mapped_stmts
self.results['duplicates2'] = pa2.unique_stmts
self.results['related2'] = pa2.related_stmts
# Print summary
if print_summary:
logger.info("\nStarting number of statements: %d" % len(stmts))
logger.info("After duplicate removal: %d" % len(pa1.unique_stmts))
logger.info("Unique statements with valid sites: %d" % len(valid))
logger.info("Unique statements with invalid sites: %d" %
len(mapped))
logger.info("After post-mapping duplicate removal: %d" %
len(pa2.unique_stmts))
logger.info("After combining related statements: %d" %
len(pa2.related_stmts))
# Save the results if we're caching
if self.basename is not None:
results_filename = '%s_results.pkl' % self.basename
with open(results_filename, 'wb') as f:
pickle.dump(self.results, f, protocol=2)
return self.results
def run_assembly(stmts, folder, pmcid):
indexcard_prefix = folder + '/index_cards/' + pmcid
otherout_prefix = folder + '/other_outputs/' + pmcid
# Filter for grounding
grounded_stmts = []
for st in stmts:
if all([is_protein_or_chemical(a) for a in st.agent_list()]):
grounded_stmts.append(st)
# Instantiate the Preassembler
pa = Preassembler(eh, mh)
pa.add_statements(grounded_stmts)
print '%d statements collected in total.' % len(pa.stmts)
unique_stmts = pa.combine_duplicates()
print '%d statements after combining duplicates.' % len(unique_stmts)
ml = MechLinker(unique_stmts)
ml.link_statements()
pa = Preassembler(eh, mh, ml.statements)
pa.combine_duplicates()
related_stmts = pa.combine_related()
print '%d statements after combining related.' % len(related_stmts)
with open(otherout_prefix + '.pkl', 'wb') as fh:
pickle.dump(related_stmts, fh)
flattened_evidence_stmts = flatten_evidence(related_stmts)
card_counter = 1
card_lim = float('inf')
top_stmts = []
for st in sorted(flattened_evidence_stmts,
key=lambda x: len(x.evidence), reverse=True):
print len(st.evidence), st
if is_background_knowledge(st):
print 'This statement is background knowledge - skipping.'
continue
# Assemble IndexCards
ia = IndexCardAssembler([st])
ia.make_model()
if ia.cards:
ia.save_model(indexcard_prefix + '-%d.json' % card_counter)
card_counter += 1
top_stmts.append(st)
if card_counter > card_lim:
break
ea = EnglishAssembler(top_stmts)
print '======================='
print ea.make_model()
print '======================='
# Print the statement graph
graph = render_stmt_graph(related_stmts)
graph.draw(otherout_prefix + '_graph.pdf', prog='dot')
# Print statement diagnostics
print_stmts(pa.stmts, otherout_prefix + '_statements.tsv')
print_stmts(related_stmts, otherout_prefix + '_related_statements.tsv')
pya = PysbAssembler()
pya.add_statements(related_stmts)
model = pya.make_model()
print 'PySB model has %d monomers and %d rules' %\
(len(model.monomers), len(model.rules))
def run_preassembly(self, stmts, print_summary=True):
"""Run complete preassembly procedure on the given statements.
Results are returned as a dict and stored in the attribute
:py:attr:`results`. They are also saved in the pickle file
`<basename>_results.pkl`.
Parameters
----------
stmts : list of :py:class:`indra.statements.Statement`
Statements to preassemble.
print_summary : bool
If True (default), prints a summary of the preassembly process to
the console.
Returns
-------
dict
A dict containing the following entries:
- `raw`: the starting set of statements before preassembly.
- `duplicates1`: statements after initial de-duplication.
- `valid`: statements found to have valid modification sites.
- `mapped`: mapped statements (list of
:py:class:`indra.preassembler.sitemapper.MappedStatement`).
- `mapped_stmts`: combined list of valid statements and statements
after mapping.
- `duplicates2`: statements resulting from de-duplication of the
statements in `mapped_stmts`.
- `related2`: top-level statements after combining the statements
in `duplicates2`.
"""
# First round of preassembly: remove duplicates before sitemapping
pa1 = Preassembler(hierarchies, stmts)
logger.info("Combining duplicates")
pa1.combine_duplicates()
# Map sites
logger.info("Mapping sites")
(valid, mapped) = sm.map_sites(pa1.unique_stmts)
# Combine valid and successfully mapped statements into single list
correctly_mapped_stmts = []
for ms in mapped:
if all([True if mm[1] is not None else False
for mm in ms.mapped_mods]):
correctly_mapped_stmts.append(ms.mapped_stmt)
mapped_stmts = valid + correctly_mapped_stmts
# Second round of preassembly: de-duplicate and combine related
pa2 = Preassembler(hierarchies, mapped_stmts)
logger.info("Combining duplicates again")
pa2.combine_duplicates()
pa2.combine_related()
# Fill out the results dict
self.results = {}
self.results['raw'] = stmts
self.results['duplicates1'] = pa1.unique_stmts
self.results['valid'] = valid
self.results['mapped'] = mapped
self.results['mapped_stmts'] = mapped_stmts
self.results['duplicates2'] = pa2.unique_stmts
self.results['related2'] = pa2.related_stmts
# Print summary
if print_summary:
logger.info("\nStarting number of statements: %d" % len(stmts))
logger.info("After duplicate removal: %d" % len(pa1.unique_stmts))
logger.info("Unique statements with valid sites: %d" % len(valid))
logger.info("Unique statements with invalid sites: %d" %
len(mapped))
logger.info("After post-mapping duplicate removal: %d" %
len(pa2.unique_stmts))
logger.info("After combining related statements: %d" %
len(pa2.related_stmts))
# Save the results if we're caching
if self.basename is not None:
results_filename = '%s_results.pkl' % self.basename
with open(results_filename, 'wb') as f:
pickle.dump(self.results, f, protocol=2)
return self.results
if __name__ == '__main__':
# Load the statements
if len(sys.argv) < 2:
print("Usage: %s reach_stmts_file" % sys.argv[0])
sys.exit()
results = load_file(sys.argv[1])
all_stmts = [stmt for paper_stmts in results.values()
for stmt in paper_stmts]
report_stmt_counts(results, plot_prefix='raw')
report_grounding(all_stmts, plot_prefix='raw')
report_stmt_types(all_stmts, plot_prefix='raw')
report_stmt_participants(all_stmts)
# Map grounding
logger.info('Mapping grounding...')
gmap = gm.GroundingMapper(gm.default_grounding_map)
map_stmts = gmap.map_agents(all_stmts)
report_grounding(map_stmts, plot_prefix='preassembled')
# Combine duplicates
logger.info('Removing duplicates...')
pa = Preassembler(hierarchies, map_stmts)
pa.combine_duplicates()
report_evidence_distribution(pa.unique_stmts, plot_prefix='preassembled')
def run_assembly(stmts, folder, pmcid, background_assertions=None):
'''Run assembly on a list of statements, for a given PMCID.'''
# Folder for index card output (scored submission)
indexcard_prefix = folder + '/index_cards/' + pmcid
# Folder for other outputs (for analysis, debugging)
otherout_prefix = folder + '/other_outputs/' + pmcid
# Do grounding mapping here
# Load the TRIPS-specific grounding map and add to the default
# (REACH-oriented) grounding map:
trips_gm = load_grounding_map('trips_grounding_map.csv')
default_grounding_map.update(trips_gm)
gm = GroundingMapper(default_grounding_map)
mapped_agent_stmts = gm.map_agents(stmts)
renamed_agent_stmts = gm.rename_agents(mapped_agent_stmts)
# Filter for grounding
grounded_stmts = []
for st in renamed_agent_stmts:
if all([is_protein_or_chemical(a) for a in st.agent_list()]):
grounded_stmts.append(st)
# Instantiate the Preassembler
pa = Preassembler(hierarchies)
pa.add_statements(grounded_stmts)
print('== %s ====================' % pmcid)
print('%d statements collected in total.' % len(pa.stmts))
# Combine duplicates
unique_stmts = pa.combine_duplicates()
print('%d statements after combining duplicates.' % len(unique_stmts))
# Run BeliefEngine on unique statements
epe = BeliefEngine()
epe.set_prior_probs(pa.unique_stmts)
# Build statement hierarchy
related_stmts = pa.combine_related()
# Run BeliefEngine on hierarchy
epe.set_hierarchy_probs(related_stmts)
print('%d statements after combining related.' % len(related_stmts))
# Instantiate the mechanism linker
ml = MechLinker(related_stmts)
# Link statements
linked_stmts = ml.link_statements()
# Run BeliefEngine on linked statements
epe.set_linked_probs(linked_stmts)
# Print linked statements for debugging purposes
print('Linked\n=====')
for ls in linked_stmts:
print(ls.inferred_stmt.belief, ls.inferred_stmt)
print('=============')
# Combine all statements including linked ones
all_statements = ml.statements + [ls.inferred_stmt for ls in linked_stmts]
# Instantiate a new preassembler
pa = Preassembler(hierarchies, all_statements)
# Build hierarchy again
pa.combine_duplicates()
# Choose the top-level statements
related_stmts = pa.combine_related()
# Remove top-level statements that came only from the prior
if background_assertions is not None:
nonbg_stmts = [
stmt for stmt in related_stmts if stmt not in background_assertions
]
else:
nonbg_stmts = related_stmts
# Dump top-level statements in a pickle
with open(otherout_prefix + '.pkl', 'wb') as fh:
pickle.dump(nonbg_stmts, fh, protocol=2)
# Flatten evidence for statements
flattened_evidence_stmts = flatten_evidence(nonbg_stmts)
# Start a card counter
card_counter = 1
# We don't limit the number of cards reported in this round
card_lim = float('inf')
top_stmts = []
###############################################
# The belief cutoff for statements
belief_cutoff = 0.3
###############################################
# Sort by amount of evidence
for st in sorted(flattened_evidence_stmts,
key=lambda x: x.belief,
reverse=True):
if st.belief >= belief_cutoff:
print(st.belief, st)
if st.belief < belief_cutoff:
print('SKIP', st.belief, st)
# If it's background knowledge, we skip the statement
if is_background_knowledge(st):
print('This statement is background knowledge - skipping.')
continue
# Assemble IndexCards
ia = IndexCardAssembler([st], pmc_override=pmcid)
ia.make_model()
# If the index card was actually made
# (not all statements can be assembled into index cards to
# this is often not the case)
if ia.cards:
# Save the index card json
ia.save_model(indexcard_prefix + '-%d.json' % card_counter)
card_counter += 1
top_stmts.append(st)
if card_counter > card_lim:
break
# Print the English-assembled model for debugging purposes
ea = EnglishAssembler(top_stmts)
print('=======================')
print(ea.make_model())
print('=======================')
# Print the statement graph
graph = render_stmt_graph(nonbg_stmts)
graph.draw(otherout_prefix + '_graph.pdf', prog='dot')
# Print statement diagnostics
print_stmts(pa.stmts, otherout_prefix + '_statements.tsv')
print_stmts(related_stmts, otherout_prefix + '_related_statements.tsv')
if args.date_range:
min_date_str, max_date_str = args.date_range.split(':')
if min_date_str:
min_date = datetime.strptime(min_date_str, '%Y%m%d%H%M%S')
clauses.add(db.RawStatements.create_date > min_date)
if max_date_str:
max_date = datetime.strptime(max_date_str, '%Y%m%d%H%M%S')
clauses.add(db.RawStatements.create_date < max_date)
all_stmts, results = load_stmts_from_db(clauses, db)
report_stmt_counts(results['reach'], plot_prefix='raw_reach')
report_stmt_counts(results['sparser'], plot_prefix='raw_sparser')
report_grounding(all_stmts, plot_prefix='raw')
report_stmt_types(all_stmts, plot_prefix='raw')
report_stmt_participants(all_stmts)
# Map grounding
logger.info('Mapping grounding...')
gmap = gm.GroundingMapper(gm.default_grounding_map)
map_stmts = gmap.map_agents(all_stmts)
report_grounding(map_stmts, plot_prefix='preassembled')
# Combine duplicates
logger.info('Removing duplicates...')
pa = Preassembler(hierarchies, map_stmts)
pa.combine_duplicates()
report_evidence_distribution(pa.unique_stmts, plot_prefix='preassembled')
def analyze(filename, plot=False):
# Load the file
results = load_file(filename)
# Put together a list of all statements
all_stmts = [
stmt for paper_stmts in results.values() for stmt in paper_stmts
]
# Map grounding
logger.info('Mapping grounding...')
gmap = gm.GroundingMapper(gm.default_grounding_map)
map_stmts = gmap.map_agents(all_stmts)
map_stmts = gmap.rename_agents(map_stmts)
# Combine duplicates
logger.info('Removing duplicates...')
pa = Preassembler(hierarchies, map_stmts)
pa.combine_duplicates()
# Map GO IDs to genes and associated statements
logger.info('Building map from GO IDs to stmts')
go_gene_map = {}
go_name_map = {}
for stmt in pa.unique_stmts:
(bp_name, go, gene) = go_gene_pair(stmt)
if bp_name is None and go is None and gene is None:
continue
go_gene_list = go_gene_map.get(go, [])
go_gene_list.append((gene, stmt))
go_gene_map[go] = go_gene_list
go_name_set = go_name_map.get(go, set([]))
go_name_set.add(bp_name)
go_name_map[go] = go_name_set
# Iterate over all of the GO IDs and compare the annotated genes in GO
# to the ones from the given statements
go_stmt_map = {}
for ix, go_id in enumerate(go_gene_map.keys()):
logger.info(
'Getting genes for %s (%s) from GO (%d of %d)' % (go_id, ','.join(
list(go_name_map[go_id])), ix + 1, len(go_gene_map.keys())))
genes_from_go = get_genes_for_go_id(go_id)
gene_stmt_list = go_gene_map[go_id]
in_go = []
not_in_go = []
for (gene, stmt) in gene_stmt_list:
if gene in genes_from_go:
in_go.append(stmt)
else:
not_in_go.append(stmt)
go_stmt_map[go_id] = {
'names': list(go_name_map[go_id]),
'in_go': in_go,
'not_in_go': not_in_go
}
with open('go_stmt_map.pkl', 'wb') as f:
pickle.dump(go_stmt_map, f, protocol=2)
if plot:
plot_stmt_counts(go_stmt_map, 'go_stmts.pdf')
for fn in fnames:
print '\n\n----------------------------'
print 'Processing %s...' % fn
xml_str = open(fn, 'rt').read()
tp = trips.process_xml(xml_str)
print 'Extracted events by type'
print '------------------------'
for k,v in tp.extracted_events.iteritems():
print k, len(v)
print '------------------------'
print '%s statements collected.' % len(tp.statements)
pa.add_statements(tp.statements)
print '----------------------------\n\n'
print '%d statements collected in total.' % len(pa.stmts)
duplicate_stmts = pa.combine_duplicates()
print '%d statements after combining duplicates.' % len(duplicate_stmts)
related_stmts = pa.combine_related()
print '%d statements after combining related.' % len(related_stmts)
# Print the statement graph
graph = render_stmt_graph(related_stmts)
graph.draw('trips_graph.pdf', prog='dot')
# Print statement diagnostics
print_stmts(pa.stmts, 'trips_statements.tsv')
print_stmts(related_stmts, 'trips_related_statements.tsv')
pya = PysbAssembler()
pya.add_statements(related_stmts)
model = pya.make_model()
def test_matches_key_fun():
from indra.statements import WorldContext, RefContext
def has_location(stmt):
if not stmt.context or not stmt.context.geo_location or \
not stmt.context.geo_location.db_refs.get('GEOID'):
return False
return True
def event_location_matches(stmt):
if isinstance(stmt, Event):
if not has_location(stmt):
context_key = None
else:
context_key = stmt.context.geo_location.db_refs['GEOID']
matches_key = str((stmt.concept.matches_key(), context_key))
else:
matches_key = stmt.matches_key()
return matches_key
def event_location_refinement(st1, st2, ontology, entities_refined):
if isinstance(st1, Event) and isinstance(st2, Event):
ref = st1.refinement_of(st2, ontology)
if not ref:
return False
if not has_location(st2):
return True
elif not has_location(st1) and has_location(st2):
return False
else:
return st1.context.geo_location.db_refs['GEOID'] == \
st2.context.geo_location.db_refs['GEOID']
context1 = WorldContext(
geo_location=RefContext('x', db_refs={'GEOID': '1'}))
context2 = WorldContext(
geo_location=RefContext('x', db_refs={'GEOID': '2'}))
health = 'wm/concept/causal_factor/health_and_life'
e1 = Event(Concept('health', db_refs={'WM': [(health, 1.0)]}),
context=context1,
evidence=Evidence(text='1', source_api='eidos'))
e2 = Event(Concept('health', db_refs={'WM': [(health, 1.0)]}),
context=context2,
evidence=Evidence(text='2', source_api='eidos'))
e3 = Event(Concept('health', db_refs={'WM': [(health, 1.0)]}),
context=context2,
evidence=Evidence(text='3', source_api='eidos'))
pa = Preassembler(world_ontology, [e1, e2, e3],
matches_fun=event_location_matches,
refinement_fun=event_location_refinement)
unique_stmts = pa.combine_duplicates()
assert len(unique_stmts) == 2, unique_stmts
from indra.tools.assemble_corpus import run_preassembly
stmts = run_preassembly([e1, e2, e3],
matches_fun=event_location_matches,
refinement_fun=event_location_refinement)
assert len(stmts) == 2, stmts
def run_assembly(stmts, folder, pmcid, background_assertions=None):
'''Run assembly on a list of statements, for a given PMCID.'''
# Folder for index card output (scored submission)
indexcard_prefix = folder + '/index_cards/' + pmcid
# Folder for other outputs (for analysis, debugging)
otherout_prefix = folder + '/other_outputs/' + pmcid
# Do grounding mapping here
# Load the TRIPS-specific grounding map and add to the default
# (REACH-oriented) grounding map:
trips_gm = load_grounding_map('trips_grounding_map.csv')
default_grounding_map.update(trips_gm)
gm = GroundingMapper(default_grounding_map)
mapped_agent_stmts = gm.map_agents(stmts)
renamed_agent_stmts = gm.rename_agents(mapped_agent_stmts)
# Filter for grounding
grounded_stmts = []
for st in renamed_agent_stmts:
if all([is_protein_or_chemical(a) for a in st.agent_list()]):
grounded_stmts.append(st)
# Instantiate the Preassembler
pa = Preassembler(hierarchies)
pa.add_statements(grounded_stmts)
print('== %s ====================' % pmcid)
print('%d statements collected in total.' % len(pa.stmts))
# Combine duplicates
unique_stmts = pa.combine_duplicates()
print('%d statements after combining duplicates.' % len(unique_stmts))
# Run BeliefEngine on unique statements
epe = BeliefEngine()
epe.set_prior_probs(pa.unique_stmts)
# Build statement hierarchy
related_stmts = pa.combine_related()
# Run BeliefEngine on hierarchy
epe.set_hierarchy_probs(related_stmts)
print('%d statements after combining related.' % len(related_stmts))
# Instantiate the mechanism linker
# Link statements
linked_stmts = MechLinker.infer_active_forms(related_stmts)
linked_stmts += MechLinker.infer_modifications(related_stmts)
linked_stmts += MechLinker.infer_activations(related_stmts)
# Run BeliefEngine on linked statements
epe.set_linked_probs(linked_stmts)
# Print linked statements for debugging purposes
print('Linked\n=====')
for ls in linked_stmts:
print(ls.inferred_stmt.belief, ls.inferred_stmt)
print('=============')
# Combine all statements including linked ones
all_statements = related_stmts + [ls.inferred_stmt for ls in linked_stmts]
# Instantiate a new preassembler
pa = Preassembler(hierarchies, all_statements)
# Build hierarchy again
pa.combine_duplicates()
# Choose the top-level statements
related_stmts = pa.combine_related()
# Remove top-level statements that came only from the prior
if background_assertions is not None:
nonbg_stmts = [stmt for stmt in related_stmts
if stmt not in background_assertions]
else:
nonbg_stmts = related_stmts
# Dump top-level statements in a pickle
with open(otherout_prefix + '.pkl', 'wb') as fh:
pickle.dump(nonbg_stmts, fh)
# Flatten evidence for statements
flattened_evidence_stmts = flatten_evidence(nonbg_stmts)
# Start a card counter
card_counter = 1
# We don't limit the number of cards reported in this round
card_lim = float('inf')
top_stmts = []
###############################################
# The belief cutoff for statements
belief_cutoff = 0.3
###############################################
# Sort by amount of evidence
for st in sorted(flattened_evidence_stmts,
key=lambda x: x.belief, reverse=True):
if st.belief >= belief_cutoff:
print(st.belief, st)
if st.belief < belief_cutoff:
print('SKIP', st.belief, st)
# If it's background knowledge, we skip the statement
if is_background_knowledge(st):
print('This statement is background knowledge - skipping.')
continue
# Assemble IndexCards
ia = IndexCardAssembler([st], pmc_override=pmcid)
ia.make_model()
# If the index card was actually made
# (not all statements can be assembled into index cards to
# this is often not the case)
if ia.cards:
# Save the index card json
ia.save_model(indexcard_prefix + '-%d.json' % card_counter)
card_counter += 1
top_stmts.append(st)
if card_counter > card_lim:
break
# Print the English-assembled model for debugging purposes
ea = EnglishAssembler(top_stmts)
print('=======================')
print(ea.make_model().encode('utf-8'))
print('=======================')
# Print the statement graph
graph = render_stmt_graph(nonbg_stmts)
graph.draw(otherout_prefix + '_graph.pdf', prog='dot')
# Print statement diagnostics
print_stmts(pa.stmts, otherout_prefix + '_statements.tsv')
print_stmts(related_stmts, otherout_prefix + '_related_statements.tsv')
