def test_pybel_neighborhood_query():
bp = bel.process_pybel_neighborhood(['TP63'],
network_type='graph_jsongz_url',
network_file=small_corpus_url)
assert bp.statements
for stmt in bp.statements:
assert_valid_statement(stmt)
assert all([s.evidence[0].context is not None for s in bp.statements])
assert all([
s.evidence[0].context.cell_line.name == 'MCF 10A'
for s in bp.statements
])
# Locate statement about epidermis development
stmt = [
st for st in bp.statements
if st.agent_list()[1].name == 'epidermis development'
][0]
assert repr(stmt.evidence[0].context) == str(stmt.evidence[0].context)
assert stmt.evidence[0].context == BioContext(
location=RefContext(name="Cytoplasm",
db_refs={'MESH': 'D003593'}),
cell_line=RefContext(name="MCF 10A",
db_refs={'EFO': '0001200'}),
cell_type=RefContext(name="keratinocyte",
db_refs={'CL': 'CL:0000312'}),
organ=RefContext(name="colon",
db_refs={'UBERON': 'UBERON:0001155'}),
disease=RefContext(name="cancer",
db_refs={'DOID': 'DOID:162'}),
species=RefContext(name="Rattus norvegicus",
db_refs={'TAXONOMY': '10116'})), \
stmt.evidence[0].context
# Test annotation manager
assert bp.annot_manager.get_mapping('Species', '9606') == \
'H**o sapiens'
def get_bel_stmts(self, filter=False):
"""Get relevant statements from the BEL large corpus.
Performs a series of neighborhood queries and then takes the union of
all the statements. Because the query process can take a long time for
large gene lists, the resulting list of statements are cached in a
pickle file with the filename `<basename>_bel_stmts.pkl`. If the
pickle file is present, it is used by default; if not present, the
queries are performed and the results are cached.
Parameters
----------
filter : bool
If True, includes only those statements that exclusively mention
genes in :py:attr:`gene_list`. Default is False. Note that the
full (unfiltered) set of statements are cached.
Returns
-------
list of :py:class:`indra.statements.Statement`
List of INDRA statements extracted from the BEL large corpus.
"""
bel_proc = bel.process_pybel_neighborhood(self.gene_list)
bel_statements = bel_proc.statements
# Save to pickle file if we're caching
if self.basename is not None:
with open('%s_bel_stmts.pkl' % self.basename, 'wb') as f:
pickle.dump(bel_statements, f)
# Optionally filter out statements not involving only our gene set
if filter:
if len(self.gene_list) > 1:
bel_statements = ac.filter_gene_list(bel_statements,
self.gene_list, 'all')
return bel_statements
def test_pybel_neighborhood_query():
corpus = path_this + '/../../data/small_corpus.bel'
bp = bel.process_pybel_neighborhood(['TP63'], corpus)
assert bp.statements
assert_pmids(bp.statements)
unicode_strs(bp.statements)
assert all([
s.evidence[0].context.cell_line.name == 'MCF 10A'
for s in bp.statements
])
assert bp.statements[0].evidence[0].context.__repr__() == \
bp.statements[0].evidence[0].context.__str__()
assert bp.statements[0].evidence[0].context == \
BioContext(location=RefContext(name="Cytoplasm",
db_refs={'MESH': 'D003593'}),
cell_line=RefContext(name="MCF 10A",
db_refs={'EFO': '0001200'}),
cell_type=RefContext(name="keratinocyte",
db_refs={'CL': '0000312'}),
organ=RefContext(name="colon",
db_refs={'UBERON': '0001155'}),
disease=RefContext(name="cancer",
db_refs={'DOID': '162'}),
species=RefContext(name="Rattus norvegicus",
db_refs={'TAXONOMY': '10116'}))
# Test annotation manager
assert bp.annot_manager.get_mapping('Species', '9606') == \
'H**o sapiens'
def test_pybel_neighborhood_query():
corpus = path_this + '/../../data/small_corpus.bel'
bp = bel.process_pybel_neighborhood(['TP63'], corpus)
assert bp.statements
assert_pmids(bp.statements)
unicode_strs(bp.statements)
assert all([s.evidence[0].context.cell_line.name == 'MCF 10A'
for s in bp.statements])
assert bp.statements[0].evidence[0].context.__repr__() == \
bp.statements[0].evidence[0].context.__str__()
assert bp.statements[0].evidence[0].context == \
BioContext(location=RefContext(name="Cytoplasm",
db_refs={'MESH': 'D003593'}),
cell_line=RefContext(name="MCF 10A",
db_refs={'EFO': '0001200'}),
cell_type=RefContext(name="keratinocyte",
db_refs={'CL': '0000312'}),
organ=RefContext(name="colon",
db_refs={'UBERON': '0001155'}),
disease=RefContext(name="cancer",
db_refs={'DOID': '162'}),
species=RefContext(name="Rattus norvegicus",
db_refs={'TAXONOMY': '10116'}))
# Test annotation manager
assert bp.annot_manager.get_mapping('Species', '9606') == \
'H**o sapiens'
def bel_process_pybel_neighborhood():
"""Process BEL Large Corpus neighborhood and return INDRA Statements."""
if request.method == 'OPTIONS':
return {}
response = request.body.read().decode('utf-8')
body = json.loads(response)
genes = body.get('genes')
bp = bel.process_pybel_neighborhood(genes)
return _stmts_from_proc(bp)
def bel_process_pybel_neighborhood():
"""Process BEL Large Corpus neighborhood and return INDRA Statements."""
if request.method == 'OPTIONS':
return {}
response = request.body.read().decode('utf-8')
body = json.loads(response)
genes = body.get('genes')
bp = bel.process_pybel_neighborhood(genes)
return _stmts_from_proc(bp)
def bel_process_pybel_neighborhood():
"""Process BEL Large Corpus neighborhood and return INDRA Statements."""
if request.method == 'OPTIONS':
return {}
response = request.body.read().decode('utf-8')
body = json.loads(response)
genes = body.get('genes')
bp = bel.process_pybel_neighborhood(genes)
if bp and bp.statements:
stmts = stmts_to_json(bp.statements)
res = {'statements': stmts}
return res
else:
res = {'statements': []}
return res
def get_bel_stmts(self, filter=False):
"""Get relevant statements from the BEL large corpus.
Performs a series of neighborhood queries and then takes the union of
all the statements. Because the query process can take a long time for
large gene lists, the resulting list of statements are cached in a
pickle file with the filename `<basename>_bel_stmts.pkl`. If the
pickle file is present, it is used by default; if not present, the
queries are performed and the results are cached.
Parameters
----------
filter : bool
If True, includes only those statements that exclusively mention
genes in :py:attr:`gene_list`. Default is False. Note that the
full (unfiltered) set of statements are cached.
Returns
-------
list of :py:class:`indra.statements.Statement`
List of INDRA statements extracted from the BEL large corpus.
"""
if self.basename is not None:
bel_stmt_path = '%s_bel_stmts.pkl' % self.basename
# Check for cached BEL stmt file
if self.basename is not None and os.path.isfile(bel_stmt_path):
logger.info("Loading BEL statements from %s" % bel_stmt_path)
with open(bel_stmt_path, 'rb') as f:
bel_statements = pickle.load(f)
# No cache, so perform the queries
else:
bel_proc = bel.process_pybel_neighborhood(self.gene_list,
network_file=self.bel_corpus)
bel_statements = bel_proc.statements
# Save to pickle file if we're caching
if self.basename is not None:
with open(bel_stmt_path, 'wb') as f:
pickle.dump(bel_statements, f)
# Optionally filter out statements not involving only our gene set
if filter:
if len(self.gene_list) > 1:
bel_statements = ac.filter_gene_list(bel_statements,
self.gene_list, 'all')
return bel_statements
def post(self):
"""Process BEL Large Corpus neighborhood and return INDRA Statements.
Parameters
----------
genes : list[str]
A list of entity names (e.g., gene names) which will be used as the
basis of filtering the result. If any of the Agents of an extracted
INDRA Statement has a name appearing in this list, the Statement is
retained in the result.
Returns
-------
statements : list[indra.statements.Statement.to_json()]
A list of extracted INDRA Statements.
"""
args = request.json
genes = args.get('genes')
bp = bel.process_pybel_neighborhood(genes)
return _stmts_from_proc(bp)
def test_pybel_readme_example():
bel_processor = bel.process_pybel_neighborhood(['KRAS', 'BRAF'])
assert bel_processor.statements
def test_readme_using_indra4():
from indra.sources import bel
# Process the neighborhood of BRAF and MAP2K1
bel_processor = bel.process_pybel_neighborhood(['BRAF', 'MAP2K1'])
assert bel_processor.statements
def test_getting_started5():
# Chunk 5
from indra.sources import bel
bel_processor = bel.process_pybel_neighborhood(['KRAS', 'BRAF'])
assert bel_processor.statements
def test_pybel_neighborhood_query():
corpus = path_this + '/../../data/small_corpus.bel'
bp = bel.process_pybel_neighborhood(['TP63'], corpus)
assert bp.statements
assert_pmids(bp.statements)
unicode_strs(bp.statements)
