def test_process_pmc():
for offline in offline_modes:
rp = reach.process_pmc('PMC4338247', offline=offline)
assert rp is not None
for stmt in rp.statements:
assert_pmid(stmt)
assert unicode_strs(rp.statements)
def reach_process_pmc():
"""Process PubMedCentral article and return INDRA Statements."""
if request.method == 'OPTIONS':
return {}
response = request.body.read().decode('utf-8')
body = json.loads(response)
pmcid = body.get('pmcid')
rp = reach.process_pmc(pmcid)
return _stmts_from_proc(rp)
def reach_process_pmc():
"""Process PubMedCentral article and return INDRA Statements."""
if request.method == 'OPTIONS':
return {}
response = request.body.read().decode('utf-8')
body = json.loads(response)
pmcid = body.get('pmcid')
rp = reach.process_pmc(pmcid)
return _stmts_from_proc(rp)
def post(self):
"""Process PubMedCentral article and return INDRA Statements.
Parameters
----------
pmc_id : str
The ID of a PubmedCentral article. The string may start with PMC
but passing just the ID also works.
Examples: 8511698, PMC8511698
https://www.ncbi.nlm.nih.gov/pmc/
offline : Optional[bool]
If set to True, the REACH system is run offline via a JAR file.
Otherwise (by default) the web service is called. Default: False
url : Optional[str]
URL for a REACH web service instance, which is used for reading if
provided. If not provided but offline is set to False (its default
value), REACH_NXML_URL set in configuration will be used. If not
provided in configuration, the Arizona REACH web service is called
(http://agathon.sista.arizona.edu:8080/odinweb/api/help).
Default: None
Returns
-------
statements : list[indra.statements.Statement.to_json()]
A list of extracted INDRA Statements.
"""
args = request.json
pmcid = args.get('pmc_id')
offline = True if args.get('offline') else False
given_url = args.get('url')
config_url = get_config('REACH_NXML_URL', failure_ok=True)
# Order: URL given as an explicit argument in the request. Then any URL
# set in the configuration. Then, unless offline is set, use the
# default REACH web service URL.
if 'url' in args: # This is to take None if explicitly given
url = given_url
elif config_url:
url = config_url
elif not offline:
url = reach_nxml_url
else:
url = None
# If a URL is set, prioritize it over the offline setting
if url:
offline = False
rp = reach.process_pmc(pmcid, offline=offline, url=url)
return _stmts_from_proc(rp)
def reach_process_pmc():
"""Process PubMedCentral article and return INDRA Statements."""
if request.method == 'OPTIONS':
return {}
response = request.body.read().decode('utf-8')
body = json.loads(response)
pmcid = body.get('pmcid')
rp = reach.process_pmc(pmcid)
if rp and rp.statements:
stmts = stmts_to_json(rp.statements)
res = {'statements': stmts}
return res
else:
res = {'statements': []}
return res
def test_readme_using_indra2():
from indra.sources import reach
reach_processor = reach.process_pmc('3717945', url=reach.local_nxml_url)
assert reach_processor.statements
def test_getting_started4():
# Chunk 4
from indra.sources import reach
reach_processor = reach.process_pmc('3717945')
assert reach_processor.statements
covidMetaDataFN = '2020-03-13/all_sources_metadata_2020-03-13.csv'
pmcids = []
with open(covidMetaDataFN) as csv_file:
csv_reader = csv.reader(csv_file, delimiter=',')
line_count = 0
for row in csv_reader:
if line_count == 0:
print(f'Column names are {", ".join(row)}')
line_count += 1
if line_count == 1:
pmc = f'{row[4]}'
pmc = pmc.replace('PMC', '', 1)
if ((pmc != '') & (pmc != 'pmcid')):
pmcids.append(pmc)
#line_count += 1
#reach_processor = reach.process_pmc(pmc)
# print(f'\t{row[0]} works in the {row[1]} department, and was born in {row[2]}.')
#print(f'Processed {line_count} lines.')
reach_processor = reach.process_pmc('1054884')
# print(reach_processor)
#line_count = 0
#for pmcid in pmcids:
# if line_count == 0:
# print(pmcid)
# reach_processor = reach.process_pmc(pmcid)
# print(reach_processor.print_event_statistics())
# line_count += 1
# print(reach_processor.get_all_events())
from indra.tools import assemble_corpus as ac
from indra.statements import stmts_to_json_file
from indra.assemblers.html import HtmlAssembler
from indra.sources import reach
tp = reach.process_pmc('PMC4455820', url=reach.local_nxml_url)
if tp:
stmts = tp.statements
print(stmts)
stmts = ac.filter_grounded_only(stmts) # Filter out ungrounded agents
stmts = ac.run_preassembly(
stmts, # Run preassembly
return_toplevel=False,
normalize_equivalences=
True, # Optional: rewrite equivalent groundings to one standard
normalize_opposites=
True, # Optional: rewrite opposite groundings to one standard
normalize_ns='WM'
) # Use 'WM' namespace to normalize equivalences and opposites
stmts = ac.filter_belief(stmts, 0.8) # Apply belief cutoff of e.g., 0.8
stmts_to_json_file(stmts, 'PMC4455820.json')
ha = HtmlAssembler(stmts)
ha.save_model('PMC4455820.html')
#
#
#
#
#attempt to combine many statements
from indra.tools import assemble_corpus as ac
from indra.statements import stmts_to_json_file
from indra.assemblers.html import HtmlAssembler
from indra.sources import reach
pmcids = ["PMC3717945", "PMC5906628"]
stmts = []
for pmcid in pmcids:
tp = reach.process_pmc(pmcid)
stmts += tp.statements
stmts = ac.filter_grounded_only(stmts) # Filter out ungrounded agents
stmts = ac.run_preassembly(
stmts, # Run preassembly
return_toplevel=False,
normalize_equivalences=
True, # Optional: rewrite equivalent groundings to one standard
normalize_opposites=
True, # Optional: rewrite opposite groundings to one standard
normalize_ns='WM'
) # Use 'WM' namespace to normalize equivalences and opposites
stmts = ac.filter_belief(stmts, 0.8) # Apply belief cutoff of e.g., 0.8
stmts_to_json_file(stmts, 'bigresults.json')
ha = HtmlAssembler(stmts)
ha.save_model('bigresults.html')
def test_process_pmc():
for offline in offline_modes:
rp = reach.process_pmc('PMC4338247', offline=offline)
for stmt in rp.statements:
assert_pmid(stmt)
assert unicode_strs(rp.statements)
