from __future__ import absolute_import, print_function, unicode_literals
from builtins import dict, str
import os
from indra.java_vm import autoclass, cast
from indra import biopax
import indra.biopax.processor as bpc
from indra.databases import uniprot_client
from indra.util import unicode_strs
from indra.preassembler import Preassembler
from indra.preassembler.hierarchy_manager import hierarchies
model_path = os.path.dirname(os.path.abspath(__file__)) +\
'/../../data/biopax_test.owl'
bp = biopax.process_owl(model_path)
uri_prefix = 'http://purl.org/pc2/7/'
def test_paxtools_autoclass():
autoclass('org.biopax.paxtools.impl.level3.ProteinImpl')
def test_biopaxpattern_autoclass():
autoclass('org.biopax.paxtools.pattern.PatternBox')
def test_cpath_autoclass():
autoclass('cpath.client.CPathClient')
def test_listify():
def get_biopax_stmts(self, filter=False, query='pathsbetween'):
"""Get relevant statements from Pathway Commons.
Performs a "paths between" query for the genes in :py:attr:`gene_list`
and uses the results to build statements. This function caches two
files: the list of statements built from the query, which is cached in
`<basename>_biopax_stmts.pkl`, and the OWL file returned by the Pathway
Commons Web API, which is cached in `<basename>_pc_pathsbetween.owl`.
If these cached files are found, then the results are returned based
on the cached file and Pathway Commons is not queried again.
Parameters
----------
filter : bool
If True, includes only those statements that exclusively mention
genes in :py:attr:`gene_list`. Default is False.
query : str
Defined what type of query is executed. The two options are
'pathsbetween' which finds paths between the given list of genes
and only works if more than 1 gene is given, and 'neighborhood'
which searches the immediate neighborhood of each given gene.
Returns
-------
list of :py:class:`indra.statements.Statement`
List of INDRA statements extracted from Pathway Commons.
"""
# If we're using a cache, initialize the appropriate filenames
if self.basename is not None:
biopax_stmt_path = '%s_biopax_stmts.pkl' % self.basename
biopax_ras_owl_path = '%s_pc_pathsbetween.owl' % self.basename
# Check for cached Biopax stmt file at the given path
# if it's there, return the statements from the cache
if self.basename is not None and os.path.isfile(biopax_stmt_path):
logger.info("Loading Biopax statements from %s" % biopax_stmt_path)
with open(biopax_stmt_path, 'rb') as f:
bp_statements = pickle.load(f)
return bp_statements
# Check for cached file before querying Pathway Commons Web API
if self.basename is not None and os.path.isfile(biopax_ras_owl_path):
logger.info("Loading Biopax from OWL file %s" %
biopax_ras_owl_path)
bp = biopax.process_owl(biopax_ras_owl_path)
# OWL file not found; do query and save to file
else:
if (len(self.gene_list) < 2) and (query == 'pathsbetween'):
logger.warning('Using neighborhood query for one gene.')
query = 'neighborhood'
if query == 'pathsbetween':
bp = biopax.process_pc_pathsbetween(self.gene_list)
elif query == 'neighborhood':
bp = biopax.process_pc_neighborhood(self.gene_list)
else:
logger.error('Invalid query type: %s' % query)
return []
# Save the file if we're caching
if self.basename is not None:
bp.save_model(biopax_ras_owl_path)
# Save statements to pickle file if we're caching
if self.basename is not None:
with open(biopax_stmt_path, 'wb') as f:
pickle.dump(bp.statements, f, protocol=2)
# Optionally filter out statements not involving only our gene set
if filter:
if len(self.gene_list) > 1:
bp_statements = ac.filter_gene_list(bp_statements,
self.gene_list, 'one')
else:
bp_statements = ac.filter_gene_list(bp_statements,
self.gene_list, 'all')
return bp.statements
from __future__ import absolute_import, print_function, unicode_literals
from builtins import dict, str
import os
from indra.java_vm import autoclass, cast
from indra import biopax
import indra.biopax.processor as bpc
from indra.databases import uniprot_client
from indra.util import unicode_strs
from indra.preassembler import Preassembler
from indra.preassembler.hierarchy_manager import hierarchies
model_path = os.path.dirname(os.path.abspath(__file__)) +\
'/../../data/biopax_test.owl'
bp = biopax.process_owl(model_path)
uri_prefix = 'http://purl.org/pc2/7/'
def test_paxtools_autoclass():
autoclass('org.biopax.paxtools.impl.level3.ProteinImpl')
def test_biopaxpattern_autoclass():
autoclass('org.biopax.paxtools.pattern.PatternBox')
def test_cpath_autoclass():
autoclass('cpath.client.CPathClient')
def test_listify():
assert(bpc._listify(1) == [1])
assert(bpc._listify([1,2] == [1,2]))
assert(bpc._listify([1] == [1]))
fname = 'egfr_model_v4.xml'
print 'Processing parser output from XML file %s...' % fname
tp = trips.process_xml(open(fname).read())
else:
print 'Submitting text to TRIPS parser...'
tstart = time.time()
tp = trips.process_text(open('model_text.txt').read())
tend = time.time()
print '> TRIPS parser took %d seconds.' % (tend - tstart)
pa.add_statements(tp.statements)
# BioPAX processing
if use_owl:
fname = 'DUSP.owl'
print 'Processing OWL file %s...' % fname
bp = biopax.process_owl('DUSP.owl')
else:
print 'Processing output from PathwayCommons query'
bp = biopax.process_pc_neighborhood(['DUSP4'])
bp.get_dephosphorylation(force_contains=['MAPK1'])
pa.add_statements(bp.statements)
# Assemble model
model = pa.make_model(initial_conditions=True)
RAF1 = model.monomers['RAF1']
HRAS = model.monomers['HRAS']
r1 = model.rules['RAF1_autophospho_RAF1_T491']
r1.rule_expression = (RAF1(HRAS=1, T491='u') % HRAS(RAF1=1) >> RAF1(HRAS=1, T491='p') % HRAS(RAF1=1))