def biopax_process_pc_neighborhood():
"""Process PathwayCommons neighborhood, return INDRA Statements."""
if request.method == 'OPTIONS':
return {}
response = request.body.read().decode('utf-8')
body = json.loads(response)
genes = body.get('genes')
bp = biopax.process_pc_neighborhood(genes)
return _stmts_from_proc(bp)
def biopax_process_pc_neighborhood():
"""Process PathwayCommons neighborhood, return INDRA Statements."""
if request.method == 'OPTIONS':
return {}
response = request.body.read().decode('utf-8')
body = json.loads(response)
genes = body.get('genes')
bp = biopax.process_pc_neighborhood(genes)
return _stmts_from_proc(bp)
def biopax_process_pc_neighborhood():
"""Process PathwayCommons neighborhood, return INDRA Statements."""
if request.method == 'OPTIONS':
return {}
response = request.body.read().decode('utf-8')
body = json.loads(response)
genes = body.get('genes')
bp = biopax.process_pc_neighborhood(genes)
if bp and bp.statements:
stmts = stmts_to_json(bp.statements)
res = {'statements': stmts}
return res
else:
res = {'statements': []}
return res
def post(self):
"""Process PathwayCommons neighborhood, return INDRA Statements.
Parameters
----------
genes : list
A list of HGNC gene symbols to search the neighborhood of.
Examples: ['BRAF'], ['BRAF', 'MAP2K1']
Returns
-------
statements : list[indra.statements.Statement.to_json()]
A list of extracted INDRA Statements.
"""
args = request.json
genes = args.get('genes')
bp = biopax.process_pc_neighborhood(genes)
return _stmts_from_proc(bp)
def get_biopax_stmts(self,
filter=False,
query='pathsbetween',
database_filter=None):
"""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 : Optional[bool]
If True, includes only those statements that exclusively mention
genes in :py:attr:`gene_list`. Default is False.
query : Optional[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.
Note that for pathsbetween queries with more thatn 60 genes, the
query will be executed in multiple blocks for scalability.
database_filter: Optional[list[str]]
A list of PathwayCommons databases to include in the query.
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.exists(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.exists(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':
if len(self.gene_list) > 60:
block_size = 60
else:
block_size = None
bp = biopax.process_pc_pathsbetween(
self.gene_list,
database_filter=database_filter,
block_size=block_size)
elif query == 'neighborhood':
bp = biopax.process_pc_neighborhood(
self.gene_list, database_filter=database_filter)
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)
# Optionally filter out statements not involving only our gene set
if filter:
policy = 'one' if len(self.gene_list) > 1 else 'all'
stmts = ac.filter_gene_list(bp.statements, self.gene_list, policy)
else:
stmts = bp.statements
return stmts
if __name__ == '__main__':
all_genes = \
OrderedDict({'signaling': ['MAPK1', 'AKT1', 'JAK1', 'GNAS', 'CTNNB1'],
'genereg': ['MYC', 'TP53', 'STAT3', 'FOXO3', 'JUN'],
'metabolism': ['IDH1', 'PFKL', 'DHFR', 'GLUL', 'NOS1',
'CHEBI:20506', 'CHEBI:28300', 'CHEBI:16084',
'CHEBI:32816', 'CHEBI:16480']})
stats = {group: {g: {} for g in genes}
for group, genes in all_genes.items()}
for group, genes in all_genes.items():
for gene in genes:
print('%s\n======' % gene)
belp = bel.process_ndex_neighborhood([gene])
num_all, num_extracted = get_bel_statistics(belp)
stats[group][gene]['bel'] = (num_all, num_extracted)
print(num_all, num_extracted)
if gene.startswith('CHEBI:'):
bpx_query = 'http://identifiers.org/chebi/' + gene
else:
bpx_query = gene
biopp = biopax.process_pc_neighborhood([bpx_query])
num_all, num_extracted = get_biopax_statistics(biopp)
print(num_all, num_extracted)
stats[group][gene]['biopax'] = (num_all, num_extracted)
with open('db_coverage_stats.json', 'w') as fh:
json.dump(stats, fh)
print_stats(stats)
'genereg': ['MYC', 'TP53', 'STAT3', 'FOXO3', 'JUN'],
'metabolism': ['IDH1', 'PFKL', 'DHFR', 'GLUL', 'NOS1',
'CHEBI:20506', 'CHEBI:28300', 'CHEBI:16084',
'CHEBI:32816', 'CHEBI:16480']})
stats = {
group: {g: {}
for g in genes}
for group, genes in all_genes.items()
}
for group, genes in all_genes.items():
for gene in genes:
print('%s\n======' % gene)
belp = bel.process_ndex_neighborhood([gene])
num_all, num_extracted = get_bel_statistics(belp)
stats[group][gene]['bel'] = (num_all, num_extracted)
print(num_all, num_extracted)
if gene.startswith('CHEBI:'):
bpx_query = 'http://identifiers.org/chebi/' + gene
else:
bpx_query = gene
biopp = biopax.process_pc_neighborhood([bpx_query])
num_all, num_extracted = get_biopax_statistics(biopp)
print(num_all, num_extracted)
stats[group][gene]['biopax'] = (num_all, num_extracted)
with open('db_coverage_stats.json', 'w') as fh:
json.dump(stats, fh)
print_stats(stats)
def get_biopax_stmts(self, filter=False, query='pathsbetween',
database_filter=None):
"""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 : Optional[bool]
If True, includes only those statements that exclusively mention
genes in :py:attr:`gene_list`. Default is False.
query : Optional[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.
Note that for pathsbetween queries with more thatn 60 genes, the
query will be executed in multiple blocks for scalability.
database_filter: Optional[list[str]]
A list of PathwayCommons databases to include in the query.
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':
if len(self.gene_list) > 60:
block_size = 60
else:
block_size = None
bp = biopax.process_pc_pathsbetween(self.gene_list,
database_filter=database_filter,
block_size=block_size)
elif query == 'neighborhood':
bp = biopax.process_pc_neighborhood(self.gene_list,
database_filter=database_filter)
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)
# Optionally filter out statements not involving only our gene set
if filter:
policy = 'one' if len(self.gene_list) > 1 else 'all'
stmts = ac.filter_gene_list(bp.statements, self.gene_list, policy)
else:
stmts = bp.statements
return stmts
