def make_halo(ratio_matrix, search_distances, scan_distances):
"""returns the organism object to work on"""
keggfile = util.read_dfile(KEGG_FILE_PATH, comment='#')
gofile = util.read_dfile(GO_FILE_PATH)
rsatdb = rsat.RsatDatabase(rsat.RSAT_BASE_URL, CACHE_DIR)
mo_db = microbes_online.MicrobesOnline(CACHE_DIR)
stringfile = 'testdata/string_links_64091.tab'
nw_factories = []
if stringfile != None:
nw_factories.append(
stringdb.get_network_factory2('hal',
stringfile,
0.5,
normalized=True))
else:
logging.warn("no STRING file specified !")
nw_factories.append(
microbes_online.get_network_factory(
mo_db, max_operon_size=ratio_matrix.num_rows / 20, weight=0.5))
org_factory = org.MicrobeFactory(org.make_kegg_code_mapper(keggfile),
org.make_rsat_organism_mapper(rsatdb),
org.make_go_taxonomy_mapper(gofile),
mo_db, nw_factories)
return org_factory.create('hal', search_distances, scan_distances)
def make_halo(search_distances, scan_distances):
"""returns the organism object to work on"""
keggfile = util.read_dfile(KEGG_FILE_PATH, comment='#')
gofile = util.read_dfile(GO_FILE_PATH)
rsatdb = rsat.RsatDatabase(rsat.RSAT_BASE_URL, CACHE_DIR)
mo_db = microbes_online.MicrobesOnline(CACHE_DIR)
org_factory = org.MicrobeFactory(org.make_kegg_code_mapper(keggfile),
org.make_rsat_organism_mapper(rsatdb),
org.make_go_taxonomy_mapper(gofile),
mo_db, [])
return org_factory.create('hal', search_distances, scan_distances)
def make_halo(search_distances, scan_distances):
"""returns the organism object to work on"""
keggfile = util.read_dfile(KEGG_FILE_PATH, comment='#')
gofile = util.read_dfile(GO_FILE_PATH)
rsatdb = rsat.RsatDatabase(RSAT_BASE_URL, CACHE_DIR )
mo_db = microbes_online.MicrobesOnline()
org_factory = org.MicrobeFactory(org.make_kegg_code_mapper(keggfile),
org.make_rsat_organism_mapper(rsatdb),
org.make_go_taxonomy_mapper(gofile),
mo_db, [])
return org_factory.create('hal', search_distances, scan_distances)
def make_microbe(self):
"""returns the organism object to work on"""
keggfile = util.read_dfile(KEGG_FILE_PATH, comment='#')
gofile = util.read_dfile(GO_FILE_PATH)
rsatdb = rsat.RsatDatabase(RSAT_BASE_URL, self['cache_dir'])
mo_db = microbes_online.MicrobesOnline()
stringfile = self.config_params['string_file']
kegg_mapper = org.make_kegg_code_mapper(keggfile)
rsat_mapper = org.make_rsat_organism_mapper(rsatdb)
# automatically download STRING file
if stringfile == None:
rsat_info = rsat_mapper(kegg_mapper(self['organism_code']))
ncbi_code = rsat_info.taxonomy_id
print "NCBI CODE IS: ", ncbi_code
url = STRING_URL_PATTERN % ncbi_code
stringfile = "%s/%s.gz" % (self['cache_dir'], ncbi_code)
self['string_file'] = stringfile
logging.info("Automatically using STRING file in '%s'", stringfile)
util.get_url_cached(url, stringfile)
nw_factories = []
if stringfile != None:
nw_factories.append(stringdb.get_network_factory2(
self['organism_code'], stringfile, 0.5))
else:
logging.warn("no STRING file specified !")
nw_factories.append(microbes_online.get_network_factory(
mo_db, max_operon_size=self.ratio_matrix.num_rows / 20,
weight=0.5))
org_factory = org.MicrobeFactory(kegg_mapper,
rsat_mapper,
org.make_go_taxonomy_mapper(gofile),
mo_db,
nw_factories)
return org_factory.create(self['organism_code'],
self['search_distances'],
self['scan_distances'])
def make_halo(ratio_matrix, search_distances, scan_distances):
"""returns the organism object to work on"""
keggfile = util.read_dfile(KEGG_FILE_PATH, comment='#')
gofile = util.read_dfile(GO_FILE_PATH)
rsatdb = rsat.RsatDatabase(RSAT_BASE_URL, CACHE_DIR )
mo_db = microbes_online.MicrobesOnline()
stringfile = 'string_links_64091.tab'
nw_factories = []
if stringfile != None:
nw_factories.append(stringdb.get_network_factory2('hal', stringfile, 0.5))
else:
logging.warn("no STRING file specified !")
nw_factories.append(microbes_online.get_network_factory(
mo_db, max_operon_size=ratio_matrix.num_rows / 20, weight=0.5))
org_factory = org.MicrobeFactory(org.make_kegg_code_mapper(keggfile),
org.make_rsat_organism_mapper(rsatdb),
org.make_go_taxonomy_mapper(gofile),
mo_db,
nw_factories)
return org_factory.create('hal', search_distances, scan_distances)
def make_microbe(self):
"""returns the organism object to work on"""
keggfile = util.DelimitedFile.read(KEGG_FILE_PATH, comment='#')
gofile = util.DelimitedFile.read(GO_FILE_PATH)
rsatdb = rsat.RsatDatabase(RSAT_BASE_URL, self['cache_dir'])
mo_db = microbes_online.MicrobesOnline()
stringfile = self.config_params['string_file']
nw_factories = []
if stringfile != None:
nw_factories.append(stringdb.get_network_factory2(stringfile, 0.5))
else:
logging.warn("no STRING file specified !")
nw_factories.append(microbes_online.get_network_factory(
mo_db, max_operon_size=self.ratio_matrix.num_rows() / 20, weight=0.5))
org_factory = org.MicrobeFactory(org.make_kegg_code_mapper(keggfile),
org.make_rsat_organism_mapper(rsatdb),
org.make_go_taxonomy_mapper(gofile),
mo_db,
nw_factories)
return org_factory.create(self['organism_code'], self['search_distances'],
self['scan_distances'])
def setUp(self): # pylint: disable-msg=C0103
"""test fixture"""
with open(RSAT_LIST_FILE_PATH) as inputfile:
html = inputfile.read()
self.mapper = org.make_rsat_organism_mapper(MockRsatDatabase(html))
def make_microbe(self):
"""returns the organism object to work on"""
self.__make_dirs_if_needed()
if os.path.exists(USER_KEGG_FILE_PATH):
keggfile = util.read_dfile(USER_KEGG_FILE_PATH, comment='#')
elif os.path.exists(SYSTEM_KEGG_FILE_PATH):
keggfile = util.read_dfile(SYSTEM_KEGG_FILE_PATH, comment='#')
else:
raise Exception('KEGG file not found !!')
if os.path.exists(USER_GO_FILE_PATH):
gofile = util.read_dfile(USER_GO_FILE_PATH)
elif os.path.exists(SYSTEM_GO_FILE_PATH):
gofile = util.read_dfile(SYSTEM_GO_FILE_PATH)
else:
raise Exception('GO file not found !!')
if self['rsat_dir']:
if not self['rsat_organism']:
raise Exception(
'override RSAT loading: please specify --rsat_organism')
logging.info("using RSAT files for '%s'", self['rsat_organism'])
rsatdb = rsat.RsatFiles(self['rsat_dir'], self['rsat_organism'],
self['ncbi_code'])
else:
rsatdb = rsat.RsatDatabase(rsat.RSAT_BASE_URL, self['cache_dir'])
if self['operon_file']:
logging.info("using operon file at '%s'", self['operon_file'])
mo_db = microbes_online.MicrobesOnlineOperonFile(
self['operon_file'])
else:
logging.info(
"attempting automatic download of operons from Microbes Online"
)
mo_db = microbes_online.MicrobesOnline(self['cache_dir'])
stringfile = self['string_file']
kegg_mapper = org.make_kegg_code_mapper(keggfile)
rsat_mapper = org.make_rsat_organism_mapper(rsatdb)
ncbi_code = self['ncbi_code']
nw_factories = []
# do we use STRING ?
if self['donetworks'] and self['use_string']:
# download if not provided
if stringfile is None:
if ncbi_code is None:
rsat_info = rsat_mapper(kegg_mapper(self['organism_code']),
self['rsat_organism'])
ncbi_code = rsat_info.taxonomy_id
logging.info("NCBI CODE IS: %s", ncbi_code)
url = STRING_URL_PATTERN % ncbi_code
stringfile = "%s/%s.gz" % (self['cache_dir'], ncbi_code)
self['string_file'] = stringfile
logging.info("Automatically using STRING file in '%s'",
stringfile)
util.get_url_cached(url, stringfile)
else:
logging.info("Loading STRING file at '%s'", stringfile)
# create and add network
nw_factories.append(
stringdb.get_network_factory2(self['organism_code'],
stringfile, 0.5))
# do we use operons ?
if self['donetworks'] and self['use_operons']:
logging.info('adding operon network factory')
nw_factories.append(
microbes_online.get_network_factory(
mo_db,
max_operon_size=self.ratio_matrix.num_rows / 20,
weight=0.5))
org_factory = org.MicrobeFactory(kegg_mapper, rsat_mapper,
org.make_go_taxonomy_mapper(gofile),
mo_db, nw_factories,
self['ncbi_code'])
return org_factory.create(self['organism_code'],
self['search_distances'],
self['scan_distances'], self['use_operons'],
self['rsat_organism'], self.ratio_matrix)
def make_microbe(self):
"""returns the organism object to work on"""
self.__make_dirs_if_needed()
if os.path.exists(USER_KEGG_FILE_PATH):
keggfile = util.read_dfile(USER_KEGG_FILE_PATH, comment='#')
elif os.path.exists(SYSTEM_KEGG_FILE_PATH):
keggfile = util.read_dfile(SYSTEM_KEGG_FILE_PATH, comment='#')
else:
raise Exception('KEGG file not found !!')
if os.path.exists(USER_GO_FILE_PATH):
gofile = util.read_dfile(USER_GO_FILE_PATH)
elif os.path.exists(SYSTEM_GO_FILE_PATH):
gofile = util.read_dfile(SYSTEM_GO_FILE_PATH)
else:
raise Exception('GO file not found !!')
if self['rsat_dir']:
if not self['rsat_organism']:
raise Exception('override RSAT loading: please specify --rsat_organism')
logging.info("using RSAT files for '%s'", self['rsat_organism'])
rsatdb = rsat.RsatFiles(self['rsat_dir'], self['rsat_organism'], self['ncbi_code'])
else:
rsatdb = rsat.RsatDatabase(rsat.RSAT_BASE_URL, self['cache_dir'])
if self['operon_file']:
logging.info("using operon file at '%s'", self['operon_file'])
mo_db = microbes_online.MicrobesOnlineOperonFile(self['operon_file'])
else:
logging.info("attempting automatic download of operons from Microbes Online")
mo_db = microbes_online.MicrobesOnline(self['cache_dir'])
stringfile = self['string_file']
kegg_mapper = org.make_kegg_code_mapper(keggfile)
rsat_mapper = org.make_rsat_organism_mapper(rsatdb)
ncbi_code = self['ncbi_code']
nw_factories = []
# do we use STRING ?
if self['donetworks'] and self['use_string']:
# download if not provided
if stringfile is None:
if ncbi_code is None:
rsat_info = rsat_mapper(kegg_mapper(self['organism_code']),
self['rsat_organism'])
ncbi_code = rsat_info.taxonomy_id
logging.info("NCBI CODE IS: %s", ncbi_code)
url = STRING_URL_PATTERN % ncbi_code
stringfile = "%s/%s.gz" % (self['cache_dir'], ncbi_code)
self['string_file'] = stringfile
logging.info("Automatically using STRING file in '%s'", stringfile)
util.get_url_cached(url, stringfile)
else:
logging.info("Loading STRING file at '%s'", stringfile)
# create and add network
nw_factories.append(stringdb.get_network_factory2(
self['organism_code'], stringfile, 0.5))
# do we use operons ?
if self['donetworks'] and self['use_operons']:
logging.info('adding operon network factory')
nw_factories.append(microbes_online.get_network_factory(
mo_db, max_operon_size=self.ratio_matrix.num_rows / 20,
weight=0.5))
org_factory = org.MicrobeFactory(kegg_mapper,
rsat_mapper,
org.make_go_taxonomy_mapper(gofile),
mo_db,
nw_factories,
self['ncbi_code'])
return org_factory.create(self['organism_code'],
self['search_distances'],
self['scan_distances'],
self['use_operons'],
self['rsat_organism'],
self.ratio_matrix)
print("extract_string_links.py, (c) 2012, Institute for Systems Biology")
print('This program is licensed under the General Public License V3.')
print('See README and LICENSE for details.\n')
if len(sys.argv) <= 2:
print(
'Usage: python extract_string_links.py <stringdb-path> <organism-code>'
)
else:
rsatdb = rsat.RsatDatabase(RSAT_BASE_URL, CACHE_DIR)
kegg_mapper = organism.make_kegg_code_mapper(
util.DelimitedFile.read(KEGG_FILE,
sep='\t',
has_header=True,
comment='#'))
kegg_org = kegg_mapper(sys.argv[2])
rsat_info = organism.make_rsat_organism_mapper(rsatdb)(kegg_org)
print "RSAT SPECIES: ", rsat_info.species
print "TAX ID: ", rsat_info.taxonomy_id
feature_names = rsatdb.get_feature_names(rsat_info.species)
feature_names_dfile = util.DelimitedFile.create_from_text(
feature_names, comment='--')
synonyms = thesaurus.create_from_rsat_feature_names(
feature_names_dfile)
string_filepath = sys.argv[1]
if string_filepath.endswith('.gz'):
with gzip.open(string_filepath) as stringfile:
process_stringdb(stringfile, rsat_info.taxonomy_id)
else:
with open(string_filepath) as stringfile:
process_stringdb(stringfile, rsat_info.taxonomy_id)
print "edges normalized."
for edge in normalized_result:
print "%s\t%s\%f" % (edge.source(), edge.target(), edge.score())
"""
if __name__ == '__main__':
print("extract_string_links.py, (c) 2012, Institute for Systems Biology")
print('This program is licensed under the General Public License V3.')
print('See README and LICENSE for details.\n')
if len(sys.argv) <= 2:
print('Usage: python extract_string_links.py <stringdb-path> <organism-code>')
else:
rsatdb = rsat.RsatDatabase(RSAT_BASE_URL, CACHE_DIR)
kegg_mapper = organism.make_kegg_code_mapper(util.DelimitedFile.read(KEGG_FILE, sep='\t',
has_header=True,
comment='#'))
kegg_org = kegg_mapper(sys.argv[2])
rsat_info = organism.make_rsat_organism_mapper(rsatdb)(kegg_org)
print "RSAT SPECIES: ", rsat_info.species
print "TAX ID: ", rsat_info.taxonomy_id
feature_names = rsatdb.get_feature_names(rsat_info.species)
feature_names_dfile = util.DelimitedFile.create_from_text(feature_names, comment='--')
synonyms = thesaurus.create_from_rsat_feature_names(feature_names_dfile)
string_filepath = sys.argv[1]
if string_filepath.endswith('.gz'):
with gzip.open(string_filepath) as stringfile:
process_stringdb(stringfile, rsat_info.taxonomy_id)
else:
with open(string_filepath) as stringfile:
process_stringdb(stringfile, rsat_info.taxonomy_id)
