def test_create_from_delimited_file2_case_sensitive(self):
"""test the delimited file second version"""
thes = thesaurus.create_from_delimited_file2(MockDelimitedFile2(),
case_sensitive=True)
self.assertEquals('gene1', thes['alt1'])
self.assertEquals('gene1', thes['alt2'])
self.assertEquals('gene2', thes['alt3'])
def test_create_from_delimited_file2_case_sensitive(self):
"""test the delimited file second version"""
thes = thesaurus.create_from_delimited_file2(MockDelimitedFile2(),
case_sensitive=True)
self.assertEquals('gene1', thes['alt1'])
self.assertEquals('gene1', thes['alt2'])
self.assertEquals('gene2', thes['alt3'])
def test_create_from_delimited_file2(self):
"""test the delimited file second version"""
thes = thesaurus.create_from_delimited_file2(MockDelimitedFile2(),
case_sensitive=False)
self.assertEquals('GENE1', thes['ALT1'])
self.assertEquals('GENE1', thes['ALT2'])
self.assertEquals('GENE2', thes['ALT3'])
def test_create_from_delimited_file2(self):
"""test the delimited file second version"""
thes = thesaurus.create_from_delimited_file2(MockDelimitedFile2(),
case_sensitive=False)
self.assertEquals('GENE1', thes['ALT1'])
self.assertEquals('GENE1', thes['ALT2'])
self.assertEquals('GENE2', thes['ALT3'])
def thesaurus(self):
"""Reads the synonyms from the provided CSV file"""
if not self.__synonyms:
self.__synonyms = thesaurus.create_from_delimited_file2(
self.__thesaurus_filename)
return self.__synonyms
def make_organism(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_map = util.make_dfile_map(keggfile, 1, 3)
ncbi_code = self['ncbi_code']
nw_factories = []
is_microbe = self['organism_code'] not in VERTEBRATES
# determine the final weights. note: for now, we will just check whether
# we have 1 or 2 networks
num_networks = 0
if not self['nonetworks'] and self['use_string']:
num_networks += 1
if is_microbe and not self['nonetworks'] and self['use_operons']:
num_networks += 1
network_weight = 0.0
if num_networks > 0:
network_weight = 1.0 / num_networks
# do we use STRING ?
if not self['nonetworks'] and self['use_string']:
# download if not provided
if stringfile is None:
if ncbi_code is None:
rsat_info = org.RsatSpeciesInfo(rsatdb,
kegg_map[self['organism_code']],
self['rsat_organism'], None)
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_factory(
self['organism_code'], stringfile, network_weight))
# do we use operons ?
if is_microbe and not self['nonetworks'] and self['use_operons']:
logging.debug('adding operon network factory')
nw_factories.append(microbes_online.get_network_factory(
mo_db, max_operon_size=self.ratios.num_rows / 20,
weight=network_weight))
orgcode = self['organism_code']
logging.debug("Creating Microbe object for '%s'", orgcode)
keggorg = kegg_map[orgcode]
rsat_info = org.RsatSpeciesInfo(rsatdb, keggorg, self['rsat_organism'],
self['ncbi_code'])
gotax = util.make_dfile_map(gofile, 0, 1)[rsat_info.go_species()]
synonyms = None
if self['synonym_file'] is not None:
synonyms = thesaurus.create_from_delimited_file2(self['synonym_file'],
self['case_sensitive'])
if is_microbe:
organism = org.Microbe(orgcode, keggorg, rsat_info, gotax, mo_db, nw_factories,
self['search_distances'], self['scan_distances'],
self['use_operons'], self.ratios, synonyms)
else:
organism = org.RSATOrganism(orgcode, keggorg, rsat_info, gotax, nw_factories,
self['search_distances'], self['scan_distances'],
self.ratios, synonyms)
conn = self.__dbconn()
with conn:
for network in organism.networks():
conn.execute("insert into statstypes values ('network',?)", [network.name])
for sequence_type in self['sequence_types']:
conn.execute("insert into statstypes values ('seqtype',?)", [sequence_type])
return organism
def make_organism(self):
"""returns the organism object to work on"""
self.__make_dirs_if_needed()
ncbi_code, kegg_species = self.__get_kegg_data()
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'], ncbi_code, self['rsat_features'], self['rsat_base_url'])
else:
rsatdb = rsat.RsatDatabase(self['rsat_base_url'], self['cache_dir'], kegg_species, ncbi_code, self['rsat_features'])
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']
nw_factories = []
is_microbe = self['organism_code'] not in VERTEBRATES
# determine the final weights. note: for now, we will just check whether
# we have 1 or 2 networks
num_networks = 0
if not self['nonetworks'] and self['use_string']:
num_networks += 1
if is_microbe and not self['nonetworks'] and self['use_operons']:
num_networks += 1
network_weight = 0.0
if num_networks > 0:
network_weight = 1.0 / num_networks
# do we use STRING ?
if not self['nonetworks'] and self['use_string']:
# download if not provided
if stringfile is None:
if ncbi_code is None:
rsat_info = org.RsatSpeciesInfo(rsatdb, kegg_species,
self['rsat_organism'], None)
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_factory(
self['organism_code'], stringfile, network_weight))
# do we use operons ?
if is_microbe and not self['nonetworks'] and self['use_operons']:
logging.debug('adding operon network factory')
nw_factories.append(microbes_online.get_network_factory(
mo_db, max_operon_size=self.ratios.num_rows / 20,
weight=network_weight))
orgcode = self['organism_code']
logging.debug("Creating Microbe object for '%s'", orgcode)
rsat_info = org.RsatSpeciesInfo(rsatdb, kegg_species, self['rsat_organism'],
ncbi_code)
gotax = util.make_dfile_map(gofile, 0, 1)[rsat_info.go_species()]
synonyms = None
if self['synonym_file'] is not None:
synonyms = thesaurus.create_from_delimited_file2(self['synonym_file'],
self['case_sensitive'])
#New logic: test to see if there's a fastafile. If not, then
#Download it from rsat, process it, and then return the new file name
is_microbe = True
if is_microbe:
organism = org.Microbe(orgcode, kegg_species, rsat_info, gotax, mo_db,
nw_factories,
self['search_distances'], self['scan_distances'],
self['use_operons'], self.ratios, synonyms,
self['fasta_file'])
else:
organism = org.RSATOrganism(orgcode, kegg_species, rsat_info, gotax,
nw_factories,
self['search_distances'], self['scan_distances'],
self.ratios, synonyms,
self['fasta_file'])
conn = self.__dbconn()
with conn:
for network in organism.networks():
conn.execute("insert into statstypes values ('network',?)", [network.name])
for sequence_type in self['sequence_types']:
conn.execute("insert into statstypes values ('seqtype',?)", [sequence_type])
return organism
def thesaurus(self):
"""Reads the synonyms from the provided CSV file"""
if not self.__synonyms:
self.__synonyms = thesaurus.create_from_delimited_file2(
self.__thesaurus_filename)
return self.__synonyms