def __read_features(self, feature_ids):
"""Returns a list containing the features for the specified feature
ids"""
def read_feature(line):
"""Creates and adds a feature and associated contig from current
DelimitedFile line"""
contig = line[3]
is_reverse = False
if line[6] == 'R':
is_reverse = True
# note that feature positions can sometimes start with a '>'
# or '<', so make sure it is stripped away
return st.Feature(line[0], line[1], line[2],
st.Location(contig,
int(string.lstrip(line[4], '<>')),
int(string.lstrip(line[5], '<>')),
is_reverse))
features = {}
dfile = util.dfile_from_text(
self.__rsatdb().get_features(self.species()), comment='--')
for line in dfile.lines:
feature_id = line[0]
if feature_id in feature_ids:
features[feature_id] = read_feature(line)
return features
def __read_features(self, feature_ids):
"""Returns a list containing the features for the specified feature
ids"""
def read_feature(line):
"""Creates and adds a feature and associated contig from current
DelimitedFile line"""
contig = line[3]
is_reverse = False
if line[6] == 'R':
is_reverse = True
# note that feature positions can sometimes start with a '>'
# or '<', so make sure it is stripped away
return st.Feature(
line[0], line[1], line[2],
st.Location(contig, int(string.lstrip(line[4], '<>')),
int(string.lstrip(line[5], '<>')), is_reverse))
features = {}
dfile = util.dfile_from_text(self.__rsatdb().get_features(
self.species()),
comment='--')
for line in dfile.lines:
feature_id = line[0]
if feature_id in feature_ids:
features[feature_id] = read_feature(line)
return features
def test_create_from_text(self):
"""Reads a tab delimited file from a text"""
dfile = util.dfile_from_text(
"value11\tvalue12\nvalue21\tvalue22")
lines = dfile.lines
self.assertEquals(["value11", "value12"], lines[0])
self.assertEquals(["value21", "value22"], lines[1])
self.assertIsNone(dfile.header)
def get_taxonomy_id(self, organism):
"""returns the specified organism name file contents"""
logging.info('RSAT - get_organism_names(%s)', organism)
cache_file = "/".join([self.cache_dir, 'rsatnames_' + organism])
text = util.read_url_cached(
"/".join([self.base_url, RsatDatabase.DIR_PATH, organism,
RsatDatabase.ORGANISM_NAMES_PATH]), cache_file)
organism_names_dfile = util.dfile_from_text(text, comment='--')
return patches.patch_ncbi_taxonomy(organism_names_dfile.lines[0][0])
def __get_predictions(microbes_online, organism):
"""reads the operon predictions for a given organism from MicrobesOnline"""
preds_text = microbes_online.get_operon_predictions_for(
organism.taxonomy_id())
dfile = util.dfile_from_text(preds_text, has_header=True)
code = organism.code
preds = [(patches.patch_mo_gene(code, line[2]),
patches.patch_mo_gene(code, line[3]))
for line in dfile.lines if line[6] == 'TRUE']
logging.info("%d prediction pairs read", len(preds))
return preds
def __get_predictions(microbes_online, organism):
"""reads the operon predictions for a given organism from MicrobesOnline"""
preds_text = microbes_online.get_operon_predictions_for(
organism.taxonomy_id())
dfile = util.dfile_from_text(preds_text, has_header=True)
code = organism.code
preds = [(patches.patch_mo_gene(code, line[2]),
patches.patch_mo_gene(code, line[3]))
for line in dfile.lines if line[6] == 'TRUE']
logging.info("%d prediction pairs read", len(preds))
return preds
def thesaurus(self):
"""reads the thesaurus from a feature_names file. The thesaurus
is also cached, because it is used many times
"""
if not self.__synonyms:
feature_names_dfile = util.dfile_from_text(
self.__rsatdb().get_feature_names(self.species()),
comment='--')
self.__synonyms = thesaurus.create_from_rsat_feature_names(
feature_names_dfile, [thesaurus.strip_vng_modification])
return self.__synonyms
def get_taxonomy_id(self, organism):
"""returns the specified organism name file contents"""
logging.info('RSAT - get_organism_names(%s)', organism)
cache_file = "/".join([self.cache_dir, 'rsatnames_' + organism])
text = util.read_url_cached(
"/".join([
self.base_url, RsatDatabase.DIR_PATH, organism,
RsatDatabase.ORGANISM_NAMES_PATH
]), cache_file)
organism_names_dfile = util.dfile_from_text(text, comment='--')
return patches.patch_ncbi_taxonomy(organism_names_dfile.lines[0][0])
def thesaurus(self):
"""reads the thesaurus from a feature_names file. The thesaurus
is also cached, because it is used many times
"""
if not self.__synonyms:
feature_names_dfile = util.dfile_from_text(
self.__rsatdb().get_feature_names(self.species()),
comment='--')
self.__synonyms = thesaurus.create_from_rsat_feature_names(
feature_names_dfile, [thesaurus.strip_vng_modification])
return self.__synonyms
def get_taxonomy_id(rsat_organism):
"""Determine the taxonomy data from the RSAT database"""
organism_names_dfile = util.dfile_from_text(
rsatdb.get_organism_names(rsat_organism), comment='--')
return organism_names_dfile.lines[0][0]
