def test_create_from_rsat_feature_names_no_transform(self):
"""test the creation from RSAT feature names file"""
thes = thesaurus.create_from_rsat_feature_names(
MockRsatFeatureNameFile())
self.assertEquals('NAME1', thes['PRIME1'])
self.assertEquals('NAME1', thes['ALT1'])
self.assertEquals('NAME2', thes['PRIME2'])
self.assertEquals('NAME2', thes['VNG2664Gm'])
def test_create_from_rsat_feature_names_with_transform(self):
"""test the creation from RSAT feature names using a key transformer"""
thes = thesaurus.create_from_rsat_feature_names(
MockRsatFeatureNameFile(), [lambda x: [x, x.rstrip('m')]])
self.assertEquals('NAME1', thes['PRIME1'])
self.assertEquals('NAME1', thes['ALT1'])
self.assertEquals('NAME2', thes['PRIME2'])
self.assertEquals('NAME2', thes['VNG2664G'])
def test_create_from_rsat_feature_names_no_transform(self):
"""test the creation from RSAT feature names file"""
thes = thesaurus.create_from_rsat_feature_names(
MockRsatFeatureNameFile())
self.assertEquals('NAME1', thes['PRIME1'])
self.assertEquals('NAME1', thes['ALT1'])
self.assertEquals('NAME2', thes['PRIME2'])
self.assertEquals('NAME2', thes['VNG2664Gm'])
def test_create_from_rsat_feature_names_with_transform(self):
"""test the creation from RSAT feature names using a key transformer"""
thes = thesaurus.create_from_rsat_feature_names(
MockRsatFeatureNameFile(), [lambda x: [x, x.rstrip('m')]])
self.assertEquals('NAME1', thes['PRIME1'])
self.assertEquals('NAME1', thes['ALT1'])
self.assertEquals('NAME2', thes['PRIME2'])
self.assertEquals('NAME2', thes['VNG2664G'])
def addThesaurusFile(self, thFile, thFileType):
# here we add a thesaurus file, can choose from different filetypes
# at least later
if thFileType == "RSAT":
infile = util.DelimitedFile.read(thFile, sep='\t', has_header=False, comment = "--")
tempD = th.create_from_rsat_feature_names(infile)
self.__synonyms = self.MergeDicts(self.__synonyms, tempD)
else:
thFileType == "unassigned - ERROR"
logging.info("\x1b[31mKapsel:\t\x1b[0mThesaurus added, %s type" % (thFileType))
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.DelimitedFile.create_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 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 __make_organism(self):
"""makes a mock organism with almost real data"""
features = {}
dfile = util.DelimitedFile.read(
'testdata/Halobacterium_sp_features', comment='--')
for line in dfile.lines():
features[line[0]] = st.Feature(
line[0], line[1], line[2],
st.Location(line[3], int(line[4]), int(line[5]),
line[6] == 'R'))
tfile = util.DelimitedFile.read(
'testdata/Halobacterium_sp_feature_names', comment='--')
synonyms = th.create_from_rsat_feature_names(tfile)
return MockOrganismWithSynonyms('64091', features, synonyms)
def __make_organism(self):
"""makes a mock organism with almost real data"""
features = {}
dfile = util.read_dfile('testdata/Halobacterium_sp_features',
comment='--')
for line in dfile.lines:
features[line[0]] = st.Feature(
line[0], line[1], line[2],
st.Location(line[3], int(line[4]), int(line[5]),
line[6] == 'R'))
tfile = util.read_dfile('testdata/Halobacterium_sp_feature_names',
comment='--')
synonyms = th.create_from_rsat_feature_names(tfile)
return MockOrganismWithSynonyms('64091', features, synonyms)
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)
