def read_ratios(params, args_in):
"""reading ratios matrix"""
if params['normalize_ratios']:
if test_data_change(params, args_in) == True:
#Turn off the nochange_filter if you're resuming a run an have changed the data matrix
ratio_filters = [dm.center_scale_filter]
else :
ratio_filters = [dm.nochange_filter, dm.center_scale_filter]
else:
ratio_filters = []
matrix_factory = dm.DataMatrixFactory(ratio_filters)
matrix_filename = args_in.ratios
if matrix_filename.startswith('http://'):
indata = util.read_url(matrix_filename)
infile = util.dfile_from_text(indata, has_header=True, quote='\"')
else:
infile = util.read_dfile(matrix_filename, has_header=True, quote='\"')
if params['case_sensitive'] or args_in.case_sensitive:
ratios = matrix_factory.create_from(infile, True)
else:
ratios = matrix_factory.create_from(infile, False)
return ratios
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(line[4].lstrip('<>')),
int(line[5].lstrip('<>')),
is_reverse))
features = {}
dfile = util.dfile_from_text(self.__rsat_info.get_features(), 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(line[4].lstrip('<>')),
int(line[5].lstrip('<>')),
is_reverse))
features = {}
dfile = util.dfile_from_text(self.__rsat_info.get_features(), 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_ratios(params, args_in):
"""reading ratios matrix"""
if params['normalize_ratios']:
if test_data_change(params, args_in) == True:
#Turn off the nochange_filter if you're resuming a run an have changed the data matrix
ratio_filters = [dm.center_scale_filter]
else:
ratio_filters = [dm.nochange_filter, dm.center_scale_filter]
else:
ratio_filters = []
matrix_factory = dm.DataMatrixFactory(ratio_filters)
matrix_filename = args_in.ratios
if matrix_filename.startswith('http://'):
indata = util.read_url(matrix_filename).decode('utf-8')
infile = util.dfile_from_text(indata, has_header=True, quote='\"')
else:
infile = util.read_dfile(matrix_filename, has_header=True, quote='\"')
if params['case_sensitive'] or args_in.case_sensitive:
ratios = matrix_factory.create_from(infile, True)
else:
ratios = matrix_factory.create_from(infile, False)
return ratios
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 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 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.__rsat_info.get_feature_names(), 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.__rsat_info.get_feature_names(), comment='--')
self.__synonyms = thesaurus.create_from_rsat_feature_names(
feature_names_dfile, [thesaurus.strip_vng_modification])
return self.__synonyms
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 get_taxonomy_id(self, organism):
"""returns the specified organism name file contents"""
logging.debug('RSAT - get_organism_names(%s)', organism)
cache_file = "/".join([self.cache_dir, 'rsatnames_' + organism])
#Changed 02-19-15 due to missing organism_names file in h.pylori
#text = util.read_url_cached(
# "/".join([self.base_url, RsatDatabase.DIR_PATH, organism,
# RsatDatabase.ORGANISM_NAMES_PATH]), cache_file)
text = util.read_url_cached(
"/".join([self.base_url, RsatDatabase.DIR_PATH, organism,
RsatDatabase.ORGANISM_PATH]), cache_file).decode('utf-8')
organism_names_dfile = util.dfile_from_text(text, comment='--')
return patches.patch_ncbi_taxonomy(organism_names_dfile.lines[0][0])
def get_taxonomy_id(self, organism):
"""returns the specified organism name file contents"""
logging.debug('RSAT - get_organism_names(%s)', organism)
cache_file = "/".join([self.cache_dir, 'rsatnames_' + organism])
#Changed 02-19-15 due to missing organism_names file in h.pylori
#text = util.read_url_cached(
# "/".join([self.base_url, RsatDatabase.DIR_PATH, organism,
# RsatDatabase.ORGANISM_NAMES_PATH]), cache_file)
text = util.read_url_cached(
"/".join([self.base_url, RsatDatabase.DIR_PATH, organism,
RsatDatabase.ORGANISM_PATH]), cache_file).decode('utf-8')
organism_names_dfile = util.dfile_from_text(text, comment='--')
return patches.patch_ncbi_taxonomy(organism_names_dfile.lines[0][0])
def read_ratios(params, args):
"""reading ratios matrix"""
if params['normalize_ratios']:
ratio_filters = [dm.nochange_filter, dm.center_scale_filter]
else:
ratio_filters = []
matrix_factory = dm.DataMatrixFactory(ratio_filters)
matrix_filename = args.ratios
if matrix_filename.startswith('http://'):
indata = util.read_url(matrix_filename)
infile = util.dfile_from_text(indata, has_header=True, quote='\"')
else:
infile = util.read_dfile(matrix_filename, has_header=True, quote='\"')
if params['case_sensitive'] or args.case_sensitive:
ratios = matrix_factory.create_from(infile, True)
else:
ratios = matrix_factory.create_from(infile, False)
return ratios
if not args.rsat_dir:
args.nomotifs = True
if not args.string and not args.operons:
args.nonetworks = True
# user overrides in config files
if args.config:
config.read(args.config)
matrix_factory = dm.DataMatrixFactory([dm.nochange_filter,
dm.center_scale_filter])
matrix_filename = args.ratios
if matrix_filename.startswith('http://'):
indata = util.read_url(matrix_filename)
infile = util.dfile_from_text(indata, has_header=True, quote='\"')
else:
infile = util.read_dfile(matrix_filename, has_header=True, quote='\"')
matrix = matrix_factory.create_from(infile)
infile = None
# override number of clusters either on the command line or through
# the config file
try:
num_clusters = config.getint("General", "num_clusters")
except:
num_clusters = args.numclusters
cmonkey_run = cmr.CMonkeyRun(args.organism, matrix,
string_file=args.string,
if not args.rsat_dir:
args.nomotifs = True
if not args.string and not args.operons:
args.nonetworks = True
# user overrides in config files
if args.config:
config.read(args.config)
matrix_factory = dm.DataMatrixFactory(
[dm.nochange_filter, dm.center_scale_filter])
matrix_filename = args.ratios
if matrix_filename.startswith('http://'):
indata = util.read_url(matrix_filename)
infile = util.dfile_from_text(indata, has_header=True, quote='\"')
else:
infile = util.read_dfile(matrix_filename, has_header=True, quote='\"')
matrix = matrix_factory.create_from(infile)
infile = None
# override number of clusters either on the command line or through
# the config file
try:
num_clusters = config.getint("General", "num_clusters")
except:
num_clusters = args.numclusters
cmonkey_run = cmr.CMonkeyRun(args.organism,
matrix,
