def create_accession_sets(genome_dict):
"""Generate set of unique and non-unique accessions.
Input is a dictionary of pdm_utils genome objects."""
accessions = []
for id in genome_dict.keys():
gnm = genome_dict[id]
# In the MySQL databse, empty accession data is stored as ''.
# There are no NULL accessions.
if gnm.accession != "":
accessions.append(gnm.accession)
unique, duplicated = basic.identify_unique_items(accessions)
return unique, duplicated
def create_accession_sets(genome_dict):
"""Generate set of unique and non-unique accessions.
Input is a dictionary of pdm_utils genome objects."""
l = []
for id in genome_dict.keys():
gnm = genome_dict[id]
# In the MySQL databse, empty accession data is stored as ''.
# There are no NULL accessions.
if gnm.accession != "":
l.append(gnm.accession)
unique, duplicated = basic.identify_unique_items(l)
if len(duplicated) > 0:
print("There are duplicated accessions. Some data will not be "
"retrieved from GenBank:")
for duplicate in duplicated:
print(duplicate)
input("\n\nPress ENTER to continue.")
return unique, duplicated
def set_unique_cds_end_orient_ids(self):
"""Identify CDS features contain unique transcription end-orientation coordinates."""
unique_id_tuples, duplicate_id_tuples = \
basic.identify_unique_items(self._cds_end_orient_ids)
self._cds_unique_end_orient_ids = set(unique_id_tuples)
self._cds_duplicate_end_orient_ids = set(duplicate_id_tuples)
def set_unique_cds_start_end_ids(self):
"""Identify CDS features contain unique start-end coordinates."""
unique_id_tuples, duplicate_id_tuples = \
basic.identify_unique_items(self._cds_start_end_ids)
self._cds_unique_start_end_ids = set(unique_id_tuples)
self._cds_duplicate_start_end_ids = set(duplicate_id_tuples)