def main():
args = get_args()
# Open database
conn = db_utils.connect_local_database(args.seed_db)
c = conn.cursor()
db_utils.attach_local_database(c, args.uniref_db, 'uniref_proteins')
# Prepare database
print('Drop seed2uniref_mappings table...')
seed_data_util.drop_seed2uniref_mappings_table(c)
print('Create seed2uniref_mappings table...')
seed_data_util.create_seed2uniref_mappings_table(c)
# Import data
print('Find genes with identical hashes...')
data_analysis.find_seed2uniref_identical_mappings(c)
print('Get genes from DIAMOND output...')
seed_data_util.load_diamond_search_results(c, args.diamond_out, 95.0, 5)
# Write changes and close database
print('Saving database...', end='')
conn.commit()
conn.close()
print('done.')
def setUp(self):
self.conn = db_utils.connect_local_database(seed_db_file)
self.cursor = self.conn.cursor()
seed_data_util.create_seed_genomes_table(self.cursor)
seed_data_util.import_seed_genomes(self.cursor, os.path.join(data_dir, 'test_seed_genomes.txt'))
seed_data_util.create_seed_genes_table(self.cursor)
seed_data_util.import_seed_genes(self.cursor, test_seed_dir)
db_utils.attach_local_database(self.cursor, uniref_db_file, 'uniref_proteins')
uniref_data_util.create_uniref_proteins_table(self.cursor)
uniref_data_util.import_uniref_fasta(self.cursor, uniref_fasta_file)
uniref_data_util.create_uniref_proteins_indices(self.cursor)
def main():
args = get_args()
# Open database
conn = db_utils.connect_local_database(args.kegg_db)
c = conn.cursor()
db_utils.attach_local_database(c, args.seed_db, 'seed_data')
print('Finding unmapped proteins...')
data_analysis.export_kegg_unmapped_proteins(c, args.infile, args.outfile)
conn.close()
print('done.')
def main():
args = get_args()
# Open database
conn = db_utils.connect_local_database(args.seed_db)
c = conn.cursor()
db_utils.attach_local_database(c, args.kegg_db, 'kegg_data')
db_utils.create_collections_table(c)
db_utils.create_collection2function_table(c)
data_analysis.import_collection_tsv(c, args.infile, args.name, args.info,
args.ver)
conn.commit()
conn.close()
print('done.')
def main():
args = get_args()
conn = db_utils.connect_local_database(args.db)
c = conn.cursor()
uniref_data_util.drop_tables(c)
uniref_data_util.drop_indices(c)
uniref_data_util.create_uniref_proteins_table(c)
uniref_data_util.import_uniref_fasta(c,args.fasta)
uniref_data_util.create_uniref_proteins_indices(c)
conn.commit()
conn.close()
def main():
args = get_args()
# Open database and prepare tables
conn = db_utils.connect_local_database(args.db)
c = conn.cursor()
seed_data_util.drop_tables(c)
seed_data_util.drop_all_indices(c)
seed_data_util.create_tables(c)
# Import data
seed_data_util.import_seed_functional_roles_table(c,args.seed_roles_file)
seed_data_util.import_seed_genomes(c,args.seed_genome_file)
seed_data_util.import_seed_genes(c,args.seed_prot_dir)
seed_data_util.import_seed_gene2roles_mapping(c,args.seed_roles_dir,args.comment)
# Save changes and close database
conn.commit()
conn.close()
def main():
args = get_args()
# Check if KEGG data directory contains all required files
if kegg_data_util.kegg_dir_is_valid(args.kegg_dir) == False:
print('Some required files are missing from ', args.kegg_dir,
'. Data import failed.')
sys.exit(1)
conn = db_utils.connect_local_database(args.db)
c = conn.cursor()
# Prepare database
print('Drop genes2ko table...')
kegg_data_util.drop_kegg_genes2ko_table(c)
print('Drop KEGG genes table...')
kegg_data_util.drop_kegg_genes_table(c)
print('Drop KEGG genomes table...')
kegg_data_util.drop_kegg_genomes_table(c)
print('Drop KEGG orthologs table...')
kegg_data_util.drop_kegg_orthologs_table(c)
print('Drop database indices...')
kegg_data_util.drop_indices(c)
print('Create KEGG orthologs table...')
kegg_data_util.create_kegg_orthologs_table(c)
print('Create KEGG genomes table...')
kegg_data_util.create_kegg_genomes_table(c)
print('Create KEGG genes table...')
kegg_data_util.create_kegg_genes_table(c)
print('Create genes2ko table...')
kegg_data_util.create_kegg_genes2ko_table(c)
# Import data
kegg_data_util.import_kegg_orthologs_list(
c, os.path.join(args.kegg_dir, 'kegg_ko_list.txt'))
kegg_data_util.import_kegg_genomes_list(
c, os.path.join(args.kegg_dir, 'kegg_genomes.txt'))
kegg_data_util.import_kegg_genes(
c, os.path.join(args.kegg_dir, 'ko_proteins_nr.fasta'))
kegg_data_util.import_genes2ko_mappings(c, args.kegg_dir)
conn.commit()
conn.close()
def main():
args = get_args()
# Open database
conn = db_utils.connect_local_database(args.seed_db)
c = conn.cursor()
db_utils.attach_local_database(c, args.kegg_db, 'kegg_data')
db_utils.attach_local_database(c, args.uniref_db, 'uniref_proteins')
# Prepare database
seed_data_util.drop_seed2kegg_mappings_table(c)
print('Creating seed2kegg_mappings table...')
seed_data_util.create_seed2kegg_mappings_table(c)
print('Populating seed2kegg_mappings table...')
data_analysis.fill_seed2kegg_mappings_table(c, args.diamond_out, 95.0, 5)
# Write changes and close database
print('Saving database...', end='')
conn.commit()
conn.close()
print('done.')
def main():
args = get_args()
# Open database
conn = db_utils.connect_local_database(args.seed_db)
c = conn.cursor()
# Prepare database
print('Creating gene2role_changes table...')
seed_data_util.create_gene2role_changes_table(c)
# Import data
print('Verifying input file and making changes in DB...')
data_analysis.correct_seed_annotations(c, args.infile, args.comment)
seed_data_util.create_gene2role_changes_indices(c)
# Write changes and close database
print('Saving database...', end='')
conn.commit()
conn.close()
print('done.')
def setUp(self):
self.conn = db_utils.connect_local_database(db_file)
self.cursor = self.conn.cursor()
db_utils.attach_local_database(self.cursor, uniref_db_file,
'uniref_proteins')