def test_fill_seed2kegg_mappings_table(self):
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)
seed_data_util.create_tables(self.cursor)
seed_data_util.import_seed_genomes(self.cursor, seed_genome_file)
seed_data_util.import_seed_genes(self.cursor, seed_gene_dir)
seed_data_util.create_seed2uniref_mappings_table(self.cursor)
seed_data_util.load_diamond_search_results(self.cursor,
seed_diamond_output, 95.0,
5)
self.cursor.execute('SELECT COUNT(*) FROM seed2uniref_mappings')
self.assertEqual(self.cursor.fetchone()[0], 3)
kegg_data_util.create_kegg_genomes_table(self.cursor)
kegg_data_util.import_kegg_genomes_list(
self.cursor, os.path.join(test_kegg_dir, 'kegg_genomes.txt'))
kegg_data_util.create_kegg_genes_table(self.cursor)
kegg_data_util.import_kegg_genes(
self.cursor, os.path.join(test_kegg_dir, 'ko_proteins_nr.fasta'))
kegg_data_util.create_kegg2uniref_mappings_table(self.cursor)
kegg_data_util.load_diamond_search_results(self.cursor,
kegg_diamond_output, 95.0,
5)
self.cursor.execute('SELECT COUNT(*) FROM kegg2uniref_mappings')
self.assertEqual(self.cursor.fetchone()[0], 2)
seed_data_util.create_seed2kegg_mappings_table(self.cursor)
data_analysis.fill_seed2kegg_mappings_table(self.cursor,
seed2kegg_diamond_output,
95.0, 5)
self.cursor.execute('SELECT COUNT(*) FROM seed2kegg_mappings')
self.assertEqual(self.cursor.fetchone()[0], 4)
def test_import_kegg_genes(self):
kegg_data_util.create_kegg_genomes_table(self.cursor)
kegg_data_util.import_kegg_genomes_list(
self.cursor, os.path.join(test_kegg_dir, 'kegg_genomes.txt'))
kegg_data_util.create_kegg_genes_table(self.cursor)
kegg_data_util.import_kegg_genes(
self.cursor, os.path.join(test_kegg_dir, 'ko_proteins_nr.fasta'))
self.cursor.execute('SELECT COUNT(*) FROM kegg_genes')
self.assertEqual(self.cursor.fetchone()[0], 3)
def setUp(self):
self.conn = db_utils.connect_local_database(
os.path.join(data_dir, kegg_db_file))
self.cursor = self.conn.cursor()
db_utils.attach_local_database(self.cursor,
os.path.join(data_dir, uniref_db_file),
'uniref_proteins')
kegg_data_util.create_kegg_genomes_table(self.cursor)
kegg_data_util.import_kegg_genomes_list(
self.cursor, os.path.join(test_kegg_dir, 'kegg_genomes.txt'))
kegg_data_util.create_kegg_genes_table(self.cursor)
kegg_data_util.import_kegg_genes(
self.cursor, os.path.join(test_kegg_dir, 'ko_proteins_nr.fasta'))
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 setUp(self):
self.conn = db_utils.connect_local_database(db_file)
self.cursor = self.conn.cursor()
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)
seed_data_util.create_tables(self.cursor)
seed_data_util.import_seed_functional_roles_table(
self.cursor, seed_roles_file)
seed_data_util.import_seed_genomes(self.cursor, seed_genome_file)
seed_data_util.import_seed_genes(self.cursor, seed_gene_dir)
seed_data_util.import_seed_gene2roles_mapping(self.cursor,
seed_gene2roles_dir,
'test')
seed_data_util.create_seed2uniref_mappings_table(self.cursor)
seed_data_util.load_diamond_search_results(self.cursor,
seed_diamond_output, 95.0,
5)
kegg_data_util.create_kegg_orthologs_table(self.cursor)
kegg_data_util.import_kegg_orthologs_list(
self.cursor, os.path.join(test_kegg_dir, 'kegg_ko_list.txt'))
kegg_data_util.create_kegg_genomes_table(self.cursor)
kegg_data_util.import_kegg_genomes_list(
self.cursor, os.path.join(test_kegg_dir, 'kegg_genomes.txt'))
kegg_data_util.create_kegg_genes_table(self.cursor)
kegg_data_util.import_kegg_genes(
self.cursor, os.path.join(test_kegg_dir, 'ko_proteins_nr.fasta'))
kegg_data_util.create_kegg_genes2ko_table(self.cursor)
kegg_data_util.import_genes2ko_mappings(self.cursor, test_kegg_dir)
kegg_data_util.create_kegg2uniref_mappings_table(self.cursor)
kegg_data_util.load_diamond_search_results(self.cursor,
kegg_diamond_output, 95.0,
5)
seed_data_util.create_seed2kegg_mappings_table(self.cursor)
data_analysis.fill_seed2kegg_mappings_table(self.cursor,
seed2kegg_diamond_output,
95.0, 5)
db_utils.create_collections_table(self.cursor)
db_utils.create_collection2function_table(self.cursor)
data_analysis.import_collection_tsv(self.cursor, collection_file,
'nitrogen_test', 'test info', '0')
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 test_export_kegg_unmapped_proteins(self):
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)
seed_data_util.create_tables(self.cursor)
seed_data_util.import_seed_genomes(self.cursor, seed_genome_file)
seed_data_util.import_seed_genes(self.cursor, seed_gene_dir)
seed_data_util.create_seed2uniref_mappings_table(self.cursor)
seed_data_util.load_diamond_search_results(self.cursor,
seed_diamond_output, 95.0,
5)
self.cursor.execute('SELECT COUNT(*) FROM seed2uniref_mappings')
self.assertEqual(self.cursor.fetchone()[0], 3)
kegg_data_util.create_kegg_genomes_table(self.cursor)
kegg_data_util.import_kegg_genomes_list(
self.cursor, os.path.join(test_kegg_dir, 'kegg_genomes.txt'))
kegg_data_util.create_kegg_genes_table(self.cursor)
kegg_data_util.import_kegg_genes(
self.cursor, os.path.join(test_kegg_dir, 'ko_proteins_nr.fasta'))
kegg_data_util.create_kegg2uniref_mappings_table(self.cursor)
kegg_data_util.load_diamond_search_results(self.cursor,
kegg_diamond_output, 95.0,
5)
self.cursor.execute('SELECT COUNT(*) FROM kegg2uniref_mappings')
self.assertEqual(self.cursor.fetchone()[0], 2)
seed_data_util.create_seed2kegg_mappings_table(self.cursor)
data_analysis.fill_seed2kegg_mappings_table(self.cursor,
seed2kegg_diamond_output,
95.0, 5)
self.cursor.execute('SELECT COUNT(*) FROM seed2kegg_mappings')
self.assertEqual(self.cursor.fetchone()[0], 4)
data_analysis.export_kegg_unmapped_proteins(
self.cursor, os.path.join(test_kegg_dir, 'ko_proteins_nr.fasta'),
os.path.join(data_dir, 'out.fasta'))
with open(os.path.join(data_dir, 'out.fasta'), 'r') as f:
line = f.readline()
self.assertEqual(line[:15], '>dml:Dmul_28240')
f.closed