def test_check_database(self):
database = pkg_resources.resource_filename('shogun.tests',
os.path.join('data'))
with open(os.path.join(database, 'metadata.yaml'), 'r') as stream:
data_files = yaml.load(stream, Loader=yaml.SafeLoader)
results = parse_function_db(data_files, database)
self.assertTrue(results is not None)
def _function(inputs, database, output, levels, save_median_taxatable=False):
# Check if output exists, if not then make
if not os.path.exists(output):
os.makedirs(output)
# Load the datafiles to locate function db
data_files = _load_metadata(database)
# Load the functional db
logger.info("Loading the functional database and converting.")
func_db = parse_function_db(data_files, database)
for input, level in zip(inputs, levels):
# Verify it is in a reasonable level
if level in ['genus', 'species', 'strain']:
logger.info(
"Starting functional prediction with input file %s at level %s"
% (os.path.abspath(input), level))
function_run_and_save(input,
func_db,
output,
TAXAMAP[level],
save_median_taxatable=save_median_taxatable)
else:
continue
def summarize_functional(ctx, input, database, output):
prefix = ".".join(os.path.basename(input).split('.')[:-1]).replace(".kegg", "")
# Check if output exists, if not then make
if not os.path.exists(output):
os.makedirs(output)
# Load the datafiles to locate function db
data_files = _load_metadata(database)
# Load the functional db
logger.info("Loading the functional database and converting.")
func_db = parse_function_db(data_files, database)
kegg_df = pd.read_csv(input, sep="\t", index_col=0)
out_kegg_modules_df, out_kegg_modules_coverage = summarize_kegg_table(kegg_df, func_db['modules'])
out_kegg_pathways_df, out_kegg_pathways_coverage = summarize_kegg_table(kegg_df, func_db['pathways'])
out_kegg_modules_df.to_csv(os.path.join(output, "%s.kegg.modules.txt" % prefix), sep='\t', float_format="%d",
na_rep=0, index_label="#MODULE ID")
out_kegg_modules_coverage.to_csv(os.path.join(output, "%s.kegg.modules.coverage.txt" % prefix), sep='\t',
float_format="%f", na_rep=0, index_label="#MODULE ID")
out_kegg_pathways_df.to_csv(os.path.join(output, "%s.kegg.pathways.txt" % prefix), sep='\t', float_format="%d",
na_rep=0, index_label="#PATHWAY ID")
out_kegg_pathways_coverage.to_csv(os.path.join(output, "%s.kegg.pathways.coverage.txt" % prefix), sep='\t',
float_format="%f", na_rep=0, index_label="#PATHWAY ID")