Mercurial > repos > iuc > data_manager_gemini_database_downloader
view data_manager/data_manager_gemini_download.py @ 6:f57426daa04d draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/data_managers/data_manager_gemini_database_downloader commit 62ed732cba355e695181924a8ed4cce49ca21c59
author | iuc |
---|---|
date | Fri, 11 Jan 2019 17:33:55 -0500 |
parents | b4b2b284230a |
children | 5bcf0e24f42c |
line wrap: on
line source
#!/usr/bin/env python import datetime import json import os import subprocess import sys import yaml def write_gemini_config(config, config_file): with open(config_file, 'w') as fo: yaml.dump(config, fo, allow_unicode=False, default_flow_style=False) def main(): today = datetime.date.today() params = json.loads( open( sys.argv[1] ).read() ) target_directory = params[ 'output_data' ][0]['extra_files_path'] os.mkdir( target_directory ) # Generate a minimal configuration file for GEMINI update # to instruct the tool to download the annotation data into a # subfolder of the target directory. config_file = os.path.join(target_directory, 'gemini-config.yaml') anno_dir = os.path.join(target_directory, 'gemini/data') gemini_bootstrap_config = {'annotation_dir': anno_dir} write_gemini_config(gemini_bootstrap_config, config_file) # Now gemini update can be called to download the data. # The GEMINI_CONFIG environment variable lets the tool discover # the configuration file we prepared for it. # Note that the tool will rewrite the file turning it into a # complete gemini configuration file. gemini_env = os.environ.copy() gemini_env['GEMINI_CONFIG'] = target_directory cmd = "gemini update --dataonly %s %s" % ( params['param_dict']['gerp_bp'], params['param_dict']['cadd'] ) subprocess.check_call( cmd, shell=True, env=gemini_env ) # GEMINI tool wrappers that need access to the annotation files # are supposed to symlink them into a gemini/data subfolder of # the job working directory. To have GEMINI discover them there, # we need to set this location as the 'annotation_dir' in the # configuration file. with open(config_file) as fi: config = yaml.load(fi) config['annotation_dir'] = 'gemini/data' write_gemini_config(config, config_file) # The name of the database should reflect whether it was built with or # without the optional GERP-bp data, the CADD scores, or both. # This builds up the correpsonding part of the name: anno_extras = [] if params['param_dict']['gerp_bp']: anno_extras.append('GERP') if params['param_dict']['cadd']: anno_extras.append('CADD') if anno_extras: anno_desc = ' w/ ' + ' & '.join(anno_extras) else: anno_desc = '' # Finally, we prepare the metadata for the new data table record ... data_manager_dict = { 'data_tables': { 'gemini_versioned_databases': [ { 'value': today.isoformat(), 'dbkey': 'hg19', 'version': params['param_dict']['gemini_db_version'], 'name': 'GEMINI annotations%s (%s snapshot)' % ( anno_desc, today.isoformat() ), 'path': './%s' % today.isoformat() } ] } } # ... and save it to the json results file with open( sys.argv[1], 'wb' ) as out: out.write( json.dumps( data_manager_dict ) ) if __name__ == "__main__": main()