def get_eggnog_taxid_info_file(): return pjoin(get_data_path(), "e5.taxid_info.tsv")
parser.add_argument('-y', action="store_true", dest='allyes', help='assume "yes" to all questions') parser.add_argument('-f', action="store_true", dest='force', help='forces download even if the files exist') parser.add_argument('-s', action="store_true", dest='simulate', help='simulate and print commands. Nothing is downloaded') args = parser.parse_args() if 'all' in args.dbs: args.dbs = EGGNOG_DATABASES if args.force or not pexists(pjoin(DATA_PATH, 'eggnog.db')): if args.allyes or ask("Download main annotation database?") == 'y': print colorify('Downloading "eggnog.db" at %s...' %DATA_PATH, 'green') download_annotations() else: print 'Skipping' else: print colorify('Skipping eggnog.db database (already present). Use -f to force download', 'lblue') if args.force or not pexists(pjoin(DATA_PATH, 'OG_fasta')): if args.allyes or ask("Download OG fasta files for annotation refinement (~20GB after decompression)?") == 'y': print colorify('Downloading fasta files " at %s/OG_fasta...' %DATA_PATH, 'green') download_groups() else: print 'Skipping'
def get_eggnog_proteins_file(): return pjoin(get_data_path(), "e5.proteomes.faa")
download_taxid_info(data_path) else: print( colorify( f'eggnog5 taxid info table was not found. Use --data_dir to specify another data path, or allow the download', 'red')) sys.exit(1) else: print( colorify( f'Using existing eggnog5 taxid info table found at {get_eggnog_taxid_info_file()}', 'green')) taxa_set = parse_taxa_table(get_eggnog_taxid_info_file(), args.taxids, args.taxa) proteins_out_file = pjoin(get_data_path(), f"{args.dbname}.faa") parse_proteins(proteins_out_file, get_eggnog_proteins_file(), taxa_set) # generate DB dbprefix = None if args.mode == "diamond": dbprefix = pjoin(get_data_path(), f'{args.dbname}.dmnd') create_diamond_db(dbprefix, proteins_out_file) elif args.mode == "mmseqs": dbdir = pjoin(get_data_path(), f'{args.dbname}.mmseqs') dbprefix = pjoin(get_data_path(), f'{args.dbname}.mmseqs', f'{args.dbname}.mmseqs') if not os.path.isdir(os.path.realpath(dbdir)): os.mkdir(dbdir)
args = parser.parse_args() if "EGGNOG_DATA_DIR" in os.environ: set_data_path(os.environ["EGGNOG_DATA_DIR"]) if args.data_dir: set_data_path(args.data_dir) # if args.force or not pexists(pjoin(get_data_path(), 'og2level.tsv.gz')): # print colorify('Downloading "og2level.tsv.gz" at %s' %get_data_path(), 'green') # download_og2level() # if 'all' in args.dbs: # args.dbs = EGGNOG_DATABASES if args.force or not pexists(pjoin(get_data_path(), 'eggnog.db')): if args.allyes or ask("Download main annotation database?") == 'y': print colorify( 'Downloading "eggnog.db" at %s...' % get_data_path(), 'green') download_annotations() else: print 'Skipping' else: if not args.quiet: print colorify( 'Skipping eggnog.db database (already present). Use -f to force download', 'lblue') # if args.force or not pexists(pjoin(get_data_path(), 'OG_fasta')): # if args.allyes or ask("Download OG fasta files for annotation refinement (~20GB after decompression)?") == 'y':
parser.add_argument('-q', action="store_true", dest='quiet', help='quiet_mode') parser.add_argument("--data_dir", metavar='', type=existing_dir, help='Directory to use for DATA_PATH.') args = parser.parse_args() if args.data_dir: set_data_path(args.data_dir) if args.force or not pexists(pjoin(get_data_path(), 'og2level.tsv.gz')): print colorify('Downloading "og2level.tsv.gz" at %s' % get_data_path(), 'green') download_og2level() if 'all' in args.dbs: args.dbs = EGGNOG_DATABASES if args.force or not pexists(pjoin(get_data_path(), 'eggnog.db')): if args.allyes or ask("Download main annotation database?") == 'y': print colorify( 'Downloading "eggnog.db" at %s...' % get_data_path(), 'green') download_annotations() else: print 'Skipping'