dsmz-match.snakefile

configfile: 'config.yaml'

import glob

rule match:
    '''
    Match strain names to NCBI nodes.
    This step uses `alvisnlp`.
    '''
    output:
        directory(config['OUTDIR'] + '/' + config['DSMZ_MATCH_DIR'])

    input:
        config['OUTDIR'] + '/' + config['DSMZ_STRAINS_DIR']

    shell: '''./dsmz-match.py {config[TAXA_FILE]} {input} {output}'''