comparison gene_family_classifier.py @ 133:b2ae23e484e8 draft

Uploaded

132:169504db8e43

BUFF_SIZE = 1048576
OUTPUT_DIR = 'geneFamilyClassification_dir'

parser = argparse.ArgumentParser()
parser.add_argument('--input', dest='input', help="Input dataset")
parser.add_argument('--scaffold', dest='scaffold', default='mode', help='Orthogroups or gene families proteins scaffold')
parser.add_argument('--method', dest='method', help='Protein clustering method')
parser.add_argument('--classifier', dest='classifier', help='Protein classification method')
parser.add_argument('--config_dir', dest='config_dir', help='Directory containing default configuration files')
parser.add_argument('--num_threads', dest='num_threads', type=int, help='Number of threads to use for execution')
parser.add_argument('--super_orthogroups', dest='super_orthogroups', default=None, help='Super orthogroups clustering specification')
parser.add_argument('--single_copy_custom', dest='single_copy_custom', default=None, help='Custom single copy orthogroup configuration')
parser.add_argument('--single_copy_taxa', dest='single_copy_taxa', type=int, default=None, help='"Minimum single copy taxa required in orthogroup')
parser.add_argument('--taxa_present', dest='taxa_present', type=int, default=None, help='Minimum taxa required in single copy orthogroup')
parser.add_argument('--orthogroup_fasta', dest='orthogroup_fasta', default=None, help='Flag to create orthogroup sequences')
parser.add_argument('--coding_sequences', dest='coding_sequences', default=None, help='Flag to create orthogroup coding sequences')
parser.add_argument('--save_hmmscan_log', dest='save_hmmscan_log', default=None, help='Flag to save the hmmscan log')
parser.add_argument('--hmmscan_log', dest='hmmscan_log', default=None, help='hmmscan log file')
parser.add_argument('--output_ptortho', dest='output_ptortho', default=None, help='Output for orthogroups')

cmd += ' --num_threads %d' % args.num_threads
if args.super_orthogroups is not None:
    cmd += ' --super_orthogroups %s' % args.super_orthogroups
if args.single_copy_custom is not None:
    cmd += ' --single_copy_custom %s' % args.single_copy_custom
if args.single_copy_taxa is not None:
    cmd += ' --single_copy_taxa %d' % args.single_copy_taxa
if args.taxa_present is not None:
    cmd += ' --taxa_present %d' % args.taxa_present
if args.orthogroup_fasta is None:
    create_ortho_sequences = False
else:
    create_ortho_sequences = True

133:b2ae23e484e8

BUFF_SIZE = 1048576
OUTPUT_DIR = 'geneFamilyClassification_dir'

parser = argparse.ArgumentParser()
parser.add_argument('--input', dest='input', help="Input dataset")
parser.add_argument('--scaffold', dest='scaffold', help='Orthogroups or gene families proteins scaffold')
parser.add_argument('--method', dest='method', help='Protein clustering method')
parser.add_argument('--classifier', dest='classifier', help='Protein classification method')
parser.add_argument('--config_dir', dest='config_dir', help='Directory containing default configuration files')
parser.add_argument('--num_threads', dest='num_threads', type=int, help='Number of threads to use for execution')
parser.add_argument('--super_orthogroups', dest='super_orthogroups', default=None, help='Super orthogroups clustering specification')
parser.add_argument('--single_copy_custom', dest='single_copy_custom', default=None, help='Custom single copy orthogroup configuration')
parser.add_argument('--single_copy_taxa', dest='single_copy_taxa', type=int, default=0, help='"Minimum single copy taxa required in orthogroup')
parser.add_argument('--taxa_present', dest='taxa_present', type=int, default=0, help='Minimum taxa required in single copy orthogroup')
parser.add_argument('--orthogroup_fasta', dest='orthogroup_fasta', default=None, help='Flag to create orthogroup sequences')
parser.add_argument('--coding_sequences', dest='coding_sequences', default=None, help='Flag to create orthogroup coding sequences')
parser.add_argument('--save_hmmscan_log', dest='save_hmmscan_log', default=None, help='Flag to save the hmmscan log')
parser.add_argument('--hmmscan_log', dest='hmmscan_log', default=None, help='hmmscan log file')
parser.add_argument('--output_ptortho', dest='output_ptortho', default=None, help='Output for orthogroups')

cmd += ' --num_threads %d' % args.num_threads
if args.super_orthogroups is not None:
    cmd += ' --super_orthogroups %s' % args.super_orthogroups
if args.single_copy_custom is not None:
    cmd += ' --single_copy_custom %s' % args.single_copy_custom
if args.single_copy_taxa > 0:
    cmd += ' --single_copy_taxa %d' % args.single_copy_taxa
if args.taxa_present > 0:
    cmd += ' --taxa_present %d' % args.taxa_present
if args.orthogroup_fasta is None:
    create_ortho_sequences = False
else:
    create_ortho_sequences = True