comparison assembly_post_processor.py @ 77:2849bcb0b7ed draft

Uploaded

76:ce5b201b7782

parser.add_argument('--dereplicate', dest='dereplicate', default=None, help='Remove duplicate sequences')
parser.add_argument('--gap_trimming', dest='gap_trimming', type=float, default=0, help='Trim alignments')
parser.add_argument('--gene_family_search', dest='gene_family_search', default=None, help='Targeted gene families')
parser.add_argument('--method', dest='method', default=None, help='Protein clustering method')
parser.add_argument('--min_length', dest='min_length', type=int, default=0, help='Minimum sequence length')
parser.add_argument('--move_stats', dest='move_stats', default=None, help='Flag to move primary targeted gene families statistics datasets')
parser.add_argument('--num_threads', dest='num_threads', type=int, help='Number of processors')
parser.add_argument('--output_cds', dest='output_cds', help='Output transcripts.cds')
parser.add_argument('--output_cleaned_cds', dest='output_cleaned_cds', help='Output transcripts.cleaned.cds')
parser.add_argument('--output_cleaned_nr_cds', dest='output_cleaned_nr_cds', default=None, help='Output transcripts.cleaned.nr.cds')
parser.add_argument('--output_cleaned_nr_pep', dest='output_cleaned_nr_pep', default=None, help='Output transcripts.cleaned.nr.pep')
parser.add_argument('--output_cleaned_pep', dest='output_cleaned_pep', help='Output transcripts.cleaned.pep')
parser.add_argument('--output_pep', dest='output_pep', help='Output transcripts.pep')
parser.add_argument('--prediction_method', dest='prediction_method', help='Coding regions prediction method')
parser.add_argument('--scaffold', dest='scaffold', default=None, help='Gene family scaffold')
parser.add_argument('--score_matrices', dest='score_matrices', default=None, help='Scores matrices')
parser.add_argument('--strand_specific', dest='strand_specific', default=None, help='Strand-specific assembly')
parser.add_argument('--transcripts', dest='transcripts', help='Transcriptome assembly fasta file')

    shutil.move(os.path.join(OUTPUT_DIR, 'transcripts.cleaned.nr.cds'), args.output_cleaned_nr_cds)
if args.output_cleaned_nr_pep is not None:
    shutil.move(os.path.join(OUTPUT_DIR, 'transcripts.cleaned.nr.pep'), args.output_cleaned_nr_pep)
shutil.move(os.path.join(OUTPUT_DIR, 'transcripts.cleaned.pep'), args.output_cleaned_pep)
shutil.move(os.path.join(OUTPUT_DIR, 'transcripts.pep'), args.output_pep)
if args.move_stats is not None:
    src_dir = os.path.join(OUTPUT_DIR, 'targeted_gene_families')
    dst_dir = os.path.join(OUTPUT_DIR, 'targeted_gene_families_statistics')
    try:
        shutil.move(os.path.join(src_dir, '*.stats'), dst_dir)
    except:
        pass

77:2849bcb0b7ed

parser.add_argument('--dereplicate', dest='dereplicate', default=None, help='Remove duplicate sequences')
parser.add_argument('--gap_trimming', dest='gap_trimming', type=float, default=0, help='Trim alignments')
parser.add_argument('--gene_family_search', dest='gene_family_search', default=None, help='Targeted gene families')
parser.add_argument('--method', dest='method', default=None, help='Protein clustering method')
parser.add_argument('--min_length', dest='min_length', type=int, default=0, help='Minimum sequence length')
parser.add_argument('--num_threads', dest='num_threads', type=int, help='Number of processors')
parser.add_argument('--output_pttgf', dest='output_pttgf', default=None, help='Primary targeted gene families dataset')
parser.add_argument('--output_cds', dest='output_cds', help='Output transcripts.cds')
parser.add_argument('--output_cleaned_cds', dest='output_cleaned_cds', help='Output transcripts.cleaned.cds')
parser.add_argument('--output_cleaned_nr_cds', dest='output_cleaned_nr_cds', default=None, help='Output transcripts.cleaned.nr.cds')
parser.add_argument('--output_cleaned_nr_pep', dest='output_cleaned_nr_pep', default=None, help='Output transcripts.cleaned.nr.pep')
parser.add_argument('--output_cleaned_pep', dest='output_cleaned_pep', help='Output transcripts.cleaned.pep')
parser.add_argument('--output_pep', dest='output_pep', help='Output transcripts.pep')
parser.add_argument('--output_pttgf_dir', dest='output_pttgf_dir', default=None, help='Directory hierarchy of targeted gene family datasets')
parser.add_argument('--prediction_method', dest='prediction_method', help='Coding regions prediction method')
parser.add_argument('--scaffold', dest='scaffold', default=None, help='Gene family scaffold')
parser.add_argument('--score_matrices', dest='score_matrices', default=None, help='Scores matrices')
parser.add_argument('--strand_specific', dest='strand_specific', default=None, help='Strand-specific assembly')
parser.add_argument('--transcripts', dest='transcripts', help='Transcriptome assembly fasta file')

    shutil.move(os.path.join(OUTPUT_DIR, 'transcripts.cleaned.nr.cds'), args.output_cleaned_nr_cds)
if args.output_cleaned_nr_pep is not None:
    shutil.move(os.path.join(OUTPUT_DIR, 'transcripts.cleaned.nr.pep'), args.output_cleaned_nr_pep)
shutil.move(os.path.join(OUTPUT_DIR, 'transcripts.cleaned.pep'), args.output_cleaned_pep)
shutil.move(os.path.join(OUTPUT_DIR, 'transcripts.pep'), args.output_pep)
if args.output_pttgf is not None and args.output_pttgf_dir is not None:
    src_output_dir = os.path.join(OUTPUT_DIR, 'targeted_gene_families')
    utils.move_directory_files(src_output_dir, args.output_pttgf_dir)
    utils.write_html_output(args.output_pttgf, 'Targeted gene families', args.output_pttgf_dir)