comparison gstf_preparation.py @ 12:99bae410128c draft

"planemo upload for repository https://github.com/TGAC/earlham-galaxytools/tree/master/tools/gstf_preparation commit 4579d0c461c30183a3092d84013e30f53f072ca1-dirty"

11:dbe37a658cd2

    for gene in gene_dict.values():
        if gene is None:
            # This can happen when loading a JSON file from Ensembl
            continue
        if 'confidence' in gene and gene['confidence'] != 'high':
            print("Gene %s has confidence %s (not high), discarding" % (gene['id'], gene['confidence']), file=sys.stderr)
            continue
        gene_id = gene['id']
        cur.execute('INSERT INTO gene (gene_id, gene_symbol, seq_region_name, seq_region_start, seq_region_end, seq_region_strand, species, biotype, gene_json) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)',
                    (gene_id, gene.get('display_name'), gene['seq_region_name'], gene['start'], gene['end'], gene['strand'], gene['species'], gene.get('biotype'), json.dumps(gene)))

    parser.add_option('--gff3', action='append', default=[], help='GFF3 file to convert, in SPECIES:FILENAME format. Use multiple times to add more files')
    parser.add_option('--json', action='append', default=[], help='JSON file to merge. Use multiple times to add more files')
    parser.add_option('--fasta', action='append', default=[], help='Path of the input FASTA files')
    parser.add_option('--filter', type='choice', choices=['canonical', 'coding', ''], default='', help='Which transcripts to keep')
    parser.add_option('--headers', type='choice',
                      choices=['TranscriptId_species', 'GeneSymbol-TranscriptID_species', 'TranscriptSymbol-TranscriptID_species', ''],
                      default='', help='Change the header line of the FASTA sequences to this format')
    parser.add_option('--regions', default="", help='Comma-separated list of region IDs for which FASTA sequences should be filtered')
    parser.add_option('-o', '--output', help='Path of the output SQLite file')
    parser.add_option('--of', help='Path of the output FASTA file')
    parser.add_option('--ff', default=os.devnull, help='Path of the filtered sequences output FASTA file')

                if options.headers == "TranscriptId_species":
                    # Change the FASTA header to '>TranscriptId_species', as required by TreeBest
                    # Remove any underscore in the species
                    entry.header = ">%s_%s" % (transcript_id, transcript['species'].replace('_', ''))
                elif options.headers == "GeneSymbol-TranscriptID_species":
                    # Remove any underscore in the species
                    entry.header = ">%s-%s_%s" % (transcript['gene_symbol'], transcript_id, transcript['species'].replace('_', ''))
                elif options.headers == "TranscriptSymbol-TranscriptID_species":
                    # Remove any underscore in the species
                    entry.header = ">%s-%s_%s" % (transcript['transcript_symbol'], transcript_id, transcript['species'].replace('_', ''))

                if transcript['seq_region_name'].lower() in regions:
                    entry.print(filtered_fasta_file)
                else:
                    entry.print(output_fasta_file)

12:99bae410128c

    for gene in gene_dict.values():
        if gene is None:
            # This can happen when loading a JSON file from Ensembl
            continue
        if 'confidence' in gene and gene['confidence'].lower() != 'high':
            print("Gene %s has confidence %s (not high), discarding" % (gene['id'], gene['confidence']), file=sys.stderr)
            continue
        gene_id = gene['id']
        cur.execute('INSERT INTO gene (gene_id, gene_symbol, seq_region_name, seq_region_start, seq_region_end, seq_region_strand, species, biotype, gene_json) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)',
                    (gene_id, gene.get('display_name'), gene['seq_region_name'], gene['start'], gene['end'], gene['strand'], gene['species'], gene.get('biotype'), json.dumps(gene)))

    parser.add_option('--gff3', action='append', default=[], help='GFF3 file to convert, in SPECIES:FILENAME format. Use multiple times to add more files')
    parser.add_option('--json', action='append', default=[], help='JSON file to merge. Use multiple times to add more files')
    parser.add_option('--fasta', action='append', default=[], help='Path of the input FASTA files')
    parser.add_option('--filter', type='choice', choices=['canonical', 'coding', ''], default='', help='Which transcripts to keep')
    parser.add_option('--headers', type='choice',
                      choices=['TranscriptId_species', 'TranscriptID-GeneSymbol_species', 'TranscriptID-TranscriptSymbol_species', ''],
                      default='', help='Change the header line of the FASTA sequences to this format')
    parser.add_option('--regions', default="", help='Comma-separated list of region IDs for which FASTA sequences should be filtered')
    parser.add_option('-o', '--output', help='Path of the output SQLite file')
    parser.add_option('--of', help='Path of the output FASTA file')
    parser.add_option('--ff', default=os.devnull, help='Path of the filtered sequences output FASTA file')

                if options.headers == "TranscriptId_species":
                    # Change the FASTA header to '>TranscriptId_species', as required by TreeBest
                    # Remove any underscore in the species
                    entry.header = ">%s_%s" % (transcript_id, transcript['species'].replace('_', ''))
                elif options.headers == "TranscriptID-GeneSymbol_species":
                    # Remove any underscore in the species
                    entry.header = ">%s-%s_%s" % (transcript_id, transcript['gene_symbol'], transcript['species'].replace('_', ''))
                elif options.headers == "TranscriptID-TranscriptSymbol_species":
                    # Remove any underscore in the species
                    entry.header = ">%s-%s_%s" % (transcript_id, transcript['transcript_symbol'], transcript['species'].replace('_', ''))

                if transcript['seq_region_name'].lower() in regions:
                    entry.print(filtered_fasta_file)
                else:
                    entry.print(output_fasta_file)