comparison gstf_preparation.py @ 14:598e9172b8e7 draft

"planemo upload for repository https://github.com/TGAC/earlham-galaxytools/tree/master/tools/gstf_preparation commit ea67c766934266e690d05e3f9ebb4cca12b8e3e7"

13:51a7a2a82902

        found_cds = False
        derived_translation_start = None
        derived_translation_end = None
        if transcript_id in cds_parent_dict:
            cds_list = cds_parent_dict[transcript_id]
            cds_ids = {_['id'] for _ in cds_list}
            if len(cds_ids) > 1:
                raise Exception("Transcript %s has multiple CDSs: this is not supported by Ensembl JSON format" % transcript_id)
            cds_id = cds_ids.pop()
            translation['id'] = cds_id
            cds_list.sort(key=lambda _: _['start'])
            translation['CDS'] = cds_list
            translation['start'] = cds_list[0]['start']
            translation['end'] = cds_list[-1]['end']

14:598e9172b8e7

        found_cds = False
        derived_translation_start = None
        derived_translation_end = None
        if transcript_id in cds_parent_dict:
            cds_list = cds_parent_dict[transcript_id]
            unique_cds_ids = {cds['id'] for cds in cds_list}
            if len(unique_cds_ids) > 1:
                msg = """Found multiple CDS IDs (%s) for transcript '%s'.
This is not supported by the Ensembl JSON format. If a CDS is split across
multiple discontinuous genomic locations, the GFF3 standard requires that all
corresponding lines use the same ID attribute."""
                raise Exception(msg % (unique_cds_ids, transcript_id))
            cds_id = unique_cds_ids.pop()
            translation['id'] = cds_id
            cds_list.sort(key=lambda _: _['start'])
            translation['CDS'] = cds_list
            translation['start'] = cds_list[0]['start']
            translation['end'] = cds_list[-1]['end']