Mercurial > repos > earlhaminst > gstf_preparation

comparison gstf_preparation.py @ 14:598e9172b8e7 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/TGAC/earlham-galaxytools/tree/master/tools/gstf_preparation commit ea67c766934266e690d05e3f9ebb4cca12b8e3e7"
author earlhaminst
date Fri, 18 Dec 2020 08:57:43 +0000
parents 51a7a2a82902
children 9c62ad7dd113
comparison
equal deleted inserted replaced
13:51a7a2a82902 14:598e9172b8e7
213 found_cds = False 213 found_cds = False
214 derived_translation_start = None 214 derived_translation_start = None
215 derived_translation_end = None 215 derived_translation_end = None
216 if transcript_id in cds_parent_dict: 216 if transcript_id in cds_parent_dict:
217 cds_list = cds_parent_dict[transcript_id] 217 cds_list = cds_parent_dict[transcript_id]
218 cds_ids = {_['id'] for _ in cds_list} 218 unique_cds_ids = {cds['id'] for cds in cds_list}
219 if len(cds_ids) > 1: 219 if len(unique_cds_ids) > 1:
220 raise Exception("Transcript %s has multiple CDSs: this is not supported by Ensembl JSON format" % transcript_id) 220 msg = """Found multiple CDS IDs (%s) for transcript '%s'.
221 cds_id = cds_ids.pop() 221 This is not supported by the Ensembl JSON format. If a CDS is split across
222 multiple discontinuous genomic locations, the GFF3 standard requires that all
223 corresponding lines use the same ID attribute."""
224 raise Exception(msg % (unique_cds_ids, transcript_id))
225 cds_id = unique_cds_ids.pop()
222 translation['id'] = cds_id 226 translation['id'] = cds_id
223 cds_list.sort(key=lambda _: _['start']) 227 cds_list.sort(key=lambda _: _['start'])
224 translation['CDS'] = cds_list 228 translation['CDS'] = cds_list
225 translation['start'] = cds_list[0]['start'] 229 translation['start'] = cds_list[0]['start']
226 translation['end'] = cds_list[-1]['end'] 230 translation['end'] = cds_list[-1]['end']