@@ -1302,6 +1302,7 @@ def load_gff3(self, organism, gff3, source=None, batch_size=1,
13021302 test = False ,
13031303 use_name = False ,
13041304 disable_cds_recalculation = False ,
1305+ cds_cleaning = False ,
13051306 timing = False ,
13061307 ):
13071308 """
@@ -1328,6 +1329,13 @@ def load_gff3(self, organism, gff3, source=None, batch_size=1,
13281329 :type disable_cds_recalculation: bool
13291330 :param disable_cds_recalculation: Disable CDS recalculation and instead use the one provided
13301331
1332+ :type cds_cleaning: bool
1333+ :param cds_cleaning: This changes the behaviour of creating GFF3
1334+ features in apollo to match more closely to what it expects. Generally
1335+ you'll probably want this on if you have transcripts with multiple
1336+ exons and CDSs, but we don't want to change existing scripts
1337+ so we are not defaulting this on.
1338+
13311339 :type timing: bool
13321340 :param timing: Output loading performance metrics
13331341
@@ -1360,7 +1368,8 @@ def load_gff3(self, organism, gff3, source=None, batch_size=1,
13601368 log .info ("Processing %s with features: %s" % (rec .id , rec .features ))
13611369 processed = self ._process_gff_entry (rec , source = source ,
13621370 disable_cds_recalculation = disable_cds_recalculation ,
1363- use_name = use_name
1371+ use_name = use_name ,
1372+ cds_cleaning = cds_cleaning
13641373 )
13651374 all_processed ['top-level' ].extend (processed ['top-level' ])
13661375 all_processed ['transcripts' ].extend (processed ['transcripts' ])
0 commit comments