def main(args):
# setup menu with argparse
class MyFormatter(argparse.ArgumentDefaultsHelpFormatter):
def __init__(self, prog):
super(MyFormatter, self).__init__(prog, max_help_position=48)
parser = argparse.ArgumentParser(prog='gff2prot.py',
description='''Script to convert GFF3 and FASTA proteins.''',
epilog="""Written by Jon Palmer (2018) [email protected]""",
formatter_class=MyFormatter)
parser.add_argument('-g', '--gff3', required=True,
help='Genome annotation GFF3 format')
parser.add_argument('-f', '--fasta', required=True,
help='Genome in FASTA format')
parser.add_argument('--no_stop', action='store_true',
help='Dont print stop codon')
args = parser.parse_args(args)
# translate GFF3 to proteins
# load into dictionary
Genes = {}
Genes = lib.gff2dict(args.gff3, args.fasta, Genes)
for k, v in natsorted(Genes.items()):
for i, x in enumerate(v['ids']):
if args.no_stop:
Prot = v['protein'][i].rstrip('*')
else:
Prot = v['protein'][i]
sys.stdout.write('>%s %s\n%s\n' % (x, k, Prot))
def main(args):
# setup menu with argparse
class MyFormatter(argparse.ArgumentDefaultsHelpFormatter):
def __init__(self, prog):
super(MyFormatter, self).__init__(prog, max_help_position=48)
parser = argparse.ArgumentParser(
prog='gff2prot.py',
description=
'''Script to convert GFF3 and FASTA to tbl, proteins, transcripts.''',
epilog="""Written by Jon Palmer (2018) [email protected]""",
formatter_class=MyFormatter)
parser.add_argument('-g',
'--gff3',
required=True,
help='Genome annotation GFF3 format')
parser.add_argument('-f',
'--fasta',
required=True,
help='Genome in FASTA format')
args = parser.parse_args(args)
# load into dictionary
Genes = {}
Genes = lib.gff2dict(args.gff3, args.fasta, Genes)
# sort the dictionary
def _sortDict(d):
return (d[1]['location'][0], d[1]['location'][1])
# now sort dictionary by contig and location, rename using prefix, translate to protein space to get proper start/stop info
sGenes = sorted(iter(Genes.items()), key=_sortDict)
sortedGenes = OrderedDict(sGenes)
scaff2genes = {}
for k, v in list(sortedGenes.items()):
if not v['contig'] in scaff2genes:
scaff2genes[v['contig']] = [k]
else:
scaff2genes[v['contig']].append(k)
# get length of scaffolds
scaffLen = scaffold2Dict(args.fasta)
# now write table
dicts2tbl(sortedGenes,
scaff2genes,
scaffLen,
'CFMR',
'12345',
annotations=True)
def main(args):
# setup menu with argparse
class MyFormatter(argparse.ArgumentDefaultsHelpFormatter):
def __init__(self, prog):
super(MyFormatter, self).__init__(prog, max_help_position=48)
parser = argparse.ArgumentParser(prog='gff_reformat.py',
description='''Script to rename gene models GFF3 file.''',
epilog="""Written by Jon Palmer (2020) [email protected]""",
formatter_class=MyFormatter)
parser.add_argument('-g', '--gff3', required=True,
help='Genome annotation GFF3 format')
parser.add_argument('-f', '--fasta', required=True,
help='Genome in FASTA format')
parser.add_argument('-l', '--locus_tag', default='FUN',
help='Basename of gene names')
parser.add_argument('-n', '--numbering', default=1, type=int,
help='Start numbering at')
parser.add_argument('-o', '--out', required=True, help='Output GFF3')
args = parser.parse_args(args)
# load into dictionary
Genes = {}
Genes = lib.gff2dict(args.gff3, args.fasta, Genes)
print('Parsed {:,} gene models from {}'.format(len(Genes), args.gff3))
# now create ordered dictionary and sort by contig and position
def _sortDict(d):
return (d[1]['contig'], d[1]['location'][0])
sGenes = natsorted(iter(Genes.items()), key=_sortDict)
sortedGenes = OrderedDict(sGenes)
renamedGenes = {}
counter = args.numbering
args.locus_tag = args.locus_tag.rstrip('_')
transcripts = 0
for k, v in list(sortedGenes.items()):
locusTag = args.locus_tag+'_'+str(counter).zfill(6)
renamedGenes[locusTag] = v
renamedGenes[locusTag]['gene_synonym'].append(k)
newIds = []
for i in range(0, len(v['ids'])):
newIds.append('{}-T{}'.format(locusTag, i+1))
transcripts += 1
renamedGenes[locusTag]['ids'] = newIds
counter += 1
# write to gff3
lib.dict2gff3(renamedGenes, args.out)
print('Sorted and renamed {:,} gene models {:,} transcripts: {}'.format(
len(renamedGenes), transcripts, args.out))