comparison fix-aragorn-gff3.py @ 3:f0f0ab9db43f draft

planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
author cpt
date Mon, 05 Jun 2023 02:42:12 +0000
parents
children 733cb0807083
comparison
equal deleted inserted replaced
2:dc22c76a57bd 3:f0f0ab9db43f
1 #!/usr/bin/env python
2 import sys
3 import logging
4 import argparse
5 from CPT_GFFParser import gffParse, gffWrite, gffSeqFeature
6 from Bio.SeqFeature import SeqFeature
7 from gff3 import feature_lambda, feature_test_type
8
9 logging.basicConfig(level=logging.INFO)
10 log = logging.getLogger(__name__)
11
12
13 def fixed_feature(rec):
14 for idx, feature in enumerate(
15 feature_lambda(
16 rec.features,
17 feature_test_type,
18 {"types": ["tRNA", "tmRNA"]},
19 subfeatures=True,
20 )
21 ):
22
23 fid = "%s-%03d" % (feature.type, 1 + idx)
24 try:
25 name = [feature.type + "-" + feature.qualifiers["Codon"][0]]
26 except KeyError:
27 name = [feature.qualifiers["product"][0]]
28 try:
29 origSource = feature.qualifiers["source"][0]
30 except:
31 origSource = "."
32 gene = gffSeqFeature(
33 location=feature.location,
34 type="gene",
35 qualifiers={"ID": [fid + ".gene"], "source": [origSource], "Name": name},
36 )
37 feature.qualifiers["Name"] = name
38 # Below that we have an mRNA
39 exon = gffSeqFeature(
40 location=feature.location,
41 type="exon",
42 qualifiers={"source": [origSource], "ID": ["%s.exon" % fid], "Name": name},
43 )
44 feature.qualifiers["ID"] = [fid]
45 exon.qualifiers["Parent"] = [fid]
46 feature.qualifiers["Parent"] = [fid + ".gene"]
47 # gene -> trna -> exon
48 feature.sub_features = [exon]
49 gene.sub_features = [feature]
50 yield gene
51
52
53 def gff_filter(gff3):
54 found_gff = False
55 for rec in gffParse(gff3):
56 found_gff = True
57 rec.features = sorted(list(fixed_feature(rec)), key=lambda x: x.location.start)
58 rec.annotations = {}
59 gffWrite([rec], sys.stdout)
60 if not found_gff:
61 print("##gff-version 3")
62
63
64 if __name__ == "__main__":
65 parser = argparse.ArgumentParser(description="add parent gene features to CDSs")
66 parser.add_argument("gff3", type=argparse.FileType("r"), help="GFF3 annotations")
67 args = parser.parse_args()
68 gff_filter(**vars(args))