Mercurial > repos > artbio > mircounts

comparison mature_mir_gff_translation.py @ 0:da29af78a960 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mircounts commit d4d8106d66b65679a1a685ab94bfcf99cdb7b959
author artbio
date Mon, 24 Jul 2017 06:27:50 -0400
parents
children 6b8adacd4750
comparison
equal deleted inserted replaced
-1:000000000000 0:da29af78a960
1 #!/usr/bin/env python
2
3 import sys
4 import argparse
5
6
7 def Parser():
8 the_parser = argparse.ArgumentParser()
9 the_parser.add_argument(
10 '--input', action="store", type=str, help="input miRBase GFF3 file")
11 the_parser.add_argument(
12 '--output', action="store", type=str, help="output GFF3 file with converted mature mir coordinates")
13 args = the_parser.parse_args()
14 return args
15
16 GFF3_header= '''##gff-version 3
17 ##generated by mature_mir_gff_translation.py
18 #
19 # Chromosomal coordinates of microRNAs ** relative to the hairpin precursors **
20 # microRNAs: miRBase current_version
21 # genome-build-id: check http://mirbase.org/
22 #
23 # Hairpin precursor sequences have type "miRNA_primary_transcript".
24 # Note, these sequences do not represent the full primary transcript,
25 # rather a predicted stem-loop portion that includes the precursor
26 # miRNA. Mature sequences have type "miRNA".
27 #
28 '''
29
30 def load_gff_in_dict(gff_input_file):
31 '''
32 Reads the gff3 file and return a dictionary of dictionaries
33 with keys equal to standard gff3 fields (9)
34 Note that the key of the primary dictionary is the ID
35 '''
36 gff_dict = {}
37 for line in open(gff_input_file, "r"):
38 if line[0]=="#":
39 continue
40 gff_fields=line[:-1].split("\t")
41 ID=gff_fields[8].split("ID=")[1].split(";")[0]
42 gff_dict[ID] = {}
43 gff_dict[ID]["seqid"]=gff_fields[0]
44 gff_dict[ID]["source"]=gff_fields[1]
45 gff_dict[ID]["type"]=gff_fields[2]
46 gff_dict[ID]["start"]=gff_fields[3]
47 gff_dict[ID]["end"]=gff_fields[4]
48 gff_dict[ID]["score"]=gff_fields[5]
49 gff_dict[ID]["strand"]=gff_fields[6]
50 gff_dict[ID]["phase"]=gff_fields[7]
51 gff_dict[ID]["attributes"]=gff_fields[8]
52 if "Derives_from" in gff_dict[ID]["attributes"]:
53 parent_primary_transcript=gff_dict[ID]["attributes"].split("Derives_from=")[1]
54 parent_primary_transcript=gff_dict[parent_primary_transcript]["attributes"].split("Name=")[1]
55 gff_dict[ID]["attributes"]="%s;Parent_mir_Name=%s" % (gff_dict[ID]["attributes"], parent_primary_transcript)
56 return gff_dict
57
58
59 def genome_to_mir_gff(gff_dict, output):
60 '''
61 Converts seqid field from chromosome to item Name
62 Then converts coordinates relative to "miRNA_primary_transcript"
63 Note that GFF files are 1-based coordinates
64 '''
65 for key in gff_dict:
66 name=gff_dict[key]["attributes"].split("Name=")[1].split(";")[0]
67 gff_dict[key]["seqid"]=name
68 if "Derives_from=" in gff_dict[key]["attributes"]:
69 parent_ID=gff_dict[key]["attributes"].split("Derives_from=")[1].split(";")[0]
70 gff_dict[key]["start"]=str(int(gff_dict[key]["start"]) - int(gff_dict[parent_ID]["start"]) + 1)
71 gff_dict[key]["end"]=str(int(gff_dict[key]["end"]) - int(gff_dict[parent_ID]["start"]) + 1)
72 hairpins={}
73 matures={}
74 for key in gff_dict: ## treats miRNA_primary_transcript coordinates in a second loop to avoid errors in conversion
75 if gff_dict[key]["type"]=="miRNA_primary_transcript":
76 gff_dict[key]["end"]=str(int(gff_dict[key]["end"]) - int(gff_dict[key]["start"]) + 1)
77 gff_dict[key]["start"]="1"
78 # now, do a dict[ID]=Name but only for miRNA_primary_transcript
79 hairpins[key]=gff_dict[key]["attributes"].split("Name=")[1].split(";")[0]
80 else:
81 matures[key]=gff_dict[key]["attributes"].split("Name=")[1].split(";")[0]
82 with open(output, "w") as output:
83 output.write(GFF3_header)
84 for ID in sorted(hairpins, key=hairpins.get):
85 output.write("\t".join([gff_dict[ID]["seqid"], gff_dict[ID]["source"],
86 gff_dict[ID]["type"], gff_dict[ID]["start"], gff_dict[ID]["end"],
87 gff_dict[ID]["score"], gff_dict[ID]["strand"], gff_dict[ID]["phase"],
88 gff_dict[ID]["attributes"]]))
89 output.write("\n")
90 for id in sorted(matures, key=matures.get, reverse=True):
91 if ID in gff_dict[id]["attributes"]:
92 output.write("\t".join([gff_dict[id]["seqid"], gff_dict[id]["source"],
93 gff_dict[id]["type"], gff_dict[id]["start"], gff_dict[id]["end"],
94 gff_dict[id]["score"], gff_dict[id]["strand"],
95 gff_dict[id]["phase"], gff_dict[id]["attributes"]]))
96 output.write("\n")
97
98
99 def main(infile, outfile):
100 gff_dict = load_gff_in_dict(infile)
101 genome_to_mir_gff(gff_dict, outfile)
102
103
104 if __name__ == "__main__":
105 args = Parser()
106 main(args.input, args.output)