Mercurial > repos > yating-l > jbrowsearchivecreator

comparison bedToGff3.py @ 0:804a93e87cc8 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/Yating-L/jbrowse_hub commit f22711ea7a464bdaf4d5aaea07f2eacf967aa66e-dirty
author yating-l
date Wed, 12 Apr 2017 17:41:55 -0400
parents
children 7e471cdd9e71
comparison
equal deleted inserted replaced
-1:000000000000 0:804a93e87cc8
1 #!/usr/bin/env python
2
3 '''
4 Convert BED format to gff3
5 '''
6 import os
7 from collections import OrderedDict
8 import utils
9
10 class bedToGff3():
11 def __init__(self, inputBedFile, chrom_sizes, bed_type, output):
12 self.input = inputBedFile
13 #file_dir = os.path.basename(inputBedFile)
14 #print file_dir + "\n\n"
15 self.output = output
16 self.chrom_sizes = chrom_sizes
17 self.type = bed_type
18 if self.type == "trfbig":
19 self.trfbig_to_gff3()
20 if self.type == "regtools":
21 self.splicejunctions_to_gff3()
22
23 def trfbig_to_gff3(self):
24 gff3 = open(self.output, 'w')
25 gff3.write("##gff-version 3\n")
26 sizes_dict = utils.sequence_region(self.chrom_sizes)
27 seq_regions = dict()
28 with open(self.input, 'r') as bed:
29 for line in bed:
30 field = OrderedDict()
31 attribute = OrderedDict()
32 li = line.rstrip().split("\t")
33 field['seqid'] = li[0]
34 if field['seqid'] not in seq_regions:
35 end_region = sizes_dict[field['seqid']]
36 gff3.write("##sequence-region " + field['seqid'] + ' 1 ' + str(end_region) + '\n')
37 seq_regions[field['seqid']] = end_region
38 field['source'] = li[3]
39 field['type'] = 'tandem_repeat'
40 # The first base in a chromosome is numbered 0 in BED format
41 field['start'] = str(int(li[1]) + 1)
42 field['end'] = li[2]
43 field['score'] = li[9]
44 field['strand'] = '+'
45 field['phase'] = '.'
46 attribute['length of repeat unit'] = li[4]
47 attribute['mean number of copies of repeat'] = li[5]
48 attribute['length of consensus sequence'] = li[6]
49 attribute['percentage match'] = li[7]
50 attribute['percentage indel'] = li[8]
51 attribute['percent of a\'s in repeat unit'] = li[10]
52 attribute['percent of c\'s in repeat unit'] = li[11]
53 attribute['percent of g\'s in repeat unit'] = li[12]
54 attribute['percent of t\'s in repeat unit'] = li[13]
55 attribute['entropy'] = li[14]
56 attribute['sequence of repeat unit element'] = li[15]
57 utils.write_features(field, attribute, gff3)
58 gff3.close()
59
60
61 def splicejunctions_to_gff3(self):
62 gff3 = open(self.output, 'w')
63 gff3.write("##gff-version 3\n")
64 sizes_dict = utils.sequence_region(self.chrom_sizes)
65 seq_regions = dict()
66 with open(self.input, 'r') as bed:
67 for line in bed:
68 field = OrderedDict()
69 attribute = OrderedDict()
70 li = line.rstrip().split("\t")
71 field['seqid'] = li[0]
72 if field['seqid'] not in seq_regions:
73 end_region = sizes_dict[field['seqid']]
74 gff3.write("##sequence-region " + field['seqid'] + ' 1 ' + str(end_region) + '\n')
75 seq_regions[field['seqid']] = end_region
76 field['source'] = li[3]
77 field['type'] = 'junction'
78 # The first base in a chromosome is numbered 0 in BED format
79 field['start'] = int(li[1]) + 1
80 field['end'] = li[2]
81 field['score'] = li[12]
82 field['strand'] = li[5]
83 field['phase'] = '.'
84 attribute['ID'] = li[3]
85 attribute['Name'] = li[3]
86 attribute['blockcount'] = li[9]
87 attribute['blocksizes'] = li[10]
88 attribute['chromstarts'] = li[11]
89 utils.write_features(field, attribute, gff3)
90 utils.child_blocks(field, attribute, gff3)
91 gff3.close()
92