Mercurial > repos > galaxyp > peptide_genomic_coordinate

annotate peptide_genomic_coordinate.py @ 0:5f49ffce52cb draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
author galaxyp
date Wed, 03 Apr 2019 04:04:18 -0400
parents
children cb0378d2d487
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
1 #!/usr/bin/env python
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
2 #
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
3 # Author: Praveen Kumar
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
4 # University of Minnesota
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
5 #
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
6 # Get peptide's genomic coordinate from the protein's genomic mapping sqlite file (which is derived from the https://toolshed.g2.bx.psu.edu/view/galaxyp/translate_bed/038ecf54cbec)
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
7 #
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
8 # python peptideGenomicCoordinate.py <peptide_list> <mz_to_sqlite DB> <genomic mapping file DB> <output.bed>
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
9 #
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
10 import sys
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
11 import sqlite3
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
12
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
13
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
14 def main():
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
15 conn = sqlite3.connect(sys.argv[2])
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
16 c = conn.cursor()
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
17 c.execute("DROP table if exists novel")
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
18 conn.commit()
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
19 c.execute("CREATE TABLE novel(peptide text)")
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
20 pepfile = open(sys.argv[1],"r")
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
21
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
22 pep_seq = []
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
23 for seq in pepfile.readlines():
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
24 seq = seq.strip()
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
25 pep_seq.append(tuple([seq]))
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
26
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
27 c.executemany("insert into novel(peptide) values(?)", pep_seq)
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
28 conn.commit()
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
29
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
30 c.execute("SELECT distinct psm.sequence, ps.id, ps.sequence from db_sequence ps, psm_entries psm, novel n, proteins_by_peptide pbp where psm.sequence = n.peptide and pbp.peptide_ref = psm.id and pbp.id = ps.id")
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
31 rows = c.fetchall()
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
32
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
33 conn1 = sqlite3.connect(sys.argv[3])
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
34 c1 = conn1.cursor()
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
35
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
36 outfh = open(sys.argv[4], "w")
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
37
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
38 master_dict = {}
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
39 for each in rows:
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
40 peptide = each[0]
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
41 acc = each[1]
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
42 acc_seq = each[2]
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
43
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
44 c1.execute("SELECT chrom,start,end,name,strand,cds_start,cds_end FROM feature_cds_map map WHERE map.name = '"+acc+"'")
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
45 coordinates = c1.fetchall()
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
46
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
47 if len(coordinates) != 0:
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
48 pep_start = 0
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
49 pep_end = 0
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
50 flag = 0
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
51 splice_flag = 0
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
52 spliced_peptide = []
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
53 for each_entry in coordinates:
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
54 chromosome = each_entry[0]
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
55 start = int(each_entry[1])
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
56 end = int(each_entry[2])
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
57 strand = each_entry[4]
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
58 cds_start = int(each_entry[5])
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
59 cds_end = int(each_entry[6])
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
60 pep_pos_start = (acc_seq.find(peptide)*3)
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
61 pep_pos_end = pep_pos_start + (len(peptide)*3)
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
62 if pep_pos_start >= cds_start and pep_pos_end <= cds_end:
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
63 if strand == "+":
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
64 pep_start = start + pep_pos_start - cds_start
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
65 pep_end = start + pep_pos_end - cds_start
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
66 pep_thick_start = 0
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
67 pep_thick_end = len(peptide)
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
68 flag == 1
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
69 else:
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
70 pep_end = end - pep_pos_start + cds_start
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
71 pep_start = end - pep_pos_end + cds_start
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
72 pep_thick_start = 0
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
73 pep_thick_end = len(peptide)
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
74 flag == 1
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
75 spliced_peptide = []
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
76 splice_flag = 0
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
77 else:
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
78 if flag == 0:
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
79 if strand == "+":
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
80 if pep_pos_start >= cds_start and pep_pos_start <= cds_end and pep_pos_end > cds_end:
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
81 pep_start = start + pep_pos_start - cds_start
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
82 pep_end = end
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
83 pep_thick_start = 0
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
84 pep_thick_end = (pep_end-pep_start)
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
85 spliced_peptide.append([pep_start,pep_end,pep_thick_start,pep_thick_end])
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
86 splice_flag = splice_flag + 1
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
87 if splice_flag == 2:
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
88 flag = 1
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
89 elif pep_pos_end >= cds_start and pep_pos_end <= cds_end and pep_pos_start < cds_start:
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
90 pep_start = start
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
91 pep_end = start + pep_pos_end - cds_start
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
92 pep_thick_start = (len(peptide)*3)-(pep_end-pep_start)
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
93 pep_thick_end = (len(peptide)*3)
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
94 spliced_peptide.append([pep_start,pep_end,pep_thick_start,pep_thick_end])
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
95 splice_flag = splice_flag + 1
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
96 if splice_flag == 2:
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
97 flag = 1
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
98 else:
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
99 pass
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
100 else:
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
101 if pep_pos_start >= cds_start and pep_pos_start <= cds_end and pep_pos_end >= cds_end:
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
102 pep_start = start
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
103 pep_end = end - pep_pos_start - cds_start
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
104 pep_thick_start = 0
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
105 pep_thick_end = (pep_end-pep_start)
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
106 spliced_peptide.append([pep_start,pep_end,pep_thick_start,pep_thick_end])
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
107 splice_flag = splice_flag + 1
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
108 if splice_flag == 2:
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
109 flag = 1
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
110 elif pep_pos_end >= cds_start and pep_pos_end <= cds_end and pep_pos_start <= cds_start:
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
111 pep_start = end - pep_pos_end + cds_start
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
112 pep_end = end
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
113 pep_thick_start = (len(peptide)*3)-(pep_end-pep_start)
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
114 pep_thick_end = (len(peptide)*3)
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
115 spliced_peptide.append([pep_start,pep_end,pep_thick_start,pep_thick_end])
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
116 splice_flag = splice_flag + 1
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
117 if splice_flag == 2:
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
118 flag = 1
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
119 else:
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
120 pass
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
121
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
122 if len(spliced_peptide) == 0:
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
123 if strand == "+":
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
124 bed_line = [chromosome, str(pep_start), str(pep_end), peptide, "255", strand, str(pep_start), str(pep_end), "0", "1", str(pep_end-pep_start), "0"]
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
125 else:
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
126 bed_line = [chromosome, str(pep_start), str(pep_end), peptide, "255", strand, str(pep_start), str(pep_end), "0", "1", str(pep_end-pep_start), "0"]
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
127 outfh.write("\t".join(bed_line)+"\n")
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
128 else:
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
129 if strand == "+":
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
130 pep_entry = spliced_peptide
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
131 pep_start = min([pep_entry[0][0], pep_entry[1][0]])
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
132 pep_end = max([pep_entry[0][1], pep_entry[1][1]])
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
133 blockSize = [str(min([pep_entry[0][3], pep_entry[1][3]])),str(max([pep_entry[0][3], pep_entry[1][3]])-min([pep_entry[0][3], pep_entry[1][3]]))]
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
134 blockStarts = ["0", str(pep_end-pep_start-(max([pep_entry[0][3], pep_entry[1][3]])-min([pep_entry[0][3], pep_entry[1][3]])))]
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
135 bed_line = [chromosome, str(pep_start), str(pep_end), peptide, "255", strand, str(pep_start), str(pep_end), "0", "2", ",".join(blockSize), ",".join(blockStarts)]
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
136 outfh.write("\t".join(bed_line)+"\n")
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
137 else:
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
138 pep_entry = spliced_peptide
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
139 pep_start = min([pep_entry[0][0], pep_entry[1][0]])
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
140 pep_end = max([pep_entry[0][1], pep_entry[1][1]])
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
141 blockSize = [str(min([pep_entry[0][3], pep_entry[1][3]])),str(max([pep_entry[0][3], pep_entry[1][3]])-min([pep_entry[0][3], pep_entry[1][3]]))]
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
142 blockStarts = ["0", str(pep_end-pep_start-(max([pep_entry[0][3], pep_entry[1][3]])-min([pep_entry[0][3], pep_entry[1][3]])))]
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
143 bed_line = [chromosome, str(pep_start), str(pep_end), peptide, "255", strand, str(pep_start), str(pep_end), "0", "2", ",".join(blockSize), ",".join(blockStarts)]
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
144 outfh.write("\t".join(bed_line)+"\n")
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
145 c.execute("DROP table novel")
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
146 conn.commit()
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
147 conn.close()
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
148 conn1.close()
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
149 outfh.close()
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
150 pepfile.close()
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
151
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
152 return None
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
153 if __name__ == "__main__":
5f49ffce52cb planemo upload commit be7e9677908b7864ef0b965a1e219a1840eeb2ec
galaxyp
parents:
diff changeset
154 main()