panacheextract 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/lib/panacheextract.rb +92 -0
- metadata +44 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA256:
|
3
|
+
metadata.gz: 7c47ef9d287de51706ed3392b4cb172077b21f203dcda5df4f91249f1af85e2a
|
4
|
+
data.tar.gz: 8a36048fe0516f70386ff1f8031c8edf516fa3f178d2269c2595ea34a56da044
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 1654b6df0c0c3435ddef07ac440b55a21f4c5336d9bf80e885519245fc0db900714fa2106eb855c91696258b39a8dc4035cb3aefe13e68c39bca8d58a476c245
|
7
|
+
data.tar.gz: f86c07f3e77e30c4db796d01d3fdf700f0395edf822a2f8ab8e8dbcc36b466c3544d50e0b87dc694dd5b79b06278591261a72dd17803cf352711afc3ab6063cb
|
@@ -0,0 +1,92 @@
|
|
1
|
+
#!/usr/bin/ruby
|
2
|
+
=begin
|
3
|
+
Author Gaurav Sablok
|
4
|
+
Universitat Potsdam
|
5
|
+
Date: 2024-4-8
|
6
|
+
a block comment iterator for the taf files using the hash iterator.
|
7
|
+
for faster iterations, i implemented the alignment corrdinate as a key unique,
|
8
|
+
so that it can be called easily. Instead of iterating through the lines, i stored
|
9
|
+
the values in a hash and then implemented the hash search, so that it search for
|
10
|
+
those specific hashes rather than going line by line.
|
11
|
+
=end
|
12
|
+
|
13
|
+
CLASS READTAF
|
14
|
+
=begin
|
15
|
+
a class initator and use this with the input file
|
16
|
+
to initiate the class for the file reading and then
|
17
|
+
use the additional functions to make the taf file format
|
18
|
+
conversions.
|
19
|
+
=end
|
20
|
+
def inititalize(inputfile, outputfile, stringvalues, sequenceids)
|
21
|
+
=begin
|
22
|
+
stringvalues represent the column third of the MAF alignments
|
23
|
+
=end
|
24
|
+
@readfile = inputfile
|
25
|
+
@outputfile = outfile
|
26
|
+
end
|
27
|
+
|
28
|
+
def getspecific(ids, inputalignment, outalignmentfile)
|
29
|
+
readiter = File.open(inputalignment, "r").readlines
|
30
|
+
writefile = File.new(outalignmentfile, "w")
|
31
|
+
for i in 0..readiter.length
|
32
|
+
writefile.write(readiter[i]) if readiter[i].to_s.strip.split[0] == "s"
|
33
|
+
end
|
34
|
+
writefile.close
|
35
|
+
readopen = File.open(outalignmentfile, "r").readlines
|
36
|
+
idsequences = []
|
37
|
+
idstrings = []
|
38
|
+
for i in 0..readopen.length
|
39
|
+
idsequences.push(readopen[i].to_s.strip.split[6])
|
40
|
+
idstrings.push(readopen[i].to_s.strip.split[1])
|
41
|
+
end
|
42
|
+
select = []
|
43
|
+
for i in 0..idstrings.length
|
44
|
+
select.push([idstrings[i],idsequences[i]]) if idstrings[i] == ids
|
45
|
+
end
|
46
|
+
return(select)
|
47
|
+
end
|
48
|
+
|
49
|
+
def getspecific(ids, inputalignment, outalignmentfile, del = "None")
|
50
|
+
if del == "None"
|
51
|
+
readiter = File.open(inputalignment, "r").readlines
|
52
|
+
writefile = File.new(outalignmentfile, "w")
|
53
|
+
for i in 0..readiter.length
|
54
|
+
writefile.write(readiter[i]) if readiter[i].to_s.strip.split[0] == "s"
|
55
|
+
end
|
56
|
+
writefile.close
|
57
|
+
readopen = File.open(outalignmentfile, "r").readlines
|
58
|
+
idsequences = []
|
59
|
+
idstrings = []
|
60
|
+
for i in 0..readopen.length
|
61
|
+
idsequences.push(readopen[i].to_s.strip.split[6])
|
62
|
+
idstrings.push(readopen[i].to_s.strip.split[1])
|
63
|
+
end
|
64
|
+
select = []
|
65
|
+
for i in 0..idstrings.length
|
66
|
+
select.push([idstrings[i],idsequences[i]]) if idstrings[i] == ids
|
67
|
+
end
|
68
|
+
return(select)
|
69
|
+
end
|
70
|
+
if del != "None"
|
71
|
+
readiter = File.open(inputalignment, "r").readlines
|
72
|
+
writefile = File.new(outalignmentfile, "w")
|
73
|
+
for i in 0..readiter.length
|
74
|
+
writefile.write(readiter[i]) if readiter[i].to_s.strip.split[0] == "s"
|
75
|
+
end
|
76
|
+
writefile.close
|
77
|
+
readopen = File.open(outalignmentfile, "r").readlines
|
78
|
+
idsequences = []
|
79
|
+
idstrings = []
|
80
|
+
for i in 0..readopen.length
|
81
|
+
idsequences.push(readopen[i].to_s.strip.split[6])
|
82
|
+
idstrings.push(readopen[i].to_s.strip.split[1])
|
83
|
+
end
|
84
|
+
select = []
|
85
|
+
for i in 0..idstrings.length
|
86
|
+
select.push([idstrings[i],idsequences[i]]) if idstrings[i] == ids
|
87
|
+
end
|
88
|
+
delselect = []
|
89
|
+
select.each { | iter | delselect.push(iter) if iter[1].count("-") >= 1 }
|
90
|
+
return(delselect)
|
91
|
+
end
|
92
|
+
end
|
metadata
ADDED
@@ -0,0 +1,44 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: panacheextract
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Gaurav Sablok
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2024-04-09 00:00:00.000000000 Z
|
12
|
+
dependencies: []
|
13
|
+
description:
|
14
|
+
email:
|
15
|
+
executables: []
|
16
|
+
extensions: []
|
17
|
+
extra_rdoc_files: []
|
18
|
+
files:
|
19
|
+
- lib/panacheextract.rb
|
20
|
+
homepage: https://github.com/sablokgaurav/maf-taf-panache
|
21
|
+
licenses:
|
22
|
+
- MIT
|
23
|
+
metadata: {}
|
24
|
+
post_install_message:
|
25
|
+
rdoc_options: []
|
26
|
+
require_paths:
|
27
|
+
- lib
|
28
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
29
|
+
requirements:
|
30
|
+
- - ">="
|
31
|
+
- !ruby/object:Gem::Version
|
32
|
+
version: '0'
|
33
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
34
|
+
requirements:
|
35
|
+
- - ">="
|
36
|
+
- !ruby/object:Gem::Version
|
37
|
+
version: '0'
|
38
|
+
requirements: []
|
39
|
+
rubygems_version: 3.3.5
|
40
|
+
signing_key:
|
41
|
+
specification_version: 4
|
42
|
+
summary: making handling of the maf and the taf files easier, extraction of the alignments,
|
43
|
+
alignments with deletions, specific ids, sequences associated with specific ids
|
44
|
+
test_files: []
|