mapp2g 0.1.0

Sign up to get free protection for your applications and to get access to all the features.
checksums.yaml ADDED
@@ -0,0 +1,7 @@
1
+ ---
2
+ SHA256:
3
+ metadata.gz: 76678699954930f428361c012a062316f3b17bb349c44ce6a241749e97f3e056
4
+ data.tar.gz: 7cb65ee78628d7074cc2b639d24b85ca4c6ba682624b9c834cdd63e936676dfc
5
+ SHA512:
6
+ metadata.gz: e796d1e41c7e53b9ffb2550214a2479c654278bd21de549f4d7b94db4f231e5166c46e69f4fc71c9153ca9066395afc9aa60b4229b26515276126634377f89e0
7
+ data.tar.gz: dd87f0d6934a3a7ec0dec8a63f629d90edcb00c98f2d9ecf701ade80d84d7859ab6bffdd5156054e784d4ba9dd1f790f1c0202bd7810fa1ccf115470616f5155
data/.rspec ADDED
@@ -0,0 +1,3 @@
1
+ --format documentation
2
+ --color
3
+ --require spec_helper
data/Gemfile ADDED
@@ -0,0 +1,12 @@
1
+ # frozen_string_literal: true
2
+
3
+ source "https://rubygems.org"
4
+
5
+ # Specify your gem's dependencies in mapp2g.gemspec
6
+ gemspec
7
+
8
+ gem "rake", "~> 13.0"
9
+
10
+ gem "rspec", "~> 3.0"
11
+
12
+ gem "bio"
data/LICENSE.txt ADDED
@@ -0,0 +1,21 @@
1
+ The MIT License (MIT)
2
+
3
+ Copyright (c) 2023 Shuji Shigenobu
4
+
5
+ Permission is hereby granted, free of charge, to any person obtaining a copy
6
+ of this software and associated documentation files (the "Software"), to deal
7
+ in the Software without restriction, including without limitation the rights
8
+ to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
9
+ copies of the Software, and to permit persons to whom the Software is
10
+ furnished to do so, subject to the following conditions:
11
+
12
+ The above copyright notice and this permission notice shall be included in
13
+ all copies or substantial portions of the Software.
14
+
15
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16
+ IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17
+ FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
18
+ AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19
+ LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
20
+ OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
21
+ THE SOFTWARE.
data/README.md ADDED
@@ -0,0 +1,35 @@
1
+ # Mapp2g
2
+
3
+ TODO: Delete this and the text below, and describe your gem
4
+
5
+ Welcome to your new gem! In this directory, you'll find the files you need to be able to package up your Ruby library into a gem. Put your Ruby code in the file `lib/mapp2g`. To experiment with that code, run `bin/console` for an interactive prompt.
6
+
7
+ ## Installation
8
+
9
+ TODO: Replace `UPDATE_WITH_YOUR_GEM_NAME_PRIOR_TO_RELEASE_TO_RUBYGEMS_ORG` with your gem name right after releasing it to RubyGems.org. Please do not do it earlier due to security reasons. Alternatively, replace this section with instructions to install your gem from git if you don't plan to release to RubyGems.org.
10
+
11
+ Install the gem and add to the application's Gemfile by executing:
12
+
13
+ $ bundle add UPDATE_WITH_YOUR_GEM_NAME_PRIOR_TO_RELEASE_TO_RUBYGEMS_ORG
14
+
15
+ If bundler is not being used to manage dependencies, install the gem by executing:
16
+
17
+ $ gem install UPDATE_WITH_YOUR_GEM_NAME_PRIOR_TO_RELEASE_TO_RUBYGEMS_ORG
18
+
19
+ ## Usage
20
+
21
+ TODO: Write usage instructions here
22
+
23
+ ## Development
24
+
25
+ After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
26
+
27
+ To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and the created tag, and push the `.gem` file to [rubygems.org](https://rubygems.org).
28
+
29
+ ## Contributing
30
+
31
+ Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/mapp2g.
32
+
33
+ ## License
34
+
35
+ The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
data/Rakefile ADDED
@@ -0,0 +1,8 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "bundler/gem_tasks"
4
+ require "rspec/core/rake_task"
5
+
6
+ RSpec::Core::RakeTask.new(:spec)
7
+
8
+ task default: :spec
data/exe/mapp2g ADDED
@@ -0,0 +1,27 @@
1
+ #!/usr/bin/env ruby
2
+
3
+ require "mapp2g"
4
+ require 'bio'
5
+ require 'tempfile'
6
+
7
+ query = ARGV[0]
8
+ genome = ARGV[1]
9
+ outdir = (ARGV[2] || "mapp2g_out_#{$$}")
10
+ mapp2g_exe = "./mapp2g.rb"
11
+
12
+ Dir.mkdir(outdir)
13
+
14
+ Bio::FlatFile.open(Bio::FastaFormat, query).each_with_index do |fas, i|
15
+ tf = Tempfile.new("#{fas.entry_id}")
16
+ tf.puts fas
17
+ tf.close
18
+ id = (i + 1).to_s
19
+ query_file_path = "#{outdir}/#{id}.fasta"
20
+ out_file_path = "#{outdir}/#{id}.exonerate.txt"
21
+ File.open(query_file_path, "w"){|o| o.puts fas}
22
+
23
+ mapper = Mapp2g::Mapper.new()
24
+ res = mapper.run(query_file_path, genome)
25
+ File.open(out_file_path, "w"){|o| o.puts res}
26
+
27
+ end
@@ -0,0 +1,141 @@
1
+ require 'tempfile'
2
+
3
+ module Mapp2g
4
+
5
+ class Mapper
6
+
7
+ EVALUE_DEFAULT = 1.0e-8
8
+ NCPU_DEFAULT = 4
9
+ MAX_HSP_INTERVAL = 50000
10
+ EXTENSION = 50000
11
+ TMPDIR_DEFAULT = Dir.tmpdir
12
+
13
+ def initialize
14
+ end
15
+
16
+ ## step 1: tblastn
17
+ def exec_tblastn_to_know_rough_target_region(query, genome, evalue=EVALUE_DEFAULT, ncpu=NCPU_DEFAULT)
18
+ cmd = "tblastn -db #{genome} -query #{query} -max_target_seqs 40 -soft_masking yes -seg yes -outfmt 6 -evalue #{evalue} -num_threads #{ncpu} "
19
+ # puts cmd
20
+ res = nil
21
+ IO.popen(cmd){|io| res = io.read}
22
+ # puts res
23
+ if res == ""
24
+ ## no hit
25
+ return nil
26
+ else
27
+ lines = []
28
+ prev_chr = nil
29
+ res.split(/\n/).each do |l|
30
+ # p prev_chr
31
+ a = l.chomp.split(/\t/)
32
+ unless prev_chr
33
+ lines << l
34
+ prev_chr = a[1]
35
+ else
36
+ break if a[1] != prev_chr
37
+ lines << l
38
+ prev_chr = a[1]
39
+ end
40
+ end
41
+
42
+ a = lines.shift.chomp.split(/\t/)
43
+ left, right = [a[8].to_i, a[9].to_i].sort
44
+
45
+ STDERR.puts [left, right].inspect
46
+
47
+ lines.each do |l|
48
+ a = l.chomp.split(/\t/)
49
+ from, to = [a[8].to_i, a[9].to_i].sort
50
+ tmpary = [left, right, from, to].sort
51
+ new_left = tmpary.first
52
+ new_right = tmpary.last
53
+ if (new_left - left).abs < MAX_HSP_INTERVAL && (new_right - right).abs < MAX_HSP_INTERVAL
54
+ right = new_right
55
+ left = new_left
56
+ else
57
+ break
58
+ end
59
+ end
60
+ # p [left, right]
61
+
62
+ top_chromosome = res.split(/\n/)[0].split(/\t/)[1]
63
+ h = {
64
+ :top_chromosome => top_chromosome,
65
+ :left => left,
66
+ :right => right
67
+ }
68
+ return h
69
+ end
70
+ end
71
+
72
+
73
+ ## step 2: get top hit
74
+ def prepare_rough_target_genomic_region(genome, top_chromosome, left, right)
75
+ cmd = "blastdbcmd -db #{genome} -entry #{top_chromosome} -outfmt %l "
76
+ res = nil
77
+ IO.popen(cmd){|io| res = io.read}
78
+ seqlength = res.to_i
79
+
80
+ left_extract = [(left - EXTENSION), 1].sort.last
81
+ right_extract = [(right + EXTENSION), seqlength].sort.first
82
+
83
+ #p [left_extract, right_extract]
84
+
85
+ cmd = "blastdbcmd -db #{genome} -entry #{top_chromosome} -range #{left_extract}-#{right_extract} -outfmt %s"
86
+ res = nil
87
+ IO.popen(cmd){|io| res = io.read}
88
+ seq = res.strip
89
+
90
+ seq = "n" * (left_extract - 1) + seq + "n" * (seqlength - right_extract)
91
+ # [res.size, seq.size, seqlength]
92
+ raise unless seq.size == seqlength
93
+ fas = ">#{top_chromosome}\n#{seq}"
94
+ fas
95
+ end
96
+
97
+ ## step 3: run exonerate
98
+
99
+ def exec_exonerate(query, target)
100
+ cmd = "exonerate -q #{query} -t #{target} --model protein2genome --bestn 1 --showquerygff yes --showtargetgff yes --showcigar yes"
101
+ res = nil
102
+ IO.popen(cmd){|io| res = io.read}
103
+ res
104
+ end
105
+
106
+ ## standard pipeline from step 1 to 3
107
+ def run(query, genome)
108
+ hit = self.exec_tblastn_to_know_rough_target_region(query, genome)
109
+ if hit
110
+ top_chromosome = hit[:top_chromosome]
111
+ left = hit[:left]
112
+ right = hit[:right]
113
+
114
+ target_fasta = prepare_rough_target_genomic_region(genome, top_chromosome, left, right)
115
+ tf = Tempfile.new("mapp2g-#{Process.pid}")
116
+ tf.puts(target_fasta)
117
+ tf.close
118
+
119
+ exonerate_result = exec_exonerate(query, tf.path)
120
+ return exonerate_result
121
+
122
+ else
123
+ return nil
124
+ end
125
+ end
126
+
127
+ end
128
+
129
+ end
130
+
131
+ #---
132
+ if __FILE__ == $0
133
+
134
+ mapper = Mapp2g::Mapper.new()
135
+
136
+ query = ARGV[0]
137
+ genome = ARGV[1]
138
+ res = mapper.run(query, genome)
139
+ puts res
140
+
141
+ end
@@ -0,0 +1,5 @@
1
+ # frozen_string_literal: true
2
+
3
+ module Mapp2g
4
+ VERSION = "0.1.0"
5
+ end
data/lib/mapp2g.rb ADDED
@@ -0,0 +1,9 @@
1
+ # frozen_string_literal: true
2
+
3
+ require_relative "mapp2g/mapper"
4
+ require_relative "mapp2g/version"
5
+
6
+ module Mapp2g
7
+ class Error < StandardError; end
8
+ # Your code goes here...
9
+ end
data/mapp2g.gemspec ADDED
@@ -0,0 +1,39 @@
1
+ # frozen_string_literal: true
2
+
3
+ require_relative "lib/mapp2g/version"
4
+
5
+ Gem::Specification.new do |spec|
6
+ spec.name = "mapp2g"
7
+ spec.version = Mapp2g::VERSION
8
+ spec.authors = ["Shuji Shigenobu"]
9
+ spec.email = ["sshigenobu@gmail.com"]
10
+
11
+ spec.summary = "mapp2g is the tool to map protein sequences to genome references in a splicing-aware way. "
12
+ spec.description = "mapp2g is a bioinformatics software, which map and align protein sequences (amino acid sequences) to genome references in a splicing-aware way. mapp2g alignment pipeline employs exonerate and tBLASTn."
13
+ spec.homepage = "https://github.com/shujishigenobu/mapp2g"
14
+ spec.license = "MIT"
15
+ spec.required_ruby_version = ">= 2.6.0"
16
+
17
+ # spec.metadata["allowed_push_host"] = "TODO: Set to your gem server 'https://example.com'"
18
+
19
+ spec.metadata["homepage_uri"] = spec.homepage
20
+ spec.metadata["source_code_uri"] = "https://github.com/shujishigenobu/mapp2g"
21
+ spec.metadata["changelog_uri"] = "https://github.com/shujishigenobu/mapp2g"
22
+
23
+ # Specify which files should be added to the gem when it is released.
24
+ # The `git ls-files -z` loads the files in the RubyGem that have been added into git.
25
+ spec.files = Dir.chdir(__dir__) do
26
+ `git ls-files -z`.split("\x0").reject do |f|
27
+ (f == __FILE__) || f.match(%r{\A(?:(?:bin|test|spec|features)/|\.(?:git|circleci)|appveyor)})
28
+ end
29
+ end
30
+ spec.bindir = "exe"
31
+ spec.executables = spec.files.grep(%r{\Aexe/}) { |f| File.basename(f) }
32
+ spec.require_paths = ["lib"]
33
+
34
+ # Uncomment to register a new dependency of your gem
35
+ # spec.add_dependency "example-gem", "~> 1.0"
36
+
37
+ # For more information and examples about making a new gem, check out our
38
+ # guide at: https://bundler.io/guides/creating_gem.html
39
+ end
data/sig/mapp2g.rbs ADDED
@@ -0,0 +1,4 @@
1
+ module Mapp2g
2
+ VERSION: String
3
+ # See the writing guide of rbs: https://github.com/ruby/rbs#guides
4
+ end
metadata ADDED
@@ -0,0 +1,61 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: mapp2g
3
+ version: !ruby/object:Gem::Version
4
+ version: 0.1.0
5
+ platform: ruby
6
+ authors:
7
+ - Shuji Shigenobu
8
+ autorequire:
9
+ bindir: exe
10
+ cert_chain: []
11
+ date: 2023-02-04 00:00:00.000000000 Z
12
+ dependencies: []
13
+ description: mapp2g is a bioinformatics software, which map and align protein sequences
14
+ (amino acid sequences) to genome references in a splicing-aware way. mapp2g alignment
15
+ pipeline employs exonerate and tBLASTn.
16
+ email:
17
+ - sshigenobu@gmail.com
18
+ executables:
19
+ - mapp2g
20
+ extensions: []
21
+ extra_rdoc_files: []
22
+ files:
23
+ - ".rspec"
24
+ - Gemfile
25
+ - LICENSE.txt
26
+ - README.md
27
+ - Rakefile
28
+ - exe/mapp2g
29
+ - lib/mapp2g.rb
30
+ - lib/mapp2g/mapper.rb
31
+ - lib/mapp2g/version.rb
32
+ - mapp2g.gemspec
33
+ - sig/mapp2g.rbs
34
+ homepage: https://github.com/shujishigenobu/mapp2g
35
+ licenses:
36
+ - MIT
37
+ metadata:
38
+ homepage_uri: https://github.com/shujishigenobu/mapp2g
39
+ source_code_uri: https://github.com/shujishigenobu/mapp2g
40
+ changelog_uri: https://github.com/shujishigenobu/mapp2g
41
+ post_install_message:
42
+ rdoc_options: []
43
+ require_paths:
44
+ - lib
45
+ required_ruby_version: !ruby/object:Gem::Requirement
46
+ requirements:
47
+ - - ">="
48
+ - !ruby/object:Gem::Version
49
+ version: 2.6.0
50
+ required_rubygems_version: !ruby/object:Gem::Requirement
51
+ requirements:
52
+ - - ">="
53
+ - !ruby/object:Gem::Version
54
+ version: '0'
55
+ requirements: []
56
+ rubygems_version: 3.2.15
57
+ signing_key:
58
+ specification_version: 4
59
+ summary: mapp2g is the tool to map protein sequences to genome references in a splicing-aware
60
+ way.
61
+ test_files: []