seqtkrb 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +9 -0
- data/.travis.yml +3 -0
- data/CODE_OF_CONDUCT.md +13 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +21 -0
- data/README.md +52 -0
- data/Rakefile +9 -0
- data/deps.yaml +10 -0
- data/lib/seqtkrb.rb +49 -0
- data/lib/seqtkrb/cmd.rb +23 -0
- data/lib/seqtkrb/sample.rb +19 -0
- data/lib/seqtkrb/version.rb +3 -0
- data/seqtkrb.gemspec +33 -0
- metadata +227 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 0f088f76ffd7699ab981e2c8a13a92681f80cb57
|
4
|
+
data.tar.gz: 8d67ca12680ce5274c0157fdf8c4dd09ec475ffa
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 223535cfe07ba02d7e307a2fa3b623afad630a63958a21bc9f3a3d43d17a759881be47c9bc25b11074960f61adcd8dde0c4a18f685367e269fa9f481ce91510b
|
7
|
+
data.tar.gz: b6f48d258777f30efd09403b6d048fea07d05dfba20a36ffe24728926056f486b6d68c96e2aa2f877860f04365bcb56eb78de7492e7fcc18f758a0ea613f8726
|
data/.gitignore
ADDED
data/.travis.yml
ADDED
data/CODE_OF_CONDUCT.md
ADDED
@@ -0,0 +1,13 @@
|
|
1
|
+
# Contributor Code of Conduct
|
2
|
+
|
3
|
+
As contributors and maintainers of this project, we pledge to respect all people who contribute through reporting issues, posting feature requests, updating documentation, submitting pull requests or patches, and other activities.
|
4
|
+
|
5
|
+
We are committed to making participation in this project a harassment-free experience for everyone, regardless of level of experience, gender, gender identity and expression, sexual orientation, disability, personal appearance, body size, race, age, or religion.
|
6
|
+
|
7
|
+
Examples of unacceptable behavior by participants include the use of sexual language or imagery, derogatory comments or personal attacks, trolling, public or private harassment, insults, or other unprofessional conduct.
|
8
|
+
|
9
|
+
Project maintainers have the right and responsibility to remove, edit, or reject comments, commits, code, wiki edits, issues, and other contributions that are not aligned to this Code of Conduct. Project maintainers who do not follow the Code of Conduct may be removed from the project team.
|
10
|
+
|
11
|
+
Instances of abusive, harassing, or otherwise unacceptable behavior may be reported by opening an issue or contacting one or more of the project maintainers.
|
12
|
+
|
13
|
+
This Code of Conduct is adapted from the [Contributor Covenant](http:contributor-covenant.org), version 1.0.0, available at [http://contributor-covenant.org/version/1/0/0/](http://contributor-covenant.org/version/1/0/0/)
|
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2015 Richard Smith-Unna
|
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 +1,52 @@
|
|
1
|
+
# seqtkrb [![Build Status](https://img.shields.io/travis/Blahah/seqtkrb.svg)](https://travis-ci.org/Blahah/seqtkrb) [![Coverage Status](https://img.shields.io/coveralls/jekyll/jekyll.svg)](https://coveralls.io/r/Blahah/seqtkrb?branch=master)
|
2
|
+
|
3
|
+
seqtkrb is a ruby gem that wraps [seqtk](). This gives you fast access to basic operations on FASTA/FASTQ files without having to roll your own C extension or write a slow implementation in ruby.
|
4
|
+
|
5
|
+
Currently only the sampling functionality of seqtk is exposed. Create an issue or a Pull Request if you want more functionality.
|
6
|
+
|
7
|
+
## Installation
|
8
|
+
|
9
|
+
Add this line to your application's Gemfile:
|
10
|
+
|
11
|
+
```ruby
|
12
|
+
gem 'seqtkrb'
|
13
|
+
```
|
14
|
+
|
15
|
+
And then execute:
|
16
|
+
|
17
|
+
```
|
18
|
+
$ bundle
|
19
|
+
```
|
20
|
+
|
21
|
+
Or install it yourself as:
|
22
|
+
|
23
|
+
```
|
24
|
+
$ gem install seqtkrb
|
25
|
+
```
|
26
|
+
|
27
|
+
## Usage
|
28
|
+
|
29
|
+
```ruby
|
30
|
+
require 'seqtkrb'
|
31
|
+
|
32
|
+
seq = Seqtkrb::Seqtk.new # will download and install seqtk if it is not found
|
33
|
+
|
34
|
+
# basic sampling
|
35
|
+
seq.sample('reads.fq', 'sampled.fq' 10_000) # sample 10,000 reads
|
36
|
+
seq.sample('reads.fq', 'sampled.fq' 0.5) # sample reads with 50% chance of taking each read
|
37
|
+
|
38
|
+
# sampling from paired files
|
39
|
+
seq.sample('reads_l.fq', 'sampled_l.fq', 1_000, 1234) # sample 1,000 left reads with seed 1234
|
40
|
+
seq.sample('reads_r.fq', 'sampled_r.fq', 1_000, 1234) # sample the matching right reads
|
41
|
+
|
42
|
+
# low memory sampling (uses two passes)
|
43
|
+
seq.sample_lowmem('reads.fq', 'sampled.fq', 1_000_000) # sample 1 million reads
|
44
|
+
```
|
45
|
+
|
46
|
+
## Contributing
|
47
|
+
|
48
|
+
1. Fork it ( https://github.com/[my-github-username]/seqtkrb/fork )
|
49
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
50
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
51
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
52
|
+
5. Create a new Pull Request
|
data/Rakefile
ADDED
data/deps.yaml
ADDED
@@ -0,0 +1,10 @@
|
|
1
|
+
seqtk:
|
2
|
+
binaries:
|
3
|
+
- seqtk
|
4
|
+
version:
|
5
|
+
number: 1.0-r82
|
6
|
+
command: seqtk
|
7
|
+
url:
|
8
|
+
64bit:
|
9
|
+
macosx: https://github.com/Blahah/seqtk/releases/download/1.0-r82/seqtk_1.0_osx.tar.gz
|
10
|
+
linux: https://github.com/Blahah/seqtk/releases/download/1.0-r82/seqtk_1.0_linux.tar.gz
|
data/lib/seqtkrb.rb
ADDED
@@ -0,0 +1,49 @@
|
|
1
|
+
require 'seqtkrb/version'
|
2
|
+
require 'seqtkrb/cmd'
|
3
|
+
require 'bindeps'
|
4
|
+
require 'fixwhich'
|
5
|
+
|
6
|
+
module Seqtk
|
7
|
+
|
8
|
+
class Seqtk
|
9
|
+
|
10
|
+
include Which
|
11
|
+
|
12
|
+
def initialize
|
13
|
+
|
14
|
+
# check seqtk is installed - install it if not
|
15
|
+
gem_dir = Gem.loaded_specs['seqtkrb'].full_gem_path
|
16
|
+
gem_deps = File.join(gem_dir, 'deps.yaml')
|
17
|
+
Bindeps.require gem_deps
|
18
|
+
|
19
|
+
missing = Bindeps.missing gem_deps
|
20
|
+
unless missing.empty?
|
21
|
+
raise StandardError.new('seqtk was not found and ' +
|
22
|
+
'could not be installed')
|
23
|
+
end
|
24
|
+
|
25
|
+
@bin = which('seqtk').first
|
26
|
+
|
27
|
+
end
|
28
|
+
|
29
|
+
def run cmd
|
30
|
+
|
31
|
+
task = Cmd.new "#{@bin} #{cmd}"
|
32
|
+
task.run
|
33
|
+
|
34
|
+
unless task.status.success?
|
35
|
+
msg = "seqtk command #{cmd} failed\n"
|
36
|
+
msg << "stdout:\n"
|
37
|
+
msg << task.stdout
|
38
|
+
msg << "\nstderr:\n"
|
39
|
+
msg << task.stderr
|
40
|
+
raise StandardError.new(msg)
|
41
|
+
end
|
42
|
+
|
43
|
+
end
|
44
|
+
|
45
|
+
end
|
46
|
+
|
47
|
+
end
|
48
|
+
|
49
|
+
require 'seqtkrb/sample'
|
data/lib/seqtkrb/cmd.rb
ADDED
@@ -0,0 +1,23 @@
|
|
1
|
+
require 'open3'
|
2
|
+
|
3
|
+
module Seqtk
|
4
|
+
|
5
|
+
class Cmd
|
6
|
+
|
7
|
+
attr_accessor :cmd, :stdout, :stderr, :status
|
8
|
+
|
9
|
+
def initialize cmd
|
10
|
+
@cmd = cmd
|
11
|
+
end
|
12
|
+
|
13
|
+
def run
|
14
|
+
@stdout, @stderr, @status = Open3.capture3 @cmd
|
15
|
+
end
|
16
|
+
|
17
|
+
def to_s
|
18
|
+
@cmd
|
19
|
+
end
|
20
|
+
|
21
|
+
end
|
22
|
+
|
23
|
+
end
|
@@ -0,0 +1,19 @@
|
|
1
|
+
module Seqtk
|
2
|
+
|
3
|
+
class Seqtk
|
4
|
+
|
5
|
+
def sample(infile, outfile, n, seed=-1)
|
6
|
+
run "sample #{seedstr seed} #{infile} #{n} > #{outfile}"
|
7
|
+
end
|
8
|
+
|
9
|
+
def sample_lowmem(infile, outfile, n, seed=-1)
|
10
|
+
run "sample -2 #{seedstr seed} #{infile} #{n} > #{outfile}"
|
11
|
+
end
|
12
|
+
|
13
|
+
def seedstr seed
|
14
|
+
seed == -1 ? "" : "-s #{seed}"
|
15
|
+
end
|
16
|
+
|
17
|
+
end
|
18
|
+
|
19
|
+
end
|
data/seqtkrb.gemspec
ADDED
@@ -0,0 +1,33 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'seqtkrb/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "seqtkrb"
|
8
|
+
spec.version = Seqtkrb::VERSION
|
9
|
+
spec.authors = ["Richard Smith-Unna"]
|
10
|
+
spec.email = ["richardsmith404@gmail.com"]
|
11
|
+
|
12
|
+
spec.summary = %q{ Fast processing of FASTA/FASTQ files }
|
13
|
+
spec.description = %q{ Fast processing of FASTA/FASTQ files - a ruby wrapper around seqtk}
|
14
|
+
spec.homepage = "https://github.com/blahah/seqtkrb"
|
15
|
+
spec.license = "MIT"
|
16
|
+
|
17
|
+
spec.files = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
|
18
|
+
spec.bindir = "exe"
|
19
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
20
|
+
spec.require_paths = ["lib"]
|
21
|
+
|
22
|
+
spec.add_dependency 'bindeps'
|
23
|
+
spec.add_dependency 'fixwhich'
|
24
|
+
|
25
|
+
spec.add_development_dependency 'bundler', '~> 1.7'
|
26
|
+
spec.add_development_dependency 'rake', '~> 10.0'
|
27
|
+
spec.add_development_dependency 'test-unit', '~> 3.0'
|
28
|
+
spec.add_development_dependency 'turn', '~> 0.9', '>= 0.9.7'
|
29
|
+
spec.add_development_dependency 'minitest', '~> 4', '>= 4.7.5'
|
30
|
+
spec.add_development_dependency 'simplecov', '~> 0.8', '>= 0.8.2'
|
31
|
+
spec.add_development_dependency 'shoulda', '~> 3.5', '>= 3.5.0'
|
32
|
+
spec.add_development_dependency 'coveralls', '~> 0.7', '>= 0.7.2'
|
33
|
+
end
|
metadata
ADDED
@@ -0,0 +1,227 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: seqtkrb
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Richard Smith-Unna
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2015-06-18 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: bindeps
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - ">="
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '0'
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ">="
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: fixwhich
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ">="
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
type: :runtime
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - ">="
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: bundler
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '1.7'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '1.7'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: rake
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '10.0'
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - "~>"
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '10.0'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: test-unit
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - "~>"
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '3.0'
|
76
|
+
type: :development
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - "~>"
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '3.0'
|
83
|
+
- !ruby/object:Gem::Dependency
|
84
|
+
name: turn
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - "~>"
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '0.9'
|
90
|
+
- - ">="
|
91
|
+
- !ruby/object:Gem::Version
|
92
|
+
version: 0.9.7
|
93
|
+
type: :development
|
94
|
+
prerelease: false
|
95
|
+
version_requirements: !ruby/object:Gem::Requirement
|
96
|
+
requirements:
|
97
|
+
- - "~>"
|
98
|
+
- !ruby/object:Gem::Version
|
99
|
+
version: '0.9'
|
100
|
+
- - ">="
|
101
|
+
- !ruby/object:Gem::Version
|
102
|
+
version: 0.9.7
|
103
|
+
- !ruby/object:Gem::Dependency
|
104
|
+
name: minitest
|
105
|
+
requirement: !ruby/object:Gem::Requirement
|
106
|
+
requirements:
|
107
|
+
- - "~>"
|
108
|
+
- !ruby/object:Gem::Version
|
109
|
+
version: '4'
|
110
|
+
- - ">="
|
111
|
+
- !ruby/object:Gem::Version
|
112
|
+
version: 4.7.5
|
113
|
+
type: :development
|
114
|
+
prerelease: false
|
115
|
+
version_requirements: !ruby/object:Gem::Requirement
|
116
|
+
requirements:
|
117
|
+
- - "~>"
|
118
|
+
- !ruby/object:Gem::Version
|
119
|
+
version: '4'
|
120
|
+
- - ">="
|
121
|
+
- !ruby/object:Gem::Version
|
122
|
+
version: 4.7.5
|
123
|
+
- !ruby/object:Gem::Dependency
|
124
|
+
name: simplecov
|
125
|
+
requirement: !ruby/object:Gem::Requirement
|
126
|
+
requirements:
|
127
|
+
- - "~>"
|
128
|
+
- !ruby/object:Gem::Version
|
129
|
+
version: '0.8'
|
130
|
+
- - ">="
|
131
|
+
- !ruby/object:Gem::Version
|
132
|
+
version: 0.8.2
|
133
|
+
type: :development
|
134
|
+
prerelease: false
|
135
|
+
version_requirements: !ruby/object:Gem::Requirement
|
136
|
+
requirements:
|
137
|
+
- - "~>"
|
138
|
+
- !ruby/object:Gem::Version
|
139
|
+
version: '0.8'
|
140
|
+
- - ">="
|
141
|
+
- !ruby/object:Gem::Version
|
142
|
+
version: 0.8.2
|
143
|
+
- !ruby/object:Gem::Dependency
|
144
|
+
name: shoulda
|
145
|
+
requirement: !ruby/object:Gem::Requirement
|
146
|
+
requirements:
|
147
|
+
- - "~>"
|
148
|
+
- !ruby/object:Gem::Version
|
149
|
+
version: '3.5'
|
150
|
+
- - ">="
|
151
|
+
- !ruby/object:Gem::Version
|
152
|
+
version: 3.5.0
|
153
|
+
type: :development
|
154
|
+
prerelease: false
|
155
|
+
version_requirements: !ruby/object:Gem::Requirement
|
156
|
+
requirements:
|
157
|
+
- - "~>"
|
158
|
+
- !ruby/object:Gem::Version
|
159
|
+
version: '3.5'
|
160
|
+
- - ">="
|
161
|
+
- !ruby/object:Gem::Version
|
162
|
+
version: 3.5.0
|
163
|
+
- !ruby/object:Gem::Dependency
|
164
|
+
name: coveralls
|
165
|
+
requirement: !ruby/object:Gem::Requirement
|
166
|
+
requirements:
|
167
|
+
- - "~>"
|
168
|
+
- !ruby/object:Gem::Version
|
169
|
+
version: '0.7'
|
170
|
+
- - ">="
|
171
|
+
- !ruby/object:Gem::Version
|
172
|
+
version: 0.7.2
|
173
|
+
type: :development
|
174
|
+
prerelease: false
|
175
|
+
version_requirements: !ruby/object:Gem::Requirement
|
176
|
+
requirements:
|
177
|
+
- - "~>"
|
178
|
+
- !ruby/object:Gem::Version
|
179
|
+
version: '0.7'
|
180
|
+
- - ">="
|
181
|
+
- !ruby/object:Gem::Version
|
182
|
+
version: 0.7.2
|
183
|
+
description: " Fast processing of FASTA/FASTQ files - a ruby wrapper around seqtk"
|
184
|
+
email:
|
185
|
+
- richardsmith404@gmail.com
|
186
|
+
executables: []
|
187
|
+
extensions: []
|
188
|
+
extra_rdoc_files: []
|
189
|
+
files:
|
190
|
+
- ".gitignore"
|
191
|
+
- ".travis.yml"
|
192
|
+
- CODE_OF_CONDUCT.md
|
193
|
+
- Gemfile
|
194
|
+
- LICENSE.txt
|
195
|
+
- README.md
|
196
|
+
- Rakefile
|
197
|
+
- deps.yaml
|
198
|
+
- lib/seqtkrb.rb
|
199
|
+
- lib/seqtkrb/cmd.rb
|
200
|
+
- lib/seqtkrb/sample.rb
|
201
|
+
- lib/seqtkrb/version.rb
|
202
|
+
- seqtkrb.gemspec
|
203
|
+
homepage: https://github.com/blahah/seqtkrb
|
204
|
+
licenses:
|
205
|
+
- MIT
|
206
|
+
metadata: {}
|
207
|
+
post_install_message:
|
208
|
+
rdoc_options: []
|
209
|
+
require_paths:
|
210
|
+
- lib
|
211
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
212
|
+
requirements:
|
213
|
+
- - ">="
|
214
|
+
- !ruby/object:Gem::Version
|
215
|
+
version: '0'
|
216
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
217
|
+
requirements:
|
218
|
+
- - ">="
|
219
|
+
- !ruby/object:Gem::Version
|
220
|
+
version: '0'
|
221
|
+
requirements: []
|
222
|
+
rubyforge_project:
|
223
|
+
rubygems_version: 2.4.6
|
224
|
+
signing_key:
|
225
|
+
specification_version: 4
|
226
|
+
summary: Fast processing of FASTA/FASTQ files
|
227
|
+
test_files: []
|