bio-faidx 0.0.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -0,0 +1,7 @@
1
+ ---
2
+ SHA1:
3
+ metadata.gz: 1c78d17dec354ee49f73fcf3b9ad112b4f2eb29d
4
+ data.tar.gz: 131d2aceda2d2be6df0686fb525b9883c97643ae
5
+ SHA512:
6
+ metadata.gz: 92a83e738d87455b096a3e537878ea2fb864211cf5d19730145fe665c1abf88d9576f42bd9328122e430069cbed5699240c4e04f9c35431a0693058953a6d63e
7
+ data.tar.gz: c1bbf2b36f518fab44ee32c6a80974e59352a8cc96902dd4678c443cb90efd32143e9e40af1a9ee5769c35589cb7a45731e2ed90d95dfcc6332155d320d1de66
@@ -0,0 +1,5 @@
1
+ lib/**/*.rb
2
+ bin/*
3
+ -
4
+ features/**/*.feature
5
+ LICENSE.txt
@@ -0,0 +1,13 @@
1
+ language: ruby
2
+ rvm:
3
+ - 1.9.2
4
+ - 1.9.3
5
+ - jruby-19mode # JRuby in 1.9 mode
6
+
7
+ # - rbx-19mode
8
+ # - 1.8.7
9
+ # - jruby-18mode # JRuby in 1.8 mode
10
+ # - rbx-18mode
11
+
12
+ # uncomment this line if your project needs to run something other than `rake`:
13
+ # script: bundle exec rspec spec
data/Gemfile ADDED
@@ -0,0 +1,15 @@
1
+ source "http://rubygems.org"
2
+ # Add dependencies required to use your gem here.
3
+ # Example:
4
+ # gem "activesupport", ">= 2.3.5"
5
+
6
+ # Add dependencies to develop your gem here.
7
+ # Include everything needed to run rake, tests, features, etc.
8
+ group :development do
9
+ gem "shoulda", ">= 0"
10
+ gem "rdoc", "~> 3.12"
11
+ gem "simplecov", ">= 0"
12
+ gem "jeweler", "~> 2.0.1", :git => "https://github.com/technicalpickles/jeweler.git"
13
+ gem "bundler", ">= 1.0.21"
14
+ gem "bio", ">= 1.4.2"
15
+ end
@@ -0,0 +1,20 @@
1
+ Copyright (c) 2014 homonecloco
2
+
3
+ Permission is hereby granted, free of charge, to any person obtaining
4
+ a copy of this software and associated documentation files (the
5
+ "Software"), to deal in the Software without restriction, including
6
+ without limitation the rights to use, copy, modify, merge, publish,
7
+ distribute, sublicense, and/or sell copies of the Software, and to
8
+ permit persons to whom the Software is furnished to do so, subject to
9
+ the following conditions:
10
+
11
+ The above copyright notice and this permission notice shall be
12
+ included in all copies or substantial portions of the Software.
13
+
14
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
15
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
16
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
17
+ NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
18
+ LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
19
+ OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
20
+ WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
@@ -0,0 +1,47 @@
1
+ # bio-faidx
2
+
3
+ [![Build Status](https://secure.travis-ci.org/homonecloco/bioruby-faidx.png)](http://travis-ci.org/homonecloco/bioruby-faidx)
4
+
5
+ API to work with the fai format produced to samtools. Useful if you don't want to rely on all the samtools component.
6
+ Can query sequences from the fasta file. At the minute, it uses bio-samtools, but the idea is to make this self-sufficient.
7
+
8
+
9
+ ## Installation
10
+
11
+ ```sh
12
+ gem install bio-faidx
13
+ ```
14
+
15
+ ## Usage
16
+
17
+ ```ruby
18
+ require 'bio-faidx'
19
+ ```
20
+
21
+ The API doc is online. For more code examples see the test files in
22
+ the source tree.
23
+
24
+ ## Project home page
25
+
26
+ Information on the source tree, documentation, examples, issues and
27
+ how to contribute, see
28
+
29
+ http://github.com/homonecloco/bioruby-faidx
30
+
31
+ The BioRuby community is on IRC server: irc.freenode.org, channel: #bioruby.
32
+
33
+ ## Cite
34
+
35
+ If you use this software, please cite one of
36
+
37
+ * [BioRuby: bioinformatics software for the Ruby programming language](http://dx.doi.org/10.1093/bioinformatics/btq475)
38
+ * [Biogem: an effective tool-based approach for scaling up open source software development in bioinformatics](http://dx.doi.org/10.1093/bioinformatics/bts080)
39
+
40
+ ## Biogems.info
41
+
42
+ This Biogem is published at (http://biogems.info/index.html#bio-faidx)
43
+
44
+ ## Copyright
45
+
46
+ Copyright (c) 2014 homonecloco. See LICENSE.txt for further details.
47
+
@@ -0,0 +1,48 @@
1
+ = bio-faidx
2
+
3
+ {<img
4
+ src="https://secure.travis-ci.org/homonecloco/bioruby-faidx.png"
5
+ />}[http://travis-ci.org/#!/homonecloco/bioruby-faidx]
6
+
7
+ Full description goes here
8
+
9
+ Note: this software is under active development!
10
+
11
+ == Installation
12
+
13
+ gem install bio-faidx
14
+
15
+ == Usage
16
+
17
+ == Developers
18
+
19
+ To use the library
20
+
21
+ require 'bio-faidx'
22
+
23
+ The API doc is online. For more code examples see also the test files in
24
+ the source tree.
25
+
26
+ == Project home page
27
+
28
+ Information on the source tree, documentation, issues and how to contribute, see
29
+
30
+ http://github.com/homonecloco/bioruby-faidx
31
+
32
+ The BioRuby community is on IRC server: irc.freenode.org, channel: #bioruby.
33
+
34
+ == Cite
35
+
36
+ If you use this software, please cite one of
37
+
38
+ * [BioRuby: bioinformatics software for the Ruby programming language](http://dx.doi.org/10.1093/bioinformatics/btq475)
39
+ * [Biogem: an effective tool-based approach for scaling up open source software development in bioinformatics](http://dx.doi.org/10.1093/bioinformatics/bts080)
40
+
41
+ == Biogems.info
42
+
43
+ This Biogem is published at http://biogems.info/index.html#bio-faidx
44
+
45
+ == Copyright
46
+
47
+ Copyright (c) 2014 homonecloco. See LICENSE.txt for further details.
48
+
@@ -0,0 +1,51 @@
1
+ # encoding: utf-8
2
+
3
+ require 'rubygems'
4
+ require 'bundler'
5
+ begin
6
+ Bundler.setup(:default, :development)
7
+ rescue Bundler::BundlerError => e
8
+ $stderr.puts e.message
9
+ $stderr.puts "Run `bundle install` to install missing gems"
10
+ exit e.status_code
11
+ end
12
+ require 'rake'
13
+
14
+ require 'jeweler'
15
+ Jeweler::Tasks.new do |gem|
16
+ # gem is a Gem::Specification... see http://guides.rubygems.org/specification-reference/ for more options
17
+ gem.name = "bio-faidx"
18
+ gem.homepage = "http://github.com/homonecloco/bioruby-faidx"
19
+ gem.license = "MIT"
20
+ gem.summary = %Q{Tools to work with fasta files, indexed with samtools}
21
+ gem.description = %Q{ools to work with fasta files, indexed with samtools. The initial releases depend on bio-samtools, but that will change}
22
+ gem.email = "ricardo.ramirez-gonzalez@tgac.ac.uk"
23
+ gem.authors = ["homonecloco"]
24
+ # dependencies defined in Gemfile
25
+ end
26
+ Jeweler::RubygemsDotOrgTasks.new
27
+
28
+ require 'rake/testtask'
29
+ Rake::TestTask.new(:test) do |test|
30
+ test.libs << 'lib' << 'test'
31
+ test.pattern = 'test/**/test_*.rb'
32
+ test.verbose = true
33
+ end
34
+
35
+ desc "Code coverage detail"
36
+ task :simplecov do
37
+ ENV['COVERAGE'] = "true"
38
+ Rake::Task['test'].execute
39
+ end
40
+
41
+ task :default => :test
42
+
43
+ require 'rdoc/task'
44
+ Rake::RDocTask.new do |rdoc|
45
+ version = File.exist?('VERSION') ? File.read('VERSION') : ""
46
+
47
+ rdoc.rdoc_dir = 'rdoc'
48
+ rdoc.title = "bio-faidx #{version}"
49
+ rdoc.rdoc_files.include('README*')
50
+ rdoc.rdoc_files.include('lib/**/*.rb')
51
+ end
data/VERSION ADDED
@@ -0,0 +1 @@
1
+ 0.0.1
@@ -0,0 +1,12 @@
1
+ # Please require your code below, respecting the naming conventions in the
2
+ # bioruby directory tree.
3
+ #
4
+ # For example, say you have a plugin named bio-plugin, the only uncommented
5
+ # line in this file would be
6
+ #
7
+ # require 'bio/bio-plugin/plugin'
8
+ #
9
+ # In this file only require other files. Avoid other source code.
10
+
11
+ require 'bio-faidx/faidx.rb'
12
+
@@ -0,0 +1,174 @@
1
+ require 'csv'
2
+ require 'bio-samtools'
3
+
4
+
5
+ class Bio::DB::Faidx
6
+
7
+ class Entry
8
+ attr_accessor :name, :length, :offset, :linebases, :linewidth
9
+ end
10
+ def initialize(opts)
11
+ @cache = false
12
+ @cache = opts[:cache] if opts[:cache]
13
+ @filename = opts[:filename]
14
+ @inited = false
15
+ end
16
+
17
+ def init_cache
18
+ @inited = true
19
+ @entries = Hash.new
20
+ @entries_order = Array.new
21
+ read_entries do |e|
22
+ @entries[e.name] = e
23
+ @entries_order << e.name
24
+ end
25
+ end
26
+
27
+ def entries
28
+ init_cache unless @inited
29
+ @entries
30
+ end
31
+
32
+ def [](entry)
33
+ init_cache unless @inited
34
+ @entries[entry]
35
+ end
36
+
37
+
38
+ def entries_order
39
+ init_cache unless @inited
40
+ return @entries_order
41
+ end
42
+
43
+ def read_entries
44
+ CSV.foreach(@filename, :col_sep => "\t", :skip_lines=>/^#/, :skip_blanks=>true) do |row|
45
+ fasta_entry = Bio::DB::Faidx::Entry.new
46
+ [:name, :length, :offset, :linebases, :linewidth].each_with_index do |sym, i|
47
+ answer = row[i]
48
+ answer = answer.to_i if [:length, :offset, :linebases, :linewidth].include?(sym)
49
+ fasta_entry.send("#{sym}=".to_sym, answer)
50
+ yield fasta_entry
51
+ end
52
+ end
53
+
54
+ def each_entry
55
+ unless @cache
56
+ read_entries { |e| yield e }
57
+ else
58
+ entries_order.each { |e| yield @entries[e] }
59
+ end
60
+ end
61
+ end
62
+
63
+
64
+ class Bio::DB::Fasta::Region
65
+ def overlaps (other)
66
+ return false if other.entry != @entry
67
+ return true if other.start >= @start and other.start <= @end
68
+ return true if other.end >= @start and other.end <= @end
69
+ return false
70
+ end
71
+
72
+ def subset (other)
73
+ return false if other.entry != @entry
74
+ return true if other.start >= @start and other.end <= @end
75
+ end
76
+
77
+ def joinRegion (other)
78
+ return nil unless self.overlaps(other)
79
+ out = self.clone
80
+ out.start = other.start if other.start < out.start
81
+ out.end = other.end if other.end > out.end
82
+ return out
83
+ end
84
+
85
+ def overlap_in_set(set)
86
+ overlap_set = Set.new
87
+ set.each do |e|
88
+ overlap_set << e if self.overlaps(e)
89
+ end
90
+ overlap_set
91
+ end
92
+ end
93
+ #class Faidx
94
+ class Entry
95
+ attr_accessor :name, :length, :offset, :linebases, :linewidth
96
+ end
97
+ def initialize(opts)
98
+ @cache = false
99
+ @cache = opts[:cache] if opts[:cache]
100
+ @filename = opts[:filename]
101
+ @inited = false
102
+ end
103
+
104
+ def init_cache
105
+ @inited = true
106
+ @entries = Hash.new
107
+ @entries_order = Array.new
108
+ read_entries do |e|
109
+ @entries[e.name] = e
110
+ @entries_order << e.name
111
+ end
112
+ end
113
+
114
+ def entries
115
+ init_cache unless @inited
116
+ @entries
117
+
118
+ end
119
+
120
+ def entries_order
121
+ init_cache unless @inited
122
+ return @entries_order
123
+ end
124
+
125
+ def read_entries
126
+ CSV.foreach(@filename, :col_sep => "\t", :skip_lines=>/^#/, :skip_blanks=>true) do |row|
127
+ fasta_entry = Bio::DB::Faidx::Entry.new
128
+ [:name, :length, :offset, :linebases, :linewidth].each_with_index do |sym, i|
129
+ answer = row[i]
130
+ answer = answer.to_i if [:length, :offset, :linebases, :linewidth].include?(sym)
131
+ fasta_entry.send("#{sym}=".to_sym, answer)
132
+ yield fasta_entry
133
+ end
134
+ end
135
+
136
+ def each_entry
137
+ unless @cache
138
+ read_entries { |e| yield e }
139
+ else
140
+ entries_order.each { |e| yield @entries[e] }
141
+ end
142
+ end
143
+ end
144
+ end
145
+
146
+ class Bio::DB::Fasta::Region
147
+ def overlaps (other)
148
+ return false if other.entry != @entry
149
+ return true if other.start >= @start and other.start <= @end
150
+ return true if other.end >= @start and other.end <= @end
151
+ return false
152
+ end
153
+
154
+ def subset (other)
155
+ return false if other.entry != @entry
156
+ return true if other.start >= @start and other.end <= @end
157
+ end
158
+
159
+ def joinRegion (other)
160
+ return nil unless self.overlaps(other)
161
+ out = self.clone
162
+ out.start = other.start if other.start < out.start
163
+ out.end = other.end if other.end > out.end
164
+ return out
165
+ end
166
+
167
+ def overlap_in_set(set)
168
+ overlap_set = Set.new
169
+ set.each do |e|
170
+ overlap_set << e if self.overlaps(e)
171
+ end
172
+ overlap_set
173
+ end
174
+ end
@@ -0,0 +1,34 @@
1
+ require 'simplecov'
2
+
3
+ module SimpleCov::Configuration
4
+ def clean_filters
5
+ @filters = []
6
+ end
7
+ end
8
+
9
+ SimpleCov.configure do
10
+ clean_filters
11
+ load_adapter 'test_frameworks'
12
+ end
13
+
14
+ ENV["COVERAGE"] && SimpleCov.start do
15
+ add_filter "/.rvm/"
16
+ end
17
+ require 'rubygems'
18
+ require 'bundler'
19
+ begin
20
+ Bundler.setup(:default, :development)
21
+ rescue Bundler::BundlerError => e
22
+ $stderr.puts e.message
23
+ $stderr.puts "Run `bundle install` to install missing gems"
24
+ exit e.status_code
25
+ end
26
+ require 'test/unit'
27
+ require 'shoulda'
28
+
29
+ $LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
30
+ $LOAD_PATH.unshift(File.dirname(__FILE__))
31
+ require 'bio-faidx'
32
+
33
+ class Test::Unit::TestCase
34
+ end
@@ -0,0 +1,7 @@
1
+ require 'helper'
2
+
3
+ class TestBioFaidx < Test::Unit::TestCase
4
+ should "probably rename this file and start testing for real" do
5
+ flunk "hey buddy, you should probably rename this file and start testing for real"
6
+ end
7
+ end
metadata ADDED
@@ -0,0 +1,143 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: bio-faidx
3
+ version: !ruby/object:Gem::Version
4
+ version: 0.0.1
5
+ platform: ruby
6
+ authors:
7
+ - homonecloco
8
+ autorequire:
9
+ bindir: bin
10
+ cert_chain: []
11
+ date: 2014-10-07 00:00:00.000000000 Z
12
+ dependencies:
13
+ - !ruby/object:Gem::Dependency
14
+ name: shoulda
15
+ requirement: !ruby/object:Gem::Requirement
16
+ requirements:
17
+ - - ">="
18
+ - !ruby/object:Gem::Version
19
+ version: '0'
20
+ type: :development
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: rdoc
29
+ requirement: !ruby/object:Gem::Requirement
30
+ requirements:
31
+ - - "~>"
32
+ - !ruby/object:Gem::Version
33
+ version: '3.12'
34
+ type: :development
35
+ prerelease: false
36
+ version_requirements: !ruby/object:Gem::Requirement
37
+ requirements:
38
+ - - "~>"
39
+ - !ruby/object:Gem::Version
40
+ version: '3.12'
41
+ - !ruby/object:Gem::Dependency
42
+ name: simplecov
43
+ requirement: !ruby/object:Gem::Requirement
44
+ requirements:
45
+ - - ">="
46
+ - !ruby/object:Gem::Version
47
+ version: '0'
48
+ type: :development
49
+ prerelease: false
50
+ version_requirements: !ruby/object:Gem::Requirement
51
+ requirements:
52
+ - - ">="
53
+ - !ruby/object:Gem::Version
54
+ version: '0'
55
+ - !ruby/object:Gem::Dependency
56
+ name: jeweler
57
+ requirement: !ruby/object:Gem::Requirement
58
+ requirements:
59
+ - - "~>"
60
+ - !ruby/object:Gem::Version
61
+ version: 2.0.1
62
+ type: :development
63
+ prerelease: false
64
+ version_requirements: !ruby/object:Gem::Requirement
65
+ requirements:
66
+ - - "~>"
67
+ - !ruby/object:Gem::Version
68
+ version: 2.0.1
69
+ - !ruby/object:Gem::Dependency
70
+ name: bundler
71
+ requirement: !ruby/object:Gem::Requirement
72
+ requirements:
73
+ - - ">="
74
+ - !ruby/object:Gem::Version
75
+ version: 1.0.21
76
+ type: :development
77
+ prerelease: false
78
+ version_requirements: !ruby/object:Gem::Requirement
79
+ requirements:
80
+ - - ">="
81
+ - !ruby/object:Gem::Version
82
+ version: 1.0.21
83
+ - !ruby/object:Gem::Dependency
84
+ name: bio
85
+ requirement: !ruby/object:Gem::Requirement
86
+ requirements:
87
+ - - ">="
88
+ - !ruby/object:Gem::Version
89
+ version: 1.4.2
90
+ type: :development
91
+ prerelease: false
92
+ version_requirements: !ruby/object:Gem::Requirement
93
+ requirements:
94
+ - - ">="
95
+ - !ruby/object:Gem::Version
96
+ version: 1.4.2
97
+ description: ools to work with fasta files, indexed with samtools. The initial releases
98
+ depend on bio-samtools, but that will change
99
+ email: ricardo.ramirez-gonzalez@tgac.ac.uk
100
+ executables: []
101
+ extensions: []
102
+ extra_rdoc_files:
103
+ - LICENSE.txt
104
+ - README.md
105
+ - README.rdoc
106
+ files:
107
+ - ".document"
108
+ - ".travis.yml"
109
+ - Gemfile
110
+ - LICENSE.txt
111
+ - README.md
112
+ - README.rdoc
113
+ - Rakefile
114
+ - VERSION
115
+ - lib/bio-faidx.rb
116
+ - lib/bio-faidx/faidx.rb
117
+ - test/helper.rb
118
+ - test/test_bio-faidx.rb
119
+ homepage: http://github.com/homonecloco/bioruby-faidx
120
+ licenses:
121
+ - MIT
122
+ metadata: {}
123
+ post_install_message:
124
+ rdoc_options: []
125
+ require_paths:
126
+ - lib
127
+ required_ruby_version: !ruby/object:Gem::Requirement
128
+ requirements:
129
+ - - ">="
130
+ - !ruby/object:Gem::Version
131
+ version: '0'
132
+ required_rubygems_version: !ruby/object:Gem::Requirement
133
+ requirements:
134
+ - - ">="
135
+ - !ruby/object:Gem::Version
136
+ version: '0'
137
+ requirements: []
138
+ rubyforge_project:
139
+ rubygems_version: 2.2.1
140
+ signing_key:
141
+ specification_version: 4
142
+ summary: Tools to work with fasta files, indexed with samtools
143
+ test_files: []