parse_fasta 0.0.4 → 0.0.5
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.gitignore +22 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +58 -0
- data/Rakefile +2 -0
- data/benchmark.rb +22 -0
- data/lib/parse_fasta/version.rb +3 -0
- data/lib/parse_fasta.rb +3 -0
- data/parse_fasta.gemspec +23 -0
- metadata +44 -7
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 2d0570f761a150d332eb2cdae3d1557b13c2e5ee
|
4
|
+
data.tar.gz: 6c7704803d913f27ed40b99ef645d81b34de2f6e
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: fe9d3b8b4b56b821b1d1936b9c9cfe1cccc6b7991bb5cddb0bf030db2a74b168999cea17369781b78e0f81720af50cb27f7d26e4d048fad22926f1eacf28edf2
|
7
|
+
data.tar.gz: bbd86ee5d54b24e7b759496cbd636239621ebac23f8616fdf06703a500b9d78b4353fc4b2e72f4b6d01adf462af48b29b3ca319e0ad8f8cd1b0ee9aaa7ffa9ee
|
data/.gitignore
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
*.gem
|
2
|
+
*.rbc
|
3
|
+
.bundle
|
4
|
+
.config
|
5
|
+
.yardoc
|
6
|
+
Gemfile.lock
|
7
|
+
InstalledFiles
|
8
|
+
_yardoc
|
9
|
+
coverage
|
10
|
+
doc/
|
11
|
+
lib/bundler/man
|
12
|
+
pkg
|
13
|
+
rdoc
|
14
|
+
spec/reports
|
15
|
+
test/tmp
|
16
|
+
test/version_tmp
|
17
|
+
tmp
|
18
|
+
*.bundle
|
19
|
+
*.so
|
20
|
+
*.o
|
21
|
+
*.a
|
22
|
+
mkmf.log
|
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2014 Ryan Moore
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,58 @@
|
|
1
|
+
# parse_fasta #
|
2
|
+
|
3
|
+
So you want to parse a fasta file...
|
4
|
+
|
5
|
+
## Installation ##
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
gem 'parse_fasta'
|
10
|
+
|
11
|
+
And then execute:
|
12
|
+
|
13
|
+
$ bundle
|
14
|
+
|
15
|
+
Or install it yourself as:
|
16
|
+
|
17
|
+
$ gem install parse_fasta
|
18
|
+
|
19
|
+
## Overview ##
|
20
|
+
|
21
|
+
Provides the method `#each_record` for the `File` class.
|
22
|
+
|
23
|
+
each_record { |header, sequence| block }
|
24
|
+
|
25
|
+
The whole file is not loaded into memory, so have no fear of giant
|
26
|
+
fasta files!
|
27
|
+
|
28
|
+
## Usage ##
|
29
|
+
|
30
|
+
An example that lists the length for each sequence.
|
31
|
+
|
32
|
+
require 'parse_fasta'
|
33
|
+
|
34
|
+
File.open(ARGV.first, 'r').each_record do |header, sequence|
|
35
|
+
puts [header, sequence.length].join("\t")
|
36
|
+
end
|
37
|
+
|
38
|
+
## Benchmark ##
|
39
|
+
|
40
|
+
Just for fun, I wanted to compare the execution time to that of
|
41
|
+
BioRuby. I calculated sequence length for each fasta record with both
|
42
|
+
the `each_record` method from this gem and using the `FastaFormat`
|
43
|
+
class from BioRuby. You can see the test script in `benchmark.rb`.
|
44
|
+
|
45
|
+
The test file contained 2,009,897 illumina reads and the file size
|
46
|
+
was 1.1 gigabytes. Here are the results from Ruby's `Benchmark` class:
|
47
|
+
|
48
|
+
user system total real
|
49
|
+
parse_fasta 64.530000 1.740000 66.270000 ( 67.081502)
|
50
|
+
bioruby 116.250000 2.260000 118.510000 (120.223710)
|
51
|
+
|
52
|
+
I just wanted a nice, clean way to parse fasta files, but being nearly
|
53
|
+
twice as fasta as BioRuby doesn't hurt either!
|
54
|
+
|
55
|
+
## Notes ##
|
56
|
+
|
57
|
+
Currently in doesn't check whether your file is actually a fasta file
|
58
|
+
or anything, so watch out.
|
data/Rakefile
ADDED
data/benchmark.rb
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require 'parse_fasta'
|
4
|
+
require 'bio'
|
5
|
+
require 'benchmark'
|
6
|
+
|
7
|
+
def parse_fasta fname
|
8
|
+
File.open(fname, 'r').each_record do |header, sequence|
|
9
|
+
[header, sequence.length].join("\t")
|
10
|
+
end
|
11
|
+
end
|
12
|
+
|
13
|
+
def bioruby fname
|
14
|
+
Bio::FastaFormat.open(fname).each do |entry|
|
15
|
+
[entry.definition, entry.seq.length].join("\t")
|
16
|
+
end
|
17
|
+
end
|
18
|
+
|
19
|
+
Benchmark.bmbm do |x|
|
20
|
+
x.report('parse_fasta') { parse_fasta(ARGV.first) }
|
21
|
+
x.report('bioruby') { bioruby(ARGV.first) }
|
22
|
+
end
|
data/lib/parse_fasta.rb
CHANGED
@@ -1,4 +1,5 @@
|
|
1
1
|
# Copyright 2014 Ryan Moore
|
2
|
+
# Contact: moorer@udel.edu
|
2
3
|
|
3
4
|
# This program is free software: you can redistribute it and/or modify
|
4
5
|
# it under the terms of the GNU General Public License as published by
|
@@ -13,6 +14,8 @@
|
|
13
14
|
# You should have received a copy of the GNU General Public License
|
14
15
|
# along with this program. If not, see <http://www.gnu.org/licenses/>.
|
15
16
|
|
17
|
+
require "parse_fasta/version"
|
18
|
+
|
16
19
|
class File
|
17
20
|
def each_record
|
18
21
|
self.each("\n>") do |line|
|
data/parse_fasta.gemspec
ADDED
@@ -0,0 +1,23 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'parse_fasta/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "parse_fasta"
|
8
|
+
spec.version = ParseFasta::VERSION
|
9
|
+
spec.authors = ["Ryan Moore"]
|
10
|
+
spec.email = ["moorer@udel.edu"]
|
11
|
+
spec.summary = %q{Easy-peasy parsing of fasta files}
|
12
|
+
spec.description = %q{So you want to parse a fasta file...}
|
13
|
+
spec.homepage = "https://github.com/mooreryan/parse_fasta"
|
14
|
+
spec.license = "GPLv3: http://www.gnu.org/licenses/gpl.txt"
|
15
|
+
|
16
|
+
spec.files = `git ls-files -z`.split("\x0")
|
17
|
+
spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
18
|
+
spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
|
19
|
+
spec.require_paths = ["lib"]
|
20
|
+
|
21
|
+
spec.add_development_dependency "bundler", "~> 1.6"
|
22
|
+
spec.add_development_dependency "rake"
|
23
|
+
end
|
metadata
CHANGED
@@ -1,25 +1,62 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: parse_fasta
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0.
|
4
|
+
version: 0.0.5
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Ryan Moore
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2014-05-
|
12
|
-
dependencies:
|
13
|
-
|
14
|
-
|
11
|
+
date: 2014-05-31 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: bundler
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.6'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.6'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ">="
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - ">="
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0'
|
41
|
+
description: So you want to parse a fasta file...
|
42
|
+
email:
|
43
|
+
- moorer@udel.edu
|
15
44
|
executables: []
|
16
45
|
extensions: []
|
17
46
|
extra_rdoc_files: []
|
18
47
|
files:
|
48
|
+
- ".gitignore"
|
49
|
+
- Gemfile
|
50
|
+
- LICENSE.txt
|
51
|
+
- README.md
|
52
|
+
- Rakefile
|
53
|
+
- benchmark.rb
|
19
54
|
- lib/parse_fasta.rb
|
55
|
+
- lib/parse_fasta/version.rb
|
56
|
+
- parse_fasta.gemspec
|
20
57
|
homepage: https://github.com/mooreryan/parse_fasta
|
21
58
|
licenses:
|
22
|
-
- http://www.gnu.org/licenses/gpl.txt
|
59
|
+
- 'GPLv3: http://www.gnu.org/licenses/gpl.txt'
|
23
60
|
metadata: {}
|
24
61
|
post_install_message:
|
25
62
|
rdoc_options: []
|
@@ -40,5 +77,5 @@ rubyforge_project:
|
|
40
77
|
rubygems_version: 2.2.2
|
41
78
|
signing_key:
|
42
79
|
specification_version: 4
|
43
|
-
summary:
|
80
|
+
summary: Easy-peasy parsing of fasta files
|
44
81
|
test_files: []
|