qu-seqcluster 1.0.0
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.
- checksums.yaml +7 -0
- data/.gitignore +19 -0
- data/Gemfile +5 -0
- data/LICENSE.txt +22 -0
- data/README.md +45 -0
- data/Rakefile +1 -0
- data/bin/seqcluster +6 -0
- data/lib/qu/seqcluster.rb +13 -0
- data/lib/qu/seqcluster/cluster.rb +53 -0
- data/lib/qu/seqcluster/options.rb +106 -0
- data/lib/qu/seqcluster/program.rb +5 -0
- data/lib/qu/seqcluster/runner.rb +29 -0
- data/lib/qu/seqcluster/version.rb +5 -0
- data/qu-seqcluster.gemspec +25 -0
- metadata +100 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: e998132776509d1b787ab5ba02ebf81c43179ce9
|
4
|
+
data.tar.gz: ec82c798b27f9eaeb12f8554be750adb46b1a8d7
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: f8027e2bfa6f14d3d9c7664f2efac98de8dc19e8786552c47ce759c2cf4a7912b8cf5b77b86112ea3b44e7ae98e01fd66be86363ee768ed22adf2f6c88ad8ccf
|
7
|
+
data.tar.gz: 51ad5ab6631c161db2e08025c6228fed584dfb640cde2cc1a956dc23e3373689708f0476b4620e8664fb3f3062a551b4ec13a84728f0ae5692d3749054ea0693
|
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2013 Wubin Qu
|
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 +1,45 @@
|
|
1
|
+
# Qu::Seqcluster
|
2
|
+
|
3
|
+
Cluster DNA/RNA based on k-mer algorithm
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
gem 'qu-seqcluster'
|
10
|
+
|
11
|
+
And then execute:
|
12
|
+
|
13
|
+
$ bundle
|
14
|
+
|
15
|
+
Or install it yourself as:
|
16
|
+
|
17
|
+
$ gem install qu-seqcluster
|
18
|
+
|
19
|
+
## Usage
|
20
|
+
|
21
|
+
```
|
22
|
+
Usage: seqcluster -i seq.fasta -k 9 -c 0.9
|
23
|
+
|
24
|
+
Required options:
|
25
|
+
|
26
|
+
-i, --in File Input sequence file in fasta format.
|
27
|
+
|
28
|
+
Optional options:
|
29
|
+
|
30
|
+
-k, --kvalue Integer K value, default is 9.
|
31
|
+
-o, --out File Output file name for storing the results, default is screen.
|
32
|
+
-c, --cutoff Float Cutoff value for the similarity for cluster, default is 0.9.
|
33
|
+
|
34
|
+
|
35
|
+
-h, --help Show this message and quit
|
36
|
+
-v, --version Show version
|
37
|
+
```
|
38
|
+
|
39
|
+
## Contributing
|
40
|
+
|
41
|
+
1. Fork it
|
42
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
43
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
44
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
45
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require "bundler/gem_tasks"
|
data/bin/seqcluster
ADDED
@@ -0,0 +1,13 @@
|
|
1
|
+
require "qu/utils"
|
2
|
+
|
3
|
+
require_relative "seqcluster/program"
|
4
|
+
require_relative "seqcluster/version"
|
5
|
+
require_relative "seqcluster/options"
|
6
|
+
require_relative "seqcluster/cluster"
|
7
|
+
require_relative "seqcluster/runner"
|
8
|
+
|
9
|
+
module Qu
|
10
|
+
module Seqcluster
|
11
|
+
# Your code goes here...
|
12
|
+
end
|
13
|
+
end
|
@@ -0,0 +1,53 @@
|
|
1
|
+
require 'set'
|
2
|
+
|
3
|
+
module Qu
|
4
|
+
module Seqcluster
|
5
|
+
class Cluster
|
6
|
+
attr_reader :opts
|
7
|
+
def initialize(opts)
|
8
|
+
@opts = opts
|
9
|
+
end
|
10
|
+
|
11
|
+
def find_cluster
|
12
|
+
records = Bio::FlatFile.new(Bio::FastaFormat, File.open(@opts.in)).to_a
|
13
|
+
records.sort_by! {|r| -r.seq.size}
|
14
|
+
|
15
|
+
groups = []
|
16
|
+
while records.size > 0
|
17
|
+
groups << []
|
18
|
+
seed_record = records.shift
|
19
|
+
groups[-1] << seed_record
|
20
|
+
seed_kmer_set = seed_kmer(seed_record, @opts.kvalue, 1)
|
21
|
+
records.each_entry do |record|
|
22
|
+
plus = cal_similarity(record.naseq, @opts.kvalue, seed_kmer_set)
|
23
|
+
minus = cal_similarity(record.naseq.reverse_complement, @opts.kvalue, seed_kmer_set)
|
24
|
+
|
25
|
+
similarity, strand = plus > minus ? [plus, '+'] : [minus, '-']
|
26
|
+
|
27
|
+
if similarity >= @opts.cutoff
|
28
|
+
groups[-1] << [record, similarity, strand]
|
29
|
+
end
|
30
|
+
end
|
31
|
+
records.delete_if {|record| groups[-1].collect {|group_record, similarity, strand| group_record}.include?(record)}
|
32
|
+
end
|
33
|
+
|
34
|
+
return groups
|
35
|
+
end
|
36
|
+
|
37
|
+
private
|
38
|
+
|
39
|
+
def seed_kmer(record, window, step)
|
40
|
+
mer_set = Set.new
|
41
|
+
record.naseq.window_search(window, step) {|s| mer_set.add(s.to_sym)}
|
42
|
+
return mer_set
|
43
|
+
end
|
44
|
+
|
45
|
+
def cal_similarity(seq, k, seed_kmer_set)
|
46
|
+
sum = 0
|
47
|
+
remainder = seq.window_search(k, k) {|s| sum += 1 if seed_kmer_set.include?(s.to_sym)}
|
48
|
+
return (sum.to_f * k) / (seq.size - remainder.size)
|
49
|
+
end
|
50
|
+
|
51
|
+
end # Cluster
|
52
|
+
end
|
53
|
+
end
|
@@ -0,0 +1,106 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require 'optparse'
|
4
|
+
require 'ostruct'
|
5
|
+
|
6
|
+
module Qu
|
7
|
+
module Seqcluster
|
8
|
+
|
9
|
+
module_function
|
10
|
+
|
11
|
+
def default_options
|
12
|
+
options = OpenStruct.new
|
13
|
+
options.in = nil
|
14
|
+
options.out = $stdout
|
15
|
+
|
16
|
+
options.kvalue = 9
|
17
|
+
options.cutoff = 0.9
|
18
|
+
|
19
|
+
return options
|
20
|
+
end
|
21
|
+
|
22
|
+
class Options
|
23
|
+
|
24
|
+
attr_reader :opts
|
25
|
+
|
26
|
+
def initialize(argv)
|
27
|
+
@opts = parse_opts(argv)
|
28
|
+
end
|
29
|
+
|
30
|
+
|
31
|
+
def parse_opts(argv)
|
32
|
+
|
33
|
+
options = Seqcluster::default_options
|
34
|
+
|
35
|
+
OptionParser.new do |opts|
|
36
|
+
opts.banner = "#{PROGRAM} [#{VERSION}]: Cluster DNA/RNA based on k-mer algorithm
|
37
|
+
Usage: #{PROGRAM} -i seq.fasta -k 9 -c 0.9"
|
38
|
+
|
39
|
+
opts.separator ""
|
40
|
+
opts.separator "Required options:"
|
41
|
+
opts.separator ""
|
42
|
+
|
43
|
+
opts.on('-i', '--in File', String, 'Input sequence file in fasta format.') do |value|
|
44
|
+
if File.directory?(value)
|
45
|
+
$stderr.puts "Error: #{value} is a direcotry."
|
46
|
+
exit
|
47
|
+
end
|
48
|
+
|
49
|
+
unless File.exists?(value)
|
50
|
+
$stderr.puts "Error: #{value} is not exists."
|
51
|
+
exit
|
52
|
+
end
|
53
|
+
options.in = value
|
54
|
+
end
|
55
|
+
|
56
|
+
opts.separator ""
|
57
|
+
opts.separator "Optional options:"
|
58
|
+
opts.separator ""
|
59
|
+
|
60
|
+
opts.on('-k', '--kvalue Integer', Integer, "K value, default is #{options.kvalue}.") do |value|
|
61
|
+
options.kvalue = value
|
62
|
+
end
|
63
|
+
|
64
|
+
opts.on("-o", "--out File", String, "Output file name for storing the results, default is screen.") do |value|
|
65
|
+
options.out = File.open(value, 'w')
|
66
|
+
end
|
67
|
+
|
68
|
+
opts.on('-c', '--cutoff Float', Float, "Cutoff value for the similarity for cluster, default is #{options.cutoff}.") do |value|
|
69
|
+
options.cutoff = value
|
70
|
+
end
|
71
|
+
|
72
|
+
opts.separator ""
|
73
|
+
opts.separator ""
|
74
|
+
|
75
|
+
opts.on("-h", "--help", "Show this message and quit") do
|
76
|
+
puts opts
|
77
|
+
exit
|
78
|
+
end
|
79
|
+
|
80
|
+
opts.on("-v", "--version", "Show version") do
|
81
|
+
puts "#{PROGRAM} #{VERSION}"
|
82
|
+
exit
|
83
|
+
end
|
84
|
+
|
85
|
+
opts.separator ""
|
86
|
+
opts.separator "Author: Wubin Qu <quwubin@gmail.com>"
|
87
|
+
opts.separator ""
|
88
|
+
|
89
|
+
begin
|
90
|
+
argv = ["-h"] if argv.empty?
|
91
|
+
opts.parse!(argv)
|
92
|
+
rescue OptionParser::ParseError => e
|
93
|
+
$stderr.puts e.message, "\n", opts
|
94
|
+
exit
|
95
|
+
end
|
96
|
+
|
97
|
+
if options.in.nil?
|
98
|
+
$stderr.puts "Error: option -i required."
|
99
|
+
exit
|
100
|
+
end
|
101
|
+
end
|
102
|
+
return options
|
103
|
+
end
|
104
|
+
end
|
105
|
+
end
|
106
|
+
end
|
@@ -0,0 +1,29 @@
|
|
1
|
+
require_relative 'options'
|
2
|
+
require_relative 'cluster'
|
3
|
+
|
4
|
+
module Qu
|
5
|
+
module Seqcluster
|
6
|
+
class Runner
|
7
|
+
attr_reader :opts
|
8
|
+
def initialize(opts)
|
9
|
+
@opts = opts
|
10
|
+
end
|
11
|
+
|
12
|
+
def run
|
13
|
+
groups = Cluster.new(@opts).find_cluster
|
14
|
+
output(groups)
|
15
|
+
end
|
16
|
+
|
17
|
+
def output(groups)
|
18
|
+
@opts.out.puts "Cluster count: #{groups.size}"
|
19
|
+
groups.each_with_index do |group, group_index|
|
20
|
+
@opts.out.puts "Cluster #{group_index + 1}: #{group[0].entry_id}"
|
21
|
+
group[1..-1].each do |record, similarity, strand|
|
22
|
+
@opts.out.puts "\tMember: #{record.entry_id} [#{strand}/#{similarity.round(2)}]"
|
23
|
+
end
|
24
|
+
end
|
25
|
+
end
|
26
|
+
|
27
|
+
end
|
28
|
+
end
|
29
|
+
end
|
@@ -0,0 +1,25 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'qu/seqcluster/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "qu-seqcluster"
|
8
|
+
spec.version = Qu::Seqcluster::VERSION
|
9
|
+
spec.authors = ["Wubin Qu"]
|
10
|
+
spec.email = ["quwubin@gmail.com"]
|
11
|
+
spec.description = %q{Cluster DNA/RNA based on k-mer algorithm}
|
12
|
+
spec.summary = %q{k-mer based cluster program}
|
13
|
+
spec.homepage = "https://github.com/quwubin/qu-seqcluster"
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files`.split($/)
|
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_runtime_dependency 'qu-utils', '~> 1.0'
|
22
|
+
|
23
|
+
spec.add_development_dependency "bundler", "~> 1.3"
|
24
|
+
spec.add_development_dependency "rake"
|
25
|
+
end
|
metadata
ADDED
@@ -0,0 +1,100 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: qu-seqcluster
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 1.0.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Wubin Qu
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2014-04-28 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: qu-utils
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.0'
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: bundler
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '1.3'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '1.3'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rake
|
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
|
+
description: Cluster DNA/RNA based on k-mer algorithm
|
56
|
+
email:
|
57
|
+
- quwubin@gmail.com
|
58
|
+
executables:
|
59
|
+
- seqcluster
|
60
|
+
extensions: []
|
61
|
+
extra_rdoc_files: []
|
62
|
+
files:
|
63
|
+
- ".gitignore"
|
64
|
+
- Gemfile
|
65
|
+
- LICENSE.txt
|
66
|
+
- README.md
|
67
|
+
- Rakefile
|
68
|
+
- bin/seqcluster
|
69
|
+
- lib/qu/seqcluster.rb
|
70
|
+
- lib/qu/seqcluster/cluster.rb
|
71
|
+
- lib/qu/seqcluster/options.rb
|
72
|
+
- lib/qu/seqcluster/program.rb
|
73
|
+
- lib/qu/seqcluster/runner.rb
|
74
|
+
- lib/qu/seqcluster/version.rb
|
75
|
+
- qu-seqcluster.gemspec
|
76
|
+
homepage: https://github.com/quwubin/qu-seqcluster
|
77
|
+
licenses:
|
78
|
+
- MIT
|
79
|
+
metadata: {}
|
80
|
+
post_install_message:
|
81
|
+
rdoc_options: []
|
82
|
+
require_paths:
|
83
|
+
- lib
|
84
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
85
|
+
requirements:
|
86
|
+
- - ">="
|
87
|
+
- !ruby/object:Gem::Version
|
88
|
+
version: '0'
|
89
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
90
|
+
requirements:
|
91
|
+
- - ">="
|
92
|
+
- !ruby/object:Gem::Version
|
93
|
+
version: '0'
|
94
|
+
requirements: []
|
95
|
+
rubyforge_project:
|
96
|
+
rubygems_version: 2.2.0
|
97
|
+
signing_key:
|
98
|
+
specification_version: 4
|
99
|
+
summary: k-mer based cluster program
|
100
|
+
test_files: []
|