ciika 0.1.0

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.
@@ -0,0 +1,7 @@
1
+ ---
2
+ SHA1:
3
+ metadata.gz: 9158850d1c86f75286d6904cab6bdb02ba7fc992
4
+ data.tar.gz: 816c70213f0fd3e47c9d431e05d557c6e15f9fcf
5
+ SHA512:
6
+ metadata.gz: 1ee73fabbed29b2694e1bdf04fdde46197522909e79aca21d3997af9a9fef45f0371984ae9cc10e1213de708e30449937babcac87744177f9b857d3c00a5ed1e
7
+ data.tar.gz: 9feee3d7a1d1e3fd1195865405223be996558b5c77f4d70dd287084369161be3cae1d038306c1b3b6aec87e84fadea444c439650327e6e4c0b900c4779d4310c
@@ -0,0 +1,10 @@
1
+ /.bundle/
2
+ /.yardoc
3
+ /Gemfile.lock
4
+ /_yardoc/
5
+ /coverage/
6
+ /doc/
7
+ /pkg/
8
+ /spec/reports/
9
+ /tmp/
10
+ vendor/bundle
data/.rspec ADDED
@@ -0,0 +1,2 @@
1
+ --format documentation
2
+ --color
@@ -0,0 +1,4 @@
1
+ language: ruby
2
+ rvm:
3
+ - 2.2.1
4
+ before_install: gem install bundler -v 1.10.6
data/Gemfile ADDED
@@ -0,0 +1,4 @@
1
+ source 'https://rubygems.org'
2
+
3
+ # Specify your gem's dependencies in ciika.gemspec
4
+ gemspec
@@ -0,0 +1,35 @@
1
+ # Ciika
2
+
3
+ [![Build Status](https://secure.travis-ci.org/inutano/ciika.png)](http://travis-ci.org/inutano/ciika)
4
+
5
+ Ciika is utility tool to handle metadata of public NGSeq repository.
6
+
7
+ ## Installation
8
+
9
+ Add this line to your application's Gemfile:
10
+
11
+ ```ruby
12
+ gem 'ciika'
13
+ ```
14
+
15
+ And then execute:
16
+
17
+ $ bundle
18
+
19
+ Or install it yourself as:
20
+
21
+ $ gem install ciika
22
+
23
+ ## Usage
24
+
25
+ Parse Sequence Read Archive metadata xml
26
+
27
+ ```ruby
28
+ xml = "/path/to/DRA000001.experiment.xml"
29
+ data = Ciika::SRA::Experiment.new(xml).parse
30
+ ```
31
+
32
+ ## Contributing
33
+
34
+ Bug reports and pull requests are welcome on GitHub at https://github.com/inutano/ciika.
35
+
@@ -0,0 +1,6 @@
1
+ require "bundler/gem_tasks"
2
+ require "rspec/core/rake_task"
3
+
4
+ RSpec::Core::RakeTask.new(:spec)
5
+
6
+ task :default => :spec
@@ -0,0 +1,11 @@
1
+ #!/usr/bin/env ruby
2
+
3
+ require "bundler/setup"
4
+ require "ciika"
5
+
6
+ # You can add fixtures and/or initialization code here to make experimenting
7
+ # with your gem easier. You can also use a different console, if you like.
8
+
9
+ # (If you use this, don't forget to add pry to your Gemfile!)
10
+ require "pry"
11
+ Pry.start
@@ -0,0 +1,7 @@
1
+ #!/bin/bash
2
+ set -euo pipefail
3
+ IFS=$'\n\t'
4
+
5
+ bundle install
6
+
7
+ # Do any other automated setup that you need to do here
@@ -0,0 +1,35 @@
1
+ # coding: utf-8
2
+ lib = File.expand_path('../lib', __FILE__)
3
+ $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
4
+ require 'ciika/version'
5
+
6
+ Gem::Specification.new do |spec|
7
+ spec.name = "ciika"
8
+ spec.version = Ciika::VERSION
9
+ spec.authors = ["Tazro Inutano Ohta"]
10
+ spec.email = ["inutano@gmail.com"]
11
+
12
+ spec.summary = %q{A ruby parser for public DNA sequence database metadata}
13
+ spec.description = %q{Ciika is a set of utils which helps to handle metadata from Sequence Read Archive, BioProject, BioSample, GEO, ArrayExpress, etc.}
14
+ spec.homepage = "http://github.com/inutano/ciika"
15
+
16
+ # Prevent pushing this gem to RubyGems.org by setting 'allowed_push_host', or
17
+ # delete this section to allow pushing this gem to any host.
18
+ if spec.respond_to?(:metadata)
19
+ spec.metadata['allowed_push_host'] = "https://rubygems.org"
20
+ else
21
+ raise "RubyGems 2.0 or newer is required to protect against public gem pushes."
22
+ end
23
+
24
+ spec.files = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
25
+ spec.bindir = "exe"
26
+ spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
27
+ spec.require_paths = ["lib"]
28
+
29
+ spec.add_development_dependency "bundler", "~> 1.10"
30
+ spec.add_development_dependency "rake", "~> 10.0"
31
+ spec.add_development_dependency "rspec"
32
+ spec.add_development_dependency "pry"
33
+ spec.add_dependency "thor"
34
+ spec.add_dependency "nokogiri"
35
+ end
@@ -0,0 +1,4 @@
1
+ #!/usr/bin/env ruby
2
+
3
+ require "ciika"
4
+ Ciika::CLI.start
@@ -0,0 +1,12 @@
1
+ require "ciika/sra/run"
2
+ require "ciika/sra/sample"
3
+ require "ciika/sra/experiment"
4
+ require "ciika/sra/study"
5
+ require "ciika/sra/submission"
6
+ require "ciika/sra"
7
+ require "ciika/cli"
8
+ require "ciika/version"
9
+
10
+ module Ciika
11
+ # Your code goes here...
12
+ end
@@ -0,0 +1,12 @@
1
+ # -*- coding: utf-8 -*-
2
+
3
+ require 'thor'
4
+
5
+ module Ciika
6
+ class CLI < Thor
7
+ desc "retrieve [db] [id]", "Retrieve metadata from db with id in json format"
8
+ def retrieve(db, id)
9
+ puts "Got information from #{db} with identifier #{id}"
10
+ end
11
+ end
12
+ end
@@ -0,0 +1,19 @@
1
+ # -*- coding: utf-8 -*-
2
+
3
+ require 'nokogiri'
4
+
5
+ module Ciika
6
+ module SRA
7
+ module_function
8
+ def id_selector(type, xml, id)
9
+ # return an array of nokogiri objects
10
+ dataset = Nokogiri::XML(open(xml)).css(type)
11
+ case id
12
+ when :all
13
+ dataset
14
+ else
15
+ dataset.select{|n| n.attr("accession") =~ /#{id}/ }
16
+ end
17
+ end
18
+ end
19
+ end
@@ -0,0 +1,90 @@
1
+ # -*- coding: utf-8 -*-
2
+
3
+ module Ciika
4
+ module SRA
5
+ class Experiment
6
+ def initialize(xml, id: :all)
7
+ @experimentset = Ciika::SRA::id_selector("EXPERIMENT", xml, id)
8
+ raise NameError, "ID not found" if @studyset == []
9
+ end
10
+
11
+ def parse
12
+ @experimentset.map do |experiment|
13
+ layout = experiment.css("LIBRARY_LAYOUT").first.children[1]
14
+ {
15
+ accession: experiment.attr("accession").to_s,
16
+ alias: experiment.attr("alias").to_s,
17
+ center_name: experiment.attr("center_name").to_s,
18
+ title: experiment.css("TITLE").inner_text,
19
+ study_accession: experiment.css("STUDY_REF").attr("accession").to_s,
20
+ study_refname: experiment.css("STUDY_REF").attr("refname").to_s,
21
+ design_description: experiment.css("DESIGN_DESCRIPTION").inner_text,
22
+ sample_accession: experiment.css("SAMPLE_DESCRIPTOR").first.attr("accession").to_s,
23
+ sample_refname: experiment.css("SAMPLE_DESCRIPTOR").first.attr("refname").to_s,
24
+
25
+ library_description: {
26
+ library_name: experiment.css("LIBRARY_NAME").inner_text,
27
+ library_strategy: experiment.css("LIBRARY_STRATEGY").inner_text,
28
+ library_source: experiment.css("LIBRARY_SOURCE").inner_text,
29
+ library_selection: experiment.css("LIBRARY_SELECTION").inner_text,
30
+ library_layout: experiment.css("LIBRARY_LAYOUT").first.children[1].name,
31
+ library_orientation: layout.attr("ORIENTATION").to_s,
32
+ library_nominal_length: layout.attr("NOMINAL_LENGTH").to_s,
33
+ library_nominal_sdev: layout.attr("NOMINAL_SDEV").to_s,
34
+ library_construction_protocol: experiment.css("LIBRARY_CONSTRUCTION_PROTOCOL").inner_text,
35
+ },
36
+
37
+ platform_information: {
38
+ platform: experiment.css("PLATFORM").first.children[1].name,
39
+ instrument_model: experiment.css("INSTRUMENT_MODEL").inner_text,
40
+ cycle_sequence: experiment.css("CYCLE_SEQUENCE").inner_text,
41
+ cycle_count: experiment.css("CYCLE_COUNT").inner_text,
42
+ flow_sequence: experiment.css("FLOW_SEQUENCE").inner_text,
43
+ flow_count: experiment.css("FLOW_COUNT").inner_text,
44
+ key_sequence: experiment.css("KEY_SEQUENCE").inner_text,
45
+ },
46
+
47
+ processing_information: {
48
+ base_calls: {
49
+ sequence_space: experiment.css("SEQUENCE_SPACE").inner_text,
50
+ base_caller: experiment.css("BASE_CALLER").inner_text,
51
+ },
52
+
53
+ quality_scores: experiment.css("QUALITY_SCORES").map{|node|
54
+ {
55
+ quality_type: node.attr("qtype").to_s,
56
+ quality_scorer: node.css("QUALITY_SCORER").inner_text,
57
+ number_of_level: node.css("NUMBER_OF_LEVELS").inner_text,
58
+ multiplier: node.css("MULTIPLIER").inner_text
59
+ }
60
+ },
61
+
62
+ pipe_section: experiment.css("PIPE_SECTION").map{|node|
63
+ {
64
+ step_index: node.css("STEP_INDEX").inner_text,
65
+ prev_step_index: node.css("PREV_STEP_INDEX").inner_text,
66
+ program: node.css("PROGRAM").inner_text,
67
+ version: node.css("VERSION").inner_text,
68
+ }
69
+ },
70
+ },
71
+
72
+ spot_information: {
73
+ number_of_reads_per_spot: experiment.css("NUMBER_OF_READS_PER_SPOT").inner_text,
74
+ spot_length: experiment.css("SPOT_LENGTH").inner_text,
75
+ },
76
+
77
+ read_spec: experiment.css("READ_SPEC").map{|node|
78
+ {
79
+ read_index: node.css("READ_INDEX").inner_text,
80
+ read_class: node.css("READ_CLASS").inner_text,
81
+ read_type: node.css("READ_TYPE").inner_text,
82
+ base_coord: node.css("BASE_COORD").inner_text,
83
+ }
84
+ },
85
+ }
86
+ end
87
+ end
88
+ end
89
+ end
90
+ end
@@ -0,0 +1,56 @@
1
+ # -*- coding: utf-8 -*-
2
+
3
+ module Ciika
4
+ module SRA
5
+ class Run
6
+ def initialize(xml, id: :all)
7
+ @runset = Ciika::SRA::id_selector("RUN", xml, id)
8
+ raise NameError, "ID not found" if @runset == []
9
+ end
10
+
11
+ def parse
12
+ @runset.map do |run|
13
+ {
14
+ accession: run.attr("accession").to_s,
15
+ alias: run.attr("alias").to_s,
16
+ center_name: run.attr("center_name").to_s,
17
+ run_center: run.attr("run_center").to_s,
18
+ run_date: run.attr("run_date").to_s,
19
+ instrument_name: run.attr("instrument_name").to_s,
20
+ total_data_blocks: run.attr("total_data_blocks").to_s,
21
+
22
+ pipeline: run.css("PIPE_SECTION").map{|node|
23
+ {
24
+ section_name: node.attr("section_name").to_s,
25
+ step_index: node.css("STEP_INDEX").inner_text,
26
+ prev_step_index: node.css("PREV_STEP_INDEX").inner_text,
27
+ program: node.css("PROGRAM").inner_text,
28
+ version: node.css("VERSION").inner_text,
29
+ }
30
+ },
31
+
32
+ spot_information: {
33
+ number_of_reads_per_spot: run.css("NUMBER_OF_READS_PER_SPOT").inner_text,
34
+ spot_length: run.css("SPOT_LENGTH").inner_text,
35
+ read_spec: run.css("READ_SPEC").map{|node|
36
+ {
37
+ read_index: node.css("READ_INDEX").inner_text,
38
+ read_class: node.css("READ_CLASS").inner_text,
39
+ read_type: node.css("READ_TYPE").inner_text,
40
+ base_coord: node.css("BASE_COORD").inner_text,
41
+ }
42
+ },
43
+ },
44
+
45
+ run_attr: run.css("RUN_ATTRIBUTE").map{|node|
46
+ {
47
+ tag: node.css("TAG").inner_text,
48
+ value: node.css("VALUE").inner_text,
49
+ }
50
+ }
51
+ }
52
+ end
53
+ end
54
+ end
55
+ end
56
+ end
@@ -0,0 +1,47 @@
1
+ # -*- coding: utf-8 -*-
2
+
3
+ module Ciika
4
+ module SRA
5
+ class Sample
6
+ def initialize(xml, id: :all)
7
+ @sampleset = Ciika::SRA::id_selector("SAMPLE", xml, id)
8
+ raise NameError, "ID not found" if @sampleset == []
9
+ end
10
+
11
+ def parse
12
+ @sampleset.map do |sample|
13
+ {
14
+ accession: sample.attr("accession").to_s,
15
+ alias: sample.attr("alias").to_s,
16
+ title: sample.css("TITLE").inner_text,
17
+ sample_description: sample.css("DESCRIPTION").inner_text,
18
+
19
+ organism_information: {
20
+ taxon_id: sample.css("TAXON_ID").inner_text,
21
+ common_name: sample.css("COMMON_NAME").inner_text,
22
+ scientific_name: sample.css("SCIENTIFIC_NAME").inner_text,
23
+ anonymized_name: sample.css("ANONYMIZED_NAME").inner_text,
24
+ individual_name: sample.css("INDIVIDUAL_NAME").inner_text,
25
+ },
26
+
27
+ sample_links: {
28
+ url_link: sample.css("URL_LINK").map{|node|
29
+ {
30
+ label: node.css("LABEL").inner_text,
31
+ url: node.css("URL").inner_text,
32
+ }
33
+ },
34
+
35
+ entrez_link: sample.css("ENTREZ_LINK").map{|node|
36
+ {
37
+ db: node.css("DB").inner_text,
38
+ id: node.css("ID").inner_text,
39
+ }
40
+ },
41
+ },
42
+ }
43
+ end
44
+ end
45
+ end
46
+ end
47
+ end
@@ -0,0 +1,49 @@
1
+ # -*- coding: utf-8 -*-
2
+
3
+ module Ciika
4
+ module SRA
5
+ class Study
6
+ def initialize(xml, id: :all)
7
+ @studyset = Ciika::SRA::id_selector("STUDY", xml, id)
8
+ raise NameError, "ID not found" if @studyset == []
9
+ end
10
+
11
+ def parse
12
+ @studyset.map do |study|
13
+ {
14
+ accession: study.attr("accession").to_s,
15
+ alias: study.attr("alias").to_s,
16
+ center_name: study.attr("center_name").to_s,
17
+ center_project_name: study.css("CENTER_PROJECT_NAME").inner_text,
18
+ study_title: study.css("STUDY_TITLE").inner_text,
19
+ study_type: study.css("STUDY_TYPE").attr("existing_study_type").to_s,
20
+ study_abstract: study.css("STUDY_ABSTRACT").inner_text,
21
+ study_description: study.css("STUDY_DESCRIPTION").inner_text,
22
+
23
+ url_link: study.css("URL_LINK").map{|node|
24
+ {
25
+ label: node.css("LABEL").inner_text,
26
+ url: node.css("URL").inner_text
27
+ }
28
+ },
29
+
30
+ entrez_link: study.css("ENTREZ_LINK").map{|node|
31
+ {
32
+ db: node.css("DB").inner_text,
33
+ id: node.css("ID").inner_text
34
+ }
35
+ },
36
+
37
+ related_link: study.css("RELATED_LINK").map{|node|
38
+ {
39
+ db: node.css("DB").inner_text,
40
+ id: node.css("ID").inner_text,
41
+ label: node.css("LABEL").inner_text
42
+ }
43
+ },
44
+ }
45
+ end
46
+ end
47
+ end
48
+ end
49
+ end
@@ -0,0 +1,25 @@
1
+ # -*- coding: utf-8 -*-
2
+
3
+ module Ciika
4
+ module SRA
5
+ class Submission
6
+ def initialize(xml, id: :all)
7
+ @submissionset = Ciika::SRA::id_selector("SUBMISSION", xml, id)
8
+ raise NameError, "ID not found" if @submission == []
9
+ end
10
+
11
+ def parse
12
+ @submissionset.map do |submission|
13
+ {
14
+ alias: submission.attr("alias").to_s,
15
+ accession: submission.attr("accession").to_s,
16
+ submission_comment: submission.attr("submission_comment").to_s,
17
+ center_name: submission.attr("center_name").to_s,
18
+ lab_name: submission.attr("lab_name").to_s,
19
+ submission_date: submission.attr("submission_date").to_s
20
+ }
21
+ end
22
+ end
23
+ end
24
+ end
25
+ end
@@ -0,0 +1,3 @@
1
+ module Ciika
2
+ VERSION = "0.1.0"
3
+ end
metadata ADDED
@@ -0,0 +1,149 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: ciika
3
+ version: !ruby/object:Gem::Version
4
+ version: 0.1.0
5
+ platform: ruby
6
+ authors:
7
+ - Tazro Inutano Ohta
8
+ autorequire:
9
+ bindir: exe
10
+ cert_chain: []
11
+ date: 2015-11-06 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: '1.10'
20
+ type: :development
21
+ prerelease: false
22
+ version_requirements: !ruby/object:Gem::Requirement
23
+ requirements:
24
+ - - "~>"
25
+ - !ruby/object:Gem::Version
26
+ version: '1.10'
27
+ - !ruby/object:Gem::Dependency
28
+ name: rake
29
+ requirement: !ruby/object:Gem::Requirement
30
+ requirements:
31
+ - - "~>"
32
+ - !ruby/object:Gem::Version
33
+ version: '10.0'
34
+ type: :development
35
+ prerelease: false
36
+ version_requirements: !ruby/object:Gem::Requirement
37
+ requirements:
38
+ - - "~>"
39
+ - !ruby/object:Gem::Version
40
+ version: '10.0'
41
+ - !ruby/object:Gem::Dependency
42
+ name: rspec
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: pry
57
+ requirement: !ruby/object:Gem::Requirement
58
+ requirements:
59
+ - - ">="
60
+ - !ruby/object:Gem::Version
61
+ version: '0'
62
+ type: :development
63
+ prerelease: false
64
+ version_requirements: !ruby/object:Gem::Requirement
65
+ requirements:
66
+ - - ">="
67
+ - !ruby/object:Gem::Version
68
+ version: '0'
69
+ - !ruby/object:Gem::Dependency
70
+ name: thor
71
+ requirement: !ruby/object:Gem::Requirement
72
+ requirements:
73
+ - - ">="
74
+ - !ruby/object:Gem::Version
75
+ version: '0'
76
+ type: :runtime
77
+ prerelease: false
78
+ version_requirements: !ruby/object:Gem::Requirement
79
+ requirements:
80
+ - - ">="
81
+ - !ruby/object:Gem::Version
82
+ version: '0'
83
+ - !ruby/object:Gem::Dependency
84
+ name: nokogiri
85
+ requirement: !ruby/object:Gem::Requirement
86
+ requirements:
87
+ - - ">="
88
+ - !ruby/object:Gem::Version
89
+ version: '0'
90
+ type: :runtime
91
+ prerelease: false
92
+ version_requirements: !ruby/object:Gem::Requirement
93
+ requirements:
94
+ - - ">="
95
+ - !ruby/object:Gem::Version
96
+ version: '0'
97
+ description: Ciika is a set of utils which helps to handle metadata from Sequence
98
+ Read Archive, BioProject, BioSample, GEO, ArrayExpress, etc.
99
+ email:
100
+ - inutano@gmail.com
101
+ executables:
102
+ - ciika
103
+ extensions: []
104
+ extra_rdoc_files: []
105
+ files:
106
+ - ".gitignore"
107
+ - ".rspec"
108
+ - ".travis.yml"
109
+ - Gemfile
110
+ - README.md
111
+ - Rakefile
112
+ - bin/console
113
+ - bin/setup
114
+ - ciika.gemspec
115
+ - exe/ciika
116
+ - lib/ciika.rb
117
+ - lib/ciika/cli.rb
118
+ - lib/ciika/sra.rb
119
+ - lib/ciika/sra/experiment.rb
120
+ - lib/ciika/sra/run.rb
121
+ - lib/ciika/sra/sample.rb
122
+ - lib/ciika/sra/study.rb
123
+ - lib/ciika/sra/submission.rb
124
+ - lib/ciika/version.rb
125
+ homepage: http://github.com/inutano/ciika
126
+ licenses: []
127
+ metadata:
128
+ allowed_push_host: https://rubygems.org
129
+ post_install_message:
130
+ rdoc_options: []
131
+ require_paths:
132
+ - lib
133
+ required_ruby_version: !ruby/object:Gem::Requirement
134
+ requirements:
135
+ - - ">="
136
+ - !ruby/object:Gem::Version
137
+ version: '0'
138
+ required_rubygems_version: !ruby/object:Gem::Requirement
139
+ requirements:
140
+ - - ">="
141
+ - !ruby/object:Gem::Version
142
+ version: '0'
143
+ requirements: []
144
+ rubyforge_project:
145
+ rubygems_version: 2.4.5
146
+ signing_key:
147
+ specification_version: 4
148
+ summary: A ruby parser for public DNA sequence database metadata
149
+ test_files: []