ciika 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 9158850d1c86f75286d6904cab6bdb02ba7fc992
+  data.tar.gz: 816c70213f0fd3e47c9d431e05d557c6e15f9fcf
+SHA512:
+  metadata.gz: 1ee73fabbed29b2694e1bdf04fdde46197522909e79aca21d3997af9a9fef45f0371984ae9cc10e1213de708e30449937babcac87744177f9b857d3c00a5ed1e
+  data.tar.gz: 9feee3d7a1d1e3fd1195865405223be996558b5c77f4d70dd287084369161be3cae1d038306c1b3b6aec87e84fadea444c439650327e6e4c0b900c4779d4310c

data/.gitignore

@@ -0,0 +1,10 @@
+/.bundle/
+/.yardoc
+/Gemfile.lock
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+vendor/bundle

data/.rspec

@@ -0,0 +1,2 @@
+--format documentation
+--color

data/.travis.yml

@@ -0,0 +1,4 @@
+language: ruby
+rvm:
+  - 2.2.1
+before_install: gem install bundler -v 1.10.6

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in ciika.gemspec
+gemspec

data/README.md

@@ -0,0 +1,35 @@
+# Ciika
+
+[![Build Status](https://secure.travis-ci.org/inutano/ciika.png)](http://travis-ci.org/inutano/ciika)
+
+Ciika is utility tool to handle metadata of public NGSeq repository.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'ciika'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install ciika
+
+## Usage
+
+Parse Sequence Read Archive metadata xml
+
+```ruby
+xml = "/path/to/DRA000001.experiment.xml"
+data = Ciika::SRA::Experiment.new(xml).parse
+```
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/inutano/ciika.
+

data/Rakefile

@@ -0,0 +1,6 @@
+require "bundler/gem_tasks"
+require "rspec/core/rake_task"
+
+RSpec::Core::RakeTask.new(:spec)
+
+task :default => :spec

data/bin/console

@@ -0,0 +1,11 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "ciika"
+
+# You can add fixtures and/or initialization code here to make experimenting
+# with your gem easier. You can also use a different console, if you like.
+
+# (If you use this, don't forget to add pry to your Gemfile!)
+require "pry"
+Pry.start

data/bin/setup

@@ -0,0 +1,7 @@
+#!/bin/bash
+set -euo pipefail
+IFS=$'\n\t'
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/ciika.gemspec

@@ -0,0 +1,35 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'ciika/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "ciika"
+  spec.version       = Ciika::VERSION
+  spec.authors       = ["Tazro Inutano Ohta"]
+  spec.email         = ["inutano@gmail.com"]
+
+  spec.summary       = %q{A ruby parser for public DNA sequence database metadata}
+  spec.description   = %q{Ciika is a set of utils which helps to handle metadata from Sequence Read Archive, BioProject, BioSample, GEO, ArrayExpress, etc.}
+  spec.homepage      = "http://github.com/inutano/ciika"
+
+  # Prevent pushing this gem to RubyGems.org by setting 'allowed_push_host', or
+  # delete this section to allow pushing this gem to any host.
+  if spec.respond_to?(:metadata)
+    spec.metadata['allowed_push_host'] = "https://rubygems.org"
+  else
+    raise "RubyGems 2.0 or newer is required to protect against public gem pushes."
+  end
+
+  spec.files         = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
+  spec.bindir        = "exe"
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "bundler", "~> 1.10"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "rspec"
+  spec.add_development_dependency "pry"
+  spec.add_dependency "thor"
+  spec.add_dependency "nokogiri"
+end

data/exe/ciika

@@ -0,0 +1,4 @@
+#!/usr/bin/env ruby
+
+require "ciika"
+Ciika::CLI.start

data/lib/ciika.rb

@@ -0,0 +1,12 @@
+require "ciika/sra/run"
+require "ciika/sra/sample"
+require "ciika/sra/experiment"
+require "ciika/sra/study"
+require "ciika/sra/submission"
+require "ciika/sra"
+require "ciika/cli"
+require "ciika/version"
+
+module Ciika
+  # Your code goes here...
+end

data/lib/ciika/cli.rb

@@ -0,0 +1,12 @@
+# -*- coding: utf-8 -*-
+
+require 'thor'
+
+module Ciika
+  class CLI < Thor
+    desc "retrieve [db] [id]", "Retrieve metadata from db with id in json format"
+    def retrieve(db, id)
+      puts "Got information from #{db} with identifier #{id}"
+    end
+  end
+end

data/lib/ciika/sra.rb

@@ -0,0 +1,19 @@
+# -*- coding: utf-8 -*-
+
+require 'nokogiri'
+
+module Ciika
+  module SRA
+    module_function
+    def id_selector(type, xml, id)
+      # return an array of nokogiri objects
+      dataset = Nokogiri::XML(open(xml)).css(type)
+      case id
+      when :all
+        dataset
+      else
+        dataset.select{|n| n.attr("accession") =~ /#{id}/ }
+      end
+    end
+  end
+end

data/lib/ciika/sra/experiment.rb

@@ -0,0 +1,90 @@
+# -*- coding: utf-8 -*-
+
+module Ciika
+  module SRA
+    class Experiment
+      def initialize(xml, id: :all)
+        @experimentset = Ciika::SRA::id_selector("EXPERIMENT", xml, id)
+        raise NameError, "ID not found" if @studyset == []
+      end
+
+      def parse
+        @experimentset.map do |experiment|
+          layout = experiment.css("LIBRARY_LAYOUT").first.children[1]
+          {
+            accession:          experiment.attr("accession").to_s,
+            alias:              experiment.attr("alias").to_s,
+            center_name:        experiment.attr("center_name").to_s,
+            title:              experiment.css("TITLE").inner_text,
+            study_accession:    experiment.css("STUDY_REF").attr("accession").to_s,
+            study_refname:      experiment.css("STUDY_REF").attr("refname").to_s,
+            design_description: experiment.css("DESIGN_DESCRIPTION").inner_text,
+            sample_accession:   experiment.css("SAMPLE_DESCRIPTOR").first.attr("accession").to_s,
+            sample_refname:     experiment.css("SAMPLE_DESCRIPTOR").first.attr("refname").to_s,
+
+            library_description: {
+              library_name:                  experiment.css("LIBRARY_NAME").inner_text,
+              library_strategy:              experiment.css("LIBRARY_STRATEGY").inner_text,
+              library_source:                experiment.css("LIBRARY_SOURCE").inner_text,
+              library_selection:             experiment.css("LIBRARY_SELECTION").inner_text,
+              library_layout:                experiment.css("LIBRARY_LAYOUT").first.children[1].name,
+              library_orientation:           layout.attr("ORIENTATION").to_s,
+              library_nominal_length:        layout.attr("NOMINAL_LENGTH").to_s,
+              library_nominal_sdev:          layout.attr("NOMINAL_SDEV").to_s,
+              library_construction_protocol: experiment.css("LIBRARY_CONSTRUCTION_PROTOCOL").inner_text,
+            },
+
+            platform_information:   {
+              platform:         experiment.css("PLATFORM").first.children[1].name,
+              instrument_model: experiment.css("INSTRUMENT_MODEL").inner_text,
+              cycle_sequence:   experiment.css("CYCLE_SEQUENCE").inner_text,
+              cycle_count:      experiment.css("CYCLE_COUNT").inner_text,
+              flow_sequence:    experiment.css("FLOW_SEQUENCE").inner_text,
+              flow_count:       experiment.css("FLOW_COUNT").inner_text,
+              key_sequence:     experiment.css("KEY_SEQUENCE").inner_text,
+            },
+
+            processing_information: {
+              base_calls: {
+                sequence_space: experiment.css("SEQUENCE_SPACE").inner_text,
+                base_caller:    experiment.css("BASE_CALLER").inner_text,
+              },
+
+              quality_scores: experiment.css("QUALITY_SCORES").map{|node|
+                {
+                  quality_type:    node.attr("qtype").to_s,
+                  quality_scorer:  node.css("QUALITY_SCORER").inner_text,
+                  number_of_level: node.css("NUMBER_OF_LEVELS").inner_text,
+                  multiplier:      node.css("MULTIPLIER").inner_text
+                }
+              },
+
+              pipe_section:   experiment.css("PIPE_SECTION").map{|node|
+                {
+                  step_index:      node.css("STEP_INDEX").inner_text,
+                  prev_step_index: node.css("PREV_STEP_INDEX").inner_text,
+                  program:         node.css("PROGRAM").inner_text,
+                  version:         node.css("VERSION").inner_text,
+                }
+              },
+            },
+
+            spot_information: {
+              number_of_reads_per_spot: experiment.css("NUMBER_OF_READS_PER_SPOT").inner_text,
+              spot_length:              experiment.css("SPOT_LENGTH").inner_text,
+            },
+
+            read_spec: experiment.css("READ_SPEC").map{|node|
+              {
+                read_index: node.css("READ_INDEX").inner_text,
+                read_class: node.css("READ_CLASS").inner_text,
+                read_type: node.css("READ_TYPE").inner_text,
+                base_coord: node.css("BASE_COORD").inner_text,
+              }
+            },
+          }
+        end
+      end
+    end
+  end
+end

data/lib/ciika/sra/run.rb

@@ -0,0 +1,56 @@
+# -*- coding: utf-8 -*-
+
+module Ciika
+  module SRA
+    class Run
+      def initialize(xml, id: :all)
+        @runset = Ciika::SRA::id_selector("RUN", xml, id)
+        raise NameError, "ID not found" if @runset == []
+      end
+
+      def parse
+        @runset.map do |run|
+          {
+            accession:         run.attr("accession").to_s,
+            alias:             run.attr("alias").to_s,
+            center_name:       run.attr("center_name").to_s,
+            run_center:        run.attr("run_center").to_s,
+            run_date:          run.attr("run_date").to_s,
+            instrument_name:   run.attr("instrument_name").to_s,
+            total_data_blocks: run.attr("total_data_blocks").to_s,
+
+            pipeline: run.css("PIPE_SECTION").map{|node|
+              {
+                section_name:    node.attr("section_name").to_s,
+                step_index:      node.css("STEP_INDEX").inner_text,
+                prev_step_index: node.css("PREV_STEP_INDEX").inner_text,
+                program:         node.css("PROGRAM").inner_text,
+                version:         node.css("VERSION").inner_text,
+              }
+            },
+
+            spot_information: {
+              number_of_reads_per_spot: run.css("NUMBER_OF_READS_PER_SPOT").inner_text,
+              spot_length:              run.css("SPOT_LENGTH").inner_text,
+              read_spec: run.css("READ_SPEC").map{|node|
+                {
+                  read_index: node.css("READ_INDEX").inner_text,
+                  read_class: node.css("READ_CLASS").inner_text,
+                  read_type: node.css("READ_TYPE").inner_text,
+                  base_coord: node.css("BASE_COORD").inner_text,
+                }
+              },
+            },
+
+            run_attr: run.css("RUN_ATTRIBUTE").map{|node|
+              {
+                tag:   node.css("TAG").inner_text,
+                value: node.css("VALUE").inner_text,
+              }
+            }
+          }
+        end
+      end
+		end
+	end
+end

data/lib/ciika/sra/sample.rb

@@ -0,0 +1,47 @@
+# -*- coding: utf-8 -*-
+
+module Ciika
+  module SRA
+    class Sample
+			def initialize(xml, id: :all)
+	      @sampleset = Ciika::SRA::id_selector("SAMPLE", xml, id)
+	      raise NameError, "ID not found" if @sampleset == []
+	    end
+
+	    def parse
+	      @sampleset.map do |sample|
+	        {
+	          accession:          sample.attr("accession").to_s,
+	          alias:              sample.attr("alias").to_s,
+	          title:              sample.css("TITLE").inner_text,
+	          sample_description: sample.css("DESCRIPTION").inner_text,
+
+	          organism_information: {
+              taxon_id:        sample.css("TAXON_ID").inner_text,
+              common_name:     sample.css("COMMON_NAME").inner_text,
+              scientific_name: sample.css("SCIENTIFIC_NAME").inner_text,
+              anonymized_name: sample.css("ANONYMIZED_NAME").inner_text,
+              individual_name: sample.css("INDIVIDUAL_NAME").inner_text,
+            },
+
+	          sample_links: {
+              url_link: sample.css("URL_LINK").map{|node|
+	              {
+	                label: node.css("LABEL").inner_text,
+	                url:   node.css("URL").inner_text,
+	              }
+	            },
+
+              entrez_link: sample.css("ENTREZ_LINK").map{|node|
+                {
+                  db: node.css("DB").inner_text,
+                  id: node.css("ID").inner_text,
+                }
+              },
+            },
+	        }
+	      end
+	    end
+		end
+	end
+end

data/lib/ciika/sra/study.rb

@@ -0,0 +1,49 @@
+# -*- coding: utf-8 -*-
+
+module Ciika
+  module SRA
+    class Study
+      def initialize(xml, id: :all)
+        @studyset = Ciika::SRA::id_selector("STUDY", xml, id)
+        raise NameError, "ID not found" if @studyset == []
+      end
+
+      def parse
+        @studyset.map do |study|
+          {
+            accession:           study.attr("accession").to_s,
+            alias:               study.attr("alias").to_s,
+            center_name:         study.attr("center_name").to_s,
+            center_project_name: study.css("CENTER_PROJECT_NAME").inner_text,
+            study_title:         study.css("STUDY_TITLE").inner_text,
+            study_type:          study.css("STUDY_TYPE").attr("existing_study_type").to_s,
+            study_abstract:      study.css("STUDY_ABSTRACT").inner_text,
+            study_description:   study.css("STUDY_DESCRIPTION").inner_text,
+
+            url_link: study.css("URL_LINK").map{|node|
+              {
+                label: node.css("LABEL").inner_text,
+                url:   node.css("URL").inner_text
+              }
+            },
+
+            entrez_link: study.css("ENTREZ_LINK").map{|node|
+              {
+                db: node.css("DB").inner_text,
+                id: node.css("ID").inner_text
+              }
+            },
+
+            related_link: study.css("RELATED_LINK").map{|node|
+              {
+                db:    node.css("DB").inner_text,
+                id:    node.css("ID").inner_text,
+                label: node.css("LABEL").inner_text
+              }
+            },
+          }
+        end
+      end
+		end
+	end
+end

data/lib/ciika/sra/submission.rb

@@ -0,0 +1,25 @@
+# -*- coding: utf-8 -*-
+
+module Ciika
+  module SRA
+    class Submission
+      def initialize(xml, id: :all)
+        @submissionset = Ciika::SRA::id_selector("SUBMISSION", xml, id)
+        raise NameError, "ID not found" if @submission == []
+      end
+
+      def parse
+        @submissionset.map do |submission|
+          {
+            alias:              submission.attr("alias").to_s,
+            accession:          submission.attr("accession").to_s,
+            submission_comment: submission.attr("submission_comment").to_s,
+            center_name:        submission.attr("center_name").to_s,
+            lab_name:           submission.attr("lab_name").to_s,
+            submission_date:    submission.attr("submission_date").to_s
+          }
+        end
+      end
+		end
+	end
+end

data/lib/ciika/version.rb

@@ -0,0 +1,3 @@
+module Ciika
+  VERSION = "0.1.0"
+end

metadata

@@ -0,0 +1,149 @@
+--- !ruby/object:Gem::Specification
+name: ciika
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Tazro Inutano Ohta
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2015-11-06 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.10'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.10'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: pry
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: thor
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+description: Ciika is a set of utils which helps to handle metadata from Sequence
+  Read Archive, BioProject, BioSample, GEO, ArrayExpress, etc.
+email:
+- inutano@gmail.com
+executables:
+- ciika
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- ".travis.yml"
+- Gemfile
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- ciika.gemspec
+- exe/ciika
+- lib/ciika.rb
+- lib/ciika/cli.rb
+- lib/ciika/sra.rb
+- lib/ciika/sra/experiment.rb
+- lib/ciika/sra/run.rb
+- lib/ciika/sra/sample.rb
+- lib/ciika/sra/study.rb
+- lib/ciika/sra/submission.rb
+- lib/ciika/version.rb
+homepage: http://github.com/inutano/ciika
+licenses: []
+metadata:
+  allowed_push_host: https://rubygems.org
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.4.5
+signing_key: 
+specification_version: 4
+summary: A ruby parser for public DNA sequence database metadata
+test_files: []