bio-sra 0.1.0

data/test/helper.rb

@@ -0,0 +1,18 @@
+require 'rubygems'
+require 'bundler'
+begin
+  Bundler.setup(:default, :development)
+rescue Bundler::BundlerError => e
+  $stderr.puts e.message
+  $stderr.puts "Run `bundle install` to install missing gems"
+  exit e.status_code
+end
+require 'test/unit'
+require 'shoulda'
+
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
+$LOAD_PATH.unshift(File.dirname(__FILE__))
+require 'bio-sra'
+
+class Test::Unit::TestCase
+end

data/test/test_bio-sra.rb

@@ -0,0 +1,78 @@
+require 'helper'
+require 'pp'
+
+class TestBioSraTables < Test::Unit::TestCase
+  include Bio::SRA::Tables
+  
+  def set
+    Bio::SRA.connect
+  end
+  
+  should "test find by accession" do
+    set
+    # 1.9.3-p0 :014 > p Bio::SRA::SRA.find_by_sra_ID('2.0')
+    #<Bio::SRA::SRA sra_ID: 2.0, SRR_bamFile: nil, SRX_bamFile: nil, SRX_fastqFTP: nil, run_ID: 2.0, run_alias: "2008-09-12.Bsu168-Lane5", run_accession: "DRR000002", run_date: "2008-09-12", updated_date: "2011-03-04", spots: 8316737, bases: 598805064, run_center: "NIG", experiment_name: "BSU168_SEP08", run_url_link: nil, run_entrez_link: nil, run_attribute: "notes: repackaged seq prb sig2", experiment_ID: 2.0, experiment_alias: "BSU168_SEP08", experiment_accession: "DRX000002", experiment_title: "B. subtilis subsp. subtilis genome resequencing Sep...", study_name: "Resequence B. subtilis 168", sample_name: "B. subtilis 168 DNA extracted Aug 2008", design_description: "Randomly fragmented by ultrasonic waves.", library_name: "B.subtilis subtilis 168 Genomic DNA fragments, isol...", library_strategy: "WGS", library_source: "GENOMIC", library_selection: "RANDOM", library_layout: "PAIRED - NOMINAL_LENGTH: 153; NOMINAL_SDEV: 29.528;...", library_construction_protocol: "The DNA is purified through the ultracentrifugation...", adapter_spec: nil, read_spec: "READ_INDEX: 0; READ_CLASS: Application Read; READ_T...", platform: "ILLUMINA", instrument_model: "Illumina Genome Analyzer II", instrument_name: nil, platform_parameters: "INSTRUMENT_MODEL: Illumina Genome Analyzer II; CYCL...", sequence_space: "Base Space", base_caller: "Solexa primary analysis", quality_scorer: "Solexa primary analysis", number_of_levels: 80, multiplier: "1", qtype: "other", experiment_url_link: nil, experiment_entrez_link: nil, experiment_attribute: nil, sample_ID: 2.0, sample_alias: "B. subtilis 168 DNA extracted Aug 2008", sample_accession: "DRS000002", taxon_id: 224308, common_name: "Bacillus subtilis subsp. subtilis str. 168", anonymized_name: nil, individual_name: nil, description: "Genomic DNA from Bacillus subtilis subsp. subtilis ...", sample_url_link: nil, sample_entrez_link: nil, sample_attribute: "strain: str. 168: ", study_ID: 2.0, study_alias: "Resequence B. subtilis 168", study_accession: "DRP000002", study_title: "Whole genome resequencing of Bacillus subtilis subs...", study_type: "Whole Genome Sequencing", study_abstract: "Whole genome resequencing of B. subtilis subtilis 1...", center_project_name: "Whole genome resequencing of B. subtilis subtilis 1...", study_description: "Whole genome resequencing of B. subtilis subtilis 1...", study_url_link: nil, study_entrez_link: "pubmed: 20398357", study_attribute: nil, related_studies: "DB: bioproject; ID: 39275; LABEL: PRJDA39275", primary_study: "true", submission_ID: 2.0, submission_accession: "DRA000002", submission_comment: "Bacillus subtilis subsp. subtilis strain 168 resequ...", submission_center: "KEIO", submission_lab: "Bioinformatics Lab.", submission_date: "2009-07-09", sradb_updated: "2012-04-04 20:00:12">
+
+    # test experiment_accession
+    assert_equal 'DRR000002', SRA.accession('DRX000002').first.run_accession
+    assert_equal 'DRR000002', SRA.accession('DRP000002').first.run_accession
+    assert_equal 'DRR000002', SRA.accession('DRA000002').first.run_accession
+    assert_equal 'DRR000002', SRA.accession('DRS000002').first.run_accession
+    assert_equal 'DRR000002', SRA.accession('DRR000002').first.run_accession
+  end
+  
+  should "find all runs from a single project" do
+    set
+    assert_equal ['ftp://ftp-trace.ncbi.nlm.nih.gov/sra/sra-instant/reads/ByRun/litesra/DRR/DRR000/DRR000002/DRR000002.lite.sra'],
+      SRA.accession('DRR000002').first.study_download_urls
+    
+    three = SRA.accession('DRR000003').first.study_download_urls.sort
+    assert_equal 9, three.length
+    assert_equal 'ftp://ftp-trace.ncbi.nlm.nih.gov/sra/sra-instant/reads/ByRun/litesra/DRR/DRR000/DRR000004/DRR000004.lite.sra',
+      three[1]
+      
+    three = SRA.accession('DRR000003').first.study_download_urls(:format => :sra).sort
+    assert_equal 9, three.length
+    assert_equal 'ftp://ftp-trace.ncbi.nlm.nih.gov/sra/sra-instant/reads/ByRun/sra/DRR/DRR000/DRR000004/DRR000004.sra',
+      three[1]
+  end
+  
+  should "find all by accession" do
+    set
+    assert_equal 9, SRA.accession('DRP000003').all.uniq.length
+    assert_equal 'DRR000004', SRA.accession('DRP000003').all.collect{|s| s.run_accession}.sort[1]
+  end
+  
+  should "sra should have foreign key to submission" do
+    set
+    assert_equal 'KEIO', SRA.accession('DRP000001').first.submission.center_name
+    sras = Submission.find(1).sras
+    assert_equal 1, sras.length
+    assert_equal 'DRP000001', sras[0].study_accession
+    
+    sras = Submission.find(3).sras
+    assert_equal 9, sras.length
+    assert_equal 'DRP000003', sras[0].study_accession
+  end
+end
+
+
+class TestBioSraAccession < Test::Unit::TestCase
+  include Bio::SRA
+  
+  should "test get regular run accession" do
+    assert_equal 'ftp://ftp-trace.ncbi.nlm.nih.gov/sra/sra-instant/reads/ByRun/litesra/DRR/DRR000/DRR000002/DRR000002.lite.sra',
+      Accession.run_download_url('DRR000002')
+    assert_equal 'ftp://ftp-trace.ncbi.nlm.nih.gov/sra/sra-instant/reads/ByRun/sra/DRR/DRR000/DRR000002/DRR000002.sra',
+      Accession.run_download_url('DRR000002', :format => :sra)
+    assert_equal 'ftp://ftp-trace.ncbi.nlm.nih.gov/sra/sra-instant/reads/ByRun/litesra/DRR/DRR000/DRR000002/DRR000002.lite.sra',
+      Accession.run_download_url('DRR000002', :format => :sralite)
+
+    assert_raise RuntimeError do
+      Accession.run_download_url('DRP000002')
+    end
+    assert_raise RuntimeError do
+      Accession.run_download_url('DRR000002', :format => :notaformat)
+    end
+  end
+end

data/test/test_sra_download.rb

@@ -0,0 +1,86 @@
+require 'helper'
+require 'pp'
+require 'bio-commandeer'
+require 'tmpdir'
+require 'tempfile'
+
+class TestSRADownload < Test::Unit::TestCase
+  include Bio::SRA::Tables
+
+  path_to_script = File.join(File.dirname(__FILE__),'..','bin','sra_download')
+
+  should "(really) download a single run file" do
+    expected_md5sum = '52b04843abcddb4ad4fa124c471c23ce  -'+"\n"
+
+    Dir.mktmpdir do |tmp|
+      Dir.chdir(tmp) do
+        Bio::Commandeer.run "#{path_to_script} ERR229501"
+        assert_equal expected_md5sum,
+          Bio::Commandeer.run("cat ERR229501.sra |md5sum")
+      end
+    end
+  end
+
+  should 'download all files from a study' do
+    Dir.mktmpdir do |tmp|
+      Dir.chdir(tmp) do
+        expected = [
+          'ftp://ftp-trace.ncbi.nlm.nih.gov/sra/sra-instant/reads/ByRun/sra/SRR/SRR033/SRR033547/SRR033547.sra',
+          'ftp://ftp-trace.ncbi.nlm.nih.gov/sra/sra-instant/reads/ByRun/sra/SRR/SRR033/SRR033549/SRR033549.sra',
+          'ftp://ftp-trace.ncbi.nlm.nih.gov/sra/sra-instant/reads/ByRun/sra/SRR/SRR033/SRR033548/SRR033548.sra',
+          ].join("\n")+"\n"
+
+        assert_equal expected, Bio::Commandeer.run("#{path_to_script} --dry-run SRP001692 -q")
+      end
+    end
+  end
+
+  should 'download all files from an experiment' do
+    Dir.mktmpdir do |tmp|
+      Dir.chdir(tmp) do
+        expected = [
+          #'ftp://ftp-trace.ncbi.nlm.nih.gov/sra/sra-instant/reads/ByRun/sra/SRR/SRR033/SRR033547/SRR033547.sra',
+          'ftp://ftp-trace.ncbi.nlm.nih.gov/sra/sra-instant/reads/ByRun/sra/SRR/SRR033/SRR033549/SRR033549.sra',
+          #'ftp://ftp-trace.ncbi.nlm.nih.gov/sra/sra-instant/reads/ByRun/sra/SRR/SRR033/SRR033548/SRR033548.sra',
+          ].join("\n")+"\n"
+
+        assert_equal expected, Bio::Commandeer.run("#{path_to_script} --dry-run SRX015618 -q")
+      end
+    end
+  end
+
+  should 'download all files from a sample' do
+    Dir.mktmpdir do |tmp|
+      Dir.chdir(tmp) do
+        expected = [
+          'ftp://ftp-trace.ncbi.nlm.nih.gov/sra/sra-instant/reads/ByRun/sra/SRR/SRR033/SRR033547/SRR033547.sra',
+          'ftp://ftp-trace.ncbi.nlm.nih.gov/sra/sra-instant/reads/ByRun/sra/SRR/SRR033/SRR033549/SRR033549.sra',
+          'ftp://ftp-trace.ncbi.nlm.nih.gov/sra/sra-instant/reads/ByRun/sra/SRR/SRR033/SRR033548/SRR033548.sra',
+          ].join("\n")+"\n"
+
+        assert_equal expected, Bio::Commandeer.run("#{path_to_script} --dry-run SRS009755 -q")
+      end
+    end
+  end
+
+
+  should 'handle mixed run and experiment input in a file input' do
+    Dir.mktmpdir do |tmp|
+      Dir.chdir(tmp) do
+        expected = [
+          'ftp://ftp-trace.ncbi.nlm.nih.gov/sra/sra-instant/reads/ByRun/sra/SRR/SRR033/SRR033547/SRR033547.sra',
+          'ftp://ftp-trace.ncbi.nlm.nih.gov/sra/sra-instant/reads/ByRun/sra/SRR/SRR033/SRR033549/SRR033549.sra',
+          'ftp://ftp-trace.ncbi.nlm.nih.gov/sra/sra-instant/reads/ByRun/sra/SRR/SRR033/SRR033548/SRR033548.sra',
+          ].join("\n")+"\n"
+
+        Tempfile.open("t") do |infile|
+          infile.puts 'SRS009755'
+          infile.puts 'SRR033548'
+          infile.close
+
+          assert_equal expected, Bio::Commandeer.run("#{path_to_script} --dry-run -f #{infile.path} -q")
+        end
+      end
+    end
+  end
+end

metadata

@@ -0,0 +1,216 @@
+--- !ruby/object:Gem::Specification
+name: bio-sra
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Ben J. Woodcroft
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2014-12-15 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: activerecord
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.2'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.2'
+- !ruby/object:Gem::Dependency
+  name: activesupport
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.2'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.2'
+- !ruby/object:Gem::Dependency
+  name: sqlite3
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.3'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.3'
+- !ruby/object:Gem::Dependency
+  name: bio-logger
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
+- !ruby/object:Gem::Dependency
+  name: shoulda
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.5'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.5'
+- !ruby/object:Gem::Dependency
+  name: rdoc
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.12'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.12'
+- !ruby/object:Gem::Dependency
+  name: jeweler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 2.0.1
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 2.0.1
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.0'
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.6'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.6'
+- !ruby/object:Gem::Dependency
+  name: bio
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.4.2
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.4'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.4.2
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.4'
+- !ruby/object:Gem::Dependency
+  name: bio-commandeer
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.1'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.1'
+description: A Sequence Read Archive (SRA) download script and Ruby interface to the
+  SRAdb (SRA metadata) SQLite database.
+email: donttrustben near gmail.com
+executables:
+- sra_download
+extensions: []
+extra_rdoc_files:
+- LICENSE.txt
+- README.md
+files:
+- ".document"
+- ".travis.yml"
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- VERSION
+- bin/sra_download
+- config/database.yml
+- lib/bio-sra.rb
+- lib/bio/sra/connect.rb
+- lib/bio/sra/sra.rb
+- lib/bio/sra/tables.rb
+- test/helper.rb
+- test/test_bio-sra.rb
+- test/test_sra_download.rb
+homepage: http://github.com/wwood/bioruby-sra
+licenses:
+- MIT
+metadata: {}
+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: 2.2.2
+signing_key: 
+specification_version: 4
+summary: A Sequence Read Archive (SRA) download script and Ruby interface to the SRAdb
+  (SRA metadata) SQLite database
+test_files: []