rbbt-sources 1.0.0 → 1.0.1

data/etc/biomart/missing_in_archive

@@ -13,3 +13,15 @@ dec2007:
     - agilent_cgh_44b
     - illumina_humanwg_6_v2
     - illumina_humanwg_6_v3
+aug2007:
+    - protein_id
+    - affy_hc_g110
+    - affy_hg_u133a_2
+    - affy_huex_1_0_st_v2
+    - affy_hugene_1_0_st_v1
+    - agilent_wholegenome
+    - agilent_cgh_44b
+    - illumina_humanwg_6_v2
+    - hgnc
+    - hgnc_id
+    - illumina_humanwg_6_v3

data/lib/rbbt/sources/biomart.rb

@@ -32,6 +32,9 @@ module BioMart
   EOT
    
   def self.set_archive(date)
+    if defined? Rbbt and Rbbt.etc.allowed_biomart_archives.exists?
+      raise "Biomart archive #{ date } is not allowed in this installation" unless Rbbt.etc.allowed_biomart_archives.read.split("\n").include? date
+    end
     @archive = date
     @archive_url = BIOMART_URL.sub(/http:\/\/biomart\./, 'http://' + date + '.archive.ensembl.')
     Log.debug "Using Archive URL #{ @archive_url }"

data/lib/rbbt/sources/jochem.rb

@@ -1,4 +1,7 @@
 require 'rbbt-util'
 module JoChem
-  Rbbt.claim Rbbt.share.databases.JoChem, :rake, Rbbt.share.install.JoChem.Rakefile.find 
+  extend Resource
+  self.subdir = "share/databases/JoChem"
+
+  JoChem.claim JoChem.root, :rake, Rbbt.share.install.JoChem.Rakefile.find 
 end

data/share/install/Organism/Hsa/Rakefile

@@ -25,6 +25,30 @@ $biomart_protein_identifiers = [
   [ 'UniProt/SwissProt Accession', "uniprot_swissprot_accession"  ],
 ]
 
+$biomart_probe_identifiers = [
+  [ 'AFFY HC G110', 'affy_hc_g110' ],
+  [ 'AFFY HG FOCUS', 'affy_hg_focus' ],
+  [ 'AFFY HG U133-PLUS-2', 'affy_hg_u133_plus_2' ],
+  [ 'AFFY HG U133A_2', 'affy_hg_u133a_2' ],
+  [ 'AFFY HG U133A', 'affy_hg_u133a' ],
+  [ 'AFFY HG U133B', 'affy_hg_u133b' ],
+  [ 'AFFY HG U95AV2', 'affy_hg_u95av2' ],
+  [ 'AFFY HG U95B', 'affy_hg_u95b' ],
+  [ 'AFFY HG U95C', 'affy_hg_u95c' ],
+  [ 'AFFY HG U95D', 'affy_hg_u95d' ],
+  [ 'AFFY HG U95E', 'affy_hg_u95e' ],
+  [ 'AFFY HG U95A', 'affy_hg_u95a' ],
+  [ 'AFFY HUGENEFL', 'affy_hugenefl' ],
+  [ 'AFFY HuEx', 'affy_huex_1_0_st_v2', "HuEx" ],
+  [ 'AFFY HuGene', 'affy_hugene_1_0_st_v1' ],
+  [ 'AFFY U133 X3P', 'affy_u133_x3p' ],
+  [ 'Agilent WholeGenome',"agilent_wholegenome" ],
+  [ 'Agilent CGH 44b', 'agilent_cgh_44b' ],
+  [ 'Codelink ID', 'codelink' ],
+  [ 'Illumina HumanWG 6 v2', 'illumina_humanwg_6_v2' ],
+  [ 'Illumina HumanWG 6 v3', 'illumina_humanwg_6_v3' ],
+]
+
 $biomart_identifiers = [ 
   [ 'Entrez Gene ID', "entrezgene"],
   [ 'Ensembl Protein ID', "ensembl_peptide_id"  ],
@@ -38,7 +62,7 @@ $biomart_identifiers = [
   [ 'HGNC ID', "hgnc_id", 'HGNC'],
   [ 'EMBL (Genbank) ID' , "embl"] , 
 
-  # Affymetrix
+  # Probes
   [ 'AFFY HC G110', 'affy_hc_g110' ],
   [ 'AFFY HG FOCUS', 'affy_hg_focus' ],
   [ 'AFFY HG U133-PLUS-2', 'affy_hg_u133_plus_2' ],

data/share/install/Organism/organism_helpers.rb

@@ -68,6 +68,7 @@ file 'identifiers' do |t|
   identifiers = BioMart.tsv($biomart_db, $biomart_ensembl_gene, $biomart_identifiers, [], nil, :namespace => $namespace)
 
   $biomart_identifiers.each do |name, key, prefix|
+    next unless identifiers.all_fields.include? name
     if prefix
       identifiers.process name do |field, key, values| field.each{|v| v.replace "#{prefix}:#{v}"} end
     end
@@ -128,6 +129,16 @@ file 'protein_identifiers' do |t|
   File.open(t.name, 'w') do |f| f.puts identifiers end
 end
 
+file 'probe_transcripts' do |t|
+  identifiers = BioMart.tsv($biomart_db, $biomart_ensembl_transcript, $biomart_probe_identifiers, [], nil, :namespace => $namespace)
+  $biomart_probe_identifiers.each do |name, key, prefix|
+    if prefix
+      identifiers.process name do |field, key, values| field.each{|v| v.replace "#{prefix}:#{v}"} end
+    end
+  end
+
+  File.open(t.name, 'w') do |f| f.puts identifiers end
+end
 
 file 'gene_transcripts' do |t|
   transcripts = BioMart.tsv($biomart_db, $biomart_ensembl_gene, $biomart_gene_transcript, [], nil, :type => :flat, :namespace => $namespace)
@@ -343,6 +354,22 @@ file 'gene_go' do |t|
   File.open(t.name, 'w') do |f| f.puts goterms end
 end
 
+file 'gene_go_bp' => 'gene_go' do |t|
+  gene_go = TSV.open(t.prerequisites.first)
+   
+  gene_go.monitor = true
+  gene_go.process "GO ID" do |key, go_id, values|
+    clean = values.zip_fields.select do |id, type|
+      type == "biological_process"
+    end
+    clean.collect{|id, type| id}
+  end
+
+
+  File.open(t.name, 'w') do |f| f.puts gene_go.slice "GO ID" end
+end
+
+
 
 file 'gene_pfam' do |t|
   goterms = BioMart.tsv($biomart_db, $biomart_ensembl_gene, $biomart_pfam, [], nil, :type => :double, :namespace => $namespace)

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: rbbt-sources
 version: !ruby/object:Gem::Version 
-  hash: 23
-  prerelease: false
+  hash: 21
+  prerelease: 
   segments: 
   - 1
   - 0
-  - 0
-  version: 1.0.0
+  - 1
+  version: 1.0.1
 platform: ruby
 authors: 
 - Miguel Vazquez
@@ -15,7 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2011-09-07 00:00:00 +02:00
+date: 2011-10-03 00:00:00 +02:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -160,7 +160,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
 requirements: []
 
 rubyforge_project: 
-rubygems_version: 1.3.7
+rubygems_version: 1.6.2
 signing_key: 
 specification_version: 3
 summary: Data sources for the Ruby Bioinformatics Toolkit (rbbt)