rbbt-sources 0.2.2 → 0.3.1

data/lib/rbbt/sources/polysearch.rb

@@ -1,10 +1,10 @@
 require 'rbbt'
 
 module Polysearch
-  Rbbt.claim "organ" ,'http://wishart.biology.ualberta.ca/polysearch/include/organ_ID.txt', 'Polysearch'
-  Rbbt.claim "tissue" ,'http://wishart.biology.ualberta.ca/polysearch/include/tissue_ID.txt', 'Polysearch'
-  Rbbt.claim "location" ,'http://wishart.biology.ualberta.ca/polysearch/include/subcellular_localization_ID.txt', 'Polysearch'
-  Rbbt.claim "disease" ,'http://wishart.biology.ualberta.ca/polysearch/include/disease_IDlist.txt', 'Polysearch'
-  Rbbt.claim "drug" ,'http://wishart.biology.ualberta.ca/polysearch/include/drugnames.txt', 'Polysearch'
+  Rbbt.share.Polysearch.organ.define_as_url 'http://wishart.biology.ualberta.ca/polysearch/include/organ_ID.txt'
+  Rbbt.share.Polysearch.tissue.define_as_url 'http://wishart.biology.ualberta.ca/polysearch/include/tissue_ID.txt'
+  Rbbt.share.Polysearch.location.define_as_url 'http://wishart.biology.ualberta.ca/polysearch/include/subcellular_localization_ID.txt'
+  Rbbt.share.Polysearch.disease.define_as_url 'http://wishart.biology.ualberta.ca/polysearch/include/disease_IDlist.txt'
+  Rbbt.share.Polysearch.drug.define_as_url 'http://wishart.biology.ualberta.ca/polysearch/include/drugnames.txt'
 end
   

data/share/install/Organism/Hsa/Rakefile

@@ -3,11 +3,11 @@ require 'rbbt/sources/biomart'
 require 'rbbt/sources/entrez'
 require File.join(File.dirname(__FILE__), '../../lib/helpers')
 
-$taxs = [559292,4932]
-$native = "SGD ID"
-$url = "ftp://genome-ftp.stanford.edu/pub/yeast/data_download/chromosomal_feature/SGD_features.tab"
+$taxs = [9606]
+$scientific_name = "Homo sapiens"
+
 $biomart_db = 'hsapiens_gene_ensembl'
-$biomart_main = ['Entrez Gene ID', 'entrezgene']
+
 $biomart_lexicon = [ 
   [ 'Associated Gene Name' , "external_gene_id"], 
   [ 'HGNC symbol', "hgnc_symbol"  ],
@@ -16,7 +16,7 @@ $biomart_lexicon = [
 ]
 
 $biomart_identifiers = [ 
-  [ 'Ensembl Gene ID', "ensembl_gene_id"  ],
+  [ 'Entrez Gene ID', "entrezgene"],
   [ 'Ensembl Protein ID', "ensembl_peptide_id"  ],
   [ 'Associated Gene Name', "external_gene_id"  ],
   [ 'CCDS ID', "ccds"  ],
@@ -52,66 +52,5 @@ $biomart_identifiers = [
   [ 'Illumina HumanWG 6 v3', 'illumina_humanwg_6_v3' ],
 ]
 
-$biomart_positions = [
-  ['Chromosome Name','chromosome_name'],
-  ['Strand','strand'],
-  ['Gene Start','start_position'],
-  ['Gene End','end_position'],
-  ['Transcript Start','transcript_start'],
-  ['Transcript End','transcript_end'],
-]
-
-
-
-file 'scientific_name' do |t|
-  File.open(t.name, 'w') do |f| f.puts "Homo sapiens" end
-end
-
-file 'lexicon' do |t|
-  lexicon = tsv_file('http://www.genenames.org/cgi-bin/hgnc_downloads.cgi?title=HGNC+output+data&hgnc_dbtag=on&col=gd_hgnc_id&col=gd_app_sym&col=gd_app_name&col=gd_prev_sym&col=gd_prev_name&col=gd_aliases&col=gd_name_aliases&col=gd_pub_acc_ids&status=Approved&status_opt=2&level=pri&=on&where=&order_by=gd_app_sym_sort&limit=&format=text&submit=submit&.cgifields=&.cgifields=level&.cgifields=chr&.cgifields=status&.cgifields=hgnc_dbtag',
-                     "HGNC ID", nil, :flatten => true, :header_hash => '')
-  merge_biomart lexicon, $biomart_db, $biomart_main, $biomart_lexicon, "HGNC ID"
-
-  File.open(t.name, 'w') do |f| f.puts lexicon end
-end
-
-file 'identifiers' do |t|
-  identifiers = BioMart.tsv($biomart_db, $biomart_main, $biomart_identifiers)
-  $biomart_identifiers.each do |name, key, prefix|
-    if prefix
-      identifiers.process name do |field, key, values| field.each{|v| v.replace "#{prefix}:#{v}"} end
-    end
-  end
-
-  File.open(t.name, 'w') do |f| f.puts identifiers end
-end
-
-file 'gene_go' do |t|
-  url = "http://cvsweb.geneontology.org/cgi-bin/cvsweb.cgi/go/gene-associations/gene_association.goa_human.gz?rev=HEAD"
-  tsv = TSV.new(Open.open(url, :gzip => true), :native => 2, :extra => 4)
-
-  index = TSV.index(Organism::Hsa.identifiers, :persistence => true)
-  new = TSV.new({})
-  tsv.through do |key, values|
-    next if index[key].nil?
-    new_key = index[key].first
-    new[new_key] = values
-  end
-
-  
-  new.key_field = "Associated Gene Name"
-  new.fields = ["GO Term"]
-  Open.write(t.name, new.to_s)
-end
-
-file 'gene_positions' do |t|
-  BioMart.set_archive('may2009')
-  positions = BioMart.tsv($biomart_db, $biomart_main, $biomart_positions)
-  BioMart.unset_archive
-
-  Open.write(t.name, positions.to_s)
-end
-
-task :default => ['name', 'lexicon', 'identifiers', 'gene_positions']
-
-
+$namespace = File.basename(File.dirname(File.expand_path(__FILE__)))
+load File.join(File.dirname(__FILE__), '../organism_helpers.rb')

data/share/install/Organism/Sce/Rakefile

@@ -17,9 +17,9 @@ end
 file 'lexicon' do |t|
   lexicon = tsv_file($url, [$native, 0], [3, 4, 5], :keep_empty => true)
 
-  merge_entrez(lexicon, $taxs, $native, proc{|code| code.sub(/SGD:S0/,'S0') }, proc{|code| code.match(/\tS0/)})
+  lexicon = merge_entrez(lexicon, $taxs, $native, proc{|code| code.sub(/SGD:S0/,'S0') }, proc{|code| code.match(/\tSGD:S0/)})
 
-  merge_biomart(lexicon, $biomart_db, $biomart_main, [['Interpro Description' , "interpro_description"]])
+  lexicon = merge_biomart(lexicon, $biomart_db, $biomart_main, [['Interpro Description' , "interpro_description"]])
 
   lexicon = lexicon.slice(lexicon.fields - ["Entrez Gene ID"])
 
@@ -29,9 +29,9 @@ end
 file 'identifiers' do |t|
   identifiers = tsv_file($url, [$native, 0], [["Ensembl Gene ID", 3], ["Associated Gene Name",4], ["Associated Gene Name Alias", 5]], :keep_empty => true)
 
-  merge_entrez(identifiers, $taxs, $native, proc{|code| code.sub(/SGD:S0/,'S0') }, proc{|code| code.match(/\tS0/)})
+  identifiers = merge_entrez(identifiers, $taxs, $native, proc{|code| code.sub(/SGD:S0/,'S0') }, proc{|code| code.match(/\tSGD:S0/)})
 
-  merge_biomart(identifiers, $biomart_db, $biomart_main,
+  identifiers = merge_biomart(identifiers, $biomart_db, $biomart_main,
                 [['Associated Gene Name' , "external_gene_id"], 
                   ['Ensembl Gene ID', "ensembl_gene_id"  ],
                   ['Ensembl Protein ID', "ensembl_peptide_id"  ],
@@ -50,69 +50,3 @@ end
 
 task :default => ['name', 'lexicon', 'identifiers']
 
-#require __FILE__.sub(/[^\/]*$/,'') + '../rake-include'
-#
-#$name = "Saccharomyces cerevisiae"
-#
-#
-#$native_id = "SGD DB Id"
-#
-#$entrez2native = {
-#  :tax => 559292,
-#  :fix => proc{|code| code.sub(/SGD:S0/,'S0') },
-#  :check => proc{|code| code.match(/^S0/)},
-#}
-#
-#$lexicon = {
-#  :file => {
-#    :url => "ftp://genome-ftp.stanford.edu/pub/yeast/data_download/chromosomal_feature/SGD_features.tab",
-#    :native => 0,
-#    :extra => [4,3,5]
-#  },
-#  :biomart => {
-#    :database => 'scerevisiae_gene_ensembl',
-#    :main => ['Entrez Gene ID', 'entrezgene'],
-#    :extra => [ 
-#      ['Interpro Description' , "interpro_description"], 
-#    ],
-#    :filter => [],
-#  }
-#
-#}
-#
-#$identifiers = {
-#  :file => {
-#    :url => "ftp://genome-ftp.stanford.edu/pub/yeast/data_download/chromosomal_feature/SGD_features.tab",
-#    :native => 0,
-#    :extra => [],
-#  },
-#  :biomart => {
-#    :database => 'scerevisiae_gene_ensembl',
-#    :main => ['Entrez Gene ID', 'entrezgene'],
-#    :extra => [ 
-#      ['Associated Gene Name' , "external_gene_id"], 
-#      ['Ensembl Gene ID', "ensembl_gene_id"  ],
-#      ['Ensembl Protein ID', "ensembl_peptide_id"  ],
-#      ['RefSeq Protein ID' , "refseq_peptide"] , 
-#      ['UniProt/SwissProt ID' , "uniprot_swissprot"] , 
-#      ['UniProt/SwissProt Accession' , "uniprot_swissprot_accession"] , 
-#      ['Protein ID' , "protein_id"] , 
-#      ['EMBL (Genbank) ID' , "embl"] , 
-#      # Affymetrix
-#      ['Affy yeast 2',"affy_yeast_2"],
-#      ['Affy yg s98', "affy_yg_s98"],
-#    ],
-#    :filter => [],
-#  }
-#}
-#
-#$go = {
-#  :url => "ftp://genome-ftp.stanford.edu/pub/yeast/data_download/literature_curation/gene_association.sgd.gz",
-#  :code => 1,
-#  :go   => 4,
-#  :pmid => 5,
-#}
-#
-#$query = '"saccharomyces cerevisiae"[All Fields] AND ((("proteins"[TIAB] NOT Medline[SB]) OR "proteins"[MeSH Terms] OR protein[Text Word]) OR (("genes"[TIAB] NOT Medline[SB]) OR "genes"[MeSH Terms] OR gene[Text Word]))  AND hasabstract[text] AND English[lang]'
-#
-#

data/share/install/Organism/organism_helpers.rb

@@ -0,0 +1,305 @@
+$biomart_ensembl_gene = ['Ensembl Gene ID', 'ensembl_gene_id']
+$biomart_ensembl_protein = ['Ensembl Protein ID', 'ensembl_peptide_id']
+$biomart_ensembl_exon = ['Ensembl Exon ID', 'ensembl_exon_id']
+$biomart_ensembl_transcript = ['Ensembl Transcript ID', 'ensembl_transcript_id']
+$biomart_somatic_variation_id = ['Variation ID', "somatic_reference_id" ]
+$biomart_germline_variation_id = ['Variation ID', "external_id" ]
+
+$biomart_gene_positions = [
+  ['Chromosome Name','chromosome_name'],
+  ['Strand','strand'],
+  ['Gene Start','start_position'],
+  ['Gene End','end_position'],
+]
+
+$biomart_gene_sequence = [
+  ['Gene Sequence','gene_exon_intron'],
+]
+
+#{{{ Transcript
+
+$biomart_gene_transcript = [
+  $biomart_ensembl_transcript
+]
+
+$biomart_transcript = [
+  ['Transcript Start (bp)','transcript_start'],
+  ['Transcript End (bp)','transcript_end'],
+  $biomart_ensembl_protein,
+  $biomart_ensembl_gene
+]
+
+$biomart_transcript_sequence = [
+  ['cDNA','cdna'],
+]
+
+$biomart_transcript_3utr = [
+  ["3' UTR", '3utr'],
+]
+
+$biomart_transcript_5utr = [
+  ["5' UTR", '5utr'],
+]
+
+
+$biomart_protein_sequence = [
+  ['Protein Sequence','peptide'],
+]
+
+#{{{ Exons
+
+$biomart_transcript_exons = [
+  $biomart_ensembl_exon,
+  ['Exon Rank in Transcript','rank'],
+]
+
+$biomart_exons = [
+  $biomart_ensembl_gene,
+  ['Exon Strand','strand'],
+  ['Exon Chr Start','exon_chrom_start'],
+  ['Exon Chr End','exon_chrom_end'],
+]
+
+#{{{ Variations
+
+$biomart_germline_variation_positions = [
+  ['Chromosome Location (bp)', "chromosome_location" ],
+  ['SNP Chromosome Strand', "snp_chromosome_strand" ],
+  ['Transcript location (bp)', "transcript_location" ],
+  ['Allele', "allele" ],
+  ['Protein Allele', "peptide_shift" ],
+  ['CDS Start', "cds_start_2076" ],
+  ['CDS End', "cds_end_2076" ],
+]
+
+$biomart_germline_variations = [
+    $biomart_ensembl_gene,
+    ['Source', "source_name" ],
+    ['Validated', "validated" ],
+    ['Consequence Type', "synonymous_status" ],
+]
+
+$biomart_somatic_variation_positions = [
+    ['Chromosome Location (bp)' , "somatic_chromosome_location" ] ,
+    ['SNP Chromosome Strand' , "somatic_snp_chromosome_strand" ] ,
+    ['Transcript location (bp)' , "somatic_transcript_location" ] ,
+    ['Allele' , "somatic_allele" ] ,
+    ['Protein Allele' , "somatic_peptide_shift" ] , 
+    ['CDS Start' , "somatic_cds_start_2076" ] ,
+    ['CDS End' , "somatic_cds_end_2076" ] , 
+]
+
+$biomart_somatic_variations = [
+    $biomart_ensembl_gene,
+    ['Source' , "somatic_source_name" ] ,
+    ['Validated' , "somatic_validated" ] ,
+    ['Consequence Type' , "somatic_synonymous_status" ] , 
+]
+
+#{{{ Rules
+
+file 'scientific_name' do |t|
+  File.open(t.name, 'w') do |f| f.write $scientific_name end
+end
+
+file 'identifiers' do |t|
+  identifiers = BioMart.tsv($biomart_db, $biomart_ensembl_gene, $biomart_identifiers, [])
+  $biomart_identifiers.each do |name, key, prefix|
+    if prefix
+      identifiers.process name do |field, key, values| field.each{|v| v.replace "#{prefix}:#{v}"} end
+    end
+  end
+
+  File.open(t.name, 'w') do |f| f.puts identifiers end
+end
+
+file 'gene_transcripts' do |t|
+  transcripts = BioMart.tsv($biomart_db, $biomart_ensembl_gene, $biomart_gene_transcript, [], nil, :type => :flat)
+
+  File.open(t.name, 'w') do |f| f.puts transcripts end
+end
+
+file 'transcripts' => 'gene_positions' do |t|
+  transcripts = BioMart.tsv($biomart_db, $biomart_ensembl_transcript, $biomart_transcript, [], nil, :type => :list)
+  transcripts.attach TSV.new('gene_positions'), "Chromosome Name"
+
+  File.open(t.name, 'w') do |f| f.puts transcripts end
+end
+
+file 'transcript_3utr' do |t|
+  utrs = BioMart.tsv($biomart_db, $biomart_ensembl_transcript, $biomart_transcript_3utr, [], nil, :type => :flat, :merge => true)
+
+  File.open(t.name, 'w') do |f| 
+    f.puts "#: :type=:single#cast=to_i"
+    f.puts "#Ensembl Transcript ID\t3' UTR Length"
+    utrs.each do |seq,trans|
+      trans.each do |tran|
+        f.puts [tran, seq.length] * "\t"
+      end
+    end
+  end
+end
+
+
+file 'transcript_5utr' do |t|
+  utrs = BioMart.tsv($biomart_db, $biomart_ensembl_transcript, $biomart_transcript_5utr, [], nil, :type => :flat, :merge => true)
+
+  File.open(t.name, 'w') do |f| 
+    f.puts "#: :type=:single#cast=to_i"
+    f.puts "#Ensembl Transcript ID\t5' UTR Length"
+    utrs.each do |seq,trans|
+      trans.each do |tran|
+        f.puts [tran, seq.length] * "\t"
+      end
+    end
+  end
+end
+
+file 'gene_positions' do |t|
+  sequences = BioMart.tsv($biomart_db, $biomart_ensembl_gene, $biomart_gene_positions, [])
+
+  File.open(t.name, 'w') do |f| f.puts sequences end
+end
+
+file 'gene_sequence' do |t|
+  sequences = BioMart.tsv($biomart_db, $biomart_ensembl_gene, $biomart_gene_sequence, [], nil, :type => :flat, :merge => true)
+
+  File.open(t.name, 'w') do |f| 
+    f.puts "#: :type=:single"
+    f.puts "#Ensembl Gene ID\tProtein Sequence"
+    sequences.each do |seq, genes|
+      genes.each do |gene|
+        f.write gene 
+        f.write "\t" 
+        f.write seq
+        f.write "\n"
+      end
+    end
+  end
+end
+
+file 'protein_sequence' do |t|
+  sequences = BioMart.tsv($biomart_db, $biomart_ensembl_protein, $biomart_protein_sequence, [], nil, :type => :flat, :merge => true)
+
+  File.open(t.name, 'w') do |f| 
+    f.puts "#: :type=:single"
+    f.puts "#Ensembl Protein ID\tProtein Sequence"
+    sequences.each do |seq, genes|
+      genes.each do |gene|
+        f.write gene 
+        f.write "\t" 
+        f.write seq
+        f.write "\n"
+      end
+    end
+  end
+
+end
+
+file 'exons' => 'gene_positions' do |t|
+  exons = BioMart.tsv($biomart_db, $biomart_ensembl_exon, $biomart_exons, [], nil, :merge => false, :type => :list)
+  exons.attach TSV.new('gene_positions'), "Chromosome Name"
+
+  File.open(t.name, 'w') do |f| f.puts exons end
+end
+
+file 'transcript_exons' do |t|
+  exons = BioMart.tsv($biomart_db, $biomart_ensembl_transcript, $biomart_transcript_exons, [], nil, :keep_empty => true)
+
+  File.open(t.name, 'w') do |f| f.puts exons end
+end
+
+file 'transcript_sequence' do |t|
+  sequences = BioMart.tsv($biomart_db, $biomart_ensembl_transcript, $biomart_transcript_sequence, [], nil, :type => :flat, :merge => true)
+
+  File.open(t.name, 'w') do |f| 
+    f.puts "#: :type=:single"
+    f.puts "#Ensembl Transcript ID\tProtein Sequence"
+    sequences.each do |seq, genes|
+      genes.each do |gene|
+        f.write gene 
+        f.write "\t" 
+        f.write seq
+        f.write "\n"
+      end
+    end
+  end
+end
+
+
+$biomart_variation_filter = ["snptype_filters", "COMPLEX_INDEL,COMPLEX_INDEL&NMD_TRANSCRIPT,COMPLEX_INDEL&SPLICE_SITE,ESSENTIAL_SPLICE_SITE&INTRONIC,ESSENTIAL_SPLICE_SITE&INTRONIC&NMD_TRANSCRIPT,FRAMESHIFT_CODING,FRAMESHIFT_CODING&NMD_TRANSCRIPT,FRAMESHIFT_CODING&SPLICE_SITE,FRAMESHIFT_CODING&SPLICE_SITE&NMD_TRANSCRIPT,NON_SYNONYMOUS_CODING,NON_SYNONYMOUS_CODING&NMD_TRANSCRIPT,NON_SYNONYMOUS_CODING&SPLICE_SITE,NON_SYNONYMOUS_CODING&SPLICE_SITE&NMD_TRANSCRIPT,REGULATORY_REGION,SPLICE_SITE&3PRIME_UTR,SPLICE_SITE&3PRIME_UTR&NMD_TRANSCRIPT,SPLICE_SITE&5PRIME_UTR,SPLICE_SITE&5PRIME_UTR&NMD_TRANSCRIPT,SPLICE_SITE&INTRONIC,SPLICE_SITE&INTRONIC&NMD_TRANSCRIPT,SPLICE_SITE&SYNONYMOUS_CODING,SPLICE_SITE&SYNONYMOUS_CODING&NMD_TRANSCRIPT,STOP_GAINED,STOP_GAINED&FRAMESHIFT_CODING,STOP_GAINED&FRAMESHIFT_CODING&NMD_TRANSCRIPT,STOP_GAINED&NMD_TRANSCRIPT,STOP_GAINED&SPLICE_SITE,STOP_GAINED&SPLICE_SITE&NMD_TRANSCRIPT,STOP_LOST,STOP_LOST&NMD_TRANSCRIPT,STOP_LOST&SPLICE_SITE,STOP_LOST&SPLICE_SITE&NMD_TRANSCRIPT,SYNONYMOUS_CODING,SYNONYMOUS_CODING&NMD_TRANSCRIPT"]
+#$biomart_variation_filter = ["snptype_filters", "COMPLEX_INDEL,SYNONYMOUS_CODING"]
+$biomart_variation_filter = ["snptype_filters", 'COMPLEX_INDEL&NMD_TRANSCRIPT']
+
+file 'germline_variations' do |t|
+  variations = BioMart.tsv($biomart_db, $biomart_germline_variation_id, $biomart_germline_variations, [], nil, :keep_empty => true, :type => :list, :merge => false)
+  File.open(t.name, 'w') do |f| f.puts variations.to_s end
+end
+
+file 'germline_variation_positions' do |t|
+  variations = BioMart.tsv($biomart_db, $biomart_germline_variation_id, $biomart_germline_variation_positions, [], nil, :keep_empty => true, :type => :list, :merge => false)
+  File.open(t.name, 'w') do |f| f.puts variations.to_s end
+end
+
+file 'somatic_variations' do |t|
+  variations = BioMart.tsv($biomart_db, $biomart_somatic_variation_id, $biomart_somatic_variations, [], nil, :keep_empty => true, :type => :list, :merge => false)
+  File.open(t.name, 'w') do |f| f.puts variations.to_s end
+end
+
+file 'somatic_variation_positions' do |t|
+  variations = BioMart.tsv($biomart_db, $biomart_somatic_variation_id, $biomart_somatic_variation_positions, [], nil, :keep_empty => true, :type => :list, :merge => false)
+  File.open(t.name, 'w') do |f| f.puts variations.to_s end
+end
+
+file 'gene_pmids' do |t|
+  tsv =  Entrez.entrez2pubmed($taxs)
+  text = "#Entrez Gene ID\tPMID"
+  tsv.each do |gene, pmids|
+    text << "\n" << gene << "\t" << pmids * "|"
+  end
+  Open.write(t.name, text)
+end
+
+file 'exon_offsets' => %w(exons transcript_exons gene_transcripts transcripts transcript_exons) do |t|
+  require 'rbbt/sources/organism/sequence'
+
+  exons = TSV.new('exons', :persistence => true)
+  exon_transcripts = TSV.new('transcript_exons', :double, :key => "Ensembl Exon ID", :fields => ["Ensembl Transcript ID"], :merge => true, :persistence => true )
+  gene_transcripts = TSV.new('gene_transcripts', :flat, :persistence => true )
+  transcript_info = TSV.new('transcripts', :list, :persistence => true )
+  transcript_exons = TSV.new('transcript_exons', :double, :fields => ["Ensembl Exon ID","Exon Rank in Transcript"], :persistence => true )
+
+
+  string = "#Ensembl Exon ID\tEnsembl Transcript ID\tOffset\n"
+  exons.each do |exon, info|
+    gene, start, finish, strand, chr = info
+
+    transcripts = Organism::Hsa.coding_transcripts_for_exon(exon, exon_transcripts, transcript_info)
+
+    transcript_offsets = {}
+    transcripts.each do |transcript|
+      offset = Organism::Hsa.exon_offset_in_transcript(exon, transcript, exons, transcript_exons)
+      transcript_offsets[transcript] = offset unless offset.nil?
+    end
+    
+    string << exon << "\t" << transcript_offsets.keys * "|" << "\t" << transcript_offsets.values * "|" << "\n"
+  end
+
+  Open.write(t.name, string)
+end
+
+rule /[a-z]{3}[0-9]{4}\/.*/i do |t|
+  t.name =~ /([a-z]{3}[0-9]{4})\/(.*)/i
+  archive = $1
+  task    = $2
+  old_pwd = FileUtils.pwd
+  begin
+    FileUtils.mkdir archive unless File.exists? archive
+    FileUtils.cd File.join(archive)
+    BioMart.set_archive archive
+    Rake::Task[task].invoke
+    BioMart.unset_archive 
+  ensure
+    FileUtils.cd old_pwd
+  end
+end