$LOAD_PATH.unshift(File.join(File.dirname(__FILE__),'..', '..', '..', '..', 'lib'))
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"
$biomart_db = 'scerevisiae_gene_ensembl'
$biomart_main = ['Entrez Gene ID', 'entrezgene']


file 'name' do |t|
  File.open(t.name, 'w') do |f| f.puts "Saccharomyces cerevisiae" end
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/)})

  merge_biomart(lexicon, $biomart_db, $biomart_main, [['Interpro Description' , "interpro_description"]])

  lexicon = lexicon.slice(lexicon.fields - ["Entrez Gene ID"])

  File.open(t.name, 'w') do |f| f.puts lexicon end
end

file 'identifiers' do |t|
  identifiers = tsv_file($url, [$native, 0], [3, 4, 5], :keep_empty => true)

  merge_entrez(identifiers, $taxs, $native, proc{|code| code.sub(/SGD:S0/,'S0') }, proc{|code| code.match(/\tS0/)})

  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"  ],
                  ['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"]])

  File.open(t.name, 'w') do |f| f.puts identifiers end
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]'
#
#