genome_reports2ttl_v2.rb

genome_reports2ttl.rb

#!/usr/bin/env ruby
#
# convert genome_reprots to RDF
# * ftp://ftp.ncbi.nlm.nih.gov/genomes/GENOME_REPORTS/prokaryotes.txt
# * ftp://ftp.ncbi.nlm.nih.gov/genomes/GENOME_REPORTS/eukaryotes.txt
#

require 'date'


def quote(str)
    return str.to_s.gsub('\\', '\\\\').gsub("\t", '\\t').gsub("\n", '\\n').gsub("\r", '\\r').gsub('"', '\\"').inspect
end

def resource_date(str)
    return quote(str)
    #str = '0001/01/01' if str == '-'
    #return quote(Date.parse(str).strftime("%Y-%m-%d")) +"^^xsd:date"
end

def output_prefix
    puts "@prefix obo: <http://purl.obolibrary.org/obo/> ."
    puts
    puts
end

def status2so str
    case str
    when "Contig"
        "obo:SO_0000149"
    when "Gapless Chromosome"
        "obo:SO_0000340"
    when "Complete"
        "obo:SO_0000148"
    when "Scaffold"
        "obo:SO_0000148"
    when "Chromosome"
        "obo:SO_0000340"
    when "Chromosome with gaps"
        "obo:SO_0000340"
    else
        warn "undefied status: #{k}"
        raise error
    end
end

def output_pv k,v
     case k
     when 'Organism/Name'
        puts "\t:organism_name\t#{quote(v)} ;" 
     when 'TaxID'
        puts "\t:tax_id\t#{quote(v)} ;" 
        puts "\t:taxon\t<http://identifiers.org/taxonomy/#{v}> ;" if v !='-'
     when 'BioProject Accession'
        puts "\t:bioproject_accession\t#{quote(v)} ;" 
        puts "\t:bioproject\t<http://identifiers.org/bioproject/#{v}> ;" 
     when 'BioProject ID'
        puts "\t:bioproject_id\t#{quote(v)} ;" 
     when 'Group'
        puts "\t:group\t#{quote(v)} ;" 
     when 'SubGroup'
        puts "\t:subgroup\t#{quote(v)} ;" 
     when 'Size (Mb)'
        puts "\t:size\t#{quote(v)} ;" 
     when 'GC%'
        puts "\t:gc\t#{quote(v)} ;" 
     when 'Assembly Accession'
        puts "\t:assembly_accession\t#{quote(v)} ;" 
     when 'Chromosomes'
        puts "\t:chromosomes\t#{quote(v)} ;" 
     when 'Organelles'
        puts "\t:organelles\t#{quote(v)} ;" 
     when 'Plasmids'
        puts "\t:plasmids\t#{quote(v)} ;" 
     when 'WGS'
        puts "\t:wgs\t#{quote(v)} ;" 
     when 'Scaffolds'
        puts "\t:scaffolds\t#{quote(v)} ;" 
     when 'Genes'
        puts "\t:genes\t#{quote(v)} ;" 
     when 'Proteins'
        puts "\t:proteins\t#{quote(v)} ;" 
     when 'Release Date'
        puts "\t:release_date\t#{resource_date(v)} ;"
     when 'Modify Date'
        puts "\t:modify_date\t#{resource_date(v)} ;"
     when 'Status'
        puts "\t:status\t#{quote(v)} ;" 
        puts "\t:status2so\t#{status2so(v)} ;"
     when 'Center'
        puts "\t:center\t#{quote(v)} ;" 
     when 'BioSample Accession'
        puts "\t:biosample_accession\t#{quote(v)} ;" 
        puts "\t:biosample\t<http://identifiers.org/biosample/#{v}> ;" if v != '-' 
     when 'Chromosomes/RefSeq'
        puts "\t:chromosomes_refseq\t#{quote(v)} ; #only prokaryotes" 
        v.split(",").each { |vv| puts "\t:chromosome\t<http://identifiers.org/refseq/#{vv}> ;"} if v != '-'
     when 'Chromosomes/INSDC'
        puts "\t:chromosomes_insdc\t#{quote(v)} ; #only prokaryotes" 
     when 'Plasmids/RefSeq'
        puts "\t:plasmids_refseq\t#{quote(v)} ; #only prokaryotes" 
        v.split(",").each { |vv| puts "\t:plasmid\t<http://identifiers.org/refseq/#{vv}> ;"} if v != '-'
     when 'Plasmids/INSDC'
        puts "\t:plasmids_insdc\t#{quote(v)} ; #only prokaryotes" 
     when 'Reference'
        puts "\t:reference\t#{quote(v)}; #only prokaryotes" 
     when 'FTP Path'
        puts "\t:ftp_path\t#{quote(v)}; #only prokaryotes" 
     when 'Pubmed ID
        puts "\t:pubmed_id\t#{quote(v)} ; #only prokaryotes" 
     else
         puts "     when '#{k}'"
         warn "undefied key: #{k}"
         raise error
     end
end
         
ary =[]
%w(GENOME_REPORTS/prokaryotes.txt GENOME_REPORTS/eukaryotes.txt).each do |input_file|
    head = []
    File.readlines(input_file).each_with_index do |line,i|
        if i == 0
           head =line.strip.gsub("\r","").gsub(/^#/,"").split("\t")
        else
           ary << head.zip(line.strip.split("\t")).inject({}){|h,col| h[col[0]]=col[1];h}
        end 
    end 
end

# {"Contig"=>12234, "Gapless Chromosome"=>2935, "Complete"=>25, "Scaffold"=>11279, "Chromosome"=>533, "Chromosome with gaps"=>339}

output_prefix

status = Hash.new{|h,k|h[k]=0}
ary.each do |project|
     acc = project["BioProject Accession"]
     puts "<http://identifiers.org/bioproject/#{acc}>"
     project.each do |k,v|
         output_pv(k,v)
     end
     puts "."
     status[project["Status"]] += 1
end

warn status





# TSV format errors in prokaryotes.txt
#< #Organism/Name  TaxID BioProject Accession  BioProject ID Group SubGroup  Size (Mb) GC% Chromosomes/RefSeq  Chromosomes/INSDC Plasmids/RefSeq Plasmids/INSDC  WGS Scaffolds Genes Proteins  Release Date  Modify Date Status  Center  BioSample Accession Assembly Accession  Reference FTP Path  Pubmed ID
#> #Organism/Name  TaxID BioProject Accession  BioProject ID Group SubGroup  Size (Mb) GC% Chromosomes/RefSeq  Chromosomes/INSDC Plasmids/RefSeq Plasmids/INSDC  WGS Scaffolds Genes Proteins  Release Date  Modify Date Status  Center  BioSample Accession Assembly Accession  Reference FTP Path  Pubmed ID
#< "The Federal Goverment Health Institution ""Stavropol Plague Control Reseach Institute"" of the Federal Service for Supervision in the Sphere of Consumer Rights Protection and Human Welfare"
#> The Federal Goverment Health Institution "Stavropol Plague Control Reseach Institute" of the Federal Service for Supervision in the Sphere of Consumer Rights Protection and Human Welfare
#< """National Center for Biotechnology"" RSE"
#> "National Center for Biotechnology" RSE
#< "1Centre ""Bioengineering"" of Russian Academy of Sciences"
#> 1Centre "Bioengineering" of Russian Academy of Sciences

## peokaryotes
#["Organism/Name", "Campylobacter jejuni subsp. jejuni CG8421"]
#["TaxID", "478547"]
#["BioProject Accession", "PRJNA21037"]
#["BioProject ID", "21037"]
#["Group", "Proteobacteria"]
#["SubGroup", "delta/epsilon subdivisions"]
#["Size (Mb)", "1.60894"]
#["GC%", "30.3"]
#["Chromosomes/RefSeq", "-"]
#["Chromosomes/INSDC", "-"]
#["Plasmids/RefSeq", "-"]
#["Plasmids/INSDC", "-"]
#["WGS", "ABGQ01"]
#["Scaffolds", "20"]
#["Genes", "1590"]
#["Proteins", "1512"]
#["Release Date", "2008/09/19"]
#["Modify Date", "2014/01/08"]
#["Status", "Contig"]
#["Center", "Naval Medical Research Center"]
#["BioSample Accession", "SAMN02470701"]
#["Assembly Accession", "GCA_000171795.1"]
#["Reference", "-"]
#["FTP Path", "Campylobacter_jejuni/GCF_000171795"]
#["Pubmed ID", "18809665"]
#
#eukaryotes
#["Organism/Name", "Emiliania huxleyi CCMP1516"]
#["TaxID", "280463"]
#["BioProject Accession", "PRJNA77753"]
#["BioProject ID", "77753"]
#["Group", "Protists"]
#["SubGroup", "Other Protists"]
#["Size (Mb)", "167.676"]
#["GC%", "64.5"]
#["Assembly Accession", "GCA_000372725.1"]
#["Chromosomes", "-"]
#["Organelles", "-"]
#["Plasmids", "-"]
#["WGS", "AHAL01"]
#["Scaffolds", "7795"]
#["Genes", "38549"]
#["Proteins", "38554"]
#["Release Date", "2013/04/19"]
#["Modify Date", "2013/07/08"]
#["Status", "Scaffold"]
#["Center", "JGI"]
#["BioSample Accession", "-"]