gistfile2.txt

Rakefile

require 'bio'

task :map_ids do
  mappings = YAML.load(File.read('data/mapping.yml'))
  v2_ids = File.readlines('data/v2_gene_ids.txt').map{|a| a.to_i}
end

task :select do
  v2_ids = File.readlines('data/v2_gene_ids.txt').map{|a| a.to_i}
  entries = Bio::FlatFile.auto('data/proteins.faa')
  entries = entries.select do |entry|
    v2_ids.include? entry.definition.split[1].split('_').last.to_i
  end
  File.open('out/selection.faa','w') do |out|
    entries.each {|entry| out.puts(entry.to_s)}
  end
end