gistfile1.rb

#!/usr/bin/env ruby

in_file = ARGV[0]
sqtocs = { "AA" => 0, "AC" => 1, "AG" => 2, "AT" => 3,
           "CA" => 1, "CC" => 0, "CG" => 3, "CT" => 2,
           "GA" => 2, "GC" => 3, "GG" => 0, "GT" => 1,
           "TA" => 3, "TC" => 2, "TG" => 1, "TT" => 0 }

# seq space Old/NEW format:
# 1       775852  rs2980300       A/G     A       GACTTCACTAACTCANAGAGACACAGTCATT
# 1       711153  drio1   CACCAAAGGAGGAAG CCTTGGTAGAAGATA C       G
# CS space NEW format:
# 1 711153        rs12565286    10020220202  02010132202  C       G       30      03
# WARNING!: 
# + ss: flanks are 15bp long
# + cs: flanks are 11bp long

i = 1
File.open(in_file).each_line do |l|
  chrm, pos, id, f_seq, t_seq, ssr, ssv = l.split

  valid_nuc = /[ACGT]/
  unless ssr =~ valid_nuc and ssv =~ valid_nuc
    next
    raise "invalid coding for nucleotides: line:\n#{i}: #{l}"
  end

  # Convert to color space the sequence
  f_cs = ""; t_cs = ""
  (0..f_seq.size-2).each {|i| f_cs << sqtocs[f_seq[i] + f_seq[i+1]].to_s }
  (0..t_seq.size-2).each {|i| t_cs << sqtocs[t_seq[i] + t_seq[i+1]].to_s }

  # Convert to color space the ref and var seq
  rd = (sqtocs[f_seq[-1] + ssr]).to_s + (sqtocs[ssr + t_seq[0]]).to_s
  vd = (sqtocs[f_seq[-1] + ssv]).to_s + (sqtocs[ssv + t_seq[0]]).to_s

  # Find the other possible alleles. sequence space
  o1, o2 = %w(A C T G).inject("") {|a, n|
    (n != ssr && n != ssv) ? a + n : a + ''
  }.split("")

  # Convert them to cs
  o1cs = (sqtocs[f_seq[-1] + o1]).to_s + (sqtocs[o1 + t_seq[0]]).to_s
  o2cs = (sqtocs[f_seq[-1] + o2]).to_s + (sqtocs[o2 + t_seq[0]]).to_s

  puts "#{chrm}\t#{pos}\t#{id}\t#{f_cs[3..14]}\t#{t_cs[0..10]}\t#{ssr}\t#{ssv}\t#{rd}\t#{vd}"
  #puts "#{chrm}\t#{pos}\t#{id}\t#{f_cs}\t#{t_cs}\t#{ssr}\t#{ssv}\t#{rd}\t#{vd} -- #{o1}:#{o1cs} #{o2}:#{o2cs}"

  i+=1
end