sequence_logo 1.0.2 → 1.0.3

data/lib/sequence_logo/ytilib/pmsd.rb

@@ -1,4 +1,4 @@
-#!/usr/bin/ruby
+#!/usr/bin/ruby
 module Ytilib
   class PM
     def score_sigma(trycount = 4**10, approx = false, bg = nil)

data/lib/sequence_logo/ytilib/ppm_support.rb

@@ -0,0 +1,85 @@
+class Object
+  def deep_dup
+    Marshal.load(Marshal.dump(self))
+  end
+end
+
+def get_ppm_from_file(in_file_name)
+  case File.ext_wo_name(in_file_name)
+  when 'pat', 'pcm'
+    pm = PM.load(in_file_name)
+    pm.fixwc  if pm.words_count
+  when 'mfa', 'fasta', 'plain'
+    pm = PM.new_pcm(Ytilib.read_seqs2array(in_file_name))
+  when 'xml'
+    pm = PM.from_bismark(Bismark.new(in_file_name).elements["//PPM"])
+  when in_file_name
+    pm = PPM.from_IUPAC(in_file_name.upcase)
+  end
+  pm.get_ppm
+rescue
+  nil
+end
+
+class PPM
+  attr_accessor :name
+  
+  def get_ppm
+    self
+  end
+  
+  def get_line(v)
+    ( (v - icd4of4) / icd4of4 ).abs
+  end
+
+  def get_logo(icd_mode)
+    case icd_mode.to_s
+    when 'weblogo'
+      get_logo_weblogo
+    when 'discrete'
+      get_logo_discrete
+    end
+  end
+
+
+  def get_logo_weblogo
+    rseq = []
+    @matrix['A'].each_index { |i|
+      rseq << 2 + ['A','C','G','T'].inject(0) { |sum, l|
+        pn = @matrix[l][i]
+        sum += (pn == 0) ? 0 : pn * Math.log(pn) / Math.log(2)
+      }
+    }
+    
+    mat = {'A'=>[], 'C'=>[], 'G'=>[], 'T'=>[]}
+    @matrix['A'].each_index { |i|
+      ['A','C','G','T'].each { |l|
+        mat[l][i]= @matrix[l][i] * rseq[i] / 2 # so we can handle a '2 bit' scale here
+      }
+    }
+    
+    mat
+  end
+
+  def get_logo_discrete
+    checkerr("words count is undefined") { !words_count }
+    
+    rseq = []
+    @matrix['A'].each_index { |i|
+      rseq << (icd4of4 == 0 ? 1.0 : ( (infocod(i) - icd4of4) / icd4of4 ).abs)
+    }
+    
+    mat = {'A'=>[], 'C'=>[], 'G'=>[], 'T'=>[]}
+    @matrix['A'].each_index { |i|
+      ['A','C','G','T'].each { |l| 
+        mat[l][i] = @matrix[l][i] * rseq[i]
+      }
+    }
+    
+    mat
+  end
+  
+  def revcomp
+    deep_dup.revcomp!
+  end
+end

data/lib/sequence_logo/ytilib/randoom.rb

@@ -1,131 +1,131 @@
-#!/usr/bin/ruby
-module Ytilib
-
-srand
-
-module Randoom
-  
-  private
-
-  def Randoom.new_counts
-    { 'A' => 0, 'C' => 0, 'G' => 0, 'T' => 0, 'N' => 0 }
-  end
-  
-  def Randoom.random_letter(probs)
-    random = rand()
-    return 'A' if random < probs['A']
-    return 'C' if random < probs['A'] + probs['C']
-    return 'G' if random < probs['A'] + probs['C'] + probs['G']
-    return 'T'
-  end
-
-  public
-  
-  def Randoom.calc_probs(input)
-    counts = new_counts
-    counts.default = 0
-    (0...input.length).each { |i|
-      counts[input[i,1].upcase] += 1
-    }
-    return make_probs!(counts)
-  end
-    
-  def Randoom.rand_seq(req_len, probs = DEF_PROBS, probs_m = nil)
-    randoom = ''
-    if (probs_m == nil)
-      req_len.times { randoom << random_letter(probs) }
-      return randoom  
-    end
-    random_l = random_letter(probs)
-    randoom = random_l
-    (req_len-1).times {
-      cur_probs = probs_m[random_l]
-      random_l = random_letter(cur_probs)
-      randoom << random_l
-    }
-    return randoom
-  end
-  
-  def Randoom.calc_probs_m(input)
-    probs_m = { 'A' => {}, 'C' => {}, 'G' => {}, 'T' => {} }
-    counts = { 'A' => new_counts, 'C' => new_counts, 'G' => new_counts, 'T' => new_counts, 'N' => new_counts }
-    (0...input.length-1).each { |i|
-      pair = input[i, 2].upcase
-      counts[pair[0,1]][pair[1,1]] += 1
-    }
-    probs_m['A'] = make_probs!(counts['A'])
-    probs_m['C'] = make_probs!(counts['C'])
-    probs_m['G'] = make_probs!(counts['G'])
-    probs_m['T'] = make_probs!(counts['T'])
-    return probs_m
-  end
-  
-  def Randoom.make_probs_m!(counts)
-    ['A','C','G','T','N'].each { |l2|
-      addv = counts['N'][l2] / 4.0
-      ['A','C','G','T'].each { |l1|
-        counts[l1][l2] += addv
-      }
-    }
-    
-    probs_m = { 'A' => {}, 'C' => {}, 'G' => {}, 'T' => {} }
-    probs_m['A'] = make_probs!(counts['A'])
-    probs_m['C'] = make_probs!(counts['C'])
-    probs_m['G'] = make_probs!(counts['G'])
-    probs_m['T'] = make_probs!(counts['T'])
-    return probs_m
-  end
-  
-  def Randoom.make_probs!(counts, length = nil)
-    probs = { 'A' => 0, 'C' => 0, 'G' => 0, 'T' => 0 }
-    length = counts['A'] + counts['C'] + counts['G'] + counts['T'] + counts['N'] if length == nil
-    length = length.to_f
-    ['A','C','G','T'].each { |l| counts[l] += counts['N'] / 4.0 }
-    return probs if length == 0
-    probs['A'] = counts['A'] / length
-    probs['C'] = counts['C'] / length
-    probs['G'] = counts['G'] / length
-    probs['T'] = 1 - probs['A'] - probs['C'] - probs['G']
-    return probs
-  end
-  
-  def Randoom.equalize!(probs)
-    probs['A'] = probs['T'] = (probs['A'] + probs['T']) / 2
-    probs['C'] = probs['G'] = (probs['C'] + probs['G']) / 2
-    return probs
-  end
-  
-  def Randoom.twostrand!(probs)
-    return Randoom.equalize!(probs)
-  end
-  
-  DEF_PROBS = PPM.probs2IUPAC!({ 'A' => 0.25, 'C' => 0.25, 'G' => 0.25, 'T' => 0.25, 'N' => 0.25 })
-  
-  # probabilities counted without _random.fa files for human genome
-  DMEL40_PROBS1 = {"A"=>0.287729562173578, "C"=>0.21236364146414, "G"=>0.212259972960341, "T"=>0.287646823401942}
-  DMEL40_PROBS2 = {"A"=>0.28768819278776, "C"=>0.21231180721224, "G"=>0.21231180721224, "T"=>0.28768819278776}
-  
-  DMEL40_PROBS1_M = {"A"=>{"A"=>0.350403075314602, "C"=>0.181194374386404, "G"=>0.188361404205017, "T"=>0.280041146093977}, 
-    "C"=>{"A"=>0.325366772443085, "C"=>0.222264645612127, "G"=>0.197213801868993, "T"=>0.255154780075794}, 
-    "G"=>{"A"=>0.260710563672393, "C"=>0.27150575901391, "G"=>0.222294234776053, "T"=>0.245489442537644}, 
-    "T"=>{"A"=>0.217189093089999, "C"=>0.192590127484359, "G"=>0.239869076706963, "T"=>0.350351702718679}}
-  
-  HG17_PROBS1 = {"A"=>0.295309361730334, "C"=>0.204413561169847, "G"=>0.204519414193999, "T"=>0.295757662905821}
-  HG17_PROBS2 = {"A"=>0.295533512318077, "C"=>0.204466487681923, "G"=>0.204466487681923, "T"=>0.295533512318077}
-  
-  HG17_PROBS1_M = {"A"=>{"A"=>0.331091206257755, "C"=>0.170458424092748, "G"=>0.236770972081246, "T"=>0.261679397568252}, 
-    "C"=>{"A"=>0.354813019140533, "C"=>0.254741288394943, "G"=>0.0481667110625576, "T"=>0.342278981401966}, 
-    "G"=>{"A"=>0.290057117684408, "C"=>0.208514091370804, "G"=>0.254732297362797, "T"=>0.246696493581991}, 
-    "T"=>{"A"=>0.222087715262152, "C"=>0.200697606508443, "G"=>0.245657322003887, "T"=>0.331557356225517}}
-  
-  HG18_PROBS1 = {"A"=>0.291900580635872, "C"=>0.207855064518284, "G"=>0.207968587245859, "T"=>0.292275767599985}
-  HG18_PROBS2 = {"A"=>0.292088174117929, "C"=>0.207911825882071, "G"=>0.207911825882071, "T"=>0.292088174117929}
-  
-  MM9_PROBS1 = {"A"=>0.289755259854654, "C"=>0.210085673636132, "G"=>0.210143929198141, "T"=>0.290015137311074}
-  MM9_PROBS2 = {"A"=>0.289885198582864, "C"=>0.210114801417136, "G"=>0.210114801417136, "T"=>0.289885198582864}
-  
-  MM9_PROBS1_M = {"A"=>{"A"=>0.310389104265713, "C"=>0.184962574392377, "G"=>0.251904718465914, "T"=>0.252743602875996}, "C"=>{"A"=>0.352189584318682, "C"=>0.250794045222924, "G"=>0.0494404816637487, "T"=>0.347575888794645}, "G"=>{"A"=>0.295931117515178, "C"=>0.197870954111653, "G"=>0.250756985626016, "T"=>0.255440942747154}, "T"=>{"A"=>0.219437756702452, "C"=>0.214548041970626, "G"=>0.255405334730743, "T"=>0.310608866596179}}
-
-end
-
-end
+#!/usr/bin/ruby
+module Ytilib
+
+srand
+
+module Randoom
+  
+  private
+
+  def Randoom.new_counts
+    { 'A' => 0, 'C' => 0, 'G' => 0, 'T' => 0, 'N' => 0 }
+  end
+  
+  def Randoom.random_letter(probs)
+    random = rand()
+    return 'A' if random < probs['A']
+    return 'C' if random < probs['A'] + probs['C']
+    return 'G' if random < probs['A'] + probs['C'] + probs['G']
+    return 'T'
+  end
+
+  public
+  
+  def Randoom.calc_probs(input)
+    counts = new_counts
+    counts.default = 0
+    (0...input.length).each { |i|
+      counts[input[i,1].upcase] += 1
+    }
+    return make_probs!(counts)
+  end
+    
+  def Randoom.rand_seq(req_len, probs = DEF_PROBS, probs_m = nil)
+    randoom = ''
+    if (probs_m == nil)
+      req_len.times { randoom << random_letter(probs) }
+      return randoom  
+    end
+    random_l = random_letter(probs)
+    randoom = random_l
+    (req_len-1).times {
+      cur_probs = probs_m[random_l]
+      random_l = random_letter(cur_probs)
+      randoom << random_l
+    }
+    return randoom
+  end
+  
+  def Randoom.calc_probs_m(input)
+    probs_m = { 'A' => {}, 'C' => {}, 'G' => {}, 'T' => {} }
+    counts = { 'A' => new_counts, 'C' => new_counts, 'G' => new_counts, 'T' => new_counts, 'N' => new_counts }
+    (0...input.length-1).each { |i|
+      pair = input[i, 2].upcase
+      counts[pair[0,1]][pair[1,1]] += 1
+    }
+    probs_m['A'] = make_probs!(counts['A'])
+    probs_m['C'] = make_probs!(counts['C'])
+    probs_m['G'] = make_probs!(counts['G'])
+    probs_m['T'] = make_probs!(counts['T'])
+    return probs_m
+  end
+  
+  def Randoom.make_probs_m!(counts)
+    ['A','C','G','T','N'].each { |l2|
+      addv = counts['N'][l2] / 4.0
+      ['A','C','G','T'].each { |l1|
+        counts[l1][l2] += addv
+      }
+    }
+    
+    probs_m = { 'A' => {}, 'C' => {}, 'G' => {}, 'T' => {} }
+    probs_m['A'] = make_probs!(counts['A'])
+    probs_m['C'] = make_probs!(counts['C'])
+    probs_m['G'] = make_probs!(counts['G'])
+    probs_m['T'] = make_probs!(counts['T'])
+    return probs_m
+  end
+  
+  def Randoom.make_probs!(counts, length = nil)
+    probs = { 'A' => 0, 'C' => 0, 'G' => 0, 'T' => 0 }
+    length = counts['A'] + counts['C'] + counts['G'] + counts['T'] + counts['N'] if length == nil
+    length = length.to_f
+    ['A','C','G','T'].each { |l| counts[l] += counts['N'] / 4.0 }
+    return probs if length == 0
+    probs['A'] = counts['A'] / length
+    probs['C'] = counts['C'] / length
+    probs['G'] = counts['G'] / length
+    probs['T'] = 1 - probs['A'] - probs['C'] - probs['G']
+    return probs
+  end
+  
+  def Randoom.equalize!(probs)
+    probs['A'] = probs['T'] = (probs['A'] + probs['T']) / 2
+    probs['C'] = probs['G'] = (probs['C'] + probs['G']) / 2
+    return probs
+  end
+  
+  def Randoom.twostrand!(probs)
+    return Randoom.equalize!(probs)
+  end
+  
+  DEF_PROBS = PPM.probs2IUPAC!({ 'A' => 0.25, 'C' => 0.25, 'G' => 0.25, 'T' => 0.25, 'N' => 0.25 })
+  
+  # probabilities counted without _random.fa files for human genome
+  DMEL40_PROBS1 = {"A"=>0.287729562173578, "C"=>0.21236364146414, "G"=>0.212259972960341, "T"=>0.287646823401942}
+  DMEL40_PROBS2 = {"A"=>0.28768819278776, "C"=>0.21231180721224, "G"=>0.21231180721224, "T"=>0.28768819278776}
+  
+  DMEL40_PROBS1_M = {"A"=>{"A"=>0.350403075314602, "C"=>0.181194374386404, "G"=>0.188361404205017, "T"=>0.280041146093977}, 
+    "C"=>{"A"=>0.325366772443085, "C"=>0.222264645612127, "G"=>0.197213801868993, "T"=>0.255154780075794}, 
+    "G"=>{"A"=>0.260710563672393, "C"=>0.27150575901391, "G"=>0.222294234776053, "T"=>0.245489442537644}, 
+    "T"=>{"A"=>0.217189093089999, "C"=>0.192590127484359, "G"=>0.239869076706963, "T"=>0.350351702718679}}
+  
+  HG17_PROBS1 = {"A"=>0.295309361730334, "C"=>0.204413561169847, "G"=>0.204519414193999, "T"=>0.295757662905821}
+  HG17_PROBS2 = {"A"=>0.295533512318077, "C"=>0.204466487681923, "G"=>0.204466487681923, "T"=>0.295533512318077}
+  
+  HG17_PROBS1_M = {"A"=>{"A"=>0.331091206257755, "C"=>0.170458424092748, "G"=>0.236770972081246, "T"=>0.261679397568252}, 
+    "C"=>{"A"=>0.354813019140533, "C"=>0.254741288394943, "G"=>0.0481667110625576, "T"=>0.342278981401966}, 
+    "G"=>{"A"=>0.290057117684408, "C"=>0.208514091370804, "G"=>0.254732297362797, "T"=>0.246696493581991}, 
+    "T"=>{"A"=>0.222087715262152, "C"=>0.200697606508443, "G"=>0.245657322003887, "T"=>0.331557356225517}}
+  
+  HG18_PROBS1 = {"A"=>0.291900580635872, "C"=>0.207855064518284, "G"=>0.207968587245859, "T"=>0.292275767599985}
+  HG18_PROBS2 = {"A"=>0.292088174117929, "C"=>0.207911825882071, "G"=>0.207911825882071, "T"=>0.292088174117929}
+  
+  MM9_PROBS1 = {"A"=>0.289755259854654, "C"=>0.210085673636132, "G"=>0.210143929198141, "T"=>0.290015137311074}
+  MM9_PROBS2 = {"A"=>0.289885198582864, "C"=>0.210114801417136, "G"=>0.210114801417136, "T"=>0.289885198582864}
+  
+  MM9_PROBS1_M = {"A"=>{"A"=>0.310389104265713, "C"=>0.184962574392377, "G"=>0.251904718465914, "T"=>0.252743602875996}, "C"=>{"A"=>0.352189584318682, "C"=>0.250794045222924, "G"=>0.0494404816637487, "T"=>0.347575888794645}, "G"=>{"A"=>0.295931117515178, "C"=>0.197870954111653, "G"=>0.250756985626016, "T"=>0.255440942747154}, "T"=>{"A"=>0.219437756702452, "C"=>0.214548041970626, "G"=>0.255405334730743, "T"=>0.310608866596179}}
+
+end
+
+end

data/lib/sequence_logo/ytilib/ytilib.rb

@@ -1,147 +1,147 @@
-module Ytilib
-  def Ytilib.time
-    return Time.now.strftime('%d %b %H:%M:%S')
-  end
-end
-
-$program_name = nil
-
-def start(fullpath)
-  report(fullpath + ARGV.inject("") { |out, v| out += " " + v})
-  return if $NO_REPORT
-  $program_name = "[#{File.name_wo_ext(fullpath)}]"
-end
-
-def report(message, program_name = nil)
-  $program_name = "[#{program_name}]" if program_name != nil
-  return if $NO_REPORT
-  puts "LLIB #{Ytilib.time} #{$program_name}\t#{message}" if !block_given? || yield
-end
-
-def checkerr(message = "checkerr failed")  
-  if !block_given? || yield
-    puts "LLIB #{Ytilib.time} [error]\t#{message}" unless $NO_REPORT
-    raise "LLIB #{Ytilib.time} #{$program_name}\n\t#{message}\n" 
-  end
-end
-
-module Ytilib
-  
-  STRAND_DIRECT = "direct"
-  STRAND_REVCOMP = "revcomp"  
-  
-  def Ytilib.read_mfa2hash(path)
-    input_fasta_f = File.new(path, "r")
-    seqs, seq_name = {}, nil
-    input_fasta_f.each_line { |line|
-      if line[0,1] == ">"
-        seq_name = line[1..-1].strip
-        seq_name = yield seq_name if block_given?
-        checkerr("multiple sequences with the same name=#{seq_name}") { seqs[seq_name] }
-        seqs[seq_name] = ""
-      elsif seq_name != nil
-        seqs[seq_name] << line.strip
-      end
-    }
-    input_fasta_f.close
-    return seqs
-  end
-  
-  def Ytilib.read_mfa2array(path)
-    input_fasta_f = File.new(path, "r")
-    seqs, seq_name = [], nil
-    input_fasta_f.each_line { |line|
-      if line[0,1] == ">"
-        seq_name = line[1..-1].strip
-        yield seq_name if block_given?
-        seqs << ""
-      elsif seq_name != nil
-        seqs.last << line.strip
-      end
-    }
-    input_fasta_f.close
-    return seqs
-  end
-  
-  def Ytilib.mfa2array(input)
-    seqs, seq_name = [], nil
-    input.each_line { |line|
-      if line[0,1] == ">"
-        seq_name = line[1..-1].strip
-        seqs << ""
-      elsif seq_name != nil
-        seqs.last << line.strip
-      end
-    }
-    return seqs
-  end
-  
-  def Ytilib.read_plain2array(path)
-    array = []
-    File.open(path).each_line { |line|
-      array << line.strip if !line.strip.empty?
-    }
-    return array
-  end  
-  
-  def Ytilib.read_seqs2array(path)
-    type = File.ext_wo_name(path)
-    case type
-    when "mfa", "fasta", "fa"
-      return Ytilib.read_mfa2array(path)
-    when "plain","txt"
-      return Ytilib.read_plain2array(path)
-    else
-      checkerr("unknown sequences-file, ext=#{type}")
-    end
-  end
-  
-  def Ytilib.write_mfa(seqs, path, prefix = " ")
-    if seqs.is_a?(Hash)
-      out_fasta_f = File.new(path, "w+")
-      seqs.each_key { |name|
-        out_fasta_f << ">#{prefix}#{name}" << $/ << seqs[name] << $/
-      }
-      out_fasta_f.close
-    else 
-      out_fasta_f = File.new(path, "w+")
-      seqs.each_with_index { |seq, i|
-        out_fasta_f << ">#{prefix}#{i+1}" << $/ << seq << $/
-      }
-      out_fasta_f.close
-    end
-  end
-  
-  def get_consensus(seqs)
-    report "consensus creating method should be checked, you are using unsafe code"
-    return 'nil' if seqs.size == 0
-    conslet = { 'A' => 'A', 'C' => 'C', 'G' => 'G', 'T' => 'T', 'U' => 'U',
-            'AG' => 'R', 'CT' => 'Y', 'GT' => 'K', 'AC' => 'M', 'CG' => 'S', 'AT' => 'W',
-            'CGT' => 'B', 'AGT' => 'D', 'ACT' => 'H', 'ACG' => 'V', 'ACGT' => 'N'
-    }
-    new_consensus, letters = '', []
-    0.upto(seqs[0].size-1) { |i|
-      seqs.each do |word|
-        letters << word[i] if !letters.include?(word[i])
-      end
-      letters.sort!
-      letters_string = ''
-      letters.each do |letter| letters_string << letter end
-      checkerr("cannot find consensus letter for a given letter set :#{}") { conslet[letters_string] == nil }
-      new_consensus << conslet[letters_string]	
-      letters.clear
-    }
-    return new_consensus
-  end
-
-  def Ytilib.new_mysql_conn(database)
-    my = Mysql.new(MYSQL_HOST, MYSQL_USER, MYSQL_PASSWORD, database)
-    checkerr("cannot connect to MySQL server") { my.query("select 1").fetch_row[0] != "1" }
-    return my
-  end  
-  
-
-end
-
-report "ytilib required, working directory #{Dir.pwd}", "ytilib"
+module Ytilib
+  def Ytilib.time
+    return Time.now.strftime('%d %b %H:%M:%S')
+  end
+end
+
+$program_name = nil
+
+def start(fullpath)
+  report(fullpath + ARGV.inject("") { |out, v| out += " " + v})
+  return if $NO_REPORT
+  $program_name = "[#{File.name_wo_ext(fullpath)}]"
+end
+
+def report(message, program_name = nil)
+  $program_name = "[#{program_name}]" if program_name != nil
+  return if $NO_REPORT
+  puts "LLIB #{Ytilib.time} #{$program_name}\t#{message}" if !block_given? || yield
+end
+
+def checkerr(message = "checkerr failed")  
+  if !block_given? || yield
+    puts "LLIB #{Ytilib.time} [error]\t#{message}" unless $NO_REPORT
+    raise "LLIB #{Ytilib.time} #{$program_name}\n\t#{message}\n" 
+  end
+end
+
+module Ytilib
+  
+  STRAND_DIRECT = "direct"
+  STRAND_REVCOMP = "revcomp"  
+  
+  def Ytilib.read_mfa2hash(path)
+    input_fasta_f = File.new(path, "r")
+    seqs, seq_name = {}, nil
+    input_fasta_f.each_line { |line|
+      if line[0,1] == ">"
+        seq_name = line[1..-1].strip
+        seq_name = yield seq_name if block_given?
+        checkerr("multiple sequences with the same name=#{seq_name}") { seqs[seq_name] }
+        seqs[seq_name] = ""
+      elsif seq_name != nil
+        seqs[seq_name] << line.strip
+      end
+    }
+    input_fasta_f.close
+    return seqs
+  end
+  
+  def Ytilib.read_mfa2array(path)
+    input_fasta_f = File.new(path, "r")
+    seqs, seq_name = [], nil
+    input_fasta_f.each_line { |line|
+      if line[0,1] == ">"
+        seq_name = line[1..-1].strip
+        yield seq_name if block_given?
+        seqs << ""
+      elsif seq_name != nil
+        seqs.last << line.strip
+      end
+    }
+    input_fasta_f.close
+    return seqs
+  end
+  
+  def Ytilib.mfa2array(input)
+    seqs, seq_name = [], nil
+    input.each_line { |line|
+      if line[0,1] == ">"
+        seq_name = line[1..-1].strip
+        seqs << ""
+      elsif seq_name != nil
+        seqs.last << line.strip
+      end
+    }
+    return seqs
+  end
+  
+  def Ytilib.read_plain2array(path)
+    array = []
+    File.open(path).each_line { |line|
+      array << line.strip if !line.strip.empty?
+    }
+    return array
+  end  
+  
+  def Ytilib.read_seqs2array(path)
+    type = File.ext_wo_name(path)
+    case type
+    when "mfa", "fasta", "fa"
+      return Ytilib.read_mfa2array(path)
+    when "plain","txt"
+      return Ytilib.read_plain2array(path)
+    else
+      checkerr("unknown sequences-file, ext=#{type}")
+    end
+  end
+  
+  def Ytilib.write_mfa(seqs, path, prefix = " ")
+    if seqs.is_a?(Hash)
+      out_fasta_f = File.new(path, "w+")
+      seqs.each_key { |name|
+        out_fasta_f << ">#{prefix}#{name}" << $/ << seqs[name] << $/
+      }
+      out_fasta_f.close
+    else 
+      out_fasta_f = File.new(path, "w+")
+      seqs.each_with_index { |seq, i|
+        out_fasta_f << ">#{prefix}#{i+1}" << $/ << seq << $/
+      }
+      out_fasta_f.close
+    end
+  end
+  
+  def get_consensus(seqs)
+    report "consensus creating method should be checked, you are using unsafe code"
+    return 'nil' if seqs.size == 0
+    conslet = { 'A' => 'A', 'C' => 'C', 'G' => 'G', 'T' => 'T', 'U' => 'U',
+            'AG' => 'R', 'CT' => 'Y', 'GT' => 'K', 'AC' => 'M', 'CG' => 'S', 'AT' => 'W',
+            'CGT' => 'B', 'AGT' => 'D', 'ACT' => 'H', 'ACG' => 'V', 'ACGT' => 'N'
+    }
+    new_consensus, letters = '', []
+    0.upto(seqs[0].size-1) { |i|
+      seqs.each do |word|
+        letters << word[i] if !letters.include?(word[i])
+      end
+      letters.sort!
+      letters_string = ''
+      letters.each do |letter| letters_string << letter end
+      checkerr("cannot find consensus letter for a given letter set :#{}") { conslet[letters_string] == nil }
+      new_consensus << conslet[letters_string]	
+      letters.clear
+    }
+    return new_consensus
+  end
+
+  def Ytilib.new_mysql_conn(database)
+    my = Mysql.new(MYSQL_HOST, MYSQL_USER, MYSQL_PASSWORD, database)
+    checkerr("cannot connect to MySQL server") { my.query("select 1").fetch_row[0] != "1" }
+    return my
+  end  
+  
+
+end
+
+#report "ytilib required, working directory #{Dir.pwd}", "ytilib"
 include Ytilib