bio-polyploid-tools 0.10.1 → 1.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 1a74407d5aee3baf6b231007be242d2097f07f74a0a012e151c3aef43175ef73
-  data.tar.gz: fff2475fcf69dec083a67bff9fd573738ac810ca764e7d6e0c7338231e4a81bd
+  metadata.gz: 9191156e91a48ec245e181a1541d4b636b01c848b03f2b7db5f7729ddfc05421
+  data.tar.gz: '0449ab8d09b268538d3604f20b555d94be53cac35ff8d591a29c792f98df3def'
 SHA512:
-  metadata.gz: dc594e3c51d0a1c7fe2facf12002fb7d75b4324dcbaf15bb862e0890662364be709a6e1f1dbd9545a8b9da01c663eb6fe89a30c074ce9f6f3672af33879195fc
-  data.tar.gz: 3ffa7f6be31f7f2f1a4fddf669d4d95a565e7189db274c579d2c8ba298adae040e43cc5042c7e5405cbcb4d6b0355ef92f71e60c2c36cc516c119cbc075b98de
+  metadata.gz: 1c23625ac5c1cdfc3b4d34c3a8f416f680bc42a274b983ee64938bc3ba3bd7b685ad3e9cd9c04521a8f1baf8f91b0efae27a4c5d3034a4a18b141ec10209a7ee
+  data.tar.gz: cebf5a46d0a3cce9b63ccd71451f2f2a0d4903ae3e0954d34ba48955cc148b3d232bc5612ed8a528ade86cbfbb6e216c9788126c53b7f8cfa2157785ee00533b

data/SECURITY.md

@@ -0,0 +1,16 @@
+# Security Policy
+
+## Supported Versions
+
+The following table shows the currently supported version. 
+
+| Version | Supported          |
+| ------- | ------------------ |
+| 1.1.x   | :white_check_mark: |
+| 1.0.x   | :x:                |
+| 0.x.x   | :x:                |
+
+
+## Reporting a Vulnerability
+
+If you find a vulneravility, please submit a comment in the security tab

data/VERSION

@@ -1 +1 @@
-0.10.1
+1.2.0

data/bin/polymarker.rb

@@ -40,8 +40,8 @@ options[:scoring] = :genome_specific
 options[:database]  = false
 options[:filter_best]  = false
 options[:aligner] = :blast
-
-
+options[:max_hits] = 8
+options[:max_specific_primers]  = 15
 options[:primer_3_preferences] = {
       :primer_product_size_range => "50-150" ,
       :primer_max_size => 25 , 
@@ -132,6 +132,15 @@ OptionParser.new do |opts|
   opts.on("-d", "--database PREFIX", "Path to the blast database. Only used if the aligner is blast. The default is the name of the contigs file without extension.") do |o|
     options[:database] = o
   end
+
+  opts.on("-H", "--max_hits INT", "Maximum number of hits to the reference. If there are more hits than this value, the marker is ignored") do |o|
+    options[:max_hits] = o.to_i
+  end
+
+  opts.on("-S", "--max_specific_primers INT", "Maximum number of candidate primers to attempt to design. Default: #{options[:max_specific_primers]} ") do |o|
+    options[:max_specific_primers]  = o.to_i
+  end
+  
 end.parse!
 
 
@@ -233,8 +242,8 @@ File.open(test_file) do | f |
        region = fasta_reference_db.index.region_for_entry(snp.gene).get_full_region
        snp.template_sequence = fasta_reference_db.fetch_sequence(region)
      else
-        write_status "WARN: Unable to find entry for #{snp.gene}"
-      end
+      write_status "WARN: Unable to find entry for #{snp.gene}"
+    end
     elsif options[:mutant_list] and options[:reference] #List and fasta file
       snp = Bio::PolyploidTools::SNPMutant.parse(line)
       entry = fasta_reference_db.index.region_for_entry(snp.contig)
@@ -242,21 +251,21 @@ File.open(test_file) do | f |
        region = fasta_reference_db.index.region_for_entry(snp.contig).get_full_region
        snp.full_sequence = fasta_reference_db.fetch_sequence(region)
      else
-        write_status "WARN: Unable to find entry for #{snp.gene}"
-      end
-    else
-      raise Bio::DB::Exonerate::ExonerateException.new "Wrong number of arguments. " 
-    end
-    raise Bio::DB::Exonerate::ExonerateException.new "No SNP for line '#{line}'" if snp == nil
-
-    snp.genomes_count = options[:genomes_count]
-    snp.snp_in = snp_in
-    snp.original_name = original_name
-    if snp.position 
-      snps << snp
-    else
-      $stderr.puts "ERROR: #{snp.gene} doesn't contain a SNP"
+      write_status "WARN: Unable to find entry for #{snp.gene}"
     end
+  else
+    raise Bio::DB::Exonerate::ExonerateException.new "Wrong number of arguments. " 
+  end
+  raise Bio::DB::Exonerate::ExonerateException.new "No SNP for line '#{line}'" if snp == nil
+  snp.max_hits = options[:max_hits]
+  snp.genomes_count = options[:genomes_count]
+  snp.snp_in = snp_in
+  snp.original_name = original_name
+  if snp.position 
+    snps << snp
+  else
+    $stderr.puts "ERROR: #{snp.gene} doesn't contain a SNP"
+  end
   end
 end
 
@@ -307,7 +316,7 @@ def do_align(aln, exo_f, found_contigs, min_identity,fasta_file,options)
 
 end
 
-Bio::DB::Blast.align({:query=>temp_fasta_query, :target=>options[:database], :model=>model}) do |aln|
+Bio::DB::Blast.align({:query=>temp_fasta_query, :target=>options[:database], :model=>model, :max_hits=>options[:max_hits]}) do |aln|
   do_align(aln, exo_f, found_contigs,min_identity, fasta_file,options)
 end if options[:aligner] == :blast
 
@@ -334,7 +343,7 @@ container.gene_models(temp_fasta_query)
 container.chromosomes(target)
 container.add_parental({:name=>snp_in})
 container.add_parental({:name=>original_name})
-
+container.max_hits = options[:max_hits]
 snps.each do |snp|
   snp.container = container
   snp.flanking_size = container.flanking_size
@@ -358,7 +367,7 @@ write_status "Running primer3"
 file = File.open(primer_3_input, "w")
 
 Bio::DB::Primer3.prepare_input_file(file, options[:primer_3_preferences])
-added_exons = container.print_primer_3_exons(file, nil, snp_in)
+added_exons = container.print_primer_3_exons(file, nil, snp_in,  max_specific_primers: options[:max_specific_primers] )
 file.close
 
 Bio::DB::Primer3.run({:in=>primer_3_input, :out=>primer_3_output}) if added_exons > 0

data/bin/polymarker_capillary.rb

@@ -35,15 +35,21 @@ options[:primer_3_preferences] = {
 }
 options[:genomes_count] = 3
 options[:allow_non_specific] = false
+options[:aligner] = :blast
+options[:arm_selection]
+model="ungapped" 
+options[:arm_selection] = Bio::PolyploidTools::ChromosomeArm.getArmSelection("nrgene")
+options[:database]  = false 
 
 OptionParser.new do |opts|
-  opts.banner = "Usage: polymarker_capillary.rb [options]"
+  opts.banner = "Usage: polymarker_deletions.rb [options]"
 
   opts.on("-r", "--reference FILE", "Fasta file with the assembly") do |o|
     options[:reference] = o
   end
 
-  opts.on("-m", "--sequences FILE", "Fasta file with the sequences to amplify. the format must be Chromosome:start-end. Chromosome should match the names to the entries in the fasta files as it is used as main target") do |o|
+  opts.on("-m", "--sequences FILE", "Fasta file with the sequences to amplify. the format must be Chromosome:start-end. Chromosome 
+    should match the names to the entries in the fasta files as it is used as main target") do |o|
     options[:markers] = o
   end
 
@@ -53,10 +59,19 @@ OptionParser.new do |opts|
   opts.on("-g", "--genomes_count INT", "Number of genomes (default 3, for hexaploid)") do |o|
     options[:genomes_count] = o.to_i
   end
-  opts.on("-a", "--allow_non_specific", "If used, semi-specific and non-specific primers will be produced") do |o|
+  opts.on("-A", "--allow_non_specific", "If used, semi-specific and non-specific primers will be produced") do |o|
     options[:allow_non_specific] = true
   end
 
+  opts.on("-d", "--database PREFIX", "Path to the blast database. Only used if the aligner is blast. The default is the name of the contigs file without extension.") do |o|
+    options[:database] = o
+  end
+
+
+  opts.on("-a", "--arm_selection #{Bio::PolyploidTools::ChromosomeArm.getValidFunctions.join('|')}", "Function to decide the chromome arm") do |o|
+    options[:arm_selection] = Bio::PolyploidTools::ChromosomeArm.getArmSelection(o)
+  end
+
 end.parse!
 
 
@@ -65,23 +80,33 @@ reference     = options[:reference]
 markers       = options[:markers]
 output_folder = options[:output_folder]
 allow_non_specific = options[:allow_non_specific]
+
+options[:database] = options[:reference] unless  options[:database] 
+temp_fasta_query="#{output_folder}/to_align.fa"
 log "Output folder: #{output_folder}"
 exonerate_file="#{output_folder}/exonerate_tmp.tab"
 Dir.mkdir(output_folder)
+arm_selection = options[:arm_selection]
 
 module Bio::PolyploidTools
-
-
   
   class SequenceToAmplify < SNP
 
-    def self.select_chromosome(contig_name)
-  
-      arr = contig_name.split('_')
-      ret = "U"
-      ret = arr[2][0,2] if arr.size >= 3
-      ret = "3B" if arr.size == 2 and arr[0] == "v443"
-      ret = arr[0][0,2] if arr.size == 1   
+    def self.select_chromosome(gene_name, arm_selection)
+      #m=/##INFO=<ID=(.+),Number=(.+),Type=(.+),Description="(.+)">/.match(gene_name)
+      #m=/TraesCS(\d{1})(\w{1})(\d{2})G(\d+)/.match(gene_name)
+      #ret = {:group : m[1],
+      #       :genome : m[2],:version=>m[3],:chr_id=>m[4]}
+    
+      
+      #arr = contig_name.split('_')
+      #ret = "U"
+      #ret = arr[2][0,2] if arr.size >= 3
+      #ret = "3B" if arr.size == 2 and arr[0] == "v443"
+      #ret = arr[0][0,2] if arr.size == 1   
+      #ret = "#{m[1]}#{m[2]}"
+      #puts ret
+      ret = arm_selection.call(gene_name)
       return ret
     end
 
@@ -92,18 +117,18 @@ module Bio::PolyploidTools
     #Format: 
     #A fasta entry with the id: contig:start-end
     #The sequence can be prodcued with samtools faidx
-    def self.parse(fasta_entry)
-
+    def self.parse(fasta_entry, arm_selection)
+      #puts fasta_entry.definition
       snp = SequenceToAmplify.new
       match_data = /(?<rname>\w*):(?<rstart>\w*)-(?<rend>\w*)/.match(fasta_entry.definition)
-      
+      #puts match_data.inspect
       rName = Regexp.last_match(:rname)
       rStart =  Regexp.last_match(:rstart).to_i
       rEnd =  Regexp.last_match(:rend).to_i
       snp.gene = fasta_entry.definition
       #snp.chromosome=rName
-
-      snp.chromosome=select_chromosome(rName)
+      #puts "Gene: #{snp.gene}"
+      snp.chromosome=select_chromosome(fasta_entry.definition, arm_selection)
       #puts "#{rName}: #{snp.chromosome}"
       snp.sequence_original = fasta_entry.seq
       snp.template_sequence = fasta_entry.seq.upcase
@@ -111,7 +136,7 @@ module Bio::PolyploidTools
       snp.rstart = rStart
       snp.rend = rEnd
 
-      snp.position   = 100
+      snp.position   = snp.sequence_original.size / 2
       snp.original   = snp.sequence_original[snp.position]
       
       tmp =  Bio::Sequence::NA.new(snp.original)
@@ -121,7 +146,7 @@ module Bio::PolyploidTools
       snp
     end
 
-    def primer_3_all_strings(target_chromosome, parental) 
+    def primer_3_all_strings(target_chromosome, parental, max_specific_primers: 20, flanking_size:500) 
       #puts target_chromosome 
       #puts parental
       #puts aligned_sequences.to_fasta
@@ -130,8 +155,11 @@ module Bio::PolyploidTools
 
       seq_original = String.new(pr.sequence)
       #puts seq_original.size.to_s << "-" << primer_3_min_seq_length.to_s
+      #puts "___"
+      #puts pr.inspect
       return primer_3_propertes if seq_original.size < primer_3_min_seq_length
-      return primer_3_propertes unless pr.snp_pos == 500
+      #puts "((("
+      return primer_3_propertes unless pr.snp_pos == flanking_size
       #puts "Sequence origina: #{ self.original}" 
       #puts pr.to_fasta
       #puts "Postion: #{pr.snp_pos}"
@@ -232,10 +260,13 @@ file = Bio::FastaFormat.open(markers)
 file.each do |entry|
 
   begin
-    tmp = Bio::PolyploidTools::SequenceToAmplify.parse(entry)
+    #puts entry.inspect
+    tmp = Bio::PolyploidTools::SequenceToAmplify.parse(entry, arm_selection)
     snps << tmp if tmp
-  rescue
+  rescue Exception => e
+    log "ERROR\t#{e.message}"
     $stderr.puts "Unable to generate the marker for: #{entry.definition}"
+    $stderr.puts e.backtrace
   end
 
 end
@@ -246,45 +277,38 @@ file.close
 exo_f = File.open(exonerate_file, "w")
 target=reference
 
-fasta_file = Bio::DB::Fasta::FastaFile.new({:fasta=>target})
+fasta_file = Bio::DB::Fasta::FastaFile.new(fasta: target)
 fasta_file.load_fai_entries
-min_identity = 95
+min_identity = 90
 found_contigs = Set.new
 
-Bio::DB::Exonerate.align({:query=>markers, :target=>reference, :model=>'ungapped'}) do |aln|
+
+def do_align(aln, exo_f, found_contigs, min_identity,fasta_file,options)
   if aln.identity > min_identity
     exo_f.puts aln.line
-    #puts aln.line
     unless found_contigs.include?(aln.target_id) #We only add once each contig. Should reduce the size of the output file. 
       found_contigs.add(aln.target_id)
       entry = fasta_file.index.region_for_entry(aln.target_id)
-      raise Exception.new,  "Entry not found! #{aln.target_id}. Make sure that the #{reference}.fai was generated properly." if entry == nil
+      raise ExonerateException.new,  "Entry not found! #{aln.target_id}. Make sure that the #{target_id}.fai was generated properly." if entry == nil
+      if options[:extract_found_contigs]
+        region = entry.get_full_region
+        seq = fasta_file.fetch_sequence(region)
+        contigs_f.puts(">#{aln.target_id}\n#{seq}") 
+      end
     end
   end  
-end
-exo_f.close
-
-arm_selection_functions = Hash.new
 
-arm_selection_functions[:full_scaffold] = lambda do | contig_name |    
-  return contig_name
 end
 
-#Function to parse stuff like: "IWGSC_CSS_1AL_scaff_110"
-#Or the first two characters in the contig name, to deal with 
-#pseudomolecules that start with headers like: "1A"
-#And with the cases when 3B is named with the prefix: v443
-arm_selection_functions[:arm_selection_embl] = lambda do | contig_name|
-  
-  arr = contig_name.split('_')
-  ret = "U"
-  ret = arr[2][0,2] if arr.size >= 3
-  ret = "3B" if arr.size == 2 and arr[0] == "v443"
-  ret = arr[0][0,2] if arr.size == 1   
-  return ret
-end
+Bio::DB::Blast.align({:query=>markers, :target=>options[:database], :model=>model, :max_hits=>options[:max_hits]}) do |aln|
+  do_align(aln, exo_f, found_contigs,min_identity, fasta_file,options)
+end if options[:aligner] == :blast
 
+Bio::DB::Exonerate.align({:query=>markers, :target=>target, :model=>model}) do |aln|
+  do_align(aln, exo_f, found_contigs, min_identity,fasta_file,options)
+end if options[:aligner] == :exonerate
 
+exo_f.close
 
 container= Bio::PolyploidTools::ExonContainer.new
 container.flanking_size=500 
@@ -292,6 +316,7 @@ container.gene_models(markers)
 container.chromosomes(target)
 container.add_parental({:name=>"A"})
 container.add_parental({:name=>"B"})
+#puts "SNPs size: #{snps.size}"
 snps.each do |snp|
   snp.snp_in = "B"
   snp.container = container
@@ -300,8 +325,10 @@ snps.each do |snp|
   snp.includeNoSpecific = allow_non_specific
   container.add_snp(snp)
 end
-container.add_alignments({:exonerate_file=>exonerate_file, :arm_selection=>arm_selection_functions[:arm_selection_embl] , :min_identity=>min_identity})
 
+container.add_alignments({:exonerate_file=>exonerate_file, 
+  :arm_selection=> arm_selection,
+  :min_identity=>min_identity})
 
 
 exons_filename="#{output_folder}/localAlignment.fa"
@@ -329,12 +356,15 @@ output_file  = "#{output_folder}/primers.csv"
 file = File.open(masks_output, "w")
 out  = File.open(output_file,  "w")
 
+out.puts ["Id","specificity","inside","type","target","orientation","product_size",
+  "left_position","left_tm","left_sequence",
+"right_position","right_tm","right_sequence"].join ","
 class Bio::DB::Primer3::Primer3Record
   attr_accessor :primerPairs
 end
 
 printed_counts = Hash.new(0)
-Bio::DB::Primer3::Primer3Record.parse_file(primer_3_output) do | primer3record |
+Bio::DB::Primer3::Primer3Record.parse_file(primer_3_output ) do | primer3record |
   #puts primer3record.inspect
   next if primer3record.primer_left_num_returned.to_i == 0
   
@@ -358,10 +388,7 @@ Bio::DB::Primer3::Primer3Record.parse_file(primer_3_output) do | primer3record |
 
   file.puts ">#{seq_id}\n#{sequence_template}"
   file.puts ">#{seq_id}:mask\n#{sequence_mask}"
-   #puts "FDFDS"
-
-   #puts primer3record.primerPairs
-
+  
    primer3record.primerPairs.each do |p| 
     #puts p.inspect
     printed += 1   
@@ -381,10 +408,10 @@ Bio::DB::Primer3::Primer3Record.parse_file(primer_3_output) do | primer3record |
     toPrint <<  p.right.sequence
 
     middle = 501 
-    toPrint << lArr[0]
-    toPrint << rArr[0]
-    toPrint << middle - lArr[0]
-    toPrint << rArr[0] - middle
+    #toPrint << lArr[0]
+    #toPrint << rArr[0]
+    #toPrint << middle - lArr[0]
+    #toPrint << rArr[0] - middle
 #Start End LeftDistance  RightDistance
 
     out.puts toPrint.join(",")

data/bin/{find_homoeologue_variations.rb → polymarker_deletions.rb}

@@ -53,14 +53,12 @@ class Bio::PolyploidTools::ExonContainer
 end
 
 class Bio::DB::Primer3::SNP
-
   def to_s
      "#{gene}:#{snp_from.chromosome}"
   end
-
 end
-class Bio::DB::Primer3::Primer3Record
 
+class Bio::DB::Primer3::Primer3Record
 
   def best_pair
     return @best_pair if @best_pair
@@ -82,7 +80,7 @@ class Bio::DB::Primer3::Primer3Record
         @total_caps = capital_count
       end
     end
-    #@best_pair = @primerPairs.min
+    
     @best_pair
   end
 
@@ -107,12 +105,13 @@ class Bio::DB::Primer3::Primer3Record
 
   def score
     best_pair
+    total_caps = "#{best_pair.left.sequence}#{best_pair.right.sequence}".scan(/[A-Z]/).length
 #    puts "score"
  #   puts self.inspect
     ret = 0
     ret += @scores[type]
     ret += @scores[:exon] if exon?
-    ret -= @total_caps * 10  
+    ret -= total_caps * 10  
     ret -= product_length
     ret
   end
@@ -123,71 +122,21 @@ class Bio::DB::Primer3::Primer3Record
 
    def left_primer_snp(snp)
       tmp_primer = String.new(left_primer)
-      #if self.orientation == :forward
-      #  base_original = snp.original 
-      #  base_snp = snp.snp
-      #elsif self.orientation == :reverse
-      #  base_original = reverse_complement_string(snp.original )
-      #  base_snp = reverse_complement_string(snp.snp)
-      #else
-      #  raise Primer3Exception.new "#{self.orientation} is not a valid orientation"
-      #end
-
-      # puts "#{snp.to_s} #{self.orientation} #{tmp_primer[-1] } #{base_original} #{base_snp}"
-      #if tmp_primer[-1] == base_original
-      #  tmp_primer[-1] = base_snp
-      #elsif tmp_primer[-1] == base_snp
-      #  tmp_primer[-1] = base_original  
-      #else
-      #  raise Primer3Exception.new "#{tmp_primer} doesnt end in a base in the SNP #{snp.to_s}"
-      #end
-      #puts "tmp_primer: #{tmp_primer}"
       return tmp_primer
     end
 
 end
 
-arm_selection_functions = Hash.new;
-
-
-arm_selection_functions[:arm_selection_first_two] = lambda do | contig_name |
-  ret = contig_name[0,2]       
-  return ret
-end
-
-#Function to parse stuff like: "IWGSC_CSS_1AL_scaff_110"
-#Or the first two characters in the contig name, to deal with 
-#pseudomolecules that start with headers like: "1A"
-#And with the cases when 3B is named with the prefix: v443
-arm_selection_functions[:arm_selection_embl] = lambda do | contig_name|
-  
-  arr = contig_name.split('_')
-  ret = "U"
-  ret = arr[2][0,2] if arr.size >= 3
-  ret = "3B" if arr.size == 2 and arr[0] == "v443"
-  ret = arr[0][0,2] if arr.size == 1   
-  return ret
-end
-
-arm_selection_functions[:arm_selection_morex] = lambda do | contig_name |
-  ret = contig_name.split(':')[0].split("_")[1];       
-  return ret
-end
-
-arm_selection_functions[:scaffold] = lambda do | contig_name |
-  ret = contig_name;       
-  return ret
-end
-
 markers = nil
 
 options = {}
+options[:aligner] = :blast
 options[:model] = "est2genome"
 options[:min_identity] = 90
-options[:extract_found_contigs] = false
-options[:arm_selection] = arm_selection_functions[:arm_selection_embl] ;
+options[:extract_found_contigs] = true
+options[:arm_selection] = Bio::PolyploidTools::ChromosomeArm.getArmSelection("nrgene")
 options[:genomes_count] = 3
-
+options[:variation_free_region] =0 
 
 options[:primer_3_preferences] = {
       :primer_product_size_range => "50-150" ,
@@ -200,11 +149,14 @@ options[:primer_3_preferences] = {
   }
 
 
+options[:database]  = false 
+
+
 OptionParser.new do |opts|
   
-  opts.banner = "Usage: find_homoeologue_variations.rb [options]"
+  opts.banner = "Usage: polymarker_deletions.rb [options]"
 
-  opts.on("-c", "--sequences FASTA", "Sequence of the region to searc") do |o|
+  opts.on("-m", "--sequences FASTA", "Sequence of the region to search") do |o|
     options[:sequences] = o
   end
   opts.on("-r", "--reference FASTA", "reference with the contigs") do |o|
@@ -221,6 +173,14 @@ OptionParser.new do |opts|
   opts.on("-x", "--extract_found_contigs", "If present, save in a separate file the contigs with matches. Useful to debug.") do |o|
     options[:extract_found_contigs] = true
   end
+
+  opts.on("-d", "--database PREFIX", "Path to the blast database. Only used if the aligner is blast. The default is the name of the contigs file without extension.") do |o|
+    options[:database] = o
+  end
+
+    opts.on("-a", "--arm_selection #{Bio::PolyploidTools::ChromosomeArm.getValidFunctions.join('|')}", "Function to decide the chromome arm") do |o|
+    options[:arm_selection] = Bio::PolyploidTools::ChromosomeArm.getArmSelection(o)
+  end
   
 end.parse!
 #reference="/Users/ramirezr/Documents/TGAC/references/Triticum_aestivum.IWGSP1.21.dna_rm.genome.fa"
@@ -231,11 +191,14 @@ throw raise Exception.new(), "Fasta file with sequences has to be provided" unle
 output_folder = options[:output] if options[:output]
 throw raise Exception.new(), "An output directory has to be provided" unless output_folder
 model=options[:model] 
+
+options[:database] = options[:reference] unless  options[:database] 
+
 Dir.mkdir(output_folder)
 min_identity= options[:min_identity]
 
 exonerate_file="#{output_folder}/exonerate_tmp.tab"
-temp_contigs="#{output_folder}/contigs_tmp.fa"
+
 primer_3_input="#{output_folder}/primer_3_input_temp"
 primer_3_output="#{output_folder}/primer_3_output_temp"
 exons_filename="#{output_folder}/exons_genes_and_contigs.fa"
@@ -248,14 +211,8 @@ fasta_file.load_fai_entries
 original_name="A"
 snp_in="B"
 
- arm_selection = options[:arm_selection]
+arm_selection = options[:arm_selection]
 
-unless arm_selection
-   arm_selection = lambda do | contig_name |
-      ret = contig_name[0,3]       
-      return ret
-    end
-end
 begin
 log "Reading exons"
 exons = Array.new
@@ -279,22 +236,28 @@ end
 log "Searching markers in genome"
 found_contigs = Set.new
 exo_f = File.open(exonerate_file, "w")
-contigs_f = File.open(temp_contigs, "w") if options[:extract_found_contigs]
-Bio::DB::Exonerate.align({:query=>sequences, :target=>reference, :model=>model}) do |aln|
-	if aln.identity > min_identity
+
+def do_align(aln, exo_f, found_contigs, min_identity,fasta_file,options)
+  if aln.identity > min_identity
     exo_f.puts aln.line
     unless found_contigs.include?(aln.target_id) #We only add once each contig. Should reduce the size of the output file. 
       found_contigs.add(aln.target_id)
       entry = fasta_file.index.region_for_entry(aln.target_id)
       raise ExonerateException.new,  "Entry not found! #{aln.target_id}. Make sure that the #{target_id}.fai was generated properly." if entry == nil
-      region = entry.get_full_region
-      seq = fasta_file.fetch_sequence(region)
-      contigs_f.puts(">#{aln.target_id}\n#{seq}") if options[:extract_found_contigs]
+
     end
   end  
 end
+
+Bio::DB::Blast.align({:query=>sequences, :target=>options[:database], :model=>model, :max_hits=>options[:max_hits]}) do |aln|
+  do_align(aln, exo_f, found_contigs,min_identity, fasta_file,options)
+end if options[:aligner] == :blast
+
+Bio::DB::Exonerate.align({:query=>sequences, :target=>target, :model=>model}) do |aln|
+  do_align(aln, exo_f, found_contigs, min_identity,fasta_file,options)
+end if options[:aligner] == :exonerate
+
 exo_f.close() 
-contigs_f.close() if options[:extract_found_contigs]
 
 
 
@@ -303,18 +266,24 @@ log "Reading best alignment on each chromosome"
 container= Bio::PolyploidTools::ExonContainer.new
 container.flanking_size=options[:flanking_size] 
 container.gene_models(sequences)
-container.chromosomes(temp_contigs)
+container.chromosomes(reference)
 container.add_parental({:name=>"A"})
 container.add_parental({:name=>"B"})
 exons.each do |exon|
   exon.container = container
-  exon.flanking_size = 50
+  exon.flanking_size = 200
   exon.variation_free_region = options[:variation_free_region]
-#  puts exon.inspect
+  #puts exon.inspect
   container.add_snp(exon)
 
 end
-container.add_alignments({:exonerate_file=>exonerate_file, :arm_selection=>options[:arm_selection] , :min_identity=>min_identity})
+container.add_alignments(
+  {:exonerate_file=>exonerate_file, 
+  :arm_selection=>options[:arm_selection] , 
+  :min_identity=>min_identity})
+
+
+
 
 #4.1 generating primer3 file
 log "Running primer3"
@@ -348,18 +317,14 @@ exons.each do |snp|
 end
 
 kasp_container.add_primers_file(primer_3_output) if added_exons > 0
-header = "Marker,SNP,RegionSize,chromosome,total_contigs,contig_regions,SNP_type,#{original_name},#{snp_in},common,primer_type,orientation,#{original_name}_TM,#{snp_in}_TM,common_TM,selected_from,product_size,errors"
+header = "Marker,SNP,RegionSize,chromosome,total_contigs,contig_regions,SNP_type,#{original_name},#{snp_in},common,primer_type,orientation,#{original_name}_TM,#{snp_in}_TM,common_TM,selected_from,product_size,errors,repetitive,blast_hits"
 File.open(output_primers, 'w') { |f| f.write("#{header}\n#{kasp_container.print_primers}") }
 
-kasp_container.snp_hash.each_pair do |name, kaspSNP|  
-  #puts kaspSNP.snp_from.surrounding_exon_sequences.inspect
-  #puts kaspSNP.first_product
-  #puts kaspSNP.realigned_primers
-
-  out_fasta_products = "#{output_folder}/#{name}.fa"
-  File.open(out_fasta_products, 'w') { |f| f.write(kaspSNP.realigned_primers_fasta) }
-
-
+out_fasta_products = "#{output_folder}/products.fa"
+File.open(out_fasta_products, 'w') do  |f|
+  kasp_container.snp_hash.each_pair do |name, kaspSNP|  
+    f.write(kaspSNP.realigned_primers_fasta) 
+  end
 end
 
 File.open(output_to_order, "w") { |io|  io.write(kasp_container.print_primers_with_tails()) }