bio-polymarker 1.3.2

data/bin/polymarker_deletions.rb

@@ -0,0 +1,350 @@
+#!/usr/bin/env ruby
+require 'bio'
+require 'rubygems'
+require 'pathname'
+require 'bio-samtools-wrapper'
+require 'optparse'
+require 'set'
+$: << File.expand_path(File.dirname(__FILE__) + '/../lib')
+$: << File.expand_path('.')
+path= File.expand_path(File.dirname(__FILE__) + '/../lib/bio-polymarker.rb')
+require path
+
+def log(msg)
+  time=Time.now.strftime("%Y-%m-%d %H:%M:%S.%L")
+  puts "#{time}: #{msg}"
+end
+
+
+class Bio::PolyploidTools::ExonContainer
+   def add_alignments(opts=Hash.new) 
+      opts = { :min_identity=>90 }.merge!(opts)
+      exonerate_filename = opts[:exonerate_file]
+      arm_selection = opts[:arm_selection]
+
+      unless arm_selection
+        arm_selection = lambda do | contig_name |
+          ret = contig_name[0,3]       
+          return ret
+        end
+      end
+
+      File.open(exonerate_filename) do |f|
+        f.each_line do | line |
+          record = Bio::DB::Exonerate::Alignment.parse_custom(line)
+          if  record and record.identity >= opts[:min_identity]
+            snp_array = @snp_map[record.query_id]
+            if snp_array != nil
+              snp_array.each do |snp|                            
+                if snp != nil and snp.position.between?( (record.query_start + 1) , record.query_end)
+                  begin
+                    exon = record.exon_on_gene_position(snp.position)
+                    snp.add_exon(exon, arm_selection.call(record.target_id))
+                  rescue Bio::DB::Exonerate::ExonerateException
+                    $stderr.puts "Failed for the range #{record.query_start}-#{record.query_end} for position #{snp.position}"
+                  end
+                end
+              end
+            end
+          end
+        end
+      end
+    end
+end
+
+class Bio::DB::Primer3::SNP
+  def to_s
+     "#{gene}:#{snp_from.chromosome}"
+  end
+end
+
+class Bio::DB::Primer3::Primer3Record
+
+  def best_pair
+    return @best_pair if @best_pair
+    @best_pair = nil
+    @total_caps = 100
+    @primerPairs.each do | primer |
+      capital_count = "#{primer.left.sequence}#{primer.right.sequence}".scan(/[A-Z]/).length
+      if @best_pair.nil?
+        @best_pair = primer 
+        @total_caps = capital_count
+        next
+      end
+      if capital_count < @total_caps
+        @best_pair = primer 
+        @total_caps = capital_count
+      end
+      if primer.size < @best_pair.size 
+        @best_pair = primer 
+        @total_caps = capital_count
+      end
+    end
+    
+    @best_pair
+  end
+
+#CL3339Contig1:T509C AvocetS chromosome_specific exon 4D forward 
+  def parse_header
+    @snp, @line, @type, @in, @polymorphism, @chromosome, @orientation   = self.sequence_id.split(" ")  
+    @type = @type.to_sym
+    if @in
+      @in = @in.to_sym == :exon 
+    else
+      @exon = false
+    end
+
+    if @polymorphism.to_sym == :homoeologous
+      @homoeologous = true
+    else
+      @homoeologous = false
+    end
+    @parsed = true
+    @orientation = @orientation.to_sym
+  end
+
+  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 -= product_length
+    ret
+  end
+
+  def to_s
+      "#{gene}:#{snp_from.chromosome}"
+  end
+
+   def left_primer_snp(snp)
+      tmp_primer = String.new(left_primer)
+      return tmp_primer
+    end
+
+end
+
+markers = nil
+
+options = {}
+options[:aligner] = :blast
+options[:model] = "est2genome"
+options[:min_identity] = 90
+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" ,
+      :primer_max_size => 25 , 
+      :primer_lib_ambiguity_codes_consensus => 1,
+      :primer_liberal_base => 1, 
+      :primer_num_return=>5,
+      :primer_explain_flag => 1,
+      :primer_thermodynamic_parameters_path=>File.expand_path(File.dirname(__FILE__) + '../../conf/primer3_config/') + '/'
+  }
+
+
+options[:database]  = false 
+
+
+OptionParser.new do |opts|
+  
+  opts.banner = "Usage: polymarker_deletions.rb [options]"
+
+  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|
+    options[:reference] = o
+  end
+  opts.on("-o", "--output DIR", "Directory to write the output") do |o|
+    options[:output] = o
+  end
+
+  opts.on("-g", "--genomes_count INT", "Number of genomes (default 3, for hexaploid)") do |o|
+    options[:genomes_count] = o.to_i
+  end
+
+  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"
+reference = options[:reference] if options[:reference]
+throw raise Exception.new(), "Reference has to be provided" unless reference
+sequences = options[:sequences] if options[:sequences]
+throw raise Exception.new(), "Fasta file with sequences has to be provided" unless sequences
+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"
+
+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"
+output_primers="#{output_folder}/primers.csv"
+output_to_order="#{output_folder}/primers_to_order.csv"
+
+fasta_file = Bio::DB::Fasta::FastaFile.new({:fasta=>reference})
+fasta_file.load_fai_entries
+
+original_name="A"
+snp_in="B"
+
+arm_selection = options[:arm_selection]
+
+begin
+log "Reading exons"
+exons = Array.new
+Bio::FlatFile.auto(sequences) do |ff|
+  ff.each do |entry|
+    fields = Array.new
+    fields << entry.definition
+    fields << arm_selection.call(entry.definition)
+    fields << entry.seq
+    
+    line = fields.join(",")
+    snp =  Bio::PolyploidTools::NoSNPSequence.parse(line)
+    snp.genomes_count = options[:genomes_count]
+    exons << snp
+     
+  end
+end
+
+
+
+log "Searching markers in genome"
+found_contigs = Set.new
+exo_f = File.open(exonerate_file, "w")
+
+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
+
+    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() 
+
+
+
+log "Reading best alignment on each chromosome"
+
+container= Bio::PolyploidTools::ExonContainer.new
+container.flanking_size=options[:flanking_size] 
+container.gene_models(sequences)
+container.chromosomes(reference)
+container.add_parental({:name=>"A"})
+container.add_parental({:name=>"B"})
+exons.each do |exon|
+  exon.container = container
+  exon.flanking_size = 200
+  exon.variation_free_region = options[:variation_free_region]
+  #puts exon.inspect
+  container.add_snp(exon)
+
+end
+container.add_alignments(
+  {:exonerate_file=>exonerate_file, 
+  :arm_selection=>options[:arm_selection] , 
+  :min_identity=>min_identity})
+
+
+
+
+#4.1 generating primer3 file
+log "Running primer3"
+file = File.open(exons_filename, "w")
+container.print_fasta_snp_exones(file)
+file.close
+
+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)
+file.close
+
+Bio::DB::Primer3.run({:in=>primer_3_input, :out=>primer_3_output}) if added_exons > 0
+
+#5. Pick the best primer and make the primer3 output
+log "Selecting best primers"
+kasp_container=Bio::DB::Primer3::KASPContainer.new
+kasp_container.line_1= original_name
+kasp_container.line_2= snp_in
+
+if options[:scoring] == :het_dels
+  kasp_container.scores = Hash.new
+  kasp_container.scores[:chromosome_specific] = 0
+  kasp_container.scores[:chromosome_semispecific] = 1000
+  kasp_container.scores[:chromosome_nonspecific] = 100    
+end
+
+exons.each do |snp|
+  snpk = kasp_container.add_snp(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,repetitive,blast_hits"
+File.open(output_primers, 'w') { |f| f.write("#{header}\n#{kasp_container.print_primers}") }
+
+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()) }
+
+log "DONE"
+rescue StandardError => e
+  log "ERROR\t#{e.message}"
+  $stderr.puts e.backtrace
+  raise e 
+rescue Exception => e
+  log "ERROR\t#{e.message}"
+  $stderr.puts e.backtrace
+  raise e  
+end
+#puts container.inspect 
+
+#container.snp_map.each do | gene, snp_array|
+#  snp_array.each do |e|
+ #   puts e.inspect
+#    puts e.aligned_sequences_fasta
+#  end
+#end
+

data/bin/snp_position_to_polymarker.rb

@@ -0,0 +1,101 @@
+#!/usr/bin/env ruby
+
+#This This script converts the a file with snps and positions with the header:
+#GENE,BASE,POS,SNP,Chromosome
+#  snp.gene, snp.original, snp.position, snp.snp, snp.chromosome 
+#To the input expected by polymarker
+#ID, Chromosome, sequence
+#With sequence containing the SNP in the notation "[A/T]"
+require 'bio'
+require 'optparse'
+
+$: << File.expand_path(File.dirname(__FILE__) + '/../lib')
+$: << File.expand_path('.')
+path= File.expand_path(File.dirname(__FILE__) + '/../lib/bio-polymarker.rb')
+require path
+
+
+def log(msg)
+  time=Time.now.strftime("%Y-%m-%d %H:%M:%S.%L")
+  puts "#{time}: #{msg}"
+end
+
+markers = nil
+
+options = {}
+options[:flanking_size] = 100
+test_file=''
+OptionParser.new do |opts|
+  
+  opts.banner = "Usage: snp_postion_to_polymarker.rb [options]"
+
+  opts.on("-s", "--snp_file CSV", "CSV file with the following columnns:\nID,Allele_1,position,Allele_1,target_chromosome") do |o|
+    options[:snp_file] = o
+    test_file = o 
+  end
+  opts.on("-r", "--reference FASTA", "reference with the genes/contings/marker seuqnece") do |o|
+    options[:reference] = o
+  end
+  opts.on("-o", "--out CSV", "Output file ") do |o|
+    options[:output] = o
+  end
+  opts.on("-f", "--flanking_size INT", "Flanking size around the SNP") do |o|
+    options[:flanking_size] = o.to_i
+  end
+
+  opts.on("-t", "--mutant_list FILE", "File with the list of positions with mutation and the mutation line. Example: IWGSC_CSS_1AL_scaff_1455974,Kronos2281,127,C,T\n\
+    requires --reference to get the sequence using a position") do |o|
+    options[:mutant_list] = o
+     test_file = o 
+  end
+  
+end.parse!
+#reference="/Users/ramirezr/Documents/TGAC/references/Triticum_aestivum.IWGSP1.21.dna_rm.genome.fa"
+
+fasta_reference = options[:reference] if options[:reference]
+fasta_reference_db = Bio::DB::Fasta::FastaFile.new({:fasta=>fasta_reference})
+fasta_reference_db.load_fai_entries
+
+out = $stdout
+lastRegion = nil
+lastTemplate = nil
+out = File.open(options[:output], "w") if options[:output]
+File.open(test_file) do | f |
+  f.each_line do | line |
+    	snp = nil
+      entry = nil
+      if options[:snp_file]
+    	   snp = Bio::PolyploidTools::SNP.parse(line)
+         entry = fasta_reference_db.index.region_for_entry(snp.gene)
+      elsif options[:mutant_list]
+         snp = Bio::PolyploidTools::SNPMutant.parse(line)
+         entry = fasta_reference_db.index.region_for_entry(snp.contig)
+      end
+    	#puts line
+    	if entry
+       		region = entry.get_full_region
+          snp_name = snp.snp_id_in_seq
+
+       		#if region != lastRegion
+          #  lastTemplate = fasta_reference_db.fetch_sequence(region)
+          #end
+          start, total, new_position = snp.to_polymarker_coordinates(options[:flanking_size])
+          region.start = start 
+          region.end = start + total
+          #puts region
+          local_template = fasta_reference_db.fetch_sequence(region)
+
+          snp.position = new_position
+
+          snp.template_sequence = local_template
+          lastRegion = region
+
+       		out.puts "#{snp.gene}_#{snp_name},#{snp.chromosome},#{snp.to_polymarker_sequence(options[:flanking_size])}"
+    	else
+    	   $stderr.puts "ERROR: Unable to find entry for #{snp.gene}"
+    	end
+	end
+end
+
+out.close if options[:output]
+

data/bin/snps_between_bams.rb

@@ -0,0 +1,107 @@
+#!/usr/bin/env ruby
+
+require 'bio'
+require 'rubygems'
+require 'pathname'
+require 'bio-samtools-wrapper'
+
+require 'set'
+
+$: << File.expand_path(File.dirname(__FILE__) + '/../lib')
+$: << File.expand_path('.')
+path=File.expand_path(File.dirname(__FILE__) + '/../lib/bio-polymarker.rb')
+$stderr.puts "Loading: #{path}"
+require path
+
+
+
+fasta_db = Bio::DB::Fasta::FastaFile.new( ARGV[0])
+fasta_db.load_fai_entries
+bam1 =  Bio::DB::Sam.new({:fasta=>ARGV[0], :bam=>ARGV[1]})
+bam2 =  Bio::DB::Sam.new({:fasta=>ARGV[0], :bam=>ARGV[2]})
+
+
+output_prefix = ARGV[3]
+
+block_size=1000
+
+min_cov = ARGV[4].to_i ? ARGV[4].to_i : 10
+chunk = ARGV[5].to_i
+chunk_size = ARGV[6].to_i
+
+
+
+
+main_table="#{output_prefix}_#{block_size}_#{min_cov}_table.#{chunk}.csv"
+
+table_file = File.open(main_table, "w")
+table_file.puts "gene\tlength\tsnps_1\tcalled_1\tsnps_per_#{block_size}_1\tsnps_2\tcalled_2\tsnps_per_#{block_size}_2\tsnps_tot\tsnps_per_1k_tot"
+
+hist_1= Hash.new(0)
+hist_2= Hash.new(0)
+
+fasta_file = File.open("#{output_prefix}_#{min_cov}.#{chunk}.fa", "w")
+i = -1
+min = chunk * chunk_size
+max = min + chunk_size
+
+fasta_db.index.entries.each do | r |
+  i = i  + 1
+  next if i < min or i >= max
+  #Np r.get_full_region
+  #container.process_region( { :region => r.get_full_region.to_s, :output_file => output_file } )
+  region=r.get_full_region
+
+
+  begin
+    reg_a = bam1.fetch_region({:region=>region,  :min_cov=>min_cov, :A=>1})
+    reg_b = bam2.fetch_region({:region=>region,  :min_cov=>min_cov, :A=>1})
+    cons_1 = reg_a.consensus
+    cons_2 = reg_b.consensus
+   
+
+    snps_1 = cons_1.count_ambiguities
+    snps_2 = cons_2.count_ambiguities
+    
+    called_1 = reg_a.called
+    called_2 = reg_b.called
+
+    snps_tot = Bio::Sequence.snps_between(cons_1, cons_2)
+
+    snps_per_1k_1   = (block_size * snps_1.to_f   ) / region.size
+    snps_per_1k_2   = (block_size * snps_2.to_f   ) / region.size
+    snps_per_1k_tot = (block_size * snps_tot.to_f ) / region.size
+
+    hist_1[snps_per_1k_1.to_i] += 1
+    hist_2[snps_per_1k_2.to_i] += 1
+
+    table_file.print "#{r.id}\t#{region.size}\t"
+    table_file.print "#{snps_1}\t#{called_1}\t#{snps_per_1k_1}\t"
+    table_file.print "#{snps_2}\t#{called_2}\t#{snps_per_1k_2}\t"
+    table_file.print "#{snps_tot}\t#{snps_per_1k_tot}\n"
+    fasta_file.puts ">#{r.id}_1"
+    fasta_file.puts "#{cons_1}"
+    fasta_file.puts ">#{r.id}_2"
+    fasta_file.puts "#{cons_2}"
+    
+  rescue Exception => e
+    $stderr.puts "Unable to process #{region}: #{e.to_s}"
+  end
+end
+fasta_file.close
+table_file.close
+
+hist_table="#{output_prefix}_#{block_size}_#{min_cov}_hist.#{chunk}.csv"
+hist_file = File.open(hist_table, "w")
+
+all_keys = SortedSet.new(hist_1.keys)
+all_keys.merge(hist_2.keys)
+hist_file.puts "SNPs/#{block_size}\thist_1\thist_2\n"
+all_keys.each do |k|
+  hist_file.puts "#{k}\t#{hist_1[k]}\t#{hist_2[k]}"
+end
+
+hist_file.close
+
+
+

data/bin/tag_stats.rb

@@ -0,0 +1,75 @@
+#!/usr/bin/env ruby
+require 'optparse'
+
+require 'csv'
+require 'fileutils'
+require 'tmpdir'
+require 'bio-samtools-wrapper'
+require 'bio'
+require 'descriptive_statistics'
+
+class Bio::DB::Tag
+  def set(str) 
+    @tag   = str[0..1]
+    @type  = str[3]
+    @value = str[5..-1]
+    @value = @value.to_i if @type == "i"
+  end
+end
+
+$: << File.expand_path(File.dirname(__FILE__) + '/../lib')
+$: << File.expand_path('.')
+path= File.expand_path(File.dirname(__FILE__) + '/../lib/bio-polymarker.rb')
+require path
+opts = {}
+opts[:tag] = "NH"
+opts[:bam] = nil
+opts[:out] = nil
+opts[:ref] = nil
+
+out = $stdout
+
+OptionParser.new do |o|
+  o.banner = "Usage: tag_stats.rb [options]"
+
+  o.on("-t", "--tag str", "The tag to extract (default NH)") do |o|
+    opts[:tag] = o
+  end
+
+  o.on("-b", "--bam FILE" , "BAM file with the alignments ") do |o|
+    opts[:bam] = o
+  end
+
+  o.on("-o", "--out_file CHAR", "File to save the stats") do |o|
+    opts[:out] = o
+  end
+  
+  o.on("-r", "--reference FILE", "Fasta file with the reference") do |o|
+    opts[:ref] = o
+  end
+end.parse!
+
+bam =  Bio::DB::Sam.new(fasta: opts[:ref], bam: opts[:bam])
+tag = opts[:tag]
+
+sample = File.basename(opts[:bam], '.sorted.bam')
+last_ref = ""
+values = []
+to_print = [:sum, :min, :max, :mean, :mode, :median, :q1, :q2, :q3]
+percentiles = [90, 95, 97.5, 99]
+#Add the 90, 95, 97.5 and 99 percentiles.
+out = File.open(opts[:out], "w")  if opts[:out]
+bam.view do |aln |
+  if(last_ref != aln.rname)
+    
+    desc_stats = values.descriptive_statistics
+    to_print.each    { |e| out.puts [sample, last_ref, e      , desc_stats[e]       ].join("\t")  } if(last_ref !=  "")
+    percentiles.each { |e| out.puts [sample, last_ref, "P#{e}", values.percentile(e)].join("\t")  } if(last_ref !=  "")
+    out.puts [sample, last_ref, "N", values.length].join("\t") if(last_ref !=  "")
+    values.clear
+    last_ref = aln.rname  
+  end
+  values << aln.tags[tag].value
+end
+
+out.close  if opts[:out]

data/bin/vcfLineToTable.rb

@@ -0,0 +1,56 @@
+require 'bio-samtools-wrapper'
+require 'optparse'
+
+$: << File.expand_path(File.dirname(__FILE__) + '/../lib')
+$: << File.expand_path('.')
+path=File.expand_path(File.dirname(__FILE__) + '/../lib/bio-polymarker.rb')
+
+
+
+
+def parseVCFheader(head_line="")
+	##INFO=<ID=NS,Number=1,Type=Integer,Description="Number of samples with data">
+
+	m=/##INFO=<ID=(.+),Number=(.+),Type=(.+),Description="(.+)">/.match(head_line)
+	{:id=>m[1],:number=>m[2],:type=>m[3],:desc=>m[4]}
+
+end
+
+
+header_info = Hash.new
+ARGF.each_line do |line|  
+	h = nil
+	h = parseVCFheader(line) if line.start_with? "##INFO"
+
+	header_info[h[:id]] = h[:desc] if h
+	#puts header_info.inspect
+	next if line.start_with? "##"
+	if line.start_with? "#CHROM"
+		arr = line.split
+		arr = arr.drop(9)
+		arr2 = arr.map { |s| [s.clone().prepend('Cov'), s.clone().prepend('Hap') ]}
+		#header += arr2.join("\t")
+		#puts header
+		next
+	end
+
+	line.chomp!
+		
+	vcf = Bio::DB::Vcf.new(line, arr)
+#	puts arr.join("\t") if vcf.info["TYPE"] == "snp"
+#	puts vcf.inspect
+	#pus vcf.pos.inspect
+	#next if vcf.info["AO"].to_i != 1
+	vcf.info.each_pair { |name, val| puts "#{name}\t#{val}\t#{header_info[name]}" }
+
+    arr2 = Array.new
+    puts "____"
+    i = 0
+	vcf.samples.each do |sample|
+		#puts sample.inspect
+		puts sample[1].keys.join("\t") if i == 0
+        puts sample[1].values.join("\t")
+        i+=1
+    end
+
+end