bio-polyploid-tools 0.1.0 → 0.2.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 2d32372b6eef65b23de3a9c669bb6f7dfb178882
-  data.tar.gz: c83526572adf6c745dd0785eb610aa18b6d7aab8
+  metadata.gz: 019bf8dc15f35de0be9a55567b8041f9b98ac326
+  data.tar.gz: 3e0a76bbefead5c5284c64a01b36645748a70098
 SHA512:
-  metadata.gz: 2994977ba9b126e2cdc27c2e511abc23d1a08677f8fd5e6d5641ab877a0e0ae38a58a03036e1c4d41b1e8225454ae08fa44ec9e93ec96cec9c3bdaab29cf65e5
-  data.tar.gz: fe025cdaa7b49550d675cdc901855f35ac3e1170ac39a2d444a8fadb785f0cf6e40f64c97c335d247b52d5dcac4a790a1b3b8019456efa232fc97e04a052fdd8
+  metadata.gz: 98e2d6c023ee8d89014efe65da619f0a98808c1540c3773aaef901de9f5c2338a3cc4645bdee1a3cdc430d525587c27d576d1f19e2ac8e59d7724a6efaac5901
+  data.tar.gz: 3d09c9a1972b7538eb160ee89786f9bdd3f8c52fec554da110222241767e7a17f6efd7f0f42a219fb06cd3689037fbee2ec88eeae0cb94e40333a5c491259421

data/Gemfile

@@ -2,12 +2,13 @@ source "http://rubygems.org"
 # Add dependencies required to use your gem here.
 # Example:
 #   gem "activesupport", ">= 2.3.5"
-gem "bio", "= 1.4.2"
-gem "bio-samtools", "= 0.6.2"
+
+gem "bio", ">= 1.4.3"
+gem "bio-samtools", ">= 2.0.3"
 gem "rake"
 gem "jeweler"
 
-#gem "systemu", ">=2.5.2"
+gem "systemu", ">=2.5.2"
 
 group :development do
 #  gem "shoulda", ">= 0"

data/Gemfile.lock

@@ -3,17 +3,16 @@ GEM
   specs:
     addressable (2.3.6)
     atomic (1.1.16)
-    bio (1.4.2)
-    bio-samtools (0.6.2)
+    bio (1.4.3.0001)
+    bio-samtools (2.0.3)
       bio (>= 1.4.2)
-      ffi
-      systemu (>= 2.5.2)
+      bio-svgenes (>= 0.4.1)
+    bio-svgenes (0.4.1)
     builder (3.2.2)
     descendants_tracker (0.0.4)
       thread_safe (~> 0.3, >= 0.3.1)
     faraday (0.9.0)
       multipart-post (>= 1.2, < 3)
-    ffi (1.9.3)
     git (1.2.6)
     github_api (0.11.3)
       addressable (~> 2.3)
@@ -53,7 +52,7 @@ GEM
     rake (10.2.2)
     rdoc (4.1.1)
       json (~> 1.4)
-    systemu (2.6.0)
+    systemu (2.6.4)
     thread_safe (0.3.1)
       atomic (>= 1.1.7, < 2)
 
@@ -61,7 +60,8 @@ PLATFORMS
   ruby
 
 DEPENDENCIES
-  bio (= 1.4.2)
-  bio-samtools (= 0.6.2)
+  bio (>= 1.4.3)
+  bio-samtools (>= 2.0.3)
   jeweler
   rake
+  systemu (>= 2.5.2)

data/README.md

@@ -0,0 +1,45 @@
+bio-polyploid-tools
+===================
+
+Introduction
+-------------
+This tools are designed to deal with polyploid wheat. The first tool is to design KASP primers, 
+making them as specific as possible. 
+
+
+Installation
+------------
+'gem install bio-polyploid-tools'
+
+You need to have in your $PATH the following programs:
+* [MAFFT]{http://mafft.cbrc.jp/alignment/software/}
+* [primer3]{http://primer3.sourceforge.net/releases.php}
+* [exonerate]{http://www.ebi.ac.uk/~guy/exonerate/} 
+
+The code has been developed on ruby 2.1.0, but it should work on 1.9.3 and above. 
+
+
+Polymarker
+----------
+
+To run poolymerker with the CSS wheat contigs, you need to unzip the 
+reference file [Triticum_aestivum.IWGSP1.22.dna_rm.genome.fa.gz{ftp://ftp.ensemblgenomes.org/pub/release-22/plants/fasta/triticum_aestivum/dna/}. 
+
+polymarker.rb --contigs Triticum_aestivum.IWGSP1.22.dna_rm.genome.fa --marker_list snp_list.csv --output output_folder
+
+The snp_list file must follow the convention
+<ID>,<Chromosome>,<SEQUENCE>
+with the SNP inside the sequence in the format [A/T]. As a reference, look at test/data/short_primer_design_test.csv
+
+Notes
+-----
+
+* If the SNP is in a gap in the alignment to the chromosomes, it is ignored. 
+
+BUG: Blocks with NNNs are picked and treated as semi-specific. 
+BUG: If the name of the reference have space, the ID is not chopped. ">gene_1 (G12A)" shouls be treated as ">gene_1". 
+TODO: If reading from a reference file, only get one reference to align when the region is queried several times
+TODO: Add a parameter file to configure the alignments. 
+TODO: Produce primers for products of different sizes
+
+

data/VERSION

@@ -1 +1 @@
-0.1.0
+0.2.3

data/bin/bfr.rb

@@ -1,3 +1,4 @@
+#!/usr/bin/env ruby
 require 'rubygems'
 #require 'extensions/all'
 require 'bio-samtools'
@@ -70,18 +71,12 @@ chunk_size = options[:chunk_size]
 output_filename =  options[:output_filename] 
 stats_file = options[:stats_file]
 
- 
-#reference = ARGV[6]
-
-
 
 min = chunk * chunk_size
 max = min + chunk_size
 
 
-#AvocetS
 parental_1=options[:parent_1]
-#AvocetS (Yr15)
 parental_2=options[:parent_2]
 
 
@@ -89,7 +84,7 @@ bulk_1 = options[:bulk_1]
 bulk_2 = options[:bulk_2]
 
 
-fasta_db = Bio::DB::Fasta::FastaFile.new(reference)
+fasta_db = Bio::DB::Fasta::FastaFile.new({:fasta=>reference})
 fasta_db.load_fai_entries
 
 

data/bin/count_variations.rb

@@ -14,7 +14,7 @@ require path
 
 puts  ARGV[0]
 
-fasta_db = Bio::DB::Fasta::FastaFile.new( ARGV[0])
+fasta_db = Bio::DB::Fasta::FastaFile.new( {:fasta=>ARGV[0]})
 fasta_db.load_fai_entries
 bam1 =  Bio::DB::Sam.new({:fasta=>ARGV[0], :bam=>ARGV[1]})
 

data/bin/find_best_exonerate.rb

@@ -0,0 +1,17 @@
+#!/usr/bin/env ruby
+
+
+found_cointigs = Set.new
+Bio::DB::Exonerate.align({:query=>temp_fasta_query, :target=>target, :model=>model, :chunk=>chunk, :total_chunks=>}) do |aln|
+  if aln.identity > min_identity
+    exo_f.puts aln.line
+    unless found_cointigs.include?(aln.target_id) #We only add once each contig. Should reduce the size of the output file. 
+      found_cointigs.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}")
+    end
+  end  
+end

data/bin/hexaploid_primers.rb

@@ -43,7 +43,7 @@ snps = Array.new
 #0. Load the fasta index 
 fasta_reference_db = nil
 if fasta_reference
-  fasta_reference_db = Bio::DB::Fasta::FastaFile.new(fasta_reference)
+  fasta_reference_db = Bio::DB::Fasta::FastaFile.new({:fasta=>fasta_reference})
   fasta_reference_db.load_fai_entries
   p "Fasta reference: #{fasta_reference}"
 end
@@ -99,7 +99,7 @@ Dir.foreach(path_to_contigs) do |filename |
     puts filename
     target="#{path_to_contigs}/#{filename}"
     
-    fasta_file = Bio::DB::Fasta::FastaFile.new(target)
+    fasta_file = Bio::DB::Fasta::FastaFile.new({:fasta=>target})
     fasta_file.load_fai_entries
     Bio::DB::Exonerate.align({:query=>temp_fasta_query, :target=>target, :model=>model}) do |aln|
       if aln.identity > min_identity

data/bin/homokaryot_primers.rb

@@ -82,7 +82,7 @@ snps = Array.new
 #0. Load the fasta index 
 fasta_reference_db = nil
 if reference_file
-  fasta_reference_db = Bio::DB::Fasta::FastaFile.new(reference_file)
+  fasta_reference_db = Bio::DB::Fasta::FastaFile.new({:fasta=>reference_file})
   fasta_reference_db.load_fai_entries
   p "Fasta reference: #{reference_file}"
 end

data/bin/polymarker.rb

@@ -87,7 +87,7 @@ snps = Array.new
 #0. Load the fasta index 
 fasta_reference_db = nil
 if fasta_reference
-  fasta_reference_db = Bio::DB::Fasta::FastaFile.new(fasta_reference)
+  fasta_reference_db = Bio::DB::Fasta::FastaFile.new({:fasta=>fasta_reference})
   fasta_reference_db.load_fai_entries
   p "Fasta reference: #{fasta_reference}"
 end
@@ -141,7 +141,7 @@ filename=path_to_contigs
 puts filename
 target=filename
 
-fasta_file = Bio::DB::Fasta::FastaFile.new(target)
+fasta_file = Bio::DB::Fasta::FastaFile.new({:fasta=>target})
 fasta_file.load_fai_entries
 
 found_cointigs = Set.new

data/bin/snps_between_bams.rb

@@ -15,7 +15,7 @@ require path
 
 
 
-fasta_db = Bio::DB::Fasta::FastaFile.new( ARGV[0])
+fasta_db = Bio::DB::Fasta::FastaFile.new(:fasta=>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]})
@@ -23,7 +23,7 @@ bam2 =  Bio::DB::Sam.new({:fasta=>ARGV[0], :bam=>ARGV[2]})
 
 output_prefix = ARGV[3]
 
-block_size=300
+block_size=1000
 
 min_cov = ARGV[4].to_i ? ARGV[4].to_i : 10
 chunk = ARGV[5].to_i
@@ -54,6 +54,38 @@ fasta_db.index.entries.each do | r |
 
 
   begin
+<<<<<<< HEAD
+    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}"
+    
+=======
 
     cons_1 = bam1.consensus_with_ambiguities({:region=>region, :case=>true, :min_cov=>min_cov})
     cons_2 = bam2.consensus_with_ambiguities({:region=>region, :case=>true, :min_cov=>min_cov})
@@ -62,13 +94,10 @@ fasta_db.index.entries.each do | r |
       snps_1 = cons_1.count_ambiguities
       snps_2 = cons_2.count_ambiguities
 
-      called_1 = cons_1.upper_case_count
-      called_2 = cons_2.upper_case_count
-
       snps_tot = Bio::Sequence.snps_between(cons_1, cons_2)
 
-      snps_per_1k_1   = (block_size * snps_1.to_f   ) / called_1
-      snps_per_1k_2   = (block_size * snps_2.to_f   ) / called_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
@@ -83,6 +112,7 @@ fasta_db.index.entries.each do | r |
       fasta_file.puts ">#{r.id}_2"
       fasta_file.puts "#{cons_2}"
     end
+>>>>>>> 1b60bd09fdb1b087d6cb53c643ff36e536efe4a3
   rescue Exception => e
     $stderr.puts "Unable to process #{region}: #{e.to_s}"
   end

data/bio-polyploid-tools.gemspec

@@ -2,32 +2,35 @@
 # DO NOT EDIT THIS FILE DIRECTLY
 # Instead, edit Jeweler::Tasks in Rakefile, and run 'rake gemspec'
 # -*- encoding: utf-8 -*-
-# stub: bio-polyploid-tools 0.1.0 ruby lib
+# stub: bio-polyploid-tools 0.2.3 ruby lib
 
 Gem::Specification.new do |s|
   s.name = "bio-polyploid-tools"
-  s.version = "0.1.0"
+  s.version = "0.2.3"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.require_paths = ["lib"]
   s.authors = ["Ricardo H.  Ramirez-Gonzalez"]
-  s.date = "2014-03-31"
+  s.date = "2014-04-27"
   s.description = "Repository of tools developed in TGAC and Crop Genetics in JIC to work with polyploid wheat"
   s.email = "ricardo.ramirez-gonzalez@tgac.ac.uk"
-  s.executables = ["bfr.rb", "count_variations.rb", "filter_blat_by_target_coverage.rb", "find_best_blat_hit.rb", "hexaploid_primers.rb", "homokaryot_primers.rb", "map_markers_to_contigs.rb", "markers_in_region.rb", "polymarker.rb", "snps_between_bams.rb"]
+  s.executables = ["bfr.rb", "count_variations.rb", "filter_blat_by_target_coverage.rb", "find_best_blat_hit.rb", "find_best_exonerate.rb", "hexaploid_primers.rb", "homokaryot_primers.rb", "map_markers_to_contigs.rb", "markers_in_region.rb", "polymarker.rb", "snps_between_bams.rb"]
   s.extra_rdoc_files = [
-    "README"
+    "README",
+    "README.md"
   ]
   s.files = [
     "Gemfile",
     "Gemfile.lock",
     "README",
+    "README.md",
     "Rakefile",
     "VERSION",
     "bin/bfr.rb",
     "bin/count_variations.rb",
     "bin/filter_blat_by_target_coverage.rb",
     "bin/find_best_blat_hit.rb",
+    "bin/find_best_exonerate.rb",
     "bin/hexaploid_primers.rb",
     "bin/homokaryot_primers.rb",
     "bin/map_markers_to_contigs.rb",
@@ -78,9 +81,7 @@ Gem::Specification.new do |s|
     "lib/bio/PolyploidTools/PrimerRegion.rb",
     "lib/bio/PolyploidTools/SNP.rb",
     "lib/bio/PolyploidTools/SNPSequence.rb",
-    "lib/bio/SAMToolsExtensions.rb",
     "lib/bio/db/exonerate.rb",
-    "lib/bio/db/fastadb.rb",
     "lib/bio/db/primer3.rb",
     "lib/bioruby-polyploid-tools.rb",
     "test/data/BS00068396_51.fa",
@@ -119,21 +120,24 @@ Gem::Specification.new do |s|
     s.specification_version = 4
 
     if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
-      s.add_runtime_dependency(%q<bio>, ["= 1.4.2"])
-      s.add_runtime_dependency(%q<bio-samtools>, ["= 0.6.2"])
+      s.add_runtime_dependency(%q<bio>, [">= 1.4.3"])
+      s.add_runtime_dependency(%q<bio-samtools>, [">= 2.0.3"])
       s.add_runtime_dependency(%q<rake>, [">= 0"])
       s.add_runtime_dependency(%q<jeweler>, [">= 0"])
+      s.add_runtime_dependency(%q<systemu>, [">= 2.5.2"])
     else
-      s.add_dependency(%q<bio>, ["= 1.4.2"])
-      s.add_dependency(%q<bio-samtools>, ["= 0.6.2"])
+      s.add_dependency(%q<bio>, [">= 1.4.3"])
+      s.add_dependency(%q<bio-samtools>, [">= 2.0.3"])
       s.add_dependency(%q<rake>, [">= 0"])
       s.add_dependency(%q<jeweler>, [">= 0"])
+      s.add_dependency(%q<systemu>, [">= 2.5.2"])
     end
   else
-    s.add_dependency(%q<bio>, ["= 1.4.2"])
-    s.add_dependency(%q<bio-samtools>, ["= 0.6.2"])
+    s.add_dependency(%q<bio>, [">= 1.4.3"])
+    s.add_dependency(%q<bio-samtools>, [">= 2.0.3"])
     s.add_dependency(%q<rake>, [">= 0"])
     s.add_dependency(%q<jeweler>, [">= 0"])
+    s.add_dependency(%q<systemu>, [">= 2.5.2"])
   end
 end
 

data/lib/bio/BFRTools.rb

@@ -5,252 +5,16 @@ require 'rubygems'
 #require 'bio/db/vcf'
 require 'pathname'
 #require_relative 'BIOExtensions.rb'
-require_relative 'db/fastadb.rb'
+
 
 require 'bio'
+require 'bio-samtools'
+
 require "set"
 require 'systemu'
 require 'json'
 #require 'strmask'
 
-=begin
-
-Extends the methods to be able to calculate the BFR and a consensus from the pileup
-
-=end
-
-class Bio::DB::Pileup
-
-  #attr_accessor :minumum_ratio_for_iup_consensus
-  #@minumum_ratio_for_iup_consensus = 0.20
-
-  #Returns a hash with the count of bases
-
-  def bases
-    return @bases if @bases
-    @bases = self.non_refs
-    #puts self.ref_count
-    @bases[self.ref_base.upcase.to_sym] = self.ref_count 
-    @bases
-  end
-
-  def base_coverage
-    total = 0
-    @bases.each do |k,v|
-      total += v  
-    end
-    total
-  end
-
-  def base_ratios
-    return @base_ratios if @base_ratios
-    bases = self.bases
-    @base_ratios = Hash.new
-    bases.each do |k,v| 
-      @base_ratios[k] = v.to_f/self.base_coverage.to_f 
-    end
-    @base_ratios
-  end
-
-  # returns the consensus (most frequent) base from the pileup, if there are equally represented bases returns a string of all equally represented bases in alphabetical order   
-  def consensus_iuap(minumum_ratio_for_iup_consensus)
-    minumum_ratio_for_iup_consensus
-    if @consensus_iuap.nil?
-      @consensus_iuap = self.ref_base.downcase
-      bases = self.bases
-      tmp = String.new
-      bases.each do |k,v|
-        tmp << k[0].to_s if v/self.coverage > minumum_ratio_for_iup_consensus
-      end
-      if tmp.length > 0
-        @consensus_iuap = Bio::NucleicAcid.to_IUAPC(tmp)
-      end
-    end 
-    @consensus_iuap
-  end
-end
-
-class Bio::DB::Fasta::Region
-  attr_accessor :pileup, :average_coverage, :snps, :reference, :base_ratios, :consensus, :coverages, :bases
-
-  #TODO: Debug, as it hasnt been tested in the actual code. 
-  def base_ratios_for_base(base)
-    @all_ratios = Hash.new unless @all_ratios
-    unless @all_ratios[base]
-      ratios = Array.new
-      for i in (0..region.size-1)
-        ratios << @base_ratios[i][base]
-      end
-      @all_ratios[base] = ratios
-    end
-    @all_ratios[base]
-  end
-
-end
-
-class Bio::DB::Sam::SAMException < RuntimeError
-
-end
-
-class Bio::DB::Sam
-
-
-  attr_accessor :minumum_ratio_for_iup_consensus
-  attr_reader :cached_regions
-  #attr_accessor :pileup_cache
-  @minumum_ratio_for_iup_consensus = 0.20
-
-
-  #Same as mpilup, but it caches the pileup, so if you want several operations on the same set of regions
-  #the pile for different operations, it won't execute the mpilup command several times
-  #Whenever you finish using a region, call mpileup_clear_cache to free the cache
-  #The argument Region is required, as it will be the key for the underlying hash. 
-  #We asume that the options are constant. If they are not, the cache mechanism may not be consistent. 
-  #
-  #TODO: It may be good to load partially the pileup
-  def mpileup_cached (opts={})      
-    raise SAMException.new(), "A region must be provided" unless opts[:r] or opts[:region]
-    @pileup_cache = Hash.new unless @pileup_cache
-    @cached_regions = Hash.new unless @cached_regions
-
-    region = opts[:r] ? opts[:r] : opts[:region]
-    opts[:r] = "'#{region.to_s}'"
-    opts[:region] = "'#{region.to_s}'"
-    opts[:A] = true
-    #reg = region.class == Bio::DB::Fasta::Region ? region : Bio::DB::Fasta::Region.parse_region(region.to_s)
-
-    unless @cached_regions[region.to_s]
-      @cached_regions[region.to_s] =  Bio::DB::Fasta::Region.parse_region(region.to_s)
-      tmp = Array.new
-      @cached_regions[region.to_s].pileup =  tmp
-      #puts "Loading #{region.to_s}"
-      mpileup(opts) do | pile | 
-        #   puts pile
-        tmp << pile 
-        yield pile
-      end
-    else   
-      #   puts "Loaded, reruning #{region.to_s}"
-      @cached_regions.pileup[region.to_s] .each do | pile |
-        yield pile
-      end
-    end
-  end
-
-  #Clears the pileup cache. If a region is passed as argument, just the specified region is removed
-  #If no region is passed, the hash is emptied
-  def mpileup_clear_cache (region)
-    return unless @cached_regions
-    if region
-      @cached_regions[region.to_s] = nil
-    else
-      @cached_regions.clear
-    end
-  end
-
-  #Gets the coverage of a region from a pileup. 
-  def average_coverage_from_pileup(opts={})
-    opts[:region] =   opts[:region].to_s if opts[:region] .class == Bio::DB::Fasta::Region 
-    region = opts[:region]
-    calculate_stats_from_pile(opts) if @cached_regions == nil or @cached_regions[region] == nil
-    @cached_regions[region].average_coverage
-  end
-
-  #
-  def coverages_from_pileup(opts={})
-    opts[:region] =   opts[:region].to_s if opts[:region] .class == Bio::DB::Fasta::Region 
-    region = opts[:region]
-    calculate_stats_from_pile(opts) if @cached_regions == nil or @cached_regions[region] == nil
-    @cached_regions[region].coverages
-  end
-
-  def consensus_with_ambiguities(opts={})
-    opts[:region] =   opts[:region].to_s if opts[:region] .class == Bio::DB::Fasta::Region 
-    region = opts[:region]
-    #   p "consensus with ambiguities for: " << opts[:region] 
-    calculate_stats_from_pile(opts) if @cached_regions == nil or @cached_regions[region] == nil
-    @cached_regions[region].consensus
-  end
-
-  def calculate_stats_from_pile(opts={})
-    min_cov = opts[:min_cov] ? opts[:min_cov] : 20  
-
-
-    opts[:region] = Bio::DB::Fasta::Region.parse_region( opts[:region] .to_s)  unless opts[:region].class == Bio::DB::Fasta::Region
-    region = opts[:region]
-    reference = self.fetch_reference(region.entry, region.start, region.end).downcase
-    #  p "calculationg from pile..." << region.to_s
-    base_ratios = Array.new(region.size, BASE_COUNT_ZERO) 
-    bases = Array.new(region.size, BASE_COUNT_ZERO) 
-    coverages = Array.new(region.size, 0)
-    total_cov = 0
-
-    self.mpileup_cached(:region=>"#{region.to_s}") do | pile |
-      #puts pile
-      #puts pile.coverage
-      if pile.coverage > min_cov
-        base_ratios[pile.pos - region.start ] = pile.base_ratios
-        reference[pile.pos - region.start   ] = pile.consensus_iuap(0.20)
-        coverages[pile.pos - region.start    ]  = pile.coverage.to_i
-        bases[pile.pos - region.start   ]  = pile.bases
-      end
-      total_cov += pile.coverage
-    end
-
-    region = @cached_regions[region.to_s]
-    region.coverages = coverages
-    region.base_ratios = base_ratios
-    region.consensus = reference
-
-    region.average_coverage = total_cov.to_f/region.size.to_f
-    region.bases = bases
-    region
-  end
-
-
-
-  BASE_COUNT_ZERO =  {:A => 0, :C => 0, :G => 0,  :T => 0}
-
-  #Gets an array with the proportions of the bases in the region. If there is no coverage, a
-  def base_ratios_in_region(opts={})
-    opts[:region] =   opts[:region].to_s if opts[:region] .class == Bio::DB::Fasta::Region 
-    region = opts[:region]
-    calculate_stats_from_pile(opts) if @cached_regions == nil or @cached_regions[region] == nil
-    @cached_regions[region].base_ratios 
-  end
-
-  #Gets an array with the bsaes count in the region. If there is no coverage, a
-  def bases_in_region(opts={})
-    opts[:region] =   opts[:region].to_s if opts[:region] .class == Bio::DB::Fasta::Region 
-    region = opts[:region]
-    calculate_stats_from_pile(opts) if @cached_regions == nil or @cached_regions[region] == nil
-    @cached_regions[region].bases 
-  end
-
-
-
-  def extract_reads(opts={})
-    opts[:region] = Bio::DB::Fasta::Region.parse_region( opts[:region] .to_s)  unless opts[:region].class == Bio::DB::Fasta::Region
-    fastq_filename = opts[:fastq]
-    fastq_file = opts[:fastq_file]
-
-    out = $stdout
-
-    print_fastq = Proc.new do |alignment|
-      out.puts "@#{alignment.qname}"
-      out.puts "#{alignment.seq}"
-      out.puts "+#{alignment.qname}"
-      out.puts "#{alignment.qual}"
-    end
-
-    fetch_with_function(chromosome, qstart, qstart+len,  print_fastq)
-
-
-  end
-
-
-
-end
 
 module Bio::BFRTools
   
@@ -267,7 +31,7 @@ module Bio::BFRTools
     BASES = [:A, :C, :G, :T]
     #Sets the reference file
     def reference(path)
-      @reference_db = Bio::DB::Fasta::FastaFile.new(path)
+      @reference_db = Bio::DB::Fasta::FastaFile.new({:fasta=>path})
       @reference_path = path
     end
 
@@ -350,33 +114,35 @@ module Bio::BFRTools
       self.entry = reg.entry
       self.start = reg.start
       self.end   = reg.end
-
+      opts[:region] = reg
       @container = opts[:container]
 
-      parental_1_sam = @container.parental_1_sam
-      parental_2_sam = @container.parental_2_sam
-      bulk_1_sam = @container.bulk_1_sam
-      bulk_2_sam = @container.bulk_2_sam
-
-      @parental_1_sequence = parental_1_sam.consensus_with_ambiguities(opts)
-      @parental_2_sequence = parental_2_sam.consensus_with_ambiguities(opts)
+      parental_1_reg = @container.parental_1_sam.fetch_region(opts)
+      parental_2_reg = @container.parental_2_sam.fetch_region(opts)
+      bulk_1_reg = @container.bulk_1_sam.fetch_region(opts)
+      bulk_2_reg = @container.bulk_2_sam.fetch_region(opts)
+      
+    
 
-      @bulk_1_sequence = bulk_1_sam.consensus_with_ambiguities(opts)
-      @bulk_2_sequence = bulk_2_sam.consensus_with_ambiguities(opts)
+      @parental_1_sequence = parental_1_reg.consensus
+      @parental_2_sequence = parental_2_reg.consensus
+      
+      @bulk_1_sequence = bulk_1_reg.consensus
+      @bulk_2_sequence = bulk_2_reg.consensus
 
       @snp_count = Container.snps_between( @parental_1_sequence , @parental_2_sequence )
 
-      @ratios_bulk_1 = bulk_1_sam.base_ratios_in_region(opts)
-      @ratios_bulk_2 = bulk_2_sam.base_ratios_in_region(opts)
+      @ratios_bulk_1 = bulk_1_reg.base_ratios
+      @ratios_bulk_2 = bulk_2_reg.base_ratios
 
-      @bases_bulk_1 = bulk_1_sam.bases_in_region(opts)
-      @bases_bulk_2 = bulk_2_sam.bases_in_region(opts)
+      @bases_bulk_1 = bulk_1_reg.bases
+      @bases_bulk_2 = bulk_2_reg.bases
 
-      @avg_cov_bulk_1 = bulk_1_sam.average_coverage_from_pileup(opts)
-      @avg_cov_bulk_2 = bulk_2_sam.average_coverage_from_pileup(opts)
+      @avg_cov_bulk_1 = bulk_1_reg.average_coverage
+      @avg_cov_bulk_2 = bulk_2_reg.average_coverage
 
-      @coverages_1 =  bulk_1_sam.coverages_from_pileup(opts)
-      @coverages_2 =  bulk_2_sam.coverages_from_pileup(opts)
+      @coverages_1 =  bulk_1_reg.coverages
+      @coverages_2 =  bulk_2_reg.coverages
 
     end
 
@@ -472,7 +238,7 @@ module Bio::BFRTools
         raise BFRToolsException.new ("The reference for the line should be :first or :second, but was " + reference.to_s )
       end
       
-      relative_position = self.start +  position + 1
+      relative_position = self.start +  position 
       
       bfr = bfrs[reference][base][position]
       cov_1 = @coverages_1[position]
@@ -622,7 +388,7 @@ module Bio::BFRTools
     end
 
     def process_region(opts={})        
-      opts = { :min_cov=>20, :max_snp_1kbp => 10 }.merge!(opts)
+      opts = { :min_cov=>20, :max_snp_1kbp => 10, :max_per=>0.20 }.merge!(opts)
 
       @proccesed_regions += 1
       output = opts[:output_file] ? opts[:output_file] : $stdout
@@ -675,7 +441,7 @@ module Bio::BFRTools
 
 
               for informative in info
-                line = region.get_bfr_line(i+1, base, informative)
+                line = region.get_bfr_line(i, base, informative)
                 output.print  line , "\n"
               end
             end