bio-polyploid-tools 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 2d32372b6eef65b23de3a9c669bb6f7dfb178882
+  data.tar.gz: c83526572adf6c745dd0785eb610aa18b6d7aab8
+SHA512:
+  metadata.gz: 2994977ba9b126e2cdc27c2e511abc23d1a08677f8fd5e6d5641ab877a0e0ae38a58a03036e1c4d41b1e8225454ae08fa44ec9e93ec96cec9c3bdaab29cf65e5
+  data.tar.gz: fe025cdaa7b49550d675cdc901855f35ac3e1170ac39a2d444a8fadb785f0cf6e40f64c97c335d247b52d5dcac4a790a1b3b8019456efa232fc97e04a052fdd8

data/Gemfile

@@ -0,0 +1,16 @@
+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 "rake"
+gem "jeweler"
+
+#gem "systemu", ">=2.5.2"
+
+group :development do
+#  gem "shoulda", ">= 0"
+#  gem "shoulda-context"
+#  gem	 "shoulda-matchers"
+end

data/Gemfile.lock

@@ -0,0 +1,67 @@
+GEM
+  remote: http://rubygems.org/
+  specs:
+    addressable (2.3.6)
+    atomic (1.1.16)
+    bio (1.4.2)
+    bio-samtools (0.6.2)
+      bio (>= 1.4.2)
+      ffi
+      systemu (>= 2.5.2)
+    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)
+      descendants_tracker (~> 0.0.1)
+      faraday (~> 0.8, < 0.10)
+      hashie (>= 1.2)
+      multi_json (>= 1.7.5, < 2.0)
+      nokogiri (~> 1.6.0)
+      oauth2
+    hashie (2.0.5)
+    highline (1.6.21)
+    jeweler (2.0.1)
+      builder
+      bundler (>= 1.0)
+      git (>= 1.2.5)
+      github_api
+      highline (>= 1.6.15)
+      nokogiri (>= 1.5.10)
+      rake
+      rdoc
+    json (1.8.1)
+    jwt (0.1.11)
+      multi_json (>= 1.5)
+    mini_portile (0.5.3)
+    multi_json (1.9.2)
+    multi_xml (0.5.5)
+    multipart-post (2.0.0)
+    nokogiri (1.6.1)
+      mini_portile (~> 0.5.0)
+    oauth2 (0.9.3)
+      faraday (>= 0.8, < 0.10)
+      jwt (~> 0.1.8)
+      multi_json (~> 1.3)
+      multi_xml (~> 0.5)
+      rack (~> 1.2)
+    rack (1.5.2)
+    rake (10.2.2)
+    rdoc (4.1.1)
+      json (~> 1.4)
+    systemu (2.6.0)
+    thread_safe (0.3.1)
+      atomic (>= 1.1.7, < 2)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  bio (= 1.4.2)
+  bio-samtools (= 0.6.2)
+  jeweler
+  rake

data/README

@@ -0,0 +1,21 @@
+= bio-polyploid-tools
+
+== Introduction
+This tools are designed to deal with polyploid wheat. The first tool is to design KASPer primers, making them as specific as possible. 
+
+
+== Installation
+'gem install bio-polyploid-tools'
+
+
+== Notes
+
+* If the SNP is in a gap in the alignmetn to the chromosomes, it is ignored. 
+
+BUG: Sometimes the primers are reversed (the first comes second)
+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 file to tweak the alignments. 
+
+

data/Rakefile

@@ -0,0 +1,61 @@
+require 'rubygems'
+require 'bundler'
+#
+#require 'bundler/version'
+
+begin
+  Bundler.setup(:default, :development)
+  rescue Bundler::BundlerError => e
+  $stderr.puts e.message
+  $stderr.puts "Run `bundle install` to install missing gems"
+  exit e.status_code
+end
+require 'rake'
+
+require 'jeweler'
+
+Jeweler::Tasks.new do |gem|
+  # gem is a Gem::Specification... see http://docs.rubygems.org/read/chapter/20 for more options
+   gem.name = "bio-polyploid-tools"
+  gem.homepage = "http://github.com/tgac/bioruby-polyploid-tools"
+  gem.license = "MIT"
+  gem.summary = %Q{Tool to work with polyploids, NGS and molecular biology}
+  gem.description = %Q{Repository of tools developed in TGAC and Crop Genetics in JIC to work with polyploid wheat}
+   gem.email = "ricardo.ramirez-gonzalez@tgac.ac.uk"
+  gem.authors = ["Ricardo H.  Ramirez-Gonzalez"]
+  # Include your dependencies below. Runtime dependencies are required when using your gem,
+  # and development dependencies are only needed for development (ie running rake tasks, tests, etc)
+  #gem.add_runtime_dependency 'bio-samtools', '= 0.6.2'
+  #  gem.add_development_dependency 'rspec', '> 1.2.3'
+#  gem.extensions = "ext/mkrf_conf.rb"
+end
+Jeweler::RubygemsDotOrgTasks.new
+
+require 'rake/testtask'
+Rake::TestTask.new(:test) do |test|
+  test.libs << 'lib' << 'test'
+  test.pattern = 'test/**/test_*.rb'
+  test.verbose = true
+end
+
+
+if RUBY_VERSION.start_with?("1.8")
+  require 'rcov/rcovtask'
+  Rcov::RcovTask.new do |test|
+    test.libs << 'test'
+    test.pattern = 'test/**/test_*.rb'
+    test.verbose = true
+  end
+end
+
+task :default => :test
+
+#require 'rdoc/task'
+##RDoc::Task.new do |rdoc|
+#  version = File.exist?('VERSION') ? File.read('VERSION') : ""
+
+#  rdoc.rdoc_dir = 'rdoc'
+#  rdoc.title = "bio-samtools #{version}"
+#  rdoc.rdoc_files.include('README*')
+#  rdoc.rdoc_files.include('lib/**/*.rb')
+#end

data/VERSION

@@ -0,0 +1 @@
+0.1.0

data/bin/bfr.rb

@@ -0,0 +1,133 @@
+require 'rubygems'
+#require 'extensions/all'
+require 'bio-samtools'
+require 'optparse'
+
+$: << File.expand_path(File.dirname(__FILE__) + '/../lib')
+$: << File.expand_path('.')
+path=File.expand_path(File.dirname(__FILE__) + '/../lib/bioruby-polyploid-tools.rb')
+$stderr.puts "Loading: #{path}"
+require path
+
+options = {}
+
+options[:chunk] = 0
+options[:chunk_size] = 0
+options[:bucket] = 1
+
+OptionParser.new do |opts|
+  opts.banner = "Usage: bfr.rb [options]"
+  
+  opts.on("-r", "--reference FILE", "Fasta file with the reference sequence. Make sure to run faidx before running bfr in parallel") do |o|
+     options[:reference] = o
+   end
+   
+  opts.on("-a", "--parent_1 FILE", "Sorted BAM file with the alginments from parental 1") do |o|
+    options[:parent_1] = o
+  end
+  
+  opts.on("-b", "--parent_2 FILE", "Sorted BAM file with the alginments from parental 2") do |o|
+    options[:parent_2] = o
+  end
+  
+  opts.on("-c", "--bulk_1 FILE", "Sorted BAM file with the alginments from bulk1 1 (corresponding to the phenotype of parental 1)") do |o|
+    options[:bulk_1] = o
+  end
+  
+  opts.on("-d", "--bulk_2 FILE", "Sorted BAM file with the alginments from bulk1 2 (corresponding to the phenotype of parental 2)") do |o|
+    options[:bulk_2] = o
+  end
+  
+  opts.on("-o", "--bfr FILE", "Output file with the BFRs in the chunck") do |o|
+    options[:output_filename] = o
+  end
+
+  opts.on("-s", "--stats FILE", "Output with the summary of the run. Only writes at the end, so in principle, paralell process should be able to write on it to get a status of how much has been completed.") do |o|
+    options[:stats_file] = o
+  end
+  opts.on("-d", "--bulk_2 FILE", "Sorted BAM file with the alginments from bulk1 2 (corresponding to the phenotype of parental 2)") do |o|
+    options[:bulk_2] = o
+  end
+  
+  opts.on("-m", "--chunk_size FILE", "Sorted BAM file with the alginments from bulk1 2 (corresponding to the phenotype of parental 2)") do |o|
+    options[:chunk_size] = o.to_i
+  end
+  
+  opts.on("-n", "--chunk FILE", "Sorted BAM file with the alginments from bulk1 2 (corresponding to the phenotype of parental 2)") do |o|
+    options[:chunk] = o.to_1
+  end
+  
+    
+end.parse!
+
+p options
+p ARGV
+
+
+reference = options[:reference] 
+chunk =  options[:chunk] 
+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]
+
+
+bulk_1 = options[:bulk_1]
+bulk_2 = options[:bulk_2]
+
+
+fasta_db = Bio::DB::Fasta::FastaFile.new(reference)
+fasta_db.load_fai_entries
+
+
+if chunk_size == 0
+  min = 0
+  max = fasta_db.index.entries.size
+end
+
+container = Bio::BFRTools::BFRContainer.new
+
+container.reference reference
+container.parental_1  ( {:path => parental_1 } )
+container.parental_2  ( {:path => parental_2 } )
+container.bulk_1 ( {:path => bulk_1  })
+container.bulk_2 ( {:path => bulk_2  })
+
+i = -1
+
+container.init_counters
+output_file =  File.open(output_filename, "w")
+puts "Range: #{min}:#{max}"
+fasta_db.index.entries.each do | r |
+  i = i  + 1
+  #puts r
+  #puts i
+  next if i < min or i >= max 
+  container.process_region({:region => r.get_full_region.to_s,:output_file => output_file } )
+  #puts "Processed"
+end
+output_file.close
+
+file_h = nil
+if !File.exists? stats_file
+  file_h = File.open(stats_file, "w")
+  container.print_header({:output_file_stats => file_h})
+else
+  file_h =  File.open(stats_file, "a")
+end
+container.print_stats({:output_file_stats => file_h})
+
+file_h.close

data/bin/count_variations.rb

@@ -0,0 +1,36 @@
+#!/usr/bin/env ruby
+
+require 'bio'
+require 'rubygems'
+require 'pathname'
+require 'bio-samtools'
+
+require 'set'
+
+$: << File.expand_path(File.dirname(__FILE__) + '/../lib')
+$: << File.expand_path('.')
+path= File.expand_path(File.dirname(__FILE__) + '/../lib/bioruby-polyploid-tools.rb')
+require path
+
+puts  ARGV[0]
+
+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]})
+
+fasta_db.index.entries.each do | r |
+  #Np r.get_full_region
+  #container.process_region( { :region => r.get_full_region.to_s, :output_file => output_file } )
+  region=r.get_full_region
+  
+  
+
+  cons_1 = bam1.consensus_with_ambiguities({:region=>region, :case=>true})
+
+  snps = cons_1.count_ambiguities
+ 
+  snps_per_1k = (1000 * snps.to_f ) / region.size
+  
+  puts "#{r.id}\t#{region.size}\t#{snps}\t#{snps_per_1k}\n#{cons_1}"
+  
+end

data/bin/filter_blat_by_target_coverage.rb

@@ -0,0 +1,15 @@
+#!/usr/bin/env ruby
+require 'bio'
+$: << File.expand_path(File.dirname(__FILE__) + '/../lib')
+$: << File.expand_path('.')
+path= File.expand_path(File.dirname(__FILE__) + '/../lib/bioruby-polyploid-tools.rb')
+require path
+
+blat_file=ARGV[0]
+
+blat_aln = Bio::Blat::Report.new(Bio::FlatFile.open(blat_file).to_io)
+blat_aln.each_hit() do |hit|
+  if hit.percentage_covered >= 50
+    puts hit.data.join("\t")
+  end
+end

data/bin/find_best_blat_hit.rb

@@ -0,0 +1,32 @@
+#!/usr/bin/env ruby
+require 'bio'
+
+def load_blat_alignments (blat_filename, best_aln)
+  blat_aln = Bio::Blat::Report.new(Bio::FlatFile.open(blat_filename).to_io)
+  blat_aln.each_hit() do |hit|
+    current_matches = hit.match 
+    current_name = hit.query_id
+    current_identity = hit.percent_identity
+    current_score = hit.score
+    #p current_name
+
+    best = best_aln[current_name]
+
+    if best == nil 
+      best_aln[current_name] = hit
+    else
+      if current_score > best.score
+        best_aln[current_name] = hit
+      end
+    end
+  end
+end
+
+blat_file=ARGV[0]
+best_aln = Hash.new
+
+load_blat_alignments( blat_file,best_aln)
+puts "QUERY\tTARGET"
+best_aln.each do |k, hit|
+  puts "#{k}\t#{hit.target_id}"
+end

data/bin/hexaploid_primers.rb

@@ -0,0 +1,168 @@
+#!
+require 'bio'
+require 'rubygems'
+require 'pathname'
+require 'bio-samtools'
+
+require 'set'
+
+$: << File.expand_path(File.dirname(__FILE__) + '/../lib')
+$: << File.expand_path('.')
+path= File.expand_path(File.dirname(__FILE__) + '/../lib/bioruby-polyploid-tools.rb')
+require path
+
+
+#TODO: Use temporary files somewhere in the file system and add traps to delete them/forward them as a result. 
+#TODO: Make all this parameters
+path_to_contigs="/Users/ramirezr/Documents/PHD/201305_Databases/iwgcs"
+#path_to_contigs=path_to_chromosomes
+snp_in="A"
+original_name="B"
+fasta_reference = nil
+#test_file="/Users/ramirezr/Dropbox/JIC/PrimersToTest/test_primers_nick_and_james_1.csv"
+test_file=ARGV[0]
+fasta_reference = ARGV[1] if ARGV[1]
+output_folder="#{test_file}_primer_design_#{Time.now.strftime('%Y%m%d-%H%M%S')}/"
+Dir.mkdir(output_folder)
+#TODO Make this tmp files
+temp_fasta_query="#{output_folder}to_align.fa"
+temp_contigs="#{output_folder}contigs_tmp.fa"
+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"
+
+primer_3_config=File.expand_path(File.dirname(__FILE__) + '/../conf/primer3_config')
+model="est2genome"
+
+
+min_identity= 92
+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.load_fai_entries
+  p "Fasta reference: #{fasta_reference}"
+end
+
+
+#1. Read all the SNP files 
+#All the SNPs should be on the same chromosome as the first SNP. 
+chromosome = nil
+File.open(test_file) do | f |
+  f.each_line do | line |
+    # p line.chomp!
+    snp = nil
+    if ARGV.size == 1 #List with Sequence
+      snp = Bio::PolyploidTools::SNPSequence.parse(line)  
+    elsif ARGV.size == 2 #List and fasta file
+      snp = Bio::PolyploidTools::SNP.parse(line)
+      region = fasta_reference_db.index.region_for_entry(snp.gene).get_full_region
+      snp.template_sequence = fasta_reference_db.fetch_sequence(region)
+    else
+      rise Bio::DB::Exonerate::ExonerateException.new "Wrong number of arguments. " 
+    end
+    rise Bio::DB::Exonerate::ExonerateException.new "No SNP for line '#{line}'" if snp == nil
+    snp.snp_in = snp_in
+    snp.original_name = original_name
+    snps << snp
+    chromosome = snp.chromosome unless chromosome
+    raise Bio::DB::Exonerate::ExonerateException.new "All the snps should come from the same chromosome" if chromosome != snp.chromosome
+  end
+end
+
+#1.1 Close fasta file
+#fasta_reference_db.close() if fasta_reference_db
+#2. Generate all the fasta files
+
+written_seqs = Set.new
+file = File.open(temp_fasta_query, "w")
+snps.each do |snp|
+  unless written_seqs.include?(snp.gene)
+    written_seqs << snp.gene 
+    file.puts snp.to_fasta
+  end
+end
+file.close
+
+#3. Run exonerate on each of the possible chromosomes for the SNP
+puts chromosome
+chr_group = chromosome[0]
+exo_f = File.open(exonerate_file, "w")
+contigs_f = File.open(temp_contigs, "w")
+Dir.foreach(path_to_contigs) do |filename |
+  #puts filename
+  if  File.fnmatch("#{chr_group}*.fa", filename)
+    puts filename
+    target="#{path_to_contigs}/#{filename}"
+    
+    fasta_file = Bio::DB::Fasta::FastaFile.new(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
+        exo_f.puts aln.line
+        region = fasta_file.index.region_for_entry(aln.target_id).get_full_region
+        seq = fasta_file.fetch_sequence(region)
+        contigs_f.puts(">#{aln.target_id}\n#{seq}")
+      end
+      
+    end
+  end
+end
+
+exo_f.close()
+contigs_f.close()
+
+#4. Load all the results from exonerate and get the input filename for primer3
+#Custom arm selection function that only uses the first two characters. Maybe
+#we want to make it a bit more cleaver
+arm_selection = lambda do | contig_name |
+  ret = contig_name[0,2]       
+  return ret
+end
+
+container= Bio::PolyploidTools::ExonContainer.new
+container.flanking_size=100
+container.gene_models(temp_fasta_query)
+container.chromosomes(temp_contigs)
+container.add_parental({:name=>snp_in})
+container.add_parental({:name=>original_name})
+snps.each do |snp|
+  snp.container = container
+  snp.flanking_size = container.flanking_size
+  container.add_snp(snp)
+end
+container.add_alignments({:exonerate_file=>exonerate_file, :arm_selection=>arm_selection})
+
+file = File.open(exons_filename, "w")
+container.print_fasta_snp_exones(file)
+file.close
+
+file = File.open(primer_3_input, "w")
+file.puts("PRIMER_PRODUCT_SIZE_RANGE=50-150")
+file.puts("PRIMER_MAX_SIZE=25")
+file.puts("PRIMER_LIB_AMBIGUITY_CODES_CONSENSUS=1")
+file.puts("PRIMER_LIBERAL_BASE=1")
+file.puts("PRIMER_NUM_RETURN=5")
+file.puts("PRIMER_THERMODYNAMIC_PARAMETERS_PATH=#{primer_3_config}/")
+container.print_primer_3_exons(file, chromosome,snp_in)
+file.close
+
+Bio::DB::Primer3.run({:in=>primer_3_input, :out=>primer_3_output})
+
+#5. Pick the best primer and make the primer3 output
+kasp_container=Bio::DB::Primer3::KASPContainer.new
+kasp_container.line_1=snp_in
+kasp_container.line_2=original_name
+
+snps.each do |snp|
+  kasp_container.add_snp(snp) 
+end
+
+kasp_container.add_primers_file(primer_3_output)
+header = "Marker,SNP,RegionSize,SNP_type,#{snp_in},#{original_name},common,primer_type,orientation,#{snp_in}_TM,#{original_name}_TM,common_TM,selected_from,product_size"
+File.open(output_primers, 'w') { |f| f.write("#{header}\n#{kasp_container.print_primers}") }
+