bio-polyploid-tools 0.8.1 → 0.8.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA256:
-  metadata.gz: 5cc3c126779f27e61f521959b82d13f240cb2ce8d5c5416e511f9150ced798eb
-  data.tar.gz: 13adf99f1336327f7b399057d66ee63892ee276ee507a398fb4a6936a2a765a2
+SHA1:
+  metadata.gz: 28167dfdf75d85d33f970351d2f9a1b166d179c7
+  data.tar.gz: f1635243148bb245ff2af217eb333ace9087a011
 SHA512:
-  metadata.gz: d345c23216e2d6aa3174885a053300ec499230125625d36fe1b5efc8de3d151b5423ad8ed5e0c563b2c9be5b07df29a759a9f95ee1196588eefa0ab2e40ec802
-  data.tar.gz: 1ed47854ec04f95c7d8449e1a15885a67f00c076b4bc07705616d6762ad7cf8822d60933cb737c71b95cbfb46293b4cb970e3d2f6413ccde70ca8e0f372e2ab4
+  metadata.gz: 1cfb4d6a3f49874f430da5bc1342b2bef31ca57cc73e4108272b8e4606426acfc303d21d9035dfcc96569988fcd6f74e35c8e60e5bcc35348ab8d6014a044e7b
+  data.tar.gz: 632d1e2488f566adb856745c9b85999b5fc8cb3e4f7326999f94fd70db7c30555e13963282785b2465ac8e6cab5d2644a06eb54a5fa1367294c99d49c30ffd60

data/.travis.yml

@@ -12,6 +12,7 @@ rvm:
   - 2.2.5
   - 2.3.5
   - 2.4.2
+  - 2.5.0
 
 before_install:
   - export RUBYOPT="-W1"

data/README.md

@@ -17,13 +17,13 @@ You need to have in your ```$PATH``` the following programs:
 * [exonerate](http://www.ebi.ac.uk/~guy/exonerate/) 
 * [blast](https://blast.ncbi.nlm.nih.gov/Blast.cgi?PAGE_TYPE%3DBlastDocs&DOC_TYPE%3DDownload)
 
-The code was originally developed on ruby 2.1.0, but it should work on 1.9.3 and above. However, it is only actively tested in currently supported ruby versions: 
+The code was originally developed on ruby 2.1, 2.3 and 2.5. It may work on older version. However, it is only actively tested in currently supported ruby versions: 
   
   * 2.1.10
   * 2.2.5
   * 2.3.5
   * 2.4.2
-
+  * 2.5.0
 
 # PolyMarker
 
@@ -102,10 +102,10 @@ This file format can be used with ```snp_positions_to_polymarker.rb``` to produc
 By default, the contigs and pseudomolecules from [ensembl](ftp://ftp.ensemblgenomes.org/pub/release-25/plants/fasta/triticum_aestivum/dna/Triticum_aestivum.IWGSC2.25.dna.genome.fa.gz
 ) are used. However, it is possible to use a custom reference. To define the chromosome where each contig belongs the argument ```arm_selection``` is used.  The defailt uses ids like: ```IWGSC_CSS_1AL_scaff_110```, where the third field, separated by underscores is used. A simple way to add costum references is to rename the fasta file to follow that convention. Another way is to use the option ```--arm_selection arm_selection_first_two```, where only the first two characters in each contig is used as identifier, useful when pseudomolecules are named after the chromosomes (ie: ">1A" in the fasta file). 
 
-If your contigs follow a different convention, in the file ```polymarker.rb``` it is possible to define new parsers, by adding at the begining, with the rest of the parsers a new lambda like:
+If your contigs follow a different convention, in the file ```ChromosomeArm.rb``` it is possible to define new parsers, by adding at the begining, with the rest of the parsers a new lambda like:
 
 ```rb
-arm_selection_functions[:arm_selection_embl] = lambda do | contig_name|
+@@arm_selection_functions[:embl] = lambda do | contig_name|
   arr = contig_name.split('_')
   ret = "U"
   ret = arr[2][0,2] if arr.size >= 3
@@ -128,6 +128,16 @@ To use blast instead of exonerate, use the following command:
 
 ## Release Notes
 
+### 0.8.2
+
+* FEATURE: The functions to select the chromosome arm are now in ```lib/bio/PolyploidTools/ChromosomeArm.rb``` and the help message is updated automatically with the valid options. 
+* FEATURE: Added option ```filter_best``` to replicate the original behaviour of selecting the best hit of each chromosome. Still useful for assemblies which still contain synthetic duplications.
+
+### 0.8.1
+
+* BUGFIX: There was an error which prevented the correct localisation of the SNP in markeres with gaps in the local alignment before the position with the snp.
+* FEATURE: PolyMarker now selects the best hit of the target chromosome. This improves the specificity in regions with a recent duplication. The drawback is that if your assembly has artificial repetitions, the primers won't be marked as 'chromosome specific', but as 'chromosome semi-specific '. In a future version this will be addressed. 
+
 ### 0.8
 
 * FEATURE: ```polymarker.rb``` added the flag ```--aligner blast|exonerate ``` which lets you pick between ```blast``` or ```exonerate``` as the aligner. For blast the default is to have the database with the same name as the ```--contigs``` file. However, it is possible to use a different name vua the option ```--database```.

data/VERSION

@@ -1 +1 @@
-0.8.1
+0.8.2

data/bin/polymarker.rb

@@ -10,43 +10,7 @@ $: << File.expand_path('.')
 path= File.expand_path(File.dirname(__FILE__) + '/../lib/bioruby-polyploid-tools.rb')
 require path
 
-arm_selection_functions = Hash.new;
 
-arm_selection_functions[:arm_selection_nrgenes] = lambda do | contig_name |
-#example format: chr2A
-  ret = contig_name[3,2]
-  return ret
-end
-
-arm_selection_functions[:arm_selection_first_two] = lambda do | contig_name |
-  contig_name.gsub!(/chr/,"")
-  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
 
 def validate_files(o)
   [
@@ -66,7 +30,7 @@ options[:chunks] = 1
 options[:bucket_size] = 0
 options[:bucket] = 1
 options[:model] = "est2genome"
-options[:arm_selection] = arm_selection_functions[:arm_selection_embl] ;
+options[:arm_selection] = Bio::PolyploidTools::ChromosomeArm.getArmSelection("nrgene");
 options[:flanking_size] = 150;
 options[:variation_free_region] = 0 
 options[:extract_found_contigs] = false
@@ -74,6 +38,7 @@ options[:genomes_count] = 3
 options[:min_identity] = 90
 options[:scoring] = :genome_specific
 options[:database]  = false
+options[:filter_best]  = false
 options[:aligner] = :exonerate
 
 
@@ -87,6 +52,8 @@ options[:primer_3_preferences] = {
       :primer_thermodynamic_parameters_path=>File.expand_path(File.dirname(__FILE__) + '../../conf/primer3_config/') + '/'
     }
 
+
+
 OptionParser.new do |opts|
   opts.banner = "Usage: polymarker.rb [options]"
 
@@ -102,6 +69,11 @@ OptionParser.new do |opts|
     options[:genomes_count] = o.to_i
   end
   
+  opts.on("-b", "--filter_best", "If set, only keep the best alignment for each chromosome") do 
+    options[:filter_best]  = true
+  end
+
+
   opts.on("-s", "--snp_list FILE", "File with the list of snps to search from, requires --reference to get the sequence using a position") do |o|
     options[:snp_list] = o
   end
@@ -127,7 +99,7 @@ OptionParser.new do |opts|
      options[:model] = o
   end
 
-  opts.on("-a", "--arm_selection arm_selection_embl|arm_selection_morex|arm_selection_first_two|scaffold", "Function to decide the chromome arm") do |o|
+  opts.on("-a", "--arm_selection #{Bio::PolyploidTools::ChromosomeArm.getValidFunctions.join('|')}", "Function to decide the chromome arm") do |o|
     tmp_str = o
     arr = o.split(",")
     if arr.size == 2
@@ -138,7 +110,7 @@ OptionParser.new do |opts|
           return ret
         end
     else
-      options[:arm_selection] = arm_selection_functions[o.to_sym];
+      options[:arm_selection] = Bio::PolyploidTools::ChromosomeArm.getArmSelection(o)
     end
 
    end
@@ -370,7 +342,11 @@ snps.each do |snp|
   snp.variation_free_region = options[:variation_free_region]
   container.add_snp(snp)
 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,
+  :filter_best=>options[:filter_best]})
 
 
 #4.1 generating primer3 file

data/bio-polyploid-tools.gemspec

@@ -2,16 +2,16 @@
 # DO NOT EDIT THIS FILE DIRECTLY
 # Instead, edit Juwelier::Tasks in Rakefile, and run 'rake gemspec'
 # -*- encoding: utf-8 -*-
-# stub: bio-polyploid-tools 0.8.1 ruby lib
+# stub: bio-polyploid-tools 0.8.2 ruby lib
 
 Gem::Specification.new do |s|
   s.name = "bio-polyploid-tools".freeze
-  s.version = "0.8.1"
+  s.version = "0.8.2"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0".freeze) if s.respond_to? :required_rubygems_version=
   s.require_paths = ["lib".freeze]
   s.authors = ["Ricardo H.  Ramirez-Gonzalez".freeze]
-  s.date = "2018-01-19"
+  s.date = "2018-01-23"
   s.description = "Repository of tools developed at Crop Genetics in JIC to work with polyploid wheat".freeze
   s.email = "ricardo.ramirez-gonzalez@jic.ac.uk".freeze
   s.executables = ["bfr.rb".freeze, "blast_triads.rb".freeze, "blast_triads_promoters.rb".freeze, "count_variations.rb".freeze, "filter_blat_by_target_coverage.rb".freeze, "filter_exonerate_by_identity.rb".freeze, "find_best_blat_hit.rb".freeze, "find_best_exonerate.rb".freeze, "find_homoeologue_variations.rb".freeze, "get_longest_hsp_blastx_triads.rb".freeze, "hexaploid_primers.rb".freeze, "homokaryot_primers.rb".freeze, "mafft_triads.rb".freeze, "mafft_triads_promoters.rb".freeze, "map_markers_to_contigs.rb".freeze, "markers_in_region.rb".freeze, "polymarker.rb".freeze, "polymarker_capillary.rb".freeze, "snp_position_to_polymarker.rb".freeze, "snps_between_bams.rb".freeze, "vcfLineToTable.rb".freeze]
@@ -172,7 +172,7 @@ Gem::Specification.new do |s|
   ]
   s.homepage = "http://github.com/tgac/bioruby-polyploid-tools".freeze
   s.licenses = ["MIT".freeze]
-  s.rubygems_version = "2.7.4".freeze
+  s.rubygems_version = "2.6.14".freeze
   s.summary = "Tool to work with polyploids, NGS and molecular biology".freeze
 
   if s.respond_to? :specification_version then

data/lib/bio/PolyploidTools/ChromosomeArm.rb

@@ -1,48 +1,51 @@
-module Bio::PolyploidTools
-  
-  class ChromosomeArm
-    attr_accessor :name
-    attr_reader :genes
-    attr_reader :loaded_entries
-    attr_reader :fasta_db
-
-    def initialize(name, path_to_fasta)
-      @name = name
-      @fasta_db = Bio::DB::Fasta::FastaFile.new({:fasta=>path_to_fasta})
-      #$stderr.puts "Loading entries for #{name}"
-      
-      @genes = Hash.new
-    end
-    
-    def fetch_contig(contig_id)
-      
-      @fasta_db.load_fai_entries unless @loaded_entries
-      @loaded_entries = true
-      entry = fasta_db.index.region_for_entry(contig_id)
-     # puts entry
-      @fasta_db.fetch_sequence(entry.get_full_region)
-    end
-
-    #Loads all the chromosome arms in a folder. 
-    #The current version requires that all the references end with .fa, and start with XXX_*.fa
-    #Where XXX is the chromosome name
-    def self.load_from_folder(path_to_contigs)
-      chromosomeArms = Hash.new
-      
-      Dir.foreach(path_to_contigs) do |filename |
-        if  File.fnmatch("*.fa", filename)
-          
-          parsed = /^(?<arm>\d\w+)/.match(filename)
-          target="#{path_to_contigs}/#{filename}"
-          #fasta_file = Bio::DB::Fasta::FastaFile.new(target)
-          #fasta_file.load_fai_entries
-          arm = ChromosomeArm.new(parsed[:arm], target)
-          chromosomeArms[arm.name] = arm
-        end
-      end
-      return chromosomeArms
-    end
-    
+class Bio::PolyploidTools::ChromosomeArm
+
+
+
+  @@arm_selection_functions = Hash.new;
+
+  #example format: chr2A
+  @@arm_selection_functions[:nrgene] = lambda do | contig_name |
+    ret = contig_name[3,2]
+    return ret
+  end
+
+  @@arm_selection_functions[:first_two] = lambda do | contig_name |
+    contig_name.gsub!(/chr/,"")
+    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[: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[: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
+
+  def self.getArmSelection(name)
+    @@arm_selection_functions[name.to_sym]
+  end
+
+  def self.getValidFunctions
+    @@arm_selection_functions.keys.map { |e| e.to_s }
   end
 
 end

data/lib/bio/PolyploidTools/ExonContainer.rb

@@ -175,9 +175,10 @@ module Bio::PolyploidTools
     end
 
     def add_alignments(opts=Hash.new) 
-      opts = { :min_identity=>90 }.merge!(opts)
+      opts = { :min_identity=>90, filter_best:false }.merge!(opts)
       exonerate_filename = opts[:exonerate_file]
       arm_selection = opts[:arm_selection]
+      filter_best = opts[:filter_best]
 
       unless arm_selection
         arm_selection = lambda do | contig_name |
@@ -197,7 +198,7 @@ module Bio::PolyploidTools
                 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))
+                    snp.add_exon(exon, arm_selection.call(record.target_id), filter_best:filter_best)
                   rescue Bio::DB::Exonerate::ExonerateException
                     $stderr.puts "Failed for the range #{record.query_start}-#{record.query_end} for position #{snp.position}"
                   end

data/lib/bio/PolyploidTools/SNP.rb

@@ -114,8 +114,14 @@ module Bio::PolyploidTools
         return ">#{self.gene}\n#{self.template_sequence}\n"
       end
 
-    def add_exon(exon, arm)
-      exon_list[arm] << exon    
+    def add_exon(exon, arm, filter_best: true)
+      if filter_best and exon_list[arm].size > 0
+        current = exon_list[arm].first
+        exon_list[arm] = [exon] if exon.record.score > current.record.score 
+      else
+         exon_list[arm] << exon 
+      end
+        
     end
 
     def covered_region

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: bio-polyploid-tools
 version: !ruby/object:Gem::Version
-  version: 0.8.1
+  version: 0.8.2
 platform: ruby
 authors:
 - Ricardo H.  Ramirez-Gonzalez
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2018-01-19 00:00:00.000000000 Z
+date: 2018-01-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bio
@@ -293,7 +293,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.7.4
+rubygems_version: 2.6.14
 signing_key: 
 specification_version: 4
 summary: Tool to work with polyploids, NGS and molecular biology