bio-polyploid-tools 0.7.2 → 0.7.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: ca90e857f0fdaba3446c19387aea4d2c58a1b450
-  data.tar.gz: 4d52a29b06d2eb283b1b4233e95172231b09ce02
+  metadata.gz: adcaebc142757300631df98a5f672cae5dc76cb7
+  data.tar.gz: 05e3acefabb42d5ea3c84236f4b79ebf338c6306
 SHA512:
-  metadata.gz: e07d9eeff0771a1d77d9fe1568b48c1cb0fd485fa79f0ae9c8e1932e8400b8e40b43291495da27490fc86bd721077902b8b1d5e90846b69799c4e16b8fb8cdd2
-  data.tar.gz: f81e1c0cf94ae0b0c77ca29d69f0a6b44919e70965b5c2b9cb0c55c065803e2c01e85954b051d2f6ff1900cc61e5eb385409a23d8e90818e0a39f9fa0db27d36
+  metadata.gz: c1fa0e9e177bad1633fc5c4d3fd3f3fe2c2b4fc9915dfeeea943d7559d8850061f9437f703a7fa462163eb7f52431b747216d540ed73e64559ca20cfc7fe471b
+  data.tar.gz: 4db9d4d8b404378b39af64978d82671d94b5babc42ea4542c9f76b880793c23a5283945dffc4d76d2ba68761c3d30e1b434f867513e8a71c3f60f61b3885cf58

data/README.md

@@ -69,12 +69,16 @@ arm_selection_functions[:arm_selection_embl] = lambda do | contig_name|
 end
 ```
 
-The function should return a 2 character string, when the first is the chromosome number and the second the chromosome group. The symbol in the hash is the name to be used in the argument ```--arm_selection```.  If you want your parser to be added to the distribution, feel free to fork and make a pull request. 
+The function should return a 2 character string, when the first is the chromosome number and the second the chromosome group. The symbol in the hash is the name to be used in the argument ```--arm_selection```.  If you want your parser to be added to the distribution, feel free to fork and make a pull request.  
 
 
 
 ##Release Notes
 
+###0.7.3
+* FEATURE: ```polymarker.rb``` Added to the flag ```--arm_selection``` the option ```scaffold```, which now supports a scaffold specific primer.
+* FEATURE: ```snp_position_to_polymarker``` Added the option ```--mutant_list```  to prepare files for PolyMarker from files with the following columns ```ID,Allele_1,position,Allele_1,target_chromosome```. 
+
 ###0.7.2
 * FEATURE: Added a flag ```min_identity``` to set the minimum identity to consider a hit. The default is 90
 

data/VERSION

@@ -1 +1 @@
-0.7.2
+0.7.3

data/bin/markers_in_region.rb

@@ -24,7 +24,7 @@ markers = nil
 options = {}
 OptionParser.new do |opts|
   
-  opts.banner = "Usage: polymarker.rb [options]"
+  opts.banner = "Usage: markers_in_region.rb [options]"
 
   opts.on("-c", "--chromosome CHR", "chromosome (1A, 3B, etc)") do |o|
     options[:chromosome] = o.upcase

data/bin/polymarker.rb

@@ -37,6 +37,11 @@ arm_selection_functions[:arm_selection_morex] = lambda do | contig_name |
   return ret
 end
 
+arm_selection_functions[:scaffold] = lambda do | contig_name |
+  ret = contig_name;       
+  return ret
+end
+
 def validate_files(o)
 
   [
@@ -113,7 +118,7 @@ OptionParser.new do |opts|
      options[:model] = o
   end
 
-  opts.on("-a", "--arm_selection arm_selection_embl|arm_selection_morex|arm_selection_first_two", "Function to decide the chromome arm") do |o|
+  opts.on("-a", "--arm_selection arm_selection_embl|arm_selection_morex|arm_selection_first_two|scaffold", "Function to decide the chromome arm") do |o|
     options[:arm_selection] = arm_selection_functions[o.to_sym];
    end
   

data/bin/snp_position_to_polymarker.rb

@@ -24,12 +24,14 @@ 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
@@ -40,6 +42,11 @@ OptionParser.new do |opts|
   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.\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"
@@ -49,16 +56,28 @@ 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(options[:snp_file]) do | f |
+File.open(test_file) do | f |
   f.each_line do | line |
     	snp = nil
-    	snp = Bio::PolyploidTools::SNP.parse(line)
-    	entry = fasta_reference_db.index.region_for_entry(snp.gene)
+      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
+    	
     	if entry
-       		region = fasta_reference_db.index.region_for_entry(snp.gene).get_full_region
-       		snp.template_sequence = fasta_reference_db.fetch_sequence(region)
-
+       		region = entry.get_full_region
+       		if region != lastRegion
+             lastTemplate = fasta_reference_db.fetch_sequence(region)
+          end
+          snp.template_sequence = lastTemplate
+          lastRegion = region
        		out.puts "#{snp.gene}_#{snp.snp_id_in_seq},#{snp.chromosome},#{snp.to_polymarker_sequence(options[:flanking_size])}"
     	else
     	   $stderr.puts "ERROR: Unable to find entry for #{snp.gene}"

data/bio-polyploid-tools.gemspec

@@ -2,16 +2,16 @@
 # DO NOT EDIT THIS FILE DIRECTLY
 # Instead, edit Jeweler::Tasks in Rakefile, and run 'rake gemspec'
 # -*- encoding: utf-8 -*-
-# stub: bio-polyploid-tools 0.7.2 ruby lib
+# stub: bio-polyploid-tools 0.7.3 ruby lib
 
 Gem::Specification.new do |s|
   s.name = "bio-polyploid-tools"
-  s.version = "0.7.2"
+  s.version = "0.7.3"
 
   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 = "2015-05-28"
+  s.date = "2015-08-10"
   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", "filter_exonerate_by_identity.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", "snp_position_to_polymarker.rb", "snps_between_bams.rb"]

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: bio-polyploid-tools
 version: !ruby/object:Gem::Version
-  version: 0.7.2
+  version: 0.7.3
 platform: ruby
 authors:
 - Ricardo H.  Ramirez-Gonzalez
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-05-28 00:00:00.000000000 Z
+date: 2015-08-10 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bio