bio-alignment 0.0.2 → 0.0.3

data/README.md

@@ -82,14 +82,14 @@ Write a (simple) version of pal2nal would be something like
   end
 ```
 
-With aln1 and aln2, the library version is the shorter
+With amino acid aln1 and nucleotide aln2 loaded, the library version is the shorter
 
 ```ruby
   aln3 = aln1.pal2nal(aln2)
-  fasta3 = FastaWriter.new('nt-aln.fa')
-  aln3.each { | rec | fasta3.write(rec) }
 ```
 
+aln3 containing the codon alignment.
+
 The API documentation is online. For more code examples see ./spec/*.rb and
 ./features/*
 

data/VERSION

@@ -1 +1 @@
-0.0.2
+0.0.3

data/doc/bio-alignment-design.md

@@ -1,5 +1,7 @@
 # Bio-alignment design
 
+''A well designed library should be simple and elegant to use...''
+
 ## Introduction
 
 Biological multi-sequence alignments (MSA) are normally matrices of

data/features/codon.feature

@@ -11,4 +11,3 @@ Feature: Read codon file
     And it should write a nucleotide alignment 
     And it should write an amino acid alignment 
 
-

data/features/pal2nal-feature.rb

@@ -39,6 +39,6 @@ Then /^I should be able to generate a codon alignment$/ do
 end
 
 Then /^I should be able to generate a codon alignment directly with pal2nal$/ do
-  # pal2nal = @aln.pal2nal(@aln1)
-  pending
+  aln3 = @aln.pal2nal(@aln2)
+  aln3.sequences[1].to_s.size.should == 1615
 end

data/lib/bio-alignment/alignment.rb

@@ -1,10 +1,13 @@
 # Alignment
 
+require 'bio-alignment/pal2nal'
+
 module Bio
   module BioAlignment
 
     class Alignment
       include Enumerable
+      include Pal2Nal
 
       attr_accessor :sequences
 

data/lib/bio-alignment/codonsequence.rb

@@ -4,12 +4,13 @@ require 'bio'
 module Bio
   module BioAlignment
 
-    CODON_TABLE = Bio::CodonTable[1]  # BioRuby Eukaryote table
-
-    # Codon element for the matrix
+    # Codon element for the matrix, used by CodonSequence.
     class Codon
-      def initialize codon
+      attr_reader :codon_table
+
+      def initialize codon, codon_table = 1
         @codon = codon
+        @codon_table = codon_table
       end
 
       def gap?
@@ -17,7 +18,7 @@ module Bio
       end
 
       def undefined?
-        aa = CODON_TABLE[@codon]
+        aa = translate
         if aa == nil and not gap?
           return true
         end
@@ -30,8 +31,8 @@ module Bio
 
       # lazily convert to Amino acid (once only)
       def to_aa
-        @aa ||= CODON_TABLE[@codon]
-        if not @aa 
+        aa = translate
+        if not aa
           if gap?
             return '-'
           elsif undefined?
@@ -40,22 +41,32 @@ module Bio
             raise 'What?'
           end
         end
+        aa
+      end
+
+    private
+
+      def translate
+        @aa ||= Bio::CodonTable[@codon_table][@codon]
         @aa
       end
     end
 
     # A CodonSequence supports the concept of codons (triple
-    # nucleotides) for an alignment
+    # nucleotides) for an alignment. A codon table number can be passed
+    # in for translation of nucleotide sequences. This is the same 
+    # table used in BioRuby.
     #
     class CodonSequence
       include Enumerable
 
       attr_reader :id, :seq
-      def initialize id, seq
+      def initialize id, seq, options = { :codon_table => 1 }
         @id = id
         @seq = []
+        @codon_table = options[:codon_table]
         seq.scan(/\S\S\S/).each do | codon |
-          @seq << Codon.new(codon)
+          @seq << Codon.new(codon, @codon_table)
         end
       end
 

data/lib/bio-alignment/pal2nal.rb

@@ -0,0 +1,36 @@
+# pal2nal (protein alignment to nucleotide alignment) implementation in Ruby
+
+module Bio
+  module BioAlignment
+    module Pal2Nal
+      def pal2nal nt_aln
+        aa_aln = self
+        codon_aln = Alignment.new
+        aa_aln.each_with_index do | aaseq, i |
+          ntseq = nt_aln.sequences[i]
+          raise "pal2nal sequence IDs do not match (for #{aaseq.id} != #{ntseq.id})" if aaseq.id != ntseq.id
+          raise "pal2nal sequence size does not match (for #{aaseq.id}'s #{aaseq.to_s.size}!= #{ntseq.to_s.size * 3})" if aaseq.id != ntseq.id
+          codonseq = CodonSequence.new(ntseq.id, ntseq.seq)
+
+          codon_pos = 0
+          result = []
+          aaseq.each do | aa |
+            result <<
+              if aa.gap?
+                '---' # inject codon gap
+              else
+                codon = codonseq[codon_pos]
+                # validate codon translates to amino acid
+                raise "codon does not match amino acid (for #{aaseq.id}, position #{codon_pos}, #{codon} translates to #{codon.to_aa} instead of #{aa.to_s})" if codon.to_aa != aa.to_s
+                codon_pos += 1
+                codon.to_s
+              end
+          end
+          codon_seq = CodonSequence.new(aaseq.id, result.join(''))
+          codon_aln.sequences << codon_seq
+        end
+        codon_aln
+      end
+    end
+  end
+end

data/lib/bio-alignment/sequence.rb

@@ -9,6 +9,9 @@ module Bio
       def gap?
         @c == '-'
       end
+      def to_s
+        @c
+      end
     end
 
     # A Sequence is a simple container for String sequences/lists

data/spec/bio-alignment_spec.rb

@@ -3,7 +3,27 @@ require File.expand_path(File.dirname(__FILE__) + '/spec_helper')
 require 'bigbio'
 include Bio::BioAlignment # Namespace
 
-describe "BioAlignment" do
+describe "BioAlignment::CodonSequence" do
+  it "should support different codon tables" do
+    seq = CodonSequence.new("test", "atgcccagacgattgg")
+    seq[0].to_aa.should == "M"
+    seq[2].to_s.should == "aga"
+    seq[2].to_aa.should == "R"
+
+    seq5 = CodonSequence.new("test", "atgcccagacgattgg", :codon_table => 5)
+    seq5[2].codon_table.should == 5
+    seq5[0].to_aa.should == "M"
+    seq5[2].to_s.should == "aga"
+    seq5[2].to_aa.should == "S"
+
+    seq2 = CodonSequence.new("test", "atgcccagacgattgg", :codon_table => 2)
+    seq2[2].codon_table.should == 2
+    seq2[0].to_aa.should == "M"
+    seq2[2].to_aa.should == "*"
+  end
+end
+
+describe "BioAlignment::Alignment" do
 
   it "should allow for adding FastaRecords that contain and id and seq" do
     aln = Alignment.new
@@ -15,7 +35,7 @@ describe "BioAlignment" do
     aln.sequences.first.seq[0..15].should == "atgcccactcgattgg"
   end
 
-  it "should allow CodonSequence inputs" do
+  it "should allow CodonSequence as an input" do
     aln = Alignment.new
     fasta = FastaReader.new('test/data/fasta/codon/codon-alignment.fa')
     fasta.each do | rec |
@@ -29,4 +49,6 @@ describe "BioAlignment" do
     aln.sequences.first.seq[0].to_aa.should == "M"
     aln.sequences.first.seq[2].to_aa.should == "T"
   end
+
 end
+

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: bio-alignment
 version: !ruby/object:Gem::Version
-  version: 0.0.2
+  version: 0.0.3
   prerelease: 
 platform: ruby
 authors:
@@ -9,11 +9,11 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-02-03 00:00:00.000000000Z
+date: 2012-02-04 00:00:00.000000000Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bio-logger
-  requirement: &13944060 !ruby/object:Gem::Requirement
+  requirement: &23657180 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -21,10 +21,10 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *13944060
+  version_requirements: *23657180
 - !ruby/object:Gem::Dependency
   name: bio
-  requirement: &13932960 !ruby/object:Gem::Requirement
+  requirement: &23655840 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -32,10 +32,10 @@ dependencies:
         version: 1.4.2
   type: :runtime
   prerelease: false
-  version_requirements: *13932960
+  version_requirements: *23655840
 - !ruby/object:Gem::Dependency
   name: bio-bigbio
-  requirement: &13932060 !ruby/object:Gem::Requirement
+  requirement: &23654620 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>'
@@ -43,10 +43,10 @@ dependencies:
         version: 0.1.3
   type: :development
   prerelease: false
-  version_requirements: *13932060
+  version_requirements: *23654620
 - !ruby/object:Gem::Dependency
   name: cucumber
-  requirement: &13930840 !ruby/object:Gem::Requirement
+  requirement: &23653020 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -54,10 +54,10 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *13930840
+  version_requirements: *23653020
 - !ruby/object:Gem::Dependency
   name: rspec
-  requirement: &13929020 !ruby/object:Gem::Requirement
+  requirement: &23651800 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -65,10 +65,10 @@ dependencies:
         version: 2.3.0
   type: :development
   prerelease: false
-  version_requirements: *13929020
+  version_requirements: *23651800
 - !ruby/object:Gem::Dependency
   name: bundler
-  requirement: &13927920 !ruby/object:Gem::Requirement
+  requirement: &23650920 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -76,10 +76,10 @@ dependencies:
         version: 1.0.0
   type: :development
   prerelease: false
-  version_requirements: *13927920
+  version_requirements: *23650920
 - !ruby/object:Gem::Dependency
   name: jeweler
-  requirement: &13926060 !ruby/object:Gem::Requirement
+  requirement: &23650280 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -87,7 +87,7 @@ dependencies:
         version: 1.7.0
   type: :development
   prerelease: false
-  version_requirements: *13926060
+  version_requirements: *23650280
 description: Alignment handler for multiple sequence alignments (MSA)
 email: pjotr.public01@thebird.nl
 executables:
@@ -113,6 +113,7 @@ files:
 - lib/bio-alignment.rb
 - lib/bio-alignment/alignment.rb
 - lib/bio-alignment/codonsequence.rb
+- lib/bio-alignment/pal2nal.rb
 - lib/bio-alignment/sequence.rb
 - spec/bio-alignment_spec.rb
 - spec/spec_helper.rb
@@ -137,7 +138,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: 3814717210769440369
+      hash: -3154039158347420524
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements: