ported analyze_seq to ruby

git-svn-id: http://biopieces.googlecode.com/svn/trunk@1132 74ccb610-7750-0410-82ae-013aeee3265d

diff --git a/code_ruby/Maasha/lib/seq.rb b/code_ruby/Maasha/lib/seq.rb
index 52f7e44fa43910beee66f23c3669d5132f7cf888..039c4cec0265ee8c4c711fef2c4d6ef5a49ce72f 100644 (file)
--- a/code_ruby/Maasha/lib/seq.rb
+++ b/code_ruby/Maasha/lib/seq.rb
@@ -2,6 +2,7 @@
 DNA     = %w[a t c g]
 RNA     = %w[a u c g]
 PROTEIN = %w[f l s y c w p h q r i m t n k v a d e g]
+INDELS  = %w[.- _ ~]
 
 # Quality scores bases
 SCORE_PHRED    = 33
@@ -32,6 +33,12 @@ class Seq
 
   alias len length
 
+  # Return the number indels in a sequence.
+  def indels
+    regex = Regexp.new(/[#{Regexp.escape(INDELS.join(""))}]/)
+    self.seq.scan(regex).size
+  end
+
   # Method that returns true is a given sequence type is DNA.
   def is_dna?
     self.type == 'dna'
@@ -141,6 +148,31 @@ class Seq
     seq_new
   end
 
+  # Method that returns the residue compositions of a sequence in
+  # a hash where the key is the residue and the value is the residue
+  # count.
+  def composition
+    comp = Hash.new(0);
+
+    self.seq.upcase.each_char do |char|
+      comp[char] += 1
+    end
+
+    comp
+  end
+
+  # Method that returns the percentage of hard masked residues
+  # or N's in a sequence.
+  def hard_mask
+    ((self.seq.upcase.scan("N").size.to_f / (self.len - self.indels).to_f) * 100).round(2)
+  end
+
+  # Method that returns the percentage of soft masked residues
+  # or lower cased residues in a sequence.
+  def soft_mask
+    ((self.seq.scan(/[a-z]/).size.to_f / (self.len - self.indels).to_f) * 100).round(2)
+  end
+
   # Method to convert the quality scores from a specified base
   # to another base.
   def convert_phred2illumina!
@@ -297,14 +329,6 @@ class Seq < String
     self.replace(self.wrap(width, delimit))
   end
 
-  # Method that generates a random sequence of a given length.
-  def generate(length)
-    raise ArgumentError, "Cannot generate negative sequence length: #{length}." if length <= 0
-
-    alph = self.residues
-    Array.new(length) { alph[rand(alph.size)] }.join("")
-  end
-
   # Method that replaces sequence with a randomly generated sequence of a given length.
   def generate!(length)
     self.replace(self.generate(length))

diff --git a/code_ruby/Maasha/test/test_seq.rb b/code_ruby/Maasha/test/test_seq.rb
index a8e81666f0bf03f1fdc35f6aaf8cf4281165165b..de60d4cfe576f5d136dcd2ae35e2624d2805b9db 100755 (executable)
--- a/code_ruby/Maasha/test/test_seq.rb
+++ b/code_ruby/Maasha/test/test_seq.rb
@@ -42,11 +42,16 @@ class TestSeq < Test::Unit::TestCase
     assert(@entry.is_protein? == true)
   end
 
-  def test_Sequence_length_is_correct
+  def test_Seq_length_is_correct
     @entry.seq = 'ATCG'
     assert_equal(4, @entry.length)
   end
 
+  def test_Seq_indels_is_correct
+    @entry.seq = 'ATCG.-~_'
+    assert_equal(4, @entry.indels)
+  end
+
   def test_Seq_to_rna_raises_if_no_sequence
     @entry.type = 'dna'
     assert_raise(SeqError) { @entry.to_rna }
@@ -177,6 +182,25 @@ class TestSeq < Test::Unit::TestCase
     end
   end
 
+  def test_Seq_composition_returns_correctly
+    @entry.seq = "AAAATTTCCG"
+    assert_equal(4, @entry.composition["A"])
+    assert_equal(3, @entry.composition["T"])
+    assert_equal(2, @entry.composition["C"])
+    assert_equal(1, @entry.composition["G"])
+    assert_equal(0, @entry.composition["X"])
+  end
+
+  def test_Seq_hard_mask_returns_correctly
+    @entry.seq = "--AAAANn"
+    assert_equal(33.33, @entry.hard_mask)
+  end
+
+  def test_Seq_soft_mask_returns_correctly
+    @entry.seq = "--AAAa"
+    assert_equal(25.00, @entry.soft_mask)
+  end
+
   def test_Digest_new_raises_on_bad_pattern_residue
     assert_raise(DigestError) { Digest.new(@entry, "X", 4) }
   end