parse_fasta 1.7.1 → 1.7.2

checksums.yaml

@@ -1,15 +1,15 @@
 ---
 !binary "U0hBMQ==":
   metadata.gz: !binary |-
-    YzcxODgzZjkxYThjOWEzODQwMDZkYzM5OTkyNmM1MjE2MzJmNzI3Mg==
+    NzY3MWVlYjVmYzM4NzhjZjIzNDUyYjFlNWZhMjMxMGE4NWQ3YTI4Yw==
   data.tar.gz: !binary |-
-    MTYxNmVjOTZjMGI5ZWIxNDZjY2ZjZTVkNjc5NTZhZjNiZGQ3OTJjMQ==
+    OTVjMThlYzg0NzUwZTdmMzIyZmJlYjc5NjBiNDUzMmE2NjJjMGVkOA==
 SHA512:
   metadata.gz: !binary |-
-    OWMxZDZhNTEyMjcxMzQ1NGZhYzNlMjM0MWQyMWQwN2NlOGRhYmExNGIyZDA0
-    ZGEwZjAyM2IzZmNjMGM1OGQ5ZWNkZTMwZmJlN2ExMGU1ZTg3ZWY5Yjc5MDYz
-    MDk3OGEwNDJkZTY3N2ZkYjVhMjg0ZWE4NjI5MWUyZTJiY2MxYzk=
+    ZTVkOTQ4MGMzMTQ4ZDg5MzczMDllMzgwNDY3Y2NmNzU4NDc5MzMwOGIwYzA3
+    Y2FjMzQ1YzA4NDhiMjY0OWMyYjMyMWFhOWM5MTI5OGFiMTJiMDFhYmJlNTI3
+    NjBkZDU5MzMzOTJlOGY0NzdiZWRiYWI5ZWE2YTBiZjJkYTk1ZTU=
   data.tar.gz: !binary |-
-    YzllMTA1ZTYxNzViMjk5ZjAzYWQ2OTIwMjNiYjFkNmU1Mzg1NDY4YTNkMjk5
-    ZTIxMDIzOGIzYWQwN2FhYWQ0YjhkNDE4NjU3OGMwNjg1ZjJjYTdjNmQ0OTA4
-    NDJjNzU1NmU1ZjY0MGJmNDk3N2I1M2I3ZDk1ZDRjMDhlMTQ1NDQ=
+    MWJkZjY5ZWY5MmYyNTJjMjIyODE0ZmQ4YWU4OTZlMTY5MzIyNGNlZGJkNjU2
+    YjBjNmI5YTIyYTdmMGJhZmVlNTExZWJkN2U4OWRlMDE0NzM3MGI4ZGE4M2Rj
+    MzNjODU3YzYzMDFmZDg1MjU1YzQ2MDgxODIwNmQ3ZDJkZDU3MWQ=

data/README.md

@@ -27,7 +27,7 @@ lightweight than BioRuby. And more fun! ;)
 ## Documentation ##
 
 Checkout
-[parse_fasta docs](http://rubydoc.info/gems/parse_fasta/1.7.0/frames)
+[parse_fasta docs](http://rubydoc.info/gems/parse_fasta/1.7.2/frames)
 for the full api documentation.
 
 ## Usage ##
@@ -70,6 +70,16 @@ Read fasta file into a hash.
 
 Add `SeqFile#to_hash`, `FastaFile#to_hash` and `FastqFile#to_hash`.
 
+#### 1.7.2 ####
+
+Strip spaces (not all whitespace) from `Sequence` and `Quality` strings.
+
+Some alignment fastas have spaces for easier reading. Strip these
+out. For consistency, also strips spaces from `Quality` strings. If
+there are spaces that don't match in the quality and sequence in a
+fastQ file, then things will get messed up in the FastQ file. FastQ
+shouldn't have spaces though.
+
 ### 1.6 ###
 
 Added `SeqFile` class, which accepts either fastA or fastQ files. It

data/lib/parse_fasta/quality.rb

@@ -19,6 +19,17 @@
 # Provide some methods for dealing with common tasks regarding
 # quality strings.
 class Quality < String
+
+  # Strips whitespace from the str argument before calling super
+  #
+  # @return [Quality] A Quality string
+  #
+  # @example Removes whitespace
+  #   Quality.new "I I 2 ! " #=> "II2!"
+  def initialize(str)
+    super(str.gsub(/ +/, ""))
+  end
+
   # Returns the mean quality for the record. This will be a good deal
   # faster than getting the average with `qual_scores` and reduce.
   #

data/lib/parse_fasta/sequence.rb

@@ -20,6 +20,16 @@
 # nucleotide sequences.
 class Sequence < String
 
+  # Strips whitespace from the str argument before calling super
+  #
+  # @return [Sequence] A Sequence string
+  #
+  # @example Removes whitespace
+  #   Sequence.new "AA CC TT" #=> "AACCTT"
+  def initialize(str)
+    super(str.gsub(/ +/, ""))
+  end
+
   # Calculates GC content
   #
   # Calculates GC content by dividing count of G + C divided by count
@@ -45,7 +55,7 @@ class Sequence < String
     t = s.count('t')
     a = s.count('a')
     u = s.count('u')
-    
+
     return 0 if c + g + t + a + u == 0
     return (c + g) / (c + g + t + a + u).to_f
   end
@@ -87,9 +97,9 @@ class Sequence < String
       warn('ERROR: A sequence contains both T and U')
       counts[:t], counts[:u] = t, u
     end
-    
+
     counts[:n] = s.count('n') if count_ambiguous_bases
-    
+
     counts
   end
 
@@ -116,7 +126,7 @@ class Sequence < String
   def base_frequencies(count_ambiguous_bases=nil)
     base_counts = self.base_counts(count_ambiguous_bases)
     total_bases = base_counts.values.reduce(:+).to_f
-    base_freqs = 
+    base_freqs =
       base_counts.map { |base, count| [base, count/total_bases] }.flatten
     Hash[*base_freqs]
   end

data/lib/parse_fasta/version.rb

@@ -17,5 +17,5 @@
 # along with parse_fasta.  If not, see <http://www.gnu.org/licenses/>.
 
 module ParseFasta
-  VERSION = "1.7.1"
+  VERSION = "1.7.2"
 end

data/spec/lib/quality_spec.rb

@@ -21,10 +21,18 @@ require 'bio'
 
 describe Quality do
   let(:qual_string) { qual_string = Quality.new('ab%63:K') }
-  let(:bioruby_qual_scores) do 
+  let(:bioruby_qual_scores) do
     Bio::Fastq.new("@seq1\nACTGACT\n+\n#{qual_string}").quality_scores
   end
 
+  describe "::new" do
+    it "removes any spaces in the quality string" do
+      q = "   ab #   :m, !    "
+      q_no_spaces = "ab#:m,!"
+      expect(Quality.new(q)).to eq q_no_spaces
+    end
+  end
+
   describe "#qual_scores" do
     context "with illumina style quality scores" do
       it "returns an array of quality scores" do
@@ -39,5 +47,5 @@ describe Quality do
       mean_quality = qual_string.qual_scores.reduce(:+) / len
       expect(qual_string.mean_qual).to eq mean_quality
     end
-  end             
+  end
 end

data/spec/lib/sequence_spec.rb

@@ -25,6 +25,14 @@ describe Sequence do
     expect(Sequence.new('ACTG')).to be_a String
   end
 
+  describe "::new" do
+    it "removes any spaces in the sequence" do
+      s = "ACT ACT ACT    GCT  "
+      s_no_spaces = "ACTACTACTGCT"
+      expect(Sequence.new(s)).to eq s_no_spaces
+    end
+  end
+
   describe "#gc" do
     it "gives the same answer as BioRuby" do
       s = 'ACtgcGAtcgCgAaTtGgCcnNuU'
@@ -75,7 +83,7 @@ describe Sequence do
         expect(s.base_counts).to eq({ a: 2, c: 2, u: 2, g: 2 })
       end
     end
-    
+
     context "for an RNA sequence with truthy argument" do
       it "returns a map of A, C, U, G and N counts" do
         s = Sequence.new('ACUGNacugn')

data/test_files/test.fa

@@ -1,6 +1,6 @@
 > empty seq at beginning
 >seq1 is fun
-AACTGGNNN
+AAC TGG NN N
 
 
 >seq2
@@ -15,4 +15,4 @@ yyyyyyyyyy
 
 yyyyy
 NNN
->empty seq at end
+>empty seq at end

data/test_files/test.fq

@@ -1,8 +1,8 @@
 @seq1
-AACCTTGG
+AA CC TT GG
 +
-)#3gTqN8
+)# 3g Tq N8
 @seq2 apples
 ACTG
 +seq2 apples
-*ujM
+*ujM

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: parse_fasta
 version: !ruby/object:Gem::Version
-  version: 1.7.1
+  version: 1.7.2
 platform: ruby
 authors:
 - Ryan Moore
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-07-14 00:00:00.000000000 Z
+date: 2015-10-19 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler