BioDSL 1.0.1 → 1.0.2

data/lib/BioDSL/commands/assemble_seq_idba.rb

@@ -21,13 +21,11 @@
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 #                                                                              #
-# This software is part of the BioDSL framework (www.BioDSL.org).        #
+# This software is part of the BioDSL (www.BioDSL.org).                        #
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 
 module BioDSL
-  # rubocop:disable ClassLength
-
   # == Assemble sequences the stream using IDBA_UD.
   #
   # +assemble_seq_idba+ is a wrapper around the prokaryotic metagenome
@@ -99,7 +97,7 @@ module BioDSL
         TmpDir.create('reads.fna', 'contig.fa') do |fa_in, fa_out, tmp_dir|
           process_input(input, output, fa_in)
           execute_idba(fa_in, tmp_dir)
-          lengths = process_output(output, fa_out)
+          process_output(output, fa_out)
         end
 
         calc_n50(status)
@@ -123,7 +121,7 @@ module BioDSL
     def defaults
       @options[:kmer_min] ||= 24
       @options[:kmer_max] ||= 48
-      @options[:cpus]     ||= 1
+      @options[:cpus] ||= 1
     end
 
     # Read all records from input and emit non-sequence records to the output
@@ -141,7 +139,7 @@ module BioDSL
             entry = BioDSL::Seq.new_bp(record)
 
             @status[:sequences_in] += 1
-            @status[:residues_in]  += entry.length
+            @status[:residues_in] += entry.length
 
             fasta_io.puts entry.to_fasta
           else
@@ -193,9 +191,9 @@ module BioDSL
       BioDSL::Fasta.open(fa_out, 'r') do |ios|
         ios.each do |entry|
           output << entry.to_bp
-          @status[:records_out]   += 1
+          @status[:records_out] += 1
           @status[:sequences_out] += 1
-          @status[:residues_out]  += entry.length
+          @status[:residues_out] += entry.length
 
           @lengths << entry.length
         end
@@ -212,7 +210,7 @@ module BioDSL
       @lengths.reverse!
 
       status[:contig_max] = @lengths.first || 0
-      status[:contig_min] = @lengths.last  || 0
+      status[:contig_min] = @lengths.last || 0
       status[:contig_n50] = 0
 
       count = 0

data/lib/BioDSL/commands/assemble_seq_ray.rb

@@ -21,7 +21,7 @@
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 #                                                                              #
-# This software is part of the BioDSL framework (www.BioDSL.org).        #
+# This software is part of the BioDSL (www.BioDSL.org).                        #
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 
@@ -164,10 +164,10 @@ module BioDSL
 
     # Set the default option values.
     def defaults
-      @options[:kmer_min]   ||= 21
-      @options[:kmer_max]   ||= 49
+      @options[:kmer_min] ||= 21
+      @options[:kmer_max] ||= 49
       @options[:contig_min] ||= 500
-      @options[:cpus]       ||= 1
+      @options[:cpus] ||= 1
     end
 
     # Read all records from input and emit non-sequence records to the output
@@ -185,7 +185,7 @@ module BioDSL
             entry = BioDSL::Seq.new_bp(record)
 
             @status[:sequences_in] += 1
-            @status[:residues_in]  += entry.length
+            @status[:residues_in] += entry.length
 
             fasta_io.puts entry.to_fasta
           else
@@ -314,11 +314,11 @@ module BioDSL
           next if entry.length < @options[:contig_min]
 
           lengths << entry.length
-          output  << entry.to_bp
+          output << entry.to_bp
 
-          @status[:records_out]   += 1
+          @status[:records_out] += 1
           @status[:sequences_out] += 1
-          @status[:residues_out]  += entry.length
+          @status[:residues_out] += entry.length
         end
       end
 
@@ -333,11 +333,11 @@ module BioDSL
       @status[:kmer]   = kmer
       @status[:paired] = @paired
 
-      unless lengths.empty?
-        @status[:contig_min] = lengths.min
-        @status[:contig_max] = lengths.max
-        @status[:n50]        = calc_n50(lengths)
-      end
+      return if lengths.empty?
+
+      @status[:contig_min] = lengths.min
+      @status[:contig_max] = lengths.max
+      @status[:n50]        = calc_n50(lengths)
     end
 
     N50 = Struct.new(:kmer, :n50)

data/lib/BioDSL/commands/assemble_seq_spades.rb

@@ -21,7 +21,7 @@
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 #                                                                              #
-# This software is part of the BioDSL framework (www.BioDSL.org).        #
+# This software is part of the BioDSL (www.BioDSL.org).                        #
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 
@@ -160,7 +160,7 @@ module BioDSL
       entry = BioDSL::Seq.new_bp(record)
 
       @status[:sequences_in] += 1
-      @status[:residues_in]  += entry.length
+      @status[:residues_in] += entry.length
 
       if entry.qual
         @type = :fastq
@@ -216,9 +216,9 @@ module BioDSL
       BioDSL::Fasta.open(output_file) do |ios|
         ios.each do |entry|
           output << entry.to_bp
-          @status[:records_out]   += 1
+          @status[:records_out] += 1
           @status[:sequences_out] += 1
-          @status[:residues_out]  += entry.length
+          @status[:residues_out] += entry.length
 
           @lengths << entry.length
         end

data/lib/BioDSL/commands/classify_seq.rb

@@ -21,7 +21,7 @@
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 #                                                                              #
-# This software is part of the BioDSL framework (www.BioDSL.org).        #
+# This software is part of the BioDSL (www.BioDSL.org).                        #
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 
@@ -185,12 +185,12 @@ module BioDSL
 
     # Set default options.
     def defaults
-      @options[:prefix]    ||= 'taxonomy'
+      @options[:prefix] ||= 'taxonomy'
       @options[:kmer_size] ||= 8
       @options[:step_size] ||= 1
-      @options[:hits_max]  ||= 50
+      @options[:hits_max] ||= 50
       @options[:consensus] ||= 0.51
-      @options[:coverage]  ||= 0.9
+      @options[:coverage] ||= 0.9
       @options[:best_only] = true if @options[:best_only].nil?
     end
 
@@ -200,14 +200,14 @@ module BioDSL
     # @param i      [Fixnum]                      Record number,
     # @param search [BioDSL::Taxonomy::Search] Search object.
     def classify_seq(record, i, search)
-      @status[:sequences_in]  += 1
+      @status[:sequences_in] += 1
       @status[:sequences_out] += 1
-      @status[:residues_in]   += record[:SEQ].length
-      @status[:residues_out]  += record[:SEQ].length
+      @status[:residues_in] += record[:SEQ].length
+      @status[:residues_out] += record[:SEQ].length
       seq_name = record[:SEQ_NAME] || i.to_s
 
       result = search.execute(BioDSL::Seq.new(seq_name: seq_name,
-                                                 seq: record[:SEQ]))
+                                              seq: record[:SEQ]))
 
       record[:TAXONOMY]      = result.taxonomy
       record[:TAXONOMY_HITS] = result.hits

data/lib/BioDSL/commands/classify_seq_mothur.rb

@@ -21,7 +21,7 @@
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 #                                                                              #
-# This software is part of the BioDSL framework (www.BioDSL.org).        #
+# This software is part of the BioDSL (www.BioDSL.org).                        #
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 
@@ -128,7 +128,7 @@ module BioDSL
     # Set default options.
     def defaults
       @options[:confidence] ||= 80
-      @options[:cpus]       ||= 1
+      @options[:cpus] ||= 1
     end
 
     # Process input data and save sequences to a temporary file for
@@ -143,10 +143,10 @@ module BioDSL
           @status[:records_in] += 1
 
           if record[:SEQ]
-            @status[:sequences_in]  += 1
+            @status[:sequences_in] += 1
             @status[:sequences_out] += 1
-            @status[:residues_in]   += record[:SEQ].length
-            @status[:records_out]   += record[:SEQ].length
+            @status[:residues_in] += record[:SEQ].length
+            @status[:records_out] += record[:SEQ].length
             seq_name = record[:SEQ_NAME] || i.to_s
 
             entry = BioDSL::Seq.new(seq_name: seq_name, seq: record[:SEQ])

data/lib/BioDSL/commands/clip_primer.rb

@@ -21,7 +21,7 @@
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 #                                                                              #
-# This software is part of the BioDSL framework (www.BioDSL.org).        #
+# This software is part of the BioDSL (www.BioDSL.org).                        #
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 
@@ -166,16 +166,16 @@ module BioDSL
 
     # Set default option values.
     def defaults
-      @options[:mismatch_percent]  ||= 0
+      @options[:mismatch_percent] ||= 0
       @options[:insertion_percent] ||= 0
-      @options[:deletion_percent]  ||= 0
+      @options[:deletion_percent] ||= 0
     end
 
     # Calculate the mismatch percentage.
     #
     # @return [Float] Mismatch percentage.
     def calc_mis
-      (@primer.length * @options[:mismatch_percent]  * 0.01).round
+      (@primer.length * @options[:mismatch_percent] * 0.01).round
     end
 
     # Calculate the insertion percentage.
@@ -189,7 +189,7 @@ module BioDSL
     #
     # @return [Float] Deletion percentage.
     def calc_del
-      (@primer.length * @options[:deletion_percent]  * 0.01).round
+      (@primer.length * @options[:deletion_percent] * 0.01).round
     end
 
     # Reset any previous clip_primer results from record.
@@ -207,7 +207,7 @@ module BioDSL
       entry = BioDSL::Seq.new_bp(record)
 
       @status[:sequences_in] += 1
-      @status[:residues_in]  += entry.length
+      @status[:residues_in] += entry.length
 
       case @options[:direction]
       when :forward then clip_primer_forward(record, entry)
@@ -217,7 +217,7 @@ module BioDSL
       end
 
       @status[:sequences_out] += 1
-      @status[:residues_out]  += entry.length
+      @status[:residues_out] += entry.length
     end
 
     # Clip forward primer from entry and save clip information

data/lib/BioDSL/commands/cluster_otus.rb

@@ -21,7 +21,7 @@
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 #                                                                              #
-# This software is part of the BioDSL framework (www.BioDSL.org).        #
+# This software is part of the BioDSL (www.BioDSL.org).                        #
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 
@@ -89,8 +89,8 @@ module BioDSL
           process_input(input, output, tmp_in)
 
           BioDSL::Usearch.cluster_otus(input: tmp_in, output: tmp_out,
-                                          identity: @options[:identity],
-                                          verbose: @options[:verbose])
+                                       identity: @options[:identity],
+                                       verbose: @options[:verbose])
 
           process_output(output, tmp_out)
         end
@@ -172,8 +172,8 @@ module BioDSL
 
           output << record
           @status[:sequences_out] += 1
-          @status[:residues_out]  += record[:SEQ].length
-          @status[:records_out]   += 1
+          @status[:residues_out] += record[:SEQ].length
+          @status[:records_out] += 1
         end
       end
     end

data/lib/BioDSL/commands/collapse_otus.rb

@@ -21,7 +21,7 @@
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 #                                                                              #
-# This software is part of the BioDSL framework (www.BioDSL.org).        #
+# This software is part of the BioDSL (www.BioDSL.org).                        #
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 
@@ -162,7 +162,7 @@ module BioDSL
     def write_tax(hash, output)
       hash.each_value do |record|
         output << record
-        @status[:otus_out]    += 1
+        @status[:otus_out] += 1
         @status[:records_out] += 1
       end
     end

data/lib/BioDSL/commands/collect_otus.rb

@@ -21,7 +21,7 @@
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 #                                                                              #
-# This software is part of the BioDSL framework (www.BioDSL.org).        #
+# This software is part of the BioDSL (www.BioDSL.org).                        #
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 
@@ -142,7 +142,7 @@ module BioDSL
 
         output << record
 
-        @status[:hits_out]    += 1
+        @status[:hits_out] += 1
         @status[:records_out] += 1
       end
     end

data/lib/BioDSL/commands/complement_seq.rb

@@ -21,7 +21,7 @@
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 #                                                                              #
-# This software is part of the BioDSL framework (www.BioDSL.org).        #
+# This software is part of the BioDSL (www.BioDSL.org).                        #
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 
@@ -106,10 +106,10 @@ module BioDSL
       entry.type = @type
       entry.complement!
 
-      @status[:sequences_in]  += 1
+      @status[:sequences_in] += 1
       @status[:sequences_out] += 1
-      @status[:residues_in]   += entry.length
-      @status[:residues_out]  += entry.length
+      @status[:residues_in] += entry.length
+      @status[:residues_out] += entry.length
 
       record.merge! entry.to_bp
     end

data/lib/BioDSL/commands/count.rb

@@ -21,7 +21,7 @@
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 #                                                                              #
-# This software is part of the BioDSL framework (www.BioDSL.org).        #
+# This software is part of the BioDSL (www.BioDSL.org).                        #
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 

data/lib/BioDSL/commands/count_values.rb

@@ -21,7 +21,7 @@
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 #                                                                              #
-# This software is part of the BioDSL framework (www.BioDSL.org).        #
+# This software is part of the BioDSL (www.BioDSL.org).                        #
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 
@@ -74,7 +74,7 @@ module BioDSL
     #
     # @return [CountValues] Instance of class.
     def initialize(options)
-      @options    = options
+      @options = options
 
       check_options
 

data/lib/BioDSL/commands/degap_seq.rb

@@ -21,7 +21,7 @@
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 #                                                                              #
-# This software is part of the BioDSL framework (www.BioDSL.org).        #
+# This software is part of the BioDSL (www.BioDSL.org).                        #
 #                                                                              #
 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
 
@@ -68,7 +68,6 @@ module BioDSL
   #    {:SEQ_NAME=>"test1", :SEQ=>"A-GTC", :SEQ_LEN=>5}
   #    {:SEQ_NAME=>"test2", :SEQ=>"AGGTC", :SEQ_LEN=>5}
   #
-  # rubocop:disable ClassLength
   class DegapSeq
     require 'narray'
 
@@ -157,14 +156,14 @@ module BioDSL
     # @param seq [String] Sequences.
     def mask_add(seq)
       @status[:sequences_in] += 1
-      @status[:residues_in]  += seq.length
+      @status[:residues_in] += seq.length
 
       @max_len ||= seq.length
 
       check_length(seq)
 
       @na_mask ||= NArray.int(seq.length)
-      na_seq  = NArray.to_na(seq, 'byte')
+      na_seq = NArray.to_na(seq, 'byte')
       @indels.each_char { |c| @na_mask += na_seq.eq(c.ord) }
     end
 
@@ -212,7 +211,7 @@ module BioDSL
       record[:SEQ_LEN] = record[:SEQ].length
 
       @status[:sequences_out] += 1
-      @status[:residues_out]  += record[:SEQ].length
+      @status[:residues_out] += record[:SEQ].length
     end
 
     # Remove all gaps from all sequences in input stream and output to output
@@ -240,12 +239,12 @@ module BioDSL
       entry = BioDSL::Seq.new_bp(record)
 
       @status[:sequences_in] += 1
-      @status[:residues_in]  += entry.length
+      @status[:residues_in] += entry.length
 
       entry.seq.delete!(@indels)
 
       @status[:sequences_out] += 1
-      @status[:residues_out]  += entry.length
+      @status[:residues_out] += entry.length
 
       record.merge! entry.to_bp
     end