lederhosen 0.3.9 → 0.4.0

data/lederhosen.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = "lederhosen"
-  s.version = "0.3.9"
+  s.version = "0.4.0"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Austin G. Davis-Richardson"]
-  s.date = "2012-08-23"
+  s.date = "2012-08-27"
   s.description = "Various tools for OTU clustering"
   s.email = "harekrishna@gmail.com"
   s.executables = ["lederhosen"]

data/lib/lederhosen/tasks/join.rb

@@ -5,14 +5,16 @@ module Lederhosen
     # PAIRED-END READ WORK-AROUND (JOIN THEM)
     #
     desc "join",
-         "join trimmed reads into a single file"
+      "join paired or unpaired reads into a single file. Paired reads are joined end-to-end"
 
     method_option :trimmed, :type => :string, :required => true
     method_option :output,  :type => :string, :required => true
+    method_option :paired,  :type => :boolean, :default => true
 
     def join
       trimmed = Dir[options[:trimmed]]
       output  = options[:output]
+      paired  = options[:paired]
 
       ohai "joining #{File.dirname(trimmed.first)} saving to #{output}"
 
@@ -24,20 +26,43 @@ module Lederhosen
 
       trimmed.each do |fasta_file|
         pbar.inc
+        records =
+          begin
+            Dna.new File.open(fasta_file)
+          rescue
+            ohai "skipping #{fasta_file} (empty?)"
+            next
+          end
 
-        begin
-          records = Dna.new File.open(fasta_file)
-        rescue
-          ohai "skipping #{fasta_file} (empty?)"
-          next
+        if paired
+          output_paired_reads(records, output, fasta_file)
+        else
+          output_unpaired_reads(records, output, fasta_file)
         end
+      end
+      pbar.finish
+    end
 
+    no_tasks do
+      ##
+      # Output paired reads joined together
+      #
+      def output_paired_reads(records, output, fasta_file)
         records.each_slice(2) do |l, r|
-          output.puts ">#{r.name}:split=#{r.sequence.size}:sample=#{File.basename(fasta_file, '.fasta')}\n#{r.sequence.reverse+l.sequence}"
+          output.puts ">#{r.name}:split=#{r.sequence.size}:sample=#{File.basename(fasta_file, '.fasta')}"
+          output.puts "#{r.sequence.reverse+l.sequence}"
         end
       end
-      pbar.finish
-    end
 
+      ##
+      # Output unpaired reads
+      #
+      def output_unpaired_reads(records, output, fasta_file)
+        records.each do |r|
+          output.puts ">#{r.name}:split=na:sample=#{File.basename(fasta_file, '.fasta')}"
+          output.puts r.sequence
+        end
+      end
+    end
   end
 end

data/lib/lederhosen/tasks/otu_filter.rb

@@ -16,10 +16,12 @@ module Lederhosen
       reads       = options[:reads]
       min_samples = options[:samples]
 
-      ohai "filtering otu file #{input} (reads = #{reads}, samples = #{min_samples}), saving to #{output}"
+      ohai "filtering otu file #{input} (reads = #{reads}, samples = #{min_samples})"
 
       cluster_sample_count = Hash.new { |h, k| h[k] = Hash.new }
 
+      ohai "loading csv file #{input}"
+
       # slurp up CSV file
       File.open input do |handle|
         header = handle.gets.strip.split(',')
@@ -34,9 +36,13 @@ module Lederhosen
         end
       end
 
+      ohai "filtering"
+
       # filter sample_cluster_count
       filtered = cluster_sample_count.reject { |k, v| v.reject { |k, v| v < reads }.size < min_samples }
 
+      ohai "saving to #{output}"
+
       # save the table
       out = File.open(output, 'w')
       samples = filtered.values.map(&:keys).flatten.uniq

data/lib/lederhosen/tasks/uc_filter.rb

@@ -44,13 +44,14 @@ module Lederhosen
       pbar = ProgressBar.new 'saving', lines
       kept, total = 1, 0
 
+      # output lederhosen filtering information because I often
+      # forget to write this down :)
+      out.puts "# filtered: #{input}"
+      out.puts "# #{reads} reads in at least #{samples} samples"
+
       File.open(input) do |handle|
         pbar = ProgressBar.new 'saving', File.size(input)
         handle.each do |line|
-          # output lederhosen filtering information because I often
-          # forget to write this down :)
-          out.puts "# filtered: #{input}"
-          out.puts "# #{reads} reads in at least #{samples} samples"
 
           pbar.inc handle.pos
           if line =~ /^#/

data/lib/lederhosen/version.rb

@@ -1,8 +1,8 @@
 module Lederhosen
   module Version
     MAJOR = 0
-    MINOR = 3
-    PATCH = 9
+    MINOR = 4
+    PATCH = 0
 
     STRING = [MAJOR, MINOR, PATCH].join('.')
   end

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: lederhosen
 version: !ruby/object:Gem::Version 
-  hash: 1
+  hash: 15
   prerelease: 
   segments: 
   - 0
-  - 3
-  - 9
-  version: 0.3.9
+  - 4
+  - 0
+  version: 0.4.0
 platform: ruby
 authors: 
 - Austin G. Davis-Richardson
@@ -15,7 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2012-08-23 00:00:00 Z
+date: 2012-08-27 00:00:00 Z
 dependencies: 
 - !ruby/object:Gem::Dependency 
   type: :runtime