lederhosen 0.4.0 → 0.5.0

data/lederhosen.gemspec

@@ -5,7 +5,7 @@
 
 Gem::Specification.new do |s|
   s.name = "lederhosen"
-  s.version = "0.4.0"
+  s.version = "0.5.0"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Austin G. Davis-Richardson"]
@@ -45,7 +45,6 @@ Gem::Specification.new do |s|
     "lib/lederhosen/tasks/trim.rb",
     "lib/lederhosen/tasks/uc_filter.rb",
     "lib/lederhosen/tasks/uc_stats.rb",
-    "lib/lederhosen/tasks/uniquify.rb",
     "lib/lederhosen/tasks/version.rb",
     "lib/lederhosen/version.rb",
     "readme.md",

data/lib/lederhosen/version.rb

@@ -1,7 +1,7 @@
 module Lederhosen
   module Version
     MAJOR = 0
-    MINOR = 4
+    MINOR = 5
     PATCH = 0
 
     STRING = [MAJOR, MINOR, PATCH].join('.')

data/spec/cli_spec.rb

@@ -45,11 +45,6 @@ describe Lederhosen::CLI do
     `./bin/lederhosen otu_filter --input=#{$test_dir}/otu_table.csv --output=#{$test_dir}/otu_table.filtered.csv --reads 1 --samples 1`
   end
 
-  it 'should uniquify reads' do
-    `./bin/lederhosen uniquify --input=#{$test_dir}/sorted.fasta --output=#{$test_dir}/uniqued.fasta --table-out=#{$test_dir}/uniquify.txt`
-    $?.success?.should be_true
-  end
-
   it 'should split joined.fasta into reads for each cluster' do
     `./bin/lederhosen split --reads=#{$test_dir}/joined.fasta --clusters=#{$test_dir}/clusters.uc --out-dir=#{$test_dir}/split --min-clst-size=1`
   end

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: lederhosen
 version: !ruby/object:Gem::Version 
-  hash: 15
+  hash: 11
   prerelease: 
   segments: 
   - 0
-  - 4
+  - 5
   - 0
-  version: 0.4.0
+  version: 0.5.0
 platform: ruby
 authors: 
 - Austin G. Davis-Richardson
@@ -141,7 +141,6 @@ files:
 - lib/lederhosen/tasks/trim.rb
 - lib/lederhosen/tasks/uc_filter.rb
 - lib/lederhosen/tasks/uc_stats.rb
-- lib/lederhosen/tasks/uniquify.rb
 - lib/lederhosen/tasks/version.rb
 - lib/lederhosen/version.rb
 - readme.md

data/lib/lederhosen/tasks/uniquify.rb

@@ -1,61 +0,0 @@
-##
-# uniquify - uniquify a fasta file generating a fasta file of only unique sequences
-# also output table with sequence_id -> number of reads
-#
-
-module Lederhosen
-  class CLI
-    desc 'uniquify',
-      'uniquify a fasta file generating a fasta file of only unique sequences.' +\
-      'also generate a table with sequence_id -> abundance'
-
-    method_option :input,     :type => :string, :required => true
-    method_option :output,    :type => :string, :required => true
-    method_option :table_out, :type => :string, :required => true
-
-    def uniquify
-      input     = options[:input]
-      output    = options[:output]
-      table_out = options[:table_out]
-
-      ohai "uniquifying #{input} to #{output} w/ table #{table_out}"
-
-      sequence_counts = Hash.new { |h, k| h[k] = 0 }
-      sequence_to_id = Hash.new
-
-      out = File.open(output, 'w')
-
-      File.open(input) do |handle|
-        pbar = ProgressBar.new 'loading', File.size(input)
-        Dna.new(handle).each do |record|
-          pbar.inc handle.pos
-          unless sequence_counts.has_key? record.sequence
-            # store the sequence and id so we can have ids in the
-            # table. If the file is sorted by length then this
-            # should also be a seed sequence.
-            sequence_to_id[record.sequence] = record.name
-            out.puts record
-          end
-          sequence_counts[record.sequence] += 1
-        end
-        pbar.finish
-      end
-
-      out.close
-
-      # write table
-      pbar = ProgressBar.new 'table', sequence_counts.size
-      File.open(table_out, 'w') do |out|
-        sequence_counts.each_pair do |sequence, count|
-          pbar.inc
-          id = sequence_to_id[sequence]
-          out.puts "#{id}\t#{count}"
-        end
-      end
-      pbar.finish
-      kept = sequence_counts.keys.size
-      total = sequence_counts.values.inject(:+)
-      ohai "kept #{kept} out of #{total} reads (#{100*kept/total.to_f})"
-    end
-  end
-end