lederhosen 1.0.2 → 1.1.0

data/lederhosen.gemspec

@@ -5,7 +5,7 @@
 
 Gem::Specification.new do |s|
   s.name = "lederhosen"
-  s.version = "1.0.2"
+  s.version = "1.1.0"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Austin G. Davis-Richardson"]

data/lib/lederhosen/tasks/otu_table.rb

@@ -8,24 +8,31 @@ module Lederhosen
   class CLI
 
     desc "otu_table",
-         "create an OTU abundance matrix from USEARCH output"
+         "create an OTU abundance matrix from USEARCH prefix"
 
     method_option :files,  :type => :string, :required => true
-    method_option :output, :type => :string, :required => true
-    method_option :level,  :type => :string, :required => true, :banner => 'valid options: domain, kingdom, phylum, class, order, genus, or species'
+
+    method_option :prefix, :type => :string, :required => true,
+                  :banner => 'prefix prefix'
+
+    method_option :levels, :type => :array, :required => true,
+                  :banner => 'valid options: domain, kingdom, phylum, class, order, genus, or species (or all of them at once)'
 
     def otu_table
       input  = Dir[options[:files]]
-      output = options[:output]
-      level  = options[:level].downcase
+      prefix = options[:prefix]
+      levels = options[:levels].map(&:downcase)
 
-      ohai "generating #{level} table from #{input.size} file(s) and saving to #{output}."
+      ohai "generating #{levels.join(', ')} table(s) from #{input.size} file(s) and saving to prefix #{prefix}."
 
-      fail "bad level: #{level}" unless %w{domain phylum class order family genus species kingdom}.include? level
+      # sanity check
+      levels.each do |level|
+        fail "bad level: #{level}" unless %w{domain phylum class order family genus species kingdom}.include? level
+      end
 
-      sample_cluster_count = Hash.new { |h, k| h[k] = Hash.new { |h, k| h[k] = 0 } }
+      level_sample_cluster_count = Hash.new { |h, k| h[k] = Hash.new { |h, k| h[k] = Hash.new { |h, k| h[k] = 0 } } }
 
-      all_names = Set.new
+      all_names = Hash.new { |h, k| h[k] = Set.new }
       pbar = ProgressBar.new "loading", input.size
 
       # Load cluster table
@@ -35,36 +42,41 @@ module Lederhosen
           handle.each do |line|
             dat = parse_usearch_line(line.strip)
             next if dat.nil?
-            name = dat[level] rescue ohai(dat.inspect)
 
-            all_names << name
-            sample_cluster_count[input_file][name] += 1
+            levels.each do |level|
+              name = dat[level] rescue nil
+              all_names[level] << name
+              level_sample_cluster_count[level][input_file][name] += 1
+            end
+
           end
         end
       end
 
       pbar.finish
 
-      ohai "found #{all_names.size} unique taxa at #{level} level"
+      # save to csv(s)
+      levels.each do |level|
+
+        ohai "saving #{level} table"
 
-      # save to csv
-      File.open(output, 'w') do |handle|
-        header = all_names.to_a.compact.sort
-        handle.puts "#{level.capitalize},#{header.join(',')}"
-        samples = sample_cluster_count.keys.sort
+        File.open("#{prefix}.#{level}.csv", 'w') do |handle|
+          header = all_names[level].to_a.compact.sort
+          handle.puts "#{level.capitalize},#{header.join(',')}"
 
-        samples.each do |sample|
-          handle.print "#{sample}"
-          header.each do |name|
-            handle.print ",#{sample_cluster_count[sample][name]}"
+          input.each do |sample|
+            handle.print "#{sample}"
+            header.each do |name|
+              handle.print ",#{level_sample_cluster_count[level][sample][name]}"
+            end
+            handle.print "\n"
           end
-          handle.print "\n"
         end
       end
     end
 
     no_tasks do
-      # parse a line of usearch output
+      # parse a line of usearch prefix
       # return a hash in the form:
       # { :taxonomy => '', :identity => 0.00, ... }
       # unless the line is not a "hit" in which case

data/lib/lederhosen/version.rb

@@ -1,9 +1,9 @@
 module Lederhosen
   module Version
     MAJOR = 1
-    CODENAME = 'Hefeweizen'
-    MINOR = 0
-    PATCH = 2
+    MINOR = 1
+    CODENAME = 'Apfelstrudel' # changes for minor versions
+    PATCH = 0
 
     STRING = [MAJOR, MINOR, PATCH].join('.')
   end

data/readme.md

@@ -7,7 +7,7 @@ Cluster raw Illumina 16S rRNA amplicon data to generate OTUs.
 - Lederhosen is a project born out of the Triplett Lab at the University of Florida.
 - Lederhosen is designed to be a fast and simple method of clustering 16S rRNA amplicons sequenced
 using paired and non-paired end short reads such as those produced by Illumina (GAIIx, HiSeq and MiSeq).
-- Lederhosen uses Semantic Versioning.
+- Lederhosen uses [Semantic Versioning](http://semver.org/).
 - Lederhosen is free and open source under the [MIT open source license](http://opensource.org/licenses/mit-license.php/).
 - Except for USEARCH which requires a license, Lederhosen is available for commercial use.
 

data/spec/cli_spec.rb

@@ -26,15 +26,14 @@ describe Lederhosen::CLI do
     `./bin/lederhosen cluster --input #{$test_dir}/trimmed/ILT_L_9_B_001.fasta --database #{$test_dir}/test_db.udb --identity 0.95 --output #{$test_dir}/clusters.uc`
   end
 
-  %w{domain phylum class ORDER Family genus species}.each do |level|
-    it "should build #{level} abundance matrix" do
-      `./bin/lederhosen otu_table --files=spec/data/test.uc --output=#{$test_dir}/otu_table.csv --level=#{level}`
-      $?.success?.should be_true
-    end
+  it 'should build abundance matrices for each level' do
+    levels = "domain phylum class order FAMILY genus Species"
+    `./bin/lederhosen otu_table --files=spec/data/test.uc --prefix=#{$test_dir}/otu_table --levels=#{levels}`
+    $?.success?.should be_true
   end
 
   it 'should filter OTU abundance matrices' do
-    `./bin/lederhosen otu_filter --input=#{$test_dir}/otu_table.csv --output=#{$test_dir}/otu_table.filtered.csv --reads 1 --samples 1`
+    `./bin/lederhosen otu_filter --input=#{$test_dir}/otu_table.species.csv --output=#{$test_dir}/otu_table.filtered.csv --reads 1 --samples 1`
     $?.success?.should be_true
   end
 

metadata

@@ -5,9 +5,9 @@ version: !ruby/object:Gem::Version
   prerelease: 
   segments: 
   - 1
+  - 1
   - 0
-  - 2
-  version: 1.0.2
+  version: 1.1.0
 platform: ruby
 authors: 
 - Austin G. Davis-Richardson