lederhosen 0.0.10 → 0.0.11

data/Gemfile

@@ -1,5 +1,7 @@
 source :rubygems
+
 gem 'thor'
 gem 'rspec'
 gem 'dna'
-gem 'progressbar'
+gem 'progressbar'
+gem 'awesome_print'

data/lib/lederhosen/tasks/join.rb

@@ -31,7 +31,7 @@ module Lederhosen
           next
         end
 
-        records.each_slice(2) do |r, l|
+        records.each_slice(2) do |l, r|
           output.puts ">#{r.name}:#{File.basename(fasta_file, '.fasta')}\n#{r.sequence.reverse+l.sequence}"
         end
       end

data/lib/lederhosen/tasks/{filter.rb → k_filter.rb}

@@ -5,7 +5,7 @@
 module Lederhosen
   class CLI
 
-    desc "filter fasta file",
+    desc "k_filter khmer filtering",
          "--input=joined.fasta --output=filtered.fasta --k=10 --cutoff=50"
 
     method_option :input,    :type => :string,  :required => true
@@ -13,7 +13,7 @@ module Lederhosen
     method_option :k,        :type => :numeric, :required => true
     method_option :cutoff,   :type => :numeric, :required => true
 
-    def filter
+    def k_filter
       input  = options[:input]
       output = options[:output]
       k_len  = options[:k].to_i
@@ -39,7 +39,7 @@ module Lederhosen
 
       kept = 0
       total_reads = total_reads.to_f
-      
+
       pbar = ProgressBar.new "saving", total_reads.to_i
       output = File.open(output, 'w')
       File.open(input) do |handle|
@@ -60,7 +60,7 @@ module Lederhosen
               break
             end
           end
-      
+
           if keep
             kept += 1
             output.puts r
@@ -70,7 +70,7 @@ module Lederhosen
       end
 
       pbar.finish
-      
+
       ohai "survivors = #{kept} (#{kept/total_reads.to_f})"
       output.close
     end

data/lib/lederhosen/tasks/otu_table.rb

@@ -45,34 +45,6 @@ module Lederhosen
         end
           
       end
-
-      # # Get representative sequences!
-      # reads_total = 0
-      # representatives = {}
-      # clusters[:count_data].each{ |k, x| representatives[x[:seed]] = k }
-      # 
-      # out_handle = File.open("#{output}.fasta", 'w')
-      # 
-      # File.open(joined_reads) do |handle|
-      #   records = Dna.new handle
-      #   records.each do |dna|
-      #     reads_total += 1
-      #     if !representatives[dna.name].nil?
-      #       dna.name = "#{dna.name}:cluster_#{representatives[dna.name]}"
-      #       out_handle.puts dna
-      #     end
-      #   end
-      # end
-      # 
-      # out_handle.close
-      # 
-      # # Print some statistics
-      # ohai "reads in clusters:  #{clusters_total}"    
-      # ohai "number of reads:    #{reads_total}"
-      # ohai "unique clusters:    #{clusters.keys.length}"
-
-
-
     end
 
   end

data/lib/lederhosen/tasks/uc_filter.rb

@@ -0,0 +1,58 @@
+##
+# FILTER UC FILE BY MIN SAMPLES
+#
+
+module Lederhosen
+  class CLI
+
+    desc "uc_filter filter uc file by min samples",
+         "--input=clusters.uc --output=clusters.uc.filtered --reads=50 --samples=10"
+
+    method_option :input,    :type => :string,  :required => true
+    method_option :output,   :type => :string,  :required => true
+    method_option :reads,    :type => :numeric, :required => true
+    method_option :samples,  :type => :numeric, :required => true
+
+    def uc_filter
+      input   = options[:input]
+      output  = options[:output]
+      reads   = options[:reads].to_i
+      samples = options[:samples].to_i
+
+      # load UC file
+      clstr_info   = Helpers.load_uc_file input
+      clstr_counts = clstr_info[:clstr_counts] # clstr_counts[:clstr][sample.to_i] = reads
+
+      # filter
+      survivors = clstr_counts.reject do |a, b|
+        b.reject{ |i, j| j < reads }.length < samples
+      end
+
+      surviving_clusters = survivors.keys
+
+      # print filtered uc file
+      out = File.open(output, 'w')
+      kept, total = 0, 0
+      File.open(input) do |handle|
+        handle.each do |line|
+          if line =~ /^#/
+            out.print line
+            next
+          end
+
+          total += 1
+
+          if surviving_clusters.include? line.split[1].to_i
+            out.print line
+            kept += 1
+          end
+        end
+      end
+      out.close
+      ohai "Survivors"
+      ohai "clusters: #{surviving_clusters.length}/#{clstr_counts.keys.length} = #{100*surviving_clusters.length/clstr_counts.keys.length.to_f}%"
+      ohai "reads:    #{kept}/#{total} = #{100*kept/total.to_f}%"
+    end
+  end
+
+end

data/lib/lederhosen.rb

@@ -1,8 +1,7 @@
 require 'rubygems'
-require 'thor'
-require 'dna'
-require 'set'
-require 'progressbar'
+require 'bundler'
+
+Bundler.require
 
 Dir.glob(File.join(File.dirname(__FILE__), 'lederhosen', '*.rb')).each { |f| require f }
 

data/lib/version.rb

@@ -1,3 +1,3 @@
 module Lederhosen
-  VERSION = '0.0.10'
+  VERSION = '0.0.11'
 end

data/pipeline.sh

@@ -0,0 +1,37 @@
+#!/bin/bash
+
+set +e
+
+# An example OTU clustering pipeline
+# Austin G. Davis-Richardson
+# <harekrishna at gmail dot com>
+
+raw_reads='raw_reads/*.txt'
+identities='0.975'
+out_dir='pipeline'
+
+# trim reads
+bin/lederhosen trim --reads-dir=$raw_reads --out-dir=$out_dir/trimmed
+
+# join reads
+bin/lederhosen join --trimmed=$out_dir/trimmed/*.fasta --output=$out_dir/joined.fasta
+
+# filter reads
+bin/lederhosen filter --input=$out_dir/joined.fasta --output=$out_dir/filtered.fasta -k=10 --cutoff=50
+
+# sort
+bin/lederhosen sort --input=$out_dir/filtered.fasta --output=$out_dir/sorted.fasta
+
+# cluster
+for i in $identities
+do
+    bin/lederhosen cluster --input=$out_dir/sorted.fasta --output=$out_dir/clusters_"$i"_.uc --identity=$i
+done
+
+# generate otu tables
+for i in $identities
+do
+    bin/lederhosen otu_table --clusters=$out_dir/clusters_"$i"_.uc --output=$out_dir/otus_"$i"
+done
+
+echo "complete!"

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: lederhosen
 version: !ruby/object:Gem::Version 
-  hash: 11
+  hash: 9
   prerelease: 
   segments: 
   - 0
   - 0
-  - 10
-  version: 0.0.10
+  - 11
+  version: 0.0.11
 platform: ruby
 authors: 
 - Austin G. Davis-Richardson
@@ -15,7 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2012-05-14 00:00:00 Z
+date: 2012-05-22 00:00:00 Z
 dependencies: 
 - !ruby/object:Gem::Dependency 
   name: dna
@@ -121,15 +121,17 @@ files:
 - lib/lederhosen/cli.rb
 - lib/lederhosen/helpers.rb
 - lib/lederhosen/tasks/cluster.rb
-- lib/lederhosen/tasks/filter.rb
 - lib/lederhosen/tasks/join.rb
+- lib/lederhosen/tasks/k_filter.rb
 - lib/lederhosen/tasks/name.rb
 - lib/lederhosen/tasks/otu_table.rb
 - lib/lederhosen/tasks/rep_reads.rb
 - lib/lederhosen/tasks/sort.rb
 - lib/lederhosen/tasks/split.rb
 - lib/lederhosen/tasks/trim.rb
+- lib/lederhosen/tasks/uc_filter.rb
 - lib/version.rb
+- pipeline.sh
 - readme.md
 - spec/data/ILT_L_9_B_001_1.txt
 - spec/data/ILT_L_9_B_001_3.txt