lederhosen 1.3.8 → 1.3.10

data/lederhosen.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = "lederhosen"
-  s.version = "1.3.8"
+  s.version = "1.3.10"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Austin G. Davis-Richardson"]
-  s.date = "2012-12-07"
+  s.date = "2012-12-13"
   s.description = "Various tools for OTU clustering"
   s.email = "harekrishna@gmail.com"
   s.executables = ["lederhosen"]

data/lib/lederhosen/no_tasks.rb

@@ -1,3 +1,4 @@
+
 module Lederhosen
   class CLI
 
@@ -7,7 +8,7 @@ module Lederhosen
 
       # parse a line of usearch prefix
       # return a hash in the form:
-      # { :taxonomy => '', :identity => 0.00, ... }
+      # { :taxonomy => '', :identity => '0.00', ... }
       # unless the line is not a "hit" in which case
       # the function returns nil
       def parse_usearch_line(str)
@@ -18,7 +19,7 @@ module Lederhosen
         str = str.split
 
         taxonomic_description = str[9]
-        identity = str[3].to_f
+        identity = str[3]
 
         # parse taxonomic_description
         taxonomies = parse_taxonomy(taxonomic_description) rescue { 'original' => str[9] }
@@ -59,9 +60,13 @@ module Lederhosen
         end
       end
 
+      RE_TAXCOLLECTOR = /^\[0\](.*);\[1\](.*);\[2\](.*);\[3\](.*);\[4\](.*);\[5\](.*);\[6\](.*);\[7\](.*);\[8\](.*)/
+      RE_GREENGENES = /k__(.*); ?p__(.*); ?c__(.*); ?o__(.*); ?f__(.*); ?g__(.*); ?(.*);/
+      RE_QIIME = /k__(.*);p__(.*);c__(.*);o__(.*);f__(.*);g__(.*);s__(.*)/
+
       def parse_taxonomy_qiime(taxonomy)
         levels = %w{kingdom phylum class order family genus species}
-        match_data = taxonomy.match(/k__(\w*);p__(\w*);c__(\w*);o__(\w*);f__(\w*);g__(\w*);s__(\w*)/)
+        match_data = taxonomy.match(RE_QIIME)
         match_data = match_data[1..-1]
 
         names = Hash.new
@@ -74,7 +79,7 @@ module Lederhosen
 
       def parse_taxonomy_greengenes(taxonomy)
         levels = %w{kingdom phylum class order family genus species}
-        match_data = taxonomy.match(/k__(\w*); ?p__(\w*); ?c__(\w*); ?o__(\w*); ?f__(\w*); ?g__(\w*); ?(\w*);/)
+        match_data = taxonomy.match(RE_GREENGENES)
         match_data = match_data[1..-1]
 
         names = Hash.new
@@ -100,9 +105,8 @@ module Lederhosen
 
         match_data =
           begin
-            taxonomy.match(/\[0\](.*);\[1\](.*);\[2\](.*);\[3\](.*);\[4\](.*);\[5\](.*);\[6\](.*);\[7\](.*);\[8\](.*)/)[1..-1]
+            taxonomy.match(RE_TAXCOLLECTOR)[1..-1]
           rescue
-            $stderr.puts taxonomy.inspect
             return nil
           end
 

data/lib/lederhosen/tasks/otu_table.rb

@@ -2,8 +2,6 @@
 # MAKE TABLES
 #
 
-require 'set'
-
 module Lederhosen
   class CLI
 
@@ -30,16 +28,19 @@ module Lederhosen
         fail "bad level: #{level}" unless %w{domain phylum class order family genus species kingdom original}.include? level
       end
 
-      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 = Hash.new { |h, k| h[k] = Set.new }
+      # there has to be a more efficient way of doing this
+      level_sample_cluster_count =
+        Hash.new do |h, k|
+          h[k] = Hash.new do |h, k|
+            h[k] = Hash.new(0)
+          end
+        end
 
       # create a progress bar with the total number of bytes of
       # the files we're slurping up
       pbar = ProgressBar.new "loading", input.size
 
       # Load cluster table
-
       input.each do |input_file|
         pbar.inc
         File.open(input_file) do |handle|
@@ -54,8 +55,8 @@ module Lederhosen
                   dat[level] || 'unparsed_name'
                 end
 
+              # the next two lines are what is slow
               level_sample_cluster_count[level][input_file][name] += 1
-              all_names[level] << name
             end
 
           end
@@ -64,6 +65,14 @@ module Lederhosen
 
       pbar.finish
 
+      # get all taxonomic names at each level
+      all_names = Hash.new.tap do |bar|
+        level_sample_cluster_count.each_pair.map do |k, v|
+          names = v.each_value.map(&:keys).flatten.uniq
+          bar[k] = names
+        end
+      end
+
       # save to csv(s)
       levels.each do |level|
 

data/lib/lederhosen/tasks/trim.rb

@@ -2,6 +2,8 @@
 # QUALITY TRIMMING
 #
 
+# This should probably be broken into its own module or command-line utility.
+
 module Lederhosen
   class CLI
 
@@ -10,10 +12,12 @@ module Lederhosen
 
     method_option :reads_dir, :type => :string, :required => true
     method_option :out_dir,   :type => :string, :required => true
+    method_option :pretrim,   :type => :numeric, :default => 11
 
     def trim
       raw_reads = options[:reads_dir]
       out_dir   = options[:out_dir]
+      pretrim   = options[:pretrim]
 
       ohai "trimming #{File.dirname(raw_reads)} and saving to #{out_dir}"
 
@@ -92,16 +96,21 @@ module Lederhosen
       # returns just the sequence
       def trim_seq(dna, args={})
 
+
+        pretrim = args[:pretrim] || false
         # trim primers off of sequence
-        # (THIS IS EXPERIMENT-SPECIFIC)
-        dna.sequence = dna.sequence[11..-1]
-        dna.quality  = dna.quality[11..-1]
+        # XXX this is experiment-specific and needs to be made
+        # into a parameter
+        if pretrim
+          dna.sequence = dna.sequence[pretrim..-1]
+          dna.quality  = dna.quality[pretrim..-1]
+        end
 
         # throw away any read with an ambiguous primer
         return nil if dna.sequence =~ /N/
 
-        min    = args[:min]    || 20
-        offset = args[:cutoff] || 64
+        min    = args[:min]    || 20 # what is this constant?
+        offset = args[:cutoff] || 64 # XXX depends on sequencing tech.
 
         _sum, _max, first, last, start, _end = 0, 0, 0, 0, 0
 
@@ -116,6 +125,8 @@ module Lederhosen
             first = a
           end
         end
+
+        # XXX why is this rescue statement here?
         dna.sequence[start + 11, _end - start].gsub('.', 'N') rescue nil
       end
     end

data/lib/lederhosen/version.rb

@@ -3,7 +3,7 @@ module Lederhosen
     MAJOR = 1
     MINOR = 3
     CODENAME = 'Dirndl' # changes for minor versions
-    PATCH = 8
+    PATCH = 10
 
     STRING = [MAJOR, MINOR, PATCH].join('.')
   end

data/lib/lederhosen.rb

@@ -1,7 +1,9 @@
 require 'rubygems'
 require 'bundler'
-Bundler.require :default
 require 'set'
+require 'dna'
+require 'progressbar'
+require 'thor'
 
 Dir.glob(File.join(File.dirname(__FILE__), 'lederhosen', '*.rb')).each { |f| require f }
 

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: lederhosen
 version: !ruby/object:Gem::Version
-  version: 1.3.8
+  version: 1.3.10
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-12-07 00:00:00.000000000 Z
+date: 2012-12-13 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: dna
@@ -176,7 +176,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: 1569227273029021963
+      hash: 2999187278262571353
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements: