lederhosen 0.2.9 → 0.2.10

data/lederhosen.gemspec

@@ -5,7 +5,7 @@
 
 Gem::Specification.new do |s|
   s.name = "lederhosen"
-  s.version = "0.2.9"
+  s.version = "0.2.10"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Austin G. Davis-Richardson"]

data/lib/lederhosen/cli.rb

@@ -3,10 +3,14 @@ module Lederhosen
     include Thor::Actions
 
     no_tasks do
-      # just print string to STDERR
       def ohai(s)
         @shell.say_status('okay', s, 'green')
       end
+
+      def ohno(s)
+        @shell.say_status('fail', s, 'red')
+        exit(-1)
+      end
     end
 
     @shell = Thor::Shell::Basic.new

data/lib/lederhosen/tasks/add_names.rb

@@ -14,9 +14,9 @@ module Lederhosen
     method_option :output, :type => :string, :required => false
 
     def add_names
-      blat =  options[:blat]
-      table = options[:table]
-      level = options[:level]
+      blat   = options[:blat]
+      table  = options[:table]
+      level  = options[:level]
       output = options[:output] || $stdout
 
       levels = { 'kingdom' => 0,
@@ -28,7 +28,9 @@ module Lederhosen
                  'genus'   => 5,
                  'species' => 6 }
 
-      fail "unknown level. try #{levels.keys.join(', ')}" unless levels.include? level
+      ohno "unknown level #{level}. try #{levels.keys.join(', ')}" unless levels.include? level
+
+      ohai "adding names to #{table} using #{blat} @ #{levels[level]} (#{level}). Saving to #{output}"
 
       # Corresponds with the numbers used in the TaxCollector database
       # taxonomic descriptions

data/lib/lederhosen/tasks/cluster.rb

@@ -27,6 +27,12 @@ module Lederhosen
       wordlen    = options[:wordlen]
       lib        = options[:lib]
 
+      ohai "clustering #{input}, saving to #{output}"
+
+      options.each_pair do |key, value|
+        ohai "#{key} = #{value}"
+      end
+
       cmd = [
         'uclust',
         "--input #{input}",

data/lib/lederhosen/tasks/join.rb

@@ -11,11 +11,12 @@ module Lederhosen
     method_option :output,  :type => :string, :required => true
 
     def join
-
       trimmed = Dir[options[:trimmed]]
-      output = options[:output]
+      output  = options[:output]
+
+      ohai "joining #{File.dirname(trimmed.first)} saving to #{output}"
 
-      fail "no reads in #{trimmed}" if trimmed.length == 0
+      ohno "no reads in #{trimmed}" if trimmed.length == 0
 
       output = File.open(output, 'w')
 

data/lib/lederhosen/tasks/k_filter.rb

@@ -19,12 +19,13 @@ module Lederhosen
       k_len  = options[:k].to_i
       cutoff = options[:cutoff]
 
+      ohai "kmer filtering #{input} (k = #{k_len}, cutoff = #{cutoff})"
+
       counting_table = Hash.new { |h, k| h[k] = 0 }
       total_reads = 0
 
-      ohai "counting kmers"
       total_reads = `grep -c '^>' #{input}`.strip.split.first.to_i
-      pbar = ProgressBar.new 'count kmers', total_reads.to_i
+      pbar = ProgressBar.new 'counting', total_reads.to_i
       File.open(input) do |handle|
         records = Dna.new handle
         records.each do |r|

data/lib/lederhosen/tasks/name.rb

@@ -17,6 +17,8 @@ module Lederhosen
       database = options[:database]
       output   = options[:output]
 
+      ohai "identifying #{reps} in #{database} and saving to #{output}"
+
       # run blat/blast
       cmd = [
         'blat',

data/lib/lederhosen/tasks/otu_filter.rb

@@ -14,6 +14,8 @@ module Lederhosen
       reads   = options[:reads]
       samples = options[:samples]
 
+      ohai "filtering otu file #{input} (reads = #{reads}, samples = #{samples}), saving to #{output}"
+
       ##
       # Iterate over otu table line by line.
       # Only print if cluster meets criteria

data/lib/lederhosen/tasks/otu_table.rb

@@ -16,7 +16,8 @@ module Lederhosen
     def otu_table
       input        = options[:clusters]
       output       = options[:output]
-      joined_reads = options[:joined]
+
+      ohai "generating otu table from #{input}, saving to #{output}"
 
       # Load cluster table
 

data/lib/lederhosen/tasks/rep_reads.rb

@@ -17,6 +17,7 @@ module Lederhosen
       output       = options[:output]
       joined_reads = options[:joined]
 
+      ohai "getting represntative reads for #{input} w/ reads #{joined_reads} and saving to #{output}"
 
       # Load cluster table!
       clstr_info      = Helpers.load_uc_file input

data/lib/lederhosen/tasks/sort.rb

@@ -12,8 +12,11 @@ module Lederhosen
     method_option :output, :type => :string, :required => true
 
     def sort
-      input = options[:input]
+      input  = options[:input]
       output = options[:output]
+
+      ohai "sorting #{input}"
+
       @shell.mute {
         run "uclust --mergesort #{input} --output #{output}"
       }

data/lib/lederhosen/tasks/split.rb

@@ -22,6 +22,9 @@ module Lederhosen
       min_clst_size = options[:min_clst_size]
       finalize_every = 100_000
 
+      ohai "spltting #{reads} by #{clusters} and saving to #{out_dir}"
+      ohai "minimum cluster size = #{min_clst_size}"
+
       run "mkdir -p #{out_dir}/"
 
       ohai "loading #{clusters}"

data/lib/lederhosen/tasks/squish.rb

@@ -14,9 +14,12 @@ module Lederhosen
       csv_file = options[:csv_file]
       output   = options[:output] || $stdout
 
+      ohai "squishing #{csv_file} to #{output}"
+
       # sample_name -> column name -> total number of reads
       total_by_sample_by_column = Hash.new { |h, k| h[k] = Hash.new { |h, k| h[k] = 0 } }
       column_names = '' # scope
+
       # Load CSV file, merge counts in columns with the same name
       File.open(csv_file) do |handle|
         column_names = handle.gets.strip.split(',')[1..-1]

data/lib/lederhosen/tasks/trim.rb

@@ -12,25 +12,26 @@ module Lederhosen
     method_option :out_dir,   :type => :string, :required => true
 
     def trim
-
       raw_reads = options[:reads_dir]
-      out_dir = options[:out_dir]
+      out_dir   = options[:out_dir]
+
+      ohai "trimming #{File.dirname(raw_reads)} and saving to #{out_dir}"
 
       run "mkdir -p #{out_dir}"
 
       raw_reads = Helpers.get_grouped_qseq_files raw_reads
+
       ohai "found #{raw_reads.length} pairs of reads"
 
       pbar = ProgressBar.new "trimming", raw_reads.length
-
       raw_reads.each do |a|
         pbar.inc
         out = File.join(out_dir, "#{File.basename(a[0])}.fasta")
         # TODO get total and trimmed
         total, trimmed = Helpers.trim_pairs a[1][0], a[1][1], out, :min_length => 70
       end
-
       pbar.finish
+
     end
   end
 end

data/lib/lederhosen/tasks/uc_filter.rb

@@ -20,6 +20,8 @@ module Lederhosen
       reads   = options[:reads].to_i
       samples = options[:samples].to_i
 
+      ohai "filtering #{input} to #{output}, reads = #{reads} & samples = #{samples}"
+
       # load UC file
       clstr_info   = Helpers.load_uc_file input
       clstr_counts = clstr_info[:clstr_counts] # clstr_counts[:clstr][sample.to_i] = reads

data/lib/lederhosen/tasks/uc_stats.rb

@@ -12,6 +12,8 @@ module Lederhosen
     def uc_stats
       input = options[:input]
 
+      ohai "calculating statistics for #{input}"
+
       # TODO add more stats
       cluster_stats = Hash.new { |h, k|
         h[k] = {

data/lib/lederhosen/tasks/uniquify.rb

@@ -18,12 +18,17 @@ module Lederhosen
       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 }
 
       out = File.open(output, 'w')
 
+      no_records = `grep -c #{input} '^>'`.split.first.to_i
+      pbar = ProgressBar.new 'loading', no_records
       File.open(input) do |handle|
         Dna.new(handle).each do |record|
+          pbar.inc
           unless sequence_counts.has_key? record.sequence
             out.puts record
           end
@@ -31,16 +36,19 @@ module Lederhosen
         end
       end
 
+      pbar.finish
       out.close
 
       # write table
+      pbar = ProgressBar.new 'table', no_records
       File.open(table_out, 'w') do |out|
         sequence_counts.each_pair do |sequence, count|
+          pbar.inc
           digest = Digest::MD5.hexdigest(sequence)
           out.puts "#{digest},#{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})"

data/lib/lederhosen/version.rb

@@ -2,7 +2,7 @@ module Lederhosen
   module Version
     MAJOR = 0
     MINOR = 2
-    PATCH = 9
+    PATCH = 10
 
     STRING = [MAJOR, MINOR, PATCH].join('.')
   end

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: lederhosen
 version: !ruby/object:Gem::Version 
-  hash: 5
+  hash: 3
   prerelease: 
   segments: 
   - 0
   - 2
-  - 9
-  version: 0.2.9
+  - 10
+  version: 0.2.10
 platform: ruby
 authors: 
 - Austin G. Davis-Richardson