bio-gag 0.0.1 → 0.1.0

data/Gemfile

@@ -4,6 +4,7 @@ source "http://rubygems.org"
 #   gem "activesupport", ">= 2.3.5"
 gem 'bio-pileup_iterator', '>=0.0.1'
 gem 'bio-logger', '>=1.0.0'
+gem 'progressbar'
 
 # Add dependencies to develop your gem here.
 # Include everything needed to run rake, tests, features, etc.

data/README.rdoc

@@ -7,13 +7,19 @@ bio-gag is a biogem for detecting and correcting a particular type of error that
 * Ion Sequencing 100 Kit
 * Ion Sequencing 200 Kit
 
-Newer versions of these kits do not appear to be affected by this error, starting with the "Ion PGM 200 Sequencing Kit". There are discussions about this on the (closed access) Ion Torrent forum: 
+Newer versions of these kits do not appear to be affected by this error, starting with the "Ion PGM 200 Sequencing Kit". *gag error* is the term I've coined to describe an error that various people have observed on certain sequencing kits with IonTorrent, though it has not previously been characterised very well that I know of (we noticed that the errors seemed to occur at GAG positions in the reads that were supposed to be GAAG). This biogem tries to find and fix these errors.
 
+Errors that appear to be of this type were recently refered to in a benchtop sequencing platform comparison (Supplementary figure 4):
+
+* http://www.ncbi.nlm.nih.gov/pubmed?term=22522955
+
+There are also some more in-depth discussions about this on the (closed access) Ion Torrent forum: 
+
+* http://lifetech-it.hosted.jivesoftware.com/message/6233
 * http://lifetech-it.hosted.jivesoftware.com/message/7893
 * http://lifetech-it.hosted.jivesoftware.com/message/7792
-* http://lifetech-it.hosted.jivesoftware.com/message/6233
 
-To search for these errors, a pileup format file of aligned sequences is required. These can be generated either from an assembly or by aligning to a reference, although it has only been tested on de-novo assemblies assembled with newbler. Note that it is probably not optimised due to time constraints combined with the fact they appear to have been fixed in newer kits.
+To search for these errors, a pileup format file of aligned sequences is required. These can be generated either from an assembly or by aligning to a reference, although it has only been tested on de-novo assemblies assembled with newbler. Note that it has not been entirely optimised due to regular time constraints combined with the fact they appear to have been fixed in newer kits.
 
 == Installation
 
@@ -57,7 +63,7 @@ Information on the source tree, documentation, issues and how to contribute, see
 
 == Cite
 
-  If you use this software, please cite http://dx.doi.org/10.1093/bioinformatics/btq475
+  Currently, this bio-gem is unpublished, but a relevant manuscript is in the works.
 
 == Biogems.info
 

data/VERSION

@@ -1 +1 @@
-0.0.1
+0.1.0

data/bin/gag

@@ -1,6 +1,7 @@
 #!/usr/bin/env ruby
 
 require 'bio'
+require 'progressbar'
 
 $:.unshift File.join(File.dirname(__FILE__),'..','lib')
 require 'bio-gag'
@@ -19,25 +20,47 @@ options = {
   :operation => FIND,
   :logger => 'stderr',
   :trace => 'info',
+  :progress => true,
 }
 o = OptionParser.new do |opts|
-  opts.banner = "\ngag [options] <pileup_output>\n\n"
+  opts.banner = "\ngag <operation> <arguments>\n\n"
 
 
-  opts.on('--lookahead', 'Work out if gag predictions are supported by orf predictions being extended [default is just to print out found gag errors]. There\'s modifed usage too - probably best for you to look at the code if you are using this operation') do |v|
+  opts.separator "\nOperations:\n\n"
+  opts.on('--find', 'Simply find gag errors given a pileup file. This is the default mode of operation. Usage: gag --find <pileup>') do
+    options[:operation] = FIND
+  end
+  opts.on('--lookahead', 'Work out if gag predictions are supported by orf predictions being extended [default is just to print out found gag errors]. '+
+    'Currently requires prodigal gene predictions in fasta format. Usage: gag --lookahead <gene_predictions1> <gene_predictions2> <gag_predictions>') do
     options[:operation] = LOOKAHEAD
   end
-  
-  opts.on('--fix CONSENSUS_FASTA_FILE', 'Find gag errors in the pileup file, correct them in CONSENSUS_FASTA_FILE, and print to STDOUT the fixed up consensus') do |v|
+  opts.on('--fix CONSENSUS_FASTA_FILE', 'Find gag errors in the pileup file, correct them in CONSENSUS_FASTA_FILE, and print to STDOUT the fixed up consensus. '+
+    'Usage: gag --fix <fasta_file> [-g <gag_predictions>]') do |v|
     options[:operation] = FIX
     options[:fix_file] = v
   end
   
+  opts.separator "\nOptions:\n\n"
+  opts.on('-p','--pileup PILEUP_FILE', 'Pileup file to be fixed [required for some operations]') do |v|
+    options[:pileup_file] = v
+  end
+  opts.on('--contexts TRINUCLEOTIDES',"Specify a comma separated set of sequences to look for gag errors in, or \'false\' to look for all possible trinucleotide contexts [Default: #{Bio::DB::PileupIterator::DEFAULT_GAG_ERROR_CONTEXTS.join(',')}]") do |v|
+    if v.downcase=='false'
+      options[:acceptable_gag_errors] = Bio::DB::PileupIterator::ALL_POSSIBLE_GAG_ERROR_CONTEXTS
+    else
+      options[:acceptable_gag_errors] = v.split(',').collect{|s| s.strip}.compact      
+    end
+  end
   opts.on('-g','--gags GAG_FILE', 'Specify a list of GAG errors to be fixed in tab-separated form (use with --fix, the tab-separated output is from regular output or --lookahead)') do |v|
     options[:gags_file] = v
   end
 
 
+
+  opts.separator "\nVerbosity:\n\n"
+  opts.on('--no-progress',"Don't show the progressbar") do
+    options[:progress] = false
+  end
   opts.on("--logger filename",String,"Log to file (default STDERR)") do | name |
     options[:logger] = name
   end
@@ -62,7 +85,10 @@ Bio::Log::CLI.configure('bio-gag')
 log = Bio::Log::LoggerPlus.new 'gag'
 Bio::Log::CLI.configure('gag')
 
-piles = Bio::DB::PileupIterator.new(ARGF)
+piles = Bio::DB::PileupIterator.new(nil)
+unless options[:pileup_file].nil?
+  piles = Bio::DB::PileupIterator.new(File.open(options[:pileup_file]))
+end
 
 if options[:operation] == FIX
   # Cache the fasta sequences
@@ -107,6 +133,10 @@ elsif options[:operation] == LOOKAHEAD
   genes1_file = ARGV[0]
   genes2_file = ARGV[1]
   gag_predictions_file = ARGV[2]
+  if genes1_file.nil? or genes2_file.nil? or gag_predictions_file.nil?
+    log.error "Lookahead operation requires specific arguments. See 'gag --help'"
+    exit 1
+  end
   
   class GenePrediction
     attr_accessor :start, :stop, :direction, :name
@@ -270,6 +300,11 @@ elsif options[:operation] == LOOKAHEAD
 else
   # Don't do anything, just predict them
   
+  unless options[:pileup_file]
+    log.error "The find operation requires a pileup file, specified by -p/--pileup. See 'gag --help'"
+    exit 1
+  end
+  
   puts %w(
   ref_name
   position
@@ -277,7 +312,19 @@ else
   context
   ).join("\t")
   
-  piles.gags do |gag|
+  options[:acceptable_gag_errors] ||= Bio::DB::PileupIterator::DEFAULT_GAG_ERROR_CONTEXTS
+  log.info "Predicting errors within these contexts: #{options[:acceptable_gag_errors].join(', ')}"
+  
+  progress = nil
+  if options[:progress]
+    num_pileup_columns = File.foreach(options[:pileup_file]).inject(0) {|c, line| c+1}
+    progress = ProgressBar.new('bio-gag',num_pileup_columns)
+  end
+
+  piles.gags(:progressbar => progress, 
+    :acceptable_gag_errors => options[:acceptable_gag_errors]
+    ) do |gag|
+
     puts [
       gag.ref_name,
       gag.position,
@@ -285,4 +332,5 @@ else
       gag.gagging_pileups.collect{|g| g.ref_base}.join('')
     ].join("\t")
   end
+  progress.finish if options[:progress]
 end

data/lib/bio-gag.rb

@@ -2,7 +2,6 @@
 require 'bio-logger'
 Bio::Log::LoggerPlus.new('bio-gag')
 
-$:.unshift File.join(File.dirname(__FILE__),'../../bioruby-pileup_iterator/lib/')
 require 'bio-pileup_iterator'
 require 'bio/db/gag'
 

data/lib/bio/db/gag.rb

@@ -1,15 +1,25 @@
 
 
 class Bio::DB::PileupIterator
+  DEFAULT_GAG_ERROR_CONTEXTS = %w(GAG CTC  AGC GCT  GCG CGC  GCA TGC)
+  ALL_POSSIBLE_GAG_ERROR_CONTEXTS = %w(
+      GAG GTG GCG
+      CTC CAC CGC
+      AGA ACA ATA
+      TAT TGT TCT
+      )
+  
   # Find places in this pileup that correspond to GAG errors
   # * Only certain sequences are considered to be possible errors. Can change this with options[:acceptable_gag_errors]
-  # ** GAAG/CTTC (namesake of GAG errors. So GAG is looked for, to see if it is probably GAAG instead)
+  # ** GAAG/CTTC (namesake of GAG errors. I.e. GAG is looked for, to see if it is probably GAAG instead)
   # ** AGGC/GCCT
   # ** GCCG/CGGC
   # ** GCCA/TGGC
   # * There is at least 3 reads that have an insertion of base Y next to Y, and are all in the one direction. Can change this with options[:min_disagreeing_absolute]
   # * The 3 or more reads form at least a proportion of 0.1 (i.e. 10%) of all the reads at that position.  Can change this with options[:min_disagreeing_proportion]
   #
+  # To not restrict options[:acceptable_gag_errors] to any sequences, use  Bio::DB::PileupIterator::ALL_POSSIBLE_GAG_ERROR_CONTEXTS
+  #
   # Returns an array of Bio::Gag objects
   #
   # When a block is given, each gag is yielded
@@ -19,7 +29,7 @@ class Bio::DB::PileupIterator
     min_disagreeing_absolute = options[:min_disagreeing_absolute]
     min_disagreeing_absolute ||= 3
     
-    options[:acceptable_gag_errors] ||= %w(GAG CTC  AGC GCT  GCG CGC  GCA TGC)
+    options[:acceptable_gag_errors] ||= DEFAULT_GAG_ERROR_CONTEXTS
     
     log = Bio::Log::LoggerPlus['bio-gag']
     
@@ -27,6 +37,8 @@ class Bio::DB::PileupIterator
     gags = []
     
     each do |pile|
+      options[:progressbar].inc unless options[:progressbar].nil?
+      
       if piles.length < 2
         #log.debug "Piles cache for this reference sequence less than length 2"
         piles = [piles, pile].flatten
@@ -42,7 +54,7 @@ class Bio::DB::PileupIterator
         #log.debug "Piles cache regular push through"
         piles = [piles[1], piles[2], pile].flatten
       end
-      #log.debug "Current piles now at #{piles[0].ref_name}, #{piles.collect{|pile| "#{pile.pos}/#{pile.ref_base}"}.join(', ')}"
+      log.debug "Current piles now at #{piles[0].ref_name}, #{piles.collect{|pile| "#{pile.pos}/#{pile.ref_base}"}.join(', ')}" if log.debug?
       
       # if not at the start/end of the contig
       first = piles[0]
@@ -50,10 +62,10 @@ class Bio::DB::PileupIterator
       third = piles[2]
       
       # Require particular sequences in the reference sequence
-      ref_bases = "#{first.ref_base}#{second.ref_base}#{third.ref_base}"
+      ref_bases = "#{first.ref_base.upcase}#{second.ref_base.upcase}#{third.ref_base.upcase}"
       index = options[:acceptable_gag_errors].index(ref_bases)
       if index.nil?
-        #log.debug "Sequence #{ref_bases} does not match whitelist, so not calling a gag"
+        log.debug "Sequence #{ref_bases} does not match whitelist, so not calling a gag" if log.debug?
         next
       end
       gag_sequence = options[:acceptable_gag_errors][index]
@@ -63,11 +75,11 @@ class Bio::DB::PileupIterator
         !(read.insertions[first.pos] and read.insertions[second.pos]) and
         (read.insertions[first.pos] or read.insertions[second.pos])
       end
-      #log.debug "Inserting reads after filtering: #{inserting_reads.inspect}"
+      log.debug "Inserting reads after filtering: #{inserting_reads.inspect}" if log.debug?
       
       # ignore regions that aren't ever going to make it past the next filter
       if inserting_reads.length < min_disagreeing_absolute or inserting_reads.length.to_f/first.coverage < min_disagreeing_proportion
-        #log.debug "Insufficient disagreement at step 1, so not calling a gag"
+        log.debug "Insufficient disagreement at step 1, so not calling a gag" if log.debug?
         next
       end
 
@@ -82,17 +94,17 @@ class Bio::DB::PileupIterator
         base_counts[insert] ||= 0
         base_counts[insert] += 1
       end
-      #log.debug "Direction counts of insertions: #{direction_counts.inspect}"
-      #log.debug "Base counts of insertions: #{base_counts.inspect}"
+      log.debug "Direction counts of insertions: #{direction_counts.inspect}" if log.debug?
+      log.debug "Base counts of insertions: #{base_counts.inspect}" if log.debug?
       max_direction = direction_counts['+']>direction_counts['-'] ? '+' : '-'
       max_base = base_counts.max do |a,b|
         a[1] <=> b[1]
       end[0]
-      #log.debug "Picking max direction #{max_direction} and max base #{max_base}"
+      log.debug "Picking max direction #{max_direction} and max base #{max_base}" if log.debug?
       
       # Only accept positions that are inserting a single base
       if max_base.length > 1
-        #log.debug "Maximal insertion is too long, so not calling a gag"
+        log.debug "Maximal insertion is too long, so not calling a gag" if log.debug?
         next
       end
       
@@ -101,22 +113,22 @@ class Bio::DB::PileupIterator
         insert ||= read.insertions[second.pos]
         insert.upcase!
         if read.direction == max_direction and insert == max_base
-          # # Remove reads that don't match the first and third bases like the consensus sequence
+          # Remove reads that don't match the first and third bases like the consensus sequence
           read.sequence[read.sequence.length-1] == third.ref_base and
           read.sequence[read.sequence.length-3] == first.ref_base
         else
           false
         end
       end
-      #log.debug "Reads counting after final filtering: #{counted_inserts.inspect}"
+      log.debug "Reads counting after final filtering: #{counted_inserts.inspect}" if log.debug?
       
       coverage = (first.coverage+second.coverage+third.coverage).to_f / 3.0
       coverage_percent = counted_inserts.length.to_f / coverage
-      #log.debug "Final abundance calculations: max base #{max_base} (comparison base #{second.ref_base.upcase}) occurs #{counted_inserts.length} times compared to coverage #{coverage} (#{coverage_percent*10}%)"
+      log.debug "Final abundance calculations: max base #{max_base} (comparison base #{second.ref_base.upcase}) occurs #{counted_inserts.length} times compared to coverage #{coverage} (#{coverage_percent*10}%)" if log.debug?
       if max_base != second.ref_base.upcase or # first and second bases must be the same 
         counted_inserts.length < min_disagreeing_absolute or # require 3 bases in that maximal direction
         coverage_percent < min_disagreeing_proportion # at least 10% of reads with disagree with the consensus and agree with the gag
-        #log.debug "Failed final abundance cutoffs, so not calling a gag"
+        log.debug "Failed final abundance cutoffs, so not calling a gag" if log.debug?
         next
       end
       

data/test/test_bio-gag.rb

@@ -42,6 +42,15 @@ contig00091 8 G 32  ,,.,,....*.,,,.....,,.,,,,,,,.,.  aaRaaRRRRZRaaaRRRRRaaRaaaa
     gags = Bio::DB::PileupIterator.new(test).gags
     assert_equal [], gags.collect{|g| g.position}
   end
+  
+  should 'find gags when ref_base is lower-case' do
+    test = "contig00036 56618 G 19  ......-1C,...,.....,,.  ~~~~~il~~~l~~~~~ll~
+contig00036 56619 c 19  .....*,+1c...,+1c.....,+1c,+1c. tulutI$uuu$uuuuu$$u
+contig00036 56620 T 21  ......,...,.....,,.^].^], qrirqILrrrLrrrrrLLrNE".gsub(/ +/,"\t")
+    
+    gags = Bio::DB::PileupIterator.new(test).gags
+    assert_equal [56619], gags.collect{|g| g.position}
+  end
 
   should "fix gag" do
     test = "contig00091 1 G 32  ,,..,,......,,,.....,,.,,,,,,,.,  {;c{{{l{l{l{{{{{{{{{{{{{{{{{{{{U
@@ -56,7 +65,17 @@ contig00091 9 C 32  ,,.,,......,,,.....,,.,,,,,,,.,.  ~~i~~~~~~Z~~~~~~~~~~~~~~~~
 contig00091 10  A 33  ,,.,,......,,,.....,,.,,,,,,,.,.^]. aaPaa^aaaYaaaaaaaaaaaaaaaaaaaaaaB".gsub(/ +/,"\t")
     hash = {'contig00091' => 'GTTCGAGGC'}
     expe = {'contig00091' => 'GTTCGAAGGC'}
-    assert_equal expe, gags = Bio::DB::PileupIterator.new(test).fix_gags(hash)
+    assert_equal expe, Bio::DB::PileupIterator.new(test).fix_gags(hash)
+  end
+  
+  should 'fix a gag when ref_base is lower-case' do
+    test = "contig00036 1 G 19  ......-1C,...,.....,,.  ~~~~~il~~~l~~~~~ll~
+contig00036 2 c 19  .....*,+1c...,+1c.....,+1c,+1c. tulutI$uuu$uuuuu$$u
+contig00036 3 T 21  ......,...,.....,,.^].^], qrirqILrrrLrrrrrLLrNE".gsub(/ +/,"\t")
+    
+    hash = {'contig00036' => 'GCT'}
+    expe = {'contig00036' => 'GCCT'}
+    assert_equal expe, Bio::DB::PileupIterator.new(test).fix_gags(hash)
   end
   
   should "fix gag prespecified" do
@@ -120,20 +139,64 @@ contig00091 5 G 32  ,,..,,......,,,.....,,.,,,,,,,.,  {{Ii{{iiii@i{{{iiiii{{i{{{
 contig00091 6 A 33  ,,.$.+1A,,.+1A.+1A.+1A.+1A.+1A.+1A,,,.+1A.+1A.+1A.+1A.+1A,,.+1A,,,,,,,.+1A,^].  z{D${{$$$$!${{{$$$$${{${{{{{{{${E
 contig00091 7 G 32  ,,.,,.....-1G.,,,.....,,.,,,,,,,.,. aaRaaRRRR&RaaaRRRRRaaRaaaaaaaRaU
 contig00091 8 G 32  ,,.,,....*.,,,.....,,.,,,,,,,.,.  aaRaaRRRRZRaaaRRRRRaaRaaaaaaaRaa".gsub(/ +/,"\t")
-    command = File.join([File.dirname(__FILE__),%w(.. bin gag)].flatten)+ ' --trace info'
-    out = nil
-    err = nil
-    Open3.popen3(command) do |stdin, stdout, stderr|
-      stdin.puts test
-      stdin.close
-      out = stdout.readlines
-      err = stderr.readlines
+
+    Tempfile.open('stdin') do |input|
+      input.puts test
+      input.close
+      
+      command = File.join([File.dirname(__FILE__),%w(.. bin gag)].flatten)+ ' --trace warn --no-progress'+' -p '+input.path
+      out = nil
+      err = nil
+      Open3.popen3(command) do |stdin, stdout, stderr|
+        out = stdout.readlines
+        err = stderr.readlines
+      end
+      assert_equal [], err
+      assert_equal [
+        "ref_name\tposition\tinserted_base\tcontext\n",
+        "contig00091\t6\tA\tGAG\n"
+        ], out
+    end
+  end
+  
+  should 'run gagger predict with specified contexts correctly' do
+    test = "contig00091 4 C 32  ,,..,,......,,,.....,,.,,,,,,,.,  ~~I~~~u~u~t~~~~~~~~~~~~~~~~~~~~~
+contig00091 5 G 32  ,,..,,......,,,.....,,.,,,,,,,.,  {{Ii{{iiii@i{{{iiiii{{i{{{{{{{i{
+contig00091 6 A 33  ,,.$.+1A,,.+1A.+1A.+1A.+1A.+1A.+1A,,,.+1A.+1A.+1A.+1A.+1A,,.+1A,,,,,,,.+1A,^].  z{D${{$$$$!${{{$$$$${{${{{{{{{${E
+contig00091 7 G 32  ,,.,,.....-1G.,,,.....,,.,,,,,,,.,. aaRaaRRRR&RaaaRRRRRaaRaaaaaaaRaU
+contig00091 8 G 32  ,,.,,....*.,,,.....,,.,,,,,,,.,.  aaRaaRRRRZRaaaRRRRRaaRaaaaaaaRaa".gsub(/ +/,"\t")
+
+    Tempfile.open('stdin') do |input|
+      input.puts test
+      input.close
+      
+      command = File.join([File.dirname(__FILE__),%w(.. bin gag)].flatten)+ ' --trace warn --contexts GAG,CGC --no-progress'+' -p '+input.path
+      out = nil
+      err = nil
+      Open3.popen3(command) do |stdin, stdout, stderr|
+        out = stdout.readlines
+        err = stderr.readlines
+      end
+      assert_equal [], err
+      assert_equal [
+        "ref_name\tposition\tinserted_base\tcontext\n",
+        "contig00091\t6\tA\tGAG\n"
+        ], out
+        
+        
+      command = File.join([File.dirname(__FILE__),%w(.. bin gag)].flatten)+ ' --trace warn --contexts TGC,GCA --no-progress'+' -p '+input.path
+      out = nil
+      err = nil
+      Open3.popen3(command) do |stdin, stdout, stderr|
+        out = stdout.readlines
+        err = stderr.readlines
+      end
+      assert_equal [], err
+      assert_equal [
+        "ref_name\tposition\tinserted_base\tcontext\n",
+        # "contig00091\t6\tA\tGAG\n"
+        ], out
     end
-    assert_equal [], err
-    assert_equal [
-      "ref_name\tposition\tinserted_base\tcontext\n",
-      "contig00091\t6\tA\tGAG\n"
-      ], out
   end
 
   should "run gagger fix ok without gags pre-specified" do
@@ -154,21 +217,24 @@ contig00091 13  A 33  ,,.,,......,,,.....,,.,,,,,,,.,.^]. aaPaa^aaaYaaaaaaaaaaaa
       tempfile.puts '>contig00091'
       tempfile.puts 'GTTCGAGGAGGCA'
       tempfile.close
+      
+      Tempfile.open('stdin') do |input|
+        input.puts test
+        input.close
 
-      command = File.join([File.dirname(__FILE__),%w(.. bin gag)].flatten)+' --trace error --fix '+tempfile.path
-      out = nil
-      err = nil
-      Open3.popen3(command) do |stdin, stdout, stderr|
-        stdin.puts test
-        stdin.close
-        out = stdout.readlines
-        err = stderr.readlines
+        command = File.join([File.dirname(__FILE__),%w(.. bin gag)].flatten)+' --trace error --fix '+tempfile.path+' -p '+input.path
+        out = nil
+        err = nil
+        Open3.popen3(command) do |stdin, stdout, stderr|
+          out = stdout.readlines
+          err = stderr.readlines
+        end
+        assert_equal [], err
+        assert_equal [
+        ">contig00091\n",
+        "GTTCGAAGGAAGGCA\n"
+        ], out
       end
-      assert_equal [], err
-      assert_equal [
-      ">contig00091\n",
-      "GTTCGAAGGAAGGCA\n"
-      ], out
     end
   end
 
@@ -191,20 +257,23 @@ contig00091 13  A 33  ,,.,,......,,,.....,,.,,,,,,,.,.^]. aaPaa^aaaYaaaaaaaaaaaa
       tempfile.puts 'GTTCGAGGAGGCA'
       tempfile.close
 
-      command = File.join([File.dirname(__FILE__),%w(.. bin gag)].flatten)+' --trace error --fix '+tempfile.path
-      out = nil
-      err = nil
-      Open3.popen3(command) do |stdin, stdout, stderr|
-        stdin.puts test
-        stdin.close
-        out = stdout.readlines
-        err = stderr.readlines
+      Tempfile.open('stdin') do |input|
+        input.puts test
+        input.close
+        command = File.join([File.dirname(__FILE__),%w(.. bin gag)].flatten)+' --trace error --fix '+tempfile.path+' -p '+input.path
+      
+        out = nil
+        err = nil
+        Open3.popen3(command) do |stdin, stdout, stderr|
+          out = stdout.readlines
+          err = stderr.readlines
+        end
+        assert_equal [], err
+        assert_equal [
+        ">contig00091\n",
+        "GTTCGAAGGAAGGCA\n"
+        ], out
       end
-      assert_equal [], err
-      assert_equal [
-      ">contig00091\n",
-      "GTTCGAAGGAAGGCA\n"
-      ], out
     end
   end
 
@@ -222,22 +291,24 @@ contig00091 5 G 32  ,,.,,....*.,,,.....,,.,,,,,,,.,.  aaRaaRRRRZRaaaRRRRRaaRaaaa
       tempfile.puts 'ATGC'
       tempfile.close
 
-      command = File.join([File.dirname(__FILE__),%w(.. bin gag)].flatten)+ ' --trace error --fix '+tempfile.path
-      out = nil
-      err = nil
-      Open3.popen3(command) do |stdin, stdout, stderr|
-        stdin.puts test
-        stdin.close
-        out = stdout.readlines
-        err = stderr.readlines
+      Tempfile.open('stdin') do |input|
+        input.puts test
+        input.close
+        command = File.join([File.dirname(__FILE__),%w(.. bin gag)].flatten)+' --trace error --fix '+tempfile.path+' -p '+input.path
+        out = nil
+        err = nil
+        Open3.popen3(command) do |stdin, stdout, stderr|
+          out = stdout.readlines
+          err = stderr.readlines
+        end
+        assert_equal [], err
+        assert_equal [
+        ">contig00091\n",
+        "CGAAGG\n",
+        ">contig00092\n",
+        "ATGC\n"
+        ], out
       end
-      assert_equal [], err
-      assert_equal [
-      ">contig00091\n",
-      "CGAAGG\n",
-      ">contig00092\n",
-      "ATGC\n"
-      ], out
     end
   end
 
@@ -259,20 +330,25 @@ contig00090 5 G 32  ,,.,,....*.,,,.....,,.,,,,,,,.,.  aaRaaRRRRZRaaaRRRRRaaRaaaa
       tempfile.puts 'CGAGG'
       tempfile.close
 
-      command = File.join([File.dirname(__FILE__),%w(.. bin gag)].flatten)+ ' --trace warn --fix '+tempfile.path
-      out = nil
-      err = nil
-      Open3.popen3(command) do |stdin, stdout, stderr|
-        stdin.puts test
-        stdin.close
-        out = stdout.readlines
-        err = stderr.readlines
+      Tempfile.open('stdin') do |input|
+        input.puts test
+        input.close
+        
+        command = File.join([File.dirname(__FILE__),%w(.. bin gag)].flatten)+ ' --trace warn --fix '+tempfile.path+' -p '+input.path
+        out = nil
+        err = nil
+        Open3.popen3(command) do |stdin, stdout, stderr|
+          stdin.puts test
+          stdin.close
+          out = stdout.readlines
+          err = stderr.readlines
+        end
+        assert_equal [" WARN bio-gag: Unexpectedly found GAG errors in sequences that weren't in the sequence that are to be fixed: Found gags in 2, but only fixed 1\n"], err
+        assert_equal [
+        ">contig00091\n",
+        "CGAAGG\n",
+        ], out
       end
-      assert_equal [" WARN bio-gag: Unexpectedly found GAG errors in sequences that weren't in the sequence that are to be fixed: Found gags in 2, but only fixed 1\n"], err
-      assert_equal [
-      ">contig00091\n",
-      "CGAAGG\n",
-      ], out
     end
   end
   
@@ -293,20 +369,23 @@ contig00090 5 G 32  ,,.,,....*.,,,.....,,.,,,,,,,.,.  aaRaaRRRRZRaaaRRRRRaaRaaaa
       tempfile.puts 'CGAGG'
       tempfile.close
 
-      command = File.join([File.dirname(__FILE__),%w(.. bin gag)].flatten)+ ' --trace debug --fix '+tempfile.path
-      out = nil
-      err = nil
-      Open3.popen3(command) do |stdin, stdout, stderr|
-        stdin.puts test
-        stdin.close
-        out = stdout.readlines
-        err = stderr.readlines
+      Tempfile.open('stdin') do |input|
+        input.puts test
+        input.close
+        
+        command = File.join([File.dirname(__FILE__),%w(.. bin gag)].flatten)+ ' --trace debug --fix '+tempfile.path+' -p '+input.path
+        out = nil
+        err = nil
+        Open3.popen3(command) do |stdin, stdout, stderr|
+          out = stdout.readlines
+          err = stderr.readlines
+        end
+        assert err.length > 1, "expected more errors"
+        assert_equal [
+        ">contig00091\n",
+        "CGAAGG\n",
+        ], out
       end
-      assert err.length > 1, "expected more errors"
-      assert_equal [
-      ">contig00091\n",
-      "CGAAGG\n",
-      ], out
     end
   end
 
@@ -323,21 +402,23 @@ contig00090 5 G 32  ,,.,,....*.,,,.....,,.,,,,,,,.,.  aaRaaRRRRZRaaaRRRRRaaRaaaa
         gags_file.puts %w(contig00091 4 G CTC).join("\t")
         gags_file.close
 
-        command = File.join([File.dirname(__FILE__),%w(.. bin gag)].flatten)+" --trace error --fix #{tempfile.path} --gags #{gags_file.path}"
-        out = nil
-        err = nil
-        Open3.popen3(command) do |stdin, stdout, stderr|
-          stdin.puts test
-          stdin.close
-          out = stdout.readlines
-          err = stderr.readlines
+        Tempfile.open('stdin') do |input|
+          input.puts test
+          input.close
+          
+          command = File.join([File.dirname(__FILE__),%w(.. bin gag)].flatten)+" --trace error --fix #{tempfile.path} --gags #{gags_file.path} -p "+input.path
+          out = nil
+          err = nil
+          Open3.popen3(command) do |stdin, stdout, stderr|
+            out = stdout.readlines
+            err = stderr.readlines
+          end
+          assert_equal [], err
+          assert_equal [
+            ">contig00091\n",
+            "GTTTCCGAGGAGGCA\n"
+            ], out
         end
-        assert_equal [], err
-        assert_equal [
-          ">contig00091\n",
-          "GTTTCCGAGGAGGCA\n"
-          ], out
-
       end
     end
   end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: bio-gag
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 0.1.0
   prerelease: 
 platform: ruby
 authors:
@@ -9,11 +9,11 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-05-17 00:00:00.000000000 Z
+date: 2012-11-05 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bio-pileup_iterator
-  requirement: &86055840 !ruby/object:Gem::Requirement
+  requirement: &19062080 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -21,10 +21,10 @@ dependencies:
         version: 0.0.1
   type: :runtime
   prerelease: false
-  version_requirements: *86055840
+  version_requirements: *19062080
 - !ruby/object:Gem::Dependency
   name: bio-logger
-  requirement: &86055510 !ruby/object:Gem::Requirement
+  requirement: &19060660 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -32,10 +32,21 @@ dependencies:
         version: 1.0.0
   type: :runtime
   prerelease: false
-  version_requirements: *86055510
+  version_requirements: *19060660
+- !ruby/object:Gem::Dependency
+  name: progressbar
+  requirement: &19059240 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: *19059240
 - !ruby/object:Gem::Dependency
   name: shoulda
-  requirement: &86055220 !ruby/object:Gem::Requirement
+  requirement: &19074720 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -43,10 +54,10 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *86055220
+  version_requirements: *19074720
 - !ruby/object:Gem::Dependency
   name: rdoc
-  requirement: &86054930 !ruby/object:Gem::Requirement
+  requirement: &19070340 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -54,10 +65,10 @@ dependencies:
         version: '3.12'
   type: :development
   prerelease: false
-  version_requirements: *86054930
+  version_requirements: *19070340
 - !ruby/object:Gem::Dependency
   name: bundler
-  requirement: &86054570 !ruby/object:Gem::Requirement
+  requirement: &19067160 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -65,10 +76,10 @@ dependencies:
         version: 1.0.0
   type: :development
   prerelease: false
-  version_requirements: *86054570
+  version_requirements: *19067160
 - !ruby/object:Gem::Dependency
   name: jeweler
-  requirement: &86054260 !ruby/object:Gem::Requirement
+  requirement: &19082660 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -76,10 +87,10 @@ dependencies:
         version: 1.8.3
   type: :development
   prerelease: false
-  version_requirements: *86054260
+  version_requirements: *19082660
 - !ruby/object:Gem::Dependency
   name: bio
-  requirement: &86053790 !ruby/object:Gem::Requirement
+  requirement: &19081160 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -87,10 +98,10 @@ dependencies:
         version: 1.4.2
   type: :development
   prerelease: false
-  version_requirements: *86053790
+  version_requirements: *19081160
 - !ruby/object:Gem::Dependency
   name: rdoc
-  requirement: &86053100 !ruby/object:Gem::Requirement
+  requirement: &19079460 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -98,7 +109,7 @@ dependencies:
         version: '3.12'
   type: :development
   prerelease: false
-  version_requirements: *86053100
+  version_requirements: *19079460
 description: bio-gag is a biogem for detecting and correcting a particular type of
   error that occurs/occurred in particular versions of the IonTorrent DNA sequencing
   kit. Recent versions of the system don't appear to suffer the same problem
@@ -137,7 +148,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: 567820925
+      hash: 4012586911664634014
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements:
@@ -146,7 +157,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.17
+rubygems_version: 1.8.15
 signing_key: 
 specification_version: 3
 summary: bio-gag is a biogem for detecting and correcting a particular type of error