seqtrimnext 2.0.45 → 2.0.46

data/History.txt

@@ -1,3 +1,7 @@
+=== 2.0.46 2012-04-13
+
+Checkpointing activated. Jobs can be restarted where stopped.
+
 === 2.0.45 2012-03-05
 
 Improved LowComplexity plugin to ignore low complexity regions inside low qual regions

data/Manifest.txt

@@ -4,9 +4,11 @@ bin/extract_seqs_from_fasta.rb
 bin/extract_seqs_from_fastq.rb
 bin/fasta2fastq.rb
 bin/fastq2fasta.rb
+bin/filter_database.rb
 bin/gen_qual.rb
 bin/get_seq.rb
 bin/group_by_range.rb
+bin/join_big_illumina_paired.sh
 bin/join_ilumina_paired.rb
 bin/parse_amplicons.rb
 bin/parse_json_results.rb
@@ -18,6 +20,7 @@ bin/seqtrimnext
 bin/split_fastq.rb
 bin/split_ilumina_paired.rb
 bin/split_paired.rb
+History.txt
 lib/seqtrimnext/actions/action_ab_adapter.rb
 lib/seqtrimnext/actions/action_ab_far_adapter.rb
 lib/seqtrimnext/actions/action_ab_left_adapter.rb
@@ -35,13 +38,13 @@ lib/seqtrimnext/actions/action_low_complexity.rb
 lib/seqtrimnext/actions/action_low_high_size.rb
 lib/seqtrimnext/actions/action_low_quality.rb
 lib/seqtrimnext/actions/action_mid.rb
+lib/seqtrimnext/actions/action_middle_adapter.rb
 lib/seqtrimnext/actions/action_multiple_linker.rb
 lib/seqtrimnext/actions/action_paired_reads.rb
 lib/seqtrimnext/actions/action_poly_a.rb
 lib/seqtrimnext/actions/action_poly_t.rb
 lib/seqtrimnext/actions/action_rem_adit_artifacts.rb
 lib/seqtrimnext/actions/action_right_adapter.rb
-lib/seqtrimnext/actions/action_middle_adapter.rb
 lib/seqtrimnext/actions/action_right_primer.rb
 lib/seqtrimnext/actions/action_short_insert.rb
 lib/seqtrimnext/actions/action_unexpected_poly_t.rb
@@ -71,6 +74,7 @@ lib/seqtrimnext/classes/sequence_with_action.rb
 lib/seqtrimnext/plugins/plugin.rb
 lib/seqtrimnext/plugins/plugin_ab_adapters.rb
 lib/seqtrimnext/plugins/plugin_adapters.rb
+lib/seqtrimnext/plugins/plugin_adapters_old.rb
 lib/seqtrimnext/plugins/plugin_amplicons.rb
 lib/seqtrimnext/plugins/plugin_contaminants.rb
 lib/seqtrimnext/plugins/plugin_extract_inserts.rb
@@ -89,9 +93,11 @@ lib/seqtrimnext/plugins/plugin_vectors.rb
 lib/seqtrimnext/templates/amplicons.txt
 lib/seqtrimnext/templates/genomics_454.txt
 lib/seqtrimnext/templates/genomics_454_with_paired.txt
+lib/seqtrimnext/templates/genomics_illumina.txt
 lib/seqtrimnext/templates/low_quality.txt
 lib/seqtrimnext/templates/low_quality_and_low_complexity.txt
 lib/seqtrimnext/templates/transcriptomics_454.txt
+lib/seqtrimnext/templates/transcriptomics_illumina.txt
 lib/seqtrimnext/templates/transcriptomics_plants.txt
 lib/seqtrimnext/utils/extract_samples.rb
 lib/seqtrimnext/utils/fasta2xml.rb
@@ -103,7 +109,6 @@ lib/seqtrimnext/utils/load_qual_in_hash.rb
 lib/seqtrimnext/utils/recover_mid.rb
 lib/seqtrimnext/utils/string_utils.rb
 lib/seqtrimnext.rb
-History.txt
 Manifest.txt
 PostInstall.txt
 Rakefile

data/bin/filter_database.rb

@@ -0,0 +1,39 @@
+#!/usr/bin/env ruby
+
+require 'scbi_fasta'
+
+if ARGV.count!=3
+  puts "Usage: #{File.basename($0)} database min_size name_list"
+  exit
+end
+min_size = ARGV[1].to_i
+
+# read keywords
+keywords=File.read(ARGV[2]).split("\n")
+
+# convert all to upcase
+keywords.map { |keyword| keyword.upcase!}
+
+# puts "Search keywords"
+# keywords.each { |keyword| puts keyword}
+
+fqr=FastaQualFile.new(ARGV[0])
+
+all=[]
+
+fqr.each do |n,s,c|
+  keywords.each do |keyword|
+    if s.length<=min_size
+      # all+=c.split(" ")
+      if c.upcase.index(keyword)
+         # puts "[#{s.length.to_s}] - #{n} - #{c}"
+        puts ">#{n} #{c}\n#{s}"
+        break
+      end
+    end
+  end
+end
+
+# puts all.sort.uniq.reject{|e| e=~/\d/}
+
+fqr.close

data/bin/join_big_illumina_paired.sh

@@ -0,0 +1,122 @@
+#!/usr/bin/env bash
+
+# Sort two big illumina files corresponding to paired-end experiment and then join common sequences on different files. Sequences not in common goes to a separate file.
+
+# cat $1 | awk '{split($0, a, " "); n++; if (n%1==0){printf("%s\t",a[1]);}; printf("%s",$0); if(n%4==0) { printf("\n");} else { printf("\t");} }'
+# 
+# exit
+
+if [ "$#" < 4 ]; 
+then
+    echo ""
+	echo "Use: $0 file1.fastq file2.fastq base_output_name tmp_dir"
+    echo ""
+	exit
+fi
+
+base_name=$3
+
+if [[ -z "$base_name" ]]; then
+    echo "Use a : $base_name doesn't exists"
+    exit -1
+fi
+
+tmp_dir=$4
+
+if [[ -z "$4" ]]; then
+    tmp_dir=`pwd`
+fi
+
+if [[ ! -e "$tmp_dir" ]]; then
+    echo "Tmp dir: $4 doesn't exists"
+    exit -1
+fi
+
+echo "Using TMPDIR $tmp_dir"
+
+f1_path=$1
+f2_path=$2
+
+f1_name=`basename $1`
+f2_name=`basename $2`
+
+f1_tmp="$tmp_dir/${f1_name}"
+f2_tmp="$tmp_dir/${f2_name}"
+
+common_names="$tmp_dir/comm.names"
+
+only_in_1="$tmp_dir/only_in_1.txt"
+only_in_2="$tmp_dir/only_in_2.txt"
+in_both="$tmp_dir/in_both.txt"
+
+
+echo "Starting sorting"
+
+if [[ ! -e "$f1_tmp.sorted" ]]; then
+    echo "Sorting $f1_name"
+    cat $f1_path | awk '{split($0, a, " "); sub(/\/1$/,"\t", a[1]); n++; if (n%4==1){printf("%s",a[1]);}; printf("%s",$0); if(n%4==0) { printf("\n");} else { printf("\t");} }' | sort -T $tmp_dir -k1,1 -t $'\t' > $f1_tmp.sorted &
+
+fi
+
+if [[ ! -e "$f2_tmp.sorted" ]]; then
+    echo "Sorting $f2_name"
+    cat $f2_path | awk '{split($0, a, " "); sub(/\/2$/,"\t", a[1]); n++; if (n%4==1){printf("%s",a[1]);}; printf("%s",$0); if(n%4==0) { printf("\n");} else { printf("\t");} }' | sort -T $tmp_dir -k1,1 -t $'\t' > $f2_tmp.sorted &
+fi
+wait
+
+echo "Starting name extraction"
+if [[ ! -e "$f1_tmp.names" ]]; then
+    echo "Extracting names from $f1_tmp.sorted"
+    # cat $1.sorted | cut -f1 | sed 's/\(.*\)\/1$/\1/' > $1.names &
+    cat $f1_tmp.sorted | cut -f1  > $f1_tmp.names &
+fi
+if [[ ! -e "$f2_tmp.names" ]]; then
+    echo "Extracting names from $f2_tmp.sorted"
+    cat $f2_tmp.sorted | cut -f1  > $f2_tmp.names &
+fi
+wait
+
+echo "Starting names comparison"
+if [[ ! -e "$common_names" ]]; then
+    echo "Making comm file"
+    # diff $1.names $2.names > names.diff
+    comm $f1_tmp.names $f2_tmp.names > $common_names
+fi
+
+echo "Starting names extraction"
+# grep '^>' names.diff | cut -d ' ' -f2 | awk '{ printf("%s/2\n",$0) }' > only_in_2.txt &
+# grep '^<' names.diff | cut -d ' ' -f2 | awk '{ printf("%s/1\n",$0) }' > only_in_1.txt &
+
+grep -P '^[^\t]' $common_names > $only_in_1 &
+grep -P '^\t[^\t]' $common_names |tr -d "\t" > $only_in_2 &
+grep -P '^\t\t[^\t]' $common_names |tr -d "\t" > $in_both &
+wait
+
+echo "Num seqs only in 1) $f1_name"
+wc -l $only_in_1
+
+echo "Num seqs only in 2) $f2_name"
+wc -l $only_in_2
+
+echo "Num seqs in both $f1_name and $f2_name"
+wc -l $in_both
+
+echo "Starting extracting seqs"
+join -t $'\t' -1 1 -2 1 $only_in_1 $f1_tmp.sorted |cut -f 2,3,4,5| tr "\t" "\n" > ${base_name}_normal1.fastq &
+join -t $'\t' -1 1 -2 1 $only_in_2 $f2_tmp.sorted |cut -f 2,3,4,5| tr "\t" "\n" > ${base_name}_normal2.fastq &
+
+join -t $'\t' -1 1 -2 1 $in_both $f1_tmp.sorted  |cut -f 2,3,4,5| tr "\t" "\n" > ${base_name}_paired1.fastq &
+join -t $'\t' -1 1 -2 1 $in_both $f2_tmp.sorted  |cut -f 2,3,4,5| tr "\t" "\n" > ${base_name}_paired2.fastq &
+wait
+
+rm $f1_tmp.names
+rm $f2_tmp.names
+
+rm $f1_tmp.sorted
+rm $f2_tmp.sorted
+
+rm $only_in_2
+rm $only_in_1
+rm $in_both
+
+rm $common_names

data/bin/seqtrimnext

@@ -57,6 +57,7 @@
 # $: << File.expand_path(ROOT_PATH)
 
 $: << File.expand_path('~/progs/ruby/gems/seqtrimnext/lib/')
+$: << File.expand_path('~/progs/ruby/gems/scbi_mapreduce/lib/')
 
 require 'seqtrimnext'
 
@@ -272,7 +273,7 @@ optparse = OptionParser.new do |opts|
   end
   
   options[:skip_report] = false
-  opts.on( '-R', '--no-report', 'Change to no verbose mode. Every sequence will not be written to output log' ) do
+  opts.on( '-R', '--no-report', 'Do not generate final PDF report (gem scbi_seqtrimnext_report required if you want to generate PDF report).' ) do
     options[:skip_report] = true
   end
 

data/lib/seqtrimnext/classes/em_classes/seqtrim_work_manager.rb

@@ -18,29 +18,21 @@ class SeqtrimWorkManager < ScbiMapreduce::WorkManager
     @@params= params
     @@exit = false
 
+    @@ongoing_stats={}
+    @@ongoing_stats[:sequence_count] = 0
+    @@ongoing_stats[:smallest_sequence_size] = 900000000000000
+    @@ongoing_stats[:biggest_sequence_size] = 0
+    
     @@skip_output=skip_output
 
     @@chunk_size = chunk_size
 
-
-    # puts "CHECKPOINT: #{self.checkpoint}\n"*20
-
-    checkpoint_exists=File.exists?('scbi_drb_checkpoint')
+    checkpoint_exists=File.exists?(ScbiMapreduce::CHECKPOINT_FILE)
 
     # @@use_qual = !qual_path.nil? and File.exists?(qual_path)
     @@open_mode='w'
     if checkpoint_exists
       @@open_mode = 'a'
-      if File.exists?(STATS_PATH)
-        # load stats
-        text = File.read(STATS_PATH)
-
-        # wipe text
-        # text=text.grep(/^\s*[^#]/).to_s
-
-        # decode json
-        @@full_stats = JSON.parse(text)
-      end
     end
 
     #open input file
@@ -91,67 +83,38 @@ class SeqtrimWorkManager < ScbiMapreduce::WorkManager
 
     puts "FULL STATS:\n" +JSON.pretty_generate(@@full_stats)
 
+    # create stats file
     f = File.open(STATS_PATH,'w')
     f.puts JSON.pretty_generate(@@full_stats)
     f.close
 
-    r=File.read(STATS_PATH)
+    # if initial files doesn't exists, create it
+    if !File.exists?(File.join(OUTPUT_PATH,'initial_stats.json'))
+      File.open(File.join(OUTPUT_PATH,'initial_stats.json'),'w') do |f|
+        f.puts JSON.pretty_generate(@@ongoing_stats)
+      end
+    end
+    
 
+    # load stats
+    r=File.read(STATS_PATH)
     stats=JSON::parse(r)
 
+    
 
+    # make graphs
     gs=GraphStats.new(stats)
 
-    #gs=GraphStats.new(@@full_stats)
-
-
     #close all files
-
-    # @@fqr.close
     if @@use_json
       @@json_output.close
     end
     @@errors_file.close
-    # @@rejected_output_file.close
-
-    # @@paired_output_files.each do |k,file|
-    #   file.close
-    # end
 
     @@files.each do |k,file|
       file.close
     end
 
-    # @@paired_qual_output_files.each do |k,file|
-    #            file.close
-    # end
-
-    # @@sequences_output_files.each do |k,file|
-    #   file.close
-    # end
-    #
-    # @@low_complexity_output_files.each do |k,file|
-    #   file.close
-    # end
-    #
-    # @@sffinfo_files.each do |k,file|
-    #   file.close
-    # end
-    #
-    # @@low_sffinfo_files.each do |k,file|
-    #   file.close
-    # end
-
-
-    # @@qual_output_files.each do |k,file|
-    #  file.close
-    # end
-
-    # more than one MID found
-    # if @@full_stats['mid_id'] && @@full_stats['mid_id'].count>1
-    #
-    # end
-
     if File.exists?('scbi_drb_checkpoint')
       File.delete('scbi_drb_checkpoint')
     end
@@ -172,21 +135,71 @@ class SeqtrimWorkManager < ScbiMapreduce::WorkManager
   end
 
   def load_user_checkpoint(checkpoint)
+    # load full_stats from file !!!!!!!!!!!!!
 
-    # reset count stats since they are repeated by checkpointing
+    if File.exists?(STATS_PATH)
 
-    if @@full_stats['sequences'] && @@full_stats['repeated']
-      @@full_stats['sequences']['count']['repeated']=0
-    end
-    
-    if @@full_stats['sequences'] && @@full_stats['processed']
-      @@full_stats['sequences']['processed']['count']=0
+      # load stats
+      text = File.read(STATS_PATH)
+
+      # wipe text
+      # text=text.grep(/^\s*[^#]/).to_s
+
+      # decode json
+      @@full_stats = JSON.parse(text)
     end
-    
-    if @@full_stats['sequences'] && @@full_stats['total']
-      @@full_stats['sequences']['total']['count']=0
+
+    # reset count stats since they are repeated by checkpointing
+
+    # {
+    #   "sequences": {
+    #   "count": {
+    #     "input_count": 1600,
+    #     "output_seqs": 933,
+    #     "rejected": 67
+    #   },
+    #   "rejected": {
+    #     "short insert": 39,
+    #     "contaminated": 26,
+    #     "unexpected vector": 2
+    #   }
+    # }
+    # }
+
+    if @@full_stats['sequences']
+      if @@full_stats['sequences']['count']
+        # set input count to 0
+        @@full_stats['sequences']['count']['input_count']=0
+
+        # do not remove outputseqs
+        # @@full_stats['sequences']['count']['output_seqs']=0
+      end
+
+      # remove rejected due to repetitions from rejected count
+      if @@full_stats['sequences']['rejected']
+
+        # it there are repeated
+        if (@@full_stats['sequences']['rejected']['repeated'])
+
+          # if repeated count > 0 and there count exists
+          if (@@full_stats['sequences']['rejected']['repeated'] > 0) and @@full_stats['sequences']['count']
+
+            # discount repeated from rejected, since they are going to be added again by checkout process
+            @@full_stats['sequences']['count']['rejected'] -= @@full_stats['sequences']['rejected']['repeated']
+          end
+
+          # set repeated to 0
+          @@full_stats['sequences']['rejected']['repeated']=0
+        end
+      end
     end
 
+
+    # puts "Loaded Stats"
+    # puts "FULL STATS:\n" +JSON.pretty_generate(@@full_stats)
+
+    # TODO - remove sequences from rejected file that were added by cloned 
+
     super
     # return checkpoint
   end
@@ -202,17 +215,7 @@ class SeqtrimWorkManager < ScbiMapreduce::WorkManager
 
   # read a work that will not be processed, only to skip until checkpoint
   def trash_checkpointed_work
-
-    @@chunk_size.times do
-      begin
-        n,f,q,c = @@fqr.next_seq
-      end while (!n.nil? && @@params.repeated_seq?(n))
-
-      if n.nil?
-        break
-      end
-    end
-
+    warn "Deprecated: trash_checkpointed_work was deprecated, it is automatic now"
   end
 
   def next_work
@@ -228,12 +231,16 @@ class SeqtrimWorkManager < ScbiMapreduce::WorkManager
       if !n.nil? && @@params.repeated_seq?(n)
         @@full_stats.add_stats({'sequences' => {'count' => {'rejected' => 1}}})
         @@full_stats.add_stats({'sequences' => {'rejected' => {'repeated' => 1}}})
-
+                
         get_file(File.join(OUTPUT_PATH,'rejected.txt')).puts('>'+n+ ' repeated')
-        
+
       end
-      
+
       if !n.nil?
+        @@ongoing_stats[:sequence_count] += 1
+        @@ongoing_stats[:smallest_sequence_size] = [f.size, @@ongoing_stats[:smallest_sequence_size]].min
+        @@ongoing_stats[:biggest_sequence_size] = [f.size, @@ongoing_stats[:smallest_sequence_size]].max
+        
         @@full_stats.add_stats({'sequences' => {'count' => {'input_count' => 1}}})
       end
     end while (!n.nil? && @@params.repeated_seq?(n))
@@ -247,50 +254,9 @@ class SeqtrimWorkManager < ScbiMapreduce::WorkManager
 
   end
 
-  # def next_work
-  #
-  #     if @@exit
-  #       return nil
-  #     end
-  #     group = SequenceGroup.new
-  #
-  #     @@chunk_size.times do
-  #       begin
-  #
-  #         n,f,q,c = @@fqr.next_seq
-  #
-  #         if !n.nil? && @@params.repeated_seq?(n)
-  #           @@full_stats.add_stats({'sequences' => {'count' => {'rejected' => 1}}})
-  #           @@full_stats.add_stats({'sequences' => {'rejected' => {'repeated' => 1}}})
-  #
-  #           get_file(File.join(OUTPUT_PATH,'rejected.txt')).puts('>'+n+ ' repeated')
-  #
-  #         end
-  #         if !n.nil?
-  #           @@full_stats.add_stats({'sequences' => {'count' => {'input_count' => 1}}})
-  #         end
-  #       end while (!n.nil? && @@params.repeated_seq?(n))
-  #
-  #       if !n.nil?
-  #         # @@full_stats.add_stats({'sequences' => {'count' => {'processed' => 1}}})
-  #         group.push SequenceWithAction.new(n,f.upcase,q,c)
-  #       else
-  #         break
-  #       end
-  #     end
-  #
-  #     # puts "Processing #{group.inspect}"
-  #
-  #     if group.empty?
-  #       return nil
-  #     else
-  #       return group
-  #     end
-  #
-  #   end
 
   def work_received(obj)
-    
+
     res = obj
 
     # collect stats

data/lib/seqtrimnext/classes/em_classes/seqtrim_worker.rb

@@ -19,6 +19,9 @@
 # 
 # $: << File.expand_path(ROOT_PATH)
 
+$: << File.expand_path('~/progs/ruby/gems/seqtrimnext/lib/')
+$: << File.expand_path('~/progs/ruby/gems/scbi_mapreduce/lib')
+
 require 'seqtrimnext'
 
 $SEQTRIM_PATH = ROOT_PATH
@@ -37,7 +40,7 @@ ENV['BLASTDB']=$FORMATTED_DB_PATH
 OUTPUT_PATH='output_files'
 
 puts "FORMATTED_DB_BLAST in workers: #{$FORMATTED_DB_PATH}"
-# $: << File.expand_path('~/progs/ruby/gems/scbi_mapreduce/lib')
+
 
 require 'scbi_mapreduce'
 require 'params'

data/lib/seqtrimnext/classes/graph_stats.rb

@@ -10,8 +10,13 @@ class GraphStats
     init_stats=initial_stats
     
     if init_stats.nil?
-      r=File.read(File.join(OUTPUT_PATH,'initial_stats.json'))
-      init_stats= JSON::parse(r)
+      if File.exists?(File.join(OUTPUT_PATH,'initial_stats.json'))
+        r=File.read(File.join(OUTPUT_PATH,'initial_stats.json'))
+        init_stats= JSON::parse(r)
+      else
+        init_stats=[]
+      end
+      
     end
     # puts init_stats.to_json
     #r=File.read(File.join(File.dirname(__FILE__),'stats.json'))

data/lib/seqtrimnext/classes/seqtrim.rb

@@ -5,8 +5,6 @@
 
 require 'extract_stats'
 
-# $: << File.expand_path('~/progs/ruby/gems/scbi_drb/lib')
-
 require 'scbi_mapreduce'
 require 'seqtrim_work_manager' 
 require 'action_manager'
@@ -340,6 +338,9 @@ class Seqtrim
         # server = ScbiMapreduce::Manager.new(ip,port, workers, SeqtrimWorkManager,custom_worker_file, STDOUT,'~/.seqtrimnext')
 				server = ScbiMapreduce::Manager.new(ip,port, workers, SeqtrimWorkManager,custom_worker_file, STDOUT,$SEQTRIMNEXT_INIT)
 				server.chunk_size=chunk_size
+        server.checkpointing=true
+        server.keep_order=true
+        server.retry_stuck_jobs=true
 				server.start_server
         
         # close sequence reader

data/lib/seqtrimnext/classes/sequence_with_action.rb

@@ -77,7 +77,7 @@ class SequenceWithAction < Sequence
   
   # Adds a new action to the sequence  
     def add_action(a)
-      $LOG.info("Adding action #{a.type} to #{seq_name}")
+      $LOG.debug("Adding action #{a.type} to #{seq_name}")
             
       @actions.push a
       

data/lib/seqtrimnext/plugins/plugin_ab_adapters.rb

@@ -25,7 +25,7 @@ class PluginAbAdapters < Plugin
  def do_blasts(seqs)
     # find MIDS  with less results than max_target_seqs value 
     blast=BatchBlast.new("-db #{@params.get_param('adapters_ab_db')}",'blastn'," -task blastn-short -perc_identity #{@params.get_param('blast_percent_ab')} -word_size #{MIN_ADAPTER_SIZE}")  
-    $LOG.info('BLAST:'+blast.get_blast_cmd)
+    $LOG.debug('BLAST:'+blast.get_blast_cmd)
 
     fastas=[]
     
@@ -61,7 +61,7 @@ class PluginAbAdapters < Plugin
      raise "Blast and seq names does not match, blast:#{blast_query.query_id} sn:#{seq.seq_name}"
    end
    
-    $LOG.info "[#{self.class.to_s}, seq: #{seq.seq_name}]: looking for adapters into the sequence" 
+    $LOG.debug "[#{self.class.to_s}, seq: #{seq.seq_name}]: looking for adapters into the sequence" 
   
         
     # blast=BatchBlast.new("-db #{File.join($FORMATTED_DB_PATH,'adapters_ab.fasta')}",'blastn'," -task blastn-short -evalue #{@params.get_param('blast_evalue_ab')} -perc_identity #{@params.get_param('blast_percent_ab')} -word_size #{MIN_ADAPTER_SIZE}")  

data/lib/seqtrimnext/plugins/plugin_adapters.rb

@@ -25,7 +25,7 @@ class PluginAdapters < Plugin
  def do_blasts(seqs)
     # find MIDS  with less results than max_target_seqs value 
     blast=BatchBlast.new("-db #{@params.get_param('adapters_db')}",'blastn'," -task blastn-short -perc_identity #{@params.get_param('blast_percent_adapters')} -word_size #{MIN_ADAPTER_SIZE}")  
-    $LOG.info('BLAST:'+blast.get_blast_cmd)
+    $LOG.debug('BLAST:'+blast.get_blast_cmd)
 
     fastas=[]
     
@@ -64,7 +64,7 @@ class PluginAdapters < Plugin
      # raise "Blast and seq names does not match, blast:#{blast_query.query_id} sn:#{seq.seq_name}"
    end
    
-    $LOG.info "[#{self.class.to_s}, seq: #{seq.seq_name}]: looking for adapters into the sequence" 
+    $LOG.debug "[#{self.class.to_s}, seq: #{seq.seq_name}]: looking for adapters into the sequence" 
   
         
     # blast=BatchBlast.new("-db #{File.join($FORMATTED_DB_PATH,'adapters.fasta')}",'blastn'," -task blastn-short -evalue #{@params.get_param('blast_evalue_adapters')} -perc_identity #{@params.get_param('blast_percent_adapters')} -word_size #{MIN_ADAPTER_SIZE}")  

data/lib/seqtrimnext/plugins/plugin_adapters_old.rb

@@ -0,0 +1,165 @@
+require "plugin"
+
+########################################################
+# Author: Almudena Bocinos Rioboo                      
+# 
+# Defines the main methods that are necessary to execute PluginAdapters                                                     
+# Inherit: Plugin
+########################################################
+
+class PluginAdaptersOld < Plugin
+  
+  def get_type_adapter(p_start,p_end,seq)
+       #if q_beg is nearer the left, add adapter action by the left,
+       #if q_end esta is nearer the right , add adapter action by  the right
+       #NOTE: If the adapter is very near from left and rigth,
+       #then the sequence isn't valid, because almost sequence is adapter.
+       
+       
+       v1= p_end.to_i
+       v2= p_start.to_i   
+       
+        # puts " startadapter #{v2} endadapter #{v1} insert_start #{seq.insert_start}  insert_end #{seq.insert_end}"
+       
+        # puts " #{v2+seq.insert_start} <? #{seq.seq_fasta.length - v1 - 1 + seq.seq_fasta_orig.length - seq.insert_end-1}"
+       if (v2+seq.insert_start  < (seq.seq_fasta.length - v1 - 1+ seq.seq_fasta_orig.length - seq.insert_end-1)) #IF THE NEAREST ONE IS THE LEFT
+         type = "ActionLeftAdapter"          
+         
+       else
+          type = "ActionRightAdapter"
+         
+       end
+       return type
+  end 
+  
+  
+  def cut_by_right(adapter,seq)
+    
+    left_size = adapter.q_beg-seq.insert_start+1
+    right_size = seq.insert_end-adapter.q_end+1
+    left_size=0 if (left_size<0)
+    right_size=0 if (right_size<0) 
+    
+    return (left_size>(right_size/2).to_i)
+    
+  end
+  
+ #Begins the plugin1's execution to warn that there are contaminants in the sequence "seq"
+ def execute(seqs)
+   blasts= do_blasts(seqs)
+   
+   seqs.each_with_index do |s,i|
+     exec_seq(s,blasts.querys[i])
+   end
+ end
+ 
+ def do_blasts(seqs)
+    # find MIDS  with less results than max_target_seqs value 
+    blast=BatchBlast.new("-db #{@params.get_param('adapters_db')}",'blastn'," -task blastn-short -evalue #{@params.get_param('blast_evalue_adapters')} -perc_identity #{@params.get_param('blast_percent_adapters')}")  
+    $LOG.debug('BLAST:'+blast.get_blast_cmd)
+
+    fastas=[]
+    
+    seqs.each do |seq|
+     fastas.push ">"+seq.seq_name
+     fastas.push seq.seq_fasta
+    end
+    
+    # fastas=fastas.join("\n")
+    
+    blast_table_results = blast.do_blast(fastas)
+    
+    # puts blast_table_results.inspect
+   
+    return blast_table_results
+ end
+ 
+ 
+ def exec_seq(seq,blast_query)
+   if blast_query.query_id != seq.seq_name
+     raise "Blast and seq names does not match, blast:#{blast_query.query_id} sn:#{seq.seq_name}"
+   end
+   
+    $LOG.debug "[#{self.class.to_s}, seq: #{seq.seq_name}]: looking for adapters into the sequence" 
+  
+        
+    # blast=BatchBlast.new("-db #{File.join($FORMATTED_DB_PATH,'adapters.fasta')}",'blastn'," -task blastn-short -evalue #{@params.get_param('blast_evalue_adapters')} -perc_identity #{@params.get_param('blast_percent_adapters')}")  
+    
+    # blast with only one sequence, no with many sequences from a database
+    #---------------------------------------------------------------------
+    
+    # blast_table_results = blast.do_blast(seq.seq_fasta)             #rise seq to adapterss  executing over blast
+    
+    #blast_table_results = BlastTableResult.new(res) 
+    
+    # blast_table_results.inspect         
+    
+    adapters=[]
+    # blast_table_results.querys.each do |query|     # first round to save adapters without overlap
+      merge_hits(blast_query,adapters)
+    # end
+
+    begin 
+      adapters2=adapters                            # second round to save adapters without overlap
+      adapters = []
+      merge_hits(adapters2,adapters)
+    end until (adapters2.count == adapters.count) 
+
+    actions=[] 
+    adapter_size=0
+    # @stats['adapter_size']={}
+    adapters.each do |ad|                           # adds the correspondent action to the sequence  
+       
+       type = get_type_adapter(ad.q_beg,ad.q_end,seq)
+       a = seq.new_action(ad.q_beg,ad.q_end,type) 
+       # puts " state left_action #{a.left_action} right_action #{a.right_action}"
+         
+
+       adapter_size=ad.q_end-ad.q_beg+1 
+       
+       if cut_by_right(ad,seq)
+        
+        # puts "action right end1 #{seq.insert_end}"
+        
+        a.right_action=true    #mark rigth action to get the left insert
+      else 
+          
+        # puts " cut1 by left #{seq.insert_start} ad #{ad.q_beg+seq.insert_start} #{ad.q_end+seq.insert_start}"
+                 
+        a.left_action = true   #mark left action to get the right insert        
+        
+      end 
+      
+      a.message = ad.subject_id 
+      a.reversed = ad.reversed 
+      actions.push a 
+      
+      # @stats[:adapter_size]={adapter_size => 1} 
+      add_stats('adapter_size',adapter_size)  
+        
+    end 
+    seq.add_actions(actions)
+    #    
+  end
+
+  #Returns an array with the errors due to parameters are missing 
+  def self.check_params(params)
+    errors=[]
+    
+    comment='Blast E-value used as cut-off when searching for adapters or primers'
+    default_value = 1e-6
+		params.check_param(errors,'blast_evalue_adapters','Float',default_value,comment)
+		
+		comment='Minimum required identity (%) for a reliable adapter'
+		default_value = 95
+		params.check_param(errors,'blast_percent_adapters','Integer',default_value,comment)
+    
+    comment='Path for adapter database'
+		default_value = File.join($FORMATTED_DB_PATH,'adapters.fasta')
+		params.check_param(errors,'adapters_db','DB',default_value,comment)		
+    
+    return errors
+  end
+  
+  
+end

data/lib/seqtrimnext/plugins/plugin_amplicons.rb

@@ -25,7 +25,7 @@ class PluginAmplicons < Plugin
   def do_blasts(seqs)
     # find MIDS  with less results than max_target_seqs value
     blast=BatchBlast.new("-db #{@params.get_param('primers_db')}",'blastn'," -task blastn-short -perc_identity #{@params.get_param('blast_percent_primers')}")
-    $LOG.info('BLAST:'+blast.get_blast_cmd)
+    $LOG.debug('BLAST:'+blast.get_blast_cmd)
 
     fastas=[]
 
@@ -49,7 +49,7 @@ class PluginAmplicons < Plugin
       raise "Blast and seq names does not match, blast:#{blast_query.query_id} sn:#{seq.seq_name}"
     end
 
-    $LOG.info "[#{self.class.to_s}, seq: #{seq.seq_name}]: looking for primers into the sequence"
+    $LOG.debug "[#{self.class.to_s}, seq: #{seq.seq_name}]: looking for primers into the sequence"
 
     # puts blast_query.inspect
     

data/lib/seqtrimnext/plugins/plugin_contaminants.rb

@@ -36,7 +36,7 @@ class PluginContaminants < Plugin
 
     blast = BatchBlast.new("-db #{@params.get_param('contaminants_db')}",'blastn'," -task blastn -evalue #{@params.get_param('blast_evalue_contaminants')} -perc_identity #{@params.get_param('blast_percent_contaminants')} -culling_limit 1")  #get contaminants -max_target_seqs #{MAX_TARGETS_SEQS}
 
-    $LOG.info('BLAST:'+blast.get_blast_cmd(:xml))
+    $LOG.debug('BLAST:'+blast.get_blast_cmd(:xml))
 
     fastas=[]
 
@@ -67,7 +67,7 @@ class PluginContaminants < Plugin
       # raise "Blast and seq names does not match, blast:#{blast_query.query_id} sn:#{seq.seq_name}"
     end
 
-    $LOG.info "[#{self.class.to_s}, seq: #{seq.seq_name}]: looking for contaminants into the sequence"
+    $LOG.debug "[#{self.class.to_s}, seq: #{seq.seq_name}]: looking for contaminants into the sequence"
 
 
     #blast = BatchBlast.new('-db DB/formatted/contaminants.fasta','blastn',' -task blastn -evalue 1e-10 -perc_identity 95')  #get contaminants
@@ -143,7 +143,7 @@ class PluginContaminants < Plugin
 
         end
       else
-        $LOG.info('Contaminant ignored due to genus match: '+c.definition)
+        $LOG.debug('Contaminant ignored due to genus match: '+c.definition)
       end
     end
 

data/lib/seqtrimnext/plugins/plugin_extract_inserts.rb

@@ -286,7 +286,7 @@ class PluginExtractInserts < Plugin
 
 
   def exec_seq(seq)
-     $LOG.info "[#{self.class.to_s}, seq: #{seq.seq_name}]: extract inserts"    
+     $LOG.debug "[#{self.class.to_s}, seq: #{seq.seq_name}]: extract inserts"    
           
      # puts "INSERTO ANTES LINKER INSERT:"+seq.seq_fasta
 

data/lib/seqtrimnext/plugins/plugin_find_poly_at.rb

@@ -319,7 +319,7 @@ class PluginFindPolyAt < Plugin
 
 
   def exec_seq(seq)
-    $LOG.info "[#{self.class.to_s}, seq: #{seq.seq_name}]: looking for strings of polyAT's into the sequence with a length indicated by the param <poly_at_length>"
+    $LOG.debug "[#{self.class.to_s}, seq: #{seq.seq_name}]: looking for strings of polyAT's into the sequence with a length indicated by the param <poly_at_length>"
 
     find_polyT(seq)
     find_polyA(seq)

data/lib/seqtrimnext/plugins/plugin_ignore_repeated.rb

@@ -21,7 +21,7 @@ def execute(seqs)
 
 
  def exec_seq(seq)
-    $LOG.info "[#{self.class.to_s}, seq: #{seq.seq_name}]: searching sequence repeated at input file" 
+    $LOG.debug "[#{self.class.to_s}, seq: #{seq.seq_name}]: searching sequence repeated at input file" 
 
     fasta_input=@params.get_param('truncated_input_file')
     

data/lib/seqtrimnext/plugins/plugin_indeterminations.rb

@@ -149,7 +149,7 @@ class PluginIndeterminations < Plugin
 
 
    def exec_seq(seq)
-     $LOG.info "[#{self.class.to_s}, seq: #{seq.seq_name}]: removing indeterminations N+" 
+     $LOG.debug "[#{self.class.to_s}, seq: #{seq.seq_name}]: removing indeterminations N+" 
      
      actions=[]
      

data/lib/seqtrimnext/plugins/plugin_key.rb

@@ -21,7 +21,7 @@ class PluginKey < Plugin
 
 
    def exec_seq(seq)
-     $LOG.info "[#{self.class.to_s}, seq: #{seq.seq_name}]: marking key into the sequence" 
+     $LOG.debug "[#{self.class.to_s}, seq: #{seq.seq_name}]: marking key into the sequence" 
      # blast_table_results.inspect        
      
      actions=[]

data/lib/seqtrimnext/plugins/plugin_linker.rb

@@ -83,7 +83,7 @@ class PluginLinker < Plugin
      # find MIDS  with less results than max_target_seqs value 
      blast = BatchBlast.new("-db #{@params.get_param('linkers_db')}",'blastn'," -task blastn-short  -evalue #{@params.get_param('blast_evalue_linkers')} -perc_identity #{@params.get_param('blast_percent_linkers')}")  #get linkers          
 
-     $LOG.info('BLAST:'+blast.get_blast_cmd)
+     $LOG.debug('BLAST:'+blast.get_blast_cmd)
 
      fastas=[]
 
@@ -106,7 +106,7 @@ class PluginLinker < Plugin
     if blast_query.query_id != seq.seq_name
       raise "Blast and seq names does not match, blast:#{blast_query.query_id} sn:#{seq.seq_name}"
     end
-     $LOG.info "[#{self.class.to_s}, seq: #{seq.seq_name}]: looking for linker into the sequence"
+     $LOG.debug "[#{self.class.to_s}, seq: #{seq.seq_name}]: looking for linker into the sequence"
      
      # key_beg,key_end=search_key(seq,0,3)   if false       
      # blast = BatchBlast.new("-subject #{File.join($FORMATTED_DB_PATH,'linkers.fasta')}",'blastn'," -task blastn  -evalue #{@params.get_param('blast_evalue_linkers')} -perc_identity #{@params.get_param('blast_percent_linkers')}")  #get linkers

data/lib/seqtrimnext/plugins/plugin_low_high_size.rb

@@ -22,7 +22,7 @@ class PluginLowHighSize < Plugin
   
   
   def exec_seq(seq)   
-    $LOG.info "[#{self.class.to_s}, seq: #{seq.seq_name}]: checking low or high size of the sequence"    
+    $LOG.debug "[#{self.class.to_s}, seq: #{seq.seq_name}]: checking low or high size of the sequence"    
     
     min_size = @params.get_param('min_sequence_size_raw').to_i #min_size is: mean - 2dev
     max_size = @params.get_param('max_sequence_size_raw').to_i #max_size is: mean + 2dev

data/lib/seqtrimnext/plugins/plugin_low_quality.rb

@@ -278,7 +278,7 @@ class PluginLowQuality < Plugin
      if ((self.class.to_s=='PluginLowQuality') && seq.seq_qual.nil? ) 
        $LOG.error " Quality File haven't been provided. It's impossible to execute " + self.class.to_s     
      elsif (seq.seq_qual.size>0)
-       $LOG.info "[#{self.class.to_s}, seq: #{seq.seq_name}]: checking low quality of the sequence"    
+       $LOG.debug "[#{self.class.to_s}, seq: #{seq.seq_name}]: checking low quality of the sequence"    
 
        @low=@params.get_param('min_quality').to_i
 

data/lib/seqtrimnext/plugins/plugin_mids.rb

@@ -29,7 +29,7 @@ class PluginMids < Plugin
   def do_blasts(seqs)
      # find MIDS  with less results than max_target_seqs value 
      blast = BatchBlast.new("-db #{@params.get_param('mids_db')}",'blastn'," -task blastn-short    -perc_identity #{@params.get_param('blast_percent_mids')} -max_target_seqs 4 ")  #get mids 
-     $LOG.info('BLAST:'+blast.get_blast_cmd)
+     $LOG.debug('BLAST:'+blast.get_blast_cmd)
 
      fastas=[]
      
@@ -54,7 +54,7 @@ class PluginMids < Plugin
     end
 
      
-     $LOG.info "[#{self.class.to_s}, seq: #{seq.seq_name}]: looking for mids into the sequence"   
+     $LOG.debug "[#{self.class.to_s}, seq: #{seq.seq_name}]: looking for mids into the sequence"   
       
 
      # blast_table_results = blast.do_blast(seq.seq_fasta[0..SIZE_SEARCH_MID])             # execute blast to find mids

data/lib/seqtrimnext/plugins/plugin_rem_adit_artifacts.rb

@@ -27,7 +27,7 @@ class PluginRemAditArtifacts < Plugin
 
   def exec_seq(seq)
    
-    $LOG.info "[#{self.class.to_s}, seq: #{seq.seq_name}]: removing artifacts into the sequence"    
+    $LOG.debug "[#{self.class.to_s}, seq: #{seq.seq_name}]: removing artifacts into the sequence"    
     seq2 = seq.seq_fasta    
     first = 0
     last = seq2.size-1    

data/lib/seqtrimnext/plugins/plugin_short_insert.rb

@@ -96,7 +96,7 @@ class PluginShortInsert < Plugin
 
   def exec_seq(seq)
     
-    $LOG.info "[#{self.class.to_s}, seq: #{seq.seq_name}]: checking if insert of sequence has enought size" 
+    $LOG.debug "[#{self.class.to_s}, seq: #{seq.seq_name}]: checking if insert of sequence has enought size" 
     # puts "inserto #{seq.insert_start}, #{seq.insert_end} size #{seq.seq_fasta.size}" 
     
     if (seq.seq_fasta.size > 0)
@@ -183,7 +183,7 @@ class PluginShortInsert < Plugin
 
   #Begins the plugin1's execution to warn if the inserted is so short 
    def execute_no_cut_quality(seq)  
-     $LOG.info "[#{self.class.to_s}, seq: #{seq.seq_name}]: checking if insert of sequence has enought size" 
+     $LOG.debug "[#{self.class.to_s}, seq: #{seq.seq_name}]: checking if insert of sequence has enought size" 
 
     
 

data/lib/seqtrimnext/plugins/plugin_vectors.rb

@@ -38,7 +38,7 @@ class PluginVectors < Plugin
     # find MIDS  with less results than max_target_seqs value 
     blast = BatchBlast.new("-db #{@params.get_param('vectors_db')}",'blastn'," -task blastn-short -evalue #{@params.get_param('blast_evalue_vectors')} -perc_identity #{@params.get_param('blast_percent_vectors')} -culling_limit 1")  #get vectors
 
-    $LOG.info('BLAST:'+blast.get_blast_cmd)
+    $LOG.debug('BLAST:'+blast.get_blast_cmd)
 
     fastas=[]
 
@@ -62,7 +62,7 @@ class PluginVectors < Plugin
      # raise "Blast and seq names does not match, blast:#{blast_query.query_id} sn:#{seq.seq_name}"
    end
   
-    $LOG.info "[#{self.class.to_s}, seq: #{seq.seq_name}]: looking for vectors into the sequence " 
+    $LOG.debug "[#{self.class.to_s}, seq: #{seq.seq_name}]: looking for vectors into the sequence " 
   
     #blast contra contaminantes
     

data/lib/seqtrimnext/templates/genomics_illumina.txt

@@ -0,0 +1,5 @@
+# ======================================
+# General parameters GENOMICS illumina
+# ======================================
+
+plugin_list = PluginLowHighSize,PluginIndeterminations,PluginContaminants,PluginLowQuality

data/lib/seqtrimnext/templates/transcriptomics_illumina.txt

@@ -0,0 +1,8 @@
+# ======================================
+# General parameters
+# ======================================
+
+
+plugin_list = PluginLowHighSize,PluginIndeterminations,PluginFindPolyAt,PluginContaminants,PluginLowQuality,PluginLowComplexity
+
+contaminants_db="contaminants.fasta cont_ribosome.fasta"

data/lib/seqtrimnext/utils/hash_stats.rb

@@ -15,8 +15,9 @@ def add_stats(h_stats)
 		add_stats.each do |property,hash_value|
 			h[plugin_hash][property]={} if h[plugin_hash][property].nil?	
 		
+      # values need to be in string format because of later loading from json file
 			hash_value.each do |value, count|
-				h[plugin_hash][property][value]=(h[plugin_hash][property][value]||0) + count
+				h[plugin_hash][property][value.to_s]=(h[plugin_hash][property][value.to_s]||0) + count
 			end
 		end
 	end

data/lib/seqtrimnext.rb

@@ -30,7 +30,7 @@ module Seqtrimnext
   # SEQTRIM_VERSION_STAGE = 'b'
   # SEQTRIM_VERSION = "2.0.0#{SEQTRIM_VERSION_STAGE}#{SEQTRIM_VERSION_REVISION}"
   
-   VERSION = '2.0.45'
+   VERSION = '2.0.46'
   
   SEQTRIM_VERSION = VERSION
   

metadata

@@ -2,7 +2,7 @@
 name: seqtrimnext
 version: !ruby/object:Gem::Version 
   prerelease: 
-  version: 2.0.45
+  version: 2.0.46
 platform: ruby
 authors: 
 - Dario Guerrero & Almudena Bocinos
@@ -10,7 +10,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2012-03-05 00:00:00 Z
+date: 2012-04-13 00:00:00 Z
 dependencies: 
 - !ruby/object:Gem::Dependency 
   name: narray
@@ -143,9 +143,11 @@ executables:
 - extract_seqs_from_fastq.rb
 - fasta2fastq.rb
 - fastq2fasta.rb
+- filter_database.rb
 - gen_qual.rb
 - get_seq.rb
 - group_by_range.rb
+- join_big_illumina_paired.sh
 - join_ilumina_paired.rb
 - parse_amplicons.rb
 - parse_json_results.rb
@@ -160,14 +162,16 @@ executables:
 extensions: []
 
 extra_rdoc_files: 
+- History.txt
 - lib/seqtrimnext/templates/amplicons.txt
 - lib/seqtrimnext/templates/genomics_454.txt
 - lib/seqtrimnext/templates/genomics_454_with_paired.txt
+- lib/seqtrimnext/templates/genomics_illumina.txt
 - lib/seqtrimnext/templates/low_quality.txt
 - lib/seqtrimnext/templates/low_quality_and_low_complexity.txt
 - lib/seqtrimnext/templates/transcriptomics_454.txt
+- lib/seqtrimnext/templates/transcriptomics_illumina.txt
 - lib/seqtrimnext/templates/transcriptomics_plants.txt
-- History.txt
 - Manifest.txt
 - PostInstall.txt
 files: 
@@ -177,9 +181,11 @@ files:
 - bin/extract_seqs_from_fastq.rb
 - bin/fasta2fastq.rb
 - bin/fastq2fasta.rb
+- bin/filter_database.rb
 - bin/gen_qual.rb
 - bin/get_seq.rb
 - bin/group_by_range.rb
+- bin/join_big_illumina_paired.sh
 - bin/join_ilumina_paired.rb
 - bin/parse_amplicons.rb
 - bin/parse_json_results.rb
@@ -191,6 +197,7 @@ files:
 - bin/split_fastq.rb
 - bin/split_ilumina_paired.rb
 - bin/split_paired.rb
+- History.txt
 - lib/seqtrimnext/actions/action_ab_adapter.rb
 - lib/seqtrimnext/actions/action_ab_far_adapter.rb
 - lib/seqtrimnext/actions/action_ab_left_adapter.rb
@@ -208,13 +215,13 @@ files:
 - lib/seqtrimnext/actions/action_low_high_size.rb
 - lib/seqtrimnext/actions/action_low_quality.rb
 - lib/seqtrimnext/actions/action_mid.rb
+- lib/seqtrimnext/actions/action_middle_adapter.rb
 - lib/seqtrimnext/actions/action_multiple_linker.rb
 - lib/seqtrimnext/actions/action_paired_reads.rb
 - lib/seqtrimnext/actions/action_poly_a.rb
 - lib/seqtrimnext/actions/action_poly_t.rb
 - lib/seqtrimnext/actions/action_rem_adit_artifacts.rb
 - lib/seqtrimnext/actions/action_right_adapter.rb
-- lib/seqtrimnext/actions/action_middle_adapter.rb
 - lib/seqtrimnext/actions/action_right_primer.rb
 - lib/seqtrimnext/actions/action_short_insert.rb
 - lib/seqtrimnext/actions/action_unexpected_poly_t.rb
@@ -244,6 +251,7 @@ files:
 - lib/seqtrimnext/plugins/plugin.rb
 - lib/seqtrimnext/plugins/plugin_ab_adapters.rb
 - lib/seqtrimnext/plugins/plugin_adapters.rb
+- lib/seqtrimnext/plugins/plugin_adapters_old.rb
 - lib/seqtrimnext/plugins/plugin_amplicons.rb
 - lib/seqtrimnext/plugins/plugin_contaminants.rb
 - lib/seqtrimnext/plugins/plugin_extract_inserts.rb
@@ -262,9 +270,11 @@ files:
 - lib/seqtrimnext/templates/amplicons.txt
 - lib/seqtrimnext/templates/genomics_454.txt
 - lib/seqtrimnext/templates/genomics_454_with_paired.txt
+- lib/seqtrimnext/templates/genomics_illumina.txt
 - lib/seqtrimnext/templates/low_quality.txt
 - lib/seqtrimnext/templates/low_quality_and_low_complexity.txt
 - lib/seqtrimnext/templates/transcriptomics_454.txt
+- lib/seqtrimnext/templates/transcriptomics_illumina.txt
 - lib/seqtrimnext/templates/transcriptomics_plants.txt
 - lib/seqtrimnext/utils/extract_samples.rb
 - lib/seqtrimnext/utils/fasta2xml.rb
@@ -276,7 +286,6 @@ files:
 - lib/seqtrimnext/utils/recover_mid.rb
 - lib/seqtrimnext/utils/string_utils.rb
 - lib/seqtrimnext.rb
-- History.txt
 - Manifest.txt
 - PostInstall.txt
 - Rakefile