seqtrimnext 2.0.52 → 2.0.54

data/History.txt

@@ -1,3 +1,12 @@
+=== 2.0.54 2012-09-07
+
+Write fastq as  fastq.gz
+
+=== 2.0.53 2012-07-24
+
+* Added illumina adapters
+* Gzipped fastq files can be used with SeqtrimNext
+
 === 2.0.52 2012-06-26
 
 * Added new plugin for user contaminants.

data/Rakefile

@@ -24,7 +24,7 @@ $hoe = Hoe.spec 'seqtrimnext' do
   self.extra_deps << ['scbi_blast','>=0.0.34']
   self.extra_deps << ['scbi_mapreduce','>=0.0.38']
   self.extra_deps << ['scbi_fasta','>=0.1.7']
-  self.extra_deps << ['scbi_fastq','>=0.0.16']
+  self.extra_deps << ['scbi_fastq','>=0.0.17']
   self.extra_deps << ['scbi_plot','>=0.0.6']
   self.extra_deps << ['scbi_math','>=0.0.1']
   self.extra_deps << ['scbi_headers','>=0.0.2']

data/bin/seqtrimnext

@@ -322,6 +322,11 @@ optparse = OptionParser.new do |opts|
     options[:skip_report] = true
   end
 
+  options[:write_in_gzip] = false
+  opts.on( '-z', '--gzip', 'Generate output files in gzip format.' ) do
+    options[:write_in_gzip] = true
+  end
+
   # This displays the help screen, all programs are
   # assumed to have this option.
   opts.on_tail( '-h', '--help', 'Display this screen' ) do

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

@@ -13,7 +13,7 @@ STATS_PATH=File.join(OUTPUT_PATH,'stats.json')
 
 class SeqtrimWorkManager < ScbiMapreduce::WorkManager
 
-  def self.init_work_manager(sequence_readers, params, chunk_size = 100, use_json=false, skip_output=false)
+  def self.init_work_manager(sequence_readers, params, chunk_size = 100, use_json=false, skip_output=false, write_in_gzip=true)
     @@full_stats={}
     @@params= params
     @@exit = false
@@ -24,6 +24,7 @@ class SeqtrimWorkManager < ScbiMapreduce::WorkManager
     @@ongoing_stats[:biggest_sequence_size] = 0
 
     @@skip_output=skip_output
+    @@write_in_gzip=write_in_gzip
 
     @@chunk_size = chunk_size
 
@@ -336,7 +337,12 @@ class SeqtrimWorkManager < ScbiMapreduce::WorkManager
       end
 
       # open file
-      res_file=File.open(file_name,@@open_mode)
+      if @@write_in_gzip && file_name.upcase.index('.FASTQ')
+        file=File.open(file_name+'.gz',@@open_mode)
+        res_file=Zlib::GzipWriter.new(file)
+      else
+        res_file=File.open(file_name,@@open_mode)
+      end
 
       # save it in hash for next use
       @@files[file_name]=res_file

data/lib/seqtrimnext/classes/seqtrim.rb

@@ -326,7 +326,7 @@ class Seqtrim
       else
   			$LOG.info 'Starting server'
       	        
- 				SeqtrimWorkManager.init_work_manager(sequence_readers, params,chunk_size,use_json,options[:skip_output])
+ 				SeqtrimWorkManager.init_work_manager(sequence_readers, params,chunk_size,use_json,options[:skip_output],options[:write_in_gzip])
 				
         begin
   				cpus=1

data/lib/seqtrimnext/plugins/plugin_contaminants.rb

@@ -56,7 +56,9 @@ class PluginContaminants < Plugin
 
   def exec_seq(seq,blast_query)
     
-    if seq.get_actions(ActionUserContaminant)
+    user_conts=seq.get_actions(ActionUserContaminant)
+    
+    if (!user_conts.nil?) && (!user_conts.empty?)
       return
     end
     

data/lib/seqtrimnext/plugins/plugin_indeterminations.rb

@@ -151,7 +151,6 @@ class PluginIndeterminations < Plugin
      
      if !match.nil?
 			 found=match[0].length
-
        
        a = seq.new_action(seq.seq_fasta.length-found,seq.seq_fasta.length,'ActionIndetermination')
        a.right_action=true

data/lib/seqtrimnext/templates/genomics_short_reads.txt

@@ -7,7 +7,7 @@
 
 # Help: <ul>
 # Help: <li>PluginIndeterminations: retaining the longest sequence fragment without indeterminations (N)</li>
-
+# Help: <li>PluginAbAdapters: trimming the Illumina adapters</li>
 # Help: <li>PluginUserContaminants: discarding sequences matching any entry in the user contaminant database saving them in a separate file</li>
 
 # Help: <li>PluginContaminants: trimming the contaminant fragments found in the contaminant database. When contamination is prevalent, sequences are rejected. </li>
@@ -15,7 +15,7 @@
 # Help: <li>PluginLowQuality: trimming low quality regions from sequences. </li>
 # Help: </ul>
 
-plugin_list = PluginIndeterminations,PluginUserContaminants,PluginContaminants,PluginVectors,PluginLowQuality
+plugin_list = PluginIndeterminations,PluginAbAdapters,PluginUserContaminants,PluginContaminants,PluginVectors,PluginLowQuality
 
 generate_initial_stats = false
 
@@ -30,3 +30,4 @@ min_insert_size_paired=40
 # do not remove cloned sequences
 remove_clonality=false
 
+adapters_ab_db="adapters_illumina.fasta"

data/lib/seqtrimnext/templates/genomics_short_reads_2.txt

@@ -7,7 +7,7 @@
 
 # Help: <ul>
 # Help: <li>PluginIndeterminations: retaining the longest sequence fragment without indeterminations (N)</li>
-
+# Help: <li>PluginAbAdapters: trimming the Illumina adapters</li>
 # Help: <li>PluginUserContaminants: discarding sequences matching any entry in the user contaminant database saving them in a separate file</li>
 
 # Help: <li>PluginContaminants: trimming the contaminant fragments found in the contaminant database. When contamination is prevalent, sequences are rejected. </li>
@@ -16,7 +16,7 @@
 # Help: <li>PluginLowComplexity: sequences with low complexity are stored on a separate file. </li>
 # Help: </ul>
 
-plugin_list = PluginIndeterminations,PluginUserContaminants,PluginContaminants,PluginVectors,PluginLowQuality,PluginLowComplexity
+plugin_list = PluginIndeterminations,PluginAbAdapters,PluginUserContaminants,PluginContaminants,PluginVectors,PluginLowQuality,PluginLowComplexity
 
 generate_initial_stats = false
 
@@ -28,3 +28,4 @@ min_insert_size_trimmed = 30
 # do not remove cloned sequences
 remove_clonality=false
 
+adapters_ab_db="adapters_illumina.fasta"

data/lib/seqtrimnext/templates/sanger.txt

@@ -19,7 +19,5 @@
 
 plugin_list = PluginIndeterminations,PluginAdapters,PluginFindPolyAt,PluginContaminants,PluginVectors,PluginLowQuality
 
-
 # do not remove cloned sequences
 remove_clonality=false
-

data/lib/seqtrimnext/templates/transcriptomics_plants.txt

@@ -27,4 +27,4 @@ contaminants_db="contaminants.fasta cont_ribosome.fasta cont_mitochondrias.fasta
 
 
 # do not remove cloned sequences
-remove_clonality=false
+remove_clonality=true

data/lib/seqtrimnext/templates/transcriptomics_short_reads.txt

@@ -8,7 +8,7 @@
 # Help: <ul>
 # Help: <li>PluginIndeterminations: retaining the longest sequence fragment without indeterminations (N)</li>
 # Help: <li>PluginFindPolyAt: trimming PolyA and PolyT. After a PolyT, the sequence is checked for low complexity. </li>
-
+# Help: <li>PluginAbAdapters: trimming the Illumina adapters</li>
 # Help: <li>PluginUserContaminants: discarding sequences matching any entry in the user contaminant database saving them in a separate file</li>
 
 # Help: <li>PluginContaminants: trimming the contaminant fragments found in the contaminant database. When contamination is prevalent, sequences are rejected. </li>
@@ -17,7 +17,7 @@
 # Help: <li>PluginLowComplexity: sequences with low complexity are stored on a separate file. </li>
 # Help: </ul>
 
-plugin_list = PluginIndeterminations,PluginFindPolyAt,PluginUserContaminants,PluginContaminants,PluginVectors,PluginLowQuality,PluginLowComplexity
+plugin_list = PluginIndeterminations,PluginFindPolyAt,PluginAbAdapters,PluginUserContaminants,PluginContaminants,PluginVectors,PluginLowQuality,PluginLowComplexity
 
 contaminants_db="contaminants.fasta cont_ribosome.fasta"
 
@@ -29,3 +29,5 @@ min_insert_size_trimmed = 30
 
 # do not remove cloned sequences
 remove_clonality=false
+
+adapters_ab_db="adapters_illumina.fasta"

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 = '2.0.52'
+   VERSION = '2.0.54'
   
   SEQTRIM_VERSION = VERSION
   

metadata

@@ -2,7 +2,7 @@
 name: seqtrimnext
 version: !ruby/object:Gem::Version 
   prerelease: 
-  version: 2.0.52
+  version: 2.0.54
 platform: ruby
 authors: 
 - Dario Guerrero & Almudena Bocinos
@@ -10,7 +10,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2012-07-16 00:00:00 Z
+date: 2012-09-07 00:00:00 Z
 dependencies: 
 - !ruby/object:Gem::Dependency 
   name: narray
@@ -97,7 +97,7 @@ dependencies:
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
-        version: 0.0.16
+        version: 0.0.17
   type: :runtime
   version_requirements: *id008
 - !ruby/object:Gem::Dependency