seqtrimnext 2.0.50 → 2.0.51

data/History.txt

@@ -1,3 +1,7 @@
+=== 2.0.51 2012-06-20
+
+Added cont_viruses database
+
 === 2.0.50 2012-06-13
 
 Added classification plugin

data/Manifest.txt

@@ -78,7 +78,7 @@ 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_classify.rb
+lib/seqtrimnext/plugins/plugin_user_contaminants.rb
 lib/seqtrimnext/plugins/plugin_extract_inserts.rb
 lib/seqtrimnext/plugins/plugin_find_poly_at.rb
 lib/seqtrimnext/plugins/plugin_ignore_repeated.rb
@@ -95,11 +95,10 @@ 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/genomics_short_reads.txt
+lib/seqtrimnext/templates/genomics_short_reads_2.txt
 lib/seqtrimnext/templates/transcriptomics_454.txt
-lib/seqtrimnext/templates/transcriptomics_illumina.txt
+lib/seqtrimnext/templates/transcriptomics_short_reads.txt
 lib/seqtrimnext/templates/transcriptomics_plants.txt
 lib/seqtrimnext/utils/extract_samples.rb
 lib/seqtrimnext/utils/fasta2xml.rb

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','>=0.0.15']
+  self.extra_deps << ['scbi_fastq','>=0.0.16']
   self.extra_deps << ['scbi_plot','>=0.0.6']
   self.extra_deps << ['scbi_math','>=0.0.1']
 

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 = '2.0.50'
+   VERSION = '2.0.51'
   
   SEQTRIM_VERSION = VERSION
   

data/lib/seqtrimnext/classes/install_database.rb

@@ -6,7 +6,7 @@ class InstallDatabase
   def initialize(type,db_path)
     
     
-    types=['core','cont_bacteria','cont_fungi','cont_mitochondrias','cont_plastids','cont_ribosome']
+    types=['core','cont_bacteria','cont_fungi','cont_mitochondrias','cont_plastids','cont_ribosome','cont_viruses']
     
     if types.include?(type)
       

data/lib/seqtrimnext/plugins/plugin_rem_adit_artifacts.rb

@@ -38,7 +38,6 @@ class PluginRemAditArtifacts < Plugin
     while (seq2 =~ /^(GCGGGG|CCCCGC)/i)
       first += 6
       seq2.slice!(0..5)
- 
     end
     
     

data/lib/seqtrimnext/plugins/{plugin_classify.rb → plugin_user_contaminants.rb}

@@ -8,7 +8,7 @@ require "make_blast_db"
 # Inherit: Plugin
 ########################################################
 
-class PluginClassify < Plugin
+class PluginUserContaminants < Plugin
 
 
   MAX_TARGETS_SEQS=4 #MAXIMUM NUMBER OF DIFFERENT ALIGNED SEQUENCES TO  KEEP FROM BLAST DATABASE
@@ -47,7 +47,7 @@ class PluginClassify < Plugin
     # TODO - Culling limit = 2 porque el blast falla con este comando cuando se le pasa cl=1 y dust=no
     # y una secuencia de baja complejidad como entrada
 
-    blast = BatchBlast.new("-db #{@params.get_param('classify_db')}",'blastn'," -task blastn -evalue #{@params.get_param('blast_evalue_classify')} -perc_identity #{@params.get_param('blast_percent_classify')} -culling_limit 1")  #get classify -max_target_seqs #{MAX_TARGETS_SEQS}
+    blast = BatchBlast.new("-db #{@params.get_param('user_contaminant_db')}",'blastn'," -task blastn -evalue #{@params.get_param('blast_evalue_classify')} -perc_identity #{@params.get_param('blast_percent_classify')} -culling_limit 1")  #get classify -max_target_seqs #{MAX_TARGETS_SEQS}
 
     $LOG.debug('BLAST:'+blast.get_blast_cmd(:xml))
 
@@ -133,7 +133,7 @@ class PluginClassify < Plugin
 
     comment='Path for classify database'
     default_value = File.join($FORMATTED_DB_PATH,'classify.fasta')
-    params.check_param(errors,'classify_db','DB',default_value,comment)
+    params.check_param(errors,'user_contaminant_db','DB',default_value,comment)
 
 
     return errors

data/lib/seqtrimnext/templates/amplicons.txt

@@ -2,6 +2,27 @@
 # General parameters to extract Amplicons
 # ======================================
 
+# Help: <br/>This template is used to get Amplicons<br/>
+
+# Help: <br/><b>Plugin list and aplication order:</b><br/>
+
+# Help: <ul>
+# Help: <li>PluginLowHighSize: rejecting too short or too long sequences</li>
+# Help: <li>PluginKey: trimming Roche 454 sequencing keys (typically 4 first nucleotides)</li>
+# Help: <li>PluginMids: trimming Roche 454 MIDs</li>
+# Help: <li>PluginIndeterminations: retaining the longest sequence fragment without indeterminations (N)</li>
+# Help: <li>PluginAbAdapters: trimming the Roche 454 AB adapters</li>
+# Help: <li>PluginAdapters: trimming the adapters found in SeqTrimNEXT database</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>
+# Help: <li>PluginFindPolyAt: trimming PolyA and PolyT. After a PolyT, the sequence is checked for low complexity. </li>
+# Help: <li>PluginAmplicons: getting sequences contained between two primers. Sequences with less than two primers are rejected. </li>
+# Help: <li>PluginLinker: splits Roche 454 paired-end sequences by any linker found in linkers database. Linker is removed.</li>
+# Help: <li>PluginLowComplexity: sequences with low complexity are stored on a separate file. </li>
+# Help: <li>PluginLowQuality: trimming low quality regions from sequences. </li>
+# Help: <li>PluginVectors: trimming any cloning vector found in SeqTrimNEXT database. </li>
+# Help: </ul>
+
 plugin_list = PluginLowHighSize,PluginKey,PluginMids,PluginIndeterminations,PluginAbAdapters,PluginAmplicons,PluginLowQuality
 
 # do not remove cloned sequences

data/lib/seqtrimnext/templates/genomics_454.txt

@@ -2,4 +2,17 @@
 # General parameters GENOMICS WITH POSSIBLE LINKER
 # ======================================
 
+# Help: <br/>This template is used to preprocess Roche 454 genomic data <br/>
+
+# Help: <br/><b>Plugin list and aplication order:</b><br/>
+# Help: <ul>
+# Help: <li>PluginLowHighSize</li>
+# Help: <li>PluginMids</li>
+# Help: <li>PluginIndeterminations</li>
+# Help: <li>PluginAbAdapters</li>
+# Help: <li>PluginContaminants</li>
+# Help: <li>PluginAmplicons</li>
+# Help: <li>PluginLowQuality</li>
+# Help: </ul>
+
 plugin_list = PluginLowHighSize,PluginMids,PluginIndeterminations,PluginAbAdapters,PluginContaminants,PluginVectors,PluginLowQuality

data/lib/seqtrimnext/templates/genomics_454_with_paired.txt

@@ -2,4 +2,6 @@
 # General parameters GENOMICS WITH POSSIBLE LINKER
 # ======================================
 
+# Help: <br/>This template is used to preprocess Roche 454 genomic data including paired-end <br/>
+
 plugin_list = PluginLowHighSize,PluginMids,PluginIndeterminations,PluginAbAdapters,PluginContaminants,PluginLinker,PluginVectors,PluginLowQuality

data/lib/seqtrimnext/templates/genomics_short_reads.txt

@@ -0,0 +1,7 @@
+# ==============================================================
+# General parameters for genomics - Illumina/SOLiD (short reads)
+# ==============================================================
+
+# Help: <br/>This template is used to preprocess short reads for genomics <br/>
+
+plugin_list = PluginIndeterminations,PluginContaminants,PluginVectors,PluginLowQuality

data/lib/seqtrimnext/templates/genomics_short_reads_2.txt

@@ -0,0 +1,7 @@
+# ==============================================================
+# General parameters for genomics - Illumina/SOLiD (short reads)
+# ==============================================================
+
+# Help: <br/>This template is used to preprocess short reads for genomics including low complexity removal<br/>
+
+plugin_list = PluginIndeterminations,PluginContaminants,PluginVectors,PluginLowQuality,PluginLowComplexity

data/lib/seqtrimnext/templates/transcriptomics_454.txt

@@ -1,7 +1,9 @@
 # ======================================
-# General parameters
+# General parameters TRANSCRIPTOMICS 
 # ======================================
 
+# Help: <br/>This template is used to preprocess Roche 454 transcriptomic data <br/>
+
 
 plugin_list = PluginLowHighSize,PluginMids,PluginIndeterminations,PluginAbAdapters,PluginAdapters,PluginFindPolyAt,PluginContaminants,PluginVectors,PluginLowQuality,PluginLowComplexity
 

data/lib/seqtrimnext/templates/transcriptomics_plants.txt

@@ -1,7 +1,8 @@
 # ======================================
-# General parameters
+# General parameters TRANSCRIPTOMICS PLANTS
 # ======================================
 
+# Help: <br/>This template is used to preprocess Roche 454 transcriptomic data. Customized for plants.<br/>
 
 plugin_list = PluginLowHighSize,PluginMids,PluginIndeterminations,PluginAbAdapters,PluginAdapters,PluginFindPolyAt,PluginContaminants,PluginVectors,PluginLowQuality,PluginLowComplexity
 

data/lib/seqtrimnext/templates/transcriptomics_short_reads.txt

@@ -0,0 +1,9 @@
+# ======================================
+# General parameters for transcriptomics - Illumina/SOLiD (short reads)
+# ======================================
+
+# Help: <br/>This template is used to preprocess short reads for transcriptomics<br/>
+
+plugin_list = PluginIndeterminations,PluginFindPolyAt,PluginContaminants,PluginVectors,PluginLowQuality,PluginLowComplexity
+
+contaminants_db="contaminants.fasta cont_ribosome.fasta"

metadata

@@ -2,7 +2,7 @@
 name: seqtrimnext
 version: !ruby/object:Gem::Version 
   prerelease: 
-  version: 2.0.50
+  version: 2.0.51
 platform: ruby
 authors: 
 - Dario Guerrero & Almudena Bocinos
@@ -10,7 +10,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2012-06-13 00:00:00 Z
+date: 2012-06-20 00:00:00 Z
 dependencies: 
 - !ruby/object:Gem::Dependency 
   name: narray
@@ -97,7 +97,7 @@ dependencies:
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
-        version: 0.0.15
+        version: 0.0.16
   type: :runtime
   version_requirements: *id008
 - !ruby/object:Gem::Dependency 
@@ -166,11 +166,10 @@ extra_rdoc_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/genomics_short_reads.txt
+- lib/seqtrimnext/templates/genomics_short_reads_2.txt
 - lib/seqtrimnext/templates/transcriptomics_454.txt
-- lib/seqtrimnext/templates/transcriptomics_illumina.txt
+- lib/seqtrimnext/templates/transcriptomics_short_reads.txt
 - lib/seqtrimnext/templates/transcriptomics_plants.txt
 - Manifest.txt
 - PostInstall.txt
@@ -255,7 +254,7 @@ files:
 - lib/seqtrimnext/plugins/plugin_adapters_old.rb
 - lib/seqtrimnext/plugins/plugin_amplicons.rb
 - lib/seqtrimnext/plugins/plugin_contaminants.rb
-- lib/seqtrimnext/plugins/plugin_classify.rb
+- lib/seqtrimnext/plugins/plugin_user_contaminants.rb
 - lib/seqtrimnext/plugins/plugin_extract_inserts.rb
 - lib/seqtrimnext/plugins/plugin_find_poly_at.rb
 - lib/seqtrimnext/plugins/plugin_ignore_repeated.rb
@@ -272,11 +271,10 @@ 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/genomics_short_reads.txt
+- lib/seqtrimnext/templates/genomics_short_reads_2.txt
 - lib/seqtrimnext/templates/transcriptomics_454.txt
-- lib/seqtrimnext/templates/transcriptomics_illumina.txt
+- lib/seqtrimnext/templates/transcriptomics_short_reads.txt
 - lib/seqtrimnext/templates/transcriptomics_plants.txt
 - lib/seqtrimnext/utils/extract_samples.rb
 - lib/seqtrimnext/utils/fasta2xml.rb

data/lib/seqtrimnext/templates/genomics_illumina.txt

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

data/lib/seqtrimnext/templates/low_quality.txt

@@ -1,5 +0,0 @@
-# ======================================
-# General parameters GENOMICS WITH POSSIBLE LINKER
-# ======================================
-
-plugin_list = PluginIndeterminations,PluginContaminants,PluginVectors,PluginLowQuality

data/lib/seqtrimnext/templates/low_quality_and_low_complexity.txt

@@ -1,5 +0,0 @@
-# ======================================
-# General parameters GENOMICS WITH POSSIBLE LINKER
-# ======================================
-
-plugin_list = PluginIndeterminations,PluginContaminants,PluginVectors,PluginLowQuality,PluginLowComplexity

data/lib/seqtrimnext/templates/transcriptomics_illumina.txt

@@ -1,7 +0,0 @@
-# ======================================
-# General parameters
-# ======================================
-
-plugin_list = PluginLowHighSize,PluginIndeterminations,PluginFindPolyAt,PluginContaminants,PluginLowQuality,PluginLowComplexity
-
-contaminants_db="contaminants.fasta cont_ribosome.fasta"