bio-ngs 0.5.0 → 0.5.2

data/README.md

@@ -14,6 +14,7 @@ Provides a framework for handling NGS data with Bioruby.
 * http://hannonlab.cshl.edu/fastx_toolkit/ (the gem tries to install this tool by itself)
 * http://www.gnuplot.info/ tested on version 4.6
 * libxslt1-dev
+* CASAVA 1.8.2 <http://support.illumina.com/sequencing/sequencing_software/casava.ilmn>
 
 ## Install
 ### Quick Start
@@ -49,6 +50,10 @@ Most of this tasks create sub-processes to speed up conversions
     biongs convert:bam:extract_genes BAM GENES --ensembl-release=N -o, --output=OUTPUT  # Extract GENES from bam. It connects to Ensembl Humnan,...
     biongs convert:bam:merge -i, --input-bams=one two three                             # Merge multiple bams in a single one, BAMS separated by...
     biongs convert:bam:sort BAM [PREFIX]                                                # Sort and create and index for the BAM file name
+    biongs convert:bcl:fastq:configure_conversion RUNDIR DATAOUTDIR                     # Configure the specific Run to be converted
+    biongs convert:bcl:fastq:convert RUNDIR DATAOUTDIR [SAMPLESHEET]                    # Convert a bcl dataset in fastq. By default it creates a
+                                                                                          directory with the same name of the dir attachin...
+    biongs convert:bcl:fastq:start_conversion CONF_DATA_DIR                             # Start the conversion
     biongs convert:bcl:qseq:convert RUN OUTPUT [JOBS]                                   # Convert a bcl dataset in qseq
     biongs convert:illumina:de:gene DIFF GTF                                            # extract the transcripts
     biongs convert:illumina:de:isoform DIFF GTF                                         # extract the transcripts
@@ -63,6 +68,9 @@ Most of this tasks create sub-processes to speed up conversions
                                                                                           SAMPLES is an array of index codes separated by commas lane
                                                                                           is an integer
 
+
+
+
 ### filter
 
     biongs filter:by_list TABLE LIST            # Extract from TABLE the row with a key in LIST
@@ -143,8 +151,56 @@ Most of this tasks create sub-processes to speed up conversions
 ## TasksExamples
 
 ### Conversion
+
+#### Extract gene(s) alignment from a BAM
+
    biongs convert:bam:extract_genes your_original.bam BLID,GATA3,PTPRC --ensembl_release=61 --ensembl_specie=homo_sapiens
 
+#### Demultiplex an Illumina Run.
+By default Illumina uses `SampleSheet.csv` in the `your_run/Data/Intensities/BaseCalls` file to describe the layout of your run
+
+    FCID,Lane,SampleID,SampleRef,Index,Description,Control,Recipe,Operator,SampleProject
+    D0C0DACXX,1,0113,Ensembl,CGATGT,Y1,N,R2,Doe,X
+    D0C0DACXX,1,0114,Ensembl,TGACCA,Y1,N,R2,Doe,X
+    D0C0DACXX,1,0115,Ensembl,ACAGTG,X1,N,R2,Doe,Y
+    D0C0DACXX,1,0116,Ensembl,GCCAAT,X1,N,R2,Doe,Y
+    D0C0DACXX,2,0117,Ensembl,CGATGT,Y1,N,R2,Doe,X
+    D0C0DACXX,2,0118,Ensembl,TGACCA,Y1,N,R2,Doe,X
+    D0C0DACXX,2,0119,Ensembl,ACAGTG,X1,N,R2,Doe,Y
+    D0C0DACXX,2,0120,Ensembl,GCCAAT,X1,N,R2,Doe,Y
+    D0C0DACXX,3,0121,Ensembl,CGATGT,Y1,N,R2,Doe,X
+    D0C0DACXX,3,0122,Ensembl,TGACCA,Y1,N,R2,Doe,X
+    D0C0DACXX,3,0123,Ensembl,ACAGTG,X1,N,R2,Doe,Y
+    D0C0DACXX,3,0124,Ensembl,GCCAAT,X1,N,R2,Doe,Y
+    D0C0DACXX,4,0125,Ensembl,CGATGT,Y1,N,R2,Doe,X
+    D0C0DACXX,4,0126,Ensembl,TGACCA,Y1,N,R2,Doe,X
+    D0C0DACXX,4,0127,Ensembl,ACAGTG,X1,N,R2,Doe,Y
+    D0C0DACXX,4,0128,Ensembl,GCCAAT,X1,N,R2,Doe,Y
+    D0C0DACXX,5,0095,Ensembl,ATCACG,Y1,N,R2,Doe,X
+    D0C0DACXX,5,0096,Ensembl,TTAGGC,Y1,N,R2,Doe,X
+    D0C0DACXX,5,0097,Ensembl,ACTTGA,X1,N,R2,Doe,Y
+    D0C0DACXX,5,0098,Ensembl,GATCAG,X1,N,R2,Doe,Y
+    D0C0DACXX,6,0109,Ensembl,ACTTGA,Y1,N,R2,Doe,X
+    D0C0DACXX,6,0110,Ensembl,GATCAG,Y1,N,R2,Doe,X
+    D0C0DACXX,6,0111,Ensembl,TAGCTT,X1,N,R2,Doe,Y
+    D0C0DACXX,6,0112,Ensembl,GGCTAC,X1,N,R2,Doe,Y
+    D0C0DACXX,7,0129,Ensembl,CGATGT,Y1,N,R2,Doe,X
+    D0C0DACXX,7,0130,Ensembl,TGACCA,Y1,N,R2,Doe,X
+    D0C0DACXX,7,0131,Ensembl,ACAGTG,X1,N,R2,Doe,Y
+    D0C0DACXX,7,0132,Ensembl,GCCAAT,X1,N,R2,Doe,Y
+    D0C0DACXX,8,0133,Ensembl,CGATGT,Y1,N,R2,Doe,X
+    D0C0DACXX,8,0134,Ensembl,TGACCA,Y1,N,R2,Doe,X
+    D0C0DACXX,8,0135,Ensembl,ACAGTG,X1,N,R2,Doe,Y
+    D0C0DACXX,8,0136,Ensembl,GCCAAT,X1,N,R2,Doe,Y
+
+We expect to find `SampleSheet.csv` in your run directory, in case of a custom name user can pass it as last parameter `--sample_sheet=your_sample_sheet.csv`.  
+To demultiplex your experiment
+
+    ngs biongs convert:bcl:fastq:convert /bio/ngs/raw/110321_H001_0100_AD10TMACXX/ /bio/ngs/data/110321_H001_0100_AD10TMACXX_DATA --cpu=8 > 110321_H125_0100_AD10TMACXX.log 2>&1
+
+This command will save the stdout on a log file in the current directory. You must specify the source directory and the destination. You can select the number of CPU to use for demultiplexing, 8 is the maximum value becase 8 lanes.  
+Typing `biongs help convert:bcl:fastq:convert` you can have a list of sub tasks. Where `biongs convert:bcl:fastq:configure_conversion RUNDIR DATAOUTDIR` corresponds to `configureBclToFastq.pl`and `biongs convert:bcl:fastq:start_conversion` to `make` in the demultiplexed directory. 
+
 ### Filtering
 When you have your mapped reads to a reference genome, you can decide to filter the output (GTF) to extract only those transcripts which have your desired requirements. You can filter for lenght, if it's multi or mono exon, the coverage, if it's a brand new transcript or an altrady annotated gene but with a new isoform or just the annotated transcripts.
 
@@ -171,6 +227,7 @@ Then in some case I need to extract only some of them or maybe parsing them from
 The first time tra_at_idx is used, it will take more time than usual becase it creates an internal index: a simple HASH mashalled and dumped, stored in a file with the name similar to the imput with an idx as postfix.
 
 
+
 # ForDevelopers
 
 ## HowToContribute 

data/VERSION

@@ -1 +1 @@
-0.5.0
+0.5.2

data/bio-ngs.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = "bio-ngs"
-  s.version = "0.5.0"
+  s.version = "0.5.2"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Francesco Strozzi", "Raoul J.P. Bonnal"]
-  s.date = "2012-06-04"
+  s.date = "2012-06-06"
   s.description = "bio-ngs provides a framework for handling NGS data with BioRuby"
   s.email = "francesco.strozzi@gmail.com"
   s.executables = ["biongs"]
@@ -42,6 +42,7 @@ Gem::Specification.new do |s|
     "lib/bio/appl/ngs/blast.rb",
     "lib/bio/appl/ngs/bowtie-inspect.rb",
     "lib/bio/appl/ngs/bwa.rb",
+    "lib/bio/appl/ngs/casava.rb",
     "lib/bio/appl/ngs/cufflinks.rb",
     "lib/bio/appl/ngs/cufflinks/gtf/gtf.rb",
     "lib/bio/appl/ngs/cufflinks/gtf/gtf_parser.rb",
@@ -188,7 +189,7 @@ Gem::Specification.new do |s|
   s.homepage = "http://github.com/helios/bioruby-ngs"
   s.licenses = ["MIT"]
   s.require_paths = ["lib"]
-  s.rubygems_version = "1.8.10"
+  s.rubygems_version = "1.8.15"
   s.summary = "bio-ngs provides a framework for handling NGS data with BioRuby"
 
   if s.respond_to? :specification_version then

data/lib/bio-ngs.rb

@@ -60,6 +60,7 @@ require 'bio/appl/ngs/samtools'
 require 'bio/appl/ngs/fastx'
 require 'bio/appl/ngs/blast'
 require 'bio/appl/ngs/bwa'
+require 'bio/appl/ngs/casava'
 
 #Illumina utility for projects
 require 'bio/ngs/illumina/illumina'

data/lib/bio/appl/ngs/bcl2qseq.rb

@@ -1,4 +1,5 @@
-#
+# DEPRECATED, refer to lib/bio/appl/ngs/casava.rb 
+
 #   bcl2qseq.rb - description
 #
 # Copyright:: Copyright (C) 2011
@@ -8,86 +9,86 @@
 #
 
 
-#require 'bio/command'
-#require 'shellwords'
-#require 'thor'
-#require 'bio/ngs/utils'
+# #require 'bio/command'
+# #require 'shellwords'
+# #require 'thor'
+# #require 'bio/ngs/utils'
 
-# usage: 
-#        setupBclToQseq.py -b /path/to/BaseCalls [--in-place|-o /path/to/Output] [options]
-# 
-# Script to setup the output directory for the conversion of BCLfiles produced by
-# RTA into a standard QSEQ-based base calls folder.
-# 
-# options:
-#   -h, --help            show this help message and exit
-#   -b BASE_CALLS_DIRECTORY, --base-calls-directory=BASE_CALLS_DIRECTORY
-#                         Full path to the Base Calls directory generated by the
-#                         instrument
-#   --in-place            Allow in-place conversion (in the Base Calls
-#                         directory)
-#   -o OUTPUT_DIRECTORY, --output-directory=OUTPUT_DIRECTORY
-#                         Full path to the output directory, if not in --in-
-#                         place mode
-#   -i INTENSITIES_DIRECTORY, --intensities-directory=INTENSITIES_DIRECTORY
-#                         Full path to the directory containing the intensities,
-#                         if different from the parent of the Base Calls
-#                         directory
-#   -f FILTER_DIRECTORY, --filter-directory=FILTER_DIRECTORY
-#                         Full path to the filter directory, if different from
-#                         the Base Calls directory
-#   -p POSITIONS_DIRECTORY, --positions-directory=POSITIONS_DIRECTORY
-#                         Full path to the positions directory, if different
-#                         from the Intensities directory
-#   -P POSITIONS_FORMAT, --positions-format=POSITIONS_FORMAT
-#                         Positions file format (supported formats are:
-#                         {'_pos.txt','.locs','.clocs'})
-#   --no-eamss            Do not apply the EAMSS quality masking
-#   --overwrite           Overwrite the content of the output directory if it
-#                         already exists
-#   --GERALD=GERALD       Path to the GERALD config file
-#   -S, --silent          Do not produce any information or warnings
-#   -Q, --quiet           Produce only warnings. Skips general information
-#   -V, --verbose         Produce additional debug information
-#   -v, --version         Print the version information and exits
-#   -L LOG_FILE, --log-file=LOG_FILE
-#                         Full path to the log file
-#   -c, --include-controls
-#                         Include controls information in Passing Filter column
-#   --ignore-missing-bcl  Assume missing *.bcl files correspond to a missed base
-#                         call (i.e., '.')
-#   --ignore-missing-stats
-#                         Fill in with zeros when *.stats files are missing
+# # usage: 
+# #        setupBclToQseq.py -b /path/to/BaseCalls [--in-place|-o /path/to/Output] [options]
+# # 
+# # Script to setup the output directory for the conversion of BCLfiles produced by
+# # RTA into a standard QSEQ-based base calls folder.
+# # 
+# # options:
+# #   -h, --help            show this help message and exit
+# #   -b BASE_CALLS_DIRECTORY, --base-calls-directory=BASE_CALLS_DIRECTORY
+# #                         Full path to the Base Calls directory generated by the
+# #                         instrument
+# #   --in-place            Allow in-place conversion (in the Base Calls
+# #                         directory)
+# #   -o OUTPUT_DIRECTORY, --output-directory=OUTPUT_DIRECTORY
+# #                         Full path to the output directory, if not in --in-
+# #                         place mode
+# #   -i INTENSITIES_DIRECTORY, --intensities-directory=INTENSITIES_DIRECTORY
+# #                         Full path to the directory containing the intensities,
+# #                         if different from the parent of the Base Calls
+# #                         directory
+# #   -f FILTER_DIRECTORY, --filter-directory=FILTER_DIRECTORY
+# #                         Full path to the filter directory, if different from
+# #                         the Base Calls directory
+# #   -p POSITIONS_DIRECTORY, --positions-directory=POSITIONS_DIRECTORY
+# #                         Full path to the positions directory, if different
+# #                         from the Intensities directory
+# #   -P POSITIONS_FORMAT, --positions-format=POSITIONS_FORMAT
+# #                         Positions file format (supported formats are:
+# #                         {'_pos.txt','.locs','.clocs'})
+# #   --no-eamss            Do not apply the EAMSS quality masking
+# #   --overwrite           Overwrite the content of the output directory if it
+# #                         already exists
+# #   --GERALD=GERALD       Path to the GERALD config file
+# #   -S, --silent          Do not produce any information or warnings
+# #   -Q, --quiet           Produce only warnings. Skips general information
+# #   -V, --verbose         Produce additional debug information
+# #   -v, --version         Print the version information and exits
+# #   -L LOG_FILE, --log-file=LOG_FILE
+# #                         Full path to the log file
+# #   -c, --include-controls
+# #                         Include controls information in Passing Filter column
+# #   --ignore-missing-bcl  Assume missing *.bcl files correspond to a missed base
+# #                         call (i.e., '.')
+# #   --ignore-missing-stats
+# #                         Fill in with zeros when *.stats files are missing
 
 
-module Bio
-  module Ngs    
-    class Bclqseq
+# module Bio
+#   module Ngs    
+#     class Bclqseq
 
-      include Bio::Command::Wrapper
+#       include Bio::Command::Wrapper
 
-      set_program Bio::Ngs::Utils.binary("setupBclToQseq.py")
+#       set_program Bio::Ngs::Utils.binary("setupBclToQseq.py")
 
-      add_option "base-calls-directory", :type => :string, :aliases =>'-b', :desc => 'Full path to the Base Calls directory generated by the instrument'
-      add_option "in-place",:type => :boolean, :desc => 'Allow in-place conversion (in the Base Calls directory)'
-      add_option "output-directory", :type => :string, :aliases => '-o', :desc => 'Full path to the output directory, if not in --in-place mode'
-      add_option "intensities-directory", :type => :string, :aliases => '-i', :desc => 'Full path to the directory containing the intensities, if different from the parent of the Base Calls directory'
-      add_option "filter-directory", :type => :string , :aliases => '-f', :desc => 'Full path to the filter directory, if different from the Base Calls directory'
-      add_option "positions-directory", :type => :string, :aliases => '-p', :desc => 'Full path to the positions directory, if different from the Intensities directory'
-      add_option "positions-format", :type => :string, :aliases => '-P', :desc => 'Positions file format (supported formats are: {\'_pos.txt\',\'.locs\',\'.clocs\'})'
-      add_option "no-eamss", :type => :boolean, :desc => 'Do not apply the EAMSS quality masking'
-      add_option "overwrite", :type => :boolean, :desc => 'Overwrite the content of the output directory if it already exists'
-      add_option "GERALD", :type => :string, :desc => 'Path to the GERALD config file'
-      add_option "silent", :type => :boolean, :aliases => '-S', :desc => 'Do not produce any information or warnings'
-      add_option "quiet", :type => :boolean, :aliases => '-Q', :desc => 'Produce only warnings. Skips general information'
-      add_option "verbose", :type => :boolean, :aliases => '-V', :desc => 'Produce additional debug information'
-      add_option "log-file", :type => :string, :aliases => '-L', :desc => 'Full path to the log file'
-      add_option "include-controls", :type => :boolean, :aliases => '-c', :desc => 'Include controls information in Passing Filter column'
-      add_option "ignore-missing-bcl", :type => :boolean, :desc => 'Assume missing *.bcl files correspond to a missed base call (i.e., \'.\')'
-      add_option "ignore-missin-stats", :type => :boolean, :desc => 'Fill in with zeros when *.stats files are missing'
+#       add_option "base-calls-directory", :type => :string, :aliases =>'-b', :desc => 'Full path to the Base Calls directory generated by the instrument'
+#       add_option "in-place",:type => :boolean, :desc => 'Allow in-place conversion (in the Base Calls directory)'
+#       add_option "output-directory", :type => :string, :aliases => '-o', :desc => 'Full path to the output directory, if not in --in-place mode'
+#       add_option "intensities-directory", :type => :string, :aliases => '-i', :desc => 'Full path to the directory containing the intensities, if different from the parent of the Base Calls directory'
+#       add_option "filter-directory", :type => :string , :aliases => '-f', :desc => 'Full path to the filter directory, if different from the Base Calls directory'
+#       add_option "positions-directory", :type => :string, :aliases => '-p', :desc => 'Full path to the positions directory, if different from the Intensities directory'
+#       add_option "positions-format", :type => :string, :aliases => '-P', :desc => 'Positions file format (supported formats are: {\'_pos.txt\',\'.locs\',\'.clocs\'})'
+#       add_option "no-eamss", :type => :boolean, :desc => 'Do not apply the EAMSS quality masking'
+#       add_option "overwrite", :type => :boolean, :desc => 'Overwrite the content of the output directory if it already exists'
+#       add_option "GERALD", :type => :string, :desc => 'Path to the GERALD config file'
+#       add_option "silent", :type => :boolean, :aliases => '-S', :desc => 'Do not produce any information or warnings'
+#       add_option "quiet", :type => :boolean, :aliases => '-Q', :desc => 'Produce only warnings. Skips general information'
+#       add_option "verbose", :type => :boolean, :aliases => '-V', :desc => 'Produce additional debug information'
+#       add_option "log-file", :type => :string, :aliases => '-L', :desc => 'Full path to the log file'
+#       add_option "include-controls", :type => :boolean, :aliases => '-c', :desc => 'Include controls information in Passing Filter column'
+#       add_option "ignore-missing-bcl", :type => :boolean, :desc => 'Assume missing *.bcl files correspond to a missed base call (i.e., \'.\')'
+#       add_option "ignore-missin-stats", :type => :boolean, :desc => 'Fill in with zeros when *.stats files are missing'
 
-    end #Bcl2seq
-  end #Ngs
-end #Bio 
+#     end #Bcl2seq
+#   end #Ngs
+# end #Bio 
 
 

data/lib/bio/appl/ngs/casava.rb

@@ -0,0 +1,271 @@
+#   casaba.rb - description
+#
+# Copyright:: Copyright (C) 2012
+#     Raoul Bonnal <@bioruby.org>
+# License:: The Ruby License
+#
+# CASAVA v1.8.2
+#
+# configureQseqToFastq.pl 
+# Usage:
+#     configureQseqToFastq.pl --input-dir DIR [options] | --help
+
+#   Summary:
+#     Create a makefile to convert a directory of qseq files to a directory
+#     tree of compressed fastq files following CASAVA 1.8 filename and
+#     directory structure conventions. If detected, configuration data used by
+#     GERALD are also transfered to the output directory.
+
+#     This script will not configure demultiplexing. The input directory must
+#     contain qseq files which are either non-demultiplexed or already
+#     demultiplexed by another utility.
+
+#   Options:
+#     --input-dir DIRECTORY
+#         Path to qseq directory (no default)
+
+#     --output-dir DIRECTORY
+#         Path to root of CASAVA 1.8 unaligned directory structure. Directory
+#         will be created if it does not exist (default:
+#         '<input-dir>/QseqToFastq/Unaligned')
+
+#     --fastq-cluster-count INTEGER
+#         Maximum number of fastq records per fastq file (default: 4000000)
+
+#     --config-file FILENAME
+#         Specify the Bustard config file to be copied to the fastq directory
+#         (default: '<input-dir>/config.xml')
+
+#     --summary-file FILENAME
+#         Specify the Bustard summary file to be copied to the fastq directory
+#         (default: '<input-dir>/BustardSummary.xml')
+
+#     --flowcell-id STRING
+#         Use the specified string as the flowcell id. (default value is
+#         parsed from the config-file)
+
+module Bio
+  module Ngs
+    class CASAVA    
+        class Bclqseq
+
+          include Bio::Command::Wrapper
+
+          set_program Bio::Ngs::Utils.binary("setupBclToQseq.py")
+
+          add_option "base-calls-directory", :type => :string, :aliases =>'-b', :desc => 'Full path to the Base Calls directory generated by the instrument'
+          add_option "in-place",:type => :boolean, :desc => 'Allow in-place conversion (in the Base Calls directory)'
+          add_option "output-directory", :type => :string, :aliases => '-o', :desc => 'Full path to the output directory, if not in --in-place mode'
+          add_option "intensities-directory", :type => :string, :aliases => '-i', :desc => 'Full path to the directory containing the intensities, if different from the parent of the Base Calls directory'
+          add_option "filter-directory", :type => :string , :aliases => '-f', :desc => 'Full path to the filter directory, if different from the Base Calls directory'
+          add_option "positions-directory", :type => :string, :aliases => '-p', :desc => 'Full path to the positions directory, if different from the Intensities directory'
+          add_option "positions-format", :type => :string, :aliases => '-P', :desc => 'Positions file format (supported formats are: {\'_pos.txt\',\'.locs\',\'.clocs\'})'
+          add_option "no-eamss", :type => :boolean, :desc => 'Do not apply the EAMSS quality masking'
+          add_option "overwrite", :type => :boolean, :desc => 'Overwrite the content of the output directory if it already exists'
+          add_option "GERALD", :type => :string, :desc => 'Path to the GERALD config file'
+          add_option "silent", :type => :boolean, :aliases => '-S', :desc => 'Do not produce any information or warnings'
+          add_option "quiet", :type => :boolean, :aliases => '-Q', :desc => 'Produce only warnings. Skips general information'
+          add_option "verbose", :type => :boolean, :aliases => '-V', :desc => 'Produce additional debug information'
+          add_option "log-file", :type => :string, :aliases => '-L', :desc => 'Full path to the log file'
+          add_option "include-controls", :type => :boolean, :aliases => '-c', :desc => 'Include controls information in Passing Filter column'
+          add_option "ignore-missing-bcl", :type => :boolean, :desc => 'Assume missing *.bcl files correspond to a missed base call (i.e., \'.\')'
+          add_option "ignore-missin-stats", :type => :boolean, :desc => 'Fill in with zeros when *.stats files are missing'
+
+      end #Bcl2seq
+
+      class ConfigBclFastq
+        include Bio::Command::Wrapper
+
+        set_program Bio::Ngs::Utils.binary("configureBclToFastq.pl")
+
+        # Usage:
+        #     configureBclToFastq.pl
+        #                 [--adapter-sequence adapter_fasta_file_path]
+        #                 [--use-bases-mask mask] [--no-eamss] [--with-failed-reads]
+        #                 [--input-dir base_calls_dir]
+        #                 [--intensities-dir intensities_dir]
+        #                 [--positions-dir positions_dir]
+        #                 [--positions-format .locs .clocs or _pos.txt]
+        #                 [--filter-dir filter_dir] [--output-dir output_dir]
+        #                 [--sample-sheet sample_sheet]
+        #                 [--mismatches num_of_mismatches per barcode component]
+        #                 [--fastq-cluster-count cluster_count]
+        #                 [--ignore-missing-stats] [--ignore-missing-bcl]
+        #                 [--ignore-missing-control] [--flowcell-id flow_cell_id]
+        #                 [--tiles tile_selection]
+
+        #     configureBclToFastq.pl
+        #                 --help or --man
+
+        # Options and Arguments:
+        #     --adapter-sequence adapter_fasta_file_path
+        #             Path to a multi-contig fasta file. If only one sequence is
+        #             specified within the fasta file, the same sequence would be used
+        #             for all reads. If multiple sequences are specified, the first
+        #             sequence would be used for the first read, the second sequence
+        #             for the second read.
+
+        #     --use-bases-mask mask[[,mask]...]
+        #             Conversion mask characters:
+
+        #               - Y or y: use
+        #               - N or n: discard
+        #               - I or i: use for indexing
+
+        #             If not given, the mask will be guessed from the RunInfo.xml file
+        #             in the run folder.
+
+        #             For instance, in a 2x76 indexed paired end run, the mask
+        #             Y76,I6n,y75n means: "use all 76 bases from the first end,
+        #             discard the last base of the indexing read, and use only the
+        #             first 75 bases of the second end".
+
+        #     --no-eamss Disable the masking of the quality values with EAMSS.
+
+        #     --with-failed-reads Include failed reads into the FASTQ files (by
+        #     default, only reads passing filter are included). default, only reads passing filter are included).
+
+        #     --input-dir base_calls_dir
+        #             Path to a valid BaseCalls directory (defaults to current dir)
+
+        #     --intensities-dir intensities_dir
+        #             Path to a valid Intensities directory (defaults to parent of
+        #             base_calls_dir)
+
+        #     --positions-dir positions_dir
+        #             Path to a directory containing positions files. (defaults
+        #             depending on RTA version)
+
+        #     --positions-format .locs .clocs or _pos.txt
+        #             Format of the input cluster positions information. (defaults to
+        #             .clocs)
+
+        #     --filter-dir filter_dir
+        #             Path to a directory containing filter files. (defaults depending
+        #             on RTA version)
+
+        #     --output-dir output_dir
+        #             Path to the demultiplexed output (defaults to
+        #             base_calls_dir/../../../Unaligned)
+
+        #     --sample-sheet sample_sheet
+        #             Path to SampleSheet.csv (defaults to
+        #             base_call_dir/SampleSheet.csv)
+
+        #     --mismatches num_of_mismatches per barcode component
+        #             Comma-separated list of mismatches allowed for each barcode
+        #             component. Either 0 or 1 (defaults to 0)
+
+        #     --fastq-cluster-count cluster_count
+        #             Maximum number of fastq records per fastq file (default:
+        #             4000000).
+
+        #     --ignore-missing-stats
+        #             Fill in with zeros when *.stats files are missing
+
+        #     --ignore-missing-bcl
+        #             Interpret missing *.bcl files as no call
+
+        #     --ignore-missing-control
+        #             Interpret missing control files as not-set control bits
+
+        #     --tiles regex[[,regex]...]
+        #             Comma-separated list of regular expressions to select only a
+        #             subset of the tiles available in the flow-cell.
+
+        #              - to select all the tiles ending with "5" in all lanes: --tiles [0-9][0-9][0-9]5
+        #              - to select tile 2 in lane 1 and all the tiles in the other lanes: --tiles s_1_0002,s_[2-8]
+
+        #     --flowcell-id flow_cell_id
+        #             Use the specified string as the flowcell id. (default value is
+        #             parsed from the config-file)
+
+        #     --help Print a brief help message and exit.
+
+        #     --man View this help formatted in "man" style.
+
+        #     Running the small test data set included with CASAVA
+        #             Note that with the example below, if the SampleSheet.csv file is
+        #             not found in the BaseCalls folder, the data is assumed to be
+        #             non-multiplexed. Use "--sample-sheet" option to override default
+        #             SampleSheet.csv location.
+
+        #              /opt/CASAVA_v1.8.2/bin/configureBclToFastq.pl \
+        #              --output-dir ./Unaligned \
+        #              --input-dir /opt/CASAVA_v1.8.2/share/CASAVA-1.8.2/examples/Validation/Default/Data/Intensities/BaseCalls
+
+        #               make -C Unaligned  # use make -j <parallel jobs> to speedup the conversion
+
+
+          add_option "adapter-sequence", :type => :string, :desc => 'Path to a multi-contig fasta file. If only one sequence is specified within the fasta file, the same sequence would be used for all reads. If multiple sequences are specified, the first sequence would be used for the first read, the second sequence for the second read.'
+          add_option "use-bases-mask", :type => :string, :desc => 'If not given, the mask will be guessed from the RunInfo.xml file in the run folder.'
+          add_option "no-eamss", :type => :boolean, :desc => 'Disable the masking of the quality values with EAMSS.'
+          add_option "with-failed-reads", :type => :boolean, :desc => 'Include failed reads into the FASTQ files (by default, only reads passing filter are included).'
+          add_option "input-dir", :type => :string, :aliases =>'-i', :desc => 'Path to a valid BaseCalls directory (defaults to current dir)'
+          add_option "intensities-dir", :type => :string, :desc => 'Path to a valid Intensities directory (defaults to parent of base_calls_dir)'
+          add_option "positions-dir", :tpe => :string, :desc => 'Path to a directory containing positions files. (defaults depending on RTA version)'
+          add_option "positions-format", :type => :string, :desc => 'Format of the input cluster positions information. (defaults to .clocs)'
+          add_option "filter_dir", :type => :string, :desc => 'Path to a directory containing filter files. (defaults depending on RTA version)'
+          add_option "output-dir",:type => :string, :aliases => '-o', :desc => 'Path to the demultiplexed output (defaults to base_calls_dir/../../../Unaligned)'
+          add_option "sample-sheet", :type => :string, :desc => 'Path to SampleSheet.csv (defaults to base_call_dir/SampleSheet.csv)' #, :default => 'SampleSheet.csv'
+          add_option "mismatches", :type => :numeric, :desc => 'Comma-separated list of mismatches allowed for each barcode component. Either 0 or 1 (defaults to 0)', :defaults=> 1
+          add_option "fastq-cluster-count", :type => :numeric, :desc => 'Maximum number of fastq records per fastq file (default: 4000000).'
+          add_option "ignore-missin-stats", :type => :boolean, :desc => 'Fill in with zeros when *.stats files are missing'
+          add_option "ignore-missing-bcl", :type => :boolean, :desc => 'Interpret missing *.bcl files as no call'
+          add_option "ignore-missing-control", :type => :boolean, :desc => 'Interpret missing control files as not-set control bits'
+          add_option "tiles", :type => :string, :desc => 'Comma-separated list of regular expressions to select only a subset of the tiles available in the flow-cell.'
+          add_option "flowcell-id", :type => :string , :desc => 'Use the specified string as the flowcell id. (default value is parsed from the config-file)'
+      end #ConfigBclFastq
+
+      class ConfigQseqFastq
+        include Bio::Command::Wrapper
+
+        set_program Bio::Ngs::Utils.binary("configureQseqToFastq.pl")
+
+        # Usage:
+        #     configureQseqToFastq.pl --input-dir DIR [options] | --help
+
+        #   Summary:
+        #     Create a makefile to convert a directory of qseq files to a directory
+        #     tree of compressed fastq files following CASAVA 1.8 filename and
+        #     directory structure conventions. If detected, configuration data used by
+        #     GERALD are also transfered to the output directory.
+
+        #     This script will not configure demultiplexing. The input directory must
+        #     contain qseq files which are either non-demultiplexed or already
+        #     demultiplexed by another utility.
+
+        #   Options:
+        #     --input-dir DIRECTORY
+        #         Path to qseq directory (no default)
+
+        #     --output-dir DIRECTORY
+        #         Path to root of CASAVA 1.8 unaligned directory structure. Directory
+        #         will be created if it does not exist (default:
+        #         '<input-dir>/QseqToFastq/Unaligned')
+
+        #     --fastq-cluster-count INTEGER
+        #         Maximum number of fastq records per fastq file (default: 4000000)
+
+        #     --config-file FILENAME
+        #         Specify the Bustard config file to be copied to the fastq directory
+        #         (default: '<input-dir>/config.xml')
+
+        #     --summary-file FILENAME
+        #         Specify the Bustard summary file to be copied to the fastq directory
+        #         (default: '<input-dir>/BustardSummary.xml')
+
+        #     --flowcell-id STRING
+        #         Use the specified string as the flowcell id. (default value is
+        #         parsed from the config-file)  
+          add_option "input-dir", :type => :string, :aliases =>'-i', :desc => 'Path to qseq directory (no default)'
+          add_option "output-dir",:type => :string, :aliases => '-o', :desc => 'Path to root of CASAVA 1.8 unaligned directory structure. Directory will be created if it does not exist (default:\'<input-dir>/QseqToFastq/Unaligned\')'
+          add_option "fastq-cluster-count", :type => :numeric, :aliases => '-c', :desc => 'Maximum number of fastq records per fastq file (default: 4000000)'
+          add_option "config-file", :type => :string, :aliases => '-f', :desc => 'Specify the Bustard config file to be copied to the fastq directory (default: \'<input-dir>/config.xml\')'
+          add_option "summary-file", :type => :string , :aliases => '-s', :desc => 'Specify the Bustard summary file to be copied to the fastq directory (default: \'<input-dir>/BustardSummary.xml\')'
+          add_option "flowcell-id", :type => :string, :aliases => '-d', :desc => 'Use the specified string as the flowcell id. (default value is parsed from the config-file)'
+      end #ConfigQseqFastq
+
+    end #CASAVA
+  end #Ngs
+end #Bio 

data/lib/tasks/convert.thor

@@ -206,13 +206,13 @@ module Convert
           module Bcl 
             class Qseq < Thor
               desc "convert RUN OUTPUT [JOBS]", "Convert a bcl dataset in qseq"
-              def converts (run_basecalls_root, output, jobs=1)
+              def convert (run_basecalls_root, output, jobs=1)
                 invoke :configure_conversion, [run_basecalls_root, output]
                 invoke :run_bcl_to_qseq, [run_basecalls_root, jobs]
               end #bcl_to_qseq
 
               desc "configure_conversion RUN_DIR OUTPUT ", "Configure the specific Run to be converted", :hide => true
-              Bio::Ngs::Bclqseq.new.thor_task(self, :configure_conversion) do |wrapper, task, run_basecalls_root, output|
+              Bio::Ngs::CASAVA::Bclqseq.new.thor_task(self, :configure_conversion) do |wrapper, task, run_basecalls_root, output|
                 #wrapper.params={"base-calls-directory" => "#{run_basecalls_root}/Data/Intensities/BaseCalls", "output-directory" => output}
                 task.options.base_calls_directory=run_basecalls_root
                 #puts "Test parametri #{task.inspect}"
@@ -227,6 +227,51 @@ module Convert
                 puts "make recursive -j #{jobs} -f #{run_basecalls_root}/Data/Intensities/BaseCalls/Makefile -C #{run_basecalls_root}/Data/Intensities/BaseCalls"
               end #run_bcl_to_qseq
             end #Qseq
+
+            class Fastq < Thor
+
+
+
+              desc "convert RUNDIR DATAOUTDIR [SAMPLESHEET]", "Convert a bcl dataset in fastq. By default it creates a directory with the same name of the rawdata dir attaching a postfix _DATA"
+              method_option :cpu, :type => :numeric, :desc => "number of cpu to use for demultiplexing", :default => 1
+              method_option "sample-sheet", :type=> :string, :default => 'SampleSheet.csv'
+              def convert(run_basecalls_root, dataoutdir, samplesheet=nil)
+                configure_conversion(run_basecalls_root, dataoutdir)
+                start_conversion(dataoutdir, options[:cpu])
+              end #convert bcl to fastq
+
+              desc "configure_conversion RUNDIR DATAOUTDIR", "Configure the specific Run to be converted"
+              Bio::Ngs::CASAVA::ConfigBclFastq.new.thor_task(self, :configure_conversion) do |wrapper, task, run_basecalls_root, dataoutdir|
+                base_calls_dir = File.join(run_basecalls_root, "Data/Intensities/BaseCalls")
+
+                if sample_sheet=task.options["sample-sheet"]
+                  if File.dirname(sample_sheet) == '.'
+                    if File.exists?(File.join(base_calls_dir,sample_sheet))
+                      #default place
+                      sample_sheet = File.join(base_calls_dir,sample_sheet)
+                    elsif File.exists?(File.join(run_basecalls_root,sample_sheet))
+                      #search for sample sheet in the root of raw data directoy
+                      sample_sheet = File.join(run_basecalls_root,sample_sheet)
+                    else
+                      raise "Unable to find a valid sample sheet: #{sample_sheet}"
+                    end
+                  elsif !File.exists?(sample_sheet)
+                    raise "Unable to find a valid sample sheet: #{sample_sheet}"
+                  end
+                end
+                wrapper.params={"input-dir" => "#{run_basecalls_root}/Data/Intensities/BaseCalls", "output-dir" => dataoutdir, "sample-sheet" => sample_sheet}
+                wrapper.run
+              end
+
+
+              desc "start_conversion CONF_DATA_DIR", "Start the conversion"
+              def start_conversion(conf_data_dir, cpu)
+                Dir.chdir(conf_data_dir) do 
+                  `make -j "#{cpu}"`
+                end
+              end #start_conversion
+
+            end #Fastq
           end #Bcl
 
 

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: bio-ngs
 version: !ruby/object:Gem::Version
-  version: 0.5.0
+  version: 0.5.2
   prerelease: 
 platform: ruby
 authors:
@@ -10,11 +10,11 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-06-04 00:00:00.000000000 Z
+date: 2012-06-06 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bio
-  requirement: &2153797260 !ruby/object:Gem::Requirement
+  requirement: &2166262160 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -22,10 +22,10 @@ dependencies:
         version: 1.4.2
   type: :runtime
   prerelease: false
-  version_requirements: *2153797260
+  version_requirements: *2166262160
 - !ruby/object:Gem::Dependency
   name: bio-samtools
-  requirement: &2153796600 !ruby/object:Gem::Requirement
+  requirement: &2166261600 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -33,10 +33,10 @@ dependencies:
         version: 0.3.2
   type: :runtime
   prerelease: false
-  version_requirements: *2153796600
+  version_requirements: *2166261600
 - !ruby/object:Gem::Dependency
   name: thor
-  requirement: &2153795920 !ruby/object:Gem::Requirement
+  requirement: &2166260980 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - =
@@ -44,10 +44,10 @@ dependencies:
         version: 0.14.6
   type: :runtime
   prerelease: false
-  version_requirements: *2153795920
+  version_requirements: *2166260980
 - !ruby/object:Gem::Dependency
   name: rubyvis
-  requirement: &2153794440 !ruby/object:Gem::Requirement
+  requirement: &2166260420 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -55,10 +55,10 @@ dependencies:
         version: 0.5.0
   type: :runtime
   prerelease: false
-  version_requirements: *2153794440
+  version_requirements: *2166260420
 - !ruby/object:Gem::Dependency
   name: daemons
-  requirement: &2153792480 !ruby/object:Gem::Requirement
+  requirement: &2166259800 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -66,10 +66,10 @@ dependencies:
         version: 1.1.0
   type: :runtime
   prerelease: false
-  version_requirements: *2153792480
+  version_requirements: *2166259800
 - !ruby/object:Gem::Dependency
   name: ruby-ensembl-api
-  requirement: &2153791560 !ruby/object:Gem::Requirement
+  requirement: &2166259280 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -77,10 +77,10 @@ dependencies:
         version: 1.0.1
   type: :runtime
   prerelease: false
-  version_requirements: *2153791560
+  version_requirements: *2166259280
 - !ruby/object:Gem::Dependency
   name: activerecord
-  requirement: &2153790500 !ruby/object:Gem::Requirement
+  requirement: &2166258500 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -88,10 +88,10 @@ dependencies:
         version: 3.0.5
   type: :runtime
   prerelease: false
-  version_requirements: *2153790500
+  version_requirements: *2166258500
 - !ruby/object:Gem::Dependency
   name: progressbar
-  requirement: &2153805400 !ruby/object:Gem::Requirement
+  requirement: &2166257420 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -99,10 +99,10 @@ dependencies:
         version: 0.9.0
   type: :runtime
   prerelease: false
-  version_requirements: *2153805400
+  version_requirements: *2166257420
 - !ruby/object:Gem::Dependency
   name: rake
-  requirement: &2153804180 !ruby/object:Gem::Requirement
+  requirement: &2166272400 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - =
@@ -110,10 +110,10 @@ dependencies:
         version: 0.9.2.2
   type: :runtime
   prerelease: false
-  version_requirements: *2153804180
+  version_requirements: *2166272400
 - !ruby/object:Gem::Dependency
   name: json
-  requirement: &2153802400 !ruby/object:Gem::Requirement
+  requirement: &2166270800 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -121,10 +121,10 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *2153802400
+  version_requirements: *2166270800
 - !ruby/object:Gem::Dependency
   name: parallel
-  requirement: &2153800840 !ruby/object:Gem::Requirement
+  requirement: &2166269020 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -132,10 +132,10 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *2153800840
+  version_requirements: *2166269020
 - !ruby/object:Gem::Dependency
   name: bio-blastxmlparser
-  requirement: &2153800100 !ruby/object:Gem::Requirement
+  requirement: &2166266860 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -143,10 +143,10 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *2153800100
+  version_requirements: *2166266860
 - !ruby/object:Gem::Dependency
   name: shoulda
-  requirement: &2153798900 !ruby/object:Gem::Requirement
+  requirement: &2166264600 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -154,10 +154,10 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *2153798900
+  version_requirements: *2166264600
 - !ruby/object:Gem::Dependency
   name: bundler
-  requirement: &2153812960 !ruby/object:Gem::Requirement
+  requirement: &2166278940 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -165,10 +165,10 @@ dependencies:
         version: 1.1.0
   type: :development
   prerelease: false
-  version_requirements: *2153812960
+  version_requirements: *2166278940
 - !ruby/object:Gem::Dependency
   name: jeweler
-  requirement: &2153812040 !ruby/object:Gem::Requirement
+  requirement: &2166277640 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -176,10 +176,10 @@ dependencies:
         version: 1.8.3
   type: :development
   prerelease: false
-  version_requirements: *2153812040
+  version_requirements: *2166277640
 - !ruby/object:Gem::Dependency
   name: rcov
-  requirement: &2153811000 !ruby/object:Gem::Requirement
+  requirement: &2166275480 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -187,10 +187,10 @@ dependencies:
         version: 0.9.11
   type: :development
   prerelease: false
-  version_requirements: *2153811000
+  version_requirements: *2166275480
 - !ruby/object:Gem::Dependency
   name: bio
-  requirement: &2153809620 !ruby/object:Gem::Requirement
+  requirement: &2166274860 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -198,10 +198,10 @@ dependencies:
         version: 1.4.2
   type: :development
   prerelease: false
-  version_requirements: *2153809620
+  version_requirements: *2166274860
 - !ruby/object:Gem::Dependency
   name: jdbc-sqlite3
-  requirement: &2153807400 !ruby/object:Gem::Requirement
+  requirement: &2166274300 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -209,10 +209,10 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *2153807400
+  version_requirements: *2166274300
 - !ruby/object:Gem::Dependency
   name: activerecord-jdbcsqlite3-adapter
-  requirement: &2153806580 !ruby/object:Gem::Requirement
+  requirement: &2166273680 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -220,10 +220,10 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *2153806580
+  version_requirements: *2166273680
 - !ruby/object:Gem::Dependency
   name: sqlite3
-  requirement: &2153821900 !ruby/object:Gem::Requirement
+  requirement: &2166273120 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -231,10 +231,10 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *2153821900
+  version_requirements: *2166273120
 - !ruby/object:Gem::Dependency
   name: thor
-  requirement: &2153821100 !ruby/object:Gem::Requirement
+  requirement: &2166288940 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - =
@@ -242,10 +242,10 @@ dependencies:
         version: 0.14.6
   type: :development
   prerelease: false
-  version_requirements: *2153821100
+  version_requirements: *2166288940
 - !ruby/object:Gem::Dependency
   name: ffi
-  requirement: &2153820420 !ruby/object:Gem::Requirement
+  requirement: &2166288460 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -253,10 +253,10 @@ dependencies:
         version: 1.0.6
   type: :development
   prerelease: false
-  version_requirements: *2153820420
+  version_requirements: *2166288460
 - !ruby/object:Gem::Dependency
   name: rubyvis
-  requirement: &2153819440 !ruby/object:Gem::Requirement
+  requirement: &2166287980 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -264,10 +264,10 @@ dependencies:
         version: 0.5.0
   type: :development
   prerelease: false
-  version_requirements: *2153819440
+  version_requirements: *2166287980
 - !ruby/object:Gem::Dependency
   name: rspec
-  requirement: &2153818340 !ruby/object:Gem::Requirement
+  requirement: &2166287500 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -275,10 +275,10 @@ dependencies:
         version: 2.5.0
   type: :development
   prerelease: false
-  version_requirements: *2153818340
+  version_requirements: *2166287500
 - !ruby/object:Gem::Dependency
   name: daemons
-  requirement: &2153816560 !ruby/object:Gem::Requirement
+  requirement: &2166286880 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -286,10 +286,10 @@ dependencies:
         version: 1.1.0
   type: :development
   prerelease: false
-  version_requirements: *2153816560
+  version_requirements: *2166286880
 - !ruby/object:Gem::Dependency
   name: bio-samtools
-  requirement: &2153814840 !ruby/object:Gem::Requirement
+  requirement: &2166286080 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -297,10 +297,10 @@ dependencies:
         version: 0.3.2
   type: :development
   prerelease: false
-  version_requirements: *2153814840
+  version_requirements: *2166286080
 - !ruby/object:Gem::Dependency
   name: ruby-ensembl-api
-  requirement: &2153827720 !ruby/object:Gem::Requirement
+  requirement: &2166285560 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -308,10 +308,10 @@ dependencies:
         version: 1.0.1
   type: :development
   prerelease: false
-  version_requirements: *2153827720
+  version_requirements: *2166285560
 - !ruby/object:Gem::Dependency
   name: activerecord
-  requirement: &2153826500 !ruby/object:Gem::Requirement
+  requirement: &2166284900 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -319,10 +319,10 @@ dependencies:
         version: 3.0.5
   type: :development
   prerelease: false
-  version_requirements: *2153826500
+  version_requirements: *2166284900
 - !ruby/object:Gem::Dependency
   name: progressbar
-  requirement: &2153825440 !ruby/object:Gem::Requirement
+  requirement: &2166283580 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -330,10 +330,10 @@ dependencies:
         version: 0.9.0
   type: :development
   prerelease: false
-  version_requirements: *2153825440
+  version_requirements: *2166283580
 - !ruby/object:Gem::Dependency
   name: json
-  requirement: &2153824660 !ruby/object:Gem::Requirement
+  requirement: &2166282460 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -341,10 +341,10 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *2153824660
+  version_requirements: *2166282460
 - !ruby/object:Gem::Dependency
   name: rake
-  requirement: &2153823940 !ruby/object:Gem::Requirement
+  requirement: &2166281940 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - =
@@ -352,10 +352,10 @@ dependencies:
         version: 0.9.2.2
   type: :development
   prerelease: false
-  version_requirements: *2153823940
+  version_requirements: *2166281940
 - !ruby/object:Gem::Dependency
   name: parallel
-  requirement: &2153823140 !ruby/object:Gem::Requirement
+  requirement: &2166281440 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -363,10 +363,10 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *2153823140
+  version_requirements: *2166281440
 - !ruby/object:Gem::Dependency
   name: bio-blastxmlparser
-  requirement: &2153822560 !ruby/object:Gem::Requirement
+  requirement: &2166311140 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -374,7 +374,7 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *2153822560
+  version_requirements: *2166311140
 description: bio-ngs provides a framework for handling NGS data with BioRuby
 email: francesco.strozzi@gmail.com
 executables:
@@ -408,6 +408,7 @@ files:
 - lib/bio/appl/ngs/blast.rb
 - lib/bio/appl/ngs/bowtie-inspect.rb
 - lib/bio/appl/ngs/bwa.rb
+- lib/bio/appl/ngs/casava.rb
 - lib/bio/appl/ngs/cufflinks.rb
 - lib/bio/appl/ngs/cufflinks/gtf/gtf.rb
 - lib/bio/appl/ngs/cufflinks/gtf/gtf_parser.rb
@@ -565,7 +566,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: 330803756225747013
+      hash: -324179817321782076
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements:
@@ -574,7 +575,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.10
+rubygems_version: 1.8.15
 signing_key: 
 specification_version: 3
 summary: bio-ngs provides a framework for handling NGS data with BioRuby