bio-ngs 0.4.2.alpha.01 → 0.4.4.alpha.01

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

@@ -0,0 +1,210 @@
+#
+#   bwa.rb - description
+#
+# Copyright:: Copyright (C) 2011
+#     Francesco Strozzi <francesco.strozzi@gmail.com>
+# License:: The Ruby License
+#
+#
+# 
+# Program: bwa (alignment via Burrows-Wheeler transformation)
+# Version: 0.6.0-r85
+# 
+
+#Usage:   bwa <command> [options]
+#
+#Command: index         index sequences in the FASTA format
+#         aln           gapped/ungapped alignment
+#         samse         generate alignment (single ended)
+#         sampe         generate alignment (paired ended)
+#         bwasw         BWA-SW for long queries
+#         fastmap       identify super-maximal exact matches
+#
+#         fa2pac        convert FASTA to PAC format
+#         pac2bwt       generate BWT from PAC
+#         pac2bwtgen    alternative algorithm for generating BWT
+#         bwtupdate     update .bwt to the new format
+#         bwt2sa        generate SA from BWT and Occ
+#         pac2cspac     convert PAC to color-space PAC
+#         stdsw         standard SW/NW alignment
+
+
+module Bio
+  module Ngs    
+    module Bwa
+            
+      #Usage:   bwa index [-a bwtsw|div|is] [-c] <in.fasta>
+      #
+      #Options: -a STR    BWT construction algorithm: bwtsw or is [is]
+      #         -p STR    prefix of the index [same as fasta name]
+      #         -c        build color-space index
+                   
+      class Index
+        include Bio::Command::Wrapper
+        set_program Bio::Ngs::Utils.binary("bwa")
+        set_sub_program "index"
+        use_aliases
+        add_option :algorithm, :type => :string, :aliases => "-a", :desc => "BWT construction algorithm: bwtsw or is [is]"
+        add_option :prefix, :type => :string, :aliases => "-p", :desc => "prefix of the index [same as fasta name]"
+      end #Index
+
+
+      #Usage:   bwa aln [options] <prefix> <in.fq>
+      #
+      #Options: -n NUM    max #diff (int) or missing prob under 0.02 err rate (float) [0.04]
+      #         -o INT    maximum number or fraction of gap opens [1]
+      #         -e INT    maximum number of gap extensions, -1 for disabling long gaps [-1]
+      #         -i INT    do not put an indel within INT bp towards the ends [5]
+      #         -d INT    maximum occurrences for extending a long deletion [10]
+      #         -l INT    seed length [32]
+      #         -k INT    maximum differences in the seed [2]
+      #         -m INT    maximum entries in the queue [2000000]
+      #         -t INT    number of threads [1]
+      #         -M INT    mismatch penalty [3]
+      #         -O INT    gap open penalty [11]
+      #         -E INT    gap extension penalty [4]
+      #         -R INT    stop searching when there are >INT equally best hits [30]
+      #         -q INT    quality threshold for read trimming down to 35bp [0]
+      #         -f FILE   file to write output to instead of stdout
+      #         -B INT    length of barcode
+      #         -L        log-scaled gap penalty for long deletions
+      #         -N        non-iterative mode: search for all n-difference hits (slooow)
+      #         -I        the input is in the Illumina 1.3+ FASTQ-like format
+      #         -b        the input read file is in the BAM format
+      #         -0        use single-end reads only (effective with -b)
+      #         -1        use the 1st read in a pair (effective with -b)
+      #         -2        use the 2nd read in a pair (effective with -b)
+      #         -Y        filter Casava-filtered sequences
+
+      class Aln
+        include Bio::Command::Wrapper
+        set_program Bio::Ngs::Utils.binary("bwa")
+        set_sub_program "aln"
+        use_aliases
+        add_option :num, :type => :numeric, :aliases => "-n", :desc => "max #diff (int) or missing prob under 0.02 err rate (float) [0.04]"
+        add_option :gap_open, :type => :numeric, :aliases => "-o", :desc => "maximum number or fraction of gap opens [1]"
+        add_option :gap_ext, :type => :numeric, :aliases => "-e", :desc => "maximum number of gap extensions, -1 for disabling long gaps [-1]"
+        add_option :indel, :type => :numeric, :aliases => "-i", :desc => "do not put an indel within INT bp towards the ends [5]"
+        add_option :extending_deletion, :type => :numeric, :aliases => "-d", :desc => "maximum occurrences for extending a long deletion [10]"
+        add_option :seed_length, :type => :numeric, :aliases => "-l", :desc => "seed length [32]"
+        add_option :seed_diff, :type => :numeric, :aliases => "-k", :desc => "maximum differences in the seed [2]"
+        add_option :queue, :type => :numeric, :aliases => "-m", :desc => "maximum entries in the queue [2000000]"
+        add_option :threads, :type => :numeric, :aliases => "-t", :desc => "number of threads [1]"
+        add_option :mismatch_penalty, :type => :numeric, :aliases => "-M", :desc => "mismatch penalty [3]"
+        add_option :gap_open_penalty, :type => :numeric, :aliases => "-O", :desc => "gap open penalty [11]"
+        add_option :gap_extension_penalty, :type => :numeric, :aliases => "-E", :desc => "gap extension penalty [4]"
+        add_option :best_hit, :type => :numeric, :aliases => "-R", :desc => "stop searching when there are >INT equally best hits [30]"
+        add_option :quality_trimming, :type => :numeric, :aliases => "-q", :desc => "quality threshold for read trimming down to 35bp [0]"
+        add_option :file_out, :type => :string, :aliases => "-f", :desc => "file to write output to instead of stdout"
+        add_option :barcode_length, :type => :numeric, :aliases => "-B", :desc => "length of barcode"
+        add_option :log_scale_penalty, :type => :boolean, :aliases => "-L", :desc => "log-scaled gap penalty for long deletions"
+        add_option :non_iterative, :type => :boolean, :aliases => "-N", :desc => "non-iterative mode: search for all n-difference hits"
+        add_option :illumina_13, :type => :boolean, :aliases => "-I", :desc => "the input is in the Illumina 1.3+ FASTQ-like format"
+        add_option :bam, :type => :boolean, :aliases => "-b", :desc => "the input read file is in the BAM format"
+        add_option :single, :type => :boolean, :aliases => "-0", :desc => "use single-end reads only (effective with -b)"
+        add_option :first, :type => :boolean, :aliases => "-1", :desc => "use the 1st read in a pair (effective with -b)"
+        add_option :second, :type => :boolean, :aliases => "-2", :desc => "use the 2nd read in a pair (effective with -b)"
+        add_option :filter, :type => :boolean, :aliases => "-Y", :desc => "filter Casava-filtered sequences"
+      end # Aln
+      
+      
+      # Usage: bwa samse [-n max_occ] [-f out.sam] [-r RG_line] <prefix> <in.sai> <in.fq>
+      
+      class Samse
+        include Bio::Command::Wrapper
+        set_program Bio::Ngs::Utils.binary("bwa")
+        set_sub_program "samse"
+        use_aliases
+        add_option :max_occ, :type => :numeric, :aliases => "-n", :desc => "max_occ"
+        add_option :file_out, :type => :string, :aliases => "-f", :desc => "file name to save data"
+        add_option :rg_line, :type => :string, :aliases => "-r", :desc => "RG line"   
+      end #Samse
+      
+      
+      
+      #Usage:   bwa sampe [options] <prefix> <in1.sai> <in2.sai> <in1.fq> <in2.fq>
+      #
+      #Options: -a INT   maximum insert size [500]
+      #         -o INT   maximum occurrences for one end [100000]
+      #         -n INT   maximum hits to output for paired reads [3]
+      #         -N INT   maximum hits to output for discordant pairs [10]
+      #         -c FLOAT prior of chimeric rate (lower bound) [1.0e-05]
+      #         -f FILE  sam file to output results to [stdout]
+      #         -r STR   read group header line such as `@RG\tID:foo\tSM:bar' [null]
+      #         -P       preload index into memory (for base-space reads only)
+      #         -s       disable Smith-Waterman for the unmapped mate
+      #         -A       disable insert size estimate (force -s)
+      
+      class Sampe
+        include Bio::Command::Wrapper
+        set_program Bio::Ngs::Utils.binary("bwa")
+        set_sub_program "sampe"
+        use_aliases    
+        add_option :max_insert, :type => :numeric, :aliases => "-a", :desc => "maximum insert size [500]"
+        add_option :max_occurrences, :type => :numeric, :aliases => "-o", :desc => "maximum occurrences for one end [100000]"
+        add_option :max_hits, :type => :numeric, :aliases => "-n", :desc => "maximum hits to output for paired reads [3]"
+        add_option :max_hits_discordant, :type => :numeric, :aliases => "-N", :desc => "maximum hits to output for discordant pairs [10]"
+        add_option :chimeric_rate, :type => :numeric, :aliases => "-c", :desc => "prior of chimeric rate (lower bound) [1.0e-05]"
+        add_option :file_out, :type => :string, :aliases => "-f", :desc => "sam file to output results to [stdout]"
+        add_option :read_group, :type => :string, :aliases => "-r", :desc => "read group header line such as `@RG\tID:foo\tSM:bar' [null]"
+        add_option :preload_index, :type => :boolean, :aliases => "-P", :desc => "preload index into memory (for base-space reads only)"
+        add_option :disable_sw, :type => :boolean, :aliases => "-s", :desc => "disable Smith-Waterman for the unmapped mate"
+        add_option :disable_insert_estimate, :type => :boolean, :aliases => "-A", :desc => "disable insert size estimate (force -s)"
+      end #Sampe
+      
+      
+      #Usage:   bwa bwasw [options] <target.prefix> <query.fa> [query2.fa]
+      #
+      #Options: -a INT   score for a match [1]
+      #         -b INT   mismatch penalty [3]
+      #         -q INT   gap open penalty [5]
+      #         -r INT   gap extension penalty [2]
+      #
+      #         -t INT   number of threads [1]
+      #
+      #         -w INT   band width [50]
+      #         -m FLOAT mask level [0.50]
+      #
+      #         -T INT   score threshold divided by a [30]
+      #         -s INT   maximum seeding interval size [3]
+      #         -z INT   Z-best [1]
+      #         -N INT   # seeds to trigger reverse alignment [5]
+      #         -c FLOAT coefficient of length-threshold adjustment [5.5]
+      #         -H       in SAM output, use hard clipping rather than soft
+      #         -f FILE  file to output results to instead of stdout
+      
+      class Bwasw
+        include Bio::Command::Wrapper
+        set_program Bio::Ngs::Utils.binary("bwa")
+        set_sub_program "bwasw"
+        use_aliases
+        add_option :paired, :type => :string, :desc => "paired reads"
+        add_option :match_score, :type => :numeric, :aliases => "-a", :desc => "score for a match [1]"
+        add_option :mismatch_penalty, :type => :numeric, :aliases => "-b", :desc => "mismatch penalty [3]"
+        add_option :gap_open_penalty, :type => :numeric, :aliases => "-q", :desc => "gap open penalty [5]"
+        add_option :gap_ext_penalty, :type => :numeric, :aliases => "-r", :desc => "gap extension penalty [2]"
+        add_option :threads, :type => :numeric, :aliases => "-t", :desc => "number of threads [1]"
+        add_option :band_width, :type => :numeric, :aliases => "-w", :desc => "band width [50]"
+        add_option :mask_level, :type => :numeric, :aliases => "-m", :desc => "mask level [0.50]"
+        add_option :score_threshold, :type => :numeric, :aliases => "-T", :desc => "score threshold divided by a [30]"
+        add_option :max_seeding, :type => :numeric, :aliases => "-s", :desc => "maximum seeding interval size [3]"
+        add_option :z_best, :type => :numeric, :aliases => "-z", :desc => "Z-best [1]"
+        add_option :seed_reverse, :type => :numeric, :aliases => "-N", :desc => "seeds to trigger reverse alignment [5]"
+        add_option :length_threshold, :type => :numeric, :aliases => "-c", :desc => "coefficient of length-threshold adjustment [5.5]"
+        add_option :hard_clip, :type => :boolean, :aliases => "-H", :desc => "in SAM output, use hard clipping rather than soft"
+        add_option :file_out, :type => :string, :aliases => "-f", :desc => "file to output results to instead of stdout"
+      end
+      
+      # Usage: bwa fastmap [-l minLen=17] [-w maxSaSize=20] <idxbase> <in.fq>
+      class Fastmap
+        include Bio::Command::Wrapper
+        set_program Bio::Ngs::Utils.binary("bwa")
+        set_sub_program "fastmap"
+        use_aliases
+        add_option :min_length, :type => :numeric, :aliases => "-l", :desc => "minLen [17]"
+        add_option :max_sa_size, :type => :numeric, :aliases => "-w", :desc => "maxSaSize [20]"        
+      end
+      
+    end #Bwa
+  end #Ngs
+end #Bio

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

@@ -107,10 +107,9 @@ module Bio
         set_program Bio::Ngs::Utils.binary("fastq_quality_boxplot_graph.sh")
         use_aliases
         add_option :ps, :type => :boolean, :aliases => "-p", :desc => "Generate PostScript (.PS) file. Default is PNG image."
-        add_option :output, :type=>:string, :aliases => "-o", :desc => "FASTQ output file."
-        add_option :input, :type=>:string, :aliases => "-i", :desc => "FASTQ input file."
+        add_option :output, :type=>:string, :aliases => "-o", :desc => "Output file name. default is STDOUT.", :collapse => true
+        add_option :input, :type=>:string, :aliases => "-i", :desc => "Input file. Should be the output of \"fastx_quality_statistics\" program.", :collapse => true
         add_option :title, :type => :string, :aliases => "-t", :desc => "Title (usually the solexa file name) - will be plotted on the graph."
-        add_option :quality_type,  :type=>:numeric, :default => 33, :aliases => "-Q", :desc=>"Quality of fastq file"
       end #ReadsBoxPlot
 
       # Solexa-Reads coverage plotter
@@ -127,10 +126,9 @@ module Bio
         set_program Bio::Ngs::Utils.binary("fastq_coverage_graph.sh")
         use_aliases
         add_option :ps, :type => :boolean, :aliases => "-p", :desc => "Generate PostScript (.PS) file. Default is PNG image."
-        add_option :output, :type=>:string, :aliases => "-o", :desc => "FASTQ output file."
-        add_option :input, :type=>:string, :aliases => "-i", :desc => "FASTQ input file."
+        add_option :output, :type=>:string, :aliases => "-o", :desc => "Output file name. default is STDOUT.", :collapse => true
+        add_option :input, :type=>:string, :aliases => "-i", :desc => "Input file. Should be the output of \"fastx_quality_statistics\" program.", :collapse => true
         add_option :title, :type => :string, :aliases => "-t", :desc => "Title (usually the solexa file name) - will be plotted on the graph."
-        add_option :quality_type,  :type=>:numeric, :default => 33, :aliases => "-Q", :desc=>"Quality of fastq file"
       end #ReadsCoverage
 
 
@@ -188,6 +186,24 @@ module Bio
         add_option :quality_type,  :type=>:numeric, :default => 33, :aliases => "-Q", :desc=>"Quality of fastq file"
       end #ReadsCoverage      
 
+  # FASTA/Q Nucleotide Distribution Plotter
+
+# Usage: /usr/local/bin/fastx_nucleotide_distribution_graph.sh [-i INPUT.TXT] [-t TITLE] [-p] [-o OUTPUT]
+
+#   [-p]           - Generate PostScript (.PS) file. Default is PNG image.
+#   [-i INPUT.TXT] - Input file. Should be the output of "fastx_quality_statistics" program.
+#   [-o OUTPUT]    - Output file name. default is STDOUT.
+#   [-t TITLE]     - Title - will be plotted on the graph.
+      class NucleotideDistribution
+        include Bio::Command::Wrapper
+        set_program Bio::Ngs::Utils.binary "fastx_nucleotide_distribution_graph.sh"
+        use_aliases
+        add_option :ps, :type => :boolean, :aliases => "-p", :desc => "Generate PostScript (.PS) file. Default is PNG image."
+        add_option :output, :type=>:string, :aliases => "-o", :desc => "Output file name. default is STDOUT.", :collapse => true
+        add_option :input, :type=>:string, :aliases => "-i", :desc => "Input file. Should be the output of \"fastx_quality_statistics\" program.", :collapse => true
+        add_option :title, :type => :string, :aliases => "-t", :desc => "Title (usually the solexa file name) - will be plotted on the graph."
+      end
+
     end #Fastx
   end #Ngs
 end #Bio

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

@@ -113,6 +113,91 @@ module Bio
         add_option :copy_header, :type => :string, :aliases => "-h", :desc => "copy the header in FILE to <out.bam> [in1.bam]"
       end #Merge
       
+      #Usage: samtools mpileup [options] in1.bam [in2.bam [...]]
+
+      #Input options:
+
+       #      -6           assume the quality is in the Illumina-1.3+ encoding
+       #      -A           count anomalous read pairs
+       #      -B           disable BAQ computation
+       #      -b FILE      list of input BAM files [null]
+       #      -C INT       parameter for adjusting mapQ; 0 to disable [0]
+       #      -d INT       max per-BAM depth to avoid excessive memory usage [250]
+       #      -E           extended BAQ for higher sensitivity but lower specificity
+       #      -f FILE      faidx indexed reference sequence file [null]
+       #      -G FILE      exclude read groups listed in FILE [null]
+       #      -l FILE      list of positions (chr pos) or regions (BED) [null]
+       #      -M INT       cap mapping quality at INT [60]
+       #      -r STR       region in which pileup is generated [null]
+       #      -R           ignore RG tags
+       #      -q INT       skip alignments with mapQ smaller than INT [0]
+       #      -Q INT       skip bases with baseQ/BAQ smaller than INT [13]
+
+      #Output options:
+
+      #       -D           output per-sample DP in BCF (require -g/-u)
+      #       -g           generate BCF output (genotype likelihoods)
+      #       -O           output base positions on reads (disabled by -g/-u)
+      #       -s           output mapping quality (disabled by -g/-u)
+      #       -S           output per-sample strand bias P-value in BCF (require -g/-u)
+      #       -u           generate uncompress BCF output
+
+      #SNP/INDEL genotype likelihoods options (effective with `-g' or `-u'):
+
+      #       -e INT       Phred-scaled gap extension seq error probability [20]
+      #       -F FLOAT     minimum fraction of gapped reads for candidates [0.002]
+      #       -h INT       coefficient for homopolymer errors [100]
+      #       -I           do not perform indel calling
+      #       -L INT       max per-sample depth for INDEL calling [250]
+      #       -m INT       minimum gapped reads for indel candidates [1]
+      #       -o INT       Phred-scaled gap open sequencing error probability [40]
+      #       -P STR       comma separated list of platforms for indels [all]
+
+      #Notes: Assuming diploid individuals.
+
+
+      class Mpileup
+        include Bio::Command::Wrapper
+        set_program Bio::Ngs::Utils.binary("samtools")
+        set_sub_program "mpileup"
+        add_option :illumina13, :type => :boolean, :aliases => "-6", :desc => "assume the quality is in the Illumina-1.3+ encoding"
+        add_option :anomalous, :type => :boolean, :aliases => "-A", :desc => "count anomalous read pairs"
+        add_option :baq, :type => :boolean, :aliases => "-B", :desc => "disable BAQ computation"
+        add_option :bam, :type => :string, :aliases => "-b", :desc => "list of input BAM files [null]"
+        add_option :adjust, :type => :numeric, :aliases => "-C", :desc => "parameter for adjusting mapQ; 0 to disable [0]"
+        add_option :depth, :type => :numeric, :aliases => "-d", :desc => "max per-BAM depth to avoid excessive memory usage [250]"
+        add_option :extended, :type => :boolean, :aliases => "-E", :desc => "extended BAQ for higher sensitivity but lower specificity"
+        add_option :file_in, :type => :string, :aliases => "-f", :desc => "faidx indexed reference sequence file [null]"
+        add_option :readgroup, :type => :string, :aliases => "-G", :desc => "exclude read groups listed in FILE [null]"
+        add_option :positions, :type => :string, :aliases => "-l", :desc => "list of positions (chr pos) or regions (BED) in FILE [null]"
+        add_option :mapping_quality, :type => :numeric, :aliases => "-M", :desc => "cap mapping quality at INT [60]"
+        add_option :region, :type => :string, :aliases => "r", :desc => "region in which pileup is generated [null]"
+        add_option :ignoreRG, :type => :boolean, :aliases => "-R", :desc => "ignore RG tags"
+        add_option :align_qual, :type => :numeric, :aliases => "-q", :desc => "skip alignments with mapQ smaller than INT [0]"
+        add_option :base_qual, :type => :numeric, :aliases => "-Q", :desc => "skip bases with baseQ/BAQ smaller than INT [13]"
+        add_option :dp, :type => :boolean, :aliases => "-D", :desc => "output per-sample DP in BCF (require -g/-u)"
+        add_option :bcfout, :type => :boolean, :aliases => "-g", :desc => "generate BCF output (genotype likelihoods)"
+        add_option :basepositions, :type => :boolean, :aliases => "-O", :desc => "output base positions on reads (disabled by -g/-u)"
+        add_option :mapq_out, :type => :boolean, :aliases => "-s", :desc => "output mapping quality (disabled by -g/-u)"  
+        add_option :strand_bias, :type => :boolean, :aliases => "-S", :desc => "output per-sample strand bias P-value in BCF (require -g/-u)"
+        add_option :uncompressed, :type => :boolean, :aliases => "-u", :desc => "generate uncompress BCF output"
+        add_option :gap_error, :type => :numeric, :aliases => "-e", :desc => "Phred-scaled gap extension seq error probability [20]"
+        add_option :reads_fraction, :type => :numeric, :aliases => "-F", :desc => "minimum fraction of gapped reads for candidates [0.002]"
+        add_option :homopolymer_errors, :type => :numeric, :aliases => "-h", :desc => "coefficient for homopolymer errors [100]"
+        add_option :noindel, :type => :boolean, :aliases => "-I", :desc => "do not perform indel calling"
+        add_option :sample_depth, :type => :numeric, :aliases => "-L", :desc => "max per-sample depth for INDEL calling [250]"
+        add_option :min_gap, :type => :numeric, :aliases => "-m", :desc => "minimum gapped reads for indel candidates [1]"
+        add_option :gap_open, :type => :numeric, :aliases => "-o", :desc => "Phred-scaled gap open sequencing error probability [40]"
+        add_option :indel_platforms, :type => :string, :aliases => "-P", :desc => "comma separated list of platforms for indels [all]"
+      end #mpileup
+
+      class Faidx
+        include Bio::Command::Wrapper
+        set_program Bio::Ngs::Utils.binary("samtools")
+        set_sub_program "faidx" 
+      end #faidx
+
+
     end #Samtools
   end #Ngs
 end #Bio

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

@@ -148,7 +148,7 @@ module Bio
       add_option "tmp-dir", :type => :string
       add_option "zpacker", :type => :string, :aliases => '-z'
       add_option "unmapped-fifo", :type => :boolean, :aliases => '-X'
-      add_option "initial-read-mismatches", :type => :int, :aliases => '-N'
+      add_option "initial-read-mismatches", :type => :numeric, :aliases => '-N'
       add_option "segment-mismatches", :type => :numeric
       add_option "segment-length", :type => :numeric
       add_option "min-closure-exon", :type => :numeric

data/lib/bio/ngs/ext/versions.yaml

@@ -13,6 +13,22 @@ common:
         suffix:   tar.bz2
         desc:     "Fastx-toolkit version 0.0.13 requires libgtextutils-0.6 (available here for download). A recent g++ compiler (tested with GNU G++ 4.1.2 and later). The fasta_clipping_histogram tool requires two perl modules: PerlIO::gzip and GD::Graph::bars. The fastx_barcode_splitter tool requires GNU sed. The fastq_quality_boxplot tool requires gnuplot version 4.2 or newer."
         type:     source
+    bwa:
+        version:  0.6.1
+        url:      http://sourceforge.net/projects/bio-bwa/files/bwa-0.6.1.tar.bz2/download
+        basename: bwa-0.6.1
+        suffix:   tar.bz2
+        desc:     "Burrows-Wheeler Aligner"
+        type:     make
+    samtools:
+        version:  0.1.18
+        url:      http://sourceforge.net/projects/samtools/files/samtools/0.1.18/samtools-0.1.18.tar.bz2/download
+        basename: samtools-0.1.18
+        suffix:   tar.bz2
+        desc:     "SAMtools"
+        type:     make       
+
+        
 linux:
     cufflinks:
         version:  1.3.0

data/lib/bio/ngs/record.rb

@@ -26,7 +26,7 @@ module Bio
       
       def load   
           tasks = []
-          YAML.each_document(@file) do |ydoc| 
+          YAML.load_stream(@file) do |ydoc| 
             ydoc[:args].flatten!
             tasks << ydoc
           end
@@ -41,7 +41,7 @@ module Bio
       
       def is_saved?(params)    
         tasks = []
-        YAML.each_document(@file) {|ydoc| tasks << ydoc}
+        YAML.load_stream(@file) {|ydoc| tasks << ydoc}
         return tasks.include?(params)
       end
       

data/lib/bio/ngs/utils.rb

@@ -23,13 +23,6 @@ module Bio
       end
       class << self
         
-        def parallel_exec(command_blocks)
-          command_blocks.each do |block|
-            fork(&block)
-          end
-          Process.waitall
-        end
-        
         def binary(name)
           begin
             if !(plugin_binaries_found = find_binary_files(name)).empty?
@@ -47,7 +40,7 @@ module Bio
 
         def os_type
           require 'rbconfig'
-          case Config::CONFIG['host_os']
+          case RbConfig::CONFIG['host_os']
           when /darwin/ then return "osx" 
           when /linux/ then return "linux"
           when /mswin|mingw/ then raise NotImplementedError, "This plugin does not run on Windows"
@@ -154,6 +147,16 @@ module Bio
               end #cd
             end #uncompress_compile
             
+            def just_make(tool_name, tool_record, path_external, path_binary)
+              puts "Uncompressing #{tool_name}..."
+              tool_dir_name = uncompress_any(tool_name, tool_record)
+              puts "Compiling #{tool_name}..."
+              cd(tool_dir_name) do
+                system "make"
+                FileUtils.cp tool_name,path_binary
+              end #cd
+            end
+            
             def install_binary(tool_name, tool_record, path_external, path_binary)
               require 'fileutils'
               include FileUtils::Verbose

data/lib/enumerable.rb

@@ -34,4 +34,16 @@ module Enumerable
     return Math.sqrt(self.sample_variance)
   end
 
-end  #  module Enumerable
+end  #  module Enumerable
+
+class Array
+  def / len
+    a = []
+    each_with_index do |x,i|
+      a << [] if i % len == 0
+      a.last << x
+    end
+    a
+  end
+end
+