miga-base 0.3.1.1 → 0.3.1.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: b722632a715da6a149257fe83361a009f7d1c965
-  data.tar.gz: 5e5582682e72ea8cfff97e82c6f72a85de7ab9b4
+  metadata.gz: 787c36c0ff7eb3a77d1b6fd4dd73015b4b49850e
+  data.tar.gz: 2a4ec0d82f8be2bb8e486d3d5410d909b01f3522
 SHA512:
-  metadata.gz: 37f1df3197453259c9a0eec7dcd679378edeb4605d63d98b2c80d57d02a966391829ee08faa8039ff44f431cf144c6e9fc1b4c75ac8bbb1683b92ebd683cbfb8
-  data.tar.gz: a5a5af7f26b8fce3979669d76c6df85ccdc94da052db2292571b8a00e594144016517226d937a59e9ef5a61d6191d09c92b976ebd6abb5e5ef875fb19e882786
+  metadata.gz: 71bf56e6cbfdeb36d3f19c9a4ea4aaac8160537ca3b7a95c6bff44d83e07298f8df3889fd3719eaaf9beae4adf9024b1f53e7a9ff743aadeb802c29664838fed
+  data.tar.gz: d351e7f4374a7859b3661a554c967f11406dcc696763da6e3b623025412ed9dcfe8bfe46f6125d22ef5ab341df1e978d93b0e54e222462faa55b7746dca931ef

data/actions/add_result.rb

@@ -3,10 +3,13 @@
 # @package MiGA
 # @license Artistic-2.0
 
-o = {q:true}
+o = {q:true, force:false}
 opts = OptionParser.new do |opt|
   opt_banner(opt)
   opt_object(opt, o, [:project, :dataset_opt, :result])
+  opt.on("-f", "--force",
+    "Forces re-indexing of the result even if it's already registered."
+    ){ |v| o[:force]=v }
   opt_common(opt, o)
 end.parse!
 
@@ -19,12 +22,8 @@ p = MiGA::Project.load(o[:project])
 raise "Impossible to load project: #{o[:project]}" if p.nil?
 
 $stderr.puts "Registering result." unless o[:q]
-if o[:dataset].nil?
-  r = p.add_result o[:name].to_sym
-else
-  d = p.dataset(o[:dataset])
-  r = d.add_result o[:name].to_sym
-end
+obj = o[:dataset].nil? ? p : p.dataset(o[:dataset])
+r = obj.add_result(o[:name].to_sym, true, force: o[:force])
 
 raise "Cannot add result, incomplete expected files." if r.nil?
 

data/actions/init.rb

@@ -107,7 +107,11 @@ File.open(File.expand_path("utils/requirements.txt", miga), "r") do |fh|
     $stderr.print "Testing #{r[0]}#{" (#{r[3]})" if r[3]}... "
     path = nil
     loop do
-      d_path = File.dirname(`which "#{r[1]}"`)
+      if File.exist? o[:config]
+        d_path = File.dirname(`source "#{o[:config]}" && which "#{r[1]}"`)
+      else
+        d_path = File.dirname(`which "#{r[1]}"`)
+      end
       if o[:ask] or d_path=="."
         path = ask_user("Where can I find it?", d_path, nil, true)
       else
@@ -188,67 +192,70 @@ $stderr.puts ""
 
 # Configure daemon
 $stderr.puts "Default daemon configuration:"
-v = {created:Time.now.to_s, updated:Time.now.to_s}
-v[:type] = ask_user("Please select the type of daemon you want to setup",
-          o[:dtype], %w(bash qsub msub))
-case v[:type]
-  when "bash"
-    v[:latency] = ask_user("How long should I sleep? (in seconds)","30").to_i
-    v[:maxjobs] = ask_user("How many jobs can I launch at once?", "6").to_i
-    v[:ppn]     = ask_user("How many CPUs can I use per job?", "2").to_i
-    $stderr.puts "Setting up internal daemon defaults."
-    $stderr.puts "If you don't understand this just leave default values:"
-    v[:cmd]     = ask_user(
-      "How should I launch tasks?\n  %1$s: script path, %2$s: variables, " +
-      "%3$d: CPUs, %4$s: log file, %5$s: task name.\n",
-      "%2$s '%1$s' > '%4$s' 2>&1")
-    v[:var]     = ask_user(
-      "How should I pass variables?\n  %1$s: keys, %2$s: values.\n",
-      "%1$s=%2$s")
-    v[:varsep]  = ask_user("What should I use to separate variables?", " ")
-    v[:alive]   = ask_user(
-      "How can I know that a process is still alive?\n  %1$s: PID, " +
-      "output should be 1 for running and 0 for non-running.\n",
-      "ps -p '%1$s'|tail -n+2|wc -l")
-    v[:kill]    = ask_user(
-      "How should I terminate tasks?\n  %s: process ID.", "kill -9 '%s'")
-  else # [qm]sub
-    queue       = ask_user("What queue should I use?", nil, nil, true)
-    v[:latency] = ask_user("How long should I sleep? (in seconds)", "150").to_i
-    v[:maxjobs] = ask_user("How many jobs can I launch at once?", "300").to_i
-    v[:ppn]     = ask_user("How many CPUs can I use per job?", "4").to_i
-    $stderr.puts "Setting up internal daemon defaults."
-    $stderr.puts "If you don't understand this just leave default values:"
-    v[:cmd]     = ask_user(
-      "How should I launch tasks?\n  %1$s: script path, %2$s: variables, " +
-      "%3$d: CPUs, %4$d: log file, %5$s: task name.\n",
-      "#{v[:type]} -q '#{queue}' -v '%2$s' -l nodes=1:ppn=%3$d %1$s " +
-      "-j oe -o '%4$s' -N '%5$s' -l mem=9g -l walltime=12:00:00 | grep .")
-    v[:var]     = ask_user(
-      "How should I pass variables?\n  %1$s: keys, %2$s: values.\n",
-      "%1$s=%2$s")
-    v[:varsep]  = ask_user("What should I use to separate variables?", ",")
-    if v[:type] == "qsub"
-      v[:alive] = ask_user(
-        "How can I know that a process is still alive?\n  %1$s: job id, " +
+daemon_f = File.expand_path(".miga_daemon.json", ENV["HOME"])
+unless File.exist?(daemon_f) and ask_user(
+          "A template daemon already exists, do you want to preserve it?",
+          "yes", %w(yes no))=="yes"
+  v = {created:Time.now.to_s, updated:Time.now.to_s}
+  v[:type] = ask_user("Please select the type of daemon you want to setup",
+            o[:dtype], %w(bash qsub msub))
+  case v[:type]
+    when "bash"
+      v[:latency] = ask_user("How long should I sleep? (in seconds)","30").to_i
+      v[:maxjobs] = ask_user("How many jobs can I launch at once?", "6").to_i
+      v[:ppn]     = ask_user("How many CPUs can I use per job?", "2").to_i
+      $stderr.puts "Setting up internal daemon defaults."
+      $stderr.puts "If you don't understand this just leave default values:"
+      v[:cmd]     = ask_user(
+        "How should I launch tasks?\n  %1$s: script path, %2$s: variables, " +
+        "%3$d: CPUs, %4$s: log file, %5$s: task name.\n",
+        "%2$s '%1$s' > '%4$s' 2>&1")
+      v[:var]     = ask_user(
+        "How should I pass variables?\n  %1$s: keys, %2$s: values.\n",
+        "%1$s=%2$s")
+      v[:varsep]  = ask_user("What should I use to separate variables?", " ")
+      v[:alive]   = ask_user(
+        "How can I know that a process is still alive?\n  %1$s: PID, " +
         "output should be 1 for running and 0 for non-running.\n",
-        "qstat -f '%1$s'|grep ' job_state ='|perl -pe 's/.*= //'|grep '[^C]'" +
-        "|tail -n1|wc -l|awk '{print $1}'")
-    v[:kill]    = ask_user(
-      "How should I terminate tasks?\n  %s: process ID.", "qdel '%s'")
-    else
-      v[:alive] = ask_user(
-        "How can I know that a process is still alive?\n  %1$s: job id, " +
-        "output should be 1 for running and 0 for non-running.\n",
-        "checkjob '%1$s'|grep '^State:'|perl -pe 's/.*: //'" +
-        "|grep 'Deferred\\|Hold\\|Idle\\|Starting\\|Running\\|Blocked'"+
-        "|tail -n1|wc -l|awk '{print $1}'")
-    v[:kill]    = ask_user(
-      "How should I terminate tasks?\n  %s: process ID.", "canceljob '%s'")
-    end
-end
-File.open(File.expand_path(".miga_daemon.json", ENV["HOME"]), "w") do |fh|
-  fh.puts JSON.pretty_generate(v)
+        "ps -p '%1$s'|tail -n+2|wc -l")
+      v[:kill]    = ask_user(
+        "How should I terminate tasks?\n  %s: process ID.", "kill -9 '%s'")
+    else # [qm]sub
+      queue       = ask_user("What queue should I use?", nil, nil, true)
+      v[:latency] = ask_user("How long should I sleep? (in seconds)","150").to_i
+      v[:maxjobs] = ask_user("How many jobs can I launch at once?", "300").to_i
+      v[:ppn]     = ask_user("How many CPUs can I use per job?", "4").to_i
+      $stderr.puts "Setting up internal daemon defaults."
+      $stderr.puts "If you don't understand this just leave default values:"
+      v[:cmd]     = ask_user(
+        "How should I launch tasks?\n  %1$s: script path, %2$s: variables, " +
+        "%3$d: CPUs, %4$d: log file, %5$s: task name.\n",
+        "#{v[:type]} -q '#{queue}' -v '%2$s' -l nodes=1:ppn=%3$d %1$s " +
+        "-j oe -o '%4$s' -N '%5$s' -l mem=9g -l walltime=12:00:00 | grep .")
+      v[:var]     = ask_user(
+        "How should I pass variables?\n  %1$s: keys, %2$s: values.\n",
+        "%1$s=%2$s")
+      v[:varsep]  = ask_user("What should I use to separate variables?", ",")
+      if v[:type] == "qsub"
+        v[:alive] = ask_user(
+          "How can I know that a process is still alive?\n  %1$s: job id, " +
+          "output should be 1 for running and 0 for non-running.\n",
+          "qstat -f '%1$s'|grep ' job_state ='|perl -pe 's/.*= //'|grep '[^C]'"+
+          "|tail -n1|wc -l|awk '{print $1}'")
+      v[:kill]    = ask_user(
+        "How should I terminate tasks?\n  %s: process ID.", "qdel '%s'")
+      else
+        v[:alive] = ask_user(
+          "How can I know that a process is still alive?\n  %1$s: job id, " +
+          "output should be 1 for running and 0 for non-running.\n",
+          "checkjob '%1$s'|grep '^State:'|perl -pe 's/.*: //'" +
+          "|grep 'Deferred\\|Hold\\|Idle\\|Starting\\|Running\\|Blocked'"+
+          "|tail -n1|wc -l|awk '{print $1}'")
+      v[:kill]    = ask_user(
+        "How should I terminate tasks?\n  %s: process ID.", "canceljob '%s'")
+      end
+  end
+  File.open(daemon_f, "w"){ |fh| fh.puts JSON.pretty_generate(v) }
 end
 $stderr.puts ""
 

data/actions/stats.rb

@@ -43,31 +43,43 @@ if o[:compute]
   stats = {}
   case o[:name]
   when :raw_reads
-    scr = "awk 'NR%4==2{L+=length($0)} END{print NR/4, L*4/NR}'"
     if r[:files][:pair1].nil?
-      s = `#{scr} '#{r.file_path :single}'`.chomp.split(" ")
-      stats = {reads: s[0].to_i, average_length: [s[1].to_f, "bp"]}
+      s = MiGA::MiGA.seqs_length(r.file_path(:single), :fastq, gc: true)
+      stats = {reads: s[:n],
+        length_average: [s[:avg], "bp"],
+        length_standard_deviation: [s[:sd], "bp"],
+        g_c_content: [s[:gc], "%"]}
     else
-      s1 = `#{scr} '#{r.file_path :pair1}'`.chomp.split(" ")
-      s2 = `#{scr} '#{r.file_path :pair2}'`.chomp.split(" ")
-      stats = {read_pairs: s1[0].to_i,
-        average_length_forward: [s1[1].to_f, "bp"],
-        average_length_reverse: [s2[1].to_f, "bp"]}
+      s1 = MiGA::MiGA.seqs_length(r.file_path(:pair1), :fastq, gc: true)
+      s2 = MiGA::MiGA.seqs_length(r.file_path(:pair2), :fastq, gc: true)
+      stats = {read_pairs: s1[:n],
+        forward_length_average: [s1[:avg], "bp"],
+        forward_length_standard_deviation: [s1[:sd], "bp"],
+        forward_g_c_content: [s1[:gc], "%"],
+        reverse_length_average: [s2[:avg], "bp"],
+        reverse_length_standard_deviation: [s2[:sd], "bp"],
+        reverse_g_c_content: [s2[:gc], "%"]}
     end
   when :trimmed_fasta
-    scr = "awk '{L+=$2} END{print NR, L/NR}'"
     f = r[:files][:coupled].nil? ? r.file_path(:single) : r.file_path(:coupled)
-    s = `FastA.length.pl '#{f}' | #{scr}`.chomp.split(" ")
-    stats = {reads: s[0].to_i, average_length: [s[1].to_f, "bp"]}
+    s = MiGA::MiGA.seqs_length(f, :fasta, gc: true)
+    stats = {reads: s[:n],
+      length_average: [s[:avg], "bp"],
+      length_standard_deviation: [s[:sd], "bp"],
+      g_c_content: [s[:gc], "%"]}
   when :assembly
-    f = r.file_path :largecontigs
-    s = `FastA.N50.pl '#{f}'`.chomp.split("\n").map{|i| i.gsub(/.*: /,'').to_i}
-    stats = {contigs: s[1], n50: [s[0], "bp"], total_length: [s[2], "bp"]}
+    s = MiGA::MiGA.seqs_length(r.file_path(:largecontigs), :fasta,
+      n50:true, gc:true)
+    stats = {contigs: s[:n], n50: [s[:n50], "bp"],
+      total_length: [s[:tot], "bp"], g_c_content: [s[:gc], "%"]}
   when :cds
-    scr = "awk '{L+=$2} END{print NR, L/NR}'"
-    f = r.file_path :proteins
-    s = `FastA.length.pl '#{f}' | #{scr}`.chomp.split(" ")
-    stats = {predicted_proteins: s[0].to_i, average_length: [s[1].to_f, "aa"]}
+    s = MiGA::MiGA.seqs_length(r.file_path(:proteins), :fasta)
+    stats = {predicted_proteins: s[:n], average_length: [s[:avg], "aa"]}
+    asm = d.add_result(:assembly, false)
+    unless asm.nil? or asm[:stats][:total_length].nil?
+      stats[:coding_density] =
+        [300.0*s[:tot]/asm[:stats][:total_length][0], "%"]
+    end
   when :essential_genes
     if d.is_multi?
       stats = {median_copies:0, mean_copies:0}
@@ -118,7 +130,7 @@ end
 
 if o[:key].nil?
   r[:stats].each do |k,v|
-    puts "#{k.to_s.unmiga_name.capitalize}: #{
+    puts "#{k==:g_c_content ? "G+C content" : k.to_s.unmiga_name.capitalize}: #{
       v.is_a?(Array) ? v.join(" ") : v}."
   end
 else

data/lib/miga/common.rb

@@ -4,6 +4,7 @@
 require "miga/version"
 require "json"
 require "tempfile"
+require "zlib"
 
 ##
 # Generic class used to handle system-wide information and methods, and parent
@@ -103,6 +104,50 @@ class MiGA::MiGA
       tmp.unlink
     end
   end
+
+  ##
+  # Calculates the average and standard deviation of the sequence lengths in
+  # a FastA or FastQ file (supports gzipped files). The +format+ must be a
+  # Symbol, one of +:fasta+ or +:fastq+. Additional estimations can be
+  # controlled via the +opts+ Hash. Supported options include:
+  # - +:n50+: If true, it also returns the N50 and the median (in bp).
+  # - +gc+: If true, it also returns the G+C content (in %).
+  def self.seqs_length(file, format, opts={})
+    fh = (file =~ /\.gz/) ? Zlib::GzipReader.open(file) : File.open(file, "r")
+    l = []
+    gc = 0
+    i = 0 # <- Zlib::GzipReader doesn't set $.
+    fh.each_line do |ln|
+      i += 1
+      if (format==:fasta and ln =~ /^>/) or (format==:fastq and (i % 4)==1)
+        l << 0
+      elsif format==:fasta or (i % 4)==2
+        l[l.size-1] += ln.chomp.size
+        gc += ln.scan(/[GCgc]/).count if opts[:gc]
+      end
+    end
+    fh.close
+    
+    o = { n: l.size, tot: l.inject(:+) }
+    o[:avg] = o[:tot].to_f/l.size
+    o[:var] = l.map{ |a| a ** 2 }.inject(:+).to_f/l.size - o[:avg]**2
+    o[:sd]  = Math.sqrt o[:var]
+    o[:gc]  = 100.0*gc/o[:tot] if opts[:gc]
+    if opts[:n50]
+      l.sort!
+      thr = o[:tot]/2
+      pos = 0
+      l.each do |a|
+        pos += a
+        o[:n50] = a
+        break if pos >= thr
+      end
+      o[:med] = o[:n].even? ?
+        0.5*( l[o[:n]/2-1,2].inject(:+) ) : l[(o[:n]-1)/2]
+    end
+    o
+  end
+  
   
   ##
   # Path to a script to be executed for +task+. Supported +opts+ are:

data/lib/miga/dataset.rb

@@ -187,16 +187,20 @@ class MiGA::Dataset < MiGA::MiGA
   ##
   # Look for the result with symbol key +result_type+ and register it in the
   # dataset. If +save+ is false, it doesn't register the result, but it still
-  # returns a result if the expected files are complete. The +opts+ array
+  # returns a result if the expected files are complete. The +opts+ hash
   # controls result creation (if necessary). Supported values include:
   # - +is_clean+: A Boolean indicating if the input files are clean.
+  # - +force+: A Boolean indicating if the result must be re-indexed. If true, it
+  #   implies save=true.
   # Returns MiGA::Result or nil.
   def add_result(result_type, save=true, opts={})
     dir = @@RESULT_DIRS[result_type]
     return nil if dir.nil?
     base = File.expand_path("data/#{dir}/#{name}", project.path)
-    r_pre = MiGA::Result.load("#{base}.json")
-    return r_pre if (r_pre.nil? and not save) or not r_pre.nil?
+    unless opts[:force]
+      r_pre = MiGA::Result.load("#{base}.json")
+      return r_pre if (r_pre.nil? and not save) or not r_pre.nil?
+    end
     r = File.exist?("#{base}.done") ?
         self.send("add_result_#{result_type}", base, opts) : nil
     r.save unless r.nil?

data/lib/miga/project.rb

@@ -269,12 +269,17 @@ class MiGA::Project < MiGA::MiGA
   
   ##
   # Add the result identified by Symbol +name+, and return MiGA::Result. Save
-  # the result if +save+.
-  def add_result(name, save=true)
+  # the result if +save+. The +opts+ hash controls result creation (if necessary).
+  # Supported values include:
+  # - +force+: A Boolean indicating if the result must be re-indexed. If true, it
+  # implies save=true.
+  def add_result(name, save=true, opts={})
     return nil if @@RESULT_DIRS[name].nil?
     base = "#{path}/data/#{@@RESULT_DIRS[name]}/miga-project"
-    r_pre = MiGA::Result.load("#{base}.json")
-    return r_pre if (r_pre.nil? and not save) or not r_pre.nil?
+    unless opts[:force]
+      r_pre = MiGA::Result.load("#{base}.json")
+      return r_pre if (r_pre.nil? and not save) or not r_pre.nil?
+    end
     r = result_files_exist?(base, ".done") ?
         send("add_result_#{name}", base) : nil
     r.save unless r.nil?

data/lib/miga/result.rb

@@ -133,22 +133,27 @@ class MiGA::Result < MiGA::MiGA
   end
 
   ##
-  # Iterate +blk+ for each registered file. If +blk+ calls for one argument, the
-  # relative path to the file is passed. If it calls for two arguments, the
-  # symbol describing the file is passed first and the path second. Note that
-  # multiple files may have the same symbol, since arrays of files are
-  # supported.
+  # Iterate +blk+ for each registered file. Depending on the number of
+  # arguments of +blk+ (arity), it's called as:
+  # - blk[file_rel]
+  # - blk[file_sym, file_rel]
+  # - blk[file_sym, file_rel, file_abs]
+  # Note that multiple files may have the same symbol (file_sym), since
+  # arrays of files are supported.
   def each_file(&blk)
     @data[:files] ||= {}
     self[:files].each do |k,files|
       files = [files] unless files.kind_of? Array
       files.each do |file|
-        if blk.arity==1
+        case blk.arity
+        when 1
           blk.call(file)
-        elsif blk.arity==2
+        when 2
           blk.call(k, file)
+        when 3
+          blk.call(k, file, File.expand_path(file, dir))
         else
-          raise "Wrong number of arguments: #{blk.arity} for one or two"
+          raise "Wrong number of arguments: #{blk.arity} for 1..3"
         end
       end
     end

data/lib/miga/version.rb

@@ -10,7 +10,7 @@ module MiGA
   # - Float representing the major.minor version.
   # - Integer representing gem releases of the current version.
   # - Integer representing minor changes that require new version number.
-  VERSION = [0.3, 1, 1]
+  VERSION = [0.3, 1, 2]
   
   ##
   # Nickname for the current major.minor version.
@@ -18,7 +18,7 @@ module MiGA
   
   ##
   # Date of the current gem release.
-  VERSION_DATE = Date.new(2017, 9, 14)
+  VERSION_DATE = Date.new(2017, 11, 22)
   
   ##
   # Reference of MiGA.

data/scripts/essential_genes.bash

@@ -36,6 +36,9 @@ else
     > "$DATASET.ess/log"
 fi
 
+# Reduce files
+( cd "${DATASET}.ess" && tar -zcf proteins.tar.gz *.faa && rm *.faa )
+
 # Finalize
 miga date > "$DATASET.done"
 miga add_result -P "$PROJECT" -D "$DATASET" -r "$SCRIPT"

data/utils/enveomics/Pipelines/assembly.pbs/FastA.N50.pl

@@ -0,0 +1 @@
+utils/enveomics/Pipelines/assembly.pbs/../../Scripts/FastA.N50.pl

data/utils/enveomics/Pipelines/assembly.pbs/FastA.filterN.pl

@@ -0,0 +1 @@
+utils/enveomics/Pipelines/assembly.pbs/../../Scripts/FastA.filterN.pl

data/utils/enveomics/Pipelines/assembly.pbs/FastA.length.pl

@@ -0,0 +1 @@
+utils/enveomics/Pipelines/assembly.pbs/../../Scripts/FastA.length.pl

data/utils/enveomics/Pipelines/blast.pbs/FastA.split.pl

@@ -0,0 +1 @@
+utils/enveomics/Pipelines/blast.pbs/../../Scripts/FastA.split.pl

data/utils/enveomics/Scripts/lib/enveomics.R

@@ -0,0 +1 @@
+utils/enveomics/Scripts/lib/../../enveomics.R

metadata

@@ -1,109 +1,109 @@
 --- !ruby/object:Gem::Specification
 name: miga-base
 version: !ruby/object:Gem::Version
-  version: 0.3.1.1
+  version: 0.3.1.2
 platform: ruby
 authors:
 - Luis M. Rodriguez-R
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2017-09-14 00:00:00.000000000 Z
+date: 2017-11-22 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rest-client
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '1.7'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '1.7'
 - !ruby/object:Gem::Dependency
   name: daemons
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '1.2'
-    - - '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: 1.2.4
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '1.2'
-    - - '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: 1.2.4
 - !ruby/object:Gem::Dependency
   name: json
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '>'
+    - - ">"
       - !ruby/object:Gem::Version
         version: '1.8'
-    - - <
+    - - "<"
       - !ruby/object:Gem::Version
         version: '3'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '>'
+    - - ">"
       - !ruby/object:Gem::Version
         version: '1.8'
-    - - <
+    - - "<"
       - !ruby/object:Gem::Version
         version: '3'
 - !ruby/object:Gem::Dependency
   name: sqlite3
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '1.3'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '1.3'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '11'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '11'
 - !ruby/object:Gem::Dependency
   name: test-unit
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '3'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '3'
 description: Microbial Genomes Atlas
@@ -114,6 +114,34 @@ extensions: []
 extra_rdoc_files:
 - README.md
 files:
+- Gemfile
+- LICENSE
+- README.md
+- Rakefile
+- actions/about.rb
+- actions/add.rb
+- actions/add_result.rb
+- actions/daemon.rb
+- actions/date.rb
+- actions/files.rb
+- actions/find.rb
+- actions/get.rb
+- actions/init.rb
+- actions/ln.rb
+- actions/ls.rb
+- actions/new.rb
+- actions/plugins.rb
+- actions/rm.rb
+- actions/run.rb
+- actions/stats.rb
+- actions/tax_dist.rb
+- actions/tax_index.rb
+- actions/tax_set.rb
+- actions/tax_test.rb
+- bin/miga
+- lib/miga.rb
+- lib/miga/_data/aai-intax.tsv.gz
+- lib/miga/_data/aai-novel.tsv.gz
 - lib/miga/common.rb
 - lib/miga/daemon.rb
 - lib/miga/dataset.rb
@@ -127,18 +155,6 @@ files:
 - lib/miga/tax_index.rb
 - lib/miga/taxonomy.rb
 - lib/miga/version.rb
-- lib/miga.rb
-- test/common_test.rb
-- test/daemon_test.rb
-- test/dataset_test.rb
-- test/metadata_test.rb
-- test/project_test.rb
-- test/remote_dataset_test.rb
-- test/tax_index_test.rb
-- test/taxonomy_test.rb
-- test/test_helper.rb
-- lib/miga/_data/aai-intax.tsv.gz
-- lib/miga/_data/aai-novel.tsv.gz
 - scripts/_distances_functions.bash
 - scripts/_distances_noref_nomulti.bash
 - scripts/_distances_ref_nomulti.bash
@@ -163,75 +179,24 @@ files:
 - scripts/taxonomy.bash
 - scripts/trimmed_fasta.bash
 - scripts/trimmed_reads.bash
+- test/common_test.rb
+- test/daemon_test.rb
+- test/dataset_test.rb
+- test/metadata_test.rb
+- test/project_test.rb
+- test/remote_dataset_test.rb
+- test/tax_index_test.rb
+- test/taxonomy_test.rb
+- test/test_helper.rb
 - utils/adapters.fa
 - utils/arch-ess-genes.rb
 - utils/core-pan-plot.R
-- utils/enveomics/build_enveomics_r.bash
-- utils/enveomics/enveomics.R/data/growth.curves.rda
-- utils/enveomics/enveomics.R/data/phyla.counts.rda
-- utils/enveomics/enveomics.R/DESCRIPTION
-- utils/enveomics/enveomics.R/man/enve.__prune.iter.Rd
-- utils/enveomics/enveomics.R/man/enve.__prune.reduce.Rd
-- utils/enveomics/enveomics.R/man/enve.__tribs.Rd
-- utils/enveomics/enveomics.R/man/enve.barplot.Rd
-- utils/enveomics/enveomics.R/man/enve.cliopts.Rd
-- utils/enveomics/enveomics.R/man/enve.col.alpha.Rd
-- utils/enveomics/enveomics.R/man/enve.col2alpha.Rd
-- utils/enveomics/enveomics.R/man/enve.df2dist.group.Rd
-- utils/enveomics/enveomics.R/man/enve.df2dist.list.Rd
-- utils/enveomics/enveomics.R/man/enve.df2dist.Rd
-- utils/enveomics/enveomics.R/man/enve.GrowthCurve-class.Rd
-- utils/enveomics/enveomics.R/man/enve.growthcurve.Rd
-- utils/enveomics/enveomics.R/man/enve.prune.dist.Rd
-- utils/enveomics/enveomics.R/man/enve.recplot.Rd
-- utils/enveomics/enveomics.R/man/enve.recplot2-class.Rd
-- utils/enveomics/enveomics.R/man/enve.recplot2.__counts.Rd
-- utils/enveomics/enveomics.R/man/enve.recplot2.__findPeak.Rd
-- utils/enveomics/enveomics.R/man/enve.recplot2.__findPeaks.Rd
-- utils/enveomics/enveomics.R/man/enve.recplot2.__peakHist.Rd
-- utils/enveomics/enveomics.R/man/enve.recplot2.__whichClosestPeak.Rd
-- utils/enveomics/enveomics.R/man/enve.recplot2.changeCutoff.Rd
-- utils/enveomics/enveomics.R/man/enve.recplot2.corePeak.Rd
-- utils/enveomics/enveomics.R/man/enve.recplot2.extractWindows.Rd
-- utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.Rd
-- utils/enveomics/enveomics.R/man/enve.recplot2.peak-class.Rd
-- utils/enveomics/enveomics.R/man/enve.recplot2.Rd
-- utils/enveomics/enveomics.R/man/enve.TRIBS-class.Rd
-- utils/enveomics/enveomics.R/man/enve.TRIBS.merge.Rd
-- utils/enveomics/enveomics.R/man/enve.tribs.Rd
-- utils/enveomics/enveomics.R/man/enve.tribs.test.Rd
-- utils/enveomics/enveomics.R/man/enve.TRIBStest-class.Rd
-- utils/enveomics/enveomics.R/man/enveomics.R-package.Rd
-- utils/enveomics/enveomics.R/man/growth.curves.Rd
-- utils/enveomics/enveomics.R/man/phyla.counts.Rd
-- utils/enveomics/enveomics.R/man/plot.enve.GrowthCurve.Rd
-- utils/enveomics/enveomics.R/man/plot.enve.recplot2.Rd
-- utils/enveomics/enveomics.R/man/plot.enve.TRIBS.Rd
-- utils/enveomics/enveomics.R/man/plot.enve.TRIBStest.Rd
-- utils/enveomics/enveomics.R/man/summary.enve.GrowthCurve.Rd
-- utils/enveomics/enveomics.R/man/summary.enve.TRIBS.Rd
-- utils/enveomics/enveomics.R/man/summary.enve.TRIBStest.Rd
-- utils/enveomics/enveomics.R/man/z$-methods.Rd
-- utils/enveomics/enveomics.R/NAMESPACE
-- utils/enveomics/enveomics.R/R/autoprune.R
-- utils/enveomics/enveomics.R/R/barplot.R
-- utils/enveomics/enveomics.R/R/cliopts.R
-- utils/enveomics/enveomics.R/R/df2dist.R
-- utils/enveomics/enveomics.R/R/growthcurve.R
-- utils/enveomics/enveomics.R/R/recplot.R
-- utils/enveomics/enveomics.R/R/recplot2.R
-- utils/enveomics/enveomics.R/R/tribs.R
-- utils/enveomics/enveomics.R/R/utils.R
-- utils/enveomics/enveomics.R/README.md
 - utils/enveomics/Examples/aai-matrix.bash
 - utils/enveomics/Examples/ani-matrix.bash
 - utils/enveomics/Examples/essential-phylogeny.bash
 - utils/enveomics/Examples/unus-genome-phylogeny.bash
-- utils/enveomics/globals.mk
 - utils/enveomics/LICENSE.txt
 - utils/enveomics/Makefile
-- utils/enveomics/Manifest/categories.json
-- utils/enveomics/Manifest/examples.json
 - utils/enveomics/Manifest/Tasks/aasubs.json
 - utils/enveomics/Manifest/Tasks/blasttab.json
 - utils/enveomics/Manifest/Tasks/distances.json
@@ -245,20 +210,21 @@ files:
 - utils/enveomics/Manifest/Tasks/tables.json
 - utils/enveomics/Manifest/Tasks/trees.json
 - utils/enveomics/Manifest/Tasks/variants.json
+- utils/enveomics/Manifest/categories.json
+- utils/enveomics/Manifest/examples.json
 - utils/enveomics/Manifest/tasks.json
-- utils/enveomics/manifest.json
 - utils/enveomics/Pipelines/assembly.pbs/CONFIG.mock.bash
+- utils/enveomics/Pipelines/assembly.pbs/FastA.N50.pl
 - utils/enveomics/Pipelines/assembly.pbs/FastA.filterN.pl
 - utils/enveomics/Pipelines/assembly.pbs/FastA.length.pl
-- utils/enveomics/Pipelines/assembly.pbs/FastA.N50.pl
-- utils/enveomics/Pipelines/assembly.pbs/kSelector.R
-- utils/enveomics/Pipelines/assembly.pbs/newbler.pbs
-- utils/enveomics/Pipelines/assembly.pbs/newbler_preparator.pl
 - utils/enveomics/Pipelines/assembly.pbs/README.md
 - utils/enveomics/Pipelines/assembly.pbs/RUNME-2.bash
 - utils/enveomics/Pipelines/assembly.pbs/RUNME-3.bash
 - utils/enveomics/Pipelines/assembly.pbs/RUNME-4.bash
 - utils/enveomics/Pipelines/assembly.pbs/RUNME.bash
+- utils/enveomics/Pipelines/assembly.pbs/kSelector.R
+- utils/enveomics/Pipelines/assembly.pbs/newbler.pbs
+- utils/enveomics/Pipelines/assembly.pbs/newbler_preparator.pl
 - utils/enveomics/Pipelines/assembly.pbs/soap.pbs
 - utils/enveomics/Pipelines/assembly.pbs/stats.pbs
 - utils/enveomics/Pipelines/assembly.pbs/velvet.pbs
@@ -270,25 +236,23 @@ files:
 - utils/enveomics/Pipelines/blast.pbs/FastA.split.pl
 - utils/enveomics/Pipelines/blast.pbs/README.md
 - utils/enveomics/Pipelines/blast.pbs/RUNME.bash
-- utils/enveomics/Pipelines/blast.pbs/sentinel.pbs.bash
 - utils/enveomics/Pipelines/blast.pbs/TASK.check.bash
 - utils/enveomics/Pipelines/blast.pbs/TASK.dry.bash
 - utils/enveomics/Pipelines/blast.pbs/TASK.eo.bash
 - utils/enveomics/Pipelines/blast.pbs/TASK.pause.bash
 - utils/enveomics/Pipelines/blast.pbs/TASK.run.bash
+- utils/enveomics/Pipelines/blast.pbs/sentinel.pbs.bash
 - utils/enveomics/Pipelines/idba.pbs/README.md
-- utils/enveomics/Pipelines/idba.pbs/run.pbs
 - utils/enveomics/Pipelines/idba.pbs/RUNME.bash
+- utils/enveomics/Pipelines/idba.pbs/run.pbs
 - utils/enveomics/Pipelines/trim.pbs/README.md
-- utils/enveomics/Pipelines/trim.pbs/run.pbs
 - utils/enveomics/Pipelines/trim.pbs/RUNME.bash
+- utils/enveomics/Pipelines/trim.pbs/run.pbs
 - utils/enveomics/README.md
-- utils/enveomics/Scripts/aai.rb
 - utils/enveomics/Scripts/AAsubs.log2ratio.rb
 - utils/enveomics/Scripts/Aln.cat.rb
 - utils/enveomics/Scripts/Aln.convert.pl
 - utils/enveomics/Scripts/AlphaDiversity.pl
-- utils/enveomics/Scripts/ani.rb
 - utils/enveomics/Scripts/BlastPairwise.AAsubs.pl
 - utils/enveomics/Scripts/BlastTab.addlen.rb
 - utils/enveomics/Scripts/BlastTab.advance.bash
@@ -301,8 +265,8 @@ files:
 - utils/enveomics/Scripts/BlastTab.pairedHits.rb
 - utils/enveomics/Scripts/BlastTab.recplot2.R
 - utils/enveomics/Scripts/BlastTab.seqdepth.pl
-- utils/enveomics/Scripts/BlastTab.seqdepth_nomedian.pl
 - utils/enveomics/Scripts/BlastTab.seqdepth_ZIP.pl
+- utils/enveomics/Scripts/BlastTab.seqdepth_nomedian.pl
 - utils/enveomics/Scripts/BlastTab.subsample.pl
 - utils/enveomics/Scripts/BlastTab.sumPerHit.pl
 - utils/enveomics/Scripts/BlastTab.taxid2taxrank.pl
@@ -310,6 +274,7 @@ files:
 - utils/enveomics/Scripts/Chao1.pl
 - utils/enveomics/Scripts/CharTable.classify.rb
 - utils/enveomics/Scripts/EBIseq2tax.rb
+- utils/enveomics/Scripts/FastA.N50.pl
 - utils/enveomics/Scripts/FastA.filter.pl
 - utils/enveomics/Scripts/FastA.filterLen.pl
 - utils/enveomics/Scripts/FastA.filterN.pl
@@ -317,7 +282,6 @@ files:
 - utils/enveomics/Scripts/FastA.gc.pl
 - utils/enveomics/Scripts/FastA.interpose.pl
 - utils/enveomics/Scripts/FastA.length.pl
-- utils/enveomics/Scripts/FastA.N50.pl
 - utils/enveomics/Scripts/FastA.per_file.pl
 - utils/enveomics/Scripts/FastA.qlen.pl
 - utils/enveomics/Scripts/FastA.rename.pl
@@ -334,36 +298,21 @@ files:
 - utils/enveomics/Scripts/FastQ.tag.rb
 - utils/enveomics/Scripts/FastQ.toFastA.awk
 - utils/enveomics/Scripts/GenBank.add_fields.rb
-- utils/enveomics/Scripts/gi2tax.rb
 - utils/enveomics/Scripts/HMM.essential.rb
 - utils/enveomics/Scripts/HMMsearch.extractIds.rb
-- utils/enveomics/Scripts/in_silico_GA_GI.pl
 - utils/enveomics/Scripts/JPlace.distances.rb
 - utils/enveomics/Scripts/JPlace.to_iToL.rb
-- utils/enveomics/Scripts/lib/data/essential.hmm.gz
-- utils/enveomics/Scripts/lib/enveomics_rb/enveomics.rb
-- utils/enveomics/Scripts/lib/enveomics_rb/jplace.rb
-- utils/enveomics/Scripts/lib/enveomics_rb/og.rb
-- utils/enveomics/Scripts/lib/enveomics_rb/remote_data.rb
-- utils/enveomics/Scripts/lib/enveomics_rb/seq_range.rb
-- utils/enveomics/Scripts/lib/enveomics_rb/stat.rb
-- utils/enveomics/Scripts/lib/enveomics_rb/vcf.rb
 - utils/enveomics/Scripts/M5nr.getSequences.rb
 - utils/enveomics/Scripts/MeTaxa.distribution.pl
 - utils/enveomics/Scripts/MyTaxa.fragsByTax.pl
 - utils/enveomics/Scripts/MyTaxa.seq-taxrank.rb
 - utils/enveomics/Scripts/NCBIacc2tax.rb
 - utils/enveomics/Scripts/Newick.autoprune.R
-- utils/enveomics/Scripts/ogs.annotate.rb
-- utils/enveomics/Scripts/ogs.core-pan.rb
-- utils/enveomics/Scripts/ogs.extract.rb
-- utils/enveomics/Scripts/ogs.mcl.rb
-- utils/enveomics/Scripts/ogs.rb
-- utils/enveomics/Scripts/ogs.stats.rb
 - utils/enveomics/Scripts/RAxML-EPA.to_iToL.pl
-- utils/enveomics/Scripts/rbm.rb
 - utils/enveomics/Scripts/RefSeq.download.bash
 - utils/enveomics/Scripts/SRA.download.bash
+- utils/enveomics/Scripts/TRIBS.plot-test.R
+- utils/enveomics/Scripts/TRIBS.test.R
 - utils/enveomics/Scripts/Table.barplot.R
 - utils/enveomics/Scripts/Table.df2dist.R
 - utils/enveomics/Scripts/Table.filter.pl
@@ -372,10 +321,37 @@ files:
 - utils/enveomics/Scripts/Table.round.rb
 - utils/enveomics/Scripts/Table.split.pl
 - utils/enveomics/Scripts/Taxonomy.silva2ncbi.rb
-- utils/enveomics/Scripts/TRIBS.plot-test.R
-- utils/enveomics/Scripts/TRIBS.test.R
 - utils/enveomics/Scripts/VCF.KaKs.rb
 - utils/enveomics/Scripts/VCF.SNPs.rb
+- utils/enveomics/Scripts/aai.rb
+- utils/enveomics/Scripts/ani.rb
+- utils/enveomics/Scripts/gi2tax.rb
+- utils/enveomics/Scripts/in_silico_GA_GI.pl
+- utils/enveomics/Scripts/lib/data/essential.hmm.gz
+- utils/enveomics/Scripts/lib/enveomics.R
+- utils/enveomics/Scripts/lib/enveomics_rb/enveomics.rb
+- utils/enveomics/Scripts/lib/enveomics_rb/jplace.rb
+- utils/enveomics/Scripts/lib/enveomics_rb/og.rb
+- utils/enveomics/Scripts/lib/enveomics_rb/remote_data.rb
+- utils/enveomics/Scripts/lib/enveomics_rb/seq_range.rb
+- utils/enveomics/Scripts/lib/enveomics_rb/stat.rb
+- utils/enveomics/Scripts/lib/enveomics_rb/vcf.rb
+- utils/enveomics/Scripts/ogs.annotate.rb
+- utils/enveomics/Scripts/ogs.core-pan.rb
+- utils/enveomics/Scripts/ogs.extract.rb
+- utils/enveomics/Scripts/ogs.mcl.rb
+- utils/enveomics/Scripts/ogs.rb
+- utils/enveomics/Scripts/ogs.stats.rb
+- utils/enveomics/Scripts/rbm.rb
+- utils/enveomics/Tests/Makefile
+- utils/enveomics/Tests/Mgen_M2288.faa
+- utils/enveomics/Tests/Mgen_M2288.fna
+- utils/enveomics/Tests/Mgen_M2321.fna
+- utils/enveomics/Tests/Nequ_Kin4M.faa
+- utils/enveomics/Tests/Xanthomonas_oryzae-PilA.tribs.Rdata
+- utils/enveomics/Tests/Xanthomonas_oryzae-PilA.txt
+- utils/enveomics/Tests/Xanthomonas_oryzae.aai-mat.tsv
+- utils/enveomics/Tests/Xanthomonas_oryzae.aai.tsv
 - utils/enveomics/Tests/a_mg.cds-go.blast.tsv
 - utils/enveomics/Tests/a_mg.reads-cds.blast.tsv
 - utils/enveomics/Tests/a_mg.reads-cds.counts.tsv
@@ -388,11 +364,6 @@ files:
 - utils/enveomics/Tests/hiv_mix-hiv1.blast.tsv
 - utils/enveomics/Tests/hiv_mix-hiv1.blast.tsv.lim
 - utils/enveomics/Tests/hiv_mix-hiv1.blast.tsv.rec
-- utils/enveomics/Tests/Makefile
-- utils/enveomics/Tests/Mgen_M2288.faa
-- utils/enveomics/Tests/Mgen_M2288.fna
-- utils/enveomics/Tests/Mgen_M2321.fna
-- utils/enveomics/Tests/Nequ_Kin4M.faa
 - utils/enveomics/Tests/phyla_counts.tsv
 - utils/enveomics/Tests/primate_lentivirus.ogs
 - utils/enveomics/Tests/primate_lentivirus.rbm/hiv1-hiv1.rbm
@@ -401,10 +372,65 @@ files:
 - utils/enveomics/Tests/primate_lentivirus.rbm/hiv2-hiv2.rbm
 - utils/enveomics/Tests/primate_lentivirus.rbm/hiv2-siv.rbm
 - utils/enveomics/Tests/primate_lentivirus.rbm/siv-siv.rbm
-- utils/enveomics/Tests/Xanthomonas_oryzae-PilA.tribs.Rdata
-- utils/enveomics/Tests/Xanthomonas_oryzae-PilA.txt
-- utils/enveomics/Tests/Xanthomonas_oryzae.aai-mat.tsv
-- utils/enveomics/Tests/Xanthomonas_oryzae.aai.tsv
+- utils/enveomics/build_enveomics_r.bash
+- utils/enveomics/enveomics.R/DESCRIPTION
+- utils/enveomics/enveomics.R/NAMESPACE
+- utils/enveomics/enveomics.R/R/autoprune.R
+- utils/enveomics/enveomics.R/R/barplot.R
+- utils/enveomics/enveomics.R/R/cliopts.R
+- utils/enveomics/enveomics.R/R/df2dist.R
+- utils/enveomics/enveomics.R/R/growthcurve.R
+- utils/enveomics/enveomics.R/R/recplot.R
+- utils/enveomics/enveomics.R/R/recplot2.R
+- utils/enveomics/enveomics.R/R/tribs.R
+- utils/enveomics/enveomics.R/R/utils.R
+- utils/enveomics/enveomics.R/README.md
+- utils/enveomics/enveomics.R/data/growth.curves.rda
+- utils/enveomics/enveomics.R/data/phyla.counts.rda
+- utils/enveomics/enveomics.R/man/enve.GrowthCurve-class.Rd
+- utils/enveomics/enveomics.R/man/enve.TRIBS-class.Rd
+- utils/enveomics/enveomics.R/man/enve.TRIBS.merge.Rd
+- utils/enveomics/enveomics.R/man/enve.TRIBStest-class.Rd
+- utils/enveomics/enveomics.R/man/enve.__prune.iter.Rd
+- utils/enveomics/enveomics.R/man/enve.__prune.reduce.Rd
+- utils/enveomics/enveomics.R/man/enve.__tribs.Rd
+- utils/enveomics/enveomics.R/man/enve.barplot.Rd
+- utils/enveomics/enveomics.R/man/enve.cliopts.Rd
+- utils/enveomics/enveomics.R/man/enve.col.alpha.Rd
+- utils/enveomics/enveomics.R/man/enve.col2alpha.Rd
+- utils/enveomics/enveomics.R/man/enve.df2dist.Rd
+- utils/enveomics/enveomics.R/man/enve.df2dist.group.Rd
+- utils/enveomics/enveomics.R/man/enve.df2dist.list.Rd
+- utils/enveomics/enveomics.R/man/enve.growthcurve.Rd
+- utils/enveomics/enveomics.R/man/enve.prune.dist.Rd
+- utils/enveomics/enveomics.R/man/enve.recplot.Rd
+- utils/enveomics/enveomics.R/man/enve.recplot2-class.Rd
+- utils/enveomics/enveomics.R/man/enve.recplot2.Rd
+- utils/enveomics/enveomics.R/man/enve.recplot2.__counts.Rd
+- utils/enveomics/enveomics.R/man/enve.recplot2.__findPeak.Rd
+- utils/enveomics/enveomics.R/man/enve.recplot2.__findPeaks.Rd
+- utils/enveomics/enveomics.R/man/enve.recplot2.__peakHist.Rd
+- utils/enveomics/enveomics.R/man/enve.recplot2.__whichClosestPeak.Rd
+- utils/enveomics/enveomics.R/man/enve.recplot2.changeCutoff.Rd
+- utils/enveomics/enveomics.R/man/enve.recplot2.corePeak.Rd
+- utils/enveomics/enveomics.R/man/enve.recplot2.extractWindows.Rd
+- utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.Rd
+- utils/enveomics/enveomics.R/man/enve.recplot2.peak-class.Rd
+- utils/enveomics/enveomics.R/man/enve.tribs.Rd
+- utils/enveomics/enveomics.R/man/enve.tribs.test.Rd
+- utils/enveomics/enveomics.R/man/enveomics.R-package.Rd
+- utils/enveomics/enveomics.R/man/growth.curves.Rd
+- utils/enveomics/enveomics.R/man/phyla.counts.Rd
+- utils/enveomics/enveomics.R/man/plot.enve.GrowthCurve.Rd
+- utils/enveomics/enveomics.R/man/plot.enve.TRIBS.Rd
+- utils/enveomics/enveomics.R/man/plot.enve.TRIBStest.Rd
+- utils/enveomics/enveomics.R/man/plot.enve.recplot2.Rd
+- utils/enveomics/enveomics.R/man/summary.enve.GrowthCurve.Rd
+- utils/enveomics/enveomics.R/man/summary.enve.TRIBS.Rd
+- utils/enveomics/enveomics.R/man/summary.enve.TRIBStest.Rd
+- utils/enveomics/enveomics.R/man/z$-methods.Rd
+- utils/enveomics/globals.mk
+- utils/enveomics/manifest.json
 - utils/index_metadata.rb
 - utils/mytaxa_scan.R
 - utils/mytaxa_scan.rb
@@ -414,31 +440,6 @@ files:
 - utils/subclades-compile.rb
 - utils/subclades-nj.R
 - utils/subclades.R
-- bin/miga
-- actions/about.rb
-- actions/add.rb
-- actions/add_result.rb
-- actions/daemon.rb
-- actions/date.rb
-- actions/files.rb
-- actions/find.rb
-- actions/get.rb
-- actions/init.rb
-- actions/ln.rb
-- actions/ls.rb
-- actions/new.rb
-- actions/plugins.rb
-- actions/rm.rb
-- actions/run.rb
-- actions/stats.rb
-- actions/tax_dist.rb
-- actions/tax_index.rb
-- actions/tax_set.rb
-- actions/tax_test.rb
-- Gemfile
-- Rakefile
-- README.md
-- LICENSE
 homepage: http://enve-omics.ce.gatech.edu/miga
 licenses:
 - Artistic-2.0
@@ -447,25 +448,25 @@ post_install_message:
 rdoc_options:
 - lib
 - README.md
-- --main
+- "--main"
 - README.md
-- --title
+- "--title"
 - MiGA
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
-  - - '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '1.9'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
-  - - '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.0.14
+rubygems_version: 2.6.13
 signing_key: 
 specification_version: 4
 summary: MiGA

data/utils/enveomics/Pipelines/assembly.pbs/FastA.N50.pl

@@ -1,56 +0,0 @@
-#!/usr/bin/env perl
-#
-# @author: Luis M. Rodriguez-R <lmrodriguezr at gmail dot com>
-# @update: Oct 07 2015
-# @license: artistic license 2.0
-#
-use strict;
-use warnings;
-use List::Util qw/sum min max/;
-
-my ($seqs, $minlen, $n__) = @ARGV;
-$seqs or die "
-Description:
-   Calculates the N50 value of a set of sequences.  Alternatively, it
-   can calculate other N** values.  It also calculates the total number
-   of sequences and the total added length.
-   
-Usage:
-   $0 seqs.fa[ minlen[ **]]
-
-   seqs.fa	A FastA file containing the sequences.
-   minlen	(optional) The minimum length to take into consideration.
-   		By default: 0.
-   **		Value N** to calculate.  By default: 50 (N50).
-";
-$minlen ||= 0;
-$n__    ||= 50;
-
-my @len = ();
-open SEQ, "<", $seqs or die "Cannot open file: $seqs: $!\n";
-while(<SEQ>){
-   if(/^>/){
-      push @len, 0;
-   }else{
-      next if /^;/;
-      chomp;
-      s/\W//g;
-      $len[-1]+=length $_;
-   }
-}
-close SEQ;
-@len = sort { $a <=> $b } map { $_>=$minlen?$_:() } @len;
-my $tot = (sum(@len) || 0);
-
-my $thr = $n__*$tot/100;
-my $pos = 0;
-for(@len){
-   $pos+= $_;
-   if($pos>=$thr){
-      print "N$n__: $_\n";
-      last;
-   }
-}
-print "Sequences: ".scalar(@len)."\n";
-print "Total length: $tot\n";
-

data/utils/enveomics/Pipelines/assembly.pbs/FastA.filterN.pl

@@ -1,60 +0,0 @@
-#!/usr/bin/env perl
-# 
-# @author  Luis M. Rodriguez-R
-# @update  Oct-07-2015
-# @license artistic license 2.0
-# 
-
-use warnings;
-use strict;
-
-my($file, $content, $stretch) = @ARGV;
-$file or die <<HELP
-
-Description:
-   Filter sequences by N-content and presence of long homopolymers.
-Usage:
-   $0 sequences.fa [content [stretch]] > filtered.fa
-Where:
-   sequences.fa	Input file in FastA format
-   content	A number between 0 and 1 indicating the maximum proportion of Ns
-   		(1 to turn off, 0.5 by default)
-   stretch	A number indicating the maximum number of consecutive identical
-   		nucleotides allowed (0 to turn off, 100 by default)
-   filtered.fa	Filtered set of sequences.
-
-HELP
-;
-($content ||= 0.5)+=0;
-($stretch ||= 100)+=0;
-
-my $good = 0;
-my $N = 0;
-
-FASTA: {
-   local $/ = "\n>";
-   open FILE, "<", $file or die "I can not open the file: $file: $!\n";
-   SEQ: while(<FILE>){
-      $N++;
-      s/^;.*//gm;
-      s/>//g;
-      my($n,$s) = split /\n/, $_, 2;
-      (my $clean = $s) =~ s/[^ACTGN]//g;
-      if($content < 1){
-         (my $Ns = $clean) =~ s/[^N]//g;
-	 next SEQ if length($Ns)>length($clean)*$content;
-      }
-      if($stretch > 0){
-         for my $nuc (qw(A C T G N)){
-	    next SEQ if $clean =~ m/[$nuc]{$stretch}/;
-	 }
-      }
-      print ">$n\n$s\n";
-      $good++;
-   }
-   close FILE;
-   print STDERR "Total sequences: $N\nAfter filtering: $good\n";
-}
-
-
-

data/utils/enveomics/Pipelines/assembly.pbs/FastA.length.pl

@@ -1,38 +0,0 @@
-#!/usr/bin/env perl
-#
-# @author  Luis M Rodriguez-R
-# @update  Oct-07-2015
-# @license artistic license 2.0
-#
-
-use warnings;
-use strict;
-
-$#ARGV>=0 or die "
-Usage:
-   $0 seqs.fa... > length.txt
-
-   seqs.fa	One or more FastA files.
-   length.txt	A table with the lengths of the sequences.
-
-";
-
-for my $fa (@ARGV){
-   open FA, "<", $fa or die "Cannot open file: $fa: $!\n";
-   my $def = '';
-   my $len = 0;
-   while(<FA>){
-      next if /^;/;
-      if(m/^>(\S+)\s?/){
-         print "$def\t$len\n" if $def;
-	 $def = $1;
-	 $len = 0;
-      }else{
-         s/[^A-Za-z]//g;
-	 $len+= length $_;
-      }
-   }
-   print "$def\t$len\n" if $def;
-   close FA;
-}
-

data/utils/enveomics/Pipelines/blast.pbs/FastA.split.pl

@@ -1,55 +0,0 @@
-#!/usr/bin/env perl
-#
-# @author Luis M. Rodriguez-R <lmrodriguezr at gmail dot com>
-# @update Oct-13-2015
-# @license artistic license 2.0
-#
-
-use warnings;
-use strict;
-use Symbol;
-
-my ($file, $base, $outN) = @ARGV;
-
-$outN ||= 12;
-($file and $base) or die "
-Usage
-   $0 in_file.fa out_base[ no_files]
-   
-   in_file.fa	Input file in FastA format.
-   out_base	Prefix for the name of the output files.  It will
-   		be appended with .<i>.fa, where <i> is a consecutive
-		number starting in 1.
-   no_files	Number of files to generate.  By default: 12.
-
-";
-
-
-my @outSym = ();
-for my $i (1 .. $outN){
-   $outSym[$i-1] = gensym;
-   open $outSym[$i-1], ">", "$base.$i.fa" or
-      die "I can not create the file: $base.$i.fa: $!\n";
-}
-
-
-my($i, $seq) = (-1, '');
-open FILE, "<", $file or die "I can not read the file: $file: $!\n";
-while(my $ln=<FILE>){
-   next if $ln=~/^;/;
-   if($ln =~ m/^>/){
-      print { $outSym[$i % $outN] } $seq if $seq;
-      $i++;
-      $seq = '';
-   }
-   $seq.=$ln;
-}
-print { $outSym[$i % $outN] } $seq if $seq;
-close FILE;
-
-for(my $j=0; $j<$outN; $j++){
-   close $outSym[$j];
-}
-
-print STDERR "Sequences: ".($i+1)."\nFiles: $outN\n";
-