miga-base 0.5.0.0 → 0.5.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: e370d282f1b28480765e1b91fcb7d8921d12baa31d22db1318975a1c2a79e19a
-  data.tar.gz: e7fb3941fd3381e0e9696a2c577aeb157657335e56434e7c6d6650be7ba45e98
+  metadata.gz: f6888c1ce3756b8cc708736c0da052e5a7396277e0c903ebcfc083f17b6915e7
+  data.tar.gz: d998f6e087316a81de4aa8897452344c1987ce0cb9807f4a1e11a29f52dfbcf2
 SHA512:
-  metadata.gz: 4642a212e1b4021e211fd144b515ff49e9ddb7a9b2292430553307a7ae165e4d8d5e6fd8426757f15ea6e70f4c3efbb055e0439497172cc1f91186d522c82635
-  data.tar.gz: 8d5d3ded3c03e56505572102110a4bca4b84d06b2e73bcf208856610a4cd6e60092ce6d54d47dcef2c8acf85f1cce5f8461097e8699344df6738ed8493215112
+  metadata.gz: c6f7f8af791664b2bb704744535e0e39c4d5fc06521beb8feb57f658d6187a667100fde4312a3a8e5f47f5dd9d4b3c06326584d95e80262dc0e02a91795e192c
+  data.tar.gz: 4f633972d8ccc1cc06cc14ca6c48b50759d63af72ba75514a0e877a58af4e1d407fda2c2608c2077dd541e30e86add8359bc2e0838d93a19f7cc1bd5c5f5fff2

data/lib/miga/cli/action/doctor.rb

@@ -104,6 +104,7 @@ class MiGA::Cli::Action::Doctor < MiGA::Cli::Action
         unless ok
           cli.say "  > Registering again #{d.name}:#{r_k}"
           d.add_result(r_k, true, force: true)
+          sr = d.result(:stats) and sr.remove!
         end
       end
     end
@@ -123,7 +124,10 @@ class MiGA::Cli::Action::Doctor < MiGA::Cli::Action
           changed = true
         end
       end
-      d.add_result(:cds, true, force: true) if changed
+      if changed
+        d.add_result(:cds, true, force: true)
+        sr = d.result(:stats) and sr.remove!
+      end
     end
   end
 
@@ -136,6 +140,7 @@ class MiGA::Cli::Action::Doctor < MiGA::Cli::Action
       if dir.nil?
         cli.say "  > Removing #{d.name}:essential_genes"
         res.remove!
+        sr = d.result(:stats) and sr.remove!
         next
       end
       next if Dir["#{dir}/*.faa"].empty?

data/lib/miga/cli/action/init.rb

@@ -220,7 +220,7 @@ BASH
 
   def check_r_packages(paths)
     cli.puts 'Looking for R packages:'
-    %w(enveomics.R ape cluster vegan).each do |pkg|
+    %w(ape cluster vegan).each do |pkg|
       cli.print "Testing #{pkg}... "
       if test_r_package(cli, paths, pkg)
         cli.puts 'yes.'

data/lib/miga/cli/action/quality_wf.rb

@@ -25,6 +25,7 @@ class MiGA::Cli::Action::QualityWf < MiGA::Cli::Action
       %w[project_stats haai_distances aai_distances ani_distances clade_finding]
         .map { |i| ["run_#{i}", false] }
     ]
+    p_metadata[:ess_coll] = cli[:ess_coll]
     d_metadata = { run_distances: false }
     d_metadata[:run_mytaxa_scan] = false unless cli[:mytaxa]
     p = create_project(:assembly, p_metadata, d_metadata)

data/lib/miga/cli/action/stats.rb

@@ -122,17 +122,18 @@ class MiGA::Cli::Action::Stats < MiGA::Cli::Action
         end
       end
     else
-      # Fix estimate for Archaea
-      if !d.metadata[:tax].nil? &&
-            d.metadata[:tax].in?(Taxonomy.new('d:Archaea')) &&
-            r.file_path(:bac_report).nil?
-        scr = "#{MiGA.root_path}/utils/arch-ess-genes.rb"
+      # Fix estimate by domain
+      if !(tax = d.metadata[:tax]).nil? &&
+            %w[Archaea Bacteria].include?(tax[:d]) &&
+            r.file_path(:raw_report).nil?
+        scr = "#{MiGA.root_path}/utils/domain-ess-genes.rb"
         rep = r.file_path(:report)
         rc_p = File.expand_path('.miga_rc', ENV['HOME'])
         rc = File.exist?(rc_p) ? ". '#{rc_p}' && " : ''
-        $stderr.print `#{rc} ruby '#{scr}' '#{rep}' '#{rep}.archaea'`
-        r.add_file(:bac_report, "#{d.name}.ess/log")
-        r.add_file(:report, "#{d.name}.ess/log.archaea")
+        $stderr.print `#{rc} ruby '#{scr}' \
+          '#{rep}' '#{rep}.domain' '#{tax[:d][0]}'`
+        r.add_file(:raw_report, "#{d.name}.ess/log")
+        r.add_file(:report, "#{d.name}.ess/log.domain")
       end
       # Extract/compute quality values
       stats = {completeness: [0.0, '%'], contamination: [0.0, '%']}

data/lib/miga/cli/action/wf.rb

@@ -24,6 +24,11 @@ module MiGA::Cli::Action::Wf
     opt.separator "    FILES...: #{files_desc}"
     opt.separator ''
     opt.separator 'Workflow Control Options'
+    opt.on(
+      '-C', '--collection STRING',
+      'Collection of essential genes to use as reference',
+      'One of: dupont_2012 (default), lee_2019'
+    ) { |v| cli[:ess_coll] = v }
     if params[:ncbi]
       opt.on(
         '-T', '--ncbi-taxon STRING',

data/lib/miga/cli/objects_helper.rb

@@ -66,6 +66,7 @@ module MiGA::Cli::ObjectsHelper
   end
 
   def add_metadata(obj, cli = self)
+    raise "Unsupported object: #{obj.class}" unless obj.respond_to? :metadata
     cli[:metadata].split(',').each do |pair|
       (k,v) = pair.split('=')
       case v

data/lib/miga/common/format.rb

@@ -25,10 +25,13 @@ module MiGA::Common::Format
   # Cleans a FastA file in place.
   def clean_fasta_file(file)
     tmp_fh = nil
+    tmp_path = nil
     begin
       if file =~ /\.gz/
         tmp_path = Tempfile.new('MiGA.gz').tap(&:close).path
-        tmp_fh = Zlib::GzipWriter.open(tmp_path)
+        File.unlink tmp_path
+        tmp_path += '.gz'
+        tmp_fh = Zlib::GzipWriter.open(tmp_path, 9)
         fh = Zlib::GzipReader.open(file)
       else
         tmp_fh = Tempfile.new('MiGA')
@@ -50,7 +53,7 @@ module MiGA::Common::Format
       tmp_fh.print buffer.wrap_width(80)
       tmp_fh.close
       fh.close
-      FileUtils.cp(tmp_path, file)
+      FileUtils.mv(tmp_path, file)
     ensure
       begin
         tmp_fh.close unless tmp_fh.nil?

data/lib/miga/daemon.rb

@@ -285,10 +285,10 @@ class MiGA::Daemon < MiGA::MiGA
       if [nil, '', 0].include? job[:pid]
         job[:pid] = nil
         @jobs_to_run << job
-        say "Unsuccessful #{job[:task_name]}, rescheduling."
+        say "Unsuccessful #{job[:task_name]}, rescheduling"
       else
         @jobs_running << job
-        say "Spawned pid:#{job[:pid]} for #{job[:task_name]}."
+        say "Spawned pid:#{job[:pid]} for #{job[:task_name]}"
       end
     end
 end

data/lib/miga/project/dataset.rb

@@ -4,7 +4,7 @@
 ##
 # Helper module including specific functions handle datasets.
 module MiGA::Project::Dataset
-  
+
   ##
   # Returns Array of MiGA::Dataset.
   def datasets
@@ -23,7 +23,7 @@ module MiGA::Project::Dataset
   def dataset_names_hash
     @dataset_names_hash ||= Hash[dataset_names.map{ |i| [i,true] }]
   end
-  
+
   ##
   # Returns MiGA::Dataset.
   def dataset(name)
@@ -47,18 +47,19 @@ module MiGA::Project::Dataset
       end
     end
   end
-  
+
   ##
   # Add dataset identified by +name+ and return MiGA::Dataset.
   def add_dataset(name)
     unless metadata[:datasets].include? name
       MiGA::Dataset.new(self, name)
       @metadata[:datasets] << name
+      @dataset_names_hash = nil # Ensure loading even if +do_not_save+ is true
       save
     end
     dataset(name)
   end
-  
+
   ##
   # Unlink dataset identified by +name+ and return MiGA::Dataset.
   def unlink_dataset(name)
@@ -68,7 +69,7 @@ module MiGA::Project::Dataset
     save
     d
   end
-  
+
   ##
   # Import the dataset +ds+, a MiGA::Dataset, using +method+ which is any method
   # supported by File#generic_transfer.
@@ -116,7 +117,7 @@ module MiGA::Project::Dataset
     end
     datasets.uniq - metadata[:datasets]
   end
-  
+
   ##
   # Are all the datasets in the project preprocessed? Save intermediate results
   # if +save+ (until the first incomplete dataset is reached).
@@ -149,6 +150,6 @@ module MiGA::Project::Dataset
   def each_dataset_profile_advance(&blk)
     each_dataset { |ds| blk.call(ds.profile_advance) }
   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 = [0.5, 0, 0]
+  VERSION = [0.5, 1, 0]
 
   ##
   # Nickname for the current major.minor version.
@@ -18,7 +18,7 @@ module MiGA
 
   ##
   # Date of the current gem release.
-  VERSION_DATE = Date.new(2019, 11, 25)
+  VERSION_DATE = Date.new(2020, 1, 6)
 
   ##
   # Reference of MiGA.

data/scripts/essential_genes.bash

@@ -22,18 +22,19 @@ fi
 # Find and extract essential genes
 [[ -d "${DATASET}.ess" ]] && rm -R "${DATASET}.ess"
 mkdir "${DATASET}.ess"
-TYPE=$(miga list_datasets -P "$PROJECT" -D "$DATASET" \
+TYPE=$(miga ls -P "$PROJECT" -D "$DATASET" \
   --metadata "type" | awk '{print $2}')
+COLL=$(miga about -P "$PROJECT" -m ess_coll)
+[[ "$COLL" == "?" ]] && COLL=dupont_2012
+CMD="HMM.essential.rb \
+  -i '$FAA' -o '${DATASET}.ess.faa' -m '${DATASET}.ess/' \
+  -t '$CORES' -r '$DATASET' --collection '$COLL'"
 if [[ "$TYPE" == "metagenome" || "$TYPE" == "virome" ]] ; then
-  HMM.essential.rb -i "$FAA" -o "${DATASET}.ess.faa" \
-    -m "${DATASET}.ess/" -t "$CORES" -r "$DATASET" --metagenome \
-    > "${DATASET}.ess/log"
+  CMD="$CMD --metagenome"
 else
-  HMM.essential.rb -i "$FAA" -o "${DATASET}.ess.faa" \
-    -m "${DATASET}.ess/" -t "$CORES" -r "$DATASET" \
-    --alignments "${DATASET}.ess/proteins.aln" \
-    > "${DATASET}.ess/log"
+  CMD="$CMD --alignments '${DATASET}.ess/proteins.aln'"
 fi
+$CMD > "${DATASET}.ess/log"
 
 # Reduce files
 if exists "$DATASET".ess/*.faa ; then

data/scripts/mytaxa.bash

@@ -38,7 +38,9 @@ else
     fi
      
     # Execute search
-    diamond blastp -q "../../../06.cds/$DATASET.faa" -d "$MT/AllGenomes.faa" \
+    FAA="../../../06.cds/$DATASET.faa"
+    [[ -s "$FAA" ]] || FAA="${FAA}.gz"
+    diamond blastp -q "$FAA" -d "$MT/AllGenomes.faa" \
       -a "$DATASET.daa" -k 5 -p "$CORES" --min-score 60
     diamond view -a "$DATASET.daa" -o "$DATASET.blast"
 

data/scripts/mytaxa_scan.bash

@@ -39,12 +39,13 @@ else
       exit 1
     fi
      
+    FAA="../../../06.cds/$DATASET.faa"
+    [[ -s "$FAA" ]] || FAA="${FAA}.gz"
     if [[ ! -s "$DATASET.mytaxa" ]] ; then
       # Execute search
       if [[ ! -s "$DATASET.blast" ]] ; then
-        diamond blastp -q "../../../06.cds/$DATASET.faa" \
-          -d "$MT/AllGenomes.faa" -k 5 -p "$CORES" --min-score 60 \
-          -a "$DATASET.daa" -t "$TMPDIR"
+        diamond blastp -q "$FAA" -a "$DATASET.daa" -t "$TMPDIR" \
+          -d "$MT/AllGenomes.faa" -k 5 -p "$CORES" --min-score 60
         diamond view -a "$DATASET.daa" -o "$DATASET.blast" -t "$TMPDIR"
       fi
 
@@ -53,8 +54,7 @@ else
         | sort -k 13 > "$DATASET.mytaxain"
       "$MT/MyTaxa" "$DATASET.mytaxain" "$DATASET.mytaxa" "0.5"
     fi
-    ruby "$MIGA/utils/mytaxa_scan.rb" "../../../06.cds/$DATASET.faa" \
-          "$DATASET.mytaxa" "$DATASET.wintax"
+    ruby "$MIGA/utils/mytaxa_scan.rb" "$FAA" "$DATASET.mytaxa" "$DATASET.wintax"
     echo "
     source('$MIGA/utils/mytaxa_scan.R');
     pdf('$DATASET.pdf', 12, 7);
@@ -70,11 +70,18 @@ else
         let i=$i+1
         awk "NR==$win" "$DATASET.wintax.genes" | tr "\\t" "\\n" \
           > "$DATASET.reg/$i.ids"
-        FastA.filter.pl -q "$DATASET.reg/$i.ids" \
-          "../../../06.cds/$DATASET.faa" > "$DATASET.reg/$i.faa"
+        if [[ "$FAA" == *.gz ]] ; then
+          gzip -c -d "$FAA" \
+            | FastA.filter.pl -q "$DATASET.reg/$i.ids" /dev/stdin \
+            > "$DATASET.reg/$i.faa"
+        else
+          FastA.filter.pl -q "$DATASET.reg/$i.ids" "$FAA" \
+            > "$DATASET.reg/$i.faa"
+        fi
       done
       # Archive regions
-      tar zcf "$DATASET.reg.tar.gz" "$DATASET.reg"
+      tar -cf "$DATASET.reg.tar" "$DATASET.reg"
+      gzip -9 "$DATASET.reg.tar"
       rm -r "$DATASET.reg"
     fi
 

data/utils/domain-ess-genes.rb

@@ -0,0 +1,63 @@
+#!/usr/bin/env ruby
+
+esslog = ARGV.shift
+outlog = ARGV.shift
+domain = ARGV.shift
+
+def quality(hsh)
+  q = {}
+  q[:found] = hsh.values.map{ |i| i==0 ? 0 : 1 }.inject(:+)
+  q[:multi] = hsh.values.map{ |i| i==0 ? 0 : i-1 }.inject(:+)
+  q[:cmp] = 100.0*q[:found].to_f/hsh.size
+  q[:cnt] = 100.0*q[:multi].to_f/hsh.size
+  q
+end
+
+# Find collection and detected anomalies
+cnt_ref = {}
+at = :header
+collection = 'dupont_2012'
+File.open(esslog, 'r') do |fh|
+  fh.each_line do |ln|
+    v = ln.chomp.gsub(/^! +/, '')
+    if v == 'Multiple copies: '
+      at = :multi
+    elsif v == 'Missing genes: '
+      at = :missing
+    elsif v =~ /Collection: (\S+)/
+      collection = $1
+    elsif at == :multi
+      v =~ /^(\d+) (\S+): .*/ or raise "Unexpected multi-copies format: #{v}"
+      cnt_ref[$2] = $1.to_i
+    elsif at == :missing
+      v =~ /^(\S+): .*/ or raise "Unexpected missing format: #{v}"
+      cnt_ref[$1] = 0
+    end
+  end
+end
+
+# Find expected genes for domain
+n_dom = Hash[
+  `HMM.essential.rb -L -q '-#{domain}' -c '#{collection}'`
+    .chomp.split("\n").map { |i| i.split("\t") }
+]
+l_dom = n_dom.keys
+cnt_dom = {}
+l_dom.each { |i| cnt_dom[i] = cnt_ref[i] || 1 }
+
+#  Correct report
+q = quality(cnt_dom)
+File.open(outlog, 'w') do |ofh|
+  ofh.puts "! Collection: #{collection} #{domain}"
+  ofh.puts "! Essential genes found: #{q[:found]}/#{cnt_dom.size}."
+  ofh.puts "! Completeness: #{q[:cmp].round(1)}%."
+  ofh.puts "! Contamination: #{q[:cnt].round(1)}%."
+  if q[:multi] > 0
+    ofh.puts "! Multiple copies: "
+    cnt_dom.each{ |k,v| ofh.puts "!   #{v} #{k}: #{n_dom[k]}." if v>1 }
+  end
+  if q[:found] < cnt_dom.size
+    ofh.puts "! Missing genes: "
+    cnt_dom.each{ |k,v| ofh.puts "!   #{k}: #{n_dom[k]}." if v==0 }
+  end
+end

data/utils/enveomics/Manifest/Tasks/other.json

@@ -371,8 +371,18 @@
           "source_url": "http://hmmer.janelia.org/software"
         }
       ],
-      "cite": [["Eddy, 2011, PLoS CB",
-        "http://dx.doi.org/10.1371/journal.pcbi.1002195"]],
+      "cite": [
+        ["Eddy, 2011, PLoS CB",
+          "http://dx.doi.org/10.1371/journal.pcbi.1002195"],
+        ["Dupont et al, 2012, ISME J",
+          "https://doi.org/10.1038/ismej.2011.189"],
+        ["Rodriguez-R et al, 2014, ISME J",
+          "https://doi.org/10.1038/ismej.2015.5"],
+        ["Lee, 2019, Bioinf",
+          "https://doi.org/10.1093/bioinformatics/btz188"],
+        ["Eren et al, 2015, PeerJ",
+          "https://doi.org/10.7717/peerj.1319"]
+      ],
       "options": [
         {
           "name": "Input file",
@@ -381,6 +391,15 @@
           "mandatory": true,
           "description": "FastA file containing all the proteins in the genome."
         },
+        {
+          "opt": "--collection",
+          "arg": "string",
+          "default": "dupont_2012",
+          "description": ["Reference collection of essential proteins to use.",
+            "One of: dupont_2012 (default, Dupont et al 2012 modified by",
+            "Rodriguez-R et al 2015), or lee_2019 (Lee 2019 modified by Eren",
+            "et al 2015)."]
+        },
         {
           "name": "Output file",
           "opt": "--out",

data/utils/enveomics/Manifest/examples.json

@@ -64,15 +64,15 @@
       "task": "HMM.essential.rb",
       "description": ["Typical single-copy bacterial genes present in",
         "Mycoplasma genitalium."],
-      "values": ["Mgen_M2288.faa",null,null,null,null,null,true,null,null,null,
-        null,null,null,null,null,null,null,null]
+      "values": ["Mgen_M2288.faa",null,null,null,null,null,null,true,null,null,
+        null,null,null,null,null,null,null,null,null]
     },
     {
       "task": "HMM.essential.rb",
       "description": ["Typical single-copy archaeal genes present in",
         "Nanoarchaeum equitans."],
-      "values": ["Mgen_M2288.faa",null,null,null,null,null,null,true,null,null,
-        null,null,null,null,null,null,null,null]
+      "values": ["Mgen_M2288.faa",null,null,null,null,null,null,null,true,null,
+        null,null,null,null,null,null,null,null,null]
     },
     {
       "task": "Newick.autoprune.R",

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

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

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

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

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

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

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

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

data/utils/enveomics/Scripts/HMM.essential.rb

@@ -10,7 +10,8 @@ use 'zlib'
 
 o = {
   bin: '', thr: 2, q: false, stats: true, genes: true, bacteria: false,
-  archaea: false, genomeeq: false, metagenome: false, list: false
+  archaea: false, genomeeq: false, metagenome: false, list: false,
+  collection: 'dupont_2012'
 }
 OptionParser.new do |opts|
   opts.banner = "
@@ -33,7 +34,15 @@ Usage: #{$0} [options]"
     'Path to the FastA file (.gz allowed) with all the proteins in a genome'
   ) { |v| o[:in] = v }
   opts.separator ''
-  opts.separator 'Report Options'
+  opts.separator 'Options'
+  opts.on(
+    '-c', '--collection STR',
+    'Reference collection of essential proteins to use. One of:',
+    '> dupont_2012 (default): https://doi.org/10.1038/ismej.2011.189',
+    '  modified by https://doi.org/10.1038/ismej.2015.5',
+    '> lee_2019: https://doi.org/10.1093/bioinformatics/btz188',
+    '  modified by https://doi.org/10.7717/peerj.1319'
+  ) { |v| o[:collection] = v }
   opts.on(
     '-o', '--out FILE',
     'Path to the output FastA file with the translated essential genes',
@@ -117,20 +126,44 @@ abort '-i is mandatory' if o[:in].nil? and not o[:list]
 o[:bin] = o[:bin] + '/' if o[:bin].size > 0
 o[:rename] = nil if o[:metagenome]
 
-not_in_archaea = %w{GrpE Methyltransf_5 TIGR00001 TIGR00002 TIGR00009 TIGR00019
-TIGR00029 TIGR00043 TIGR00059 TIGR00060 TIGR00061 TIGR00062 TIGR00082 TIGR00086
-TIGR00092 TIGR00115 TIGR00116 TIGR00152 TIGR00158 TIGR00165 TIGR00166 TIGR00168
-TIGR00362 TIGR00388 TIGR00396 TIGR00409 TIGR00418 TIGR00420 TIGR00422 TIGR00436
-TIGR00459 TIGR00460 TIGR00472 TIGR00487 TIGR00496 TIGR00575 TIGR00631 TIGR00663
-TIGR00775 TIGR00810 TIGR00855 TIGR00922 TIGR00952 TIGR00959 TIGR00963 TIGR00964
-TIGR00967 TIGR00981 TIGR01009 TIGR01011 TIGR01017 TIGR01021 TIGR01024 TIGR01029
-TIGR01030 TIGR01031 TIGR01032 TIGR01044 TIGR01049 TIGR01050 TIGR01059 TIGR01063
-TIGR01066 TIGR01067 TIGR01071 TIGR01079 TIGR01164 TIGR01169 TIGR01171 TIGR01391
-TIGR01393 TIGR01632 TIGR01953 TIGR02012 TIGR02013 TIGR02027 TIGR02191 TIGR02350
-TIGR02386 TIGR02387 TIGR02397 TIGR02432 TIGR02729 TIGR03263 TIGR03594}
-not_in_bacteria = %w{TIGR00389 TIGR00408 TIGR00471 TIGR00775 TIGR02387}
-not_as_genomeeq = %w{TIGR02386 TIGR02387 TIGR00471 TIGR00472 TIGR00408 TIGR00409
-TIGR00389 TIGR00436 tRNA-synth_1d}
+case o[:collection]
+when 'dupont_2012'
+  not_in_archaea = %w{GrpE Methyltransf_5 TIGR00001 TIGR00002 TIGR00009
+  TIGR00019 TIGR00029 TIGR00043 TIGR00059 TIGR00060 TIGR00061 TIGR00062
+  TIGR00082 TIGR00086 TIGR00092 TIGR00115 TIGR00116 TIGR00152 TIGR00158
+  TIGR00165 TIGR00166 TIGR00168 TIGR00362 TIGR00388 TIGR00396 TIGR00409
+  TIGR00418 TIGR00420 TIGR00422 TIGR00436 TIGR00459 TIGR00460 TIGR00472
+  TIGR00487 TIGR00496 TIGR00575 TIGR00631 TIGR00663 TIGR00775 TIGR00810
+  TIGR00855 TIGR00922 TIGR00952 TIGR00959 TIGR00963 TIGR00964 TIGR00967
+  TIGR00981 TIGR01009 TIGR01011 TIGR01017 TIGR01021 TIGR01024 TIGR01029
+  TIGR01030 TIGR01031 TIGR01032 TIGR01044 TIGR01049 TIGR01050 TIGR01059
+  TIGR01063 TIGR01066 TIGR01067 TIGR01071 TIGR01079 TIGR01164 TIGR01169
+  TIGR01171 TIGR01391 TIGR01393 TIGR01632 TIGR01953 TIGR02012 TIGR02013
+  TIGR02027 TIGR02191 TIGR02350 TIGR02386 TIGR02387 TIGR02397 TIGR02432
+  TIGR02729 TIGR03263 TIGR03594}
+  not_in_bacteria = %w{TIGR00389 TIGR00408 TIGR00471 TIGR00775 TIGR02387}
+  not_as_genomeeq = %w{TIGR02386 TIGR02387 TIGR00471 TIGR00472 TIGR00408
+  TIGR00409 TIGR00389 TIGR00436 tRNA-synth_1d}
+when 'lee_2019'
+  not_in_archaea = %w{ADK AICARFT_IMPCHas ATP-synt ATP-synt_A Chorismate_synt
+  EF_TS eIF-1a Exonuc_VII_L GrpE IPPT OSCP Pept_tRNA_hydro PGK RBFA RecO_C
+  Ribonuclease_P Ribosomal_L17 Ribosomal_L18p Ribosomal_L19 Ribosomal_L20
+  Ribosomal_L21p ribosomal_L24 Ribosomal_S3_C Ribosomal_L5 Ribosomal_L2
+  Ribosomal_L27 Ribosomal_L27A Ribosomal_L28 Ribosomal_L32p Ribosomal_L35p
+  Ribosomal_L9_C Ribosomal_S10 Ribosomal_S16 Ribosomal_S20p Ribosomal_S6
+  RNA_pol_L RRF RsfS RuvX SecE SecG SmpB tRNA_m1G_MT TsaE UPF0054 YajC}
+  not_in_bacteria = %w{AdoHcyase Archease ATP-synt_D ATP-synt_F CarS-like
+  CTP-dep_RFKase Diphthamide_syn DNA_primase_lrg dsDNA_bind DUF357 DUF359
+  DUF655 eIF-6 FbpA HMG-CoA_red NDK PPS_PS Prefoldin PTH2 PyrI Ribosomal_L15e
+  Ribosomal_L21e Ribosomal_L26 Ribosomal_L31e Ribosomal_L32e Ribosomal_L37ae
+  Ribosomal_L39 Ribosomal_L44 Ribosomal_L5e Ribosomal_S17e Ribosomal_S19e
+  Ribosomal_S24e Ribosomal_S27e Ribosomal_S28e Ribosomal_S3Ae Ribosomal_S8e
+  Rib_5-P_isom_A RNase_HII RNA_pol_L_2 RNA_pol_N RNA_pol_Rpb4 RtcB Spt4 TIM
+  Trm56 tRNA-synt_1c tRNA-synt_His TruD vATP-synt_AC39 vATP-synt_E V_ATPase_I}
+  not_as_genomeeq = not_in_archaea + not_in_bacteria
+else
+  raise "Unsupported collection: '#{o[:collection]}'"
+end
 
 begin
   Dir.mktmpdir do |dir|
@@ -148,7 +181,8 @@ begin
     models = {}
     model_id = nil
     dbh = File.open("#{dir}/essential.hmm", 'w')
-    o[:model_file] ||= File.expand_path('../lib/data/essential.hmm.gz',__FILE__)
+    o[:model_file] ||= File.expand_path(
+      "../lib/data/#{o[:collection]}_essential.hmm.gz", __FILE__)
     mfh = (File.extname(o[:model_file]) == '.gz') ?
       Zlib::GzipReader.open(o[:model_file]) :
       File.open(o[:model_file], 'r')
@@ -201,6 +235,9 @@ begin
     # Report statistics
     if o[:stats]
       reph = o[:report].nil? ? $stdout : File.open(o[:report], 'w')
+      modifiers = [:bacteria, :archaea, :genomeeq]
+        .map { |i| o[i] ? i.to_s[0].upcase : '' }.join('')
+      reph.puts "! Collection: #{o[:collection]} #{modifiers}"
       if o[:metagenome]
         reph.printf "! Essential genes found: %d/%d.\n", genes.size, models.size
         gc = [0] * (models.size - genes.size) +

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

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

data/utils/enveomics/enveomics.R/DESCRIPTION

@@ -1,5 +1,5 @@
 Package: enveomics.R
-Version: 1.7.0
+Version: 1.7.1
 Authors@R: c(person("Luis M.","Rodriguez-R",role=c("aut","cre"),
 	   email="lmrodriguezr@gmail.com"))
 Title: Various Utilities for Microbial Genomics and Metagenomics

data/utils/enveomics/enveomics.R/R/df2dist.R

@@ -25,25 +25,24 @@
 
 enve.df2dist <- function(
   x,
-  obj1.index=1,
-  obj2.index=2,
-  dist.index=3,
-  default.d=NA,
-  max.sim=0
+  obj1.index = 1,
+  obj2.index = 2,
+  dist.index = 3,
+  default.d = NA,
+  max.sim = 0
 ){
-  x <- as.data.frame(x);
-  a <- as.character(x[, obj1.index]);
-  b <- as.character(x[, obj2.index]);
-  d <- as.double(x[, dist.index]);
-  if(max.sim!=0) d <- (max.sim - d)/max.sim
-  ids <- unique(c(a,b));
-  m <- matrix(default.d, nrow=length(ids), ncol=length(ids), dimnames=list(ids, ids));
+  x <- as.data.frame(x)
+  a <- as.character(x[, obj1.index])
+  b <- as.character(x[, obj2.index])
+  d <- as.double(x[, dist.index])
+  if(max.sim != 0) d <- (max.sim - d) / max.sim
+  ids <- unique(c(a,b))
+  m <- matrix(default.d,
+    nrow = length(ids), ncol = length(ids), dimnames = list(ids, ids))
   diag(m) <- 0.0
-  for(i in 1:nrow(x)){
-    m[a[i], b[i]] <- d[i];
-  }
-  m <- pmin(m, t(m), na.rm=TRUE)
-  return(as.dist(m));
+  m[cbind(a,b)] <- d
+  m <- pmin(m, t(m), na.rm = TRUE)
+  return(as.dist(m))
 }
 
 #' Enveomics: Data Frame to Dist (Group)

data/utils/enveomics/enveomics.R/R/recplot2.R

@@ -666,15 +666,16 @@ enve.recplot2.findPeaks <- function(
 #' A vector of number of components to evaluate.
 #' @param criterion
 #' Criterion to use for components selection. Must be one of:
-#' \code{aic} (Akaike Information Criterion),
-#' \code{bic} or \code{sbc} (Bayesian Information Criterion or Schwarz Criterion).
+#' \code{aic} (Akaike Information Criterion), \code{bic} or \code{sbc}
+#' (Bayesian Information Criterion or Schwarz Criterion).
 #' @param merge.tol
 #' When attempting to merge peaks with very similar sequencing depth, use
 #' this number of significant digits (in log-scale).
 #' @param verbose
 #' Display (mostly debugging) information.
 #' @param ...
-#' Any additional parameters supported by \code{\link{enve.recplot2.findPeaks.em}}.
+#' Any additional parameters supported by
+#' \code{\link{enve.recplot2.findPeaks.em}}.
 #'
 #' @return Returns a list of \code{\link{enve.RecPlot2.Peak}} objects.
 #'
@@ -684,10 +685,10 @@ enve.recplot2.findPeaks <- function(
 
 enve.recplot2.findPeaks.emauto <- function(
   x,
-  components=seq(1,10),
-  criterion='aic',
-  merge.tol=2L,
-  verbose=FALSE,
+  components = seq(1, 5),
+  criterion = 'aic',
+  merge.tol = 2L,
+  verbose = FALSE,
   ...
 ){
   best <- list(crit=0, pstore=list())
@@ -758,19 +759,19 @@ enve.recplot2.findPeaks.emauto <- function(
 
 enve.recplot2.findPeaks.em <- function(
   x,
-  max.iter=1000,
-  ll.diff.res=1e-8,
-  components=2,
-  rm.top=0.05,
-  verbose=FALSE,
+  max.iter = 1000,
+  ll.diff.res = 1e-8,
+  components = 2,
+  rm.top = 0.05,
+  verbose = FALSE,
   init,
-  log=TRUE
+  log = TRUE
 ){
 
   # Essential vars
   pos.binsize  <- x$pos.breaks[-1] - x$pos.breaks[-length(x$pos.breaks)]
   lsd1  <- (x$pos.counts.in/pos.binsize)[ x$pos.counts.in > 0 ]
-  lsd1 <- lsd1[ lsd1 < quantile(lsd1, 1-rm.top, names=FALSE) ]
+  lsd1 <- lsd1[ lsd1 < quantile(lsd1, 1-rm.top, names = FALSE) ]
   if(log) lsd1 <- log(lsd1)
 
   # 1. Initialize
@@ -779,7 +780,7 @@ enve.recplot2.findPeaks.em <- function(
     init <- list(
       mu = tapply(lsd1, km.clust, mean),
       sd = tapply(lsd1, km.clust, sd),
-      alpha = table(km.clust)/length(km.clust)
+      alpha = table(km.clust) / length(km.clust)
     )
   }
   m.step <- init
@@ -795,6 +796,7 @@ enve.recplot2.findPeaks.em <- function(
     ll.diff <- abs(cur.ll - e.step[["ll"]])
     cur.ll <- e.step[["ll"]]
     if(verbose) cat(i, '\t| LL =', cur.ll, '\t| LL.diff =', ll.diff, '\n')
+    if(is.na(ll.diff) || ll.diff == Inf) break
     if(ll.diff <= ll.diff.res) break
   }
 
@@ -1431,6 +1433,9 @@ enve.recplot2.findPeaks.__em_e <- function
                                               theta[['sd']][i])*theta[['alpha']][i]))
   sum.of.components <- rowSums(product)
   posterior <- product / sum.of.components
+  for(i in which(sum.of.components == Inf)) {
+    cat(i,'/',nrow(product), ':', product[i,], '\n')
+  }
 
   return(list(ll=sum(log(sum.of.components)), posterior=posterior))
 }

data/utils/enveomics/enveomics.R/README.md

@@ -52,6 +52,7 @@ For additional information on recruitment plots, see the
 [Recruitment plots working document](https://github.com/lmrodriguezr/enveomics/blob/master/Docs/recplot2.md).
 
 ## Changelog
+* 1.7.1: Improved efficiency of `enve.df2dist` about five-fold.
 * 1.7.0: Uniformized output for `enve.recplot2.extractWindows` and
   `enve.recplot2.coordinates` to ease automation. Thanks to Tomeu Viver and
   Roth Conrad for troubleshooting.

data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.emauto.Rd

@@ -4,7 +4,7 @@
 \alias{enve.recplot2.findPeaks.emauto}
 \title{Enveomics: Recruitment Plot (2) Emauto Peak Finder}
 \usage{
-enve.recplot2.findPeaks.emauto(x, components = seq(1, 10),
+enve.recplot2.findPeaks.emauto(x, components = seq(1, 5),
   criterion = "aic", merge.tol = 2L, verbose = FALSE, ...)
 }
 \arguments{
@@ -13,15 +13,16 @@ enve.recplot2.findPeaks.emauto(x, components = seq(1, 10),
 \item{components}{A vector of number of components to evaluate.}
 
 \item{criterion}{Criterion to use for components selection. Must be one of:
-\code{aic} (Akaike Information Criterion),
-\code{bic} or \code{sbc} (Bayesian Information Criterion or Schwarz Criterion).}
+\code{aic} (Akaike Information Criterion), \code{bic} or \code{sbc}
+(Bayesian Information Criterion or Schwarz Criterion).}
 
 \item{merge.tol}{When attempting to merge peaks with very similar sequencing depth, use
 this number of significant digits (in log-scale).}
 
 \item{verbose}{Display (mostly debugging) information.}
 
-\item{...}{Any additional parameters supported by \code{\link{enve.recplot2.findPeaks.em}}.}
+\item{...}{Any additional parameters supported by
+\code{\link{enve.recplot2.findPeaks.em}}.}
 }
 \value{
 Returns a list of \code{\link{enve.RecPlot2.Peak}} objects.

data/utils/find-medoid.R

@@ -7,7 +7,12 @@
 #= Load stuff
 argv <- commandArgs(trailingOnly = T)
 suppressPackageStartupMessages(library(ape))
-suppressPackageStartupMessages(library(enveomics.R))
+if(Sys.getenv('MIGA') == ''){
+  suppressPackageStartupMessages(library(enveomics.R))
+}else{
+  source(file.path(Sys.getenv('MIGA'),
+    'utils', 'enveomics', 'enveomics.R', 'R', 'df2dist.R'))
+}
 
 find_medoids <- function(ani.df, out, clades) {
   if(nrow(ani.df) == 0) return(NULL)

data/utils/mytaxa_scan.rb

@@ -1,5 +1,7 @@
 #!/usr/bin/env ruby
 
+require 'zlib'
+
 abort "
 Usage:
 #{$0} {FastA file} {MyTaxa file} {Data output}
@@ -7,52 +9,53 @@ Usage:
 " if ARGV[2].nil?
 
 begin
-   # Get arguments
-   faa, mytaxa, outdata = ARGV
-   winsize = 10
-
-   # Extract gene IDs
-   ids = File.open(faa).grep(/^>/).map{|dl| dl.chomp.sub(/^>/,"").sub(/\s.*/,"")}
-   tax = Hash[ids.map{|k| [k, "NA"]}]
-
-   # Get MyTaxa distributions
-   k, l = nil
-   File.open(mytaxa).each do |ln|
-      ln.chomp!
-      if $.%2 == 1
-	 k, l = ln.split /\t/
-      else
-	 tax[k] = ln.gsub(/<[^>]+>/,"").gsub(/;/,"::")
-      end
-   end
-   all_tax = tax.values.uniq.sort{|x,y| tax.values.count(y) <=> tax.values.count(x) }
-
-   # Estimate Windows and save gene IDs
-   fh = File.open(outdata + ".genes", "w")
-   c = []
-   c << all_tax.map{|t| tax.values.count(t) }
-   n_wins = (ids.size/winsize).ceil
-   (0 .. (n_wins-1)).each do |win|
-      k = ids[win*winsize, winsize]
-      win_t = tax.values_at(*k)
-      fh.puts k.join("\t")
-      c << all_tax.map{|t| win_t.count(t)}
-   end
-   p = c.map{|col| col.map{|cell| cell.to_f/col.inject(:+)}}
-   fh.close
-
-   # Save window profiles
-   fh = File.open(outdata, "w")
-   fh.puts "# Data derived from #{mytaxa}, with #{winsize}-genes windows"
-   fh.puts "# " + (["Tax-label", "Genome"] + (1 .. n_wins).map{|i| "Win_#{i}"}).join("\t")
-   (0 .. (all_tax.size - 1)).each do |row|
-      fh.puts ([all_tax[row]] + p.map{|col| col[row]}).join "\t"
-   end
-   fh.close
+  # Get arguments
+  faa, mytaxa, outdata = ARGV
+  winsize = 10
+
+  # Extract gene IDs
+  ifh = faa =~ /\.gz/ ? Zlib::GzipReader.open(faa) : File.open(faa, 'r')
+  ids = ifh.each_line.grep(/^>/).map{|dl| dl.chomp.sub(/^>/,'').sub(/\s.*/,'')}
+  ifh.close
+  tax = Hash[ids.map{|k| [k, "NA"]}]
+
+  # Get MyTaxa distributions
+  k, l = nil
+  File.open(mytaxa).each do |ln|
+    ln.chomp!
+    if $.%2 == 1
+      k, l = ln.split /\t/
+    else
+      tax[k] = ln.gsub(/<[^>]+>/,"").gsub(/;/,"::")
+    end
+  end
+  all_tax = tax.values.uniq.sort{|x,y| tax.values.count(y) <=> tax.values.count(x) }
+
+  # Estimate Windows and save gene IDs
+  fh = File.open(outdata + ".genes", "w")
+  c = []
+  c << all_tax.map{|t| tax.values.count(t) }
+  n_wins = (ids.size/winsize).ceil
+  (0 .. (n_wins-1)).each do |win|
+    k = ids[win*winsize, winsize]
+    win_t = tax.values_at(*k)
+    fh.puts k.join("\t")
+    c << all_tax.map{|t| win_t.count(t)}
+  end
+  p = c.map{|col| col.map{|cell| cell.to_f/col.inject(:+)}}
+  fh.close
+
+  # Save window profiles
+  fh = File.open(outdata, "w")
+  fh.puts "# Data derived from #{mytaxa}, with #{winsize}-genes windows"
+  fh.puts "# " + (["Tax-label", "Genome"] + (1 .. n_wins).map{|i| "Win_#{i}"}).join("\t")
+  (0 .. (all_tax.size - 1)).each do |row|
+    fh.puts ([all_tax[row]] + p.map{|col| col[row]}).join "\t"
+  end
+  fh.close
 rescue => err
-   $stderr.puts "Exception: #{err}\n\n"
-   err.backtrace.each { |l| $stderr.puts l + "\n" }
-   err
+  $stderr.puts "Exception: #{err}\n\n"
+  err.backtrace.each { |l| $stderr.puts l + "\n" }
+  err
 end
 
-

data/utils/ref-tree.R

@@ -7,7 +7,12 @@
 #= Load stuff
 argv <- commandArgs(trailingOnly=T)
 suppressPackageStartupMessages(library(ape))
-suppressPackageStartupMessages(library(enveomics.R))
+if(Sys.getenv('MIGA') == ''){
+  suppressPackageStartupMessages(library(enveomics.R))
+}else{
+  source(file.path(Sys.getenv('MIGA'),
+    'utils', 'enveomics', 'enveomics.R', 'R', 'df2dist.R'))
+}
 inst <- c("phangorn", "phytools") %in% rownames(installed.packages())
 if(inst[1]){
   suppressPackageStartupMessages(library(phangorn))

data/utils/subclades-nj.R

@@ -12,7 +12,12 @@ suppressPackageStartupMessages(library(cluster))
 suppressPackageStartupMessages(library(phytools))
 suppressPackageStartupMessages(library(phangorn))
 suppressPackageStartupMessages(library(parallel))
-suppressPackageStartupMessages(library(enveomics.R))
+if(Sys.getenv('MIGA') == ''){
+  suppressPackageStartupMessages(library(enveomics.R))
+}else{
+  source(file.path(Sys.getenv('MIGA'),
+    'utils', 'enveomics', 'enveomics.R', 'R', 'df2dist.R'))
+}
 
 #= Main function
 subclades <- function(ani_file, out_base, thr=1, ani=c()) {

data/utils/subclades.R

@@ -10,7 +10,12 @@ suppressPackageStartupMessages(library(ape))
 suppressPackageStartupMessages(library(vegan))
 suppressPackageStartupMessages(library(cluster))
 suppressPackageStartupMessages(library(parallel))
-suppressPackageStartupMessages(library(enveomics.R))
+if(Sys.getenv('MIGA') == ''){
+  suppressPackageStartupMessages(library(enveomics.R))
+}else{
+  source(file.path(Sys.getenv('MIGA'),
+    'utils', 'enveomics', 'enveomics.R', 'R', 'df2dist.R'))
+}
 
 #= Main function
 subclades <- function(ani_file, out_base, thr = 1, ani.d = dist(0), sel = NA) {

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: miga-base
 version: !ruby/object:Gem::Version
-  version: 0.5.0.0
+  version: 0.5.1.0
 platform: ruby
 authors:
 - Luis M. Rodriguez-R
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2019-11-25 00:00:00.000000000 Z
+date: 2020-01-06 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: daemons
@@ -197,7 +197,6 @@ files:
 - test/taxonomy_test.rb
 - test/test_helper.rb
 - utils/adapters.fa
-- utils/arch-ess-genes.rb
 - utils/cleanup-databases.rb
 - utils/core-pan-plot.R
 - utils/distance/base.rb
@@ -207,6 +206,7 @@ files:
 - utils/distance/runner.rb
 - utils/distance/temporal.rb
 - utils/distances.rb
+- utils/domain-ess-genes.rb
 - utils/enveomics/Docs/recplot2.md
 - utils/enveomics/Examples/aai-matrix.bash
 - utils/enveomics/Examples/ani-matrix.bash
@@ -356,7 +356,8 @@ files:
 - utils/enveomics/Scripts/clust.rand.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/data/dupont_2012_essential.hmm.gz
+- utils/enveomics/Scripts/lib/data/lee_2019_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
@@ -514,8 +515,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.7.6
+rubygems_version: 3.0.3
 signing_key: 
 specification_version: 4
 summary: MiGA

data/utils/arch-ess-genes.rb

@@ -1,57 +0,0 @@
-#!/usr/bin/env ruby
-
-esslog = ARGV.shift
-outlog = ARGV.shift
-l_all = `HMM.essential.rb -l -q`.chomp.split("\n").map{ |i| i.gsub(/\t.*/,"") }
-n_arc = Hash[
-  `HMM.essential.rb -l -q -A`.chomp.split("\n").map{ |i| i.split("\t") }
-]
-l_arc = n_arc.keys
-
-def quality(hsh)
-  q = {}
-  q[:found] = hsh.values.map{ |i| i==0 ? 0 : 1 }.inject(:+)
-  q[:multi] = hsh.values.map{ |i| i==0 ? 0 : i-1 }.inject(:+)
-  q[:cmp] = 100.0*q[:found].to_f/hsh.size
-  q[:cnt] = 100.0*q[:multi].to_f/hsh.size
-  q
-end
-
-cnt_ref = {}
-l_all.each{ |i| cnt_ref[i] = 1 }
-
-at = :header
-File.open(esslog, "r") do |fh|
-  fh.each_line do |ln|
-    v = ln.chomp.gsub(/^! +/, "")
-    if v=="Multiple copies: "
-      at = :multi
-    elsif v=="Missing genes: "
-      at = :missing
-    elsif at==:multi
-      v =~ /^(\d+) (\S+): .*/ or raise "Unexpected multi-copies format: #{v}"
-      cnt_ref[$2] = $1.to_i
-    elsif at==:missing
-      v =~ /^(\S+): .*/ or raise "Unexpected missing format: #{v}"
-      cnt_ref[$1] = 0
-    end
-  end
-end
-
-cnt_arc = {}
-l_arc.each{ |i| cnt_arc[i] = cnt_ref[i] }
-
-q = quality(cnt_arc)
-File.open(outlog, "w") do |ofh|
-  ofh.puts "! Essential genes found: #{q[:found]}/#{cnt_arc.size}."
-  ofh.puts "! Completeness: #{q[:cmp].round(1)}%."
-  ofh.puts "! Contamination: #{q[:cnt].round(1)}%."
-  if q[:multi] > 0
-    ofh.puts "! Multiple copies: "
-    cnt_arc.each{ |k,v| ofh.puts "!   #{v} #{k}: #{n_arc[k]}." if v>1 }
-  end
-  if q[:found] < cnt_arc.size
-    ofh.puts "! Missing genes: "
-    cnt_arc.each{ |k,v| ofh.puts "!   #{k}: #{n_arc[k]}." if v==0 }
-  end
-end