miga-base 0.4.3.0 → 0.5.0.0

data/lib/miga/daemon.rb

@@ -35,13 +35,16 @@ class MiGA::Daemon < MiGA::MiGA
 
   ##
   # Initialize an unactive daemon for the MiGA::Project +project+. See #daemon
-  # to wake the daemon.
-  def initialize(project)
+  # to wake the daemon. If passed, +json+ must be the path to a daemon
+  # definition in json format. Otherwise, the project-stored daemon definition
+  # is used. In either case, missing variables are used as defined in
+  # ~/.miga_daemon.json.
+  def initialize(project, json = nil)
     $_MIGA_DAEMON_LAIR << self
     @project = project
+    json ||= File.expand_path('daemon/daemon.json', project.path)
     @runopts = MiGA::Json.parse(
-      File.expand_path('daemon/daemon.json', project.path),
-      default: File.expand_path('.miga_daemon.json', ENV['MIGA_HOME']))
+      json, default: File.expand_path('.miga_daemon.json', ENV['MIGA_HOME']))
     @jobs_to_run = []
     @jobs_running = []
     @loop_i = -1

data/lib/miga/dataset/base.rb

@@ -35,14 +35,14 @@ module MiGA::Dataset::Base
   ##
   # Supported dataset types.
   @@KNOWN_TYPES = {
-    genome: {description: 'The genome from an isolate.', multi: false},
-    scgenome: {description: 'A Single-cell Amplidied Genome (SAG).',
+    genome: {description: 'The genome from an isolate', multi: false},
+    scgenome: {description: 'A Single-cell Amplified Genome (SAG)',
       multi: false},
-    popgenome: {description: 'A Metagenome-Assembled Genome (MAG).',
+    popgenome: {description: 'A Metagenome-Assembled Genome (MAG)',
       :multi=>false},
-    metagenome: {description: 'A metagenome (excluding viromes).',
+    metagenome: {description: 'A metagenome (excluding viromes)',
       multi: true},
-    virome: {description: 'A viral metagenome.', multi: true}
+    virome: {description: 'A viral metagenome', multi: true}
   }
 
   ##

data/lib/miga/project/base.rb

@@ -76,13 +76,13 @@ module MiGA::Project::Base
   # Supported types of projects.
   @@KNOWN_TYPES = {
     mixed: {
-      description: "Mixed collection of genomes, metagenomes, and viromes.",
+      description: "Mixed collection of genomes, metagenomes, and viromes",
       single: true, multi: true},
-    genomes: {description: "Collection of genomes.",
+    genomes: {description: "Collection of genomes",
       single: true, multi: false},
-    clade: {description: "Collection of closely-related genomes (ANI >= 90%).",
+    clade: {description: "Collection of closely-related genomes (ANI >= 90%)",
       single: true, multi: false},
-    metagenomes: {description: "Collection of metagenomes and/or viromes.",
+    metagenomes: {description: "Collection of metagenomes and/or viromes",
       single: false, multi: true}
   }
 

data/lib/miga/project/result.rb

@@ -110,7 +110,8 @@ module MiGA::Project::Result
       r.add_file(:proposal,      'miga-project.proposed-clades')
       r.add_file(:clades_aai90,  'miga-project.aai90-clades')
       r.add_file(:clades_ani95,  'miga-project.ani95-clades')
-      r.add_file(:medoids_ani95, 'miga-project.ani95-medoids')
+      r.add_file(:clades_gsp,  'miga-project.gsp-clades')
+      r.add_file(:medoids_gsp, 'miga-project.gsp-medoids')
       r
     end
 

data/lib/miga/remote_dataset/base.rb

@@ -35,9 +35,9 @@ module MiGA::RemoteDataset::Base
   @@UNIVERSE = {
     web: {
       dbs: {
-        assembly: {stage: :assembly, format: :fasta},
-        assembly_gz: {stage: :assembly, format: :fasta_gz},
-        text: {stage: :metadata, format: :text}
+        assembly: { stage: :assembly, format: :fasta },
+        assembly_gz: { stage: :assembly, format: :fasta_gz },
+        text: { stage: :metadata, format: :text }
       },
       url: '%2$s',
       method: :net
@@ -59,8 +59,8 @@ module MiGA::RemoteDataset::Base
     },
     ncbi_map: {
       dbs: {
-        nuccore: {stage: :metadata, map_to: [:biosample, :assembly],
-          format: :json},
+        nuccore: { stage: :metadata, map_to: [:biosample, :assembly],
+          format: :json },
         biosample: {stage: :metadata, map_to: [:assembly], format: :json}
       },
       url: "#{@@_EUTILS}elink.fcgi?dbfrom=%1$s&id=%2$s&db=%4$s&retmode=%3$s",

data/lib/miga/remote_dataset/download.rb

@@ -84,7 +84,7 @@ class MiGA::RemoteDataset
       end
       doc
     end
-
+    
     ##
     # Looks for the entry +id+ in +dbfrom+, and returns the linked
     # identifier in +db+ (or nil).

data/lib/miga/version.rb

@@ -10,15 +10,15 @@ 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 = [0.4, 3, 0]
+  VERSION = [0.5, 0, 0]
 
   ##
   # Nickname for the current major.minor version.
-  VERSION_NAME = 'aquatint'
+  VERSION_NAME = 'collotype'
 
   ##
   # Date of the current gem release.
-  VERSION_DATE = Date.new(2019, 9, 10)
+  VERSION_DATE = Date.new(2019, 11, 25)
 
   ##
   # Reference of MiGA.

data/scripts/cds.bash

@@ -36,7 +36,9 @@ perl -pe 's/ID=([0-9]+_[0-9]+);/ID=gene_$1;/' "$DATASET.gff3" \
 mv "$DATASET.gff3.t" "$DATASET.gff3"
 
 # Gzip
-gzip -9 -f "$DATASET.gff3"
+for ext in gff3 faa fna ; do
+  [[ -e "$DATASET.$ext" ]] && gzip -9 -f "$DATASET.$ext"
+done
 
 # Finalize
 miga date > "$DATASET.done"

data/scripts/essential_genes.bash

@@ -9,6 +9,7 @@ cd "$PROJECT/data/07.annotation/01.function/01.essential"
 # Initialize
 miga date > "${DATASET}.start"
 FAA="../../../06.cds/${DATASET}.faa"
+[[ -s "$FAA" ]] || FAA="${FAA}.gz"
 
 # Check if there are any proteins
 if [[ ! -s $FAA ]] ; then

data/scripts/stats.bash

@@ -12,7 +12,7 @@ cd "$DIR"
 miga date > "$DATASET.start"
 
 # Calculate statistics
-for i in raw_reads trimmed_fasta assembly cds essential_genes distances ; do
+for i in raw_reads trimmed_fasta assembly cds essential_genes ssu distances taxonomy ; do
   echo "# $i"
   miga result_stats --compute-and-save -P "$PROJECT" -D "$DATASET" -r $i
 done

data/scripts/trimmed_fasta.bash

@@ -13,9 +13,11 @@ miga date > "$DATASET.start"
 
 # Gunzip (if necessary)
 for sis in 1 2 ; do
-  [[ -e "../02.trimmed_reads/$b.$sis.clipped.fastq.gz" \
-    && ! -e "../02.trimmed_reads/$b.$sis.clipped.fastq" ]] \
-      && gunzip "../02.trimmed_reads/$b.$sis.clipped.fastq.gz"
+  for ext in clipped clipped.single ; do
+    [[ -e "../02.trimmed_reads/$b.$sis.${ext}.fastq.gz" \
+      && ! -e "../02.trimmed_reads/$b.$sis.${ext}.fastq" ]] \
+        && gzip -d "../02.trimmed_reads/$b.$sis.${ext}.fastq.gz"
+  done
 done
 miga add_result -P "$PROJECT" -D "$DATASET" -r trimmed_reads -f
 

data/utils/distance/runner.rb

@@ -23,6 +23,9 @@ class MiGA::DistanceRunner
     @dataset = project.dataset(dataset_name)
     @home = File.expand_path('data/09.distances', project.path)
     # Default opts
+    if project.metadata[:aai_save_rbm] == false
+      @opts[:aai_save_rbm] ||= 'no-save-rbm'
+    end
     @opts[:aai_save_rbm] ||= ENV.fetch('MIGA_AAI_SAVE_RBM') do
       project.is_clade? ? 'save-rbm' : 'no-save-rbm'
     end

data/utils/distance/temporal.rb

@@ -1,5 +1,6 @@
 
 require 'tmpdir'
+require 'zlib'
 
 module MiGA::DistanceRunner::Temporal
 
@@ -9,7 +10,15 @@ module MiGA::DistanceRunner::Temporal
     rf.each do |res, file|
       r = dataset.result(res)
       f = r.nil? ? nil : r.file_path(file)
-      FileUtils.cp(f, tmp_file("#{file}.fa")) unless f.nil?
+      unless f.nil?
+        if f =~ /\.gz/
+          File.open(tmp_file("#{file}.fa"), 'w') do |ofh|
+            Zlib::GzipReader.open(f) { |ifh| ofh.print ifh.read }
+          end
+        else
+          FileUtils.cp(f, tmp_file("#{file}.fa"))
+        end
+      end
     end
   end
 

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

@@ -610,6 +610,11 @@
           "opt": "--defline",
           "description": "Keep the original defline after a space."
         },
+        {
+          "opt": "--list",
+          "arg": "in_file",
+          "description": "Reads a list of IDS."
+        },
         {
           "opt": "--quiet",
           "description": "Run quietly (no STDERR output)."

data/utils/enveomics/Manifest/Tasks/sequence-identity.json

@@ -388,6 +388,13 @@
           "arg": "out_file",
           "description": "Output file containing the aligned proteins."
         },
+	{
+	  "opt": "--components",
+	  "arg": "out_file",
+	  "description": ["Output file containing the components of the",
+	    "estimation. Tab-delimited file with model name, matches, and",
+	    "columns."]
+	},
         {
           "opt": "--quiet",
           "description": "Run quietly (no STDERR output)."

data/utils/enveomics/Scripts/BlastTab.addlen.rb

@@ -2,46 +2,46 @@
 
 #
 # @author: Luis M. Rodriguez-R
-# @update: Feb-06-2015
 # @license: artistic license 2.0
 #
 
 require 'optparse'
 
-o = {:subject=>FALSE, :quiet=>FALSE}
-ARGV << '-h' if ARGV.size==0
+o = { sbj: false, q: false }
+ARGV << '-h' if ARGV.size == 0
 OptionParser.new do |opts|
-   opts.banner = "
-Appends an extra column to a BLAST with the length of the query or the subject sequence.
-You can pipe two instances to add both:
-   cat input.blast | #{$0} -f queries.fa | #{$0} -f subjects.fa -s > output.blast
+  opts.banner = "
+Appends an extra column to a BLAST with the length of the query or the subject
+sequence. You can pipe two instances to add both:
+  cat input.blast | #{$0} -f queries.fa | #{$0} -f subjects.fa -s > output.blast
 
 Usage: #{$0} [options] < input.blast > output.blast"
-   opts.separator ""
-   opts.separator "Mandatory"
-   opts.on("-f", "--fasta FILE", "Path to the FastA file"){ |v| o[:fasta] = v }
-   opts.separator ""
-   opts.separator "Options"
-   opts.on("-s", "--subject",
-   	"Use the subject column of the BLAST, by default the query column is used"){ o[:subject] = TRUE }
-   opts.on("-q", "--quiet", "Run quietly (no STDERR output)"){ o[:quiet] = TRUE }
-   opts.on("-h", "--help", "Display this screen") do
-      puts opts
-      exit
-   end
-   opts.separator ""
+  opts.separator ''
+  opts.separator 'Mandatory'
+  opts.on('-f', '--fasta FILE', 'Path to the FastA file'){ |v| o[:fasta] = v }
+  opts.separator ''
+  opts.separator 'Options'
+  opts.on('-s', '--subject',
+    'Use the subject column of the BLAST, by default the query column is used'
+    ){ o[:sbj] = true }
+  opts.on('-q', '--quiet', 'Run quietly (no STDERR output)'){ o[:q] = true }
+  opts.on('-h', '--help', 'Display this screen') do
+    puts opts
+    exit
+  end
+  opts.separator ''
 end.parse!
-abort "-f is mandatory" if o[:fasta].nil?
+abort '-f is mandatory' if o[:fasta].nil?
 
 len = {}
-id  = ""
-$stderr.puts "Reading FastA file: #{o[:fasta]}" unless o[:quiet]
-fh = File.open(o[:fasta], "r")
+id  = ''
+$stderr.puts "Reading FastA file: #{o[:fasta]}" unless o[:q]
+fh = File.open(o[:fasta], 'r')
 fh.each_line do |ln|
    defline = /^>(\S+)/.match(ln)
    if defline.nil?
       ln.gsub! /[^A-Za-z]/, ''
-      abort "Error: Unsupported format, expecting FastA" if len[id].nil?
+      abort 'Error: Unsupported format, expecting FastA' if len[id].nil?
       len[id] = len[id] + ln.size
    else
       id = defline[1]
@@ -50,12 +50,14 @@ fh.each_line do |ln|
 end
 fh.close
 
-$stderr.puts "Appending #{o[:subject]?"subject":"query"} length column" unless o[:quiet]
+unless o[:q]
+  $stderr.puts 'Appending %s length column' % (o[:sbj] ? 'subject' : 'query')
+end
 ARGF.each_line do |ln|
-   ln.chomp!
-   row = ln.split /\t/
-   id = o[:subject] ? row[1] : row[0];
-   abort "Impossible to find sequence of #{id}" if len[id].nil?
-   puts "#{ln}\t#{len[id]}"
+  ln.chomp!
+  row = ln.split /\t/
+  id = o[:sbj] ? row[1] : row[0]
+  abort "Impossible to find sequence of #{id}" if len[id].nil?
+  puts "#{ln}\t#{len[id]}"
 end
 

data/utils/enveomics/Scripts/FastA.tag.rb

@@ -1,64 +1,65 @@
 #!/usr/bin/env ruby
 
-#
 # @author  Luis M. Rodriguez-R
-# @update  Oct-07-2015
 # @license artistic license 2.0
-#
 
 require 'optparse'
 
-o = {:q=>FALSE, :p=>"", :s=>"", :d=>FALSE}
+o = {q: false, p: '', s: '', d: false}
 ARGV << '-h' if ARGV.size==0
 OptionParser.new do |opts|
-   opts.banner = "
+  opts.banner = "
 Generates easy-to-parse tagged reads from FastA files.
 
 Usage: #{$0} [options]"
-   opts.separator ""
-   opts.separator "Mandatory"
-   opts.on("-i", "--in FILE",
-      "Path to the FastA file containing the sequences."){ |v| o[:in] = v }
-   opts.on("-o", "--out FILE",
-      "Path to the FastA to create."){ |v| o[:out] = v }
-   opts.separator ""
-   opts.separator "ID options"
-   opts.on("-p", "--prefix STR", "Prefix to use in all IDs."){ |v| o[:p] = v }
-   opts.on("-s", "--suffix STR", "Suffix to use in all IDs."){ |v| o[:s] = v }
-   opts.on("-d", "--defline",
-      "Keep the original defline after a space."){ o[:d]=TRUE }
-   opts.separator ""
-   opts.separator "Other Options"
-   opts.on("-q", "--quiet", "Run quietly (no STDERR output)"){ o[:q] = TRUE }
-   opts.on("-h", "--help", "Display this screen") do
-      puts opts
-      exit
-   end
-   opts.separator ""
+  opts.separator ''
+  opts.separator 'Mandatory'
+  opts.on('-i', '--in FILE',
+    'Path to the FastA file containing the sequences.'){ |v| o[:in] = v }
+  opts.on('-o', '--out FILE',
+    'Path to the FastA to create.'){ |v| o[:out] = v }
+  opts.separator ''
+  opts.separator 'ID options'
+  opts.on('-p', '--prefix STR', 'Prefix to use in all IDs.'){ |v| o[:p] = v }
+  opts.on('-s', '--suffix STR', 'Suffix to use in all IDs.'){ |v| o[:s] = v }
+  opts.on('-d', '--defline',
+    'Keep the original defline after a space.'){ o[:d] = true }
+  opts.on('-l', '--list FILE',
+    'Reads a list of IDS.'){ |v| o[:l] = v }
+  opts.separator ''
+  opts.separator 'Other Options'
+  opts.on('-q', '--quiet', 'Run quietly (no STDERR output)'){ o[:q] = true }
+  opts.on('-h', '--help', 'Display this screen') do
+    puts opts
+    exit
+  end
+  opts.separator ''
 end.parse!
-abort "-i is mandatory" if o[:in].nil?
-abort "-o is mandatory" if o[:out].nil?
+abort '-i is mandatory' if o[:in].nil?
+abort '-o is mandatory' if o[:out].nil?
    
 begin
-   ifh = File.open(o[:in], 'r');
-   ofh = File.open(o[:out], 'w');
-   i=0
-   while ln=ifh.gets
+  list = o[:l].nil? ? nil :
+    File.readlines(o[:l]).map{ |i| i.chomp.gsub(/^>/, '') }
+  ofh = File.open(o[:out], 'w')
+  i = 0
+  File.open(o[:in], 'r') do |ifh|
+    ifh.each do |ln|
       ln.chomp!
       next if ln =~ /^;/
       unless /^>/.match(ln).nil?
-	 i+=1
-	 ofh.puts ">#{o[:p]}#{i}#{o[:s]}#{ o[:d]?" #{ln[1, ln.size-1]}":"" }"
+        i += 1
+        new_id = o[:l].nil? ? i : list.shift
+        ofh.puts ">#{o[:p]}#{new_id}#{o[:s]}#{o[:d]?" #{ln[1, ln.size-1]}":''}"
       else
-         ofh.puts ln
+        ofh.puts ln
       end
-   end
-   ifh.close
-   ofh.close
+    end
+  end
+  ofh.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/enveomics/Scripts/HMM.essential.rb

@@ -8,8 +8,10 @@ require 'enveomics_rb/enveomics'
 use 'tmpdir'
 use 'zlib'
 
-o = {bin: '', thr: 2, q: false, stats: true, genes: true, bacteria: false,
-  archaea: false, genomeeq: false, metagenome: false, list: false}
+o = {
+  bin: '', thr: 2, q: false, stats: true, genes: true, bacteria: false,
+  archaea: false, genomeeq: false, metagenome: false, list: false
+}
 OptionParser.new do |opts|
   opts.banner = "
 Finds and extracts a collection of essential proteins suitable for genome
@@ -26,65 +28,86 @@ Requires HMMer 3.0+ (http://hmmer.janelia.org/software).
 Usage: #{$0} [options]"
   opts.separator ''
   opts.separator 'Mandatory'
-  opts.on('-i', '--in FILE',
-    'Path to the FastA file containing all the proteins in a genome.'
-    ){ |v| o[:in] = v }
+  opts.on(
+    '-i', '--in FILE',
+    '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.on('-o', '--out FILE',
-    'Path to the output FastA file with the translated essential genes.',
-    'By default the file is not produced.'){ |v| o[:out] = v }
-  opts.on('-m', '--per-model STR',
+  opts.on(
+    '-o', '--out FILE',
+    'Path to the output FastA file with the translated essential genes',
+    'By default the file is not produced'
+  ) { |v| o[:out] = v }
+  opts.on(
+    '-m', '--per-model STR',
     'Prefix of translated genes in independent files with the name of the',
-    'model appended. By default files are not produced.'
-    ){ |v| o[:permodel] = v }
-  opts.on('-R', '--report FILE',
-    'Path to the report file. By default, the report is sent to the STDOUT.'
-    ){ |v| o[:report] = v }
-  opts.on('--hmm-out FILE',
-    'Save HMMsearch output in this file. By default, not saved.'
-    ){ |v| o[:hmmout] = v }
-  opts.on('--alignments FILE',
+    'model appended. By default files are not produced'
+  ) { |v| o[:permodel] = v }
+  opts.on(
+    '-R', '--report FILE',
+    'Path to the report file. By default, the report is sent to the STDOUT'
+  ) { |v| o[:report] = v }
+  opts.on(
+    '--hmm-out FILE',
+    'Save HMMsearch output in this file. By default, not saved'
+  ) { |v| o[:hmmout] = v }
+  opts.on(
+    '--alignments FILE',
     'Save the aligned proteins in this file. By default, not saved'
-    ){ |v| o[:alignments] = v }
-  opts.on('-B', '--bacteria',
-    'If set, ignores models typically missing in Bacteria.'
-    ){ |v| o[:bacteria] = v }
-  opts.on('-A', '--archaea',
-    'If set, ignores models typically missing in Archaea.'
-    ){ |v| o[:archaea] = v }
-  opts.on('-G', '--genome-eq',
-    'If set, ignores models not suitable for genome-equivalents estimations.',
-    'See Rodriguez-R et al, 2015, ISME J 9(9):1928-1940.'
-    ){ |v| o[:genomeeq] = v }
-  opts.on('-r', '--rename STR',
+  ) { |v| o[:alignments] = v }
+  opts.on(
+    '-B', '--bacteria',
+    'If set, ignores models typically missing in Bacteria'
+  ) { |v| o[:bacteria] = v }
+  opts.on(
+    '-A', '--archaea',
+    'If set, ignores models typically missing in Archaea'
+  ) { |v| o[:archaea] = v }
+  opts.on(
+    '-G', '--genome-eq',
+    'If set, ignores models not suitable for genome-equivalents estimations',
+    'See Rodriguez-R et al, 2015, ISME J 9(9):1928-1940'
+  ) { |v| o[:genomeeq] = v }
+  opts.on(
+    '-r', '--rename STR',
     'If set, renames the sequences with the string provided and appends it',
-    'with pipe and the gene name (except in --per-model files).'
-    ){ |v| o[:rename]=v }
-  opts.on('-n', '--no-stats',
-    'If set, no statistics are reported on genome evaluation.'
-    ){ |v| o[:stats] = v }
-  opts.on('-s', '--no-genes',
-    'If set, statistics won\'t include the lists of missing/multi-copy genes.'
-    ){ |v| o[:genes] = v }
-  opts.on('-M', '--metagenome',
+    'with pipe and the gene name (except in --per-model files)'
+  ) { |v| o[:rename] = v }
+  opts.on(
+    '-n', '--no-stats',
+    'If set, no statistics are reported on genome evaluation'
+  ) { |v| o[:stats] = v }
+  opts.on(
+    '-s', '--no-genes',
+    'If set, statistics won\'t include the lists of missing/multi-copy genes'
+  ) { |v| o[:genes] = v }
+  opts.on(
+    '-M', '--metagenome',
     'If set, it allows for multiple copies of each gene and turns on',
-    'metagenomic report mode.'){ |v| o[:metagenome] = v }
+    'metagenomic report mode'
+  ) { |v| o[:metagenome] = v }
   opts.separator ''
   opts.separator 'Other Options'
-  opts.on('-L', '--list-models',
+  opts.on(
+    '-L', '--list-models',
     'If set, it only lists the models and exits. Compatible with -A, -B, -G,',
-    'and -q; ignores all other parameters.'){ |v| o[:list] = v }
-  opts.on('-b', '--bin DIR',
-    'Path to the directory containing the binaries of HMMer 3.0+.'
-    ){ |v| o[:bin] = v }
-  opts.on('--model-file',
-    'External file containing models to search.'){ |v| o[:model_file] = v }
-  opts.on('-t', '--threads INT',
-    "Number of parallel threads to be used.  By default: #{o[:thr]}."
-    ){ |v| o[:thr] = v.to_i }
-  opts.on('-q', '--quiet', 'Run quietly (no STDERR output).'){ o[:q] = true }
-  opts.on('-h', '--help', 'Display this screen.') do
+    'and -q; ignores all other parameters'
+  ) { |v| o[:list] = v }
+  opts.on(
+    '-b', '--bin DIR',
+    'Path to the directory containing the binaries of HMMer 3.0+'
+  ) { |v| o[:bin] = v }
+  opts.on(
+    '--model-file',
+    'External file containing models to search'
+  ) { |v| o[:model_file] = v }
+  opts.on(
+    '-t', '--threads INT', Integer,
+    "Number of parallel threads to be used.  By default: #{o[:thr]}"
+  ) { |v| o[:thr] = v }
+  opts.on('-q', '--quiet', 'Run quietly (no STDERR output)'){ o[:q] = true }
+  opts.on('-h', '--help', 'Display this screen') do
     puts opts
     exit
   end
@@ -112,6 +135,13 @@ TIGR00389 TIGR00436 tRNA-synth_1d}
 begin
   Dir.mktmpdir do |dir|
     $stderr.puts "Temporal directory: #{dir}." unless o[:q]
+    if o[:in] =~ /\.gz/
+      tmp_in = File.expand_path('sequences.fa', dir)
+      Zlib::GzipReader.open(o[:in]) do |ifh|
+        File.open(tmp_in, 'w') { |ofh| ofh.print ifh.read }
+      end
+      o[:in] = tmp_in
+    end
 
     # Create database.
     $stderr.puts 'Searching models.' unless o[:q]
@@ -144,9 +174,9 @@ begin
         'This script requires HMMER 3.0+.'
     end
     o[:hmmout] ||= "#{dir}/hmmsearch"
-    `"#{o[:bin]}hmmsearch" --cpu #{o[:thr]} --tblout "#{o[:hmmout]}" \
-      -A "#{dir}/a.sto" --cut_tc --notextw "#{dir}/essential.hmm" "#{o[:in]}" \
-      > #{dir}/hmmsearch.log`
+    `'#{o[:bin]}hmmsearch' --cpu #{o[:thr]} --tblout '#{o[:hmmout]}' \
+      -A '#{dir}/a.sto' --cut_tc --notextw '#{dir}/essential.hmm' '#{o[:in]}' \
+      > '#{dir}/hmmsearch.log'`
 
     # Parse output
     $stderr.puts 'Parsing results.' unless o[:q]