miga-base 1.3.22.6 → 1.4.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: b7617c312b68875e84d349bc0613493cc5423da5930c7c4639646c968743f8c7
-  data.tar.gz: 8cc072f053bf244889f928ce842e79311eff9deb5dc36fed9d42702536b5cdfb
+  metadata.gz: 5525ee26722f9be06bf3d8ddd8a94909457c55d8e2ac9d8f137bf44e15cf2035
+  data.tar.gz: ce4036f422bb2cc4e5da887d0dfaea6de89a73f152f63269c5894644f8a92127
 SHA512:
-  metadata.gz: 200520c0b8a9a4a13d22db354e8f1d9cfe5876fbca2ab4f6ea454f8638d9dc10d6898b027002ed50f003ddf898311242b3321e5c77836546b45e807bc858f7f9
-  data.tar.gz: 493c26112d46fa6f83783129be0d1a0832b147ac9476f00da6abf5678b67da08bd64ab2e6a92f56124d1bed85de2c9bd626ca60b0f96a809674ef58e4d964ac2
+  metadata.gz: 8b3393571b1f4425a243181ba50117829b264022c02ac251717721bb6ef092ac81f323b8ccb1f4ea1989fe77d61b9f224115f0758f81a0963503127938b59b3f
+  data.tar.gz: d6dd244f7ea5261900d4fc8329398e5bb07a44e28e0ddf8706c546798546814735142c0179831193a4a48d8b3c2bdc93745bd0a021ee31df7ec385f7ef58c4fe

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

@@ -170,7 +170,15 @@ class MiGA::Cli::Action::Add < MiGA::Cli::Action
     r_path = File.expand_path("data/#{r_dir}/#{d.name}", p.path)
     file_type[2].each_with_index do |ext, i|
       gz = file[i] =~ /\.gz/ ? '.gz' : ''
-      FileUtils.cp(file[i], "#{r_path}#{ext}#{gz}")
+      fo = "#{r_path}#{ext}#{gz}"
+      if gz == ''
+        FileUtils.cp(file[i], fo)
+      else
+        MiGA::MiGA.run_cmd(
+          "gzip -cd #{file[i].shellescape} | gzip -c > #{fo.shellescape}",
+          source: :miga_env # <- To load pigz if available
+        )
+      end
       cli.say "  file: #{File.basename(file[i])}"
     end
     File.open("#{r_path}.done", 'w') { |f| f.print Time.now.to_s }

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

@@ -83,8 +83,9 @@ module MiGA::Cli::Action::Doctor::Base
     data = MiGA::SQLite.new(db_file).run(sql) || []
     Hash[
       data.map do |row|
-        k, v = row.shift(2)
-        [k, row.all?(&:zero?) ? v : [v] + row]
+        r = row.dup
+        k, v = r.shift(2)
+        [k, r.all?(&:zero?) ? v : [v] + r]
       end
     ]
   end

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

@@ -18,6 +18,10 @@ class MiGA::Cli::Action::Env < MiGA::Cli::Action
       for util in enveomics/Scripts FastAAI/fastaai multitrim ; do
         export PATH="$MIGA/utils/$util:$PATH"
       done
+      # Override gzip with pigz (if available)
+      if command -v pigz &>/dev/null ; then
+        function gzip { pigz -p ${CORES:-2} "$@" ; }
+      fi
     BASH
   end
 

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

@@ -7,7 +7,7 @@ class MiGA::Cli::Action::Files < MiGA::Cli::Action
   def parse_cli
     cli.defaults = { details: false, json: true }
     cli.parse do |opt|
-      cli.opt_object(opt, [:project, :dataset_opt])
+      cli.opt_object(opt, %i[project dataset_opt result_opt])
       opt.on(
         '-i', '--info',
         'Print additional details for each file'
@@ -21,7 +21,10 @@ class MiGA::Cli::Action::Files < MiGA::Cli::Action
   end
 
   def perform
-    cli.load_project_or_dataset.each_result do |sym, res|
+    obj = cli.load_project_or_dataset
+    res = cli[:result] ? [cli.load_result] : cli.load_project_or_dataset.results
+    res.each do |res|
+      sym = res.key
       cli.puts "#{"#{sym}\tjson\t" if cli[:details]}#{res.path}" if cli[:json]
       res.each_file do |k, f|
         cli.puts "#{"#{sym}\t#{k}\t" if cli[:details]}#{res.dir}/#{f}"

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

@@ -140,7 +140,7 @@ class MiGA::Cli::Action::Init < MiGA::Cli::Action
           paths[r[1]] = cli[:"path_to_#{r[1]}"]
           cli.puts "user-provided: #{paths[r[1]]}"
         else
-          path = find_software(r[1])
+          path = find_software(r[1], rc_fh)
           paths[r[1]] = File.expand_path(r[1], path).shellescape
         end
       end
@@ -169,7 +169,7 @@ class MiGA::Cli::Action::Init < MiGA::Cli::Action
       ) == 'yes'
   end
 
-  def find_software(exec)
+  def find_software(exec, rc_fh)
     path = nil
     loop do
       d_path = File.dirname(run_cmd(cli, ['which', exec], raise: false))

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

@@ -14,6 +14,10 @@ class MiGA::Cli::Action::Option < MiGA::Cli::Action
       ) { |v| cli[:key] = v }
       opt.on(
         '--value STRING',
+        '::HIDE::' # Replaced by --set, but aliased for backward compatibility
+      ) { |v| cli[:value] = v }
+      opt.on(
+        '-s', '--set STRING',
         'Value of the option to set (by default, option value is not changed)',
         'Recognized tokens: nil, true, false'
       ) { |v| cli[:value] = v }

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

@@ -7,7 +7,7 @@ class MiGA::Cli::Action::Run < MiGA::Cli::Action
   def parse_cli
     cli.defaults = { try_load: false, thr: 1, env: false, check_first: false }
     cli.parse do |opt|
-      cli.opt_object(opt, [:project, :dataset_opt, :result_opt])
+      cli.opt_object(opt, %i[project dataset_opt result_opt])
       opt.on(
         '-t', '--threads INT', Integer,
         "Threads to use in the local run (by default: #{cli[:thr]})"

data/lib/miga/cli/opt_helper.rb

@@ -92,22 +92,22 @@ module MiGA::Cli::OptHelper
         opt.on(
           '-r', '--result STRING',
           "#{'(Mandatory) ' if w == :result}Name of the result",
-          'Recognized names for dataset-specific results include:',
-          *MiGA::Dataset.RESULT_DIRS.keys.map { |n| " ~ #{n}" },
-          'Recognized names for project-wide results include:',
-          *MiGA::Project.RESULT_DIRS.keys.map { |n| " ~ #{n}" }
+          '~ Recognized names for dataset-specific results include:',
+          *list_to_paragraph(MiGA::Dataset.RESULT_DIRS.keys),
+          '~ Recognized names for project-wide results include:',
+          *list_to_paragraph(MiGA::Project.RESULT_DIRS.keys)
         ) { |v| self[:result] = v.downcase.to_sym }
       when :result_dataset
         opt.on(
           '-r', '--result STRING',
           '(Mandatory) Name of the result, one of:',
-          *MiGA::Dataset.RESULT_DIRS.keys.map { |n| " ~ #{n}" }
+          *list_to_paragraph(MiGA::Dataset.RESULT_DIRS.keys, indent: 0)
         ) { |v| self[:result] = v.downcase.to_sym }
       when :result_project
         opt.on(
           '-r', '--result STRING',
           '(Mandatory) Name of the result, one of:',
-          *MiGA::Project.RESULT_DIRS.keys.map { |n| " ~ #{n}" }
+          *list_to_paragraph(MiGA::Project.RESULT_DIRS.keys, indent: 0)
         ) { |v| self[:result] = v.downcase.to_sym }
       else
         raise "Internal error: Unrecognized option: #{w}"
@@ -174,4 +174,10 @@ module MiGA::Cli::OptHelper
     sym = flag.to_sym if sym.nil?
     opt.on("--#{flag.to_s.tr('_', '-')}", description) { |v| self[sym] = v }
   end
+
+  def list_to_paragraph(list, width: 50, indent: 2)
+    list.map(&:to_s).join(', ')
+        .scan(/\S.{0,#{width}}\S(?=\s|$)|\S+/).to_a
+        .map { |i| "#{' ' * indent}#{i}" }
+  end
 end

data/lib/miga/dataset/base.rb

@@ -158,6 +158,9 @@ module MiGA::Dataset::Base
     },
     dist_req: {
       desc: 'Run distances against these datasets', type: Array, default: []
+    },
+    keep_assembly_graphs: {
+      desc: 'Do not clean assembly graphs', in: [true, false], default: false
     }
   }
 end

data/lib/miga/dataset/result/add.rb

@@ -58,10 +58,12 @@ module MiGA::Dataset::Result::Add
     return nil unless
       result_files_exist?(base, '.CoupledReads.fa') ||
       result_files_exist?(base, '.SingleReads.fa')  ||
-      result_files_exist?(base, %w[.1.fasta .2.fasta])
+      result_files_exist?(base, %w[.1.fasta .2.fasta]) ||
+      result_files_exist?(base, '.empty')
 
     add_files_to_ds_result(
       MiGA::Result.new("#{base}.json"), name,
+      empty: '.empty',
       coupled: '.CoupledReads.fa',
       single: '.SingleReads.fa',
       pair1: '.1.fasta',

data/lib/miga/dataset.rb

@@ -199,7 +199,9 @@ class MiGA::Dataset < MiGA::MiGA
 
   ##
   # Retrieves the option with name +key+ from the dataset's metadata
-  # extending support to relative paths in +:db_project+
+  # extending support to relative paths in +:db_project+, and for all
+  # other options looks for metadata defined in the project before
+  # returning the default
   def option_by_metadata(key)
     case key.to_sym
     when :db_project
@@ -209,6 +211,8 @@ class MiGA::Dataset < MiGA::MiGA
       return y
     end
 
+    return project.metadata[key] unless project.metadata[key].nil?
+
     super
   end
 end

data/lib/miga/project/base.rb

@@ -133,6 +133,11 @@ module MiGA::Project::Base
       desc: 'Maximum p-value to transfer taxonomy', default: 0.1, type: Float,
       in: 0.0..1.0
     },
+    indexing: {
+      desc: 'Approach used to index the collection as database', type: String,
+      default: 'hierarchical',
+      in: %w[hierarchical gsearch no]
+    },
     haai_p: {
       desc: 'Value of aai.rb -p on hAAI', type: String,
       default: proc { |project|
@@ -146,7 +151,7 @@ module MiGA::Project::Base
     },
     ani_p: {
       desc: 'Value of ani.rb -p on ANI', default: 'fastani', type: String,
-      in: %w[blast+ blast blat fastani]
+      in: %w[blast+ blast blat fastani no]
     },
     max_try: {
       desc: 'Maximum number of task attempts', default: 10, type: Integer,

data/lib/miga/result/stats.rb

@@ -42,6 +42,10 @@ module MiGA::Result::Stats
     stats
   end
 
+  def compute_stats_trimmed_reads
+    compute_stats_raw_reads
+  end
+
   def compute_stats_trimmed_fasta
     f = self[:files][:coupled].nil? ? file_path(:single) : file_path(:coupled)
     s = MiGA::MiGA.seqs_length(f, :fasta, gc: true, x: true, skew: true)

data/lib/miga/version.rb

@@ -12,7 +12,7 @@ module MiGA
   # - String indicating release status:
   #   - rc* release candidate, not released as gem
   #   - [0-9]+ stable release, released as gem
-  VERSION = [1.3, 22, 6].freeze
+  VERSION = [1.4, 0, 0].freeze
 
   ##
   # Nickname for the current major.minor version.
@@ -20,7 +20,7 @@ module MiGA
 
   ##
   # Date of the current gem relese.
-  VERSION_DATE = Date.new(2025, 5, 19)
+  VERSION_DATE = Date.new(2025, 9, 23)
 
   ##
   # References of MiGA

data/scripts/assembly.bash

@@ -11,6 +11,7 @@ miga date > "$DATASET.start"
 
 # Interpose (if needed)
 interpose=no
+TR="../02.trimmed_reads"
 TF="../04.trimmed_fasta"
 b=$DATASET
 if [[ -s "$TF/${b}.2.fasta" || -s "$TF/${b}.2.fasta.gz" ]] ; then
@@ -38,25 +39,66 @@ for i in SingleReads CoupledReads ; do
     miga add_result -P "$PROJECT" -D "$DATASET" -r trimmed_fasta -f
   fi
 done
+for i in 1 2 ; do
+  base="$TR/${DATASET}.${i}.clipped.fastq"
+  if [[ -e "$base" && ! -s "${base}.gz" ]] ; then
+    gzip -9f "$base"
+    miga add_result -P "$PROJECT" -D "$DATASET" -r trimmed_reads -f
+  fi
+done
 
 # Assemble
-FA="$TF/${DATASET}.CoupledReads.fa.gz"
-[[ -e "$FA" ]] || FA="$TF/${DATASET}.SingleReads.fa.gz"
-RD="r"
-[[ $FA == *.SingleReads.fa* ]] && RD="l"
-gzip -cd "$FA" \
-  | idba_ud --pre_correction -$RD /dev/stdin \
-    -o "$DATASET" --num_threads "$CORES" || true
-[[ -s "$DATASET/contig.fa" ]] || exit 1
+CMD="spades.py -o $DATASET -t $CORES"
+TYPE_OPT=""
+case "$(miga ls -P "$PROJECT" -D "$DATASET" -m type | cut -f 2)" in
+  "metagenome")
+    TYPE_OPT="--meta" ;;
+  "plasmid")
+    TYPE_OPT="--plasmid" ;;
+  "scgenome")
+    TYPE_OPT="--sc" ;;
+  "genome")
+    TYPE_OPT="--isolate" ;;
+  "virome")
+    TYPE_OPT="--metaviral" ;;
+esac
+F1="$TR/${DATASET}.1.clipped.fastq.gz"
+F2="$TR/${DATASET}.2.clipped.fastq.gz"
+if [[ -s "$F1" ]] ; then
+  if [[ -s "$F2" ]] ; then
+    CMD="$CMD -1 $F1 -2 $F2"
+  else
+    CMD="$CMD -s $F1"
+    [[ "$TYPE_OPT" == "--meta" ]] && TYPE_OPT=""
+  fi
+else
+  F1="$TF/${DATASET}.CoupledReads.fa.gz"
+  F1="$TF/${DATASET}.SingleReads.fa.gz"
+  if [[ -s "$F1" ]] ; then
+    CMD="$CMD --12 $F1"
+  elif [[ -s "$F2" ]] ; then
+    CMD="$CMD -s $F2"
+    [[ "$TYPE_OPT" == "--meta" ]] && TYPE_OPT=""
+  else
+    echo "No input files found to assemble" >&2
+    exit 1
+  fi
+fi
+CMD="$CMD $TYPE_OPT"
+echo "$CMD"
+$CMD || true
+[[ -s "$DATASET/contigs.fa" ]] || exit 1
 
 # Clean
-( cd "$DATASET" && rm kmer graph-*.fa align-* local-contig-*.fa contig-*.fa )
+KEEP_GR=$(miga option -P "$PROJECT" -D "$DATASET" -k keep_assembly_graphs)
+[[ "$KEEP_GR" == "true" ]] || ( cd "$DATASET" && rm -R *.gfa *.fastg *.paths )
+( cd "$DATASET" && rm -R K* corrected misc pipeline_state before_rr.fasta )
 
 # Extract
-if [[ -s "$DATASET/scaffold.fa" ]] ; then
-  ln -s "$DATASET/scaffold.fa" "$DATASET.AllContigs.fna"
+if [[ -s "$DATASET/scaffolds.fasta" ]] ; then
+  ln -s "$DATASET/scaffolds.fasta" "$DATASET.AllContigs.fna"
 else
-  ln -s "$DATASET/contig.fa" "$DATASET.AllContigs.fna"
+  ln -s "$DATASET/contigs.fasta" "$DATASET.AllContigs.fna"
 fi
 FastA.length.pl "$DATASET.AllContigs.fna" | awk '$2 >= 1000 { print $1 }' \
   | FastA.filter.pl /dev/stdin "$DATASET.AllContigs.fna" \
@@ -64,6 +106,7 @@ FastA.length.pl "$DATASET.AllContigs.fna" | awk '$2 >= 1000 { print $1 }' \
 
 # Finalize
 miga date > "$DATASET.done"
+[[ -n "$OPT_TYPE" ]] || OPT_TYPE="default"
 cat <<VERSIONS \
   | miga add_result -P "$PROJECT" -D "$DATASET" -r "$SCRIPT" -f --stdin-versions
 => MiGA
@@ -74,7 +117,6 @@ $(
     echo "version unknown"
   fi
 )
-=> IDBA-UD
-version unknown
+=> SPADES
+$(spades.py --version | perl -pe 's/.* //') [$OPT_TYPE]
 VERSIONS
-

data/scripts/miga.bash

@@ -15,11 +15,6 @@ function exists { [[ -e "$1" ]] ; }
 # Evaluates if the first passed argument is a function
 function fx_exists { [[ $(type -t "$1") == "function" ]] ; }
 
-# Override gzip with pigz (if available)
-if command -v pigz &>/dev/null ; then
-  function gzip { pigz -p ${CORES:-2} "$@" ; }
-fi
-
 # Initiate a project-wide run
 function miga_start_project_step {
   local dir="$1"

data/scripts/trimmed_fasta.bash

@@ -11,35 +11,18 @@ b=$DATASET
 # Initialize
 miga date > "$DATASET.start"
 
-# FastQ -> FastA
-for s in 1 2 ; do
-  in="../02.trimmed_reads/${b}.${s}.clipped.fastq.gz"
-  [[ -s "$in" ]] \
-    && FastQ.maskQual.rb -i "$in" -o "${b}.${s}.fasta" --fasta --qual 18
-done
-
-# Interpose
-if [[ -e "${b}.2.fasta" ]] ; then
-  FastA.interpose.pl "${b}.CoupledReads.fa" "$b".[12].fasta
-else
-  mv "${b}.1.fasta" "${b}.SingleReads.fa"
-fi
-
-# Gzip
+# Gzip (if needed)
 for x in 1.fasta 2.fasta SingleReads.fa CoupledReads.fa ; do
   in="${b}.${x}"
   [[ -e "$in" ]] && gzip -9f "$in"
 done
 
 # Finalize
+echo 'Using FastQ directly' > "${DATASET}.empty"
 miga date > "${DATASET}.done"
 cat <<VERSIONS \
   | miga add_result -P "$PROJECT" -D "$DATASET" -r "$SCRIPT" -f --stdin-versions
 => MiGA
 $(miga --version)
-=> Enveomics Collection: FastQ.maskQual.rb
-$(FastQ.maskQual.rb --version | perl -pe 's/.* //')
-=> Enveomics Collection: FastA.interpose.pl
-version unknown
 VERSIONS
 

data/scripts/trimmed_reads.bash

@@ -67,7 +67,7 @@ $(miga --version)
 => Enveomics Collection: FastQ.tag.rb
 $(FastQ.tag.rb --version | perl -pe 's/.* //')
 => Multitrim
-version unknown
+$(multitrim.py --version | perl -pe 's/.* //')
 => FaQCs
 $(FaQCs --version 2>&1 | perl -pe 's/.*: //')
 => Seqtk

data/test/common_test.rb

@@ -26,11 +26,13 @@ class CommonTest < Test::Unit::TestCase
     assert_respond_to(MiGA::MiGA, :DEBUG_ON)
     assert_respond_to(MiGA::MiGA, :DEBUG_OFF)
     MiGA::MiGA.DEBUG_TRACE_ON
+    assert(MiGA::MiGA.debug_trace?)
     err = capture_stderr do
       MiGA::MiGA.DEBUG 'Dandadi'
     end
-    assert_match(/Dandadi\n    .*block in test_debug_trace/, err.string)
+    assert_match(/Dandadi\n    .*block in .*test_debug_trace/, err.string)
     MiGA::MiGA.DEBUG_TRACE_OFF
+    assert(!MiGA::MiGA.debug_trace?)
     err = capture_stderr do
       MiGA::MiGA.DEBUG 'Dandada'
     end

data/test/result_stats_test.rb

@@ -53,7 +53,8 @@ class ResultStatsTest < Test::Unit::TestCase
     r = dataset.add_result(:trimmed_reads)
     assert_equal({}, r.stats)
     r.compute_stats
-    assert_equal({}, r.stats)
+    assert_equal([nil, '%'], r.stats[:a_t_skew])
+    assert_equal(0, r.stats[:reads])
   end
 
   def test_read_quality

data/test/test_helper.rb

@@ -1,9 +1,10 @@
+require_relative 'test_patch'
 require 'simplecov'
 SimpleCov.start
 
 require 'rubygems'
-require 'test/unit'
 require 'assertions'
+require 'test/unit'
 require 'miga/common'
 require 'stringio'
 

data/test/test_patch.rb

@@ -0,0 +1,20 @@
+# Narrowly filter known legacy-gem noise without changing behavior.
+
+module Warning
+  class << self
+    alias_method :__warn_original, :warn
+
+    def warn(msg)
+      # 1) test-unit <-> assertions duplicate method warning
+      return if msg.include?('method redefined; discarding old assert_raise_message')
+      return if msg.include?('previous definition of assert_raise_message was here')
+
+      # 2) simplecov 0.13 "literal string will be frozen in the future"
+      # (emitted by simplecov/version.rb when assigning the VERSION constant)
+      return if msg.include?('simplecov/version.rb') &&
+                msg.include?('literal string will be frozen in the future')
+
+      __warn_original(msg)
+    end
+  end
+end

data/utils/distance/commands.rb

@@ -44,6 +44,7 @@ module MiGA::DistanceRunner::Commands
     $stderr.puts "[#{Time.now}] ANI: #{dataset.name} vs #{targets.size} targets"
     empty_vals = targets.map { |_i| nil }
     return empty_vals unless File.size?(tmp_file('largecontigs.fa'))
+    return empty_vals if opts[:ani_p] == 'no'
 
     # Launch comparisons
     sbj = pending_targets(targets, :ani)

data/utils/distance/database.rb

@@ -106,7 +106,7 @@ module MiGA::DistanceRunner::Database
         [n1, n2]
       ).first
     end if File.size?(db)
-    y
+    y.dup
   rescue SQLite3::CorruptException => e
     $stderr.puts "Corrupt database: #{db}"
     raise e
@@ -157,7 +157,7 @@ module MiGA::DistanceRunner::Database
     data = {}
     SQLite3::Database.new(db) do |conn|
       sql = "select seq2, #{table}, sd, n, omega from #{table}"
-      conn.execute(sql).each { |row| data[row.shift] = row }
+      conn.execute(sql).each { |row| r = row.dup; data[r.shift] = r }
     end
     data
   rescue => e
@@ -187,7 +187,7 @@ module MiGA::DistanceRunner::Database
   # Iterates for each entry in +db+
   def foreach_in_db(db, metric, &blk)
     SQLite3::Database.new(db) do |conn|
-      conn.execute("select * from #{metric}").each { |r| blk[r] }
+      conn.execute("select * from #{metric}").each { |r| blk[r.dup] }
     end
   end
 

data/utils/distance/runner.rb

@@ -25,9 +25,8 @@ class MiGA::DistanceRunner
       @ref_project = project
     end
     @opts[:thr] ||= ENV.fetch('CORES') { 1 }.to_i
-    %i[haai_p aai_p ani_p distances_checkpoint aai_save_rbm].each do |m|
-      @opts[m] ||= ref_project.option(m)
-    end
+    %i[haai_p aai_p ani_p distances_checkpoint aai_save_rbm indexing]
+      .each { |m| @opts[m] ||= ref_project.option(m) }
     $stderr.puts "Options: #{opts}"
   end
 
@@ -46,6 +45,27 @@ class MiGA::DistanceRunner
   # Launch analysis for reference datasets
   def go_ref!
     $stderr.puts 'Launching analysis for reference dataset'
+
+    # Check if the project is non-hierarchical
+    case ref_project.option(:indexing)
+    when 'no'
+      # No index? No distance
+      out_base = File.expand_path(dataset.name, home)
+      File.open("#{out_base}.empty", 'w') { |fh| fh.puts 'No indexing' }
+      return
+    when 'gsearch'
+      if project == ref_project
+        # No need to pre-calculate any distances for GSearch indexes
+        out_base = File.expand_path(dataset.name, home)
+        File.open("#{out_base}.empty", 'w') { |fh| fh.puts 'GSearch indexing' }
+        return
+      else
+        # Just keep going, gsearch will override haai_p and aai_p
+      end
+    when 'hierarchical'
+      # Just keep going
+    end
+
     # Initialize databases
     initialize_dbs! true
 

data/utils/index_metadata.rb

@@ -12,8 +12,10 @@ db.execute 'create table metadata(' \
   '`name` varchar(256), `field` varchar(256), `value` text)'
 
 def searchable(db, d, k, v)
-  db.execute 'insert into metadata values(?,?,?)',
-             d.name, k.to_s, " #{v.to_s.downcase.gsub(/[^A-Za-z0-9\-]+/, ' ')} "
+  db.execute(
+    'insert into metadata values(?,?,?)',
+    [d.name, k.to_s, " #{v.to_s.downcase.gsub(/[^A-Za-z0-9\-]+/, ' ')} "]
+  )
 end
 
 p.each_dataset do |d|

data/utils/multitrim/multitrim.py

@@ -515,7 +515,7 @@ def adapter_identification_pe(artificial_artifacts, seqtk_binary, faqcs_binary,
 				begin_assessment = True
 		else:
 			segment = line.strip().split()
-			detected_adapters[segment[0]] = float(re.findall("\d+\.\d+", segment[3])[0])
+			detected_adapters[segment[0]] = float(re.findall(r"\d+\.\d+", segment[3])[0])
 
 	detection_report.close()
 
@@ -576,7 +576,7 @@ def adapter_identification_se(artificial_artifacts, seqtk_binary, faqcs_binary,
 				begin_assessment = True
 		else:
 			segment = line.strip().split()
-			detected_adapters[segment[0]] = float(re.findall("\d+\.\d+", segment[3])[0])
+			detected_adapters[segment[0]] = float(re.findall(r"\d+\.\d+", segment[3])[0])
 
 	detection_report.close()
 
@@ -1028,11 +1028,13 @@ def gather_opts():
 
 	parser.add_argument("--resources", dest = "resource_list", action = 'store_true', help = "Print a list of resources used by Multitrim and quit.")
 
+	parser.add_argument("--version", dest = "version", action = 'store_true', help = "Print the version of multitrim and exit")
+
 
 	return(parser, parser.parse_args())
 
 def print_resources():
-	print("Multitrim github: https://github.com/KGerhardt/multitrim")
+	print("Multitrim github: https://github.com/bio-miga/multitrim")
 	print("MiGA adapters available at: https://github.com/bio-miga/miga/blob/main/utils/adapters.fa")
 	internal_adapters = faqcs_internal_adapters()
 	print("FaQCs mandatory adapters are:")
@@ -1042,6 +1044,9 @@ def print_resources():
 	print("fastp github: https://github.com/OpenGene/fastp")
 	print("Falco github: https://github.com/smithlabcode/falco")
 
+def print_version():
+	print("MiGA's Multitrim 1.0")
+
 #Program Control
 def main():
 	#Keep the parser on hand so I can prent usage as needed.s
@@ -1052,6 +1057,10 @@ def main():
 		print_resources()
 		quit()
 
+	if options.version:
+		print_version()
+		quit()
+
 
 	#Allows for the script to take no inputs and print help/usage
 	if len(sys.argv)==1:

data/utils/requirements.txt

@@ -12,11 +12,11 @@ Bedtools	bedtools	http://bedtools.readthedocs.org/en/latest/
 Prodigal	prodigal	http://prodigal.ornl.gov
 MCL		mcl		http://micans.org/mcl/
 Barrnap		barrnap		http://www.vicbioinformatics.com/software.barrnap.shtml
-IDBA (reads)	idba_ud		http://i.cs.hku.hk/~alse/hkubrg/projects/idba
 FaQCs (reads)	FaQCs		https://github.com/LANL-Bioinformatics/FaQCs
 Falco (reads)	falco		https://github.com/smithlabcode/falco
 Seqtk (reads)	seqtk		https://github.com/lh3/seqtk
 Fastp (reads)	fastp		https://github.com/OpenGene/fastp
+SPADES (reads)	spades.py	https://ablab.github.io/spades/			Required version: 3+
 Temurin (rdp)	java		https://adoptium.net/				Any Java VM would work
 MyTaxa (mytaxa)	MyTaxa		http://enve-omics.ce.gatech.edu/mytaxa
 Krona (mytaxa)	ktImportText	https://github.com/marbl/Krona/wiki

data/utils/subclade/pipeline.rb

@@ -2,6 +2,7 @@
 module MiGA::SubcladeRunner::Pipeline
   # Run species-level clusterings using ANI > 95% / AAI > 90%
   def cluster_species
+    return unless opts[:indexing] == 'hierarchical'
     tasks = {
       ani95: [:ani_distances, opts[:gsp_ani], :ani],
       aai90: [:aai_distances, opts[:gsp_aai], :aai]
@@ -69,6 +70,17 @@ module MiGA::SubcladeRunner::Pipeline
   end
 
   def subclades(metric)
+    case opts[:indexing]
+    when 'no'
+      # Do nothing
+    when 'gsearch'
+      subclades_gsearch(metric)
+    when 'hierarchical'
+      subclades_hierarchical(metric)
+    end
+  end
+
+  def subclades_hierarchical(metric)
     src = File.expand_path('utils/subclades.R', MiGA::MiGA.root_path)
     step = :"#{metric}_distances"
     metric_res = project.result(step) or raise "Incomplete step #{step}"
@@ -82,6 +94,34 @@ module MiGA::SubcladeRunner::Pipeline
     end
   end
 
+  def subclades_gsearch(metric)
+    tmp_dir = tmp_file('genomes')
+    Dir.mkdir(tmp_dir)
+
+    cmd  = %w[gsearch --pio 2000 --nbthreads] + [opts[:thr].to_s]
+    cmd += %w[tohnsw -k 16 -n 128 --ef 1600 --algo optdens]
+    cmd += %w[--scale_modify_f 0.25 -d] + tmp_dir
+
+    if metric.to_sym == :ani
+      project.dataset_ref_active.each do |ds|
+        f = ds&.result(:assembly)&.file_path(:largecontigs) or next
+        FileUtils.ln_s(f, tmp_dir)
+      end
+      cmd += %w[-s 18000]
+    else
+      project.dataset_ref_active.each do |ds|
+        f = ds&.result(:cds)&.file_path(:proteins) or next
+        FileUtils.ln_s(f, tmp_dir)
+      end
+      cmd += %w[-s 12000 --aa]
+    end
+
+    Dir.mkdir('gsearch.d')
+    Dir.chdir('gsearch.d')
+    run_cmd(cmd)
+    Dir.chdir('..')
+  end
+
   def compile
     src = File.expand_path('utils/subclades-compile.rb', MiGA::MiGA.root_path)
     run_cmd(['ruby', src, '.', 'miga-project.class'])

data/utils/subclade/runner.rb

@@ -14,20 +14,21 @@ class MiGA::SubcladeRunner
       @step == :clade_finding ? '01.find.running' : '02.ani.running'
     )
     @opts[:thr] ||= ENV.fetch('CORES') { 2 }.to_i
-    @opts[:run_clades] = @project.option(:run_clades)
-    @opts[:gsp_ani] = @project.option(:gsp_ani)
-    @opts[:gsp_aai] = @project.option(:gsp_aai)
-    @opts[:gsp_metric] = @project.option(:gsp_metric)
+    %i[run_clades gsp_ani gsp_aai gsp_metric indexing].each do |m|
+      @opts[m] = @project.option(m)
+    end
   end
 
   # Launch the appropriate analysis
   def go!
     return if project.type == :metagenomes
 
-    unless @project.dataset_names.any? { |i| @project.dataset(i).ref? }
+    if @opts[:indexing] == 'no' ||
+          !@project.dataset_names.any? { |i| @project.dataset(i).ref? }
       FileUtils.touch(File.join(@home, 'miga-project.empty'))
       return
     end
+
     Dir.chdir home
     Dir.mktmpdir do |tmp_dir|
       @tmp = tmp_dir

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: miga-base
 version: !ruby/object:Gem::Version
-  version: 1.3.22.6
+  version: 1.4.0.0
 platform: ruby
 authors:
 - Luis M. Rodriguez-R
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2025-05-19 00:00:00.000000000 Z
+date: 2025-09-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: daemons
@@ -44,14 +44,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.3'
+        version: '2.7'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.3'
+        version: '2.7'
 - !ruby/object:Gem::Dependency
   name: net-http
   requirement: !ruby/object:Gem::Requirement
@@ -100,14 +100,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '12'
+        version: '13.0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '12'
+        version: '13.0'
 - !ruby/object:Gem::Dependency
   name: test-unit
   requirement: !ruby/object:Gem::Requirement
@@ -317,6 +317,7 @@ files:
 - test/tax_index_test.rb
 - test/taxonomy_test.rb
 - test/test_helper.rb
+- test/test_patch.rb
 - test/with_daemon_test.rb
 - test/with_option_test.rb
 - utils/FastAAI/FastAAI-legacy/FastAAI
@@ -642,7 +643,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '2.7'
+      version: '3.1'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="