miga-base 1.3.5.0 → 1.3.6.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: d17244b326441f224e4626b53702018fd0f3915d44e16e9be939a70dd86ceefa
-  data.tar.gz: 8f6c7544ab57957dbfeb53230e56ba9e7eda37c7bab2fea538ee17d9f54fd9f7
+  metadata.gz: a9035e8f6ccd641c75bedc38b5f78d3eb1815c51956d399728b1e862c2920cbb
+  data.tar.gz: 2ffdecb639083a3a40d2bab3a39f1df92cb22279314ede2a5a843b278c8be9ee
 SHA512:
-  metadata.gz: bd77962a43caa04c72d01ddbe251fb02650f0f003c55b2b13a44ac1affb77b52535e5dd5fd7713c387f5a7bafdd8839255f2cd8d82be8d4c025b562a7beabfbd
-  data.tar.gz: b0cd50e25aa16ce2c64202daa5bbbb256e3f83742513ac984715f1b7c96f7297887856a2853ac6ec49dd43fe63b5c37cd96e83f8047ebcd32fdbc47addf892f7
+  metadata.gz: 42db29082a3b8097f8ec6f55839202d79e8d00496d55bab8093e4355a26f9133249506266e7f0eb64acea18fb91885abc493a0fe92c81c0eef27ec11f08d3eff
+  data.tar.gz: 5b4ce9ae27ac4542e2af836176dde909f013461b9916f1d1f4cfc0831d6e494d5de76c57d9c7b64ebd87aefd21a2c79edf55a0192838b6e589be21e9e5a4ebb1

data/lib/miga/cli/action/{get_db.rb → db.rb}

@@ -4,12 +4,12 @@
 require 'miga/cli/action'
 require 'digest/md5'
 
-class MiGA::Cli::Action::GetDb < MiGA::Cli::Action
+class MiGA::Cli::Action::Db < MiGA::Cli::Action
   def parse_cli
     cli.defaults = {
       database: :recommended,
       version: :latest,
-      local: File.expand_path('.miga_db', ENV['MIGA_HOME']),
+      local: File.join(ENV['MIGA_HOME'], '.miga_db'),
       host: MiGA::MiGA.known_hosts(:miga_db),
       pb: true,
       reuse_archive: false,
@@ -40,6 +40,10 @@ class MiGA::Cli::Action::GetDb < MiGA::Cli::Action
         '--list-versions',
         'List available versions of the database and exit'
       ) { |v| cli[:list_versions] = v }
+      opt.on(
+        '--list-local',
+        'List only the versions of the local databases (if any) and exit'
+      ) { |v| cli[:list_local] = v }
       opt.on(
         '--reuse-archive',
         'Reuse a previously downloaded archive if available'
@@ -48,6 +52,10 @@ class MiGA::Cli::Action::GetDb < MiGA::Cli::Action
         '--no-overwrite',
         'Exit without downloading if the target database already exists'
       ) { |v| cli[:overwrite] = v }
+      opt.on(
+        '--tab',
+        'Return a tab-delimited table'
+      ) { |v| cli[:tabular] = v }
       opt.on('--no-progress', 'Supress progress bars') { |v| cli[:pb] = v }
     end
   end
@@ -60,6 +68,12 @@ class MiGA::Cli::Action::GetDb < MiGA::Cli::Action
       return
     end
 
+    # If dealing with local checks only
+    if cli[:list_local]
+      list_local
+      return
+    end
+
     # Remote manifest
     @ftp = remote_connection
     manif = remote_manifest(@ftp)
@@ -89,6 +103,28 @@ class MiGA::Cli::Action::GetDb < MiGA::Cli::Action
 
   private
 
+  def list_local
+    local_manif = local_manifest
+    raise "Local manifest not found." unless local_manif
+    databases =
+      if %i[recommended test].include?(cli[:database])
+        local_manif[:databases].keys
+      else
+        [cli[:database].to_sym]
+      end
+    cli.table(
+      %w[database version genomes updated path],
+      databases.map do |db|
+        path = File.join(cli[:local], db.to_s)
+        p = MiGA::Project.load(path)
+        if p
+          md = p.metadata
+          [db, md[:release], md[:datasets].count, md[:updated], p.path]
+        end
+      end.compact
+    )
+  end
+
   def remote_connection
     cli.say "Connecting to '#{cli[:host]}'"
     MiGA::MiGA.remote_connection(cli[:host])
@@ -113,6 +149,11 @@ class MiGA::Cli::Action::GetDb < MiGA::Cli::Action
     MiGA::Json.parse(file)
   end
 
+  def local_manifest
+    file = File.join(cli[:local], '_local_manif.json')
+    MiGA::Json.parse(file) if File.exist?(file)
+  end
+
   def db_requested(manif)
     [:recommended, :test].each do |n|
       if cli[:database] == n
@@ -208,8 +249,7 @@ class MiGA::Cli::Action::GetDb < MiGA::Cli::Action
 
   def register_database(manif, db, ver)
     cli.say "Registering database locally"
-    local_manif = File.expand_path('_local_manif.json', cli[:local])
-    reg = File.exist?(local_manif) ? MiGA::Json.parse(local_manif) : {}
+    local_manif = local_manifest || {}
     reg[:last_update] = Time.now.to_s
     reg[:databases] ||= {}
     reg[:databases][cli[:database]] ||= {}

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

@@ -1,5 +1,19 @@
 
 module MiGA::Cli::Action::Doctor::Operations
+  ##
+  # Perform refdb operation with MiGA::Cli +cli+
+  def check_refdb(cli)
+    cli.say 'Checking index format of reference database'
+    ref_dbs = File.join(ENV['MIGA_HOME'], '.miga_db')
+    manif_file = File.join(ref_dbs, '_local_manif.json')
+    return unless File.size?(manif_file)
+
+    MiGA::Json.parse(manif_file)[:databases]&.keys&.each do |db|
+      p = MiGA::Project.load(File.join(ref_dbs, db.to_s))
+      md = p&.metadata
+    end
+  end
+
   ##
   # Perform status operation with MiGA::Cli +cli+
   def check_status(cli)

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

@@ -46,16 +46,18 @@ class MiGA::Cli::Action::Doctor < MiGA::Cli::Action
   end
 
   @@OPERATIONS = {
+    # TODO Implement this check:
+    # refdb:  ['ref-db', 'Check index format of reference databases'],
     status: ['status', 'Update metadata status of all datasets'],
-    db: ['databases', 'Check integrity of database files'],
-    bidir: ['bidirectional', 'Check distances are bidirectional'],
-    dist: ['distances', 'Check distance summary tables'],
-    files: ['files', 'Check for outdated files'],
-    cds: ['cds', 'Check for gzipped genes and proteins'],
-    ess: ['essential-genes', 'Check for outdated essential genes'],
-    mts: ['mytaxa-scan', 'Check for unarchived MyTaxa scan'],
-    start: ['start', 'Check for lingering .start files'],
-    tax: ['taxonomy', 'Check for taxonomy consistency (not yet implemented)']
+    db:     ['databases', 'Check integrity of database files'],
+    bidir:  ['bidirectional', 'Check distances are bidirectional'],
+    dist:   ['distances', 'Check distance summary tables'],
+    files:  ['files', 'Check for outdated files'],
+    cds:    ['cds', 'Check for gzipped genes and proteins'],
+    ess:    ['essential-genes', 'Check for outdated essential genes'],
+    mts:    ['mytaxa-scan', 'Check for unarchived MyTaxa scan'],
+    start:  ['start', 'Check for lingering .start files'],
+    tax:    ['taxonomy', 'Check for taxonomy consistency (not yet implemented)']
   }
 
   class << self

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

@@ -7,9 +7,9 @@ class MiGA::Cli::Action::Rm < MiGA::Cli::Action
   def parse_cli
     cli.defaults = { remove: false }
     cli.parse do |opt|
-      cli.opt_object(opt)
+      cli.opt_object(opt, %i[project dataset_opt result_opt])
       opt.on(
-        '-r', '--remove',
+        '-R', '--remove',
         'Also remove all associated files',
         'By default, only unlinks from metadata'
       ) { |v| cli[:remove] = v }
@@ -17,8 +17,13 @@ class MiGA::Cli::Action::Rm < MiGA::Cli::Action
   end
 
   def perform
-    d = cli.load_dataset
-    cli.load_project.unlink_dataset(d.name)
-    d.remove! if cli[:remove]
+    if r = cli.load_result
+      cli[:remove] ? r.remove! : r.unlink
+    elsif d = cli.load_dataset
+      cli.load_project.unlink_dataset(d.name)
+      d.remove! if cli[:remove]
+    else
+      raise "You must define one of --result or --dataset"
+    end
   end
 end

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

@@ -21,6 +21,10 @@ module MiGA::Cli::Action::Wf
       '-o', '--out_dir PATH',
       '(Mandatory) Directory to be created with all output data'
     ) { |v| cli[:outdir] = v }
+    opt.on(
+      '-P', '--project PATH',
+      '::HIDE::' # Applying the principle of least surprise, alias of -o
+    ) { |v| cli[:outdir] = v }
     opt.separator ''
     opt.separator "    FILES...: #{files_desc}"
     opt.separator ''

data/lib/miga/cli/base.rb

@@ -2,60 +2,61 @@
 
 module MiGA::Cli::Base
   @@TASK_DESC = {
-    generic: 'MiGA: The Microbial Genomes Atlas',
+    generic:     'MiGA: The Microbial Genomes Atlas',
     # Workflows
-    quality_wf: 'Evaluate the quality of input genomes',
-    derep_wf: 'Dereplicate a collection of input genomes',
+    quality_wf:  'Evaluate the quality of input genomes',
+    derep_wf:    'Dereplicate a collection of input genomes',
     classify_wf: 'Classify input genomes against a reference database',
-    preproc_wf: 'Preprocess input genomes or metagenomes',
-    index_wf: 'Generate distance indexing of input genomes',
+    preproc_wf:  'Preprocess input genomes or metagenomes',
+    index_wf:    'Generate distance indexing of input genomes',
     # Projects
-    new: 'Create an empty MiGA project',
-    about: 'Display information about a MiGA project',
-    doctor: 'Perform consistency checks on a MiGA project',
-    get_db: 'Download a pre-indexed database',
-    browse: 'Explore a project locally using a web browser',
+    new:         'Create an empty MiGA project',
+    about:       'Display information about a MiGA project',
+    doctor:      'Perform consistency checks on a MiGA project',
+    browse:      'Explore a project locally using a web browser',
     # Datasets
-    add: 'Create a dataset in a MiGA project',
-    get: 'Download a dataset from public databases into a MiGA project',
-    ncbi_get: 'Download all genomes in a taxon from NCBI into a MiGA project',
-    gtdb_get: 'Download all genomes in a taxon from GTDB into a MiGA project',
-    seqcode_get: 'Download all type genomes from SeqCode into a MiGA project',
-    rm: 'Remove a dataset from a MiGA project',
-    find: 'Find unregistered datasets based on result files',
-    ln: 'Link datasets (including results) from one project to another',
-    ls: 'List all registered datasets in a MiGA project',
-    archive: 'Generate a tar-ball with all files from select datasets',
+    add:         'Create a dataset in a MiGA project',
+    get:         'Download a dataset from public databases into a MiGA project',
+    ncbi_get:    'Download the genomes of a taxon from NCBI to a MiGA project',
+    gtdb_get:    'Download the genomes of a taxon from GTDB to a MiGA project',
+    seqcode_get: 'Download all type genomes from SeqCode to a MiGA project',
+    rm:          'Remove a dataset from a MiGA project',
+    find:        'Find unregistered datasets based on result files',
+    ln:          'Link datasets (incl. results) from one project to another',
+    ls:          'List all registered datasets in a MiGA project',
+    archive:     'Generate a tar-ball with all files from select datasets',
     # Results
-    add_result: 'Register a result',
-    stats: 'Extract statistics for the given result',
-    files: 'List registered files from the results of a dataset or project',
-    run: 'Execute locally one step analysis producing the given result',
-    summary: 'Generate a summary table for the statistics of all datasets',
-    next_step: 'Return the next task to run in a dataset or project',
+    add_result:  'Register a result',
+    stats:       'Extract statistics for the given result',
+    files:       'List registered files from a dataset or project',
+    run:         'Execute locally one step analysis producing the given result',
+    summary:     'Generate a summary table for the statistics of all datasets',
+    next_step:   'Return the next task to run in a dataset or project',
     # Objects (Datasets or Projects)
-    edit: 'Edit the metadata of a dataset or project',
-    option: 'Get or set options of a dataset or project',
-    touch: 'Change the "last modified" time to now without changes',
+    edit:        'Edit the metadata of a dataset or project',
+    option:      'Get or set options of a dataset or project',
+    touch:       'Change the "last modified" time to now without changes',
     # System
-    init: 'Initialize MiGA to process new projects',
-    daemon: 'Control the daemon of a MiGA project',
-    lair: 'Control groups of daemons for several MiGA projects',
-    date: 'Return the current date in standard MiGA format',
-    console: 'Open an IRB console with MiGA',
-    env: 'Shell code to load MiGA environment',
+    init:        'Initialize MiGA to process new projects',
+    daemon:      'Control the daemon of a MiGA project',
+    lair:        'Control groups of daemons for several MiGA projects',
+    db:          'Download a pre-indexed database',
+    date:        'Return the current date in standard MiGA format',
+    console:     'Open an IRB console with MiGA',
+    env:         'Shell code to load MiGA environment',
     # Taxonomy
-    tax_set: 'Register taxonomic information for datasets',
-    tax_test: 'Return test of taxonomic distributions for query datasets',
-    tax_index: 'Create a taxonomy-indexed list of the datasets',
-    tax_dist: 'Estimate distributions of distance by taxonomy',
+    tax_set:     'Register taxonomic information for datasets',
+    tax_test:    'Return test of taxonomic distributions for query datasets',
+    tax_index:   'Create a taxonomy-indexed list of the datasets',
+    tax_dist:    'Estimate distributions of distance by taxonomy',
   }
 
   @@TASK_ALIAS = {
     # Projects
     create_project: :new,
     project_info: :about,
-    download: :get_db,
+    download: :db,
+    get_db: :db,
     # Datasets
     create_dataset: :add,
     download_dataset: :get,

data/lib/miga/taxonomy.rb

@@ -137,6 +137,12 @@ class MiGA::Taxonomy < MiGA::MiGA
     self[:ns]
   end
 
+  ##
+  # Domain of the taxonomy (a String) or +nil+
+  def domain
+    self[:d]
+  end
+
   ##
   # Get the most general rank as a two-entry Array (rank and value).
   # If +force_ranks+ is true, it always returns the value for domain (d)

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, 5, 0].freeze
+  VERSION = [1.3, 6, 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(2023, 4, 21)
+  VERSION_DATE = Date.new(2023, 4, 25)
 
   ##
   # References of MiGA

data/scripts/aai_distances.bash

@@ -10,23 +10,31 @@ DIR="$PROJECT/data/09.distances/02.aai"
 miga_start_project_step "$DIR"
 
 # Extract values
-rm -f miga-project.txt
-SQL="SELECT seq1, seq2, aai, sd, n, omega from aai;"
-DS=$(miga ls -P "$PROJECT" --ref --no-multi --active)
-(
-  echo "a b value sd n omega" | tr " " "\\t"
-  for i in $DS ; do
-    echo "$SQL" | sqlite3 "$DIR/$i.db" | tr "\\|" "\\t"
+function foreach_database_aai {
+  local SQL="SELECT seq1, seq2, aai, sd, n, omega from aai;"
+  local k=0
+  while [[ -n ${DS[$k]} ]] ; do
+    echo "$SQL" | sqlite3 "$DIR/${DS[$k]}.db" | tr "\\|" "\\t"
+    let k=$k+1
   done
-  # The following block pipes retrieved data from all databases, reorganizes the
-  # names in cannonical order, and removes repeats from the first two columns,
-  # in order to keep only one result per pair. This is not being included into
-  # production, but the code may be useful for extremely large databases.
-  # | tee \
-  # | awk -F"\t" \
-  #   'BEGIN { OFS="\t" } { if($1 > $2) { a=$1; $1=$2; $2=a; } } { print $0 }' \
-  # | sort -k 1,2 -u
-) | gzip -9c > miga-project.txt.gz
+}
+
+function aai_tsv {
+  DS=($(miga ls -P "$PROJECT" --ref --no-multi --active))
+  echo "a b value sd n omega" | tr " " "\\t"
+  if [[ ${#DS[@]} -gt 40000 ]] ; then
+    # Use comparisons in strictly one direction only for huge projects
+    foreach_database_aai \
+      | awk -F"\t" 'BEGIN { OFS="\t" }
+          { if ($1 > $2) { a=$1; $1=$2; $2=a; } } { print $0 }' \
+      | sort -k 1,2 -u
+  else
+    foreach_database "$SQL"
+  fi
+}
+
+rm -f "miga-project.txt"
+aai_tsv | gzip -9c > "miga-project.txt.gz"
 
 # R-ify
 cat <<R | R --vanilla

data/scripts/distances.bash

@@ -9,7 +9,7 @@ cd "$PROJECT/data/09.distances"
 # Initialize
 miga date > "$DATASET.start"
 
-# Check quality first
+# Check quality
 miga stats -P "$PROJECT" -D "$DATASET" -r essential_genes --compute-and-save
 inactive=$(miga ls -P "$PROJECT" -D "$DATASET" -m inactive | cut -f 2)
 [[ "$inactive" == "true" ]] && exit

data/scripts/essential_genes.bash

@@ -12,7 +12,7 @@ FAA="../../../06.cds/${DATASET}.faa"
 [[ -s "$FAA" ]] || FAA="${FAA}.gz"
 
 # Check if there are any proteins
-if [[ ! -s $FAA ]] ; then
+if [[ ! -s "$FAA" ]] ; then
   echo Empty protein set, bypassing essential genes
   rm "${DATASET}.start"
   miga edit -P "$PROJECT" -D "$DATASET" -m run_essential_genes=false
@@ -35,13 +35,31 @@ HMM.essential.rb \
   -t "$CORES" -r "$DATASET" --collection "$COLL" $FLAGS \
   > "${DATASET}.ess/log"
 
-# Index for FastAAI
+# Index for FastAAI and classify (if needed and possible)
 NOMULTI=$(miga ls -P "$PROJECT" -D "$DATASET" --no-multi \
             | wc -l | awk '{print $1}')
-[[ "$NOMULTI" -eq "1" ]] && \
+if [[ "$NOMULTI" -eq "1" ]] ; then
   python3 "$MIGA/utils/FastAAI/fastaai/fastaai_miga_preproc.py" \
     --protein "$FAA" --output_crystal "${DATASET}.crystal" \
     --compress
+  
+  # Classify
+  DOMAIN=$(miga ls -P "$PROJECT" -D "$DATASET" -m tax:d | cut -f 2)
+  if [[ "$DOMAIN" == "?" ]] ; then
+    REF_PROJ=$(miga db --list-local -n Phyla_Lite --tab | tail -n +2 | cut -f 5)
+    echo "Phylum-level classification against $REF_PROJ"
+    if [[ -n "$REF_PROJ" ]] ; then
+      cp "${DATASET}.start" "${DATASET}.start.bak"
+      miga date > "${DATASET}.done"
+      miga add_result -P "$PROJECT" -D "$DATASET" -r "$SCRIPT" -f
+      ruby -I "$MIGA/lib" \
+        "$MIGA/utils/distances.rb" "$PROJECT" "$DATASET" \
+        run_taxonomy=1 only_domain=1 "ref_project=$REF_PROJ"
+      mv "${DATASET}.start.bak" "${DATASET}.start"
+      rm "${DATASET}.done" "${DATASET}.json"
+    fi
+  fi
+fi
 
 # Reduce files
 if exists "$DATASET".ess/*.faa ; then

data/utils/distance/database.rb

@@ -1,4 +1,4 @@
-require 'sqlite3'
+require 'miga/sqlite'
 
 module MiGA::DistanceRunner::Database
   ##
@@ -11,6 +11,8 @@ module MiGA::DistanceRunner::Database
     { haai: :aai, aai: :aai, ani: :ani }.each do |m, t|
       @db_counts[m] = 0
       @dbs[m] = for_ref ? ref_db(m) : query_db(m)
+      @tmp_dbs[m] = tmp_file("#{m}.db")
+
       # Remove if corrupt
       if File.size?(dbs[m])
         begin
@@ -21,9 +23,12 @@ module MiGA::DistanceRunner::Database
           FileUtils.rm dbs[m]
         end
       end
-      # Initialize if it doesn't exist
-      unless File.size? dbs[m]
-        SQLite3::Database.new(dbs[m]) do |conn|
+
+      # Initialize if it doesn't exist, copy otherwise
+      if File.size? dbs[m]
+        FileUtils.cp(dbs[m], tmp_dbs[m])
+      else
+        SQLite3::Database.new(tmp_dbs[m]) do |conn|
           conn.execute <<~SQL
             create table if not exists #{t}(
               seq1 varchar(256), seq2 varchar(256),
@@ -31,10 +36,8 @@ module MiGA::DistanceRunner::Database
             )
           SQL
         end
+        FileUtils.cp(tmp_dbs[m], dbs[m]) unless opts[:only_domain]
       end
-      # Copy over to (local) temporals
-      @tmp_dbs[m] = tmp_file("#{m}.db")
-      FileUtils.cp(dbs[m], tmp_dbs[m])
     end
   end
 
@@ -157,6 +160,20 @@ module MiGA::DistanceRunner::Database
       conn.execute(sql).each { |row| data[row.shift] = row }
     end
     data
+  rescue => e
+    $stderr.puts "Database file: #{db}" if db ||= nil
+    raise e
+  end
+
+  ##
+  # Retrieve the name and AAI of the closest relative from the AAI database
+  def closest_relative
+    db = tmp_dbs[:aai]
+    sql = 'select seq2, aai from aai order by aai desc limit 1'
+    MiGA::SQLite.new(db).run(sql).first
+  rescue => e
+    $stderr.puts "Database file: #{db}" if db ||= nil
+    raise e
   end
 
   ##

data/utils/distance/pipeline.rb

@@ -72,22 +72,13 @@ module MiGA::DistanceRunner::Pipeline
     $stderr.puts "Testing taxonomy | opts = #{opts}"
     # Get taxonomy of closest relative
     from_ref_project = (project != ref_project)
-    res_dir =
-      from_ref_project ?
-        File.expand_path('data/09.distances/05.taxonomy', project.path) :
-        home
-    Dir.mkdir res_dir unless Dir.exist? res_dir
-    File.open(File.expand_path("#{dataset.name}.done", res_dir), 'w') do |fh|
-      fh.puts Time.now.to_s
-    end
-    dataset.add_result(from_ref_project ? :taxonomy : :distances, true)
-    cr = dataset.closest_relatives(1, from_ref_project)
+    cr = closest_relative
     return if cr.nil? or cr.empty?
 
-    tax = ref_project.dataset(cr[0][0]).metadata[:tax] || {}
+    tax = ref_project.dataset(cr[0]).metadata[:tax] || {}
 
     # Run the test for each rank
-    tax_test = MiGA::TaxDist.aai_pvalues(cr[0][1], :intax, engine: opts[:aai_p])
+    tax_test = MiGA::TaxDist.aai_pvalues(cr[1], :intax, engine: opts[:aai_p])
     r = tax_test.map do |k, v|
       sig = ''
       [0.5, 0.1, 0.05, 0.01].each { |i| sig << '*' if v < i }
@@ -95,12 +86,14 @@ module MiGA::DistanceRunner::Pipeline
     end
 
     # Save test
-    File.open(File.expand_path("#{dataset.name}.intax.txt", home), 'w') do |fh|
-      fh.puts "Closest relative: #{cr[0][0]} with AAI: #{cr[0][1]}."
-      fh.puts ''
-      fh.puts MiGA::MiGA.tabulate(%w[Rank Taxonomy P-value Signif.], r)
-      fh.puts ''
-      fh.puts 'Significance at p-value below: *0.5, **0.1, ***0.05, ****0.01.'
+    unless opts[:only_domain]
+      File.open(File.join(home, "#{dataset.name}.intax.txt"), 'w') do |fh|
+        fh.puts "Closest relative: #{cr[0]} with AAI: #{cr[1]}."
+        fh.puts ''
+        fh.puts MiGA::MiGA.tabulate(%w[Rank Taxonomy P-value Signif.], r)
+        fh.puts ''
+        fh.puts 'Significance at p-value below: *0.5, **0.1, ***0.05, ****0.01.'
+      end
     end
     return r
   end
@@ -115,6 +108,7 @@ module MiGA::DistanceRunner::Pipeline
             .select { |i| i[1] != '?' && i[2] <= pval }
             .map { |i| i[0, 2].join(':') }
     dataset.metadata[:tax] = MiGA::Taxonomy.new(tax_a)
+    $stderr.puts " > #{dataset.metadata[:tax]}"
     dataset.save
   end
 end

data/utils/distance/runner.rb

@@ -12,8 +12,9 @@ class MiGA::DistanceRunner
     @home = File.expand_path('data/09.distances', project.path)
 
     # Default opts
-    if opts[:run_taxonomy] && project.option(:ref_project)
-      ref_path = project.option(:ref_project)
+    if opts[:run_taxonomy] &&
+          (opts[:ref_project] || project.option(:ref_project))
+      ref_path = opts[:ref_project] || project.option(:ref_project)
       @home = File.expand_path('05.taxonomy', @home)
       @ref_project = MiGA::Project.load(ref_path)
       raise "Cannot load reference project: #{ref_path}" if @ref_project.nil?
@@ -73,48 +74,55 @@ class MiGA::DistanceRunner
     # Initialize the databases
     initialize_dbs! false
     distances_by_request(tsk[1])
+
     # Calculate the classification-informed AAI/ANI traverse
-    results = File.expand_path("#{dataset.name}.#{tsk[1]}-medoids.tsv", home)
-    fh = File.open(results, 'w')
+    tmp_results = tmp_file("#{tsk[1]}-medoids.tsv")
+    fh = File.open(tmp_results, 'w')
     classif, val_cls = *classify(res.dir, '.', tsk[1], fh)
     fh.close
 
-    # Calculate all the AAIs/ANIs against the lowest subclade (if classified)
-    par_dir = File.dirname(File.expand_path(classif, res.dir))
-    par = File.expand_path('miga-project.classif', par_dir)
-    closest = { dataset: nil, ani: 0.0 }
-    sbj_datasets = []
-    if File.size? par
-      File.open(par, 'r') do |fh|
-        fh.each_line do |ln|
-          r = ln.chomp.split("\t")
-          sbj_datasets << ref_project.dataset(r[0]) if r[1].to_i == val_cls
+    unless opts[:only_domain]
+      results = File.join(home, "#{dataset.name}.#{tsk[1]}-medoids.tsv")
+      FileUtils.move(tmp_results, results)
+
+      # Calculate all the AAIs/ANIs against the lowest subclade (if classified)
+      par_dir = File.dirname(File.expand_path(classif, res.dir))
+      par = File.expand_path('miga-project.classif', par_dir)
+      closest = { dataset: nil, ani: 0.0 }
+      sbj_datasets = []
+      if File.size? par
+        File.open(par, 'r') do |fh|
+          fh.each_line do |ln|
+            r = ln.chomp.split("\t")
+            sbj_datasets << ref_project.dataset(r[0]) if r[1].to_i == val_cls
+          end
         end
+        ani = ani_after_aai(sbj_datasets, 80.0)
+        ani_max = ani.map(&:to_f).each_with_index.max
+        closest = { ds: sbj_datasets[ani_max[1]].name, ani: ani_max[0] }
       end
-      ani = ani_after_aai(sbj_datasets, 80.0)
-      ani_max = ani.map(&:to_f).each_with_index.max
-      closest = { ds: sbj_datasets[ani_max[1]].name, ani: ani_max[0] }
-    end
 
-    # Calculate all the AAIs/ANIs against the closest ANI95-clade (if AAI > 80%)
-    cl_path = res.file_path :clades_ani95
-    if !cl_path.nil? && File.size?(cl_path) && tsk[0] == :clade_finding
-      clades = File.foreach(cl_path).map { |i| i.chomp.split(',') }
-      sbj_dataset_names = clades.find { |i| i.include?(closest[:ds]) }
-      sbj_datasets = sbj_dataset_names&.map { |i| ref_project.dataset(i) }
-      ani_after_aai(sbj_datasets, 80.0) if sbj_datasets
+      # Calculate all the AAIs/ANIs against the closest ANI95-clade
+      # (if AAI > 80%)
+      cl_path = res.file_path :clades_ani95
+      if !cl_path.nil? && File.size?(cl_path) && tsk[0] == :clade_finding
+        clades = File.foreach(cl_path).map { |i| i.chomp.split(',') }
+        sbj_dataset_names = clades.find { |i| i.include?(closest[:ds]) }
+        sbj_datasets = sbj_dataset_names&.map { |i| ref_project.dataset(i) }
+        ani_after_aai(sbj_datasets, 80.0) if sbj_datasets
+      end
     end
 
     # Finalize
     [:haai, :aai, :ani].each { |m| checkpoint! m if db_counts[m] > 0 }
-    build_medoids_tree(tsk[1])
+    build_medoids_tree(tsk[1]) unless opts[:only_domain]
     transfer_taxonomy(tax_test)
   end
 
   # Launch analysis for taxonomy jobs
   def go_taxonomy!
     $stderr.puts 'Launching taxonomy analysis'
-    return unless project.option(:ref_project)
+    return unless opts[:ref_project] || project.option(:ref_project)
 
     go_query! # <- yeah, it's actually the same, just different ref_project
   end

data/utils/distance/temporal.rb

@@ -41,6 +41,7 @@ module MiGA::DistanceRunner::Temporal
 
   # Copies temporal databases back to the MiGA Project
   def checkpoint!(metric)
+    return if opts[:only_domain]
     $stderr.puts "Checkpoint (metric = #{metric})"
 
     # This is simply to test database consistency before overwriting the

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: miga-base
 version: !ruby/object:Gem::Version
-  version: 1.3.5.0
+  version: 1.3.6.0
 platform: ruby
 authors:
 - Luis M. Rodriguez-R
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2023-04-21 00:00:00.000000000 Z
+date: 2023-04-25 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: daemons
@@ -152,6 +152,7 @@ files:
 - lib/miga/cli/action/console.rb
 - lib/miga/cli/action/daemon.rb
 - lib/miga/cli/action/date.rb
+- lib/miga/cli/action/db.rb
 - lib/miga/cli/action/derep_wf.rb
 - lib/miga/cli/action/doctor.rb
 - lib/miga/cli/action/doctor/base.rb
@@ -168,7 +169,6 @@ files:
 - lib/miga/cli/action/find.rb
 - lib/miga/cli/action/generic.rb
 - lib/miga/cli/action/get.rb
-- lib/miga/cli/action/get_db.rb
 - lib/miga/cli/action/gtdb_get.rb
 - lib/miga/cli/action/index_wf.rb
 - lib/miga/cli/action/init.rb