miga-base 0.2.0.6 → 0.2.0.7

data/lib/miga/dataset.rb

@@ -1,286 +1,363 @@
-#
 # @package MiGA
-# @author  Luis M. Rodriguez-R <lmrodriguezr at gmail dot com>
-# @license artistic license 2.0
-# @update  Jan-18-2016
-#
+# @license Artistic-2.0
 
 require "miga/metadata"
-require "miga/project"
 require "miga/result"
 
-module MiGA
-   class Dataset
-      # Class
-      @@RESULT_DIRS = {
-	 # Preprocessing
-	 raw_reads: "01.raw_reads", trimmed_reads: "02.trimmed_reads",
-	 read_quality: "03.read_quality", trimmed_fasta: "04.trimmed_fasta",
-	 assembly: "05.assembly", cds: "06.cds",
-	 # Annotation
-	 essential_genes: "07.annotation/01.function/01.essential",
-	 ssu: "07.annotation/01.function/02.ssu",
-	 mytaxa: "07.annotation/02.taxonomy/01.mytaxa",
-	 mytaxa_scan: "07.annotation/03.qa/02.mytaxa_scan",
-	 # Mapping
-	 mapping_on_contigs: "08.mapping/01.read-ctg",
-	 mapping_on_genes: "08.mapping/02.read-gene",
-	 # Distances (for single-species datasets)
-	 distances: "09.distances"
-      }
-      @@KNOWN_TYPES = {
-         genome: {description: "The genome from an isolate.", multi: false},
-	 metagenome: {description: "A metagenome (excluding viromes).",
-	    multi: true},
-	 virome: {description: "A viral metagenome.", multi: true},
-	 scgenome: {description: "A genome from a single cell.", multi: false},
-	 popgenome: {description: "The genome of a population (including " +
-	    "microdiversity).", :multi=>false}
-      }
-      @@PREPROCESSING_TASKS = [:raw_reads, :trimmed_reads, :read_quality,
-	 :trimmed_fasta, :assembly, :cds, :essential_genes, :ssu, :mytaxa,
-	 :mytaxa_scan, :distances]
-      @@EXCLUDE_NOREF_TASKS = [:essential_genes, :mytaxa_scan]
-      @@ONLY_NONMULTI_TASKS = [:mytaxa_scan, :distances]
-      @@ONLY_MULTI_TASKS = [:mytaxa]
-      def self.PREPROCESSING_TASKS ; @@PREPROCESSING_TASKS ; end
-      def self.RESULT_DIRS ; @@RESULT_DIRS end
-      def self.KNOWN_TYPES ; @@KNOWN_TYPES end
-      def self.exist?(project, name)
-	 File.exist? project.path + "/metadata/" + name + ".json"
-      end
-      def self.INFO_FIELDS
-	 %w(name created updated type ref user description comments)
-      end
-      # Instance
-      attr_reader :project, :name, :metadata
-      def initialize(project, name, is_ref=true, metadata={})
-	 abort "Invalid name '#{name}', please use only alphanumerics and " +
-	    "underscores." unless name.miga_name?
-	 @project = project
-	 @name = name
-	 metadata[:ref] = is_ref
-	 @metadata = Metadata.new(project.path + "/metadata/" + name + ".json",
-	    metadata)
-      end
-      def save
-	 self.metadata[:type] = :metagenome if !metadata[:tax].nil? and
-	    !metadata[:tax][:ns].nil? and
-	    metadata[:tax][:ns]=="COMMUNITY"
-	 self.metadata.save
-	 self.load
-      end
-      def load
-         # Nothing here...
-      end
-      def remove!
-         self.results.each{ |r| r.remove! }
-	 self.metadata.remove!
-      end
-      def info()
-	 Dataset.INFO_FIELDS.map do |k|
-	    (k=="name") ? self.name : self.metadata[k.to_sym]
-	 end
-      end
-      def is_ref?() !!self.metadata[:ref] end
-      def is_multi?
-	 return false if self.metadata[:type].nil?
-	 return @@KNOWN_TYPES[self.metadata[:type]][:multi]
-      end
-      def is_nonmulti?
-	 return false if self.metadata[:type].nil?
-	 return !@@KNOWN_TYPES[self.metadata[:type]][:multi]
-      end
-      def result(k)
-	 return nil if @@RESULT_DIRS[k.to_sym].nil?
-	 Result.load(project.path + "/data/" + @@RESULT_DIRS[k.to_sym] +
-	    "/" + name + ".json")
-      end
-      def results() @@RESULT_DIRS.keys.map{ |k| self.result k }.compact end
-      def each_result(&blk)
-         @@RESULT_DIRS.keys.each do |k|
-	    v = self.result k
-	    blk.call(k,v) unless v.nil?
-	 end
-      end
-      def add_result result_type
-	 return nil if @@RESULT_DIRS[result_type].nil?
-	 base = project.path + "/data/" + @@RESULT_DIRS[result_type] +
-	    "/" + name
-	 return nil unless File.exist? base + ".done"
-	 r = nil
-	 case result_type
-	 when :raw_reads
-	    return nil unless
-	       File.exist? base + ".1.fastq" or
-	       File.exist? base + ".1.fastq.gz"
-	    r = Result.new base + ".json"
-	    r.data[:gz] = File.exist?(base + ".1.fastq.gz")
-	    if File.exist? base + ".2.fastq" + (r.data[:gz] ? ".gz" : "")
-	       r.add_file :pair1, name + ".1.fastq"
-	       r.add_file :pair2, name + ".2.fastq"
-	    else
-	       r.add_file :single, name + ".1.fastq"
-	    end
-	 when :trimmed_reads
-	    return nil unless
-	       File.exist?(base + ".1.clipped.fastq") or
-	       File.exist?(base + ".1.clipped.fastq.gz")
-	    r = Result.new base + ".json"
-	    r.data[:gz] = File.exist?(base + ".1.clipped.fastq.gz")
-	    if File.exist? base + ".2.clipped.fastq" + (r.data[:gz] ? ".gz":"")
-	       r.add_file :pair1, name + ".1.clipped.fastq"
-	       r.add_file :pair2, name + ".2.clipped.fastq"
-	    end
-	    r.add_file :single, name + ".1.clipped.single.fastq"
-	    add_result :raw_reads #-> Post gunzip (if any)
-	 when :read_quality
-	    return nil unless
-	       Dir.exist?(base + ".solexaqa") and
-	       Dir.exist?(base + ".fastqc")
-	    r = Result.new base + ".json"
-	    r.add_file :solexaqa, self.name + ".solexaqa"
-	    r.add_file :fastqc, self.name + ".fastqc"
-	    add_result :trimmed_reads #-> Post cleaning
-	 when :trimmed_fasta
-	    return nil unless
-	       File.exist?(base + ".CoupledReads.fa") or
-	       File.exist?(base + ".SingleReads.fa")
-	    r = Result.new base + ".json"
-	    if File.exist?(base + ".CoupledReads.fa")
-	       r.add_file :coupled, name + ".CoupledReads.fa"
-	       r.add_file :pair1, name + ".1.fa"
-	       r.add_file :pair2, name + ".2.fa"
-	    end
-	    r.add_file :single, name + ".SingleReads.fa"
-	    add_result :raw_reads #-> Post gzip
-	 when :assembly
-	    return nil unless
-	       File.exist?(base + ".LargeContigs.fna")
-	    r = Result.new base + ".json"
-	    r.add_file :largecontigs, name + ".LargeContigs.fna"
-	    r.add_file :allcontigs, name + ".AllContigs.fna"
-	 when :cds
-	    return nil unless
-	       File.exist?(base + ".faa") and
-	       File.exist?(base + ".fna")
-	    r = Result.new base + ".json"
-	    r.add_file :proteins, name + ".faa"
-	    r.add_file :genes, name + ".fna"
-	    %w(gff2 gff3 tab).each do |ext|
-	       r.add_file ext, "#{name}.#{ext}"
-	    end
-	 when :essential_genes
-	    return nil unless
-	       File.exist?(base + ".ess.faa") and
-	       Dir.exist?(base + ".ess") and
-	       File.exist?(base + ".ess/log")
-	    r = Result.new base + ".json"
-	    r.add_file :ess_genes, name + ".ess.faa"
-	    r.add_file :collection, name + ".ess"
-	    r.add_file :report, name + ".ess/log"
-	 when :ssu
-	    if result(:assembly).nil?
-	       r = Result.new base + ".json"
-	    else
-	       return nil unless
-		  File.exist?(base + ".ssu.fa") or
-		  File.exist?(base + ".ssu.fa.gz")
-	       r = Result.new base + ".json"
-	       r.data[:gz] = File.exist?(base + ".ssu.fa.gz")
-	       r.add_file :longest_ssu_gene, name + ".ssu.fa"
-	       r.add_file :gff, name + ".ssu.gff"
-	       r.add_file :all_ssu_genes, name + ".ssu.all.fa"
-	    end
-	 when :mytaxa
-	    if is_multi?
-	       return nil unless File.exist?(base + ".mytaxa")
-	       r = Result.new base + ".json"
-	       r.data[:gz] = File.exist?(base + ".mytaxain.gz")
-	       r.add_file :mytaxa, name + ".mytaxa"
-	       r.add_file :blast, name + ".blast"
-	       r.add_file :mytaxain, name + ".mytaxain"
-	    else
-	       r = Result.new base + ".json"
-	       r.data[:files] = {}
-	    end
-	 when :mytaxa_scan
-	    if is_nonmulti?
-	       return nil unless
-		  File.exists?(base + ".pdf") and
-		  File.exist?(base + ".wintax") and
-		  File.exist?(base + ".mytaxa") and
-		  Dir.exist?(base + ".reg")
-	       r = Result.new base + ".json"
-	       r.add_file :mytaxa, name + ".mytaxa"
-	       r.add_file :wintax, name + ".wintax"
-	       r.add_file :report, name + ".pdf"
-	       r.add_file :regions, name + ".reg"
-	       r.add_file :gene_ids, name + ".wintax.genes"
-	       r.add_file :region_ids, name + ".wintax.regions"
-	       r.add_file :blast, name + ".blast"
-	       r.add_file :mytaxain, name + ".mytaxain"
-	    else
-	       r = Result.new base + ".json"
-	       r.data[:files] = {}
-	    end
-	 when :distances
-	    if is_nonmulti?
-	       pref = project.path + "/data/" + @@RESULT_DIRS[result_type]
-	       if is_ref?
-		  return nil unless
-		     File.exist?(pref + "/01.haai/" + name + ".db")
-	       else
-		  return nil unless
-		     File.exist?(pref + "/02.aai/" + name + ".db")
-	       end
-	       r = Result.new base + ".json"
-	       r.add_file :haai_db, "01.haai/" + name + ".db"
-	       r.add_file :aai_db, "02.aai/" + name + ".db"
-	       r.add_file :ani_db, "03.ani/" + name + ".db"
-	    else
-	       r = Result.new base + ".json"
-	       r.data[:files] = {}
-	    end
-	 end
-	 r.save
-	 r
-      end # def add_result
-      def first_preprocessing
-	 @@PREPROCESSING_TASKS.find{ |t| not self.add_result(t).nil? }
-      end
-      def next_preprocessing
-         after_first = false
-	 first = self.first_preprocessing
-	 return nil if first.nil?
-	 @@PREPROCESSING_TASKS.each do |t|
-	    next if @@EXCLUDE_NOREF_TASKS.include?(t) and not is_ref?
-	    next if @@ONLY_MULTI_TASKS.include?(t) and not is_multi?
-	    next if @@ONLY_NONMULTI_TASKS.include?(t) and not is_nonmulti?
-	    return t if after_first and add_result(t).nil?
-	    after_first = (after_first or (t==first))
-	 end
-	 nil
+##
+# Dataset representation in MiGA.
+class MiGA::Dataset < MiGA::MiGA
+  
+  # Class-level
+
+  ##
+  # Directories containing the results from dataset-specific tasks.
+  def self.RESULT_DIRS ; @@RESULT_DIRS end
+  @@RESULT_DIRS = {
+    # Preprocessing
+    raw_reads: "01.raw_reads", trimmed_reads: "02.trimmed_reads",
+    read_quality: "03.read_quality", trimmed_fasta: "04.trimmed_fasta",
+    assembly: "05.assembly", cds: "06.cds",
+    # Annotation
+    essential_genes: "07.annotation/01.function/01.essential",
+    ssu: "07.annotation/01.function/02.ssu",
+    mytaxa: "07.annotation/02.taxonomy/01.mytaxa",
+    mytaxa_scan: "07.annotation/03.qa/02.mytaxa_scan",
+    # Mapping
+    mapping_on_contigs: "08.mapping/01.read-ctg",
+    mapping_on_genes: "08.mapping/02.read-gene",
+    # Distances (for single-species datasets)
+    distances: "09.distances"
+  }
+
+  ##
+  # Supported dataset types.
+  def self.KNOWN_TYPES ; @@KNOWN_TYPES end
+  @@KNOWN_TYPES = {
+    genome: {description: "The genome from an isolate.", multi: false},
+    metagenome: {description: "A metagenome (excluding viromes).",
+      multi: true},
+    virome: {description: "A viral metagenome.", multi: true},
+    scgenome: {description: "A genome from a single cell.", multi: false},
+    popgenome: {description: "The genome of a population (including " +
+      "microdiversity).", :multi=>false}
+  }
+
+  ##
+  # Returns an Array of tasks to be executed before project-wide tasks.
+  def self.PREPROCESSING_TASKS ; @@PREPROCESSING_TASKS ; end
+  @@PREPROCESSING_TASKS = [:raw_reads, :trimmed_reads, :read_quality,
+    :trimmed_fasta, :assembly, :cds, :essential_genes, :ssu, :mytaxa,
+    :mytaxa_scan, :distances]
+  
+  ##
+  # Tasks to be excluded from query datasets.
+  @@EXCLUDE_NOREF_TASKS = [:essential_genes, :mytaxa_scan]
+  
+  ##
+  # Tasks to be executed only in datasets that are not multi-organism. These
+  # tasks are ignored for multi-organism datasets or for unknown types.
+  @@ONLY_NONMULTI_TASKS = [:mytaxa_scan, :distances]
+
+  ##
+  # Tasks to be executed only in datasets that are multi-organism. These
+  # tasks are ignored for single-organism datasets or for unknwon types.
+  @@ONLY_MULTI_TASKS = [:mytaxa]
+
+  ##
+  # Does the +project+ already have a dataset with that +name+?
+  def self.exist?(project, name)
+    File.exist? project.path + "/metadata/" + name + ".json"
+  end
+
+  ##
+  # Standard fields of metadata for datasets.
+  def self.INFO_FIELDS
+    %w(name created updated type ref user description comments)
+  end
+
+  # Instance-level
+
+  ##
+  # MiGA::Project that contains the dataset.
+  attr_reader :project
+  
+  ##
+  # Datasets are uniquely identified by +name+ in a project.
+  attr_reader :name
+  
+  ##
+  # MiGA::Metadata with information about the dataset.
+  attr_reader :metadata
+  
+  ##
+  # Create a MiGA::Dataset object in a +project+ MiGA::Project with a
+  # uniquely identifying +name+. +is_ref+ indicates if the dataset is to
+  # be treated as reference (true, default) or query (false). Pass any
+  # additional +metadata+ as a Hash.
+  def initialize(project, name, is_ref=true, metadata={})
+    raise "Invalid name '#{name}', please use only alphanumerics and " +
+      "underscores." unless name.miga_name?
+    @project = project
+    @name = name
+    metadata[:ref] = is_ref
+    @metadata = MiGA::Metadata.new(project.path + "/metadata/" + name + ".json",
+      metadata)
+  end
+  
+  ##
+  # Save any changes you've made in the dataset.
+  def save
+    self.metadata[:type] = :metagenome if !metadata[:tax].nil? and
+      !metadata[:tax][:ns].nil? and metadata[:tax][:ns]=="COMMUNITY"
+    self.metadata.save
+  end
+  
+  ##
+  # Delete the dataset with all it's contents (including results) and returns
+  # nil.
+  def remove!
+    self.results.each{ |r| r.remove! }
+    self.metadata.remove!
+  end
+  
+  ##
+  # Get standard metadata values for the dataset as Array.
+  def info
+    MiGA::Dataset.INFO_FIELDS.map do |k|
+      (k=="name") ? self.name : self.metadata[k.to_sym]
+    end
+  end
+  
+  ##
+  # Is this dataset a reference?
+  def is_ref? ; !!self.metadata[:ref] ; end
+  
+  ##
+  # Is this dataset known to be multi-organism?
+  def is_multi?
+    return false if self.metadata[:type].nil?
+    return @@KNOWN_TYPES[self.metadata[:type]][:multi]
+  end
+  
+  ##
+  # Is this dataset known to be single-organism?
+  def is_nonmulti?
+    return false if self.metadata[:type].nil?
+    return !@@KNOWN_TYPES[self.metadata[:type]][:multi]
+  end
+  
+  ##
+  # Get the result MiGA::Result in this dataset identified by the symbol +k+.
+  def result(k)
+    return nil if @@RESULT_DIRS[k.to_sym].nil?
+    MiGA::Result.load(project.path + "/data/" + @@RESULT_DIRS[k.to_sym] +
+      "/" + name + ".json")
+  end
+  
+  ##
+  # Get all the results (Array of MiGA::Result) in this dataset.
+  def results ; @@RESULT_DIRS.keys.map{ |k| result k }.compact ; end
+  
+  ##
+  # For each result executes the 2-ary +blk+ block: key symbol and MiGA::Result.
+  def each_result(&blk)
+    @@RESULT_DIRS.keys.each do |k|
+      blk.call(k, result(k)) unless result(k).nil?
+    end
+  end
+  
+  ##
+  # Look for the result with symbol key +result_type+ and register it in the
+  # dataset. If +save+ is false, it doesn't register the result, but it still
+  # returns a result if the expected files are complete. Returns MiGA::Result
+  # or nil.
+  def add_result(result_type, save=true)
+    return nil if @@RESULT_DIRS[result_type].nil?
+    base = project.path + "/data/" + @@RESULT_DIRS[result_type] +
+      "/" + name
+    return MiGA::Result.load(base + ".json") unless save
+    return nil unless result_files_exist?(base, ".done")
+    r = self.send("add_result_#{result_type}", base)
+    r.save unless r.nil?
+    r
+  end
+
+  ##
+  # Returns the key symbol of the first registered result (sorted by the
+  # execution order). This typically corresponds to the result used as the
+  # initial input. Passes +save+ to #add_result.
+  def first_preprocessing(save=false)
+    @@PREPROCESSING_TASKS.find{ |t| not add_result(t, save).nil? }
+  end
+  
+  ##
+  # Returns the key symbol of the next task that needs to be executed. Passes
+  # +save+ to #add_result.
+  def next_preprocessing(save=false)
+    after_first = false
+    first = first_preprocessing(save)
+    return nil if first.nil?
+    @@PREPROCESSING_TASKS.each do |t|
+      next if ignore_task? t
+      return t if after_first and add_result(t, save).nil?
+      after_first = (after_first or (t==first))
+    end
+    nil
+  end
+
+  ##
+  # Should I ignore +task+ for this dataset?
+  def ignore_task?(task)
+    ( (@@EXCLUDE_NOREF_TASKS.include?(task) and not is_ref?) or
+      (@@ONLY_MULTI_TASKS.include?(task) and not is_multi?) or
+      (@@ONLY_NONMULTI_TASKS.include?(task) and not is_nonmulti?))
+  end
+  
+  ##
+  # Are all the dataset-specific tasks done? Passes +save+ to #add_result.
+  def done_preprocessing?(save=false)
+    !first_preprocessing(save).nil? and next_preprocessing(save).nil?
+  end
+  
+  ##
+  # Returns an array indicating the stage of each task (sorted by execution
+  # order). The values are integers:
+  # - 0 for an undefined result (a task before the initial input).
+  # - 1 for a registered result (a completed task).
+  # - 2 for a queued result (a task yet to be executed).
+  # It passes +save+ to #add_result
+  def profile_advance(save=false)
+    first_task = first_preprocessing(save)
+    return Array.new(@@PREPROCESSING_TASKS.size, 0) if first_task.nil?
+    adv = []
+    state = 0
+    next_task = next_preprocessing(save)
+    @@PREPROCESSING_TASKS.each do |task|
+      state = 1 if first_task==task
+      state = 2 if !next_task.nil? and next_task==task
+      adv << state
+    end
+    adv
+  end
+
+  private
+    
+    def add_result_raw_reads(base)
+      return nil unless result_files_exist?(base, ".1.fastq")
+      r = MiGA::Result.new(base + ".json")
+      add_files_to_ds_result(r, name,
+        ( result_files_exist?(base, ".2.fastq") ?
+          {:pair1=>".1.fastq", :pair2=>".2.fastq"} :
+          {:single=>".1.fastq"} ))
+    end
+
+    def add_result_trimmed_reads(base)
+      return nil unless result_files_exist?(base, ".1.clipped.fastq")
+      r = MiGA::Result.new base + ".json"
+      r = add_files_to_ds_result(r, name,
+        {:pair1=>".1.clipped.fastq", :pair2=>".2.clipped.fastq"}) if
+        result_files_exist?(base, ".2.clipped.fastq")
+      r.add_file(:single, name + ".1.clipped.single.fastq")
+      add_result(:raw_reads) #-> Post gunzip
+      r
+    end
+
+    def add_result_read_quality(base)
+      return nil unless result_files_exist?(base, %w[.solexaqa .fastqc])
+      r = MiGA::Result.new(base + ".json")
+      r = add_files_to_ds_result(r, name,
+        {:solexaqa=>".solexaqa", :fastqc=>".fastqc"})
+      add_result(:trimmed_reads) #-> Post cleaning
+      r
+    end
+
+    def add_result_trimmed_fasta(base)
+      return nil unless
+        result_files_exist?(base, ".CoupledReads.fa") or
+        result_files_exist?(base, ".SingleReads.fa")
+      r = MiGA::Result.new base + ".json"
+      r = add_files_to_ds_result(r, name, {:coupled=>".CoupledReads.fa",
+        :pair1=>".1.fa", :pair2=>".2.fa"}) if
+        result_files_exist?(base, ".CoupledReads.fa")
+      r.add_file(:single, name + ".SingleReads.fa")
+      add_result(:raw_reads) #-> Post gzip
+      r
+    end
+
+    def add_result_assembly(base)
+      return nil unless result_files_exist?(base, ".LargeContigs.fna")
+      r = MiGA::Result.new(base + ".json")
+      add_files_to_ds_result(r, name, {:largecontigs=>".LargeContigs.fna",
+        :allcontigs=>".AllContigs.fna"})
+    end
+
+    def add_result_cds(base)
+      return nil unless result_files_exist?(base, %w[.faa .fna])
+      r = MiGA::Result.new(base + ".json")
+      add_files_to_ds_result(r, name, {:proteins=>".faa", :genes=>".fna",
+        :gff2=>".gff2", :gff3=>".gff3", :tab=>".tab"})
+    end
+
+    def add_result_essential_genes(base)
+      return nil unless result_files_exist?(base, %w[.ess.faa .ess .ess/log])
+      r = MiGA::Result.new(base + ".json")
+      add_files_to_ds_result(r, name, {:ess_genes=>".ess.faa",
+        :collection=>".ess", :report=>".ess/log"})
+    end
+
+    def add_result_ssu(base)
+      return MiGA::Result.new(base + ".json") if result(:assembly).nil?
+      return nil unless result_files_exist?(base, ".ssu.fa")
+      r = MiGA::Result.new(base + ".json")
+      add_files_to_ds_result(r, name, {:longest_ssu_gene=>".ssu.fa",
+        :gff=>".ssu.gff", :all_ssu_genes=>".ssu.all.fa"})
+    end
+
+    def add_result_mytaxa(base)
+      if is_multi?
+        return nil unless result_files_exist?(base, ".mytaxa")
+        r = MiGA::Result.new(base + ".json")
+        add_files_to_ds_result(r, name, {:mytaxa=>".mytaxa", :blast=>".blast",
+          :mytaxain=>".mytaxain"})
+      else
+        MiGA::Result.new base + ".json"
       end
-      def done_preprocessing?
-	 !first_preprocessing.nil? and next_preprocessing.nil?
+    end
+
+    def add_result_mytaxa_scan(base)
+      if is_nonmulti?
+        return nil unless
+          result_files_exist?(base, %w[.pdf .wintax .mytaxa .reg])
+        r = MiGA::Result.new(base + ".json")
+        add_files_to_ds_result(r, name, {:mytaxa=>".mytaxa", :wintax=>".wintax",
+          :blast=>".blast", :mytaxain=>".mytaxain", :report=>".pdf",
+          :regions=>".reg", :gene_ids=>".wintax.genes",
+          :region_ids=>".wintax.regions"})
+      else
+        MiGA::Result.new base + ".json"
       end
-      def profile_advance
-         if first_preprocessing.nil?
-	    adv = Array.new(@@PREPROCESSING_TASKS.size, 0)
-	 else
-	    adv = []
-	    state = 0
-	    first_task = first_preprocessing
-	    next_task = next_preprocessing
-	    @@PREPROCESSING_TASKS.each do |task|
-	       state = 1 if first_task==task
-	       state = 2 if !next_task.nil? and next_task==task
-	       adv << state
-	    end
-	 end
-	 adv
+    end
+
+    def add_result_distances(base)
+      if is_nonmulti?
+        pref = File.dirname(base)
+        return nil unless
+          File.exist?("#{pref}/#{is_ref? ? "01.haai" : "02.aai"}/#{name}.db")
+        r = MiGA::Result.new(base + ".json")
+        r.add_files({:haai_db=>"01.haai/#{name}.db",
+          :aai_db=>"02.aai/#{name}.db", :ani_db=>"03.ani/#{name}.db"})
+      else
+        r = MiGA::Result.new "#{base}.json"
       end
-   end # class Dataset
-end # module MiGA
+      r
+    end
+
+    def add_files_to_ds_result(r, name, rel_files)
+      files = {}
+      rel_files.each{ |k,v| files[k] = name + v }
+      r.add_files(files)
+      r
+    end
 
+end # class MiGA::Dataset