miga-base 0.7.3.0 → 0.7.7.0

data/lib/miga/result/base.rb

@@ -1,4 +1,3 @@
-
 class MiGA::Result < MiGA::MiGA
   class << self
     def RESULT_DIRS
@@ -10,4 +9,3 @@ end
 
 module MiGA::Result::Base
 end
-

data/lib/miga/result/dates.rb

@@ -1,4 +1,3 @@
-
 require 'miga/result/base'
 
 ##
@@ -29,7 +28,7 @@ module MiGA::Result::Dates
   end
 
   private
-    
+
   ##
   # Internal function to detect start and end dates
   def date_at(event)
@@ -42,4 +41,3 @@ module MiGA::Result::Dates
     Time.parse(date) unless date.nil?
   end
 end
-

data/lib/miga/result/source.rb

@@ -1,30 +1,30 @@
-
 require 'miga/result/base'
 
 ##
 # Helper module including functions to access the source of results
 module MiGA::Result::Source
-
   ##
   # Load and return the source (parent object) of a result
   def source
-    @source ||= if MiGA::Project.RESULT_DIRS[key]
-      project
-    else
-      project.dataset(File.basename(path, '.json'))
-    end
+    @source ||=
+      if MiGA::Project.RESULT_DIRS[key]
+        project
+      else
+        project.dataset(File.basename(path, '.json'))
+      end
   end
 
   ##
   # Detect the result key assigned to this result
   def key
-    @key ||= if relative_dir == 'data/90.stats' && file_path(:metadata_index)
-      :project_stats
-    else
-      MiGA::Result.RESULT_DIRS.find do |k, v|
-        "data/#{v}" == relative_dir
-      end.first
-    end
+    @key ||=
+      if relative_dir == 'data/90.stats' && file_path(:metadata_index)
+        :project_stats
+      else
+        MiGA::Result.RESULT_DIRS.find do |k, v|
+          "data/#{v}" == relative_dir
+        end.first
+      end
   end
 
   ##
@@ -51,7 +51,6 @@ module MiGA::Result::Source
   # so the path referencing is identical to that of +self.path+ whenever they
   # need to be compared.
   def project_path
-    path[ 0 .. path.rindex('/data/') - 1 ]
+    path[0..path.rindex('/data/') - 1]
   end
 end
-

data/lib/miga/result/stats.rb

@@ -1,11 +1,9 @@
-
 require 'zlib'
 require 'miga/result/base'
 
 ##
 # Helper module including stats-specific functions for results
 module MiGA::Result::Stats
-
   ##
   # (Re-)calculate and save the statistics for the result
   def compute_stats
@@ -23,46 +21,55 @@ module MiGA::Result::Stats
   def compute_stats_raw_reads
     stats = {}
     if self[:files][:pair1].nil?
-      s = MiGA::MiGA.seqs_length(file_path(:single), :fastq, gc: true)
+      s = MiGA::MiGA.seqs_length(file_path(:single), :fastq, gc: true, x: true)
       stats = {
         reads: s[:n],
         length_average: [s[:avg], 'bp'],
         length_standard_deviation: [s[:sd], 'bp'],
-        g_c_content: [s[:gc], '%']}
+        g_c_content: [s[:gc], '%'],
+        x_content: [s[:x], '%']
+      }
     else
-      s1 = MiGA::MiGA.seqs_length(file_path(:pair1), :fastq, gc: true)
-      s2 = MiGA::MiGA.seqs_length(file_path(:pair2), :fastq, gc: true)
+      s1 = MiGA::MiGA.seqs_length(file_path(:pair1), :fastq, gc: true, x: true)
+      s2 = MiGA::MiGA.seqs_length(file_path(:pair2), :fastq, gc: true, x: true)
       stats = {
         read_pairs: s1[:n],
         forward_length_average: [s1[:avg], 'bp'],
         forward_length_standard_deviation: [s1[:sd], 'bp'],
         forward_g_c_content: [s1[:gc], '%'],
+        forward_x_content: [s1[:x], '%'],
         reverse_length_average: [s2[:avg], 'bp'],
         reverse_length_standard_deviation: [s2[:sd], 'bp'],
-        reverse_g_c_content: [s2[:gc], '%']}
+        reverse_g_c_content: [s2[:gc], '%'],
+        reverse_x_content: [s2[:x], '%']
+      }
     end
     stats
   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)
+    s = MiGA::MiGA.seqs_length(f, :fasta, gc: true, x: true)
     {
       reads: s[:n],
       length_average: [s[:avg], 'bp'],
       length_standard_deviation: [s[:sd], 'bp'],
-      g_c_content: [s[:gc], '%']
+      g_c_content: [s[:gc], '%'],
+      x_content: [s[:x], '%']
     }
   end
 
   def compute_stats_assembly
-    s = MiGA::MiGA.seqs_length(file_path(:largecontigs), :fasta,
-      n50: true, gc: true)
+    s = MiGA::MiGA.seqs_length(
+      file_path(:largecontigs), :fasta, n50: true, gc: true, x: true
+    )
     {
       contigs: s[:n],
       n50: [s[:n50], 'bp'],
       total_length: [s[:tot], 'bp'],
-      g_c_content: [s[:gc], '%']
+      longest_sequence: [s[:max], 'bp'],
+      g_c_content: [s[:gc], '%'],
+      x_content: [s[:x], '%']
     }
   end
 
@@ -70,7 +77,8 @@ module MiGA::Result::Stats
     s = MiGA::MiGA.seqs_length(file_path(:proteins), :fasta)
     stats = {
       predicted_proteins: s[:n],
-      average_length: [s[:avg], 'aa']}
+      average_length: [s[:avg], 'aa']
+    }
     asm = source.result(:assembly)
     unless asm.nil? or asm[:stats][:total_length].nil?
       stats[:coding_density] =
@@ -92,7 +100,7 @@ module MiGA::Result::Stats
   def compute_stats_essential_genes
     stats = {}
     if source.is_multi?
-      stats = {median_copies: 0, mean_copies: 0}
+      stats = { median_copies: 0, mean_copies: 0 }
       File.open(file_path(:report), 'r') do |fh|
         fh.each_line do |ln|
           if /^! (Mean|Median) number of copies per model: (.*)\./.match(ln)
@@ -103,8 +111,8 @@ module MiGA::Result::Stats
     else
       # Fix estimate by domain
       if !(tax = source.metadata[:tax]).nil? &&
-            %w[Archaea Bacteria].include?(tax[:d]) &&
-            file_path(:raw_report).nil?
+         %w[Archaea Bacteria].include?(tax[:d]) &&
+         file_path(:raw_report).nil?
         scr = "#{MiGA::MiGA.root_path}/utils/domain-ess-genes.rb"
         rep = file_path(:report)
         rc_p = File.expand_path('.miga_rc', ENV['HOME'])
@@ -115,7 +123,7 @@ module MiGA::Result::Stats
         add_file(:report, "#{source.name}.ess/log.domain")
       end
       # Extract/compute quality values
-      stats = {completeness: [0.0, '%'], contamination: [0.0, '%']}
+      stats = { completeness: [0.0, '%'], contamination: [0.0, '%'] }
       File.open(file_path(:report), 'r') do |fh|
         fh.each_line do |ln|
           if /^! (Completeness|Contamination): (.*)%/.match(ln)
@@ -124,22 +132,24 @@ module MiGA::Result::Stats
         end
       end
       stats[:quality] = stats[:completeness][0] - stats[:contamination][0] * 5
-      source.metadata[:quality] = case stats[:quality]
-        when 80..100 ; :excellent
-        when 50..80  ; :high
-        when 20..50  ; :intermediate
-        else         ; :low
-      end
+      source.metadata[:quality] =
+        case stats[:quality]
+        when 80..100; :excellent
+        when 50..80; :high
+        when 20..50; :intermediate
+        else; :low
+        end
       source.save
     end
     stats
   end
 
   def compute_stats_ssu
-    stats = {ssu: 0, complete_ssu: 0}
+    stats = { ssu: 0, complete_ssu: 0 }
     Zlib::GzipReader.open(file_path(:gff)) do |fh|
       fh.each_line do |ln|
         next if ln =~ /^#/
+
         rl = ln.chomp.split("\t")
         len = (rl[4].to_i - rl[3].to_i).abs + 1
         stats[:max_length] = [stats[:max_length] || 0, len].max
@@ -158,9 +168,9 @@ module MiGA::Result::Stats
       stats[:aai] = [$2.to_f, '%']
       3.times { fh.gets }
       fh.each_line do |ln|
-        row = ln.chomp.gsub(/^\s*/,'').split(/\s+/)
-        break if row.empty?
-        stats[:"#{row[0]}_pvalue"] = row[2].to_f unless row[0] == 'root'
+        next unless ln.chomp =~ /^\s*(\S+)\s+(.+)\s+([0-9\.e-]+)\s+\**\s*$/
+
+        stats[:"#{$1}_pvalue"] = $3.to_f unless $1 == 'root'
       end
     end
     stats

data/lib/miga/tax_dist.rb

@@ -10,7 +10,6 @@ require 'zlib'
 module MiGA::TaxDist
   # Class-level
   class << self
-
     ##
     # Absolute path to the :intax or :novel data file (determined by +test+) for
     # AAI, determined for options +opts+. Supported options:
@@ -20,8 +19,10 @@ module MiGA::TaxDist
       engine = opts[:engine].to_s.downcase.to_sym
       test = test.to_s.downcase.to_sym
       return nil unless %i[intax novel].include? test
+
       engine = :blast if %i[blast+ blat].include? engine
       return nil unless %i[blast diamond].include? engine
+
       File.expand_path("../_data/aai-#{test}-#{engine}.tsv.gz", __FILE__)
     end
 
@@ -43,7 +44,7 @@ module MiGA::TaxDist
             keys.each do |i|
               v = row.shift
               next if v == 'NA' # <- missing data
-              next if i == 1 # <- namespace, not a taxonomic rank
+
               rank = i.zero? ? :root : MiGA::Taxonomy.KNOWN_RANKS[i]
               vals[rank] = v.to_f
             end
@@ -64,8 +65,8 @@ module MiGA::TaxDist
     # with cannonical rank (as in MiGA::Taxonomy) and estimated p-value.
     def aai_taxtest(aai, test, opts = {})
       meaning = {
-        most_likely:   [0.00, 0.01],
-        probably:      [0.01, 0.10],
+        most_likely: [0.00, 0.01],
+        probably: [0.01, 0.10],
         possibly_even: [0.10, 0.50]
       }
       pvalues = aai_pvalues(aai, test, opts)
@@ -74,6 +75,7 @@ module MiGA::TaxDist
         lwr, upr = thresholds
         min = pvalues.values.select { |v| v < upr }.max
         return out if min.nil?
+
         if min >= lwr
           v = pvalues.select { |_, vj| vj == min }
           out[phrase] = (test == :intax ? v.reverse_each : v).first

data/lib/miga/tax_index.rb

@@ -6,7 +6,6 @@ require 'miga/taxonomy'
 ##
 # Indexing methods based on taxonomy.
 class MiGA::TaxIndex < MiGA::MiGA
-
   # Instance-level
 
   ##
@@ -26,9 +25,11 @@ class MiGA::TaxIndex < MiGA::MiGA
   # Index +dataset+, a MiGA::Dataset object.
   def <<(dataset)
     return nil if dataset.metadata[:tax].nil?
+
     taxon = @root
     MiGA::Taxonomy.KNOWN_RANKS.each do |rank|
       next if rank == :ns
+
       taxon = taxon.add_child(rank, dataset.metadata[:tax][rank])
     end
     taxon.add_dataset dataset
@@ -43,7 +44,7 @@ class MiGA::TaxIndex < MiGA::MiGA
     select = []
     loop do
       new_taxa = []
-      taxa.map{ |tx| tx.children }.flatten.each do |ch|
+      taxa.map { |tx| tx.children }.flatten.each do |ch|
         if ch.rank == rank
           select << ch
         elsif not ch.children.empty?
@@ -59,7 +60,8 @@ class MiGA::TaxIndex < MiGA::MiGA
   # Generate JSON String for the index.
   def to_json
     MiGA::Json.generate(
-      { root: root.to_hash, datasets: datasets.map{ |d| d.name } })
+      { root: root.to_hash, datasets: datasets.map { |d| d.name } }
+    )
   end
 
   ##
@@ -72,7 +74,6 @@ end
 ##
 # Helper class for MiGA::TaxIndex.
 class MiGA::TaxIndexTaxon < MiGA::MiGA
-
   # Instance-level
 
   ##
@@ -96,14 +97,14 @@ class MiGA::TaxIndexTaxon < MiGA::MiGA
 
   ##
   # String representation of the taxon.
-  def tax_str ; "#{rank}:#{name.nil? ? '?' : name}" ; end
+  def tax_str; "#{rank}:#{name.nil? ? '?' : name}"; end
 
   ##
   # Add child at +rank+ with +name+.
   def add_child(rank, name)
     rank = rank.to_sym
     name = name.miga_name unless name.nil?
-    child = children.find{ |it| it.rank==rank and it.name==name }
+    child = children.find { |it| it.rank == rank and it.name == name }
     if child.nil?
       child = MiGA::TaxIndexTaxon.new(rank, name)
       @children << child
@@ -113,45 +114,44 @@ class MiGA::TaxIndexTaxon < MiGA::MiGA
 
   ##
   # Add dataset at the current taxon (not children).
-  def add_dataset(dataset) @datasets << dataset ; end
+  def add_dataset(dataset) @datasets << dataset; end
 
   ##
   # Get the number of datasets in the taxon (including children).
   def datasets_count
-    children.map{ |it| it.datasets_count }.reduce(datasets.size, :+)
+    children.map { |it| it.datasets_count }.reduce(datasets.size, :+)
   end
 
   ##
   # Get all the datasets in the taxon (including children).
   def all_datasets
-    children.map{ |it| it.datasets }.reduce(datasets, :+)
+    children.map { |it| it.datasets }.reduce(datasets, :+)
   end
 
   ##
   # JSON String of the taxon.
   def to_json(*a)
-    { str:tax_str, datasets:datasets.map{|d| d.name},
-      children:children }.to_json(a)
+    { str: tax_str, datasets: datasets.map { |d| d.name },
+      children: children }.to_json(a)
   end
 
   ##
   # Hash representation of the taxon.
   def to_hash
-    { str:tax_str, datasets:datasets.map{|d| d.name},
-      children:children.map{ |it| it.to_hash } }
+    { str: tax_str, datasets: datasets.map { |d| d.name },
+      children: children.map { |it| it.to_hash } }
   end
 
   ##
   # Tabular String of the taxon.
-  def to_tab(unknown, indent=0)
+  def to_tab(unknown, indent = 0)
     o = ''
     if unknown or not datasets.empty? or not name.nil?
       o = "#{' ' * indent}#{tax_str}: #{datasets_count}\n"
     end
     indent += 2
-    datasets.each{ |ds| o << "#{' ' * indent}# #{ds.name}\n" }
-    children.each{ |it| o << it.to_tab(unknown, indent) }
+    datasets.each { |ds| o << "#{' ' * indent}# #{ds.name}\n" }
+    children.each { |it| o << it.to_tab(unknown, indent) }
     o
   end
-
 end

data/lib/miga/taxonomy.rb

@@ -45,6 +45,7 @@ class MiGA::Taxonomy < MiGA::MiGA
     when Hash
       value.each do |r, n|
         next if n.nil? || n == ''
+
         @ranks[self.class.normalize_rank(r)] = n.tr('_', ' ')
       end
     when Array
@@ -87,6 +88,7 @@ class MiGA::Taxonomy < MiGA::MiGA
   # the alternative (or master) is replaced instead if +replace+ is true.
   def add_alternative(tax, replace = true)
     raise 'Unsupported taxonomy class.' unless tax.is_a? MiGA::Taxonomy
+
     alt_ns = alternative(tax.namespace)
     if !replace || tax.namespace.nil? || alt_ns.nil?
       @alt << tax
@@ -96,7 +98,7 @@ class MiGA::Taxonomy < MiGA::MiGA
   end
 
   ##
-  # Removes (and returns) all alternative taxonomies. 
+  # Removes (and returns) all alternative taxonomies.
   def delete_alternative
     alt = @alt.dup
     @alt = []
@@ -109,6 +111,7 @@ class MiGA::Taxonomy < MiGA::MiGA
   def in?(taxon)
     r = taxon.ranks.keys.first
     return false if self[r].nil?
+
     self[r].casecmp(taxon[r]).zero?
   end
 
@@ -120,6 +123,7 @@ class MiGA::Taxonomy < MiGA::MiGA
     @@KNOWN_RANKS.map do |r|
       next if
         (r == :ns && !with_namespace) || (ranks[r].nil? && !force_ranks)
+
       [r, ranks[r]]
     end.compact
   end
@@ -179,6 +183,7 @@ class MiGA::Taxonomy < MiGA::MiGA
     unless ranks.size == str.size
       raise "Unequal number of ranks and names: #{ranks} => #{str}"
     end
+
     str.each_with_index { |i, k| self << "#{ranks[k]}:#{i}" }
   end
 end