miga-base 0.7.3.1 → 0.7.8.0

data/utils/index_metadata.rb

@@ -13,17 +13,18 @@ db.execute 'create table metadata(' \
 
 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\-]+/, ' ')} "
+             d.name, k.to_s, " #{v.to_s.downcase.gsub(/[^A-Za-z0-9\-]+/, ' ')} "
 end
 
-p.each_dataset do |name, d|
+p.each_dataset do |d|
   next unless d.is_ref?
   next unless d.is_active?
+
   searchable(db, d, :name, d.name)
   d.metadata.each do |k, v|
     next if [:created, :updated].include? k
-    v = v.sorted_ranks.map{ |r| r[1] }.join(" ") if k==:tax
+
+    v = v.sorted_ranks.map { |r| r[1] }.join(' ') if k == :tax
     searchable(db, d, k, v)
   end
 end
-

data/utils/mytaxa_scan.rb

@@ -15,42 +15,45 @@ begin
 
   # Extract gene IDs
   ifh = faa =~ /\.gz/ ? Zlib::GzipReader.open(faa) : File.open(faa, 'r')
-  ids = ifh.each_line.grep(/^>/).map{|dl| dl.chomp.sub(/^>/,'').sub(/\s.*/,'')}
+  ids = ifh.each_line.grep(/^>/).map { |dl| dl.chomp.sub(/^>/, '').sub(/\s.*/, '') }
   ifh.close
-  tax = Hash[ids.map{|k| [k, "NA"]}]
+  tax = Hash[ids.map { |k| [k, "NA"] }]
 
   # Get MyTaxa distributions
   k, l = nil
   File.open(mytaxa).each do |ln|
     ln.chomp!
-    if $.%2 == 1
+    if $. % 2 == 1
       k, l = ln.split /\t/
     else
-      tax[k] = ln.gsub(/<[^>]+>/,"").gsub(/;/,"::")
+      tax[k] = ln.gsub(/<[^>]+>/, '').gsub(/;/, '::')
     end
   end
-  all_tax = tax.values.uniq.sort{|x,y| tax.values.count(y) <=> tax.values.count(x) }
+  all_tax = tax.values.uniq.sort do |x, y|
+    tax.values.count(y) <=> tax.values.count(x)
+  end
 
   # Estimate Windows and save gene IDs
-  fh = File.open(outdata + ".genes", "w")
+  fh = File.open(outdata + '.genes', 'w')
   c = []
-  c << all_tax.map{|t| tax.values.count(t) }
-  n_wins = (ids.size/winsize).ceil
-  (0 .. (n_wins-1)).each do |win|
-    k = ids[win*winsize, winsize]
+  c << all_tax.map { |t| tax.values.count(t) }
+  n_wins = (ids.size / winsize).ceil
+  (0..(n_wins - 1)).each do |win|
+    k = ids[win * winsize, winsize]
     win_t = tax.values_at(*k)
     fh.puts k.join("\t")
-    c << all_tax.map{|t| win_t.count(t)}
+    c << all_tax.map { |t| win_t.count(t) }
   end
-  p = c.map{|col| col.map{|cell| cell.to_f/col.inject(:+)}}
+  p = c.map { |col| col.map { |cell| cell.to_f / col.inject(:+) } }
   fh.close
 
   # Save window profiles
   fh = File.open(outdata, "w")
   fh.puts "# Data derived from #{mytaxa}, with #{winsize}-genes windows"
-  fh.puts "# " + (["Tax-label", "Genome"] + (1 .. n_wins).map{|i| "Win_#{i}"}).join("\t")
-  (0 .. (all_tax.size - 1)).each do |row|
-    fh.puts ([all_tax[row]] + p.map{|col| col[row]}).join "\t"
+  fh.puts '# ' + (['Tax-label', 'Genome'] +
+    (1..n_wins).map { |i| "Win_#{i}" }).join("\t")
+  (0..(all_tax.size - 1)).each do |row|
+    fh.puts ([all_tax[row]] + p.map { |col| col[row] }).join "\t"
   end
   fh.close
 rescue => err
@@ -58,4 +61,3 @@ rescue => err
   err.backtrace.each { |l| $stderr.puts l + "\n" }
   err
 end
-

data/utils/representatives.rb

@@ -19,7 +19,8 @@ end
 ani_spp = []
 File.open(pf, 'r') do |fh|
   fh.each_line do |ln|
-    next if $.==1 and ln.chomp == 'G' # <- Legacy check
+    next if $. == 1 and ln.chomp == 'G' # <- Legacy check
+
     ani_spp << ln.chomp.split(',')
   end
 end
@@ -32,10 +33,10 @@ ani_spp.each_with_index do |datasets, i|
     dr = d.result(:essential_genes) or next
     q = dr[:stats][:quality] or next
     if best.nil? or q > best[:q]
-      best = {d: d, q: q}
+      best = { d: d, q: q }
     end
   end
   raise "Unavailable statistics for any of:\n#{datasets}\n" if best.nil?
-  puts "ANIsp_#{i+1}\t#{best[:d].name}"
-end
 
+  puts "ANIsp_#{i + 1}\t#{best[:d].name}"
+end

data/utils/requirements.txt

@@ -1,6 +1,6 @@
 Software	Test exec	Website								Notes
 --------	---------	-------								-----
-Ruby		ruby		https://www.ruby-lang.org/					Required version: 2.1+
+Ruby		ruby		https://www.ruby-lang.org/					Required version: 2.3+
 Python		python		https://www.python.org/
 R		R		http://www.r-project.org/
 SQLite3		sqlite3		https://www.sqlite.org/

data/utils/subclade/base.rb

@@ -1,4 +1,3 @@
-
 require 'zlib'
 require 'miga'
 

data/utils/subclade/pipeline.rb

@@ -1,7 +1,5 @@
-
 # High-end pipelines for SubcladeRunner
 module MiGA::SubcladeRunner::Pipeline
-
   # Run species-level clusterings using ANI > 95% / AAI > 90%
   def cluster_species
     tasks = {
@@ -12,7 +10,7 @@ module MiGA::SubcladeRunner::Pipeline
       # Final output
       ogs_file = "miga-project.#{k}-clades"
       next if File.size? ogs_file
-      
+
       # Build ABC files
       abc_path = tmp_file("#{k}.abc")
       ofh = File.open(abc_path, 'w')
@@ -20,6 +18,7 @@ module MiGA::SubcladeRunner::Pipeline
       Zlib::GzipReader.open(metric_res.file_path(:matrix)) do |ifh|
         ifh.each_line do |ln|
           next if ln =~ /^metric\t/
+
           r = ln.chomp.split("\t")
           ofh.puts "G>#{r[1]}\tG>#{r[2]}\t#{r[3]}" if r[3].to_f >= par[1]
         end
@@ -55,7 +54,8 @@ module MiGA::SubcladeRunner::Pipeline
     ofh = File.open('miga-project.proposed-clades', 'w')
     File.open('miga-project.gsp-clades', 'r') do |ifh|
       ifh.each_line do |ln|
-        next if $.==1
+        next if $. == 1
+
         r = ln.chomp.split(',')
         ofh.puts r.join("\t") if r.size >= 5
       end
@@ -70,8 +70,9 @@ module MiGA::SubcladeRunner::Pipeline
     matrix = metric_res.file_path(:matrix)
     `Rscript '#{src}' '#{matrix}' miga-project '#{opts[:thr]}' \
       miga-project.ani95-medoids '#{opts[:run_clades] ? 'cluster' : 'empty'}'`
-    File.rename('miga-project.nwk',"miga-project.#{metric}.nwk") if
-          File.exist? 'miga-project.nwk'
+    if File.exist? 'miga-project.nwk'
+      File.rename('miga-project.nwk', "miga-project.#{metric}.nwk")
+    end
   end
 
   def compile

data/utils/subclade/runner.rb

@@ -1,33 +1,34 @@
-
 require_relative 'base.rb'
 require_relative 'temporal.rb'
 require_relative 'pipeline.rb'
 
 class MiGA::SubcladeRunner
-
   include MiGA::SubcladeRunner::Temporal
   include MiGA::SubcladeRunner::Pipeline
 
   attr_reader :project, :step, :opts, :home, :tmp
 
-  def initialize(project_path, step, opts_hash={})
+  def initialize(project_path, step, opts_hash = {})
     @opts = opts_hash
     @project = MiGA::Project.load(project_path) or
-          raise "No project at #{project_path}"
+      raise "No project at #{project_path}"
     @step = step.to_sym
-    clades_dir = File.expand_path('data/10.clades', project.path)
-    @home = File.expand_path(@step == :clade_finding ? '01.find' : '02.ani',
-          clades_dir)
+    @home = File.join(
+      File.join(project.path, 'data', '10.clades'),
+      @step == :clade_finding ? '01.find' : '02.ani'
+    )
     @opts[:thr] ||= ENV.fetch('CORES') { 2 }.to_i
     @opts[:run_clades] = !!@project.metadata.data.fetch(:run_clades) { true }
     @opts[:gsp_ani] = @project.metadata.data.fetch(:gsp_ani) { 95.0 }.to_f
     @opts[:gsp_aai] = @project.metadata.data.fetch(:gsp_aai) { 90.0 }.to_f
-    @opts[:gsp_metric] = @project.metadata.data.fetch(:gsp_metric){ 'ani' }.to_s
+    @opts[:gsp_metric] =
+      @project.metadata.data.fetch(:gsp_metric) { 'ani' }.to_s
   end
 
   # Launch the appropriate analysis
   def go!
     return if project.type == :metagenomes
+
     unless @project.dataset_names.any? { |i| @project.dataset(i).is_ref? }
       FileUtils.touch(File.expand_path('miga-project.empty', @home))
       return
@@ -54,5 +55,4 @@ class MiGA::SubcladeRunner
     subclades :ani
     compile
   end
-
 end

data/utils/subclade/temporal.rb

@@ -1,8 +1,6 @@
-
 require 'tmpdir'
 
 module MiGA::SubcladeRunner::Temporal
-
   # Create the empty temporal structure
   def create_temporals
   end

data/utils/subclades-compile.rb

@@ -1,49 +1,51 @@
 #!/usr/bin/env ruby
 
-$:.push File.expand_path(File.dirname(__FILE__) + "/lib")
 dir = ARGV.shift
 out = ARGV.shift or abort "Usage: #{$0} <classif.dir> <out.base>"
 
-def read_classif(dir, classif={})
-   classif_file = File.expand_path("miga-project.classif", dir)
-   return classif unless File.exist? classif_file
-   ready = File.expand_path('miga-project.ready', dir)
-   File.size?(ready) or raise "Incomplete recursion found at #{dir}"
-   File.unlink ready
-   fh = File.open(classif_file, "r")
-   klass = []
-   while ln = fh.gets
-      r = ln.chomp.split("\t")
-      classif[r[0]] ||= []
-      classif[r[0]] << r[1]
-      klass[r[1].to_i] = r[1]
-   end
-   fh.close
-   klass.each do |i|
-      d = File.expand_path("miga-project.sc-#{i}", dir)
-      classif = read_classif(d, classif) if Dir.exist? d
-   end
-   classif
+def read_classif(dir, classif = {})
+  classif_file = File.expand_path('miga-project.classif', dir)
+  return classif unless File.exist? classif_file
+
+  ready = File.expand_path('miga-project.ready', dir)
+  File.size?(ready) or raise "Incomplete recursion found at #{dir}"
+  File.unlink ready
+  fh = File.open(classif_file, 'r')
+  klass = []
+  while ln = fh.gets
+    r = ln.chomp.split("\t")
+    classif[r[0]] ||= []
+    classif[r[0]] << r[1]
+    klass[r[1].to_i] = r[1]
+  end
+  fh.close
+  klass.each do |i|
+    d = File.expand_path("miga-project.sc-#{i}", dir)
+    classif = read_classif(d, classif) if Dir.exist? d
+  end
+  classif
 end
 
-def print_tree(classif, col=0)
-   klass = classif.values.map{ |i| i[col] }.compact.uniq
-   if klass.size<=1
-      o = classif.keys
-   else
-      o = klass.map do |c|
-	 oo = print_tree(classif.select{ |k,v| v[col]==c }, col+1)
-	 "#{oo}[#{c}]" unless oo.nil?
-      end.compact
-   end
-   o.size==0 ? nil :
-      o.size==1 ? o[0] :
-      "(#{o.join(",")})"
+def print_tree(classif, col = 0)
+  klass = classif.values.map { |i| i[col] }.compact.uniq
+  if klass.size <= 1
+    o = classif.keys
+  else
+    o = klass.map do |c|
+      oo = print_tree(classif.select { |k, v| v[col] == c }, col + 1)
+      "#{oo}[#{c}]" unless oo.nil?
+    end.compact
+  end
+  case o.size
+  when 0; nil
+  when 1; o[0]
+  else; "(#{o.join(',')})"
+  end
 end
 
 c = read_classif(dir)
-max_depth = c.values.map{|i| i.count}.max
+max_depth = c.values.map { |i| i.count }.max
 File.open("#{out}.tsv", 'w') do |fh|
-  c.each { |k,v| fh.puts ([k] + v + ["0"]*(max_depth-v.count)).join("\t") }
+  c.each { |k, v| fh.puts ([k] + v + ['0'] * (max_depth - v.count)).join("\t") }
 end
-File.open("#{out}.nwk", 'w') { |fh| fh.puts print_tree(c).to_s + ";" }
+File.open("#{out}.nwk", 'w') { |fh| fh.puts print_tree(c).to_s + ';' }

data/utils/subclades.rb

@@ -4,6 +4,6 @@ require_relative 'subclade/runner.rb'
 
 project = ARGV.shift
 step = ARGV.shift
-opts = Hash[ ARGV.map{ |i| i.split("=",2).tap{ |j| j[0] = j[0].to_sym } } ]
+opts = Hash[ARGV.map { |i| i.split("=", 2).tap { |j| j[0] = j[0].to_sym } }]
 runner = MiGA::SubcladeRunner.new(project, step, opts)
 runner.go!

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: miga-base
 version: !ruby/object:Gem::Version
-  version: 0.7.3.1
+  version: 0.7.8.0
 platform: ruby
 authors:
 - Luis M. Rodriguez-R
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2020-04-23 00:00:00.000000000 Z
+date: 2020-06-07 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: daemons
@@ -44,14 +44,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.4'
+        version: '1.3'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.4'
+        version: '1.3'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
@@ -124,6 +124,7 @@ files:
 - lib/miga/cli/action/date.rb
 - lib/miga/cli/action/derep_wf.rb
 - lib/miga/cli/action/doctor.rb
+- lib/miga/cli/action/doctor/base.rb
 - lib/miga/cli/action/edit.rb
 - lib/miga/cli/action/files.rb
 - lib/miga/cli/action/find.rb
@@ -213,6 +214,7 @@ files:
 - scripts/trimmed_fasta.bash
 - scripts/trimmed_reads.bash
 - test/common_test.rb
+- test/daemon_helper.rb
 - test/daemon_test.rb
 - test/dataset_test.rb
 - test/format_test.rb