miga-base 0.7.3.1 → 0.7.8.0

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

@@ -5,7 +5,6 @@ require 'miga/cli/action'
 require 'shellwords'
 
 class MiGA::Cli::Action::Run < MiGA::Cli::Action
-
   def parse_cli
     cli.defaults = { try_load: false, thr: 1, env: false }
     cli.parse do |opt|
@@ -38,20 +37,20 @@ class MiGA::Cli::Action::Run < MiGA::Cli::Action
       cli[:thr] ||= ENV['CORES'].to_i unless ENV['CORES'].nil?
       cli[:result] = File.basename(cli[:result].to_s, '.bash').to_sym
     end
-    
+
     # Unset dataset if the requested result is for projects
     if (MiGA::Project.RESULT_DIRS.keys + [:p]).include? cli[:result]
       cli[:dataset] = nil
     end
-    
+
     # Load project
     p = cli.load_project
-    
+
     # Prepare command
     miga = MiGA.root_path
     cmd = ["PROJECT=#{p.path.shellescape}",
-      "RUNTYPE=#{cli[:remote] ? 'ssh' : 'bash'}",
-      "MIGA=#{miga.shellescape}", "CORES=#{cli[:thr]}"]
+           "RUNTYPE=#{cli[:remote] ? 'ssh' : 'bash'}",
+           "MIGA=#{miga.shellescape}", "CORES=#{cli[:thr]}"]
     obj = cli.load_project_or_dataset
     klass = obj.class
     virtual_task = [:p, :d].include?(cli[:result])
@@ -59,13 +58,14 @@ class MiGA::Cli::Action::Run < MiGA::Cli::Action
     if klass.RESULT_DIRS[cli[:result]].nil? and not virtual_task
       raise "Unsupported #{klass.to_s.sub(/.*::/, '')} result: #{cli[:result]}."
     end
+
     cmd << MiGA.script_path(cli[:result], miga: miga, project: p).shellescape
     if cli[:remote]
       cmd = ['ssh', '-t', '-t', cli[:remote].shellescape,
-        cmd.join(' ').shellescape]
+             cmd.join(' ').shellescape]
     end
     cmd << ['>', cli[:log].shellescape, '2>&1'] if cli[:log]
-    
+
     # Launch
     pid = spawn cmd.join(' ')
     Process.wait pid

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

@@ -4,7 +4,6 @@
 require 'miga/cli/action'
 
 class MiGA::Cli::Action::Stats < MiGA::Cli::Action
-
   def parse_cli
     cli.defaults = { try_load: false }
     cli.parse do |opt|
@@ -21,13 +20,18 @@ class MiGA::Cli::Action::Stats < MiGA::Cli::Action
         '--try-load',
         'Check if stat exists instead of computing on --compute-and-save'
       ) { |v| cli[:try_load] = v }
+      opt.on(
+        '--ignore-empty',
+        'If the result does not exist, exit without throwing exceptions'
+      ) { |v| cli[:ignore_result_empty] = v }
     end
   end
 
   def perform
-    cli[:compute] = false if cli[:try_load] and
-      (not r[:stats].nil?) and (not r[:stats].empty?)
-    r = cli.load_result
+    if cli[:try_load] && !r[:stats].nil? && !r[:stats].empty?
+      cli[:compute] = false
+    end
+    r = cli.load_result or return
     if cli[:compute]
       cli.say 'Computing statistics'
       r.compute_stats

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

@@ -4,9 +4,8 @@
 require 'miga/cli/action'
 
 class MiGA::Cli::Action::Summary < MiGA::Cli::Action
-
   def parse_cli
-    cli.defaults = {units: false, tabular: false}
+    cli.defaults = { units: false, tabular: false }
     cli.parse do |opt|
       cli.opt_object(opt, [:project, :dataset_opt])
       cli.opt_filter_datasets(opt)
@@ -37,7 +36,7 @@ class MiGA::Cli::Action::Summary < MiGA::Cli::Action
     stats = ds.map do |d|
       r = d.add_result(cli[:result].to_sym, false)
       s = r.nil? ? {} : r[:stats]
-      s.tap{ |i| i[:dataset] = d.name }
+      s.tap { |i| i[:dataset] = d.name }
     end
     keys = cli[:key_md].nil? ? stats.map(&:keys).flatten.uniq :
       [:dataset, cli[:key_md].downcase.miga_name.to_sym]
@@ -45,9 +44,11 @@ class MiGA::Cli::Action::Summary < MiGA::Cli::Action
     keys.unshift :dataset
 
     table = cli[:units] ?
-      stats.map{ |s| keys.
-        map{ |k| s[k].is_a?(Array) ? s[k].map(&:to_s).join('') : s[k] } } :
-      stats.map{ |s| keys.map{ |k| s[k].is_a?(Array) ? s[k].first : s[k] } }
+      stats.map { |s|
+        keys
+          .map { |k| s[k].is_a?(Array) ? s[k].map(&:to_s).join('') : s[k] }
+      } :
+      stats.map { |s| keys.map { |k| s[k].is_a?(Array) ? s[k].first : s[k] } }
     io = cli[:output].nil? ? $stdout : File.open(cli[:output], 'w')
     cli.puts(io, MiGA.tabulate(keys, table, cli[:tabular]))
     io.close unless cli[:output].nil?

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

@@ -7,7 +7,6 @@ require 'zlib'
 require 'tmpdir'
 
 class MiGA::Cli::Action::TaxDist < MiGA::Cli::Action
-
   def parse_cli
     cli.parse do |opt|
       cli.opt_object(opt, [:project])
@@ -49,17 +48,20 @@ class MiGA::Cli::Action::TaxDist < MiGA::Cli::Action
   def read_distances
     p = cli.load_project
     cli[:metric] ||= p.is_clade? ? 'ani' : 'aai'
-    res_n  = "#{cli[:metric]}_distances"
+    res_n = "#{cli[:metric]}_distances"
     cli.say "Reading distances: 1-#{cli[:metric].upcase}"
     res = p.result(res_n)
     raise "#{res_n} not yet calculated" if res.nil?
+
     matrix = res.file_path(:matrix)
     raise "#{res_n} has no matrix" if matrix.nil?
+
     dist = {}
     mfh = (matrix =~ /\.gz$/) ?
       Zlib::GzipReader.open(matrix) : File.open(matrix, 'r')
     mfh.each_line do |ln|
       next if mfh.lineno == 1
+
       row = ln.chomp.split("\t")
       dist[cannid(row[1], row[2])] = [row[3], row[5], row[6], 0, ['root:biota']]
       cli.advance('Lines:', mfh.lineno, nil, false) if (mfh.lineno % 1_000) == 0
@@ -90,16 +92,17 @@ class MiGA::Cli::Action::TaxDist < MiGA::Cli::Action
     rank_i = 0
     Taxonomy.KNOWN_RANKS.each do |rank|
       next if rank == :ns
+
       rank_n = 0
       rank_i += 1
       in_rank = nil
       ds_name = []
       File.open(tab, 'r') do |fh|
         fh.each_line do |ln|
-          if ln =~ /^ {#{(rank_i-1)*2}}\S+:\S+:/
+          if ln =~ /^ {#{(rank_i - 1) * 2}}\S+:\S+:/
             in_rank = nil
             ds_name = []
-          elsif ln =~ /^ {#{rank_i*2}}(#{rank}:(\S+)):/
+          elsif ln =~ /^ {#{rank_i * 2}}(#{rank}:(\S+)):/
             in_rank = $2 == '?' ? nil : $1
             ds_name = []
           elsif ln =~ /^ *# (\S+)/ and not in_rank.nil?
@@ -108,6 +111,7 @@ class MiGA::Cli::Action::TaxDist < MiGA::Cli::Action
             ds_name.each do |ds_j|
               k = cannid(ds_i, ds_j)
               next if dist[k].nil?
+
               rank_n += 1
               dist[k][3] = rank_i
               dist[k][4].unshift in_rank

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

@@ -5,20 +5,19 @@ require 'miga/cli/action'
 require 'miga/tax_index'
 
 class MiGA::Cli::Action::TaxIndex < MiGA::Cli::Action
-
   def parse_cli
-    cli.defaults = {format: :json}
+    cli.defaults = { format: :json }
     cli.parse do |opt|
       cli.opt_object(opt, [:project])
       opt.on(
         '-i', '--index PATH',
         '(Mandatory) File to create with the index'
-        ){ |v| cli[:index] = v }
+      ) { |v| cli[:index] = v }
       opt.on(
         '-f', '--format STRING',
         "Format of the index file, by default: #{cli[:format]}",
         'Supported: json, tab.'
-        ){ |v| cli[:format] = v.downcase.to_sym }
+      ) { |v| cli[:format] = v.downcase.to_sym }
       cli.opt_filter_datasets(opt)
     end
   end

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

@@ -4,7 +4,6 @@
 require 'miga/cli/action'
 
 class MiGA::Cli::Action::TaxSet < MiGA::Cli::Action
-
   def parse_cli
     cli.parse do |opt|
       cli.opt_object(opt, [:project, :dataset_opt])
@@ -12,14 +11,15 @@ class MiGA::Cli::Action::TaxSet < MiGA::Cli::Action
         '-s', '--tax-string STRING',
         'String corresponding to the taxonomy of the dataset',
         'A space-delimited set of \'rank:name\' pairs'
-        ){ |v| cli[:taxstring] = v }
-      opt.on('-t', '--tax-file PATH',
+      ) { |v| cli[:taxstring] = v }
+      opt.on(
+        '-t', '--tax-file PATH',
         '(Mandatory unless -D and -s are provided)',
         'Tab-delimited file containing datasets taxonomy',
         'Each row corresponds to a datasets and each column to a rank',
         'The first row must be a header with the rank names,',
         'and the first column must contain dataset names'
-        ){ |v| cli[:taxfile] = v }
+      ) { |v| cli[:taxfile] = v }
     end
   end
 
@@ -31,6 +31,7 @@ class MiGA::Cli::Action::TaxSet < MiGA::Cli::Action
       header = nil
       tfh.each_line do |ln|
         next if ln =~ /^\s*?$/
+
         r = ln.chomp.split(/\t/, -1)
         dn = r.shift
         if header.nil?
@@ -48,8 +49,8 @@ class MiGA::Cli::Action::TaxSet < MiGA::Cli::Action
       end
       tfh.close
     else
-      cli.ensure_par({dataset: '-D', taxstring: '-s'},
-        '%<flag>s is mandatory unless -t is provided')
+      cli.ensure_par({ dataset: '-D', taxstring: '-s' },
+                     '%<flag>s is mandatory unless -t is provided')
       cli.say 'Registering taxonomy'
       d = cli.load_dataset
       d.metadata[:tax] = Taxonomy.new(cli[:taxstring])

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

@@ -5,19 +5,18 @@ require 'miga/cli/action'
 require 'miga/tax_dist'
 
 class MiGA::Cli::Action::TaxTest < MiGA::Cli::Action
-
   def parse_cli
-    cli.defaults = {test: 'both', ref_project: false}
+    cli.defaults = { test: 'both', ref_project: false }
     cli.parse do |opt|
       cli.opt_object(opt, [:project, :dataset])
       opt.on(
         '--ref-project',
         'Use the taxonomy from the reference project, not the current project'
-        ){ |v| cli[:ref_project] = v }
+      ) { |v| cli[:ref_project] = v }
       opt.on(
         '-t', '--test STRING',
         'Test to perform. Supported values: intax, novel, both'
-        ){ |v| cli[:test] = v.downcase }
+      ) { |v| cli[:test] = v.downcase }
     end
   end
 
@@ -27,6 +26,7 @@ class MiGA::Cli::Action::TaxTest < MiGA::Cli::Action
     cr = d.closest_relatives(1, cli[:ref_project])
     if cr.nil? or cr.empty?
       raise 'Action not supported for the project or dataset' if cr.nil?
+
       raise 'No close relatives found'
     else
       query_probability_distributions(d, cr[0])
@@ -65,6 +65,7 @@ class MiGA::Cli::Action::TaxTest < MiGA::Cli::Action
       if (q = MiGA::Project.load(ref)).nil?
         raise '--ref-project requested but reference project doesn\'t exist'
       end
+
       cr_d = q.dataset(cr[0])
     else
       cr_d = p.dataset(cr[0])
@@ -75,7 +76,7 @@ class MiGA::Cli::Action::TaxTest < MiGA::Cli::Action
   end
 
   def test_closest_relative(cr, tax, test)
-    TaxDist.aai_pvalues(cr[1], test).map do |k,v|
+    TaxDist.aai_pvalues(cr[1], test).map do |k, v|
       sig = ''
       [0.5, 0.1, 0.05, 0.01].each { |i| sig << '*' if v < i }
       [Taxonomy.LONG_RANKS[k], (tax[k] || '?'), v, sig]

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

@@ -9,7 +9,8 @@ module MiGA::Cli::Action::Wf
     cli.defaults = {
       clean: false, regexp: MiGA::Cli.FILE_REGEXP,
       project_type: :genomes, dataset_type: :popgenome,
-      ncbi_draft: true }
+      ncbi_draft: true
+    }
   end
 
   def opts_for_wf(opt, files_desc, params = {})
@@ -88,6 +89,10 @@ module MiGA::Cli::Action::Wf
   end
 
   def opts_for_wf_distances(opt)
+    opt.on('--sensitive', 'Alias to: --aai-p blast+ --ani-p blast+') do
+      cli[:aai_p] = 'blast+'
+      cli[:ani_p] = 'blast+'
+    end
     opt.on('--fast', 'Alias to: --aai-p diamond --ani-p fastani') do
       cli[:aai_p] = 'diamond'
       cli[:ani_p] = 'fastani'
@@ -110,13 +115,14 @@ module MiGA::Cli::Action::Wf
     cli.ensure_par(
       outdir: '-o',
       project_type: '--project-type',
-      dataset_type: '--dataset-type')
+      dataset_type: '--dataset-type'
+    )
     # Create empty project
     call_cli([
-      'new',
-      '-P', cli[:outdir],
-      '-t', cli[:project_type]
-    ]) unless MiGA::Project.exist? cli[:outdir]
+               'new',
+               '-P', cli[:outdir],
+               '-t', cli[:project_type]
+             ]) unless MiGA::Project.exist? cli[:outdir]
     # Define project metadata
     p = cli.load_project(:outdir, '-o')
     [:haai_p, :aai_p, :ani_p, :ess_coll].each { |i| p_metadata[i] = cli[i] }
@@ -124,11 +130,11 @@ module MiGA::Cli::Action::Wf
     transfer_metadata(p, p_metadata)
     # Download datasets
     call_cli([
-      'ncbi_get',
-      '-P', cli[:outdir],
-      '-T', cli[:ncbi_taxon],
-      (cli[:ncbi_draft] ? '--all' : '--complete')
-    ]) unless cli[:ncbi_taxon].nil?
+               'ncbi_get',
+               '-P', cli[:outdir],
+               '-T', cli[:ncbi_taxon],
+               (cli[:ncbi_draft] ? '--all' : '--complete')
+             ]) unless cli[:ncbi_taxon].nil?
     # Add datasets
     call_cli([
       'add',
@@ -149,17 +155,18 @@ module MiGA::Cli::Action::Wf
     which.each do |r|
       cli.say "Summary: #{r}"
       call_cli([
-        'summary',
-        '-P', cli[:outdir],
-        '-r', r,
-        '-o', File.expand_path("#{r}.tsv", cli[:outdir]),
-        '--tab'
-      ])
+                 'summary',
+                 '-P', cli[:outdir],
+                 '-r', r,
+                 '-o', File.expand_path("#{r}.tsv", cli[:outdir]),
+                 '--tab'
+               ])
     end
   end
 
   def cleanup
     return unless cli[:clean]
+
     cli.say 'Cleaning up intermediate files'
     %w[data daemon metadata miga.project.json].each do |f|
       FileUtils.rm_rf(File.expand_path(f, cli[:outdir]))
@@ -184,12 +191,11 @@ module MiGA::Cli::Action::Wf
 
   def transfer_metadata(obj, md)
     # Clear old metadata
-    obj.metadata.each do |k,v|
+    obj.metadata.each do |k, v|
       obj.metadata[k] = nil if k.to_s =~ /^run_/ || k == :ref_project
     end
     # Transfer and save
     md.each { |k, v| obj.metadata[k] = v }
     obj.save
   end
-
 end

data/lib/miga/cli/base.rb

@@ -2,46 +2,45 @@
 # @license Artistic-2.0
 
 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:      'Creates an empty MiGA project',
-    about:    'Displays information about a MiGA project',
-    doctor:   'Performs consistency checks on a MiGA project',
-    get_db:   'Downloads a pre-indexed database',
+    new: 'Creates an empty MiGA project',
+    about: 'Displays information about a MiGA project',
+    doctor: 'Performs consistency checks on a MiGA project',
+    get_db: 'Downloads a pre-indexed database',
     # Datasets
-    add:      'Creates a dataset in a MiGA project',
-    get:      'Downloads a dataset from public databases into a MiGA project',
+    add: 'Creates a dataset in a MiGA project',
+    get: 'Downloads a dataset from public databases into a MiGA project',
     ncbi_get: 'Downloads all genomes in a taxon from NCBI into a MiGA project',
-    rm:       'Removes a dataset from an MiGA project',
-    find:     'Finds unregistered datasets based on result files',
-    ln:       'Link datasets (including results) from one project to another',
-    ls:       'Lists all registered datasets in an MiGA project',
-    archive:  'Generates a tar-ball with all files from select datasets',
+    rm: 'Removes a dataset from an MiGA project',
+    find: 'Finds unregistered datasets based on result files',
+    ln: 'Link datasets (including results) from one project to another',
+    ls: 'Lists all registered datasets in an MiGA project',
+    archive: 'Generates a tar-ball with all files from select datasets',
     # Results
     add_result: 'Registers a result',
-    stats:    'Extracts statistics for the given result',
-    files:    'Lists registered files from the results of a dataset or project',
-    run:      'Executes locally one step analysis producing the given result',
-    summary:  'Generates a summary table for the statistics of all datasets',
+    stats: 'Extracts statistics for the given result',
+    files: 'Lists registered files from the results of a dataset or project',
+    run: 'Executes locally one step analysis producing the given result',
+    summary: 'Generates a summary table for the statistics of all datasets',
     next_step: 'Returns the next task to run in a dataset or project',
     # Objects (Datasets or Projects)
-    edit:     'Edits the metadata of a dataset or project',
+    edit: 'Edits the metadata of a dataset or project',
     # System
-    init:     'Initialize MiGA to process new projects',
-    daemon:   'Controls the daemon of a MiGA project',
-    lair:     'Controls groups of daemons for several MiGA projects',
-    date:     'Returns the current date in standard MiGA format',
-    console:  'Opens an IRB console with MiGA',
+    init: 'Initialize MiGA to process new projects',
+    daemon: 'Controls the daemon of a MiGA project',
+    lair: 'Controls groups of daemons for several MiGA projects',
+    date: 'Returns the current date in standard MiGA format',
+    console: 'Opens an IRB console with MiGA',
     # Taxonomy
-    tax_set:  'Registers taxonomic information for datasets',
+    tax_set: 'Registers taxonomic information for datasets',
     tax_test: 'Returns test of taxonomic distributions for query datasets',
     tax_index: 'Creates a taxonomy-indexed list of the datasets',
     tax_dist: 'Estimates distributions of distance by taxonomy',
@@ -77,7 +76,8 @@ module MiGA::Cli::Base
   }
 
   @@TASK_ALIAS.each do |nick, task|
-    @@TASK_DESC[task] = ((@@TASK_DESC[task] =~ /\(alias: .*\)\./) ?
+    @@TASK_DESC[task] = (
+      (@@TASK_DESC[task] =~ /\(alias: .*\)\./) ?
         @@TASK_DESC[task].sub(/\)\.$/, ", #{nick}).") :
         @@TASK_DESC[task].sub(/\.$/, " (alias: #{nick}).")
     )
@@ -85,18 +85,20 @@ module MiGA::Cli::Base
 
   @@EXECS = @@TASK_DESC.keys
 
-  @@FILE_REGEXP = %r{^(?:.*/)?(.+?)(\.[A-Z]*([12]|Reads|Contigs))?(\.f[nastq]+)?$}i
-
+  @@FILE_REGEXP =
+    %r{^(?:.*/)?(.+?)(\.[A-Z]*([12]|Reads|Contigs))?(\.f[nastq]+)?$}i
 end
 
 class MiGA::Cli < MiGA::MiGA
-
   include MiGA::Cli::Base
 
   class << self
     def TASK_DESC; @@TASK_DESC end
+
     def TASK_ALIAS; @@TASK_ALIAS end
+
     def EXECS; @@EXECS end
+
     def FILE_REGEXP; @@FILE_REGEXP end
   end
 end