miga-base 0.7.10.2 → 0.7.13.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA256:
-  metadata.gz: f3b350bb3e5dce2f0f8d0006d7f0693ff746c157006890a1250f30d71d89a523
-  data.tar.gz: 1d94e39c61bfe191388d309eeb992b995350f6191dc74d5c7b15ae9741bcca09
+SHA1:
+  metadata.gz: 964b803e09887476153335589fad3d5aee2861ea
+  data.tar.gz: ee0d34a4a7c8569d39bea4855a6054c57de78c81
 SHA512:
-  metadata.gz: f2a47ca016873723f030c9435db7daa81c819a3f19c65ed7614c21d8d68d556af0dd7313b79d2678508a12762ecd36f7bd922f5cf45640b383c6aaadde91cdfe
-  data.tar.gz: e8218114c0e89d80eab2b6cf7eba5a1de6f26b7d27e3560af1da12fdfc9037f3557a5994e1b982cff35635cea3d23e18ef234758ef8e12b86fb56f782a41ef89
+  metadata.gz: b84efbc94fbfc848b85ae7c3cca7e26f2baea74c5f066a63cf1ede7fb26ed6c634f4c2e2cbe1c2752e54624cf48d6597b933474d4b4d6083cb505a3b17063cf5
+  data.tar.gz: 0c7cfc6a149cab5fa1cfc5e386de789f84c132d227ad8ebbbc42dee2b076010bfe06b6697e69efe00a6639283c472f9ca3793a1e113506e691e50a182cfee2c6

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

@@ -0,0 +1,214 @@
+# frozen_string_literal: true
+
+require 'miga/cli/action'
+
+# Action: miga browse
+class MiGA::Cli::Action::Browse < MiGA::Cli::Action
+  def parse_cli
+    cli.parse do |opt|
+      cli.defaults = { open: true }
+      cli.opt_object(opt, [:project])
+    end
+  end
+
+  def perform
+    p = cli.load_project
+    create_empty_page(p)
+    generate_project_page(p)
+    say 'Creating dataset pages'
+    cli.load_project.each_dataset do |d|
+      generate_dataset_page(p, d)
+    end
+    generate_datasets_index(p)
+    say "Open in your browser: #{File.join(p.path, 'index.html')}"
+  end
+
+  private
+
+  ##
+  # Create an empty page with necessary assets for project +p+
+  def create_empty_page(p)
+    say 'Creating project page'
+    FileUtils.mkdir_p(browse_file(p, '.'))
+    %w[favicon-32.png style.css].each do |i|
+      FileUtils.cp(template_file(i), browse_file(p, i))
+    end
+    write_file(p, 'about.html') do
+      build_from_template('about.html', citation: MiGA::MiGA.CITATION)
+    end
+  end
+
+  ##
+  # Create landing page for project +p+
+  def generate_project_page(p)
+    # Redirect page
+    write_file(p, '../index.html') { build_from_template('redirect.html') }
+
+    # Summaries
+    summaries = Dir["#{p.path}/*.tsv"].map do |i|
+      b = File.basename(i)
+      "<li><a href='../#{b}'>#{b}</a></li>"
+    end.join('')
+
+    # Project index page
+    data = {
+      project_active: 'active',
+      information: format_metadata(p),
+      summaries: summaries.empty? ? 'None' : "<ul>#{summaries}</ul>",
+      results: format_results(p)
+    }
+    write_file(p, 'index.html') { build_from_template('index.html', data) }
+  end
+
+  ##
+  # Create page for dataset +d+ within project +p+
+  def generate_dataset_page(p, d)
+    data = {
+      unmiga_name: d.name.unmiga_name,
+      information: format_metadata(d),
+      results: format_results(d)
+    }
+    write_file(p, "d_#{d.name}.html") do
+      build_from_template('dataset.html', data)
+    end
+  end
+
+  ##
+  # Create pages for reference and query dataset indexes
+  def generate_datasets_index(p)
+    say 'Creating index pages'
+    data = format_dataset_index(p)
+    data.each do |k, v|
+      write_file(p, "#{k}_datasets.html") do
+        v[:list] = 'None' if v[:list] == ''
+        build_from_template(
+          'datasets.html',
+          v.merge(:"#{k}_datasets_active" => 'active')
+        )
+      end
+    end
+  end
+
+  def format_dataset_index(p)
+    data = {
+      ref: { type_name: 'Reference', list: '' },
+      qry: { type_name: 'Query', list: '' }
+    }
+    p.each_dataset do |d|
+      data[d.ref? ? :ref : :qry][:list] +=
+        "<li><a href='d_#{d.name}.html'>#{d.name.unmiga_name}</a></li>"
+    end
+    data
+  end
+
+  ##
+  # Format +obj+ metadata as a table
+  def format_metadata(obj)
+    '<table class="table table-sm table-responsive">' +
+      obj.metadata.data.map do |k, v|
+        case k
+        when /^run_/, :plugins, :user
+          next
+        when :web_assembly_gz
+          v = "<a href='#{v}'>#{v[0..50]}...</a>"
+        when :datasets
+          v = v.size
+        end
+        "<tr><td class='text-right pr-4'><b>#{format_name(k)}</b></td>" \
+             "<td>#{v}</td></tr>"
+      end.compact.join('') +
+      '</table>'
+  end
+
+  ##
+  # Format +obj+ results as cards
+  def format_results(obj)
+    o = ''
+    obj.each_result do |key, res|
+      links = format_result_links(res)
+      stats = format_result_stats(res)
+      next unless links || stats
+      name = format_name(key)
+      url_doc =
+        'http://manual.microbial-genomes.org/part5/workflow#' +
+        key.to_s.tr('_', '-')
+      o += <<~CARD
+        <div class="col-md-6 mb-4">
+          <h3>#{name}</h3>
+          <div class='border-left p-3'>
+            #{stats}
+            #{links}
+          </div>
+          <div class='border-top p-2 bg-light'>
+            <a target=_blank href="#{url_doc}" class='p-2'>Learn more</a>
+          </div>
+        </div>
+      CARD
+    end
+    "<div class='row'>#{o}</div>"
+  end
+
+  def format_name(str)
+    str
+      .to_s.unmiga_name
+      .sub(/^./, &:upcase)
+      .gsub(/(Aai|Ani|Ogs|Cds|Ssu| db$| ssu )/, &:upcase)
+      .sub(/Haai/, 'hAAI')
+      .sub(/Mytaxa/, 'MyTaxa')
+      .sub(/ pvalue$/, ' p-value')
+      .sub(/contigs$/, 'Contigs')
+  end
+
+  def format_result_links(res)
+    links = []
+    res.each_file do |key, _|
+      name = format_name(key)
+      links << "<a href='../#{res.file_path(key, true)}'>#{name}</a><br/>"
+    end
+    links.empty? ? nil : links.join('')
+  end
+
+  def format_result_stats(res)
+    res.stats.map do |k, v|
+      v = [v, ''] unless v.is_a? Array
+      v[0] = ('%.3g' % v[0]) if v[0].is_a? Float
+      "<b>#{format_name(k)}:</b> #{v[0]}#{v[1]}<br/>"
+    end.join('') + '<br/>' unless res.stats.empty?
+  end
+
+  ##
+  # Write +file+ within the browse folder of project +p+ using the passed
+  # block output as content
+  def write_file(p, file)
+    File.open(browse_file(p, file), 'w') { |fh| fh.print yield }
+  end
+
+  ##
+  # Use a +template+ file to generate content with a hash of +data+ over the
+  # layout page if +layout+ is true
+  def build_from_template(template, data = {}, layout = true)
+    cont = File.read(template_file(template)).miga_variables(data)
+    return cont unless layout
+
+    build_from_template(
+      'layout.html',
+      data.merge(content: cont, project_name: cli.load_project.name),
+      false
+    )
+  end
+
+  ##
+  # Path to the template browse file
+  def template_file(file)
+    File.join(
+      MiGA::MiGA.root_path,
+      'lib', 'miga', 'cli', 'action', 'browse', file
+    )
+  end
+
+  ##
+  # Path to the browse file in the project
+  def browse_file(p, file)
+    File.join(p.path, 'browse', file)
+  end
+end

data/lib/miga/cli/action/browse/about.html

@@ -0,0 +1,31 @@
+<h1 class="h2 border-bottom pt-3 pb-2 mb-3">About MiGA</h1>
+<p>
+MiGA is developed and maintained by
+<a href='https://rodriguez-r.com/'>Luis M. Rodriguez-R</a>.
+
+The MiGA codebase is
+<a href='http://code.microbial-genomes.org/miga'>freely available</a> under the
+terms of the terms of the
+<a href='http://code.microbial-genomes.org/miga/blob/master/LICENSE'>Artistic License 2.0</a>.
+</p>
+
+<p>
+MiGA is the result of a collaboration between the
+<a href='http://enve-omics.gatech.edu/'>Kostas Lab</a>
+(<a href='http://www.gatech.edu/'>Georgia Institute of Technology</a>) and the
+<a href='http://rdp.cme.msu.edu/'>RDP team</a>
+(<a href='http://cme.msu.edu/'>Center for Microbial Ecology</a>,
+<a href='https://msu.edu/'>Michigan State University</a>).
+The MiGA project is funded by the
+<a href='http://nsf.gov/'>US National Science Foundation</a>
+(Awards <a href='http://nsf.gov/awardsearch/showAward?AWD_ID=1356288'>#1356288</a> &amp;
+<a href='https://xras.xsede.org/public/requests/31162-XSEDE-MCB190042-1190572'>#MCB190042</a>).
+</p>
+
+<h1 class="h2 border-bottom pt-3 pb-2 mb-3">Citation</h1>
+If you use MiGA in your work, consider citing:
+<blockquote class='border-left p-3'>
+{{citation}}
+</blockquote>
+
+

data/lib/miga/cli/action/browse/dataset.html

@@ -0,0 +1,5 @@
+<h1 class="h2 border-bottom pt-3 pb-2 mb-3">{{unmiga_name}}</h1>
+{{information}}
+
+<h1 class="h2 border-bottom pt-3 pb-2 mb-3">Results</h1>
+{{results}}

data/lib/miga/cli/action/browse/dataset_menu_item.html

@@ -0,0 +1,3 @@
+<li class="nav-item">
+  <a class="nav-link" href="ds_{{name}}.html">{{unmiga_name}}</a>
+</li>

data/lib/miga/cli/action/browse/datasets.html

@@ -0,0 +1,4 @@
+<h1 class="h2 border-bottom pt-3 pb-2 mb-3">{{type_name}} Datasets</h1>
+<ul>
+  {{list}}
+</ul>

data/lib/miga/cli/action/browse/index.html

@@ -0,0 +1,8 @@
+<h1 class="h2 border-bottom pt-3 pb-2 mb-3">Project Information</h1>
+{{information}}
+
+<h1 class="h2 border-bottom pt-3 pb-2 mb-3">Summaries</h1>
+{{summaries}}
+
+<h1 class="h2 border-bottom pt-3 pb-2 mb-3">Project Results</h1>
+{{results}}

data/lib/miga/cli/action/browse/layout.html

@@ -0,0 +1,57 @@
+<!doctype html>
+<head>
+  <meta charset="utf-8">
+  <title>MiGA | {{project_name}}</title>
+
+  <!-- Remote assets -->
+  <link rel="stylesheet" href="https://stackpath.bootstrapcdn.com/bootstrap/4.5.0/css/bootstrap.min.css" integrity="sha384-9aIt2nRpC12Uk9gS9baDl411NQApFmC26EwAOH8WgZl5MYYxFfc+NcPb1dKGj7Sk" crossorigin="anonymous">
+  <script src="https://code.jquery.com/jquery-3.5.1.slim.min.js" integrity="sha384-DfXdz2htPH0lsSSs5nCTpuj/zy4C+OGpamoFVy38MVBnE+IbbVYUew+OrCXaRkfj" crossorigin="anonymous"></script>
+  <script src="https://cdn.jsdelivr.net/npm/popper.js@1.16.0/dist/umd/popper.min.js" integrity="sha384-Q6E9RHvbIyZFJoft+2mJbHaEWldlvI9IOYy5n3zV9zzTtmI3UksdQRVvoxMfooAo" crossorigin="anonymous"></script>
+  <script src="https://stackpath.bootstrapcdn.com/bootstrap/4.5.0/js/bootstrap.min.js" integrity="sha384-OgVRvuATP1z7JjHLkuOU7Xw704+h835Lr+6QL9UvYjZE3Ipu6Tp75j7Bh/kR0JKI" crossorigin="anonymous"></script>
+
+  <!-- Local assets -->
+  <link href="style.css" rel="stylesheet">
+  <link rel="icon" href="favicon-32.png" sizes="32x32" type="image/png">
+</head>
+<body>
+  <nav class="navbar navbar-dark sticky-top bg-dark flex-md-nowrap p-0 shadow">
+    <a class="navbar-brand col-md-12 col-lg-12 mr-0 px-3"
+          href="index.html">MiGA | {{project_name}}</a>
+    <button class="navbar-toggler position-absolute d-md-none collapsed"
+          type="button" data-toggle="collapse" data-target="#sidebarMenu"
+          aria-controls="sidebarMenu" aria-expanded="false"
+          aria-label="Toggle navigation">
+      <span class="navbar-toggler-icon"></span>
+    </button>
+  </nav>
+  <div class="container-fluid">
+  <div class="row">
+    <nav id="sidebarMenu" class="col-md-3 col-lg-2 d-md-block bg-light sidebar collapse">
+      <div class="sidebar-sticky pt-3">
+        <ul class="nav flex-column">
+          <li class="nav-item">
+            <a class="nav-link {{project_active}}" href="index.html">Project</a>
+          </li>
+          <li class="nav-item">
+            <a class="nav-link {{ref_datasets_active}}"
+                  href="ref_datasets.html">Reference datasets</a>
+          </li>
+          <li class="nav-item">
+            <a class="nav-link {{qry_datasets_active}}"
+                  href="qry_datasets.html">Query datasets</a>
+          </li>
+          <li class="nav-item border-top mt-4">
+            <a class="nav-link {{about_miga_active}}"
+                  href="about.html">About MiGA</a>
+          </li>
+        </ul>
+      </div>
+    </nav>
+
+    <main role="main" class="col-md-9 ml-sm-auto col-lg-10 px-md-4">
+      {{content}}
+    </main>
+  </div>
+</div>
+</body>
+

data/lib/miga/cli/action/browse/redirect.html

@@ -0,0 +1,11 @@
+<!doctype html>
+<head>
+  <title>MiGA Project</title>
+  <meta http-equiv = "refresh" content = "1; url = browse/index.html" />
+</head>
+<body>
+  <div style='font-size:200%; margin-top: 5em; text-align: center;'>
+    Redirecting to <a href='browse/index.html'>Project page</a>...
+  </div>
+</body>
+

data/lib/miga/cli/action/browse/style.css

@@ -0,0 +1,97 @@
+body {
+  font-size: .875rem;
+}
+
+/*
+ * Sidebar
+ */
+
+.sidebar {
+  position: fixed;
+  top: 0;
+  bottom: 0;
+  left: 0;
+  z-index: 100; /* Behind the navbar */
+  padding: 48px 0 0; /* Height of navbar */
+  box-shadow: inset -1px 0 0 rgba(0, 0, 0, .1);
+}
+
+@media (max-width: 767.98px) {
+  .sidebar {
+    top: 3rem;
+  }
+}
+
+.sidebar-sticky {
+  position: relative;
+  top: 0;
+  height: calc(100vh - 48px);
+  padding-top: .5rem;
+  overflow-x: hidden;
+  overflow-y: auto; /* Scrollable contents if viewport is shorter than content. */
+}
+
+@supports ((position: -webkit-sticky) or (position: sticky)) {
+  .sidebar-sticky {
+    position: -webkit-sticky;
+    position: sticky;
+  }
+}
+
+.sidebar .nav-link {
+  font-weight: 500;
+  color: #333;
+}
+
+.sidebar .nav-link .feather {
+  margin-right: 4px;
+  color: #999;
+}
+
+.sidebar .nav-link.active {
+  color: #007bff;
+}
+
+.sidebar .nav-link:hover .feather,
+.sidebar .nav-link.active .feather {
+  color: inherit;
+}
+
+.sidebar-heading {
+  font-size: .75rem;
+  text-transform: uppercase;
+}
+
+/*
+ * Navbar
+ */
+
+.navbar-brand {
+  padding-top: .75rem;
+  padding-bottom: .75rem;
+  font-size: 1rem;
+  background-color: rgba(0, 0, 0, .25);
+  box-shadow: inset -1px 0 0 rgba(0, 0, 0, .25);
+}
+
+.navbar .navbar-toggler {
+  top: .25rem;
+  right: 1rem;
+}
+
+.navbar .form-control {
+  padding: .75rem 1rem;
+  border-width: 0;
+  border-radius: 0;
+}
+
+.form-control-dark {
+  color: #fff;
+  background-color: rgba(255, 255, 255, .1);
+  border-color: rgba(255, 255, 255, .1);
+}
+
+.form-control-dark:focus {
+  border-color: transparent;
+  box-shadow: 0 0 0 3px rgba(255, 255, 255, .25);
+}

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

@@ -27,10 +27,13 @@ class MiGA::Cli::Action::DerepWf < MiGA::Cli::Action
         '--threshold FLOAT', Float,
         "Metric threshold (%) to dereplicate. By default: #{cli[:threshold]}"
       ) { |v| cli[:threshold] = v }
+      opt.on(
+        '--quality',
+        'Use genome with highest quality as clade representatives (default)'
+      ) { |v| cli[:criterion] = :quality }
       opt.on(
         '--medoids',
-        'Use medoids as clade representatives',
-        'By default: Use genome with the highest quality'
+        'Use medoids as clade representatives'
       ) { |v| cli[:criterion] = :medoids }
       opt.on(
         '--no-collection',
@@ -47,12 +50,18 @@ class MiGA::Cli::Action::DerepWf < MiGA::Cli::Action
 
   def perform
     # Input data
-    p = create_project(:assembly,
-                       { run_project_stats: false, run_clades: false,
-                         gsp_metric: cli[:metric], :"gsp_#{cli[:metric]}" => cli[:threshold] },
-                       { run_mytaxa_scan: false, run_ssu: false })
+    p = create_project(
+      :assembly,
+      {
+        run_project_stats: false,
+        run_clades: false,
+        gsp_metric: cli[:metric],
+        :"gsp_#{cli[:metric]}" => cli[:threshold]
+      },
+      { run_mytaxa_scan: false, run_ssu: false }
+    )
     unless cli[:threshold] >= 0.0 && cli[:threshold] <= 100.0
-      raise "The threshold of identity must be in the range [0,100]"
+      raise 'The threshold of identity must be in the range [0,100]'
     end
 
     # Run
@@ -65,8 +74,8 @@ class MiGA::Cli::Action::DerepWf < MiGA::Cli::Action
   private
 
   def dereplicate(p)
-    cli.say "Extracting genomospecies clades"
-    r = p.result(:clade_finding) or raise "Result unavailable: run failed"
+    cli.say 'Extracting genomospecies clades'
+    r = p.result(:clade_finding) or raise 'Result unavailable: run failed'
     c_f = r.file_path(:clades_gsp) or raise 'Result incomplete: run failed'
     clades = File.readlines(c_f).map { |i| i.chomp.split("\t") }
     rep = representatives(p)
@@ -87,7 +96,7 @@ class MiGA::Cli::Action::DerepWf < MiGA::Cli::Action
   end
 
   def representatives(p)
-    cli.say "Identifying representatives"
+    cli.say 'Identifying representatives'
     f = File.expand_path('representatives.txt', cli[:outdir])
     if cli[:criterion] == :medoids
       FileUtils.cp(p.result(:clade_finding).file_path(:medoids_gsp), f)

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

@@ -38,7 +38,7 @@ class MiGA::Cli::Action::Stats < MiGA::Cli::Action
     end
     if cli[:key].nil?
       r[:stats].each do |k, v|
-        k_n = k == :g_c_content ? 'G+C content' : k.to_s.unmiga_name.capitalize
+        k_n = k.to_s.unmiga_name.sub(/^./, &:upcase)
         cli.puts "#{k_n}: #{v.is_a?(Array) ? v.join(' ') : v}"
       end
     else

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

@@ -169,6 +169,7 @@ module MiGA::Cli::Action::Wf
                  '--tab', '--ref', '--active'
                ])
     end
+    call_cli(['browse', '-P', cli[:outdir]])
   end
 
   def cleanup

data/lib/miga/cli/base.rb

@@ -11,39 +11,40 @@ module MiGA::Cli::Base
     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: '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',
     # Datasets
-    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',
+    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',
+    rm: 'Remove a dataset from an MiGA project',
+    find: 'Find 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',
+    ls: 'List all registered datasets in an MiGA project',
+    archive: 'Generate 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',
-    next_step: 'Returns 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 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',
     # Objects (Datasets or Projects)
-    edit: 'Edits the metadata of a dataset or project',
+    edit: 'Edit 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',
+    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',
     # Taxonomy
-    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',
+    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 = {

data/lib/miga/common/format.rb

@@ -68,15 +68,20 @@ module MiGA::Common::Format
   # a FastA or FastQ file (supports gzipped files). The +format+ must be a
   # Symbol, one of +:fasta+ or +:fastq+. Additional estimations can be
   # controlled via the +opts+ Hash. Supported options include:
-  # - +:n50+: If true, it also returns the N50 and the median (in bp)
-  # - +:gc+: If true, it also returns the G+C content (in %)
-  # - +:x+: If true, it also returns the undetermined bases content (in %)
+  # - +:n50+: Include the N50 and the median (in bp)
+  # - +:gc+: Include the G+C content (in %)
+  # - +:x+: Include the undetermined bases content (in %)
+  # - +:skew+: Include G-C and A-T sequence skew (in %; forces gc: true).
+  #   See definition used here in DOI:10.1177/117693430700300006
   def seqs_length(file, format, opts = {})
+    opts[:gc] = true if opts[:skew]
     fh = file =~ /\.gz/ ? Zlib::GzipReader.open(file) : File.open(file, 'r')
     l = []
     gc = 0
     xn = 0
-    i = 0 # <- Zlib::GzipReader doesn't set `$.`
+    t  = 0
+    c  = 0
+    i  = 0 # <- Zlib::GzipReader doesn't set `$.`
     fh.each_line do |ln|
       i += 1
       if (format == :fasta and ln =~ /^>/) or
@@ -86,6 +91,10 @@ module MiGA::Common::Format
         l[l.size - 1] += ln.chomp.size
         gc += ln.scan(/[GCgc]/).count if opts[:gc]
         xn += ln.scan(/[XNxn]/).count if opts[:x]
+        if opts[:skew]
+          t += ln.scan(/[Tt]/).count
+          c += ln.scan(/[Cc]/).count
+        end
       end
     end
     fh.close
@@ -97,6 +106,12 @@ module MiGA::Common::Format
     o[:sd]  = Math.sqrt o[:var]
     o[:gc]  = 100.0 * gc / o[:tot] if opts[:gc]
     o[:x]   = 100.0 * xn / o[:tot] if opts[:x]
+    if opts[:skew]
+      at = o[:tot] - gc
+      o[:at_skew] = 100.0 * (2 * t - at) / at
+      o[:gc_skew] = 100.0 * (2 * c - gc) / gc
+    end
+
     if opts[:n50]
       l.sort!
       thr = o[:tot] / 2
@@ -132,9 +147,14 @@ class String
   end
 
   ##
-  # Replace underscores by spaces or dots (depending on context).
+  # Replace underscores by spaces or other symbols depending on context
   def unmiga_name
-    gsub(/_(str|sp|subsp|pv)__/, '_\\1._').tr('_', ' ')
+    gsub(/_(str|sp|subsp|pv)__/, '_\\1._')
+      .gsub(/g_c_(content)/, 'G+C \\1')
+      .gsub(/g_c_(skew)/, 'G-C \\1')
+      .gsub(/a_t_(skew)/, 'A-T \\1')
+      .gsub(/x_content/, &:capitalize)
+      .tr('_', ' ')
   end
 
   ##

data/lib/miga/daemon.rb

@@ -91,7 +91,8 @@ class MiGA::Daemon < MiGA::MiGA
     flush!
     if (loop_i % 12).zero?
       purge!
-      recalculate_status!
+      # TEMPORARILY DISABLED:
+      # recalculate_status!
     end
     save_status
     sleep(latency)

data/lib/miga/dataset/base.rb

@@ -66,7 +66,7 @@ module MiGA::Dataset::Base
   @@PREPROCESSING_TASKS = [
     :raw_reads, :trimmed_reads, :read_quality, :trimmed_fasta,
     :assembly, :cds, :essential_genes, :ssu, :mytaxa, :mytaxa_scan,
-    :distances, :taxonomy, :stats
+    :taxonomy, :distances, :stats
   ]
 
   ##
@@ -77,7 +77,7 @@ module MiGA::Dataset::Base
   ##
   # 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, :taxonomy]
+  @@ONLY_NONMULTI_TASKS = [:mytaxa_scan, :taxonomy, :distances]
   @@_ONLY_NONMULTI_TASKS_H = Hash[@@ONLY_NONMULTI_TASKS.map { |i| [i, true] }]
 
   ##

data/lib/miga/result.rb

@@ -81,20 +81,22 @@ class MiGA::Result < MiGA::MiGA
   end
 
   ##
-  # Directory containing the result
-  def dir
-    File.dirname(path)
+  # Directory containing the result; by default an absolute path, if
+  # +relative+ is true returns the path relative to the parent project
+  def dir(relative = false)
+    relative ? relative_dir : File.dirname(path)
   end
 
   ##
-  # Absolute path to the file(s) defined by symbol +k+
-  def file_path(k)
+  # Absolute path to the file(s) defined by symbol +k+, or relative
+  # path if +relative+ is true
+  def file_path(k, relative = false)
     k = k.to_sym
     f = self[:files].nil? ? nil : self[:files][k]
     return nil if f.nil?
-    return File.expand_path(f, dir) unless f.is_a? Array
+    return File.join(dir(relative), f) unless f.is_a? Array
 
-    f.map { |fi| File.expand_path(fi, dir) }
+    f.map { |fi| File.join(dir(relative), fi) }
   end
 
   ##

data/lib/miga/result/stats.rb

@@ -17,32 +17,45 @@ module MiGA::Result::Stats
     self[:stats]
   end
 
+  ##
+  # Access the stats entry of results
+  def stats
+    self[:stats]
+  end
+
   private
 
   def compute_stats_raw_reads
     stats = {}
+    seq_opts = { gc: true, x: true, skew: true }
     if self[:files][:pair1].nil?
-      s = MiGA::MiGA.seqs_length(file_path(:single), :fastq, gc: true, x: true)
+      s = MiGA::MiGA.seqs_length(file_path(:single), :fastq, seq_opts)
       stats = {
         reads: s[:n],
         length_average: [s[:avg], 'bp'],
         length_standard_deviation: [s[:sd], 'bp'],
         g_c_content: [s[:gc], '%'],
-        x_content: [s[:x], '%']
+        x_content: [s[:x], '%'],
+        g_c_skew: [s[:gc_skew], '%'],
+        a_t_skew: [s[:at_skew], '%']
       }
     else
-      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)
+      s1 = MiGA::MiGA.seqs_length(file_path(:pair1), :fastq, seq_opts)
+      s2 = MiGA::MiGA.seqs_length(file_path(:pair2), :fastq, seq_opts)
       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], '%'],
+        forward_g_c_skew: [s1[:gc_skew], '%'],
+        forward_a_t_skew: [s1[:at_skew], '%'],
         reverse_length_average: [s2[:avg], 'bp'],
         reverse_length_standard_deviation: [s2[:sd], 'bp'],
         reverse_g_c_content: [s2[:gc], '%'],
-        reverse_x_content: [s2[:x], '%']
+        reverse_x_content: [s2[:x], '%'],
+        reverse_g_c_skew: [s2[:gc_skew], '%'],
+        reverse_a_t_skew: [s2[:at_skew], '%']
       }
     end
     stats
@@ -50,19 +63,22 @@ module MiGA::Result::Stats
 
   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, x: true)
+    s = MiGA::MiGA.seqs_length(f, :fasta, gc: true, x: true, skew: true)
     {
       reads: s[:n],
       length_average: [s[:avg], 'bp'],
       length_standard_deviation: [s[:sd], 'bp'],
       g_c_content: [s[:gc], '%'],
-      x_content: [s[:x], '%']
+      x_content: [s[:x], '%'],
+      g_c_skew: [s[:gc_skew], '%'],
+      a_t_skew: [s[:at_skew], '%']
     }
   end
 
   def compute_stats_assembly
     s = MiGA::MiGA.seqs_length(
-      file_path(:largecontigs), :fasta, n50: true, gc: true, x: true
+      file_path(:largecontigs), :fasta,
+      n50: true, gc: true, x: true, skew: true
     )
     {
       contigs: s[:n],
@@ -70,7 +86,9 @@ module MiGA::Result::Stats
       total_length: [s[:tot], 'bp'],
       longest_sequence: [s[:max], 'bp'],
       g_c_content: [s[:gc], '%'],
-      x_content: [s[:x], '%']
+      x_content: [s[:x], '%'],
+      g_c_skew: [s[:gc_skew], '%'],
+      a_t_skew: [s[:at_skew], '%']
     }
   end
 
@@ -133,7 +151,7 @@ module MiGA::Result::Stats
       source.save
 
       # Inactivate low-quality datasets
-      min_qual = (project.metadata[:min_qual] || 50)
+      min_qual = (project.metadata[:min_qual] || 25)
       if min_qual != 'no' && stats[:quality] < min_qual
         source.inactivate! 'Low quality genome'
       end

data/lib/miga/version.rb

@@ -8,7 +8,7 @@ module MiGA
   # - Float representing the major.minor version.
   # - Integer representing gem releases of the current version.
   # - Integer representing minor changes that require new version number.
-  VERSION = [0.7, 10, 2]
+  VERSION = [0.7, 13, 0]
 
   ##
   # Nickname for the current major.minor version.
@@ -16,7 +16,7 @@ module MiGA
 
   ##
   # Date of the current gem release.
-  VERSION_DATE = Date.new(2020, 6, 30)
+  VERSION_DATE = Date.new(2020, 7, 31)
 
   ##
   # Reference of MiGA.

data/scripts/aai_distances.bash

@@ -13,17 +13,20 @@ echo -n "" > miga-project.log
 DS=$(miga ls -P "$PROJECT" --ref --no-multi --active)
 
 # Extract values
-echo "metric a b value sd n omega" | tr " " "\\t" >miga-project.txt
-for i in $DS ; do
-  echo "SELECT CASE WHEN omega!=0 THEN 'AAI' ELSE 'hAAI_AAI' END," \
-    " seq1, seq2, aai, sd, n, omega from aai;" \
-    | sqlite3 "$i.db" | tr "\\|" "\\t" >>miga-project.txt
-  echo "$i" >> miga-project.log
-done
+rm -f miga-project.txt
+(
+  echo "metric a b value sd n omega" | tr " " "\\t"
+  for i in $DS ; do
+    echo "SELECT CASE WHEN omega!=0 THEN 'AAI' ELSE 'hAAI_AAI' END," \
+      " seq1, seq2, aai, sd, n, omega from aai;" \
+      | sqlite3 "$i.db" | tr "\\|" "\\t"
+    echo "$i" >> miga-project.log
+  done
+) | gzip -9c > miga-project.txt.gz
 
 # R-ify
 echo "
-aai <- read.table('miga-project.txt', sep='\\t', h=T, as.is=TRUE);
+aai <- read.table(gzfile('miga-project.txt.gz'), sep='\\t', h=T, as.is=TRUE);
 save(aai, file='miga-project.Rdata');
 if(sum(aai[,'a'] != aai[,'b']) > 0){
   h <- hist(aai[aai[,'a'] != aai[,'b'], 'value'], breaks=100, plot=FALSE);
@@ -35,9 +38,6 @@ if(sum(aai[,'a'] != aai[,'b']) > 0){
 }
 " | R --vanilla
 
-# Gzip
-gzip -9 -f miga-project.txt
-
 # Finalize
 miga date > "miga-project.done"
 miga add_result -P "$PROJECT" -r "$SCRIPT" -f

data/scripts/ani_distances.bash

@@ -13,16 +13,19 @@ echo -n "" > miga-project.log
 DS=$(miga ls -P "$PROJECT" --ref --no-multi --active)
 
 # Extract values
-echo "metric a b value sd n omega" | tr " " "\\t" >miga-project.txt
-for i in $DS ; do
-  echo "SELECT 'ANI', seq1, seq2, ani, sd, n, omega from ani ;" \
-    | sqlite3 "$i.db" | tr "\\|" "\\t" >>miga-project.txt
-  echo "$i" >> miga-project.log
-done
+rm -f miga-project.txt
+(
+  echo "metric a b value sd n omega" | tr " " "\\t"
+  for i in $DS ; do
+    echo "SELECT 'ANI', seq1, seq2, ani, sd, n, omega from ani ;" \
+      | sqlite3 "$i.db" | tr "\\|" "\\t"
+    echo "$i" >> miga-project.log
+  done
+) | gzip -9c > miga-project.txt.gz
 
 # R-ify
 echo "
-ani <- read.table('miga-project.txt', sep='\\t', h=T, as.is=TRUE);
+ani <- read.table(gzfile('miga-project.txt.gz'), sep='\\t', h=T, as.is=TRUE);
 save(ani, file='miga-project.Rdata');
 if(sum(ani[,'a'] != ani[,'b']) > 0){
   h <- hist(ani[ani[,'a'] != ani[,'b'], 'value'], breaks=100, plot=FALSE);
@@ -34,9 +37,6 @@ if(sum(ani[,'a'] != ani[,'b']) > 0){
 }
 " | R --vanilla
 
-# Gzip
-gzip -9 -f miga-project.txt
-
 # Finalize
 miga date > "miga-project.done"
 miga add_result -P "$PROJECT" -r "$SCRIPT" -f

data/scripts/cds.bash

@@ -20,7 +20,6 @@ fi
 TYPE=$(miga ls -P "$PROJECT" -D "$DATASET" -m type | cut -f 2)
 case "$TYPE" in
   metagenome|virome)
-    $CMD -p meta
     prodigal -a "${DATASET}.faa" -d "${DATASET}.fna" -o "${DATASET}.gff3" \
       -f gff -q -i "../05.assembly/${DATASET}.LargeContigs.fna" -p meta
     ;;

data/scripts/haai_distances.bash

@@ -17,30 +17,30 @@ echo -n "" > miga-project.log
 DS=$(miga ls -P "$PROJECT" --ref --no-multi --active)
 
 # Extract values
-echo "metric a b value sd n omega" | tr " " "\\t" >miga-project.txt
-for i in $DS ; do
-  echo "SELECT 'hAAI', seq1, seq2, aai, sd, n, omega from aai ;" \
-    | sqlite3 "$i.db" | tr "\\|" "\\t" >>miga-project.txt
-  echo "$i" >> miga-project.log
-done
+rm -f miga-project.txt
+(
+  echo "metric a b value sd n omega" | tr " " "\\t"
+  for i in $DS ; do
+    echo "SELECT 'hAAI', seq1, seq2, aai, sd, n, omega from aai ;" \
+      | sqlite3 "$i.db" | tr "\\|" "\\t"
+    echo "$i" >> miga-project.log
+  done
+) | gzip -9c > miga-project.txt.gz
 
 # R-ify
 echo "
-haai <- read.table('miga-project.txt', sep='\\t', h=T, as.is=TRUE);
+haai <- read.table(gzfile('miga-project.txt.gz'), sep='\\t', h=T, as.is=TRUE);
 save(haai, file='miga-project.Rdata');
 if(sum(haai[,'a'] != haai[,'b']) > 0){
   h <- hist(haai[haai[,'a'] != haai[,'b'], 'value'], breaks=100, plot=FALSE);
   write.table(
     cbind(h[['breaks']][-length(h[['breaks']])],
-      h[['breaks']][-1],h[['counts']]),
+      h[['breaks']][-1], h[['counts']]),
     file='miga-project.hist', quote=FALSE, sep='\\t',
     col.names=FALSE, row.names=FALSE);
 }
 " | R --vanilla
 
-# Gzip
-gzip -9 -f miga-project.txt
-
 # Finalize
 miga date > "miga-project.done"
 miga add_result -P "$PROJECT" -r "$SCRIPT" -f

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: miga-base
 version: !ruby/object:Gem::Version
-  version: 0.7.10.2
+  version: 0.7.13.0
 platform: ruby
 authors:
 - Luis M. Rodriguez-R
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2020-06-30 00:00:00.000000000 Z
+date: 2020-07-31 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: daemons
@@ -118,6 +118,16 @@ files:
 - lib/miga/cli/action/add.rb
 - lib/miga/cli/action/add_result.rb
 - lib/miga/cli/action/archive.rb
+- lib/miga/cli/action/browse.rb
+- lib/miga/cli/action/browse/about.html
+- lib/miga/cli/action/browse/dataset.html
+- lib/miga/cli/action/browse/dataset_menu_item.html
+- lib/miga/cli/action/browse/datasets.html
+- lib/miga/cli/action/browse/favicon-32.png
+- lib/miga/cli/action/browse/index.html
+- lib/miga/cli/action/browse/layout.html
+- lib/miga/cli/action/browse/redirect.html
+- lib/miga/cli/action/browse/style.css
 - lib/miga/cli/action/classify_wf.rb
 - lib/miga/cli/action/console.rb
 - lib/miga/cli/action/daemon.rb
@@ -550,7 +560,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.1.2
+rubyforge_project:
+rubygems_version: 2.5.2.3
 signing_key:
 specification_version: 4
 summary: MiGA