miga-base 0.7.11.0 → 0.7.12.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 7b4a168130d732c670246cd4a874272e77e5f7d88fdef00e10d81ab8e5f9979a
-  data.tar.gz: '069e2dd280b4afecb67478612f1dee35bf2cada3ae57cbc61c6e70d0ef3bd233'
+  metadata.gz: f99f8fd530489d42672cdd96123f321725b9437ee4a81e822a07854ec924ad53
+  data.tar.gz: c4d6607a4b6062b45cc94985b8bc920bb25307232851b20436ee4b9cd8a8986b
 SHA512:
-  metadata.gz: a37fd7d69339c7a63d5ac38e0c232fed96d479c3f2f2bc67b2ee956bb908d8690a55f21a6fa0185c05f209139e16b6b2ddcd6b0f36fac471f9e0b4fd2c4a5f04
-  data.tar.gz: cb156656c79f1a765281f163691650e32f90056dc767827d4b3fe958b4042e6359b810f5a3249c6902bce042f6a457507a027836797c39328889d9cbbbc5c5d0
+  metadata.gz: '03478c56a40e948ad9eb4cb09fbedc72bac331072ccf46ce5468f1f78a08e891260684771e455b92841d8af454fcab997d7d51a68360b8337ffa13c8c2ec88a4'
+  data.tar.gz: e992d10e5de206a85ac425e15c7594629f86e8088ec6f59ba820c5ecaf6c8901af0142455501a1d8af03902a3ca559d0374692e4df9f41acdceaf45d5d750b1f

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

@@ -0,0 +1,213 @@
+# 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|
+      "<li><a href='file://#{i}'>#{File.basename(i)}</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='file://#{res.file_path(key)}'>#{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/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/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/stats.rb

@@ -17,6 +17,12 @@ module MiGA::Result::Stats
     self[:stats]
   end
 
+  ##
+  # Access the stats entry of results
+  def stats
+    self[:stats]
+  end
+
   private
 
   def compute_stats_raw_reads
@@ -145,7 +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, 11, 0]
+  VERSION = [0.7, 12, 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, 7, 1)
+  VERSION_DATE = Date.new(2020, 7, 22)
 
   ##
   # Reference of MiGA.

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
     ;;

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: miga-base
 version: !ruby/object:Gem::Version
-  version: 0.7.11.0
+  version: 0.7.12.0
 platform: ruby
 authors:
 - Luis M. Rodriguez-R
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2020-07-01 00:00:00.000000000 Z
+date: 2020-07-22 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: daemons
@@ -118,6 +118,7 @@ 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/classify_wf.rb
 - lib/miga/cli/action/console.rb
 - lib/miga/cli/action/daemon.rb