bio-gfastqc 0.0.1 → 0.0.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: cac0f88eccf1fbe76912a8a3a0b4fb6a25a436dd
-  data.tar.gz: 37a6c8e3af76d4c896fb2ae57ff9a34335fa3014
+  metadata.gz: ef248148ccf0f2c2ba5d8171ab80eb6e52a30b77
+  data.tar.gz: 0689965afa3c8c63a54721718e9e56e86763324d
 SHA512:
-  metadata.gz: 44cd149bc4a1d5423b2dedf2fe7fa9da739ef4c3fbbc30e29980e97d6b621b2856230de52aa1069f76dc6c8e90db8e78f0b104badb23de9b9cc7b84439f227bf
-  data.tar.gz: f97b5e978ebe87225c793ab81e06ddbac514ee80fc9220ee39bf8a418593a0078f422d749d7e440830ec02b0f27147fa0cded93195fe47ffe077ae6957075b89
+  metadata.gz: be301904e3135c415db9c65ca330352d3f6ae7364b1c53c0f8aab83ed9045205c9f162440c28aefffedb18db05c0ccaa55c00654762f70f7017c9cd60cb9fbe3
+  data.tar.gz: b2b160b23a4f7bd7098eaf7b53c19b64e2da5e5f4d60b42b2aec9b9fa2158e02853704fc561496c65f15216b8a47092591e14bf44bf40912d5f1f08c297be220

data/README.md

@@ -2,7 +2,7 @@
 
 [![Build Status](https://secure.travis-ci.org/helios/bioruby-gfastqc.png)](http://travis-ci.org/helios/bioruby-gfastqc)
 
-Full description goes here
+Bioinformatics. Aggregate FastQC (quality control for Next Generation Sequencing -NGS-) results from many different samples in a single web page, with charts and tables organized and simplified. The main goal is to speed up the communication process with colleagues (PIs, Biologists, BioInformaticians).
 
 Note: this software is under active development!
 
@@ -20,6 +20,8 @@ require 'bio-gfastqc'
 
 The API doc is online. For more code examples see the test files in
 the source tree.
+
+Note: at this time there is not a real API, it will follow.
         
 ## Project home page
 
@@ -43,18 +45,31 @@ it contents is for example:
 
 then run the script in the directory of the `config.yml` file and specify the sub directory for each sampel where is located the result of the FASTQC
 
-    ruby gfastqc.rb -a R1 -b R2
+    gfastqc -a R1 -b R2
 
 in case you have the results of FastQC in a sub folder and you want to keep the definition of the sample independen from it, you can use the step option
 
-    ruby gfastqc.rb -a R1 -b R2 --step qc_pre_trimming
+    gfastqc -a R1 -b R2 --step qc_pre_trimming
 
 Then open index.html in your browser
 
+### Pipengine
+Pipengine, https://github.com/fstrozzi/bioruby-pipengine, a simple launcher for complex biological pipelines. Because we are developing it we found usefult to reuse some best practices from it. An example is the `-s/--step` options which let you select the sample inner directory from which grab the FastQC results. In the current examples we defined just samples and their absolut path, but following the Pipengine directives it is necessary to define another tag:
+
+    output: /path/where_the_pipe_engine_data_are_processed_and_saved
+
+to reuse that tag from gfastqc the user can simply select the option
+
+    -p/--pipengine
+
+the software will look for the results of single fastqc applied to the different samples in the `output` directory.
+
 
 
 ## TODO
 
+* ~~read output tag from sample config file (YAML)~~
+* ~~add reference to pipengine~~
 * avoid user to specify -a and -b. By default discover zip files and ordering them define the first and second strand.
 * ~~package everything as a gem~~
 * provide better documentation for installing the gem on multiple system (GNU/Linux, OSX, Windows)

data/Rakefile

@@ -17,8 +17,8 @@ Jeweler::Tasks.new do |gem|
   gem.name = "bio-gfastqc"
   gem.homepage = "http://github.com/helios/bioruby-gfastqc"
   gem.license = "MIT"
-  gem.summary = %Q{TODO: one-line summary of your gem}
-  gem.description = %Q{TODO: longer description of your gem}
+  gem.summary = %Q{Aggregate FastQC (quality control for Next Generation Sequencing -NGS-)}
+  gem.description = %Q{Bioinformatics. Aggregate FastQC (quality control for Next Generation Sequencing -NGS-) results from many different samples in a single web page, with charts and tables organized and simplified. The main goal is to speed up the communication process with colleagues (PIs, Biologists, BioInformaticians).}
   gem.email = "ilpuccio.febo@gmail.com"
   gem.authors = ["Raoul Jean Pierre Bonnal"]
   # dependencies defined in Gemfile

data/VERSION

@@ -1 +1 @@
-0.0.1
+0.0.4

data/bin/gfastqc

@@ -40,6 +40,7 @@ require 'bio-gfastqc'
 # Bio::Log::CLI.trace('info')
 
 
+
 class OptHandlingBox
   def  self.parse(args)
     options = OpenStruct.new
@@ -54,6 +55,16 @@ class OptHandlingBox
         options.config = config
       end
 
+      opts.on('-p', '--pipengine',
+              'if you used pipengine to produce the fastqc result is better to use this option. gfastqc will look into the output directory specified in the sample.yml') do
+        options.pipengine = true
+      end
+
+      opts.on('-g', '--groups',
+              'if you specified groups in your configuration file, select this option') do
+        options.groups = true
+      end
+
       opts.on('-s', '--step [STEP]',
               'choose the step from which extract the fastqc data') do |step|
         options.step = step
@@ -69,6 +80,11 @@ class OptHandlingBox
         options.second = second
       end
 
+      opts.on('-n', '--usename',
+              'use sample name to build the path (maybe later implement placeholding like pipengine') do
+        options.usename = true
+      end
+
 
       opts.on_tail("-h", "--help", "Show this message") do
         puts opts
@@ -81,66 +97,37 @@ class OptHandlingBox
   end #parse
 end #class OptGtfSplit
 
+
+
+
+
+
+
+
+
+
 options = OptHandlingBox.parse(ARGV)
 
-if !File.exists?(options.config)
-  puts
-  puts "Warning: there is not config file #{options.config}"
-  exit
-end
-config = YAML.load_file(options.config)
-@data = {}
-@tables = {}
-@base_file_names = []
-@base_file_names << options.first #this must be mandatory
-@base_file_names << options.second if options.second # this can be optional
-
-
-config['samples'].each_pair do |name, path|
-  @data[name] = {}
-  @tables[name] = {}
-  @base_file_names.each do |base_file_name|
-    @data[name][base_file_name]={}
-    @tables[name][base_file_name]={}
-    file = File.join(path, options.step, "#{base_file_name}_fastqc.zip")
-    Zip::File.open(file) do |zip_file|
-      zip_file.glob('*/Images/*.png').each do |entry|
-        @data[name][base_file_name][File.basename(entry.name,".png")]=Base64.encode64(entry.get_input_stream.read)
-      end #each entry
-      zip_file.glob('*/fastqc_data.txt').each do |entry|
-        entry.get_input_stream.read.scan(/>>(.*?)>>END_MODULE/m).each do |match|
-          match_data = match.first.split("\n")
-          field_name, status = match_data[0].split("\t")
-          begin 
-            header = match_data[1].tr("#","").split("\t")
-            content = match_data[2..-1].map do |data_row|
-              data_row.split("\t")
-            end
-            # puts field_name
-            @tables[name][base_file_name][field_name.tr(" ","_")]={ "status" => status,
-              "header"=> header,
-              "content" => content
-            }
-          rescue
-            # $stderr.puts match_data.inspect #This is a generic warning to notify the user that this records has no data associated with.
-          end
-
-        end #match
-      end #fastq data.txt
-    end #zip
-  end #files
-end
+@gfastqc = Bio::GFASTQC.new(options)
+
+
+
+
+
+
 # File.open('test.json','w') do |file|
 #   file.write data.to_json
 # end
 
-@type_images = %w(kmer_profiles per_sequence_gc_content per_base_sequence_content duplication_levels sequence_length_distribution per_sequence_quality per_base_quality adapter_content per_base_n_content per_tile_quality)
-@type_tables = %w(Adapter_Content Basic_Statistics Kmer_Content Per_base_N_content Per_base_sequence_content Per_base_sequence_quality Per_sequence_quality_scores Sequence_Duplication_Levels Sequence_Length_Distribution)
+@gfastqc.type_images = %w(kmer_profiles per_sequence_gc_content per_base_sequence_content duplication_levels sequence_length_distribution per_sequence_quality per_base_quality adapter_content per_base_n_content per_tile_quality)
+@gfastqc.type_tables = %w(Adapter_Content Basic_Statistics Kmer_Content Overrepresented_sequences Per_base_N_content Per_base_sequence_content Per_base_sequence_quality Per_sequence_quality_scores Sequence_Duplication_Levels Sequence_Length_Distribution)
 # dropped tables to avoid wast of space or not so informative:
 # Per_sequence_GC_content Overrepresented_sequences Per_tile_sequence_quality 
 # Overrepresented_sequences temporary removed it seems that when this fields pass the test there are no data associated with
 
 
+# puts @gfastqc.inspect
+
 erb_file = 'index.html.erb'
 
 html_file = File.basename(erb_file, '.erb') #=>"page.html"

data/lib/bio-gfastqc/gfastqc.rb

@@ -1,3 +1,128 @@
 
-module BioGfastqc
-end
+module Bio
+  class GFASTQC
+    attr_accessor :data, :tables, :config, :output, :base_file_names, :step
+    attr_accessor :type_images #An array of names of images that must be reported into the html page
+    attr_accessor :type_tables #An array of names of tables that must be reported into the html page 
+    attr_reader :options
+
+    def initialize(options=OpenStruct.new)
+      @options = options
+      @config = YAML.load_file(options.config)
+      @data = Hash.new { |hash, key| hash[key] = Hash.new { |ihash, ikey| ihash[ikey] = {} } }
+      @tables = Hash.new { |hash, key| hash[key] = Hash.new { |ihash, ikey| ihash[ikey] = {} } }
+      @base_file_names = []
+      @base_file_names << options.first #this must be mandatory
+      @base_file_names << options.second if options.second # this can be optional
+      @step = options.step
+
+      if options.pipengine 
+        unless @config['resources'] && @config['resources']['output']
+          raise "Error: If you selected the compatible option -p/--pipengine, an 'output' tag must occour in your configuration file."
+        end
+      end #pipengine
+
+      @output = get_output
+
+      read_each_sample
+
+    end #initialize
+
+    def use_pipengine?
+      @options.pipengine
+    end 
+
+    def use_groups?
+      @options.groups
+    end
+
+    def use_sample_name?
+      @options.usename
+    end
+
+    def samples
+      @config['samples']
+    end
+
+    protected
+
+    def process_sample(sample_name, path, group_name='')
+
+      base_file_names.each do |base_file_name|
+        # data[name][base_file_name]={}
+        # tables[name][base_file_name]={}
+        filename = use_sample_name? ? "#{name}_#{base_file_name}" : base_file_name
+        file = File.join(use_pipengine? ? File.join(output, group_name, sample_name) : path, step, "#{filename}_fastqc.zip")
+        Zip::File.open(file) do |zip_file|
+          zip_file.glob('*/Images/*.png').each do |entry|
+            field_name = File.basename(entry.name,".png")
+            data[sample_name][base_file_name][field_name]=Base64.encode64(entry.get_input_stream.read)
+          end #each entry
+          zip_file.glob('*/fastqc_data.txt').each do |entry|
+            entry.get_input_stream.read.scan(/>>(.*?)>>END_MODULE/m).each do |match|
+              match_data = match.first.split("\n")
+              field_name, status = match_data[0].split("\t")
+              begin 
+              if field_name == "Overrepresented sequences" && status == 'pass'
+                header = []
+                content = []
+              else
+                header = match_data[1].tr("#","").split("\t")
+                content = match_data[2..-1].map do |data_row|
+                  data_row.split("\t")
+                end
+              end
+                # puts field_name
+                # puts header
+                field_name = field_name.tr(" ","_")
+                tables[sample_name][base_file_name][field_name]={ "status" => status,
+                  "header"=> header,
+                  "content" => content
+                }
+              rescue
+               $stderr.puts match.inspect #This is a generic warning to notify the user that this records has no data associated with.
+               $stderr.puts field_name
+               $stderr.puts status
+              end #begin
+
+            end #match
+          end #fastq data.txt
+        end #zip
+      end #files
+
+    end #process_sample
+
+
+    def read_each_sample
+      if options.groups
+      #both are exact the name only iterate on groups and the other only on samples (without groups)
+        samples.each_pair do |group_name, sample|
+          sample.each_pair do |sample_name, path|
+            process_sample(sample_name, path, group_name)
+          end #iterate over samples
+        end #iterage over groups
+      else
+        samples.each_pair do |sample_name, path|
+          process_sample(sample_name, path)
+        end #iterate over samples
+      end #groups or not
+    end 
+
+
+
+    
+    def get_output
+      if @config['output']
+        @config['output']
+      elsif options.pipengine && @config['resources'] && @config['resources']['output']
+        @config['resources']['output']
+      elsif @config['resources'] && @config['resources']['output']
+        @config['resources']['output']
+      else
+        '.'
+      end #output
+    end #get_output  
+
+
+  end #GFASTQC
+end #Bio

data/lib/bio-gfastqc/index.html.erb

@@ -31,33 +31,68 @@
 
         <div role="tabpanel">
           <ul class="nav nav-tabs" role="tablist" >
+              <li role="presentation"><a href="#summaries" aria-controls="summaries" role="tab" data-toggle="tab">Summaries</a></li>
               <li role="presentation"><a href="#charts" aria-controls="charts" role="tab" data-toggle="tab">Charts</a></li>
               <li role="presentation"><a href="#tables" aria-controls="tables" role="tab" data-toggle="tab">Tables</a></li>
           </ul>
           <div class="tab-content">
+      <div role="tabpanel" class="tab-pane" id="summaries">
+      <!-- Summaries Start-->
+
+                <table id="summy" class="display" cellspacing="0" width="100%">
+                  <thead>
+                    <tr>
+                    <% (["source"]+@gfastqc.type_tables).each do |col_name| %>
+                      <th><%= col_name %></th>
+                    <% end %>  
+                    </tr>
+                  </thead>
+                  <tbody>
+                  <% @gfastqc.tables.each_pair do |sample_name, reads| %>
+                    <tr>
+                      <td><%= sample_name %></td>
+                      <% @gfastqc.type_tables.each do |col_name| %>
+                        <td>
+                          <% reads.each_pair do |reads_name, tables| %>
+                            <% if tables[col_name]["status"] == 'fail'%>
+                            <%= "f:#{reads_name}" %>
+                            <% elsif tables[col_name]["status"] == "warn" %>
+                            <%= "w:#{reads_name}" %>
+                            <% end %>
+                          <% end %>
+                        </td>
+                      <% end %>
+                    </tr>
+                  <% end %>
+                  </tbody>
+                </table>
+
+      <!-- Summaries End-->  
+      </div>
+
 
             <div role="tabpanel" class="tab-pane" id="charts">
       <!-- Charts Start-->
         <div role="tabpanel">
           <ul class="nav nav-pills" role="tablist" >
-            <% @type_images.each do |type| %>
+            <% @gfastqc.type_images.each do |type| %>
               <li role="presentation"><a href="#<%= type %>" aria-controls="<%= type %>" role="tab" data-toggle="tab"><%= type %></a></li>
             <% end %>
           </ul>
           <div class="tab-content">
-          <% @type_images.each do |type| %>
+          <% @gfastqc.type_images.each do |type| %>
             <div role="tabpanel" class="tab-pane" id="<%= type %>">
               <div class="row">
-                <% @data.each_pair do |sample_name, pairs| %>
+                <% @gfastqc.data.each_pair do |sample_name, pairs| %>
                 <div class="col-xs-6 col-md-6">
                   <div class="caption">
                   <h3><%= sample_name %></h3>
-                  <a href="#" class="thumbnail">
-                    <img data-src="holder.js/300x200" src="data:image/png;base64,<%= pairs[@base_file_names[0]][type] %>" alt="<%= sample_name + ' ' + @base_file_names[0] %>">
-                  </a>
-                  <a href="#" class="thumbnail">
-                    <img data-src="holder.js/300x200" src="data:image/png;base64,<%= pairs[@base_file_names[1]][type] %>" alt="<%= sample_name + ' ' + @base_file_names[1] %>">
+                  <% pairs.each_pair  do |pair, images| %>
+                  <h4><%= pair %></h4>
+                  <a href="#" class="thumbnail"> 
+                    <img data-src="holder.js/300x200" src="data:image/png;base64,<%= pairs[pair][type] %>" alt="<%= sample_name + ' ' + pair %>">
                   </a>
+                  <% end %>
                   </div>
                 </div>
                 <% end %>  
@@ -73,17 +108,19 @@
       <!-- Tables Start-->
         <div role="tabpanel">
           <ul class="nav nav-pills" role="tablist" >
-            <% @type_tables.each do |type| %>
+            <% @gfastqc.type_tables.each do |type| %>
               <li role="presentation"><a href="#<%= type %>_div_table" aria-controls="<%= type %>_div_table" role="tab" data-toggle="tab"><%= type %></a></li>
             <% end %>
           </ul>
           <div class="tab-content">
 
-          <% @type_tables.each do |type| %>
+          <% @gfastqc.type_tables.each do |type| %>
             <div role="tabpanel" class="tab-pane" id="<%= type %>_div_table">
               <div class="row">
-                <% @tables.each_pair do |sample_name, reads| %>
+                <% @gfastqc.tables.each_pair do |sample_name, reads| %>
                   <% reads.each_pair do |reads_name, tables| %>
+                  <% unless tables[type]['header'].empty? %>
+                    <h3><%= sample_name + "_" + reads_name %></h3>
                     <table id="<%= type %>_<%= sample_name %>_<%= reads_name %>_table" class="display" cellspacing="0" width="100%">
                       <thead>
                         <tr>
@@ -102,6 +139,9 @@
                       <% end %>
                       </tbody>
                     </table>
+                    <% else %>
+                    <h3><%= sample_name + "_" + reads_name %> has no over represented sequences.</h3>
+                    <% end %>
                   <% end %>
                 <% end %>
               </div>             
@@ -109,7 +149,7 @@
           <% end %>
           </div>
         </div>
-      <!-- Charts End-->  
+      <!-- Tables End-->  
             </div>
 
 
@@ -125,13 +165,16 @@
 </body>
 <script type="text/javascript">
 $(document).ready(function() {
-<% @type_tables.each do |type| %>
-  <% @tables.each_pair do |sample_name, reads| %>
+$("#summy").DataTable();
+<% @gfastqc.type_tables.each do |type| %>
+  <% @gfastqc.tables.each_pair do |sample_name, reads| %>
     <% reads.each_pair do |reads_name, tables| %>                    
-      $("#<%= type %>_<%= sample_name %>_<%= reads_name %>_table").DataTable();
+      $("#"+"<%= type %>_<%= sample_name %>_<%= reads_name %>_table").DataTable();
+
     <% end %>
   <% end %>
 <% end %>
+
 } );
 </script>
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: bio-gfastqc
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 0.0.4
 platform: ruby
 authors:
 - Raoul Jean Pierre Bonnal
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-03-22 00:00:00.000000000 Z
+date: 2015-06-26 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rubyzip
@@ -111,7 +111,7 @@ dependencies:
 description: Bioinformatics. Aggregate FastQC (quality control for Next Generation
   Sequencing -NGS-) results from many different samples in a single web page, with
   charts and tables organized and simplified. The main goal is to speed up the communication
-  process with out colleagues (PIs, Biologists, BioInformaticians).
+  process with colleagues (PIs, Biologists, BioInformaticians).
 email: ilpuccio.febo@gmail.com
 executables:
 - gfastqc
@@ -157,8 +157,5 @@ rubyforge_project:
 rubygems_version: 2.4.3
 signing_key: 
 specification_version: 4
-summary: Bioinformatics. Aggregate FastQC (quality control for Next Generation Sequencing
-  -NGS-) results from many different samples in a single web page, with charts and
-  tables organized and simplified. The main goal is to speed up the communication
-  process with out colleagues (PIs, Biologists, BioInformaticians).
+summary: Aggregate FastQC (quality control for Next Generation Sequencing -NGS-)
 test_files: []