seqtrimnext_report 0.0.2

data/History.txt

@@ -0,0 +1,7 @@
+=== 0.0.2 2011-06-15
+
+Some small fixes
+
+=== 0.0.1 2011-06-14
+
+* Initial release

data/Manifest.txt

@@ -0,0 +1,24 @@
+History.txt
+Manifest.txt
+PostInstall.txt
+README.rdoc
+Rakefile
+lib/seqtrimnext_report.rb
+script/console
+script/destroy
+script/generate
+test/test_helper.rb
+test/test_seqtrimnext_report.rb
+bin/generate_report.rb
+lib/seqtrimnext_report/classes/params_report.rb
+lib/seqtrimnext_report/classes/rejected_report.rb
+lib/seqtrimnext_report/classes/stats_report.rb
+lib/seqtrimnext_report/config/plugin_nts.json
+lib/seqtrimnext_report/config/plugin_seqs.json
+lib/seqtrimnext_report/latex_src/input_graph.tex
+lib/seqtrimnext_report/latex_src/main.tex
+lib/seqtrimnext_report/latex_src/output_files.tex
+lib/seqtrimnext_report/latex_src/output_graph.tex
+lib/seqtrimnext_report/latex_src/piescbi.jpg
+lib/seqtrimnext_report/latex_src/qv_graph.tex
+lib/seqtrimnext_report/latex_src/ref_seqs.png

data/PostInstall.txt

@@ -0,0 +1,7 @@
+
+For more information on seqtrimnext_report, see http://seqtrimnext_report.rubyforge.org
+
+NOTE: Change this information in PostInstall.txt 
+You can also delete it if you don't want it.
+
+

data/README.rdoc

@@ -0,0 +1,49 @@
+= seqtrimnext_report
+
+* http://www.scbi.uma.es/downloads
+
+== DESCRIPTION:
+
+A PDF report generator for SeqtrimNEXT preprocessing software from SCBI.
+
+== FEATURES/PROBLEMS:
+
+* Generates an eye-catching PDF report with the output produced by SeqtrimNEXT
+
+== SYNOPSIS:
+
+  generate_report.rb seqtrim_output_folder
+
+== REQUIREMENTS:
+
+* seqtrimnext gem
+* pdflatex binary
+
+== INSTALL:
+
+gem install seqtrimnext_report
+
+== LICENSE:
+
+(The MIT License)
+
+Copyright (c) 2011 FIXME full name
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+'Software'), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED 'AS IS', WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
+CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
+TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
+SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/Rakefile

@@ -0,0 +1,26 @@
+require 'rubygems'
+gem 'hoe', '>= 2.1.0'
+require 'hoe'
+require 'fileutils'
+require './lib/seqtrimnext_report'
+
+Hoe.plugin :newgem
+# Hoe.plugin :website
+# Hoe.plugin :cucumberfeatures
+
+# Generate all the Rake tasks
+# Run 'rake -T' to see list of generated tasks (from gem root directory)
+$hoe = Hoe.spec 'seqtrimnext_report' do
+  self.developer 'Noe Fernandez & Dario Guerrero', 'noefp@gmail.com, dariogf@gmail.com'
+  self.post_install_message = 'PostInstall.txt' # TODO remove if post-install message not required
+  self.rubyforge_name       = self.name # TODO this is default value
+  self.extra_deps         = [['seqtrimnext','>= 2.0.31']]
+
+end
+
+require 'newgem/tasks'
+Dir['tasks/**/*.rake'].each { |t| load t }
+
+# TODO - want other tests/tasks run by default? Add them to the list
+# remove_task :default
+task :default => [:spec, :featuresm, :redocs]

data/bin/generate_report.rb

@@ -0,0 +1,118 @@
+#!/usr/bin/env ruby
+
+# Noe Fdez Pozo 2011-05-11. To build a PDF with latex parsing SeqTrimNext output files
+
+#---------------------------------------------- para indicar donde estan las clases
+ROOT_PATH=File.dirname(__FILE__)
+# $: << File.expand_path(File.join(ROOT_PATH, "classes"))
+# $: << '/Users/dariogf/progs/ruby/gems/seqtrimnext/lib'
+
+#---------------------------------------------- gems
+require 'json'
+#---------------------------------------------- classes
+
+require 'seqtrimnext'
+require 'seqtrimnext_report'
+require 'params'
+require 'scbi_stats'
+require 'params_report'
+require 'stats_report'
+require 'rejected_report'
+
+#---------------------------------------------- method to parse a json
+def get_json_data(file)
+
+  data=nil
+
+  if File.exists?(file)
+    file1 = File.open(file)
+    text = file1.read
+    file1.close
+
+    text=text.gsub(/^\s*#.*$/,'').gsub(/^\n$/,'')
+    if !text.nil? && !text.empty?
+      data = JSON.parse(text)
+    end
+  end
+
+  return data
+end
+
+if ARGV.count!=1
+  puts "Usage: #{File.basename($0)} output_files_folder"
+  exit(-1)
+end
+
+#---------------------------------------------- check if files exists
+output_files=ARGV.shift
+if !Dir.exists?(output_files)
+  puts "Directory #{output_files} doesn't exists"
+  exit(-1)
+end
+
+if !File.exist?(File.join(output_files,'used_params.txt'))
+  puts "File used_params.txt not found.\n"
+  exit(-1)
+elsif !File.exist?(File.join(output_files,'initial_stats.json'))
+  puts "File initial_stats.json not found.\n"
+  exit(-1)
+elsif !File.exist?(File.join(output_files,'stats.json'))
+  puts "File stats.json not found.\n"
+  exit(-1)
+end
+
+puts "Generating report"
+puts "="*50
+puts "used_params.txt, initial_stats.json and stats.json files were found"
+
+
+#----------------------------------------------  MAIN --------------------------------
+begin
+
+  # load used params
+  all_params=Params.new(File.join(output_files,'used_params.txt'))
+  
+  # load initial and final stats
+  initial_stats = get_json_data(File.join(output_files,'initial_stats.json'))
+  stats = get_json_data(File.join(output_files,'stats.json'))
+  
+  # load json configuration
+  plugin_fix_hash = get_json_data(File.join(File.dirname(__FILE__),'..','lib','seqtrimnext_report','config','plugin_seqs.json'))
+  plugin_nts_hash = get_json_data(File.join(File.dirname(__FILE__),'..','lib','seqtrimnext_report','config','plugin_nts.json'))
+
+  output_latex=File.join(output_files,'latex')
+
+  # copy latex required files to output_folder
+  `cp -r #{File.join(File.dirname(__FILE__),'..','lib','seqtrimnext_report','latex_src')} #{output_latex}`
+  `cp -r #{File.join(output_files,'..','graphs')} #{output_latex}`
+
+  #---------------------------------------------- Parameters
+  ParamsReport.new(all_params,output_files, output_latex)
+
+  #---------------------------------------------- Statistics
+  StatsReport.new(all_params,initial_stats,stats,plugin_nts_hash, output_files, output_latex)
+
+  #---------------------------------------------- Rejected
+  RejectedReport.new(stats,plugin_fix_hash,output_files, output_latex)
+
+  #---------------------------------------------- Build pdf
+  # system('pdflatex main.tex')
+  cmd="pushd .; cd #{output_latex}; pdflatex -halt-on-error main.tex; popd"
+  puts "Running pdflatex: #{cmd}"
+
+  # it must be repeated to solve links in latex
+  `#{cmd}`
+  `#{cmd}`
+
+  if File.exists?(File.join(output_latex,'main.pdf'))
+    `cp #{File.join(output_latex,'main.pdf')} #{File.join(output_files,'statistics_report.pdf')}`
+    `zip -r #{File.join(output_files,'latex.zip')} #{output_latex}`
+    `rm -r #{output_latex}`
+  end
+
+rescue
+
+  puts "output PDF couldn't be created for this dataset"
+
+end
+# system(cmd)

data/lib/seqtrimnext_report.rb

@@ -0,0 +1,12 @@
+$:.unshift(File.dirname(__FILE__)) unless
+  $:.include?(File.dirname(__FILE__)) || $:.include?(File.expand_path(File.dirname(__FILE__)))
+
+# require 'seqtrimnext'
+
+ROOT_PATH=File.join(File.dirname(__FILE__),'seqtrimnext_report')
+
+$: << File.expand_path(File.join(ROOT_PATH, 'classes'))
+
+module SeqtrimnextReport
+   VERSION = '0.0.2'
+end

data/lib/seqtrimnext_report/classes/params_report.rb

@@ -0,0 +1,84 @@
+class ParamsReport
+	
+	def initialize(all_params,output_files, output_latex)
+		
+		# all_params.print_parameters
+		
+		params_in_pdf = {}
+
+		params_in_pdf['general']=['plugin_list','remove_clonality','min_insert_size_trimmed','min_insert_size_paired','seqtrim_version','min_sequence_size_raw']
+		params_in_pdf['quality']=['min_quality','window_width']
+		params_in_pdf['contaminants']=['blast_evalue_contaminants','blast_percent_contaminants','min_contam_seq_presence','genus','contaminants_reject','contaminants_db']
+
+		output=File.open(File.join(output_latex,'UsedParams.tex'), 'w')
+		output.puts "%!TEX root = FinalReport.tex"
+
+		output.puts '\subsection{General}'
+		print_each_group_of_params(output,all_params,params_in_pdf,'general')
+		
+		if (all_params.get_param('min_quality'))
+			output.puts '\subsection{Quality}'
+			print_each_group_of_params(output,all_params,params_in_pdf,'quality')
+		end
+		
+		if (all_params.get_param('blast_evalue_contaminants'))
+			output.puts '\subsection{Contaminants}'
+			print_each_group_of_params(output,all_params,params_in_pdf,'contaminants')
+		end
+		
+		output.close
+
+		puts "used parameters information was added to the report"
+
+	end
+	
+	def print_each_group_of_params(output,all_params,params_in_pdf,my_group)
+
+		params_in_pdf[my_group].each do |param_name|
+
+			if !all_params.get_comment('params',param_name).nil?
+				description = all_params.get_comment('params',param_name).last
+
+				description.gsub!('%','\%')
+				description.gsub!('_','\_')
+
+				if description =~/^\#\#+/
+					description = ''
+				end
+			else
+				description = ''
+			end
+
+			value = all_params.get_param(param_name)
+
+			if (param_name == 'plugin_list')
+        puts value
+				values = value.split(",")
+				output.puts "#{description}"+'\\\\'
+
+				count = 0
+				values.each do |plugin|
+					count += 1
+					output.puts '\indent'+"#{count}\. #{plugin}"+'\\\\'
+				end
+				
+				output.puts '\\\\'
+			elsif (param_name == 'contaminants_db')
+				value.gsub!('"','')
+				values = value.split(" ")
+				output.puts "#{description}"+'\\\\'
+				values.each do |plugin|
+					plugin = File.basename(plugin)
+					plugin.gsub!('_','\_')
+					output.puts '\indent \texttt{'+" #{plugin}"+'}\\\\'
+				end
+			else
+				param_name.gsub!('_','\_')
+				output.puts "#{description}"+'\\\\'
+				output.puts '\indent \texttt{'+"#{param_name}: #{value}"+'}\\\\'
+			end
+		end
+	end
+	
+end
+

data/lib/seqtrimnext_report/classes/rejected_report.rb

@@ -0,0 +1,207 @@
+class RejectedReport
+
+  def initialize(stats,plugin_fix_hash,output_files, output_latex)
+
+    # write_plugin_json
+
+    output3=File.open(File.join(output_latex,'rejected.tex'), 'w')
+    output3.puts "%!TEX root = FinalReport.tex\n\n"
+
+    input_seqs = stats['sequences']['count']['input_count'].to_i
+    rejected_seqs = stats['sequences']['count']['rejected'].to_i
+    output_seqs = stats['sequences']['count']['output_seqs'].to_i
+
+    output_seqs_paired = 0
+    total_output_seqs = 0
+    if (!stats['sequences']['count']['output_seqs_paired'].nil?)
+      output_seqs_paired = stats['sequences']['count']['output_seqs_paired'].to_i # solo cuando hay pareadas
+      total_output_seqs = output_seqs_paired+output_seqs
+    end
+    low_complex = 0
+    if (!stats['sequences']['count']['output_seqs_low_complexity'].nil?)
+      low_complex = stats['sequences']['count']['output_seqs_low_complexity'].to_i # no hay cuando es genomico
+    end
+
+    rejected_hash = {}
+    data_hash = {}
+
+    data_hash['value'] = rejected_seqs
+    data_hash['warning'] = 'OK'
+    data_hash['warning_msg'] = ''
+    data_hash['percent'] = sprintf("%0.3f", (rejected_seqs.to_f*100/input_seqs.to_f))
+    rejected_hash['rejected']=data_hash
+
+    if (!stats['sequences']['rejected'].nil?)
+      rejected_hash = load_plugins_info(stats, rejected_hash, input_seqs, plugin_fix_hash)
+
+      #-------------------------------------------------- build table
+      output3.puts '\begin{table}[H]'
+      output3.puts '\begin{center}'
+      output3.puts '\begin{tabular}{r r}'
+
+      output3.puts "Input sequences & #{input_seqs}\\\\"
+      output3.puts "Output sequences & #{output_seqs}\\\\"
+      output3.puts "Rejected sequences & #{rejected_seqs}\\\\"
+      if (output_seqs_paired != 0)
+        output3.puts "Output paired sequences & #{output_seqs_paired} \\\\"
+        output3.puts "Total output sequences & #{total_output_seqs} \\\\"
+      end
+      if (low_complex != 0)
+        output3.puts "Low complexity sequences & #{low_complex} \\\\"
+      end
+
+      output3.puts '\end{tabular}'
+      output3.puts '\label{table:input_seqs}'
+      output3.puts '\end{center}'
+      output3.puts '\end{table}'+"\n\n"
+      #-------------------------------------------------- end table
+
+      #-------------------------------------------------- build table
+      output3.puts '\begin{table}[H]'
+      output3.puts '\caption{Summary of reads removed in every plugin.}'
+      output3.puts '\begin{center}'
+      output3.puts '\begin{tabular}{l r r c}'
+      output3.puts '\hline'
+      output3.puts 'Case & Number of sequences & Percent & Warnings \\\\ [0.5ex]'
+      output3.puts '\hline'
+
+      #the hash of hashes is ordered by value (number of sequences rejected)
+      rejected_ordered = rejected_hash.sort {|a,b| b[1]['value']<=>a[1]['value']}
+
+      rejected_ordered.each do |plugin|
+
+        my_name = plugin[1]['name']
+        my_value = plugin[1]['value']
+        my_percent = plugin[1]['percent']
+        my_warning = plugin[1]['warning']
+
+        if (plugin[0] != 'rejected')
+          if (plugin[0] == 'Indeterminations in middle of sequence')
+            plugin[0] = plugin[0].sub(' in middle of sequence','')
+          end
+          output3.puts "#{my_name}&#{my_value}&#{my_percent} \\%&#{my_warning}\\\\"
+        end
+      end
+
+      output3.puts '\hline'
+      output3.puts "Total rejected&#{rejected_hash['rejected']['value']}&#{rejected_hash['rejected']['percent']} \\%&#{rejected_hash['rejected']['warning']}\\\\ [1ex]"
+      output3.puts '\hline'
+      output3.puts '\end{tabular}'
+      output3.puts '\end{center}'
+      output3.puts '\label{table:reads_removed}'
+      output3.puts '\end{table}'+"\n\n"
+      #-------------------------------------------------- end table
+
+      rejected_ordered.each do |plugin|
+        if (plugin[1]['warning'] != 'OK')
+          plugin[1]['warning_msg'].gsub!('my_percent',"#{rejected_hash["#{plugin[0]}"]['percent']}")
+          output3.puts '\noindent\fcolorbox{black}{yellow}{'+"\n"+'\begin{minipage}{\linewidth}{'+"\n"+'\textbf{'+"#{plugin[1]['warning']}   #{plugin[1]['warning_msg']}"+'}'+"\n"+'}'+"\n"+'\end{minipage}'+"\n"+'}\\\\\\\\'
+        end
+      end
+    else
+      output3.puts 'There are not rejected sequences\\\\'
+    end
+
+    output3.close
+
+    puts "Information about rejected sequences was added to the report"
+  end
+
+  def load_plugins_info(stats, rejected_hash, input_seqs, plugin_fix_hash)
+    data_hash = {}
+
+    stats['sequences']['rejected'].each do |rejected|
+      data_hash = {}
+      if plugin_fix_hash[rejected[0]]
+        data_hash['name'] = plugin_fix_hash[rejected[0]]['name']
+        data_hash['value'] = rejected[1]
+        data_hash['warning'] = 'OK'
+        data_hash['warning_msg'] = ''
+        data_hash['percent'] = sprintf("%0.3f", (rejected[1].to_f*100/input_seqs.to_f))
+        rejected_hash[rejected[0]]=data_hash
+      end
+    end
+
+    rejected_hash.each_key do |key|
+      if (rejected_hash[key]['percent'].to_f >= plugin_fix_hash[key]['threshold'] )
+        rejected_hash[key]['warning'] = plugin_fix_hash[key]['warning']
+        rejected_hash[key]['warning_msg'] = plugin_fix_hash[key]['msg']
+      end
+    end
+
+    return rejected_hash
+  end
+
+  def write_plugin_json
+
+    plugin_fix_hash = {}
+    msgs_hash = {}
+
+    msgs_hash['msg'] = "Warning!, there are a my_percent \\% of repeated sequences"
+    msgs_hash['threshold'] = 9
+    msgs_hash['warning'] = 'W1'
+
+    plugin_fix_hash['repeated'] = msgs_hash
+    msgs_hash = {}
+
+    msgs_hash['msg'] = "Warning!, a my_percent \\% of your sequences are too short"
+    msgs_hash['threshold'] = 10
+    msgs_hash['warning'] = 'W2'
+
+    plugin_fix_hash['short insert'] = msgs_hash
+    msgs_hash = {}
+
+    msgs_hash['msg'] = "Warning!, a my_percent \\% of your sequences are empty (without an insert)"
+    msgs_hash['warning'] = 'W3'
+    msgs_hash['threshold'] = 1
+
+    plugin_fix_hash['empty insert'] = msgs_hash
+    msgs_hash = {}
+
+    msgs_hash['msg'] = "Warning!, a my_percent \\% of your sequences are from a contaminant organism or from organelles"
+    msgs_hash['warning'] = 'W4'
+    msgs_hash['threshold'] = 1
+
+    plugin_fix_hash['contaminated'] = msgs_hash
+    msgs_hash = {}
+
+    msgs_hash['msg'] = "Warning!, a my_percent \\% of your sequences are no valid sequences"
+    msgs_hash['threshold'] = 0.1
+    msgs_hash['warning'] = 'W5'
+
+    plugin_fix_hash['No valid inserts found'] = msgs_hash
+    msgs_hash = {}
+
+    msgs_hash['msg'] = "Warning!, a my_percent \\% of your sequences are low complexity sequences"
+    msgs_hash['warning'] = 'W6'
+    msgs_hash['threshold'] = 1
+
+    plugin_fix_hash['low complexity by polyt'] = msgs_hash
+    msgs_hash = {}
+
+    msgs_hash['msg'] = "Warning!, a my_percent \\% of your sequences contain a vector in an unexpected position"
+    msgs_hash['warning'] = 'W7'
+    msgs_hash['threshold'] = 1
+
+    plugin_fix_hash['unexpected vector'] = msgs_hash
+    msgs_hash = {}
+
+    msgs_hash['msg'] = "Warning!, a my_percent \\% of your sequences contain too much indeterminations"
+    msgs_hash['threshold'] = 0.1
+    msgs_hash['warning'] = 'W8'
+
+    plugin_fix_hash['Indeterminations in middle of sequence'] = msgs_hash
+    msgs_hash = {}
+
+    msgs_hash['msg'] = "WT  Warning!, a my_percent \\% of your sequences were rejected!"
+    msgs_hash['threshold'] = 25
+    msgs_hash['warning'] = 'WT'
+
+    plugin_fix_hash['rejected'] = msgs_hash
+    msgs_hash = {}
+
+    puts JSON.pretty_generate(plugin_fix_hash)
+
+  end
+
+end