seqtrimnext_report 0.0.2

data/lib/seqtrimnext_report/classes/stats_report.rb

@@ -0,0 +1,323 @@
+class StatsReport
+	
+	def initialize(all_params,initial_stats,stats,plugin_nts_hash,output_folder,output_latex)
+		
+		output2=File.open(File.join(output_latex,'stats.tex'), 'w')
+		output2.puts "%!TEX root = FinalReport.tex"
+		
+		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
+		#------------------------------------------------------------------------------------------ solo cuando hay pareadas
+		if (!stats['sequences']['count']['output_seqs_paired'].nil?)
+			output_seqs_paired = stats['sequences']['count']['output_seqs_paired'].to_i
+			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 # solo cuando hay baja complejidad (no hay cuando es genomico)
+		end
+		# graph files ----------------------------------------------------
+		
+    # if File.exist?(File.join(output_latex,'graphs','size_stats.png'))
+			output2.puts '\input{input_graph}'
+    # end
+		
+    # if File.exist?(File.join(output_latex,'graphs','qualities.png'))
+			output2.puts '\input{qv_graph}'
+    # end
+		
+    # if File.exist?(File.join(output_latex,'graphs','PluginExtractInserts_insert_size.png'))
+			output2.puts '\input{output_graph}'+"\n\n"
+    # end
+		#------------------------------------------------------------------
+		
+		(input_mode, output_mode) = get_mode(initial_stats,stats)
+		(input_mean, output_mean) = get_mean(initial_stats,stats)
+		
+		#--------------------------------------------------------------------------- build table
+		output2.puts '\begin{table}[H]'
+		output2.puts '\begin{center}'
+		output2.puts '\begin{tabular}{l r r}'
+		output2.puts " \\hline"
+		output2.puts "Input reads: & total & #{input_seqs} \\\\"
+		output2.puts " & Smallest read (bp) & #{initial_stats['smallest_sequence_size'].to_i} \\\\"
+		output2.puts " & Largest read (bp)& #{initial_stats['biggest_sequence_size'].to_i} \\\\"
+		output2.puts " & Mode (bp) & #{input_mode} \\\\"
+		output2.puts " & Mean (bp)& #{input_mean} \\\\"
+
+		output2.puts " \\\\ \\hline"
+		output2.puts "Output results: & total & #{output_seqs} \\\\"
+		output2.puts " & Rejected & #{rejected_seqs} \\\\"
+		if (low_complex != 0)
+			output2.puts " & Low complexity reads & #{low_complex} \\\\"
+		end
+		output2.puts " & Mode (bp)& #{output_mode} \\\\"
+		output2.puts " & Mean (bp)& #{output_mean} \\\\"
+		
+		#-------------------------------------------------- solo cuando hay pareadas
+		output2.puts "\\\\"
+		if (output_seqs_paired != 0)
+			output2.puts " & Output paired reads & #{output_seqs_paired} \\\\"
+			output2.puts " & Total output reads & #{total_output_seqs} \\\\"
+			output2.puts "\\\\ \\hline"
+			output2.puts "Linkers: & & \\\\"
+			
+			if (!stats['PluginLinker'].nil?)
+				if (!stats['PluginLinker']['linker_id'].nil?)
+					stats['PluginLinker']['linker_id'].each do |linker|
+						output2.puts " & #{linker[0]} & #{linker[1]} \\\\"
+					end
+				end
+				output2.puts "\\\\ \\hline"
+				if (!stats['PluginLinker']['without_linker'].nil?)
+					output2.puts "Without linkers: & total & #{stats['PluginLinker']['without_linker']['0']} \\\\"
+				end
+				
+				output2.puts "\\\\ \\hline"
+				output2.puts "Multiple linkers: & & \\\\"
+
+				if (!stats['PluginLinker']['multiple_linker_id'].nil?)
+					stats['PluginLinker']['multiple_linker_id'].each do |linker|
+						output2.puts " & #{linker[0]} & #{linker[1]} \\\\"
+					end
+				end
+				if (!stats['PluginLinker']['multiple_linker_count'].nil?)
+					stats['PluginLinker']['multiple_linker_count'].each do |linker|
+						output2.puts " & With #{linker[0]} linkers & #{linker[1]} \\\\"
+					end
+				end
+			end
+		end
+		#-----------------------------------------------------------------------------
+		
+		output2.puts "\\hline"
+		
+		
+
+		output2.puts '\end{tabular}'
+		output2.puts '\label{table:nonlin}'
+		output2.puts '\end{center}'
+		output2.puts '\end{table}'+"\n\n"
+		#------------------------------------------------------------------------------- end table
+
+		#-------------------------------------------------- MIDs
+		if (!stats['PluginMids'].nil?) && (!stats['PluginMids']['mid_id'].nil?)
+			mid_seqs = stats['PluginMids']['mid_id']['total']
+			mid_seqs_percent = sprintf("%0.3f", (mid_seqs.to_f*100/input_seqs.to_f))
+			output2.puts '\noindent \begin{minipage}{\linewidth}'
+			output2.puts "number of reads with MID: #{mid_seqs} \(#{mid_seqs_percent}\\%\)"+'\\\\'+'\\\\'
+
+			if (mid_seqs_percent.to_f <= 1)
+				output2.puts '\fcolorbox{black}{yellow}{'+"\n"+'\begin{minipage}{\linewidth}{'+"\n"+'\textbf{WARNING: The number of reads with MID is so low that can be interpreted as a random finding. Your useful sequences are in the no\_MID folder, but you can also add any read classified as having a MID}'+"\n"+'}'+"\n"+'\end{minipage}'+"\n"+'}\\\\\\\\'
+			end
+			output2.puts '\end{minipage}'+"\n\n"
+		end
+		#----------------------------------------------------------------------------
+
+		#------------------------------------------------------- make top five tables
+		if !(stats['PluginVectors']).nil?
+			if !(top_hash = stats['PluginVectors']['vectors_ids']).nil?
+				make_a_top_five(output2, top_hash, 'Vectors')
+			end
+		end
+		
+		if !(stats['PluginAbAdapters']).nil?
+			if !(top_hash = stats['PluginAbAdapters']['adapter_id']).nil?
+				make_a_top_five(output2, top_hash, 'Adapters')
+			end
+		end
+		
+		if !(stats['PluginContaminants']).nil?
+			if !(top_hash = stats['PluginContaminants']['contaminants_ids']).nil?
+				make_a_top_five(output2, top_hash, 'Contaminants')
+			end
+		end
+		#--------------------------------------------------------------------------
+		
+		# en las pareadas añadimos el inserto de izq y derecha ------------------------------------- solo cuando hay pareadas
+		paired_nts=0
+		if (stats['PluginExtractInserts']['left_insert_size']) || (stats['PluginExtractInserts']['right_insert_size'])
+			stats['PluginExtractInserts']['left_insert_size'].each do |element|
+				paired_nts += element[0].to_i*element[1].to_i
+			end
+			stats['PluginExtractInserts']['right_insert_size'].each do |element|
+				paired_nts += element[0].to_i*element[1].to_i
+			end
+		end
+		#-------------------------------------------------------------------------------------------------------------------
+		
+		nts_total = initial_stats['nucleotide_count']
+		print_trimmed_nts_stats_table(stats, output2, plugin_nts_hash,nts_total,paired_nts)
+		
+		output2.close
+
+		puts "Statistic information was added to the report"
+		
+	end
+	
+	def get_mode(initial_stats,stats)
+		output_mode = 0
+		mode_array = []
+		# take the mode from initial_stats.json
+		input_mode = initial_stats['mode_of_sizes']
+		
+		# calculate the mode using data from stats.json
+		stats['PluginExtractInserts']['insert_size'].each do |key,value|
+			mode_array[key.to_i]=value
+		end
+		
+		mode_array.map!{|e| e || 0}
+		s=ScbiStats.new(mode_array)
+		
+		output_mode = s.fat_mode
+		
+		return [input_mode, output_mode]
+	end
+	
+	def get_mean(initial_stats,stats)
+		output_mean = 0
+
+		# take the mean from initial_stats.json
+		input_mean = sprintf("%0.1f", (initial_stats['mean_of_sequence_sizes']))
+		# input_mean = sprintf("%0.2f", (initial_stats['mean_of_sequence_sizes']))
+
+		# calculate the mean using data from stats.json
+		nts_count = 0
+		seqs_count = 0
+		stats['PluginExtractInserts']['insert_size'].each do |key,value|
+			seqs_count += value.to_i
+			nts_count += (key.to_f*value)
+			# nts_count += (key.to_f*value.to_f)
+		end
+		
+		
+		output_mean = sprintf("%0.1f", (nts_count/seqs_count))
+		# output_mean = sprintf("%0.2f", (nts_count/seqs_count))
+		
+		return [input_mean, output_mean]
+	end
+	
+	def make_a_top_five(output2,top_hash,name)
+#-------------------------------------------------- build table
+		output2.puts '\begin{table}[H]'
+		output2.puts '\caption{'+"List of the most frequent~#{name}~found among your reads"+'}'
+		output2.puts '\vspace{-0.5cm}'
+		output2.puts '\begin{center}'
+		output2.puts '\begin{tabular}{|p{11cm}|r|}'
+		output2.puts '\hline'
+		output2.puts "#{name} " +'& sequences \\\\ [0.5ex]'
+		output2.puts '\hline'
+
+		cont = 0
+		top_hash.sort{|a,b| b[1]<=>a[1]}.each do |elem|
+			tmp_name = elem[0].gsub('_','\_')
+		  output2.puts "#{tmp_name} \& #{elem[1]}"+'\\\\'
+			cont+=1
+			if (cont == 5)
+				break
+			end
+		end
+
+		output2.puts '\hline'
+		output2.puts '\end{tabular}'
+		output2.puts '\end{center}'
+		# output2.puts '\label{table:top5}'
+		output2.puts '\end{table}'+"\n\n"
+#-------------------------------------------------- end table
+	end
+	
+	def print_trimmed_nts_stats_table(stats, output2, plugin_nts_hash, nts_total,paired_nts)
+
+		nts_table_hash = {}
+		insert_array = []
+		warning_array = []
+
+		plugin_nts_hash.each do |plugin|
+			
+			my_name = plugin[0]
+			plugin_name = plugin[1]['plugin']
+			plugin_field = plugin[1]['field']
+			plugin_msg = plugin[1]['msg']
+			plugin_threshold = plugin[1]['threshold']
+			plugin_warning = plugin[1]['warning']
+			
+			if (!stats[plugin_name].nil?)
+				if (!stats[plugin_name][plugin_field].nil?)
+						
+					count = 0
+					stats[plugin_name][plugin_field].each do |element|
+						count += element[0].to_i*element[1].to_i
+					end
+					
+					if (plugin_name == 'PluginExtractInserts') && (plugin_field == 'insert_size') && (paired_nts > 0)
+						count += paired_nts
+					end
+					
+					my_percent = sprintf("%0.3f", (count.to_f*100/nts_total.to_f))
+				
+					if (plugin_name == 'PluginExtractInserts')
+						if (my_percent.to_f <= plugin_threshold)
+							plugin_msg.gsub!('my_percent',"#{my_percent}")
+							insert_array.push '\noindent \fcolorbox{black}{pink}{'+"\n"+'\begin{minipage}{\linewidth}{'+"\n"+'\textbf{'+"#{plugin_warning}  #{plugin_msg}"+'}'+"\n"+'}'+"\n"+'\end{minipage}'+"\n"+'}\\\\\\\\'
+						else
+							plugin_warning = 'OK'
+						end
+					else
+						if (my_percent.to_f >= plugin_threshold)
+							plugin_msg.gsub!('my_percent',"#{my_percent}")
+							warning_array.push '\noindent \fcolorbox{black}{yellow}{'+"\n"+'\begin{minipage}{\linewidth}{'+"\n"+'\textbf{'+"#{plugin_warning}  #{plugin_msg}"+'}'+"\n"+'}'+"\n"+'\end{minipage}'+"\n"+'}\\\\\\\\'
+						else
+							plugin_warning = 'OK'
+						end
+					end
+				
+					nts_table_hash[plugin_field] = ["#{my_name}&#{count}&#{my_percent} \\%&#{plugin_warning}\\\\",my_percent]
+				
+					# puts "#{plugin_name} #{plugin_field} #{count}"
+				end
+			end
+		end
+		
+#-------------------------------------------------- build table
+		output2.puts '\begin{table}[H]'
+		output2.puts '\caption{Summary of nucleotides removed in every plugin.}'
+		output2.puts '\begin{center}'
+		output2.puts '\begin{tabular}{l r r c}'
+		output2.puts '\hline'
+		output2.puts 'Plugin & Nucleotides & Percent & Warnings \\\\ [0.5ex]'
+		output2.puts '\hline'
+
+		#the hash of hashes is ordered by value (number of sequences rejected)
+		nts_table_ordered = nts_table_hash.sort {|a,b| b[1][1].to_i<=>a[1][1].to_i}
+
+		nts_table_ordered.each do |element|
+			if (element[0] != 'insert_size')
+				output2.puts element[1][0]
+			end
+		end
+		
+		output2.puts '\hline'
+		output2.puts nts_table_hash['insert_size'][0]
+		output2.puts '\hline'
+		output2.puts '\end{tabular}'
+		output2.puts '\label{table:nonlin}'
+		output2.puts '\end{center}'
+		output2.puts '\end{table}'+"\n\n"
+#-------------------------------------------------- end table
+
+		output2.puts '\noindent \begin{minipage}{\textwidth}'
+		
+		output2.puts insert_array.join("\n")
+		output2.puts warning_array.join("\n")
+		
+		output2.puts '\end{minipage}'+"\n\n"
+		
+	end
+	
+end
+

data/lib/seqtrimnext_report/config/plugin_nts.json

@@ -0,0 +1,65 @@
+{
+  "Low Quality": {
+    "plugin": "PluginLowQuality",
+    "field": "low_qual",
+    "msg": "Warning!, there are too many (my_percent \\%) low quality nucleotides",
+    "threshold": 10,
+    "warning": "ntW1"
+  },
+  "Low Complexity": {
+    "plugin": "PluginLowComplexity",
+    "field": "low_complexity",
+    "msg": "Warning!, there are too many (my_percent \\%) low complexity nucleotides",
+    "threshold": 1.5,
+    "warning": "ntW4"
+  },
+  "Poly T": {
+    "plugin": "PluginFindPolyAt",
+    "field": "poly_t_size",
+    "msg": "Warning!, too many nucleotides (my_percent \\%) are poly T",
+    "threshold": 1.5,
+    "warning": "ntW5"
+  },
+  "Poly A": {
+    "plugin": "PluginFindPolyAt",
+    "field": "poly_a_size",
+    "msg": "Warning!, too many nucleotides (my_percent \\%) are poly A",
+    "threshold": 1.5,
+    "warning": "ntW6"
+  },
+  "Contaminants": {
+    "plugin": "PluginContaminants",
+    "field": "contaminants_size",
+    "msg": "Warning!, too many nucleotides (my_percent \\%) come from a contaminant sequence",
+    "threshold": 0.75,
+    "warning": "ntW7"
+  },
+  "Adapters": {
+    "plugin": "PluginAbAdapters",
+    "field": "adapter_size",
+    "msg": "Warning!, too many nucleotides (my_percent \\%) come from adapters",
+    "threshold": 1.5,
+    "warning": "ntW3"
+  },
+  "Vectors": {
+    "plugin": "PluginVectors",
+    "field": "vector_size",
+    "msg": "Warning!, too many nucleotides (my_percent \\%) come from vectors",
+    "threshold": 0.75,
+    "warning": "ntW2"
+  },
+  "Indeterminations": {
+    "plugin": "PluginIndeterminations",
+    "field": "indetermination_size",
+    "msg": "Warning!, too many nucleotides (my_percent \\%) are indeterminations (Ns)",
+    "threshold": 0.01,
+    "warning": "ntW8"
+  },
+  "Inserts": {
+    "plugin": "PluginExtractInserts",
+    "field": "insert_size",
+    "msg": "Warning!, only my_percent \\% of nucleotides are useful",
+    "threshold": 50,
+    "warning": "iW1"
+  }
+}

data/lib/seqtrimnext_report/config/plugin_seqs.json

@@ -0,0 +1,69 @@
+{
+  "contaminated": {
+    "name": "Contaminants",
+    "msg": "Warning!, a my_percent \\% of your sequences are from a contaminant organism or from organelles",
+    "threshold": 0.75,
+    "warning": "rdW4"
+  },
+  "short insert": {
+    "name": "Short inserts",
+    "msg": "Warning!, a my_percent \\% of your sequences are too short",
+    "threshold": 7.5,
+    "warning": "rdW2"
+  },
+  "low complexity by polyt": {
+    "name": "Low Complexity",
+    "msg": "Warning!, a my_percent \\% of your sequences are low complexity sequences",
+    "threshold": 1,
+    "warning": "rdW6"
+  },
+  "empty insert": {
+    "name": "Empty Inserts",
+    "msg": "Warning!, a my_percent \\% of your sequences are empty (without an insert)",
+    "threshold": 0.5,
+    "warning": "rdW3"
+  },
+  "No valid inserts found": {
+    "name": "No Valid Inserts",
+    "msg": "Warning!, a my_percent \\% of your sequences are no valid sequences",
+    "threshold": 0.05,
+    "warning": "rdW5"
+  },
+  
+  "At least one N found": {
+    "name": "At least one N found",
+    "msg": "",
+    "threshold": 1,
+    "warning": ""
+  },
+    "Primer pair not found": {
+    "name": "Primer pair not found",
+    "msg": "",
+    "threshold": 1,
+    "warning": ""
+  },
+  "repeated": {
+    "name": "Repeated Sequences",
+    "msg": "Warning!, there are a my_percent \\% of repeated sequences",
+    "threshold": 9,
+    "warning": "rdW1"
+  },
+  "Indeterminations in middle of sequence": {
+    "name": "Indeterminations",
+    "msg": "Warning!, a my_percent \\% of your sequences contain too much indeterminations",
+    "threshold": 0.05,
+    "warning": "rdW8"
+  },
+  "unexpected vector": {
+    "name": "Unexpected Vector",
+    "msg": "Warning!, a my_percent \\% of your sequences contain a vector in an unexpected position",
+    "threshold": 0.01,
+    "warning": "rdW7"
+  },
+  "rejected": {
+    "name": "Total Rejected",
+    "msg": "Warning!, a my_percent \\% of your sequences were rejected!",
+    "threshold": 30,
+    "warning": "rdWT"
+  }
+}