full_lengther_next 0.0.6 → 0.0.8

data/History.txt

@@ -1,3 +1,11 @@
+=== 0.0.8 2012-11-28
+
+Protection against empty seqs when all seqs match against user_db
+
+=== 0.0.7 2012-07-25
+
+Chimera detection
+
 === 0.0.6 2012-04-16
 
 Fixed some cosmetic issues and parameters names

data/Manifest.txt

@@ -3,6 +3,7 @@ bin/make_user_db.rb
 bin/full_lengther_next
 History.txt
 lib/full_lengther_next/classes/common_functions.rb
+lib/full_lengther_next/classes/chimeric_seqs.rb
 lib/full_lengther_next/classes/fl_analysis.rb
 lib/full_lengther_next/classes/fl_string_utils.rb
 lib/full_lengther_next/classes/fln_stats.rb

data/Rakefile

@@ -20,7 +20,7 @@ $hoe = Hoe.spec 'full_lengther_next' do
   # self.extra_deps << ['gnuplot','>=0']
   # self.extra_deps << ['term-ansicolor','>=1.0.5']
   self.extra_deps << ['xml-simple','>=1.0.12']
-  self.extra_deps << ['scbi_blast','>=0.0.32']
+  self.extra_deps << ['scbi_blast','>=0.0.37']
   self.extra_deps << ['scbi_mapreduce','>=0.0.29']
   self.extra_deps << ['scbi_fasta','>=0.1.7']
   # self.extra_deps << ['scbi_fastq','>=0.0.13']

data/bin/full_lengther_next

@@ -50,6 +50,11 @@ optparse = OptionParser.new do |opts|
 		options[:distance] = distance.to_i
 	end
 	
+	options[:chimera] = nil
+	opts.on( '-q', '--chimera_detection', "apply chimera detection mode\n\n" ) do |chimera|
+		options[:chimera] = chimera
+	end
+
 	options[:workers] = 2
 	opts.on( '-w', '--workers INTEGER/FILE', 'Number of CPUs, or a file containing machine names to launch workers with ssh' ) do |workers|
     if File.exists?(workers)
@@ -91,7 +96,7 @@ optparse = OptionParser.new do |opts|
   
 
 	# Set a banner, displayed at the top of the help screen.
-	opts.banner = "Usage: full_lengther_next -f input.fasta -g [fungi|human|invertebrates|mammals|plants|rodents|vertebrates] [options]\n\n"
+	opts.banner = "\nUsage: full_lengther_next -f input.fasta -g [fungi|human|invertebrates|mammals|plants|rodents|vertebrates] [options]\n\n"
 
 	# This displays the help screen
 	opts.on( '-h', '--help', 'Display this screen' ) do
@@ -172,6 +177,8 @@ require 'my_worker_manager'
 $LOG = Logger.new(STDOUT)
 $LOG.datetime_format = "%Y-%m-%d %H:%M:%S"
 
+# puts "ROOT_PATH: #{ROOT_PATH}"
+
 custom_worker_file = File.join(File.dirname(ROOT_PATH),'lib','full_lengther_next','classes','my_worker.rb')
 
 	$LOG.info 'Starting server'

data/bin/make_user_db.rb

@@ -126,16 +126,16 @@ end
 ENV['BLASTDB']=formatted_db_path
 
 
-if !File.exists?(File.join(ENV['BLASTDB'], my_group))
-	Dir.mkdir("blast_dbs/#{my_group}")
+if !File.exists?(File.join(formatted_db_path, my_group))
+	Dir.mkdir(File.join(formatted_db_path,my_group))
 end
 
-output_file_path=File.join(ENV['BLASTDB'],my_group,my_group+".fasta")
+output_file_path=File.join(formatted_db_path,my_group,my_group+".fasta")
 
 output_file = File.new(output_file_path, "w")
 
-filter_incomplete_seqs(output_file, File.join(ENV['BLASTDB'], "uniprot_sprot_#{uniprot_group}.dat"), my_group)
-filter_incomplete_seqs(output_file, File.join(ENV['BLASTDB'], "uniprot_trembl_#{uniprot_group}.dat"), my_group)
+filter_incomplete_seqs(output_file, File.join(formatted_db_path, "uniprot_sprot_#{uniprot_group}.dat"), my_group)
+filter_incomplete_seqs(output_file, File.join(formatted_db_path, "uniprot_trembl_#{uniprot_group}.dat"), my_group)
 
 output_file.close
 

data/lib/full_lengther_next.rb

@@ -1,13 +1,13 @@
 $:.unshift(File.dirname(__FILE__)) unless
   $:.include?(File.dirname(__FILE__)) || $:.include?(File.expand_path(File.dirname(__FILE__)))
 
-root_path=File.join(File.dirname(__FILE__),'full_lengther_next')
+# ROOT_PATH=File.join(File.dirname(__FILE__),'full_lengther_next')
 
-$: << File.expand_path(File.join(root_path, 'classes'))
+$: << File.expand_path(File.join(File.dirname(__FILE__), 'full_lengther_next', 'classes'))
 
 
 module FullLengtherNext
-   VERSION = '0.0.6'
+   VERSION = '0.0.8'
   
   FULLLENGHTER_VERSION = VERSION
 end

data/lib/full_lengther_next/classes/chimeric_seqs.rb

@@ -0,0 +1,78 @@
+
+require 'scbi_blast'
+
+module ChimericSeqs
+	
+	def search_chimeras(seq, blast_query, options, db_name)
+		
+		# used to detect if the sequence and the blast are from different query
+		if (seq.seq_name != blast_query.query_def)
+			puts "#{seq.seq_name} --> #{blast_query.query_def}"
+			raise "BLAST query name and sequence are different"
+		end
+		
+		q=blast_query
+		# puts "#{q.query_def}"
+		
+		ref_hit_beg = q.hits[0].q_beg
+		ref_hit_end = q.hits[0].q_end
+
+		q.hits.each do |hit|
+			# puts "---------#{hit.acc}"
+			# if overlaps or is contained in the ref hit
+			if ((ref_hit_beg <= hit.q_beg) && (ref_hit_end > hit.q_beg)) || ((hit.q_beg <= ref_hit_beg) && (hit.q_end > ref_hit_beg))
+				# puts "hits overlapping: ref_hit #{ref_hit_beg}-#{ref_hit_end}, current hit #{hit.q_beg}-#{hit.q_end}"
+				ref_hit_beg = [ref_hit_beg,hit.q_beg].min
+				ref_hit_end = [ref_hit_end,hit.q_end].max
+				# puts "modified ref_hit #{ref_hit_beg}-#{ref_hit_end}"
+			end
+		end
+		q.hits.each do |hit|
+			if ((ref_hit_beg <= hit.q_beg) && (ref_hit_end > hit.q_beg)) || ((hit.q_beg <= ref_hit_beg) && (hit.q_end > ref_hit_beg))
+			else
+				if (hit.acc != q.hits[0].acc)
+					# puts "\nreference: #{ref_hit_beg} - #{ref_hit_end}"
+					# puts "hit 0: #{q.hits[0].q_beg} - #{q.hits[0].q_end}"
+					# puts "current: #{hit.q_beg} - #{hit.q_end}"
+					# puts "putative chimeric seq: \n#{q.hits[0].definition}\n#{hit.definition}\n------------------------------------------"
+					
+					chimera_annotations = "\n#{q.query_def}\t#{seq.fasta_length}\t#{q.hits[0].acc}\t#{db_name}\tPutative chimera\t\t#{q.hits[0].e_val}\t#{q.hits[0].ident}\t\t\tPutative chimera detected showing similarity with two different genes #{q.hits[0].acc} - #{hit.acc}\t#{q.hits[0].q_frame}\t#{q.hits[0].q_beg}\t#{q.hits[0].q_end}\t#{q.hits[0].s_beg.to_i}\t#{q.hits[0].s_end.to_i}\t#{q.hits[0].definition}\t\n#{q.query_def}\t#{seq.fasta_length}\t#{hit.acc}\t#{db_name}\tPutative chimera\t\t#{hit.e_val}\t#{hit.ident}\t\t\tPutative chimera detected showing similarity with two different genes #{q.hits[0].acc} - #{hit.acc}\t#{hit.q_frame}\t#{hit.q_beg}\t#{hit.q_end}\t#{hit.s_beg.to_i}\t#{hit.s_end.to_i}\t#{hit.definition}\t"
+					seq.annotate(:chimera,chimera_annotations,false)
+				end
+				
+				return
+			end
+		end
+		
+	end
+	
+	def select_best_blast(tmp_blast_obj, new_seqs)
+		
+		my_seqs ={}
+		
+		new_seqs.each do |seq|
+			my_seqs[seq.seq_name] = true
+		end
+		
+		reverse_counter = (tmp_blast_obj.querys.length - 1)
+		
+		tmp_blast_obj.querys.reverse_each do |query|
+			if (!my_seqs[query.query_def]) # los marcados como quimeras se eliminan para no utilizarse posteriormente
+				# tmp_blast_obj.querys[reverse_counter].delete
+				tmp_blast_obj.querys.delete_at(reverse_counter)
+			else
+				reverse_hit_counter = (query.hits.length - 1)
+				query.hits.reverse_each do |hit|
+					if (hit.acc != query.hits[0].acc)
+						tmp_blast_obj.querys[reverse_counter].hits.delete_at(reverse_hit_counter)
+					end
+					reverse_hit_counter -= 1
+				end
+			end
+			reverse_counter -= 1
+		end
+		
+		return tmp_blast_obj
+	end
+	
+end

data/lib/full_lengther_next/classes/fln_stats.rb

@@ -4,20 +4,28 @@ module FlnStats
 	def summary_stats
 		stats_file = File.open('fln_results/summary_stats.html', 'w')
 		
+		size_filter1 = 200
+		size_filter2 = 500
+		
 		# recogemos los trozos de html fijos
 		(html_head, html_st, html_uni, html_db, html_as, html_end) = html_code
 		
 		total_seqs = 0
 		status_suma = 0
 		#recogemos los datos que necesitamos de los ficheros de resultados
-		(status_array, db_usage, seqs_number1, error_1_num, seq_uniq, complete_uniq, db_uni_500, db_uni_200, db_longest_one) = annotation_stats
-		(tcode_array, seqs_number2, unk_200, tc_uni_500, tc_uni_200, tc_longest_one) = testcode_stats
-		(ncrna_total, nc_uni_500, nc_uni_200, nc_longest_one)=ncrna_stats
+		(status_array, db_usage, seqs_number1, error_1_num, seq_uniq, complete_uniq, db_uni_500, db_uni_200, db_longest_one) = annotation_stats(size_filter1,size_filter2)
+		(tcode_array, seqs_number2, tc_uni_500, tc_uni_200, tc_longest_one) = testcode_stats(size_filter1,size_filter2)
+		(ncrna_total, nc_uni_500, nc_uni_200, nc_longest_one)=ncrna_stats(size_filter1,size_filter2)
+		(chimera_total, ch_uni_500, ch_uni_200, ch_longest_one, ch_db_usage)=chimera_stats(size_filter1,size_filter2)
 		
-		total_seqs = seqs_number1 + seqs_number2 + ncrna_total.to_i
-		uni_500 = (db_uni_500 + tc_uni_500 + nc_uni_500)
-		uni_200 = (db_uni_200 + tc_uni_200 + nc_uni_200)
-		longest_one = [db_longest_one, tc_longest_one, nc_longest_one].max
+		seqs_number1 = (seqs_number1+chimera_total.to_i)
+		total_seqs = (seqs_number1 + seqs_number2 + ncrna_total.to_i)
+		uni_500 = (db_uni_500 + tc_uni_500 + nc_uni_500 + ch_uni_500)
+		uni_200 = (db_uni_200 + tc_uni_200 + nc_uni_200 + ch_uni_200)
+		longest_one = [db_longest_one, tc_longest_one, nc_longest_one, ch_longest_one].max
+		db_usage[0] += ch_db_usage[0]
+		db_usage[1] += ch_db_usage[1]
+		db_usage[2] += ch_db_usage[2]
 		stats_file.puts html_head
 		
 		if (total_seqs.to_i > 0)
@@ -46,6 +54,15 @@ module FlnStats
 				end
 				status_suma += status[0]
 			end
+			
+			# adding chimeric seqs
+			stats_file.puts '				<tr>
+					<td colspan="2" align="left">Putative chimera</td>
+					<td align="right">'+chimera_total.to_s+'</td>
+					<td align="right">'+'%.2f' % (100*chimera_total.to_f/total_seqs.to_f).to_s+' %</td>
+				</tr>'
+				status_suma += chimera_total
+				
 			# añadimos los coding, P.coding
 			tcode_array.each do |status|
 				if (status[1] == 'Coding')
@@ -64,6 +81,7 @@ module FlnStats
 				end
 				status_suma += status[0]
 			end
+			
 			# se ponen los ncRNA
 			stats_file.puts '				<tr>
 					<td colspan="2" align="left">Putative ncRNA</td>
@@ -156,12 +174,12 @@ module FlnStats
 					<td align="right">'+'%.2f' % (100*total_seqs.to_f/total_seqs.to_f).to_s+' %</td>
 				</tr>'
 				stats_file.puts '				<tr>
-					<td align="left">Unigenes >500pb</td>
+					<td align="left">Unigenes >'+size_filter2.to_s+'pb</td>
 					<td align="right">'+uni_500.to_s+'</td>
 					<td align="right">'+'%.2f' % (100*uni_500.to_f/total_seqs.to_f).to_s+' %</td>
 				</tr>'
 				stats_file.puts '				<tr>
-					<td align="left">Unigenes >200pb</td>
+					<td align="left">Unigenes >'+size_filter1.to_s+'pb</td>
 					<td align="right">'+uni_200.to_s+'</td>
 					<td align="right">'+'%.2f' % (100*uni_200.to_f/total_seqs.to_f).to_s+' %</td>
 				</tr>'
@@ -175,6 +193,8 @@ module FlnStats
 					<td align="right">'+seqs_number1.to_s+'</td>
 					<td align="right">'+'%.2f' % (100*seqs_number1.to_f/total_seqs.to_f).to_s+' %</td>
 				</tr>'
+
+			if (seqs_number1.to_i > 0)
 				stats_file.puts '				<tr>
 					<td align="left">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Different orthologue IDs</td>
 					<td align="right">'+seq_uniq.to_s+'</td>
@@ -195,21 +215,49 @@ module FlnStats
 					<td align="right">'+error_1_num.to_s+'</td>
 					<td align="right">'+'%.2f' % (100*error_1_num.to_f/seqs_number1.to_f).to_s+' %</td>
 				</tr>'
+				stats_file.puts '				<tr>
+					<td align="left">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Putative chimera</td>
+					<td align="right">'+chimera_total.to_s+'</td>
+					<td align="right">'+'%.2f' % (100*chimera_total.to_f/seqs_number1.to_f).to_s+' %</td>
+				</tr>'
+			end
 				stats_file.puts '				<tr>
 					<td align="left">Without orthologue <sup>1</sup></td>
 					<td align="right">'+no_db.to_s+'</td>
 					<td align="right">'+'%.2f' % (100*seqs_number2.to_f/total_seqs.to_f).to_s+' %</td>
 				</tr>'
+
+			if (no_db.to_i > 0) && (seqs_number2.to_i > 0)
 				stats_file.puts '				<tr>
-					<td align="left">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Coding</td>
+					<td align="left">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Coding (all)</td>
 					<td align="right">'+tcode_array[0][0].to_s+'</td>
 					<td align="right">'+'%.2f' % (100*tcode_array[0][0].to_f/no_db.to_f).to_s+' %</td>
 				</tr>'
 				stats_file.puts '				<tr>
-					<td align="left">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Putative Coding</td>
+					<td align="left">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Coding > '+size_filter1.to_s+'bp</td>
+					<td align="right">'+tcode_array[0][2].to_s+'</td>
+					<td align="right">'+'%.2f' % (100*tcode_array[0][2].to_f/no_db.to_f).to_s+' %</td>
+				</tr>'
+				stats_file.puts '				<tr>
+					<td align="left">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Coding > '+size_filter2.to_s+'bp</td>
+					<td align="right">'+tcode_array[0][3].to_s+'</td>
+					<td align="right">'+'%.2f' % (100*tcode_array[0][3].to_f/no_db.to_f).to_s+' %</td>
+				</tr>'
+				stats_file.puts '				<tr>
+					<td align="left">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Putative Coding (all)</td>
 					<td align="right">'+tcode_array[1][0].to_s+'</td>
 					<td align="right">'+'%.2f' % (100*tcode_array[1][0].to_f/no_db.to_f).to_s+' %</td>
 				</tr>'
+				stats_file.puts '				<tr>
+					<td align="left">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Putative Coding > '+size_filter1.to_s+'bp</td>
+					<td align="right">'+tcode_array[1][2].to_s+'</td>
+					<td align="right">'+'%.2f' % (100*tcode_array[1][2].to_f/no_db.to_f).to_s+' %</td>
+				</tr>'
+				stats_file.puts '				<tr>
+					<td align="left">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Putative Coding > '+size_filter2.to_s+'bp</td>
+					<td align="right">'+tcode_array[1][3].to_s+'</td>
+					<td align="right">'+'%.2f' % (100*tcode_array[1][3].to_f/no_db.to_f).to_s+' %</td>
+				</tr>'
 				stats_file.puts '				<tr>
 					<td align="left">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Putative ncRNA</td>
 					<td align="right">'+ncrna_total.to_s+'</td>
@@ -221,16 +269,19 @@ module FlnStats
 					<td align="right">'+'%.2f' % (100*tcode_array[2][0].to_f/no_db.to_f).to_s+' %</td>
 				</tr>'
 				stats_file.puts '				<tr>
-					<td align="left">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Unknown < 200bp</td>
-					<td align="right">'+unk_200.to_s+'</td>
-					<td align="right">'+'%.2f' % (100*unk_200.to_f/no_db.to_f).to_s+' %</td>
-				</tr>
-			</table>
+					<td align="left">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Unknown > '+size_filter1.to_s+'bp</td>
+					<td align="right">'+tcode_array[2][2].to_s+'</td>
+					<td align="right">'+'%.2f' % (100*tcode_array[2][2].to_f/no_db.to_f).to_s+' %</td>
+				</tr>'
+				stats_file.puts '				<tr>
+					<td align="left">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Unknown > '+size_filter2.to_s+'bp</td>
+					<td align="right">'+tcode_array[2][3].to_s+'</td>
+					<td align="right">'+'%.2f' % (100*tcode_array[2][3].to_f/no_db.to_f).to_s+' %</td>
+				</tr>'
+			end
+			stats_file.puts '			</table>
 			<sup>1</sup> Percents for subclassifications of this category were calculated using this line as 100% reference.'
 				
-			
-		
-		
 		end
 		stats_file.puts html_end
 		
@@ -309,7 +360,7 @@ module FlnStats
 		end
 
 
-		def annotation_stats
+		def annotation_stats(size_filter1,size_filter2)
 
 			seqs_number = 0
 			array_of_all_accs = []
@@ -353,10 +404,10 @@ module FlnStats
 					end
 
 					# -------------------------------------------------------------------------
-					if (fasta_length.to_i >= 200)
+					if (fasta_length.to_i >= size_filter1)
 						uni_200 += 1
 					end
-					if (fasta_length.to_i >= 500)
+					if (fasta_length.to_i >= size_filter2)
 						uni_500 += 1
 					end
 					# -------------------------------------------------------------------------
@@ -394,18 +445,17 @@ module FlnStats
 		end
 
 
-		def testcode_stats
+		def testcode_stats(size_filter1,size_filter2)
 
 			seqs_number = 0
-			unk_200 = 0
 			uni_500 = 0
 			uni_200 = 0
 			longest_one = 0
 
 			# total, status
-			coding_stats = [0,'Coding']
-			p_coding_stats = [0,'Putative Coding']
-			unknown_stats = [0,'Unknown']
+			coding_stats = [0,'Coding',0,0]
+			p_coding_stats = [0,'Putative Coding',0,0]
+			unknown_stats = [0,'Unknown',0,0]
 
 			File.open('fln_results/new_coding.txt').each do |line|
 				line.chomp!
@@ -419,17 +469,31 @@ module FlnStats
 					end
 
 					# -------------------------------------------------------------------------
-					if (fasta_length.to_i >= 200)
+					if (fasta_length.to_i >= size_filter1)
 						uni_200 += 1
 					end
-					if (fasta_length.to_i >= 500)
+					if (fasta_length.to_i >= size_filter2)
 						uni_500 += 1
 					end
 					# -------------------------------------------------------------------------
 
-					if (fasta_length.to_i < 200)
-						if (status == 'unknown')
-							unk_200 += 1
+					if (fasta_length.to_i > size_filter1)
+						if (status == 'coding')
+							coding_stats[2] += 1
+						elsif (status == 'putative_coding')
+							p_coding_stats[2] += 1
+						elsif (status == 'unknown')
+							unknown_stats[2] += 1
+						end
+					end
+
+					if (fasta_length.to_i > size_filter2)
+						if (status == 'coding')
+							coding_stats[3] += 1
+						elsif (status == 'putative_coding')
+							p_coding_stats[3] += 1
+						elsif (status == 'unknown')
+							unknown_stats[3] += 1
 						end
 					end
 
@@ -447,11 +511,11 @@ module FlnStats
 
 			status_array = [coding_stats, p_coding_stats, unknown_stats]
 
-			return [status_array, seqs_number, unk_200, uni_500, uni_200, longest_one]
+			return [status_array, seqs_number, uni_500, uni_200, longest_one]
 		end
 
 
-		def ncrna_stats
+		def ncrna_stats(size_filter1,size_filter2)
 
 			uni_500 = 0
 			uni_200 = 0
@@ -468,10 +532,10 @@ module FlnStats
 						longest_one = fasta_length.to_i
 					end
 					# -------------------------------------------------------------------------
-					if (fasta_length.to_i >= 200)
+					if (fasta_length.to_i >= size_filter1)
 						uni_200 += 1
 					end
-					if (fasta_length.to_i >= 500)
+					if (fasta_length.to_i >= size_filter2)
 						uni_500 += 1
 					end
 					# -------------------------------------------------------------------------
@@ -484,5 +548,53 @@ module FlnStats
 			return [nc_total, uni_500, uni_200, longest_one]
 		end
 
+		def chimera_stats(size_filter1,size_filter2)
+			
+			uni_500 = 0
+			uni_200 = 0
+			ch_total = 0
+			longest_one = 0
+			db_usage = [0,0,0]
+				
+			if !File.exists?('fln_results/chimeric_sequences.txt')
+				return [0, 0, 0, longest_one, db_usage]
+			else
+				File.open('fln_results/chimeric_sequences.txt').each do |line|
+					line.chomp!
+					if (!line.empty?)
+						(name,fasta_length,acc,db_name,status) = line.split("\t")
+						if (status == 'Putative chimera')
+							if (fasta_length.to_i > longest_one)
+								longest_one = fasta_length.to_i
+							end
+							# -------------------------------------------------------------------------
+							if (fasta_length.to_i >= size_filter1)
+								uni_200 += 1
+							end
+							if (fasta_length.to_i >= size_filter2)
+								uni_500 += 1
+							end
+							# -------------------------------------------------------------------------
+							if (db_name =~ /^sp_/)
+								db_usage[1] += 1
+							elsif (db_name =~ /^tr_/)
+								db_usage[2] += 1
+							else
+								db_usage[0] += 1
+							end
+							# -------------------------------------------------------------------------
+							ch_total += 1
+						end
+					end
+				end
+			
+				db_usage.each_with_index do |db,i|
+					db_usage[i] = db/2
+				end
+			
+				return [(ch_total/2), (uni_500/2), (uni_200/2), longest_one, db_usage]
+			end
+		end
+
 
 end

data/lib/full_lengther_next/classes/my_worker.rb

@@ -8,6 +8,9 @@ require 'fl_string_utils'
 require "lcs" # like the class simliar of seqtrim, return the longest common sequence
 require "test_code"
 
+require 'chimeric_seqs'
+include ChimericSeqs
+
 require 'fl_analysis'
 include FlAnalysis
 
@@ -46,7 +49,12 @@ class MyWorker < ScbiMapreduce::Worker
 	# ejecuta blast utilizando los parametros fichero de entrada, base de datos, fichero de salida y tipo de blast
 	def run_blast(input, database, blast_type, evalue)
 		
-		blast=BatchBlast.new("-db #{database}",blast_type,"-evalue #{evalue} -max_target_seqs 1")
+		if (@options[:chimera].nil?)
+			blast=BatchBlast.new("-db #{database}",blast_type,"-evalue #{evalue} -max_target_seqs 1")
+		else
+			blast=BatchBlast.new("-db #{database}",blast_type,"-evalue #{evalue}")
+		end
+		
 		blast_result = blast.do_blast_seqs(input, :xml)
 		
 		return blast_result
@@ -73,34 +81,71 @@ class MyWorker < ScbiMapreduce::Worker
 			# do blast
 			my_blast = run_blast(seqs, "#{@options[:user_db]}", 'blastx', '1e-6')
 			
+			# chimera detection
+			if (!@options[:chimera].nil?)
+				seqs.each_with_index do |seq,i|
+					if (!my_blast.querys[i].hits[0].nil?)
+						search_chimeras(seq, my_blast.querys[i], @options, user_db_name)
+					end
+				end
+				
+				seqs=seqs.select{|s| s.get_annotations(:chimera).empty?}
+				my_blast = select_best_blast(my_blast, seqs)
+			end
+			
 			# split and parse blast
 			seqs.each_with_index do |seq,i|
 				analiza_orf_y_fl(seq, my_blast.querys[i], @options, user_db_name)
 			end
 			
-			new_seqs=seqs.select{|s| s.get_annotations(:complete).empty?}
+			new_seqs=seqs.select{|s| (s.get_annotations(:complete).empty? && s.get_annotations(:chimera).empty?)}
 			
 		else
 			new_seqs = seqs
 		end
+
+		return if new_seqs.empty?
 		
 		# -------------------------------------------- UniProt (sp)
 		# blast
 		sp_path=File.join("sp_#{@options[:tax_group]}","sp_#{@options[:tax_group]}.fasta")
 		my_blast = run_blast(new_seqs, sp_path, 'blastx', '1e-6')
 		
+		# chimera detection
+		if (!@options[:chimera].nil?)
+			new_seqs.each_with_index do |seq,i|
+				if (!my_blast.querys[i].hits[0].nil?)
+					search_chimeras(seq, my_blast.querys[i], @options, "sp_#{@options[:tax_group]}")
+				end
+			end
+			new_seqs=seqs.select{|s| s.get_annotations(:chimera).empty?}
+			my_blast = select_best_blast(my_blast, new_seqs)
+		end
+		
 		# split and parse blast
 		new_seqs.each_with_index do |seq,i|
 			analiza_orf_y_fl(seq, my_blast.querys[i], @options, "sp_#{@options[:tax_group]}")
 		end
 		
-		new_seqs=seqs.select{|s| s.get_annotations(:complete).empty?}
+		new_seqs=seqs.select{|s| (s.get_annotations(:complete).empty? && s.get_annotations(:chimera).empty?)}
+		return if new_seqs.empty?
 		
 		# -------------------------------------------- UniProt (tr)
 		# blast
 		tr_path=File.join("tr_#{@options[:tax_group]}","tr_#{@options[:tax_group]}.fasta")
 		my_blast = run_blast(new_seqs, tr_path, 'blastx', '1e-6')
 		
+		# chimera detection
+		if (!@options[:chimera].nil?)
+			new_seqs.each_with_index do |seq,i|
+				if (!my_blast.querys[i].hits[0].nil?)
+					search_chimeras(seq, my_blast.querys[i], @options, "tr_#{@options[:tax_group]}")
+				end
+			end
+			new_seqs=new_seqs.select{|s| s.get_annotations(:chimera).empty?}
+			my_blast = select_best_blast(my_blast, new_seqs)
+		end
+		
 		# split and parse blast
 		new_seqs.each_with_index do |seq,i|
 			analiza_orf_y_fl(seq, my_blast.querys[i], @options, "tr_#{@options[:tax_group]}")
@@ -108,8 +153,9 @@ class MyWorker < ScbiMapreduce::Worker
 		
 		# -------------------------------------------- Test Code
 		# the sequences without a reliable similarity with an orthologue are processed with Test Code
-		testcode_input=seqs.select{|s| !s.get_annotations(:apply_tcode).empty?}
-
+		testcode_input=seqs.select{|s| (!s.get_annotations(:apply_tcode).empty? && s.get_annotations(:chimera).empty?)}
+		return if testcode_input.empty?
+		
 # active this line to test tcode, and comment all lines above in this function
 # testcode_input=seqs
 	
@@ -119,6 +165,8 @@ class MyWorker < ScbiMapreduce::Worker
 		
 		# -------------------------------------------- nc RNA
 		unknown_seqs=seqs.select{|s| !s.get_annotations(:tcode_unknown).empty?}
+		return if unknown_seqs.empty?
+		
 		# run blastn
 		ncrna_path=File.join('nc_rna_db','ncrna_fln_100.fasta')
 		my_blast = run_blast(unknown_seqs, ncrna_path, 'blastn', '1e-3')

data/lib/full_lengther_next/classes/my_worker_manager.rb

@@ -34,6 +34,15 @@ class MyWorkerManager < ScbiMapreduce::WorkManager
 		@@nc_rna_file = File.open("fln_results/nc_rnas.txt", 'w')
 		@@nc_rna_file.puts file_head
 
+		if (!options[:chimera].nil?)
+			@@chimera_file = File.open("fln_results/chimeric_sequences.txt", 'w')
+			@@chimera_file.puts file_head
+		else
+			if File.exists?("fln_results/chimeric_sequences.txt")
+				File.delete("fln_results/chimeric_sequences.txt")
+			end
+		end
+
 		# @@error_fasta_file = File.open("fln_results/error_seqs.fasta", 'w')
 		# @@error_file = File.open("fln_results/errors_info.txt", 'w')
 
@@ -50,6 +59,10 @@ class MyWorkerManager < ScbiMapreduce::WorkManager
 		@@tcode_file.close
 		@@nc_rna_file.close
 		
+		if (!@@options[:chimera].nil?)
+			@@chimera_file.close
+		end
+		
 		# @@error_fasta_file.close
 		# @@error_file.close
 		
@@ -113,50 +126,101 @@ class MyWorkerManager < ScbiMapreduce::WorkManager
 
 	def write_seq(seq)
 		begin
-# --------------------------------------------------------     Complete Seqs
-			if (e=seq.get_annotations(:complete).first)
+# --------------------------------------------------------     Chimeric Seqs
+			if (!@@options[:chimera].nil?)
+				if (q=seq.get_annotations(:chimera).first)
+					@@chimera_file.puts q[:message]
+# --------------------------------------------------     Complete Seqs
+				elsif (e=seq.get_annotations(:complete).first)
+
+					@@annotation_file.puts e[:message]
+				
+					if (a=seq.get_annotations(:alignment).first)
+						@@alignment_file.puts a[:message]
+					end
+				
+					if (p=seq.get_annotations(:protein).first)
+						@@prot_file.puts p[:message]
+					end
+				
+					if (n=seq.get_annotations(:nucleotide).first)
+						@@nts_file.puts n[:message]
+					end
+# ---------------------------------------------------    Non Complete Seqs
+				elsif (e=seq.get_annotations(:tmp_annotation).first)
 
-				@@annotation_file.puts e[:message]
+					@@annotation_file.puts e[:message][0]
 				
-				if (a=seq.get_annotations(:alignment).first)
-					@@alignment_file.puts a[:message]
-				end
+					if (a=seq.get_annotations(:alignment).first)
+						if !a[:message].empty?
+							@@alignment_file.puts a[:message]
+						end
+					end
 				
-				if (p=seq.get_annotations(:protein).first)
-					@@prot_file.puts p[:message]
-				end
+					if (p=seq.get_annotations(:protein).first)
+						if !p[:message].empty?
+							@@prot_file.puts p[:message]
+						end
+					end
 				
-				if (n=seq.get_annotations(:nucleotide).first)
-					@@nts_file.puts n[:message]
+					if (n=seq.get_annotations(:nucleotide).first)
+						@@nts_file.puts n[:message]
+					end
+# -------------------------------------------------     nc RNA
+				elsif (nc=seq.get_annotations(:ncrna).first)
+					@@nc_rna_file.puts nc[:message]
+# -------------------------------------------------     Test Code
+				elsif (t=seq.get_annotations(:tcode).first)
+	  				@@tcode_file.puts t[:message]
 				end
-# --------------------------------------------------------     Non Complete Seqs
-			elsif (e=seq.get_annotations(:tmp_annotation).first)
+# ---------------------------------------------------------------------------------
+# --------------------------------------------------------    without Chimeric Seqs Mode
+			else
+# -------------------------------------------------     Complete Seqs
+				if (e=seq.get_annotations(:complete).first)
 
-				@@annotation_file.puts e[:message][0]
+					@@annotation_file.puts e[:message]
 				
-				if (a=seq.get_annotations(:alignment).first)
-					if !a[:message].empty?
+					if (a=seq.get_annotations(:alignment).first)
 						@@alignment_file.puts a[:message]
 					end
-				end
 				
-				if (p=seq.get_annotations(:protein).first)
-					if !p[:message].empty?
+					if (p=seq.get_annotations(:protein).first)
 						@@prot_file.puts p[:message]
 					end
-				end
 				
-				if (n=seq.get_annotations(:nucleotide).first)
-					@@nts_file.puts n[:message]
+					if (n=seq.get_annotations(:nucleotide).first)
+						@@nts_file.puts n[:message]
+					end
+# -------------------------------------------------     Non Complete Seqs
+				elsif (e=seq.get_annotations(:tmp_annotation).first)
+
+					@@annotation_file.puts e[:message][0]
+				
+					if (a=seq.get_annotations(:alignment).first)
+						if !a[:message].empty?
+							@@alignment_file.puts a[:message]
+						end
+					end
+				
+					if (p=seq.get_annotations(:protein).first)
+						if !p[:message].empty?
+							@@prot_file.puts p[:message]
+						end
+					end
+				
+					if (n=seq.get_annotations(:nucleotide).first)
+						@@nts_file.puts n[:message]
+					end
+# -------------------------------------------------     nc RNA
+				elsif (nc=seq.get_annotations(:ncrna).first)
+					@@nc_rna_file.puts nc[:message]
+# -------------------------------------------------     Test Code
+				elsif (t=seq.get_annotations(:tcode).first) 
+	  				@@tcode_file.puts t[:message]
 				end
-# --------------------------------------------------------     nc RNA
-			elsif (nc=seq.get_annotations(:ncrna).first)
-				@@nc_rna_file.puts nc[:message]
-# --------------------------------------------------------     Test Code
-			elsif (t=seq.get_annotations(:tcode).first) 
-  				@@tcode_file.puts t[:message]
 			end
-# --------------------------------------------------------     errors
+# -------------------------------------------------     errors
 			# if e=seq.get_annotations(:error).first
 			# 	if !e[:message].empty?
 			# 		@@error_fasta_file.puts ">#{seq.seq_name}\n#{seq.seq_fasta}"

metadata

@@ -2,7 +2,7 @@
 name: full_lengther_next
 version: !ruby/object:Gem::Version 
   prerelease: 
-  version: 0.0.6
+  version: 0.0.8
 platform: ruby
 authors: 
 - Noe Fernandez & Dario Guerrero
@@ -10,7 +10,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2012-04-16 00:00:00 Z
+date: 2012-11-28 00:00:00 Z
 dependencies: 
 - !ruby/object:Gem::Dependency 
   name: xml-simple
@@ -31,7 +31,7 @@ dependencies:
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
-        version: 0.0.32
+        version: 0.0.37
   type: :runtime
   version_requirements: *id002
 - !ruby/object:Gem::Dependency 
@@ -97,6 +97,7 @@ files:
 - bin/full_lengther_next
 - History.txt
 - lib/full_lengther_next/classes/common_functions.rb
+- lib/full_lengther_next/classes/chimeric_seqs.rb
 - lib/full_lengther_next/classes/fl_analysis.rb
 - lib/full_lengther_next/classes/fl_string_utils.rb
 - lib/full_lengther_next/classes/fln_stats.rb
@@ -142,7 +143,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
 requirements: []
 
 rubyforge_project: full_lengther_next
-rubygems_version: 1.7.2
+rubygems_version: 1.8.24
 signing_key: 
 specification_version: 3
 summary: FULL-LENGTHERNEXT is a tool adapted to NGS technologies, able to work in parallel and in a distributed way to minimise computing time