full_lengther_next 0.0.1

data/lib/full_lengther_next/classes/fl_string_utils.rb

@@ -0,0 +1,139 @@
+
+class String
+	
+	def translate
+		s = self.upcase
+		a = s.split('').each_slice(3).map{|e| e.join}
+		
+	    c={'GCT'=>'A', 'GCC'=>'A','GCA'=>'A','GCG'=>'A',
+			'CGT'=>'R','CGC'=>'R','CGA'=>'R','CGG'=>'R','AGA'=>'R','AGG'=>'R',
+			'AAT'=>'N','AAC'=>'N',
+			'GAT'=>'D','GAC'=>'D',
+			'TGT'=>'C','TGC'=>'C',
+			'CAA'=>'Q','CAG'=>'Q',
+			'GAA'=>'E','GAG'=>'E',
+			'GGT'=>'G','GGC'=>'G','GGA'=>'G','GGG'=>'G',
+			'CAT'=>'H','CAC'=>'H',
+			'ATT'=>'I','ATC'=>'I','ATA'=>'I',
+			'TTA'=>'L','TTG'=>'L','CTT'=>'L','CTC'=>'L','CTA'=>'L','CTG'=>'L',
+			'ATG'=>'M',
+			'AAA'=>'K','AAG'=>'K',
+			'TTT'=>'F','TTC'=>'F',
+			'CCT'=>'P','CCC'=>'P','CCA'=>'P','CCG'=>'P',
+			'TCT'=>'S','TCC'=>'S','TCA'=>'S','TCG'=>'S','AGT'=>'S','AGC'=>'S',
+			'ACT'=>'T','ACC'=>'T','ACA'=>'T','ACG'=>'T',
+			'TGG'=>'W',
+			'TAT'=>'Y','TAC'=>'Y',
+			'GTT'=>'V','GTC'=>'V','GTA'=>'V','GTG'=>'V',
+			'TAG'=>'*','TGA'=>'*','TAA'=>'*'}
+		
+		#EN CASO DE NO ENCONTRAR EL TRIPLETE SE AÑADE UNA X
+		
+		res=a.map{
+			|e|
+			if (e.length == 3)
+				if (e =~ /[NnRrWwMmKkSsYyHhBbDdVv]/)
+					'x'
+				else
+					c[e]||'x'
+				end
+			end
+		}
+		return res.compact.join
+	end
+	
+	def generate_orf_old(a,frame)
+		
+		all_orfs = []
+		each_orf = []
+		
+		atg_codon = false
+		stop_codon = false
+		orf =''
+		t_start = 0
+		t_end = 0
+		
+		a.each do |e|
+			t_end += 3
+			if (atg_codon)
+				orf += e
+				if (e == 'TAG') or (e == 'TGA') or (e == 'TAA')
+					if (orf.length >= 200)
+						each_orf.push orf
+						each_orf.push t_start
+						each_orf.push t_end
+						each_orf.push frame
+						each_orf.push stop_codon
+						
+						all_orfs.push each_orf
+						each_orf = []
+					end
+					orf=''
+					stop_codon = true
+					atg_codon = false
+					t_start = t_end
+				end
+			elsif (e == 'ATG')
+				atg_codon = true
+				orf += e
+				t_start += 1
+			elsif (e == 'TAG') or (e == 'TGA') or (e == 'TAA')
+				stop_codon = true
+				t_start += 3
+			else
+				t_start += 3
+			end
+		end
+		
+		if (all_orfs != '') && (all_orfs != nil)
+			return all_orfs
+		else
+			return nil
+		end
+	end
+	
+	def orf_finder_old
+		res =[]
+		
+		s = self.upcase
+		f1 = s.split('').each_slice(3).map{|e| e.join}
+		r1 = generate_orf(f1,1)
+		res += r1
+		
+		s.sub!(/^./,'')
+		f2 = s.split('').each_slice(3).map{|e| e.join}
+		r2 = generate_orf(f2,2)
+		res += r2
+		
+		s.sub!(/^./,'')
+		f3 = s.split('').each_slice(3).map{|e| e.join}
+		r3 = generate_orf(f3,3)
+		res += r3
+		
+		# vamos a por los ORFs de la cadena complementaria
+		s = self.upcase
+		s = s.complementary_dna
+		
+		f4 = s.split('').each_slice(3).map{|e| e.join}
+		r4 = generate_orf(f4,-1)
+		res += r4
+		
+		s.sub!(/^./,'')
+		f5 = s.split('').each_slice(3).map{|e| e.join}
+		r5 = generate_orf(f5,-2)
+		res += r5
+		
+		s.sub!(/^./,'')
+		f6 = s.split('').each_slice(3).map{|e| e.join}
+		r6 = generate_orf(f6,-3)
+		res += r6
+		
+		return res
+	end
+	
+	def complementary_dna
+	    c={'A'=>'T', 'a' => 't', 'T' => 'A', 't' => 'a', 'C' => 'G', 'c'=>'g' , 'G' => 'C', 'g' => 'c', 'N' => 'N', 'n' => 'N' , 'R' => 'N', 'r' => 'N', 'W' => 'N', 'w' => 'N', 'M' => 'N', 'm' => 'N', 'K' => 'N', 'k' => 'N', 'S' => 'N', 's' => 'N', 'Y' => 'N', 'y' => 'N', 'H' => 'N', 'h' => 'N', 'B' => 'N', 'b' => 'N', 'D' => 'N', 'd' => 'N', 'V' => 'N', 'v' => 'N' }
+	    return self.reverse.split('').map{|e| c[e]}.join
+	end
+	
+end

data/lib/full_lengther_next/classes/lcs.rb

@@ -0,0 +1,33 @@
+
+
+class String
+	
+	def lcs(s2)
+		s1=self
+		res="" 
+		num=Array.new(s1.size){Array.new(s2.size)}
+		len,ans=0
+		lastsub=0
+		s1.scan(/./).each_with_index do |l1,i |
+			s2.scan(/./).each_with_index do |l2,j |
+			  unless l1==l2
+			    num[i][j]=0
+			  else
+			    (i==0 || j==0)? num[i][j]=1 : num[i][j]=1 + num[i-1][j-1]
+			    if num[i][j] > len
+			      len = ans = num[i][j]
+			      thissub = i
+			      thissub -= num[i-1][j-1] unless num[i-1][j-1].nil?  
+			      if lastsub==thissub
+			        res+=s1[i,1]
+			      else
+			        lastsub=thissub
+			        res=s1[lastsub, (i+1)-lastsub]
+			      end
+			    end
+			  end
+			end
+		end
+		res
+	end
+end

data/lib/full_lengther_next/classes/my_worker.rb

@@ -0,0 +1,122 @@
+$: << File.expand_path(File.join(File.dirname(__FILE__)))
+
+require 'scbi_mapreduce'
+require 'scbi_blast'
+require 'json'
+require 'sequence'
+require 'fl_string_utils'
+require "lcs" # like the class simliar of seqtrim, return the longest common sequence
+require "test_code"
+
+require 'fl_analysis'
+include FlAnalysis
+
+
+class MyWorker < ScbiMapreduce::Worker
+
+	def starting_worker
+		
+		# $WORKER_LOG.info "Loading actions"
+		rescue Exception => e
+		puts (e.message+ e.backtrace.join("\n"))
+		
+	end
+		
+	def receive_initial_config(obj)
+		
+		# Reads the parameters
+		# $WORKER_LOG.info "Params received: #{obj.to_json}"
+		@options = obj
+		
+	end
+		
+	def process_object(obj)
+
+		full_lenghter2(obj)
+		return obj
+		
+	end
+		
+	def closing_worker
+		 
+	end
+	
+	# ejecuta blastx utilizando los parametros fichero de entrada, base de datos y fichero de salida
+	def run_blastx(input, database, user_db_name)
+		# puts "\n#{user_db_name} ..... executing BLASTx"
+		
+		blast=BatchBlast.new("-db #{database}",'blastx',"-evalue 1e-6 -num_alignments 1 -num_descriptions 1")
+		blast_result = blast.do_blast_seqs(input, :xml)
+		
+		# puts "#{user_db_name} ..... BLASTx finished"
+
+		return blast_result
+	end
+	
+	
+	def full_lenghter2(seqs)
+		
+		# -------------------------------------------- User database
+		# if the user has included his own database in the parameters entry,
+		# the location of the database is tested, and blast and the results analysis is done
+		
+		if (@options[:user_db])
+		
+			if (@options[:user_db] =~ /\//)
+				user_db_name = @options[:user_db].sub(/.+\//,'')
+			end
+		
+			if !File.exists?("#{@options[:user_db]}.psq")
+				puts "user database: #{@options[:user_db]} was not found"
+				exit
+			end
+		
+			# do blast
+			my_blast = run_blastx(seqs, "#{@options[:user_db]}", user_db_name)
+			
+			# 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?}
+			
+		else
+			new_seqs = seqs
+		end
+		
+		# -------------------------------------------- UniProt (sp)
+		# blast
+		my_blast = run_blastx(new_seqs, "sp_#{@options[:tax_group]}/sp_#{@options[:tax_group]}.fasta", "sp_#{@options[:tax_group]}")
+		
+		# 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?}
+		
+		# -------------------------------------------- UniProt (tr)
+		# blast
+		my_blast = run_blastx(new_seqs, "tr_#{@options[:tax_group]}/tr_#{@options[:tax_group]}.fasta", "tr_#{@options[:tax_group]}")
+		
+		# 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]}")
+		end
+		
+		# -------------------------------------------- Test Code
+		# the sequences without a reliable similarity with an orthologue are processed with Test Code
+		testcode_input=seqs.select{|s| !s.get_annotations(:tcode).empty?}
+
+# active this line to test tcode. hay que comentar todas las lineas de arriba de este metodo
+# testcode_input=seqs
+
+		testcode_input.each do |seq|
+			TestCode.new(seq)
+		end
+
+	end
+	
+end
+

data/lib/full_lengther_next/classes/my_worker_manager.rb

@@ -0,0 +1,167 @@
+require 'json'
+require 'scbi_fasta'
+require 'sequence'
+
+require 'fl2_stats'
+include Fl2Stats
+
+class MyWorkerManager < ScbiMapreduce::WorkManager
+
+	# open files and prepare global data
+	def self.init_work_manager(options,chunk_size=100)
+
+		input_file=options[:fasta]
+		
+		if !File.exists?('fl2_results')
+			Dir.mkdir('fl2_results')
+		end
+
+		@@fasta_file = FastaQualFile.new(input_file,'')
+		@@chunk_size=chunk_size
+		@@options = options
+
+		@@annotation_file = File.open("fl2_results/annotations.txt", 'w')
+		@@annotation_file.puts "Query_id\tfasta_length\tSubject_id\tdb_name\tStatus\tt_code\te_value\tp_ident\tprotein_length\ts_length\tWarning_msgs\tframe\tORF_start\tORF_end\ts_start\ts_end\tDescription\tProtein_sequence"
+
+		@@alignment_file = File.open("fl2_results/alignments.txt", 'w')
+		@@prot_file = File.open("fl2_results/proteins.fasta", 'w')
+		@@nts_file = File.open("fl2_results/nt_seq.txt", 'w')
+		@@tcode_file=File.open("fl2_results/tcode_result.txt", 'w')
+		@@tcode_file.puts "Query_id\tfasta_length\tSubject_id\tdb_name\tStatus\tt_code\te_value\tp_ident\tprotein_length\ts_length\tWarning_msgs\tframe\tORF_start\tORF_end\ts_start\ts_end\tDescription\tProtein_sequence"
+
+		# @@error_fasta_file = File.open("fl2_results/error_seqs.fasta", 'w')
+		# @@error_file = File.open("fl2_results/errors_info.txt", 'w')
+
+	end
+		
+	# close files
+	def self.end_work_manager
+		@@fasta_file.close
+		
+		@@annotation_file.close
+		@@alignment_file.close
+		@@prot_file.close
+		@@nts_file.close
+		@@tcode_file.close
+		
+		# @@error_fasta_file.close
+		# @@error_file.close
+		
+		summary_stats
+	end
+		
+	def error_received(worker_error, obj)
+		puts "Error while processing object #{obj.inspect}\n" + worker_error.original_exception.message + ":\n" +worker_error.original_exception.backtrace.join("\n")
+  end
+
+  def too_many_errors_received
+		$LOG.error "Too many errors: #{@@error_count} errors on #{@@count} executed sequences, exiting before finishing"
+  end
+
+	# send initial config
+	def worker_initial_config
+		return @@options
+	end
+		 
+	# this method is called every time a worker needs a new work
+	# Return the work data or nil if no more data is available
+	def next_work
+		
+    # seqs=[]
+		# if (@@count % 2==0)
+		# 	$LOG.info("Processed #{@@count}")
+		# end
+					
+		# prepare work
+    # @@chunk_size.times do
+		n,f,q = @@fasta_file.next_seq
+		
+		if !n.nil?
+				return Sequence.new(n,f,q)
+			else
+				return nil
+		end
+    
+    # end
+		
+		# return work
+		# if !seqs.empty?
+		#       return seqs
+		#     else
+		#       return nil
+		#     end
+		
+	end
+  	
+		# this method is ejecuted each time an obj is finished
+	def work_received(obj)
+	
+			obj.each do |seq|
+				# puts seq.seq_name
+				
+				write_seq(seq)
+				
+			end
+	end 
+
+
+	def write_seq(seq)
+		begin
+# --------------------------------------------------------     Complete Seqs
+			if (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][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
+# --------------------------------------------------------     Test Code
+			elsif (t=seq.get_annotations(:tcode).first)
+				@@tcode_file.puts t[:message]
+			end
+# --------------------------------------------------------     Errors
+			# if e=seq.get_annotations(:error).first
+			# 	if !e[:message].empty?
+			# 		@@error_fasta_file.puts ">#{seq.seq_name}\n#{seq.seq_fasta}"
+			# 		@@error_file.puts e[:message]
+			# 	end
+			# end
+
+		rescue
+			puts "Error printing #{seq.seq_name}"
+		end
+		
+	end
+	
+	
+  	
+end
+