full_lengther_next 0.0.1

data/lib/full_lengther_next/classes/une_los_hit.rb

@@ -0,0 +1,287 @@
+
+require 'common_functions'
+include CommonFunctions
+
+class UneLosHit
+	
+	attr_reader :output_seq, :final_hit, :msgs, :number_x, :wrong_seq, :is_ok, :q_index_start, :full_prot
+   
+	def initialize(q, query_fasta, pident_threshold)
+				
+		(mismas_ids_array, query_fasta, wrong_seq) = hits_misma_id(q, query_fasta)
+		
+		@wrong_seq = wrong_seq
+		@mismas_ids_array = mismas_ids_array
+		@msgs = ''
+		@number_x = 0
+		num_x = ''
+		
+		@output_seq = query_fasta
+		
+		if (mismas_ids_array.count > 1)
+			mismas_ids_array.sort! {|h1,h2| h1.q_beg <=> h2.q_beg} # ordenamos los hit por el inicio del query
+			@final_hit = mismas_ids_array[0].dup
+
+			mismas_ids_array.each do |hit|
+				if (hit.ident >= pident_threshold)
+					# if ($verbose)
+						# puts "#{hit.acc}\tsc:#{hit.score}\teval:#{hit.e_val}\tid:#{hit.ident}\tframe:#{hit.q_frame}\tqb:#{hit.q_beg + 1}\tqe:#{hit.q_end + 1}\tsb:#{hit.s_beg + 1}\tse:#{hit.s_end + 1}"
+						# puts "#{query_fasta[hit.q_beg..hit.q_end].translate}"
+					# end
+				
+					same = same_hit(hit)
+			
+					if (!same)
+						if (@final_hit.q_frame == hit.q_frame)
+							same_frame_hits(hit)
+						else
+							# condiciones para corregir el frame en el que tiene que continuar la seq de nt
+							correccion_x = 0
+							if (@final_hit.q_frame - hit.q_frame == 1)
+								correccion_x = 1
+							elsif (@final_hit.q_frame - hit.q_frame == 2)
+								correccion_x = 2
+							elsif (@final_hit.q_frame - hit.q_frame == -1)
+								correccion_x = 2
+							elsif (@final_hit.q_frame - hit.q_frame == -2)
+								correccion_x = 1
+							end
+						
+							# las secuencias solapan en el query
+							if ((@final_hit.q_end >= hit.q_beg) && (@final_hit.q_end < hit.q_end)) && (hit.q_end > @final_hit.q_end + 15)
+								overlapped_hits(hit, correccion_x, q)
+								# puts "---#{@output_seq[@final_hit.q_frame-1, @output_seq.length+1].translate}"
+						
+							elsif (@final_hit.q_end < hit.q_beg) && (hit.q_end > @final_hit.q_end + 15) # las secuencias estan separadas en el query
+								separated_hits(hit, correccion_x, q)
+								# puts "----------#{@output_seq[@final_hit.q_frame-1, @output_seq.length+1].translate}"
+							else
+								@msgs = 'warning!, putative chimeric sequence! or repetitive structure'
+								# puts "\nWARNING!, PUTATIVE CHIMERIC SEQUENCE !!!\n\n"
+							end
+						end
+					end
+				end # pident
+			end
+
+		else
+
+			@final_hit = mismas_ids_array[0].dup
+			
+			# if ($verbose)
+				# puts "***#{@final_hit.acc}\t#{@final_hit.score}\t#{@final_hit.e_val}\t#{@final_hit.ident}\t#{@final_hit.align_len}\t#{@final_hit.q_frame}\t#{@final_hit.q_beg + 1}\t#{@final_hit.q_end + 1}\t#{@final_hit.s_beg + 1}\t#{@final_hit.s_end + 1}\t#{@final_hit.q_seq}"
+				# puts "#{query_fasta[@final_hit.q_beg..@final_hit.q_end].translate}"
+			# end
+		end
+		# puts "***#{@final_hit.acc}\t#{@final_hit.score}\t#{@final_hit.e_val}\t#{@final_hit.ident}\t#{@final_hit.align_len}\t#{@final_hit.q_frame}\t#{@final_hit.q_beg + 1}\t#{@final_hit.q_end + 1}\t#{@final_hit.s_beg + 1}\t#{@final_hit.s_end + 1}\t#{@final_hit.q_seq}"
+		# puts "#{query_fasta[@final_hit.q_beg..@final_hit.q_end].translate}"
+		
+		@full_prot = @output_seq[@final_hit.q_frame-1, @output_seq.length+1].translate
+		# puts "\nfull_prot_ulh: \n#{full_prot}"
+		
+		(@is_ok, @q_index_start) = contenidos_en_prot(@final_hit, @full_prot, q)
+		
+	end
+
+
+
+	def same_hit(hit)
+	
+		same = false
+		if (hit.score == @final_hit.score &&
+			hit.q_beg == @final_hit.q_beg &&
+			hit.q_end == @final_hit.q_end &&
+			hit.s_beg == @final_hit.s_beg &&
+			hit.s_end == @final_hit.s_end)
+		
+			same = true
+		end
+	
+		return same
+	end
+
+
+
+	def same_frame_hits(hit)
+		
+		@final_hit.q_beg = @final_hit.q_beg
+		@final_hit.q_end = hit.q_end
+		
+		@final_hit.s_beg = [@final_hit.s_beg,hit.s_beg].min
+		@final_hit.s_end = [@final_hit.s_end,hit.s_end].max
+		
+	end
+
+
+
+	def overlapped_hits(hit,correccion_x,q)
+	  # puts q.inspect
+		# puts "los hits solapan!!!"
+		
+		if (@msgs.empty?)
+			@msgs = "Overlapping hits, possible frame ERROR between #{@final_hit.q_end + 1} and #{hit.q_beg + 1}, "
+		else
+			@msgs += " and overlapping frame ERROR between #{@final_hit.q_end + 1} and #{hit.q_beg + 1}, "
+		end
+		
+		# -------------------------------------   preparamos los nt y aas que solapan
+		overlapped_nt = 0
+		overlapped_nt = (@final_hit.q_end - hit.q_beg + 1)
+
+		overlapped_aas = 0
+		overlapped_aas = (@final_hit.s_end - hit.s_beg + 1)
+		# ------------------------------------- 
+		if (overlapped_nt % 3 == 1)
+			overlapped_nt += 2
+		elsif (overlapped_nt % 3 == 2)
+			overlapped_nt += 1
+		end
+		# -------------------------------------   calculamos el numero de x a añadir 
+		@number_x = (((correccion_x + overlapped_nt)/3)+1)*3
+		@number_x_aa = overlapped_aas
+		num_x = ''
+		num_x_aa = ''
+
+		if (@number_x.to_i > 0)
+			num_x = 'x'*@number_x.to_i
+		elsif (@number_x.to_i == 0)
+			num_x = ''
+		else
+			@msgs = "ERROR#2 unexpected negative index in x_number, "
+			# puts "ERROR#2 unexpected negative index in x_number"
+		end
+
+		if (@number_x_aa.to_i > 0)
+			num_x_aa = 'x'*@number_x_aa.to_i
+		elsif (@number_x_aa.to_i == 0)
+			num_x_aa = ''
+		else
+			num_x_aa = 'x'*@number_x_aa.to_i.abs
+			@msgs = "Warning!, your query overlaps and the subject is separated, "
+		end
+
+		if (@number_x_aa.to_i >= 0)
+			@final_hit.q_seq = "#{@final_hit.q_seq[0..@final_hit.q_seq.length - 1 - overlapped_aas]}#{num_x_aa}#{hit.q_seq[overlapped_aas..hit.q_seq.length]}"
+			@final_hit.s_seq = "#{@final_hit.s_seq[0..@final_hit.s_seq.length - 1 - overlapped_aas]}#{num_x_aa}#{hit.s_seq[overlapped_aas..hit.s_seq.length]}"
+		else
+			@final_hit.q_seq = "#{@final_hit.q_seq[0..@final_hit.q_seq.length - 1]}#{num_x_aa}#{hit.q_seq[0..hit.q_seq.length]}"
+			@final_hit.s_seq = "#{@final_hit.s_seq[0..@final_hit.s_seq.length - 1]}#{num_x_aa}#{hit.s_seq[0..hit.s_seq.length]}"
+		end
+		
+		
+		output_seq_tmp = "#{@output_seq[0..(@final_hit.q_end - overlapped_nt)]}#{num_x}#{@output_seq[(hit.q_beg + overlapped_nt)..(@output_seq.length)]}"
+
+		full_prot_tmp = output_seq_tmp[@final_hit.q_frame-1, output_seq_tmp.length+1].translate
+		
+		(is_ok_tmp, q_index_start_tmp) = contenidos_en_prot(@final_hit, full_prot_tmp, q)
+
+		@output_seq = output_seq_tmp.dup
+		
+		@final_hit.q_beg = @final_hit.q_beg
+		@final_hit.q_end = hit.q_end
+		
+		@final_hit.s_beg = [@final_hit.s_beg,hit.s_beg].min
+		@final_hit.s_end = [@final_hit.s_end,hit.s_end].max
+		
+	end
+
+
+
+	def separated_hits(hit,correccion_x,q)
+		
+		# puts "los hits estan separados!!!"
+		
+		if (@msgs.empty?)
+			@msgs = "Separated hits, possible frame ERROR between #{@final_hit.q_end + 1} and #{hit.q_beg + 1}, "
+		else
+			@msgs += " and possible frame ERROR between #{@final_hit.q_end + 1} and #{hit.q_beg + 1}, "
+		end
+		
+		# PROBAR CON % 3!!!!!!!!!!!!!!!!!!!!!!!!
+		@number_x = (hit.q_beg - @final_hit.q_end - 1)
+		# @number_x = (hit.q_beg - @final_hit.q_end - 1) + correccion_x
+		if (@number_x % 3 == 1)
+			@number_x += 2
+		elsif (@number_x % 3 == 2)
+			@number_x += 1
+		end
+		
+
+		if (@number_x.to_i > 0)
+			num_x = 'x'*@number_x.to_i
+			num_x_aa = 'x'*(@number_x.to_i/3)
+		elsif (@number_x.to_i == 0)
+			num_x = ''
+			num_x_aa = ''
+		else
+			@msgs = "ERROR#2 unexpected negative index in x_number"
+			# puts "ERROR#2 unexpected negative index in x_number"
+		end
+
+		@output_seq = @output_seq[0..@final_hit.q_end-1]+num_x+@output_seq[hit.q_beg-1..@output_seq.length-1]
+		# @output_seq = @output_seq[0..@final_hit.q_end-1]+num_x+@output_seq[hit.q_beg-1..@output_seq.length-1]
+
+		@final_hit.score += 1
+		@final_hit.q_beg = @final_hit.q_beg
+		@final_hit.q_end = hit.q_end
+		@final_hit.s_beg = @final_hit.s_beg
+		@final_hit.s_end = hit.s_end
+
+		@final_hit.q_seq = "#{@final_hit.q_seq[0, @final_hit.q_seq.length]}#{num_x_aa}#{hit.q_seq[0, hit.q_seq.length]}"
+		@final_hit.s_seq = "#{@final_hit.s_seq[0, @final_hit.s_seq.length]}#{num_x_aa}#{hit.s_seq[0, hit.s_seq.length]}"
+
+		num_x = ''
+		num_x_aa = ''
+		
+		full_prot_tmp = @output_seq[@final_hit.q_frame-1, @output_seq.length+1].translate
+		# puts "\n\nfull_prot_tmp:#{full_prot_tmp}"
+		# puts "\n\n#{@output_seq[@final_hit.q_frame-1, @output_seq.length+1]}"
+		
+		(is_ok_tmp, q_index_start_tmp) = contenidos_en_prot(@final_hit, full_prot_tmp, q)
+		
+		# puts "#{q.query_def}: is_ok_tmp: #{is_ok_tmp} separated hits"
+	end
+
+
+
+	# creamos un array en el que esten solo los hits con la misma id. 
+	def hits_misma_id(q, query_fasta_ori)
+		
+		# Se les hace la reveso complementaria si es necesario, y se comprueba que para un mismo query no hay hits en sentidos diferentes
+		wrong_seq = false
+		
+		misma_id = []
+		
+		query_fasta = query_fasta_ori.dup
+		frame_ori = q.hits[0].q_frame
+
+		q.hits.each do |h|
+
+			# puts "#{q.query_def} f_ori :#{frame_ori} y h_f: #{h.q_frame}"
+			reversed_hit = false # con respecto al primer hit, que es el de mayor score o evalue
+			if (h.acc == q.hits[0].acc)
+
+				# comprobar si los frames tiene el mismo sentido
+				if ((frame_ori < 0 && h.q_frame > 0) or (frame_ori > 0 && h.q_frame < 0))
+					wrong_seq = true
+					reversed_hit = true
+					# puts "The sequence #{q.query_def} contains sense and antisense hits!!! #{frame_ori} y #{h.q_frame}"
+				end
+				
+				if (reversed_hit == false)
+					if (h.q_frame.to_i < 0) # si la secuencia esta al reves le damos la vuelta
+						(query_fasta, h.q_frame, h.q_beg, h.q_end) = reverse_seq(query_fasta_ori, h.q_frame, h.q_beg, h.q_end)
+						h.reversed = true
+					end
+					misma_id.push h
+				end
+
+			end
+
+		end
+
+		return [misma_id, query_fasta, wrong_seq]
+	end
+
+
+end

data/script/console

@@ -0,0 +1,10 @@
+#!/usr/bin/env ruby
+# File: script/console
+irb = RUBY_PLATFORM =~ /(:?mswin|mingw)/ ? 'irb.bat' : 'irb'
+
+libs =  " -r irb/completion"
+# Perhaps use a console_lib to store any extra methods I may want available in the cosole
+# libs << " -r #{File.dirname(__FILE__) + '/../lib/console_lib/console_logger.rb'}"
+libs <<  " -r #{File.dirname(__FILE__) + '/../lib/full_lengther_next.rb'}"
+puts "Loading full_lengther_next gem"
+exec "#{irb} #{libs} --simple-prompt"

data/script/destroy

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+APP_ROOT = File.expand_path(File.join(File.dirname(__FILE__), '..'))
+
+begin
+  require 'rubigen'
+rescue LoadError
+  require 'rubygems'
+  require 'rubigen'
+end
+require 'rubigen/scripts/destroy'
+
+ARGV.shift if ['--help', '-h'].include?(ARGV[0])
+RubiGen::Base.use_component_sources! [:rubygems, :newgem, :newgem_theme, :test_unit]
+RubiGen::Scripts::Destroy.new.run(ARGV)

data/script/generate

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+APP_ROOT = File.expand_path(File.join(File.dirname(__FILE__), '..'))
+
+begin
+  require 'rubigen'
+rescue LoadError
+  require 'rubygems'
+  require 'rubigen'
+end
+require 'rubigen/scripts/generate'
+
+ARGV.shift if ['--help', '-h'].include?(ARGV[0])
+RubiGen::Base.use_component_sources! [:rubygems, :newgem, :newgem_theme, :test_unit]
+RubiGen::Scripts::Generate.new.run(ARGV)

data/test/test_full_lengther_next.rb

@@ -0,0 +1,11 @@
+require File.dirname(__FILE__) + '/test_helper.rb'
+
+class TestFullLengtherNext < Test::Unit::TestCase
+
+  def setup
+  end
+  
+  def test_truth
+    assert true
+  end
+end

data/test/test_helper.rb

@@ -0,0 +1,3 @@
+require 'stringio'
+require 'test/unit'
+require File.dirname(__FILE__) + '/../lib/full_lengther_next'

metadata

@@ -0,0 +1,150 @@
+--- !ruby/object:Gem::Specification 
+name: full_lengther_next
+version: !ruby/object:Gem::Version 
+  prerelease: 
+  version: 0.0.1
+platform: ruby
+authors: 
+- Noe Fernandez & Dario Guerrero
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2012-02-06 00:00:00 Z
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: xml-simple
+  prerelease: false
+  requirement: &id001 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 1.0.12
+  type: :runtime
+  version_requirements: *id001
+- !ruby/object:Gem::Dependency 
+  name: scbi_blast
+  prerelease: false
+  requirement: &id002 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 0.0.32
+  type: :runtime
+  version_requirements: *id002
+- !ruby/object:Gem::Dependency 
+  name: scbi_mapreduce
+  prerelease: false
+  requirement: &id003 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 0.0.29
+  type: :runtime
+  version_requirements: *id003
+- !ruby/object:Gem::Dependency 
+  name: scbi_fasta
+  prerelease: false
+  requirement: &id004 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 0.1.7
+  type: :runtime
+  version_requirements: *id004
+- !ruby/object:Gem::Dependency 
+  name: scbi_plot
+  prerelease: false
+  requirement: &id005 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 0.0.6
+  type: :runtime
+  version_requirements: *id005
+- !ruby/object:Gem::Dependency 
+  name: hoe
+  prerelease: false
+  requirement: &id006 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 2.8.0
+  type: :development
+  version_requirements: *id006
+description: "FULL-LENGTHERNEXT is a tool adapted to NGS technologies, able to work in parallel and in a distributed way to minimise computing time. It is able to classify unigenes to full-length, 5\xE2\x80\x99-end, 3\xE2\x80\x99-end and internal, suggesting which unknown genes are coding or not. It will be also shown that FULL-LENGTHERNEXT fixes frame shifts, one of the main mistake found in wrong entries of full-length sequences databases, and it is a fast tool to compare different transcriptome assemblies."
+email: 
+- noeisneo@gmail.com & dariogf@gmail.com
+executables: 
+- download_fln_dbs.rb
+- make_user_db.rb
+- full_lengther_next
+extensions: []
+
+extra_rdoc_files: 
+- History.txt
+- Manifest.txt
+- PostInstall.txt
+files: 
+- bin/download_fln_dbs.rb
+- bin/make_user_db.rb
+- bin/full_lengther_next
+- History.txt
+- lib/full_lengther_next/classes/common_functions.rb
+- lib/full_lengther_next/classes/fl2_stats.rb
+- lib/full_lengther_next/classes/fl_analysis.rb
+- lib/full_lengther_next/classes/fl_string_utils.rb
+- lib/full_lengther_next/classes/lcs.rb
+- lib/full_lengther_next/classes/my_worker.rb
+- lib/full_lengther_next/classes/my_worker_manager.rb
+- lib/full_lengther_next/classes/orf.rb
+- lib/full_lengther_next/classes/sequence.rb
+- lib/full_lengther_next/classes/test_code.rb
+- lib/full_lengther_next/classes/une_los_hit.rb
+- lib/full_lengther_next.rb
+- Manifest.txt
+- PostInstall.txt
+- Rakefile
+- README.rdoc
+- script/console
+- script/destroy
+- script/generate
+- test/test_full_lengther_next.rb
+- test/test_helper.rb
+homepage: http://www.scbi.uma.es/downloads
+licenses: []
+
+post_install_message: PostInstall.txt
+rdoc_options: 
+- --main
+- README.rdoc
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+requirements: []
+
+rubyforge_project: full_lengther_next
+rubygems_version: 1.7.2
+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
+test_files: 
+- test/test_full_lengther_next.rb
+- test/test_helper.rb