full_lengther_next 0.0.8 → 0.5.6

data/lib/full_lengther_next/classes/warnings.rb

@@ -0,0 +1,40 @@
+$warnings_hash = {}
+
+#Chimeras
+$warnings_hash['solved'] = 'SOLVED'
+
+#Ncrna
+$warnings_hash['<200nt'] = 'Sequence length < 200 nt'
+
+#Artifacts
+$warnings_hash['ERROR#1'] = 'ERROR#1, contains sense and antisense hits!!!, putative chimeric sequence, ' 
+$warnings_hash['ERROR#2'] = 'ERROR#2, query has several hsps that overlaps on same protein zone'
+$warnings_hash['ERROR#3'] = 'ERROR#3, Sequence has a lot of errors or reference protein is too different'
+
+#FL_analisys
+$warnings_hash['PositionResult'] = 'Selected protein is hit number (*replace*) in blast result, '
+$warnings_hash['SingleResult'] = 'Selected protein is the only available option, '
+$warnings_hash['noM1'] = 'W1: There is no M at the beginning, possible sequencing error, '
+$warnings_hash['UnexpSTOP5p'] = ' Unexpected STOP codon in 5 prime region, '
+$warnings_hash['NoStopMfar'] = 'No stop codon before M and M found is too far from subject M, '
+$warnings_hash['noM2'] = 'W2: There is no M at the beginning, '
+$warnings_hash['UnexpSTOP3p'] = ' Unexpected STOP codon at 3\' end. '
+$warnings_hash['UnexpSTOP3pDist'] = ' Unexpected STOP codon at 3\' end. Distance to subject end: (*replace*) aas, '
+$warnings_hash['DistSubj'] = 'Distance to subject end: (*replace*) aas, not enough to search stop codon'
+$warnings_hash['qStopTooFar'] = 'query STOP codon too far from subject stop. Distance to subject end: (*replace*) aas, putative chimeric sequence,'
+$warnings_hash['qStopFar'] = 'query STOP codon is far from subject stop. Distance to subject end: (*replace*) aas,'
+$warnings_hash['noStopDist'] = ' STOP codon was not found. Distance to subject end: (*replace*) aas, ' 
+$warnings_hash['UnexpStopBegSeq'] = 'Unexpected stop codon in the beginning of your sequence, ' 
+$warnings_hash['SeqLonger'] = ' your sequence is longer than subject: (*replace*) - (*replace*)' 
+$warnings_hash['SeqShorter'] = 'your sequence is shorter than subject: (*replace*) - (*replace*)' 
+$warnings_hash['VeryShorter'] = '. Was predicted as Complete, but is very much shorter than subject'
+$warnings_hash['NoStop'] = ' STOP codon was not found, '
+$warnings_hash['ProtFusion'] = ' Possible protein fusion, '
+$warnings_hash['QueryTooLong'] = ' Query too long, '
+$warnings_hash['ExFrameS'] = ' Frameshift at (*replace*) (ex), '
+
+#UneLosHit
+$warnings_hash['OverlapHit'] = 'Overlapping hits, possible frame ERROR between (*replace*) and (*replace*), '
+$warnings_hash['AndOverlapHit'] = ' and overlapping frame ERROR between (*replace*) and (*replace*), ' 
+$warnings_hash['SeparatedHit'] = 'Separated hits, possible frame ERROR between (*replace*) and (*replace*), ' 
+$warnings_hash['AndSeparatedHit'] = ' and possible frame ERROR between (*replace*) and (*replace*), '

metadata

@@ -1,152 +1,266 @@
---- !ruby/object:Gem::Specification 
+--- !ruby/object:Gem::Specification
 name: full_lengther_next
-version: !ruby/object:Gem::Version 
+version: !ruby/object:Gem::Version
+  version: 0.5.6
   prerelease: 
-  version: 0.0.8
 platform: ruby
-authors: 
-- Noe Fernandez & Dario Guerrero
+authors:
+- ! 'Pedro Seoane & Noe Fernandez & Dario Guerrero '
 autorequire: 
 bindir: bin
 cert_chain: []
-
-date: 2012-11-28 00:00:00 Z
-dependencies: 
-- !ruby/object:Gem::Dependency 
+date: 2015-12-07 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
   name: xml-simple
-  prerelease: false
-  requirement: &id001 !ruby/object:Gem::Requirement 
+  requirement: !ruby/object:Gem::Requirement
     none: false
-    requirements: 
-    - - ">="
-      - !ruby/object:Gem::Version 
+    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 
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 1.0.12
+- !ruby/object:Gem::Dependency
+  name: scbi_blast
+  requirement: !ruby/object:Gem::Requirement
     none: false
-    requirements: 
-    - - ">="
-      - !ruby/object:Gem::Version 
-        version: 0.0.37
+    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 
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 0.0.32
+- !ruby/object:Gem::Dependency
+  name: scbi_mapreduce
+  requirement: !ruby/object:Gem::Requirement
     none: false
-    requirements: 
-    - - ">="
-      - !ruby/object:Gem::Version 
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
         version: 0.0.29
   type: :runtime
-  version_requirements: *id003
-- !ruby/object:Gem::Dependency 
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 0.0.29
+- !ruby/object:Gem::Dependency
   name: scbi_fasta
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 0.1.7
+  type: :runtime
   prerelease: false
-  requirement: &id004 !ruby/object:Gem::Requirement 
+  version_requirements: !ruby/object:Gem::Requirement
     none: false
-    requirements: 
-    - - ">="
-      - !ruby/object:Gem::Version 
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
         version: 0.1.7
+- !ruby/object:Gem::Dependency
+  name: bio-cd-hit-report
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 0.1.0
   type: :runtime
-  version_requirements: *id004
-- !ruby/object:Gem::Dependency 
-  name: scbi_plot
   prerelease: false
-  requirement: &id005 !ruby/object:Gem::Requirement 
+  version_requirements: !ruby/object:Gem::Requirement
     none: false
-    requirements: 
-    - - ">="
-      - !ruby/object:Gem::Version 
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 0.1.0
+- !ruby/object:Gem::Dependency
+  name: bio
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 1.4.3
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 1.4.3
+- !ruby/object:Gem::Dependency
+  name: scbi_plot
+  requirement: !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 
+  version_requirements: !ruby/object:Gem::Requirement
     none: false
-    requirements: 
-    - - ">="
-      - !ruby/object:Gem::Version 
-        version: 2.8.0
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 0.0.6
+- !ruby/object:Gem::Dependency
+  name: rdoc
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '3.10'
   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: 
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '3.10'
+- !ruby/object:Gem::Dependency
+  name: newgem
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 1.5.3
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 1.5.3
+- !ruby/object:Gem::Dependency
+  name: hoe
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '3.3'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '3.3'
+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’-end, 3’-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:
+- seoanezonjic@hotmail.com & noeisneo@gmail.com & dariogf@gmail.com
+executables:
+- plot_taxonomy.rb
+- plot_fln.rb
 - download_fln_dbs.rb
-- make_user_db.rb
 - full_lengther_next
+- make_user_db.rb
+- make_test_dataset.rb
 extensions: []
-
-extra_rdoc_files: 
+extra_rdoc_files:
+- PostInstall.txt
+- README.rdoc
 - History.txt
 - Manifest.txt
-- PostInstall.txt
-files: 
+files:
+- Rakefile
+- script/generate
+- script/destroy
+- script/console
+- test/test_full_lengther_next.rb
+- test/test_helper.rb
+- bin/plot_taxonomy.rb
+- bin/plot_fln.rb
 - bin/download_fln_dbs.rb
-- bin/make_user_db.rb
 - bin/full_lengther_next
+- bin/make_user_db.rb
+- bin/make_test_dataset.rb
+- PostInstall.txt
+- README.rdoc
 - History.txt
-- lib/full_lengther_next/classes/common_functions.rb
+- Manifest.txt
+- lib/full_lengther_next/classes/blast_functions.rb
+- lib/full_lengther_next/classes/my_worker_manager_fln.rb
+- lib/full_lengther_next/classes/types.rb
 - lib/full_lengther_next/classes/chimeric_seqs.rb
+- lib/full_lengther_next/classes/artifacts.rb
+- lib/full_lengther_next/classes/cdhit.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
-- 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/nc_rna.rb
-- lib/full_lengther_next/classes/orf.rb
 - lib/full_lengther_next/classes/sequence.rb
+- lib/full_lengther_next/classes/my_worker_EST.rb
 - lib/full_lengther_next/classes/test_code.rb
+- lib/full_lengther_next/classes/orf.rb
 - lib/full_lengther_next/classes/une_los_hit.rb
+- lib/full_lengther_next/classes/warnings.rb
+- lib/full_lengther_next/classes/fln_stats.rb
+- lib/full_lengther_next/classes/my_worker_manager_EST.rb
+- lib/full_lengther_next/classes/nc_rna.rb
+- lib/full_lengther_next/classes/reptrans.rb
+- lib/full_lengther_next/classes/common_functions.rb
+- lib/full_lengther_next/classes/exonerate_result.rb
+- lib/full_lengther_next/classes/handle_db.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
+- lib/expresscanvas.zip
+- .gemtest
 homepage: http://www.scbi.uma.es/downloads
 licenses: []
-
 post_install_message: PostInstall.txt
-rdoc_options: 
+rdoc_options:
 - --main
 - README.rdoc
-require_paths: 
+require_paths:
 - lib
-required_ruby_version: !ruby/object:Gem::Requirement 
+required_ruby_version: !ruby/object:Gem::Requirement
   none: false
-  requirements: 
-  - - ">="
-    - !ruby/object:Gem::Version 
-      version: "0"
-required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
-  requirements: 
-  - - ">="
-    - !ruby/object:Gem::Version 
-      version: "0"
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
 requirements: []
-
 rubyforge_project: full_lengther_next
-rubygems_version: 1.8.24
+rubygems_version: 1.8.23
 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: 
+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

data/lib/full_lengther_next/classes/lcs.rb

@@ -1,33 +0,0 @@
-
-
-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_manager.rb

@@ -1,240 +0,0 @@
-require 'json'
-require 'scbi_fasta'
-require 'sequence'
-
-require 'fln_stats'
-include FlnStats
-
-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?('fln_results')
-			Dir.mkdir('fln_results')
-		end
-		
-		file_head = "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"
-		
-		@@fasta_file = FastaQualFile.new(input_file,'')
-		@@chunk_size=chunk_size
-		@@options = options
-
-		@@annotation_file = File.open("fln_results/dbannotated.txt", 'w')
-		@@annotation_file.puts file_head
-
-		@@alignment_file = File.open("fln_results/alignments.txt", 'w')
-		@@prot_file = File.open("fln_results/proteins.fasta", 'w')
-		@@nts_file = File.open("fln_results/nt_seq.txt", 'w')
-		@@tcode_file=File.open("fln_results/new_coding.txt", 'w')
-		@@tcode_file.puts file_head
-
-		@@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')
-
-	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
-		@@nc_rna_file.close
-		
-		if (!@@options[:chimera].nil?)
-			@@chimera_file.close
-		end
-		
-		# @@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
-# --------------------------------------------------------     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][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
-# ---------------------------------------------------------------------------------
-# --------------------------------------------------------    without Chimeric Seqs Mode
-			else
-# -------------------------------------------------     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
-# -------------------------------------------------     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
-			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
-