full_lengther_next 0.9.9 → 1.0.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 4a6a23e7a0bc8c6ba6ad5e3f1579accb80a16bf1
-  data.tar.gz: 3980b046483ecbfe54147cffb20cf8f6a61bea69
+SHA256:
+  metadata.gz: e6d28d54912b46305ba0047c8458469afffe6660189cb1950c1d30290982e2c4
+  data.tar.gz: fca1a71701c8b1c763102623b6fc60d7699b697ebd636ce53f14886d07fb35f4
 SHA512:
-  metadata.gz: c5ecb5ebcf8077a0000a5ce404dcc6a1468654fdeac3f2a48aa3dd8f2ef3eed6db51f6123abf3452ddc33ef56c3b896ad15125fc76621105d1db6e5a486954c6
-  data.tar.gz: 795f3cea0505142218ad29411e1fdbc8e0ce2b4e72c42a18b54763f77f9e0d4c7e711836fe1f0561557224cb089bd511078e7a6a81fe87fb4e5d68fce3864910
+  metadata.gz: c1398e4d8448f10550769e4f6cb7baa2492337f377fab2f33b3de7067213f1d45ceae1a717de69c59c113c80d585d85bd7d4f1b0d6ed236fb0a5c8d7ac244f3e
+  data.tar.gz: 85c5238d3569e17509135e97383e748183fadc00c2c9eca9f984492b12ba4b4bd22e908eaae755162e4070c5eda8df1fcdffdbdb794c216537a0304b7bbe45bd

data/bin/download_fln_dbs.rb

@@ -10,6 +10,7 @@ require 'scbi_zcat'
 require 'optparse'
 require 'cdhit'
 require 'handle_db'
+require 'bio_patch'
 
 ############################################################################################## 
 ## METHODS
@@ -69,29 +70,30 @@ def filtering_seqs(fasta_file, max_length, black_list)
 end
 
 def compare_list(string, list)
-    res = FALSE
+    res = false
     list.each do |word|
         if string.include?(word)
-            res = TRUE
+            res = true
             break
         end
     end
     return res
 end
 
-def conecta_uniprot(my_array, formatted_db_path)
+def conecta_uniprot(my_array, formatted_db_path, no_trembl, passive_ftp)
 	
 	Dir.mkdir(formatted_db_path) if !File.exists?(formatted_db_path)
 	varsplic_out=File.join(formatted_db_path,'uniprot_sprot_varsplic.fasta.gz')
 
 	$ftp = Net::FTP.new()
+	$ftp.passive = true if passive_ftp
 	$ftp.connect('ftp.ebi.ac.uk')
 	$ftp.login
 	
 	puts "connected to UniProt"
 	my_array.each do |db_group|
 		puts "Downloading #{db_group}"
-		download_uniprot(db_group, formatted_db_path)
+		download_uniprot(db_group, formatted_db_path, no_trembl)
 	end
 
 	#archivo de variantes de splicing. POR QUE?
@@ -102,13 +104,13 @@ def conecta_uniprot(my_array, formatted_db_path)
 	puts "isoform files downloaded"
 end
 
-def download_uniprot(uniprot_group, formatted_db_path)
+def download_uniprot(uniprot_group, formatted_db_path, no_trembl)
 	
 	sp_out=File.join(formatted_db_path,"uniprot_sprot_#{uniprot_group}.dat.gz")
 	tr_out=File.join(formatted_db_path,"uniprot_trembl_#{uniprot_group}.dat.gz")
 	$ftp.chdir("/pub/databases/uniprot/current_release/knowledgebase/taxonomic_divisions")
 	$ftp.getbinaryfile("uniprot_sprot_#{uniprot_group}.dat.gz", sp_out)
-	$ftp.getbinaryfile("uniprot_trembl_#{uniprot_group}.dat.gz", tr_out)
+	$ftp.getbinaryfile("uniprot_trembl_#{uniprot_group}.dat.gz", tr_out) if !no_trembl
 
 	puts "#{uniprot_group} files downloaded"
 	
@@ -138,13 +140,13 @@ def filter_and_makeDB(formatted_db_path, dbtype, db_group, isoform_hash, prefix,
 end
 
 def complete?(uniprot_record)
-	complete = TRUE
+	complete = true
 	if uniprot_record.description.include?('Flags: Fragment') || #Discard non full length records
 		uniprot_record.seq[0] != 'M' ||
 		uniprot_record.seq.include?('XX') ||
 		uniprot_record.ft.keys.include?('NON_TER') ||# The residue at an extremity of the sequence is not the terminal residue. If applied to position 1, this signifies that the first position is not the N-terminus of the complete molecule. If applied to the last position, it means that this position is not the C-terminus of the complete molecule. There is no description field for this key
 		uniprot_record.ft.keys.include?('NON_CONS') # Non-consecutive residues. Indicates that two residues in a sequence are not consecutive and that there are a number of unreported or missing residues between them
-		complete = FALSE
+		complete = false
 	end
 	return complete	
 end
@@ -304,29 +306,29 @@ optparse = OptionParser.new do |opts|
 		end         
   end
 
-  options[:no_download] = FALSE
+  options[:no_download] = false
   opts.on( '-d', '--no_download', 'Only parse downloaded files without download them again') do 
-		options[:no_download] = TRUE
+		options[:no_download] = true
   end
 
-  options[:no_ncrna] = FALSE
+  options[:no_ncrna] = false
   opts.on( '-n', '--no_ncrna', 'No use ncrna sequences') do 
-		options[:no_ncrna] = TRUE
+		options[:no_ncrna] = true
   end
 
-  options[:only_index] = FALSE
+  options[:only_index] = false
   opts.on( '-i', '--only_index', 'Build annotation index only without do blast DB') do 
-		options[:only_index] = TRUE
+		options[:only_index] = true
   end
 
-  options[:no_trembl] = FALSE
+  options[:no_trembl] = false
   opts.on( '-t', '--no_trembl', 'No use trembl sequences') do 
-		options[:no_trembl] = TRUE
+		options[:no_trembl] = true
   end
 
-  options[:all] = FALSE
+  options[:all] = false
   opts.on( '-a', '--all_sequences', 'Generate databases with all sequences') do 
-		options[:all] = TRUE
+		options[:all] = true
   end
 
   options[:cdhit] = 0
@@ -334,11 +336,15 @@ optparse = OptionParser.new do |opts|
 		options[:cdhit] = cdhit.to_f
   end
 
-  options[:no_uniprot] = FALSE
+  options[:no_uniprot] = false
   opts.on( '-p', '--no_uniprot', 'No use uniprot sequences') do 
-		options[:no_uniprot] = TRUE
+		options[:no_uniprot] = true
   end
 
+  options[:passive_ftp] = false
+  opts.on( '-P', '--passive_ftp', 'Use pasive ftp') do
+                options[:passive_ftp] = true
+  end
 
   # Set a banner, displayed at the top of the help screen.
   opts.banner = "Usage: #{File.basename(__FILE__)} [options]  \n\n"
@@ -359,23 +365,22 @@ optparse.parse!
 ## MAIN
 ##############################################################################################
 
-
-if ENV['BLASTDB'] && File.exists?(ENV['BLASTDB'])
-  formatted_db_path = ENV['BLASTDB']
+if !ENV['BLASTDB'].nil? 
+  formatted_db_path = File.expand_path(ENV['BLASTDB'])
 else # otherwise use ROOTPATH + DB
   formatted_db_path = File.expand_path(File.join(ROOT_PATH, "blast_dbs"))
-  Dir.mkdir(formatted_db_path)
 end
+Dir.mkdir(formatted_db_path) if !File.exists?(formatted_db_path)
 
 
 ENV['BLASTDB'] = formatted_db_path
 puts "Databases will be downloaded at: #{ENV['BLASTDB']}"
 puts "\nTo set the path for storing databases, execute next line in your terminal or add it to your .bash_profile:\n\n\texport BLASTDB=/my_path/\n\n"
-
+puts "Patched? #{Bio::UniProtKB.patched?}"
 download_ncrna(formatted_db_path, options[:no_download]) if !options[:no_ncrna]
 
 if !options[:no_download]
-	conecta_uniprot(options[:uniprot_div], formatted_db_path) 
+	conecta_uniprot(options[:uniprot_div], formatted_db_path, options[:no_trembl], options[:passive_ftp]) 
 end
 
 if !options[:no_uniprot]

data/bin/full_lengther_next

@@ -86,9 +86,9 @@ optparse = OptionParser.new do |opts|
 		end
 	end
 
-	options[:exonerate] = TRUE
+	options[:exonerate] = true
 	opts.on( '-e', '--exonerate', 'Disables exonerate analysis' ) do |exonerate|
-		options[:exonerate] = FALSE
+		options[:exonerate] = false
 	end
 
 	options[:fasta] = nil
@@ -106,9 +106,9 @@ optparse = OptionParser.new do |opts|
 		options[:ident] = ident.to_f 
 	end
 
-	options[:high_clustering] = FALSE
+	options[:high_clustering] = false
 	opts.on( '-k', '--high_clustering', 'Only for representative transcriptome. Add a clustering step using pfam ids. Default false' ) do
-		options[:high_clustering] = TRUE
+		options[:high_clustering] = true
 	end
 
 	options[:subject_coverage] = 0.25
@@ -165,7 +165,7 @@ optparse = OptionParser.new do |opts|
 	options[:user_db] = nil
 	opts.on( '-u', '--user_db UserDB', 'User blast+ database' ) do |db|
 		options[:user_db] = db	
-		if !File.exists?(File.expand_path(db+'.psq'))
+		if Dir.glob(File.expand_path(db+'*.psq')).empty?
 			puts "user database: #{options[:user_db]} was not found"
 			exit
 		end 	
@@ -196,9 +196,9 @@ optparse = OptionParser.new do |opts|
 		options[:training_ident] = ident.to_f 
 	end
 
-	options[:hdd] = FALSE
+	options[:hdd] = false
 	opts.on( '-z', '--hdd', 'Write/use blast report on HDD' ) do |hdd|
-		options[:hdd] = TRUE
+		options[:hdd] = true
 	end
 
 
@@ -207,9 +207,9 @@ optparse = OptionParser.new do |opts|
 		options[:files2map] = files2map.split(';').map{|map_files| map_files.split(',')}
 	end
 
-	options[:remove_unmapped] = TRUE
+	options[:remove_unmapped] = true
 	opts.on('-R', '--remove_unmapped', 'When fastq files are provided, all sequences without at least a read pair are removed. When this option is enabled this filtering is disabled' ) do 
-		options[:remove_unmapped] = FALSE
+		options[:remove_unmapped] = false
 	end
 	
 	# Set a banner, displayed at the top of the help screen.
@@ -268,8 +268,8 @@ if !File.exists?(ncrna_path) && options[:acess_db].include?('c')
 end
 
 if options[:acess_db].include?('s') || options[:acess_db].include?('t')
-	sp_path=File.join(ENV['BLASTDB'],"sp_#{options[:tax_group]}","sp_#{options[:tax_group]}.psq")
-	if !File.exists?(sp_path)
+	sp_path=File.join(ENV['BLASTDB'],"sp_#{options[:tax_group]}","sp_#{options[:tax_group]}*.psq")
+	if Dir.glob(sp_path).empty?
 		puts "DB File #{sp_path} doesn't exists, or"
 		puts "incorrect taxon group name: #{options[:tax_group]} choose:"
 		puts optparse.help

data/bin/make_test_dataset.rb

@@ -120,29 +120,29 @@ optparse = OptionParser.new do |opts|
           options[:duplicate] = duplicate.to_i
   end
 
-  options[:split]= FALSE
+  options[:split]= false
   opts.on( '-s', '--split', 'Split sequences in each case') do
           options[:duplicate] = 3
   end
 
-  options[:chim]= TRUE
+  options[:chim]= true
   opts.on( '-c', '--chim', 'Make sequence set of chimeras') do
-          options[:chim] = FALSE
+          options[:chim] = false
   end
 
-  options[:indel]= TRUE
+  options[:indel]= true
   opts.on( '-i', '--indel', 'Make sequence set of indels') do
-          options[:indel] = FALSE
+          options[:indel] = false
   end
 
-  options[:pair]= TRUE
+  options[:pair]= true
   opts.on( '-p', '--pair', 'Make sequence set of paired') do
-          options[:pair] = FALSE
+          options[:pair] = false
   end
 
-  options[:trim]= TRUE
+  options[:trim]= true
   opts.on( '-t', '--trim', 'Make sequence set of trimmed') do
-          options[:trim] = FALSE
+          options[:trim] = false
   end
 
   # Set a banner, displayed at the top of the help screen.

data/bin/make_user_db.rb

@@ -63,9 +63,9 @@ optparse = OptionParser.new do |opts|
 	options[:name] = name
   end
 
-  options[:local] = FALSE
+  options[:local] = false
   opts.on( '-l', '--local', 'Only parse downloaded files without download them again') do 
-		options[:local] = TRUE
+		options[:local] = true
   end
 
   options[:user_fasta] = nil

data/full_lengther_next.gemspec

@@ -32,7 +32,8 @@ Gem::Specification.new do |spec|
   spec.add_runtime_dependency 'scbi_blast'
   spec.add_runtime_dependency 'scbi_mapreduce'
   spec.add_runtime_dependency 'scbi_zcat'
-  spec.add_runtime_dependency 'bio-cd-hit-report'
+  spec.add_runtime_dependency 'bio'
+  #spec.add_runtime_dependency 'bio-cd-hit-report' # Removed due to conflicts with bio-ruby2. This gem depends on bio ruby 1.4.3. cdhit options disabled
   spec.add_runtime_dependency 'report_html'
 
 

data/lib/full_lengther_next/artifacts.rb

@@ -7,11 +7,11 @@ include ChimericSeqs
 ## MAIN FUNCTION
 #####################################################################
 def artifact?(seq, query, db_name, db_path, options, new_seqs)
-	artifact = FALSE
+	artifact = false
 	# UNMAPPED CONTIG DETECTION
 	if query.nil? && seq.unmapped? #If seq is misassembled stop chimera analisys
 		seq.hit = nil
-		artifact = TRUE
+		artifact = true
 		seq.type = UNMAPPED
 	end
 
@@ -19,7 +19,7 @@ def artifact?(seq, query, db_name, db_path, options, new_seqs)
 		# MISASSEMBLED DETECTION
 		if !artifact && misassembled_detection(query) #If seq is misassembled stop chimera analisys
 			seq.hit = query.hits.first
-			artifact = TRUE
+			artifact = true
 			seq.type = MISASSEMBLED
 			seq.warnings('ERROR#1')
 		end
@@ -35,7 +35,7 @@ def artifact?(seq, query, db_name, db_path, options, new_seqs)
 				else
 					seq.hit = query.hits.first
 				end
-				artifact = TRUE
+				artifact = true
 				seq.type = OTHER
 				seq.warnings('ERROR#2')
 			end
@@ -55,7 +55,7 @@ def artifact?(seq, query, db_name, db_path, options, new_seqs)
 				new_seqs.concat(chimera)
 				seq.db_name = db_name
 				seq.type = CHIMERA
-				artifact = TRUE
+				artifact = true
 			end
 		end
 	end
@@ -64,8 +64,8 @@ def artifact?(seq, query, db_name, db_path, options, new_seqs)
 			puts seq.prot_annot_calification
 		end
 		seq.db_name = db_name
-		seq.save_fasta = FALSE
-		seq.ignore = TRUE
+		seq.save_fasta = false
+		seq.ignore = true
 	end
 	return artifact
 end

data/lib/full_lengther_next/bio_patch.rb

@@ -0,0 +1,93 @@
+module Bio
+	class UniProtKB
+		 def self.patched?
+		 	return true
+		 end
+		 
+		 def ft(feature_key = nil)
+		    return ft[feature_key] if feature_key
+		    return @data['FT'] if @data['FT']
+
+		    table = []
+		    begin
+		      get('FT').split("\n").each do |line|
+		        if line =~ /^FT   \w/
+		          feature = line.chomp.ljust(74)
+		          table << [feature[ 5..12].strip,   # Feature Name
+		                    feature[14..19].strip,   # From
+		                    feature[21..26].strip,   # To
+		                    feature[34..74].strip ]  # Description
+		        else
+		          table.last << line.chomp.sub!(/^FT +/, '')
+		        end
+		      end
+
+		      # Joining Description lines
+		      table = table.map { |feature| 
+		        ftid = feature.pop if feature.last =~ /FTId=/
+		        if feature.size > 4
+		          feature = [feature[0], 
+		                     feature[1], 
+		                     feature[2], 
+		                     feature[3, feature.size - 3].join(" ")]
+		        end
+		        feature << if ftid then ftid else '' end
+		      }
+		      
+		      ###### PATCH TO RECOVER PARSER
+		      to_delete = []
+		      table.each_with_index do |feature, i|
+		      		name, from, to, descrition = feature
+		      		if from.empty?
+		      			coors = to.split("..")
+		      			if coors.length == 2
+		      				feature[1] = coors[0]
+		      				feature[2] = coors[1]
+		      			elsif /[^\d]/ =~ to
+		      				to_delete << i 
+		      			else
+		      				feature[1] = to
+		      				feature[2] = to
+		      			end
+		      		end
+		      end
+		      to_delete.reverse_each{|i| table.delete_at(i)}
+		      #####
+
+		      hash = {}
+		      table.each do |feature|
+		        hash[feature[0]] = [] unless hash[feature[0]]
+		        hash[feature[0]] << {
+		          # Removing '<', '>' or '?' in FROM/TO endopoint.
+		          'From' => feature[1].sub(/\D/, '').to_i,  
+		          'To'   => feature[2].sub(/\D/, '').to_i, 
+		          'Description' => feature[3], 
+		          'FTId' => feature[4].to_s.sub(/\/FTId=/, '').sub(/\.$/, ''),
+		          'diff' => [],
+		          'original' => feature
+		        }
+
+		        case feature[0]
+		        when 'VARSPLIC', 'VARIANT', 'VAR_SEQ', 'CONFLICT'
+		          case hash[feature[0]].last['Description']
+		          when /(\w[\w ]*\w*) - ?> (\w[\w ]*\w*)/
+		            original_res = $1
+		            changed_res = $2
+		            original_res = original_res.gsub(/ /,'').strip
+		            chenged_res = changed_res.gsub(/ /,'').strip
+		          when /Missing/i
+		            original_res = seq.subseq(hash[feature[0]].last['From'],
+		                                      hash[feature[0]].last['To'])
+		            changed_res = ''
+		          end
+		          hash[feature[0]].last['diff'] = [original_res, chenged_res]
+		        end
+		      end
+		    rescue
+		      raise "Invalid FT Lines(#{$!}) in #{entry_id}:, \n'#{self.get('FT')}'\n"
+		    end
+
+		    @data['FT'] = hash
+		  end
+	end
+end

data/lib/full_lengther_next/blast_functions.rb

@@ -105,31 +105,31 @@ def set_thresold_evalue(hits)
 end
 
 def same_subject_hsp(hit, second_hit)
-	same = FALSE
+	same = false
 	if hit.acc == second_hit.acc
 		if hit.s_beg <= second_hit.s_beg && hit.s_end >= hit.s_end && (second_hit.s_beg - hit.s_end).abs > 1
-			same = TRUE
+			same = true
 		end
 	end
 	return same
 end
 
 def same_query_hsp(hit, second_hit)
-	same = FALSE
+	same = false
 	if hit.acc == second_hit.acc
 		if hit.q_beg <= second_hit.q_beg && hit.q_end >= hit.q_end && (second_hit.q_beg - hit.q_end).abs > 1
-			same = TRUE
+			same = true
 		end
 	end
 	return same		
 end
 
 def same_sense?(hit, second_hit)
-	same= FALSE
+	same= false
 	hit_sense = hit.q_frame <=> 0
 	second_hit_sense = second_hit.q_frame <=> 0
 	if hit_sense == second_hit_sense
-		same = TRUE
+		same = true
 	end
 	return same
 end
@@ -158,7 +158,7 @@ def clean_by_query_length_match(blast_result, min_len_nt)
 end
 
 
-def clean_overlapping_hsps(blast_result, keep_if_diff_sense = FALSE)
+def clean_overlapping_hsps(blast_result, keep_if_diff_sense = false)
 	blast_result.querys.each do |query|
 		if query.hits.length > 1
 			query.hits.each_with_index do |hit, j|
@@ -190,7 +190,7 @@ end
 #####################################################################
 
 def misassembled_detection(query)
-	miss=FALSE
+	miss=false
 	hits = cluster_hsps(query.hits)
 	misassembled_hits = []
 	hits.each do |hit|
@@ -202,7 +202,7 @@ def misassembled_detection(query)
 		end
 	end
 	if misassembled_hits.length*1.0/ hits.length > 0.5
-		miss = TRUE
+		miss = true
 	else #Remove missassembled hits to avoid broken analysis
 		query.hits.reverse_each do |hsp|
 			if misassembled_hits.include?(hsp.acc)
@@ -214,16 +214,16 @@ def misassembled_detection(query)
 end
 
 def multiple_hsps(query, num)
-	multiple = FALSE
+	multiple = false
 	hsps = query.hits.select{|h| h.acc == query.hits.first.acc}	
 	if hsps.length >= num
-		multiple = TRUE
+		multiple = true
 	end
 	return multiple
 end
 
 def overlapping_hsps_on_subject(query)
-	overlapping = FALSE
+	overlapping = false
 	current_hit = query.hits.first.acc
 	complete_hit = []
 	cleaned_hits = []
@@ -252,16 +252,16 @@ def clean_subject_overlapping_hsps(complete_hit, cleaned_hits)
 end
 
 def subject_overlapping_hsps(hit)
-	overlapping = FALSE
+	overlapping = false
 	hsp_table = hsps_relationship_subject(hit)
 	if !hsp_table.empty?
 		hit = clean_hsp_by_identity(hit, 55)
 		if hit.empty?
-			overlapping = TRUE
+			overlapping = true
 		else 
 			hsp_table = hsps_relationship_subject(hit)
 			if !hsp_table.empty?
-				overlapping = TRUE
+				overlapping = true
 			end	
 		end
 	end
@@ -286,10 +286,10 @@ def hsps_relationship_subject(hit)
 end
 
 def same_subject_hsp(hit, second_hit)
-	same = FALSE
+	same = false
 	if hit.acc == second_hit.acc
 		if hit.s_beg <= second_hit.s_beg && hit.s_end >= hit.s_end && (second_hit.s_beg - hit.s_end).abs > 1
-			same = TRUE
+			same = true
 		end
 	end
 	return same

data/lib/full_lengther_next/cdhit.rb

@@ -59,8 +59,8 @@ class Cdhit
 			if master_seq.db != 'sp'
 				sp_seq=get_sp(cluster)
 				if !sp_seq.nil?
-					cluster.map{|seq| seq.master=FALSE}
-					sp_seq.master=TRUE
+					cluster.map{|seq| seq.master=false}
+					sp_seq.master= true
 				end			
 			end
 		}
@@ -109,7 +109,7 @@ class Cdhit
 	
 
 	def cd_hit_clusters(clust_file)
-		require 'bio-cd-hit-report'
+		#require 'bio-cd-hit-report'
 		report = Bio::CdHitReport.new(clust_file)
 		report.each_cluster do |cluster|
 			clust=[]
@@ -128,9 +128,9 @@ class Cdhit
 		member.gsub!('>','')
 		fields = member.split(',')
 		data = fields[1].split(' ',2)
-		master = FALSE
+		master = false
 		if data[1] == '*'
-			master = TRUE
+			master =  true
 		end			
 		return data[0],master
 	end

data/lib/full_lengther_next/chimeric_seqs.rb

@@ -110,8 +110,8 @@ module ChimericSeqs
 		seq_bak.clean_warnings
 		seq_bak.seq_name += "_split_#{hit_position}"
 		seq_bak.clean_orfs
-		seq_bak.save_fasta = TRUE
-		seq_bak.ignore = FALSE
+		seq_bak.save_fasta = true
+		seq_bak.ignore = false
 
 		# Cut sequence and move hit/hsps limits
 		#----------------------------------------
@@ -244,10 +244,10 @@ module ChimericSeqs
 	end
 
 	def hit_is_in?(h_beg, h_end, hit)
-		is=FALSE
+		is=false
 				# CONTIENE					#OVERLAP
 		if h_beg <= hit[BEG] && h_end > hit[BEG] || hit[BEG] <= h_beg && hit[STOP] > h_beg
-			is=TRUE
+			is=true
 		end
 		return is
 	end
@@ -324,7 +324,7 @@ module ChimericSeqs
 		cmd='clustalo -i -  -o /dev/null --percent-id --full --distmat-out=/dev/stdout --force'
 		clustal_matrix = nil
 		IO.popen(cmd,'w+') {|clustal|
-			clustal.sync = TRUE
+			clustal.sync = true
 			clustal.write(seq_fasta)
 			clustal.close_write
 			clustal_matrix = clustal.readlines

data/lib/full_lengther_next/common_functions.rb

@@ -101,7 +101,7 @@ module CommonFunctions
 		hit.q_frame = -hit.q_frame
 		hit.q_end = query_fasta.length - 1 - hit.q_end 	
 		hit.q_beg = query_fasta.length - 1 - hit.q_beg
-		hit.reversed = TRUE
+		hit.reversed = true
 		query_fasta = query_fasta.complementary_dna # ESTO REALMENTE HACE LA REVERSO COMPLEMENTARIA.
 		if hit.class.to_s == 'ExoBlastHit'
 			hit.q_frameshift.map!{|position, num_nts|

data/lib/full_lengther_next/exonerate_result.rb

@@ -39,7 +39,7 @@ end
 class ExonerateResult
 
   # Parser initialization
-  def initialize(input, seqs= nil, query_seqs = nil, all = TRUE)
+  def initialize(input, seqs= nil, query_seqs = nil, all = true)
     @querys = []
     @seqs = seqs #unigenes
     @prot_seqs = query_seqs#prot
@@ -106,8 +106,8 @@ class ExonerateResult
    
    #this method only works fine with --model protein2dna parameter of exonerate
  	def hiting(features, tags, query) #Convierte las coordenadas relativas del exonerate a absolutas tipo blast, definiendo solo los hits		
-		do_align = FALSE
-		do_align = TRUE if !@prot_seqs.nil? && !@seqs.nil?
+		do_align = false
+		do_align = true if !@prot_seqs.nil? && !@seqs.nil?
 		start_target = features['target_start_align']#Unigen
 		start_query = features['query_start_align'] #proteina
 		ends_target = features['target_end_align']
@@ -143,7 +143,7 @@ class ExonerateResult
 				target_alignment << target_seq[counter_target, tag[TARGET]].translate
 			end
 			if tag[OPERATION] == 'F'
-				if tag[TARGET] > 0 && tag[TARGET] < 3 #TRUE FRAMESHIFT
+				if tag[TARGET] > 0 && tag[TARGET] < 3 #true FRAMESHIFT
 					gap_shift += 1
 					if tags[n_operation+1][OPERATION] != 'G' #there are frameshift that not insert a gap, we do it
 						query_alignment <<  '-' if do_align
@@ -203,7 +203,7 @@ class ExonerateResult
 	def define_hit_parameters(hit, features, tags)
 		hit.gaps = 0
 		tags.map{|aln| hit.gaps += 1 if aln[0] == 'G'}
-		hit.reversed = FALSE
+		hit.reversed = false
 		hit.align_len =(features['query_end_align'] - features['query_start_align']).abs+1 
 		hit.mismatches=0
 		hit.e_val=0

data/lib/full_lengther_next/fl_analysis.rb

@@ -171,9 +171,9 @@ module FlAnalysis
 		end
 		
 		if atg_status == 'putative' || end_status == 'putative'
-			status = FALSE # Putative
+			status = false # Putative
 		else
-			status = TRUE # Sure
+			status = true # Sure
 		end
 
 		return type, status
@@ -187,7 +187,7 @@ module FlAnalysis
 			$global_warnings << ['SeqShorter', final_prot.length, final_hit.s_len]
 			if final_prot.length + 100 < final_hit.s_len || final_prot.length*2 < final_hit.s_len				
 				if type == COMPLETE
-					status = FALSE
+					status = false
 					$global_warnings << 'VeryShorter'
 				end
 			end
@@ -209,7 +209,7 @@ module FlAnalysis
 			$global_warnings = [] # Clean all warnings for current sequence
 			seq.seq_nt = mark_nt_seqs(final_hit, query_fasta)
 			if type == COMPLETE
-				seq.ignore = TRUE
+				seq.ignore = true
 			end
 		end
 		if  $verbose > 2
@@ -265,8 +265,8 @@ module FlAnalysis
 
 ## VERBOSE METHODS
 	def show_nts
-		show = FALSE	
-		show = TRUE if $verbose && $verbose > 3
+		show = false	
+		show = true if $verbose && $verbose > 3
 		return show
 	end
 

data/lib/full_lengther_next/fln_stats.rb

@@ -74,7 +74,7 @@ module FlnStats
 			if !$1.nil?
 				organism = $1
 			else
-				name =~ /(\w+ \w+) \(([\w ]+)\)/
+				name =~ /(\w+ \w+) \(([\w \/]+)\)/
 				if !$1.nil?
 					organism = $1  
 				end
@@ -610,4 +610,4 @@ module FlnStats
 		html = 	'<div style="font-size:25px; margin: 10"><b>'+title+'</b></div>'
 		return html
 	end
-end
+end

data/lib/full_lengther_next/handle_db.rb

@@ -35,7 +35,7 @@ end
 def do_makeblastdb(seqs, output, dbtype)
 	cmd="makeblastdb -in - -out #{output} -title #{File.basename(output)} -dbtype #{dbtype} -parse_seqids"
 	IO.popen(cmd,'w+') {|makedb|
-		makedb.sync = TRUE
+		makedb.sync = true
 		makedb.write(seqs)
 		makedb.close_write
 		puts makedb.readlines

data/lib/full_lengther_next/my_worker.rb

@@ -193,7 +193,7 @@ class MyWorker < ScbiMapreduce::Worker
 
 
 	# ejecuta blast utilizando los parametros fichero de entrada, base de datos, tipo de blast y evalue
-	def run_blast(input, database, blast_type, evalue, additional_blast_options, do_exonerate, filter = TRUE)
+	def run_blast(input, database, blast_type, evalue, additional_blast_options, do_exonerate, filter = true)
 		if !input.empty? && !input.nil?
 			$WORKER_LOG.info "DB: #{File.basename(database)} #{input.length}"
 			blast = BatchBlast.new("-db #{database}", blast_type, "-evalue #{evalue} #{additional_blast_options}")
@@ -202,7 +202,7 @@ class MyWorker < ScbiMapreduce::Worker
 			if @options[:hdd] #Write/parse blast on Disk
 				file_name = file_path+'.blast' #Each blast is identified with database_name and first sequence's name on chunk
 				if !File.exists?(file_name)
-					blast_result = blast.do_blast_seqs(input, :table, TRUE, file_name)
+					blast_result = blast.do_blast_seqs(input, :table, true, file_name)
 				else
 					blast = nil
 					blast_result=BlastTableResult.new(file_name)
@@ -223,8 +223,8 @@ class MyWorker < ScbiMapreduce::Worker
 	end
 	
 	def rescue_sequence(e, seq, status)
-		seq.save_fasta = FALSE
-		seq.ignore = TRUE
+		seq.save_fasta = false
+		seq.ignore = true
 		seq.type = FAILED
 		puts 	'-- '+seq.seq_name+' FAILED ANALYSIS -- '+status,
 			e.message,
@@ -232,7 +232,7 @@ class MyWorker < ScbiMapreduce::Worker
 	end
 
 	def  check_ncRNA(check_seqs, ncrna_path, blast_type, evalue)
-		my_blast = run_blast(check_seqs, ncrna_path, blast_type, evalue, '', FALSE, nil)	
+		my_blast = run_blast(check_seqs, ncrna_path, blast_type, evalue, '', false, nil)	
 		if !my_blast.nil?
 			check_seqs.each_with_index do |seq,i|
 				find_nc_rna(seq, my_blast.querys[i])
@@ -280,7 +280,7 @@ class MyWorker < ScbiMapreduce::Worker
 
 		if seq.type == FAILED
 			seq.type = UNKNOWN
-			seq.ignore = FALSE
+			seq.ignore = false
 		else
 			best_option.warnings(warning) if !warning.nil?
 		end

data/lib/full_lengther_next/my_worker_EST.rb

@@ -28,7 +28,7 @@ class MyWorkerEst < MyWorker
 	#####################################################################################
 	
 	def blastEST(array_seqs)
-		blast = run_blast(array_seqs, @blast_path, 'blastn', 1e-6, nil, FALSE)
+		blast = run_blast(array_seqs, @blast_path, 'blastn', 1e-6, nil, false)
 		if blast.nil?
 			$LOG.info 'BLAST FAILED'
 			Process.exit(-1)

data/lib/full_lengther_next/my_worker_manager_fln.rb

@@ -444,7 +444,7 @@ class MyWorkerManagerFln < ScbiMapreduce::WorkManager
 		@@stats_hash['coding'] += 1
 		coding = select_orf(coding)
 		if coding[1] == 'complete'
-			seq.status = TRUE 
+			seq.status = true 
 			@@stats_hash['coding_sure'] += 1
 		else
 			@@stats_hash['coding_putative'] += 1

data/lib/full_lengther_next/sequence.rb

@@ -16,7 +16,7 @@ class Sequence
 		@seq_aa = nil # Protein sequence generated over unigen
 		@db =nil
 		@type = UNKNOWN # See types.rb
-		@status = FALSE # TRUE => Sure, FALSE => Putative
+		@status = false # true => Sure, false => Putative
 		@id = nil #Prot or EST id, can be several => array
 		@warnings = []
 		@annotations=[]
@@ -27,9 +27,9 @@ class Sequence
 		@fpkm = []
 		@coverage_analysis = []
 		
-		@area_without_annotation=FALSE
-		@save_fasta=TRUE
-		@ignore=FALSE 
+		@area_without_annotation=false
+		@save_fasta=true
+		@ignore = false 
 		@hit=nil
 		@t_code=0
 	end
@@ -86,7 +86,7 @@ class Sequence
 
 	def reset_classification
 		@type = UNKNOWN
-		@status = FALSE
+		@status = false
 	end
 
 	def clean_warnings
@@ -150,7 +150,7 @@ class Sequence
 	def test_code(test_code)
 		@t_code = test_code
 		if @t_code >= 0.95
-			@status = TRUE
+			@status = true
 		end
 	end
 
@@ -470,7 +470,7 @@ class Sequence
 		upstream_annotation_space = hit.q_beg 
 		downstream_annotation_space = @fasta_length - hit.q_end
 		if upstream_annotation_space >= 150 || downstream_annotation_space >= 150
-			@area_without_annotation = TRUE
+			@area_without_annotation = true
 		end
 		return @area_without_annotation
 	end
@@ -490,8 +490,8 @@ class Sequence
 	end
 
 	def unmapped?
-		res = FALSE
-		res = TRUE if !@coverage_analysis.empty? && @coverage_analysis[3] == 0 #3 => percentage of sequence covered by reads 
+		res = false
+		res = true if !@coverage_analysis.empty? && @coverage_analysis[3] == 0 #3 => percentage of sequence covered by reads 
 		return res
 	end
 end

data/lib/full_lengther_next/une_los_hit.rb

@@ -165,7 +165,7 @@ class UneLosHit
 				#if frame_ori < 0 && h.q_frame > 0 || frame_ori > 0 && h.q_frame < 0
 					if h.q_frame < 0 # si la secuencia esta al reves le damos la vuelta
 						query_fasta = reverse_seq(query_fasta_ori, h)
-						h.reversed = TRUE
+						h.reversed = true
 					end
 					misma_id << h
 				#end
@@ -176,17 +176,17 @@ class UneLosHit
 	end
 
 	def overlapping_hits?(hit)
-		overlap = FALSE
+		overlap = false
 		if @final_hit.q_end >= hit.q_beg && @final_hit.q_end < hit.q_end && @final_hit.q_end < hit.q_end
-			overlap = TRUE
+			overlap = true
 		end
 		return overlap
 	end
 
 	def separated_hits?(hit)
-		separated=FALSE
+		separated=false
 		if @final_hit.q_end < hit.q_beg && hit.q_end > @final_hit.q_end
-			separated = TRUE
+			separated = true
 		end
 		return separated
 	end

data/lib/full_lengther_next/version.rb

@@ -1,3 +1,3 @@
 module FullLengtherNext
-  VERSION = '0.9.9'
+  VERSION = '1.0.2'
 end

metadata

@@ -1,16 +1,16 @@
 --- !ruby/object:Gem::Specification
 name: full_lengther_next
 version: !ruby/object:Gem::Version
-  version: 0.9.9
+  version: 1.0.2
 platform: ruby
 authors:
 - Pedro Seoane
 - Noe Fernandez
 - Dario Guerrero
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2018-03-12 00:00:00.000000000 Z
+date: 2022-09-05 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: xml-simple
@@ -83,7 +83,7 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
-  name: bio-cd-hit-report
+  name: bio
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
@@ -189,6 +189,7 @@ files:
 - full_lengther_next.gemspec
 - lib/full_lengther_next.rb
 - lib/full_lengther_next/artifacts.rb
+- lib/full_lengther_next/bio_patch.rb
 - lib/full_lengther_next/blast_functions.rb
 - lib/full_lengther_next/cdhit.rb
 - lib/full_lengther_next/chimeric_seqs.rb
@@ -220,7 +221,7 @@ homepage: https://github.com/seoanezonjic
 licenses:
 - MIT
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -235,9 +236,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.4.8
-signing_key: 
+rubygems_version: 3.3.7
+signing_key:
 specification_version: 4
 summary: Tool to annotate transcriptomes and it is able to stablish the integrity
   of each transcript. Also, FLN can detect novel genes on a target organism.