full_lengther_next 0.5.7 → 0.6.0

data/Rakefile

@@ -22,13 +22,11 @@ $hoe = Hoe.spec 'full_lengther_next' do
   self.extra_deps << ['xml-simple','>=1.0.12']
   self.extra_deps << ['scbi_blast','>=0.0.32']
   self.extra_deps << ['scbi_mapreduce','>=0.0.29']
-  self.extra_deps << ['scbi_fasta','>=0.1.7']
+  self.extra_deps << ['scbi_zcat']
   self.extra_deps << ['bio-cd-hit-report', '>= 0.1.0  ']
   self.extra_deps << ['bio', '>= 1.4.3']
-  # self.extra_deps << ['scbi_fastq','>=0.0.13']
   self.extra_deps << ['scbi_plot','>=0.0.6']
-  # self.extra_deps << ['scbi_math','>=0.0.1']
-
+  
 end
 
 require 'newgem/tasks'

data/bin/download_fln_dbs.rb

@@ -10,7 +10,7 @@ $: << File.expand_path(File.join(ROOT_PATH, "../lib/full_lengther_next/classes/"
 require 'bio'
 require 'net/ftp'
 require 'open-uri'
-require 'scbi_fasta'
+require 'scbi_zcat'
 require 'optparse'
 require 'cdhit'
 require 'handle_db'
@@ -20,52 +20,64 @@ require 'handle_db'
 #############################################################################################
 def download_ncrna(formatted_db_path, no_download)
 
-	ncrna_zip = File.join(formatted_db_path, 'ncrna.zip')
-	ncrna_fasta = File.join(formatted_db_path, 'ncrna.fasta')
+	ncrna_zip = File.join(formatted_db_path, 'ncrna.gz')
 	db_path = File.join(formatted_db_path, 'nc_rna_db')
-	source_file = File.join(db_path, ncrna_fasta)
-
-	
+	db_files = File.join(db_path, 'ncrna')
+	fasta = File.join(db_path , 'filtered.fasta')
 	if !no_download 
 		puts "Downloading ncRNA database"
 		open(ncrna_zip, 'wb') do |my_file|
-		 	my_file.print open('http://www.ncrna.org/frnadb/files/ncrna.zip').read
+		 	my_file.print open('ftp://ftp.ebi.ac.uk/pub/databases/RNAcentral/current_release/sequences/rnacentral_active.fasta.gz').read
+		 	#my_file.print open('http://www.ncrna.org/frnadb/files/ncrna.zip').read
 		end
 		puts "\nncRNA database downloaded"
-		system("unzip", ncrna_zip, "-d", ncrna_fasta)
-		system("rm", ncrna_zip)
 	end
 	
-	if  File.exists?(ncrna_fasta)
+	if  File.exists?(ncrna_zip)
 		Dir.mkdir(db_path) if !File.exists?(db_path)
-		db_files = File.join(db_path, 'ncrna')
-		filtered_fasta = filtering_ncbi_seqs(ncrna_fasta, 40)
-		#system("LANG=C sed 's/[^A-Za-z0-9\.> -\|]/_/g' #{ncrna_fasta}_filtered > #{ncrna_fasta}_cln")
+		black_list = [' 16S ', 'rRNA', 'ribosomal', 'tRNA', 'rrn'] #rrn = ribosonal rna
+		filtered_fasta = filtering_ncbi_seqs(ncrna_zip, 40, black_list)
 		puts "\nncRNA database decompressed and cleaned"
-		do_makeblastdb(filtered_fasta, db_files, 'nucl')
-		system("rm #{ncrna_fasta}")
+		#do_makeblastdb(filtered_fasta, db_files, 'nucl')
+		output_file = File.open(fasta, 'w')
+		output_file.puts filtered_fasta
+		output_file.close
+		system("cd-hit -i #{fasta} -o /dev/stderr -c 0.95 -n 11 -M 0 2>&1 >/dev/null | makeblastdb -in - -out #{db_files} -title #{File.basename(db_files)} -dbtype 'nucl' -parse_seqids")
 		puts "\nncRNA database completed"
 	end
 end
 
-def filtering_ncbi_seqs(fasta_file, max_length)
-    fasta = FastaQualFile.new(fasta_file)
+def filtering_ncbi_seqs(fasta_file, max_length, black_list)
+	fasta = ScbiZcatFile.new(fasta_file)
     filtered_fasta = ''
-    fasta.each do |name, seq, comments|
-    	name ="#{name} #{comments}"
-        if seq.length >= max_length
-            fields = name.split('|')
-            if fields[1] == '' || name.include?('||') 
-                new_name = name
-            else #Cut huge description
-                new_name = fields[0]+'|'
-                ids = fields[1].split(',')
-                new_name << "#{ids.first}\|#{fields[2]}"
-            end
-            filtered_fasta << ">#{new_name}\n#{seq}\n"
+	seq_name = nil
+	seq = ''
+	while !fasta.eof
+	        line = fasta.readline.chomp
+	        if line[0] == '>'
+	                if !seq_name.nil?
+	                    filtered_fasta << "#{seq_name}\n#{seq}\n" if seq.length >= max_length && !compare_list(seq_name, black_list)
+	                end
+	                seq_name = line
+	                seq = ''
+	        else
+	                seq << line
+	        end
+	end
+    filtered_fasta << "#{seq_name}\n#{seq}\n" if seq.length >= max_length && !compare_list(seq_name, black_list)
+
+    return filtered_fasta
+end
+
+def compare_list(string, list)
+    res = FALSE
+    list.each do |word|
+        if string.include?(word)
+            res = TRUE
+            break
         end
     end
-    return filtered_fasta
+    return res
 end
 
 def conecta_uniprot(my_array, formatted_db_path)
@@ -312,7 +324,7 @@ optparse = OptionParser.new do |opts|
   end
 
   options[:all] = FALSE
-  opts.on( '-a', '--all_sequences', 'Generate databaeses with all sequences') do 
+  opts.on( '-a', '--all_sequences', 'Generate databases with all sequences') do 
 		options[:all] = TRUE
   end
 
@@ -354,7 +366,6 @@ else # otherwise use ROOTPATH + DB
   Dir.mkdir(formatted_db_path)
 end
 
-puts formatted_db_path
 
 ENV['BLASTDB'] = formatted_db_path
 puts "Databases will be downloaded at: #{ENV['BLASTDB']}"

data/bin/full_lengther_next

@@ -63,9 +63,9 @@ optparse = OptionParser.new do |opts|
 		options[:ident] = ident.to_f 
 	end
 
-	options[:high_clustering] = TRUE
-	opts.on( '-k', '--high_clustering', 'Only for representative transcriptome. Add a clustering step using pfam ids. Default true' ) do
-		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
 	end
 
 	options[:subject_coverage] = 0.25

data/bin/make_user_db.rb

@@ -63,6 +63,11 @@ optparse = OptionParser.new do |opts|
 		options[:local] = TRUE
   end
 
+  options[:user_fasta] = nil
+  opts.on( '-f', '--user_fasta FILE', 'Use a cutom fasta file to build the user database') do |file|
+		options[:user_fasta] = file
+  end
+
   options[:cdhit] = 0
   opts.on( '-c', '--cdhit FLOAT', 'Compact databases with cdhit. 0 for deactivate, >0 - 1 to set percentage of identity. Default: 0') do |cdhit|
 		options[:cdhit] = cdhit.to_f
@@ -85,10 +90,14 @@ optparse.parse!
 ########################################################
 ##  MAIN
 ########################################################
-
-if options[:taxon].nil? || options[:uniprot_div].nil?
-	puts 'Taxon or uniprot division was not specified'
-  	Process.exit(-1)
+if options[:user_fasta].nil?
+	if options[:taxon].nil? || options[:uniprot_div].nil?
+		puts 'Taxon or uniprot division was not specified'
+	  	Process.exit(-1)
+	end
+elsif !File.exists?(options[:user_fasta]) || options[:taxon].nil?
+	puts 'User fasta file not exists or taxon was not specified'
+	Process.exit(-1)
 end
 
 if ENV['BLASTDB'] && File.exists?(ENV['BLASTDB'])
@@ -102,15 +111,21 @@ if !options[:local]
 else
 	user_db_folder = File.join(Dir.pwd, options[:taxon])
 end
-output_file_path = File.join(user_db_folder, options[:taxon]+".fasta")
+
 user_db_folder.gsub!(' ', '_')
-output_file_path.gsub!(' ', '_')
 Dir.mkdir(user_db_folder) if !File.exists?(user_db_folder)
+output_file_path = File.join(user_db_folder, options[:taxon]+".fasta")
+output_file_path.gsub!(' ', '_')
 
-isoform_hash = load_isoform_hash(File.join(formatted_db_path, 'uniprot_sprot_varsplic.fasta'))
-seqs = get_seqs(File.join(formatted_db_path, 'sp_' + options[:uniprot_div],"sp_#{options[:uniprot_div]}.index"), options[:taxon], isoform_hash)
-isoform_hash = nil
-seqs << get_seqs(File.join(formatted_db_path, 'tr_' + options[:uniprot_div],"tr_#{options[:uniprot_div]}.index"), options[:taxon], isoform_hash)
+seqs = ''
+if options[:user_fasta].nil?
+	isoform_hash = load_isoform_hash(File.join(formatted_db_path, 'uniprot_sprot_varsplic.fasta'))
+	seqs = get_seqs(File.join(formatted_db_path, 'sp_' + options[:uniprot_div],"sp_#{options[:uniprot_div]}.index"), options[:taxon], isoform_hash)
+	isoform_hash = nil
+	seqs << get_seqs(File.join(formatted_db_path, 'tr_' + options[:uniprot_div],"tr_#{options[:uniprot_div]}.index"), options[:taxon], isoform_hash)
+else
+	seqs = File.open(options[:user_fasta]).read
+end
 
 if options[:cdhit] > 0
 	output_file = File.open(output_file_path, 'w')

data/lib/full_lengther_next.rb

@@ -7,7 +7,7 @@ $: << File.expand_path(File.join(File.dirname(__FILE__), 'full_lengther_next', '
 
 
 module FullLengtherNext
-  VERSION = '0.5.7'
+  VERSION = '0.6.0'
   
   FULL_LENGHTER_VERSION = VERSION
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: full_lengther_next
 version: !ruby/object:Gem::Version
-  version: 0.5.7
+  version: 0.6.0
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-02-17 00:00:00.000000000 Z
+date: 2016-04-14 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: xml-simple
@@ -60,13 +60,13 @@ dependencies:
       - !ruby/object:Gem::Version
         version: 0.0.29
 - !ruby/object:Gem::Dependency
-  name: scbi_fasta
+  name: scbi_zcat
   requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
-        version: 0.1.7
+        version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
@@ -74,7 +74,7 @@ dependencies:
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
-        version: 0.1.7
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: bio-cd-hit-report
   requirement: !ruby/object:Gem::Requirement