full_lengther_next 0.6.0 → 0.6.1

data/bin/download_fln_dbs.rb

@@ -23,7 +23,7 @@ def download_ncrna(formatted_db_path, no_download)
 	ncrna_zip = File.join(formatted_db_path, 'ncrna.gz')
 	db_path = File.join(formatted_db_path, 'nc_rna_db')
 	db_files = File.join(db_path, 'ncrna')
-	fasta = File.join(db_path , 'filtered.fasta')
+	fasta = File.join(db_path, 'filtered.fasta')
 	if !no_download 
 		puts "Downloading ncRNA database"
 		open(ncrna_zip, 'wb') do |my_file|
@@ -34,20 +34,23 @@ def download_ncrna(formatted_db_path, no_download)
 	end
 	
 	if  File.exists?(ncrna_zip)
+		puts "\nFiltering ncRNA database"
 		Dir.mkdir(db_path) if !File.exists?(db_path)
 		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"
+		filtered_fasta = filtering_seqs(ncrna_zip, 40, black_list)
 		#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 filtered"
+		puts "\nncRNA database removing redundance with cdhit and creating BlastDb"
+		cmd = "cd-hit-est -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"
+		system(cmd)
 		puts "\nncRNA database completed"
 	end
 end
 
-def filtering_ncbi_seqs(fasta_file, max_length, black_list)
+def filtering_seqs(fasta_file, max_length, black_list)
 	fasta = ScbiZcatFile.new(fasta_file)
     filtered_fasta = ''
 	seq_name = nil
@@ -288,13 +291,14 @@ end
 
 options = {}
 
-divs = %w{human fungi invertebrates mammals plants rodents vertebrates}
+divs = %w{fungi invertebrates mammals plants rodents vertebrates}
+all_divs = %w{human fungi invertebrates mammals plants rodents vertebrates}
 
 optparse = OptionParser.new do |opts|
   options[:uniprot_div] = divs
   opts.on( '-u', '--file String', 'Uniprot DBs to be downloaded. String structure: \'div_name1,div_name2..\'. Posible options: human, fungi, invertebrates, mammals, plants, rodents, vertebrates. Default: download all') do |uniprot_div|
 		temp_divs = uniprot_div.split(',')
-		check_valid_ids = temp_divs - divs
+		check_valid_ids = temp_divs - all_divs
 		if !check_valid_ids.empty?
 			puts 'This uniprot division not exists', check_valid_ids
 			process.exit
@@ -314,7 +318,7 @@ optparse = OptionParser.new do |opts|
   end
 
   options[:only_index] = FALSE
-  opts.on( '-i', '--only_index', 'Build annotation index only without blast DB') do 
+  opts.on( '-i', '--only_index', 'Build annotation index only without do blast DB') do 
 		options[:only_index] = TRUE
   end
 
@@ -333,7 +337,7 @@ 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
   end
@@ -374,8 +378,10 @@ puts "\nTo set the path for storing databases, execute next line in your termina
 download_ncrna(formatted_db_path, options[:no_download]) if !options[:no_ncrna]
 
 if !options[:no_download]
-	conecta_uniprot(options[:uniprot_div], formatted_db_path) 
-	system('gunzip '+formatted_db_path+'*.gz')
+	if !options[:no_uniprot]
+		conecta_uniprot(options[:uniprot_div], formatted_db_path) 
+		system('gunzip '+formatted_db_path+'*.gz')
+	end
 end
 
 if !options[:no_uniprot]

data/lib/full_lengther_next.rb

@@ -7,7 +7,7 @@ $: << File.expand_path(File.join(File.dirname(__FILE__), 'full_lengther_next', '
 
 
 module FullLengtherNext
-  VERSION = '0.6.0'
+  VERSION = '0.6.1'
   
   FULL_LENGHTER_VERSION = VERSION
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: full_lengther_next
 version: !ruby/object:Gem::Version
-  version: 0.6.0
+  version: 0.6.1
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-04-14 00:00:00.000000000 Z
+date: 2016-05-03 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: xml-simple