full_lengther_next 0.0.8 → 0.5.6

data/History.txt

@@ -1,6 +1,6 @@
-=== 0.0.8 2012-11-28
+=== 0.1.0 2013-09-12
 
-Protection against empty seqs when all seqs match against user_db
+Major rewrite of script
 
 === 0.0.7 2012-07-25
 

data/Manifest.txt

@@ -1,29 +1,44 @@
+Rakefile
+script
+script/generate
+script/destroy
+script/console
+test
+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
+lib/full_lengther_next/classes
+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
-script/console
-script/destroy
-script/generate
-test
-test/test_full_lengther_next.rb
-test/test_helper.rb
+lib/expresscanvas.zip

data/Rakefile

@@ -11,7 +11,7 @@ Hoe.plugin :newgem
 # Generate all the Rake tasks
 # Run 'rake -T' to see list of generated tasks (from gem root directory)
 $hoe = Hoe.spec 'full_lengther_next' do
-  self.developer 'Noe Fernandez & Dario Guerrero', 'noeisneo@gmail.com & dariogf@gmail.com'
+  self.developer 'Pedro Seoane & Noe Fernandez & Dario Guerrero ', 'seoanezonjic@hotmail.com & noeisneo@gmail.com & dariogf@gmail.com'
   self.post_install_message = 'PostInstall.txt' # TODO remove if post-install message not required
   self.rubyforge_name       = self.name # TODO this is default value
   # self.extra_deps         = [['activesupport','>= 2.0.2']]
@@ -20,9 +20,11 @@ $hoe = Hoe.spec 'full_lengther_next' do
   # self.extra_deps << ['gnuplot','>=0']
   # self.extra_deps << ['term-ansicolor','>=1.0.5']
   self.extra_deps << ['xml-simple','>=1.0.12']
-  self.extra_deps << ['scbi_blast','>=0.0.37']
+  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 << ['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']

data/bin/download_fln_dbs.rb

@@ -1,66 +1,94 @@
 #!/usr/bin/env ruby
-
+ 
 # 15-2-2011 Noe Fernandez-Pozo
 # Script to download Full-LengtherNext databases.
 # Once in UniProtKB/Swiss-Prot, a protein entry is removed from UniProtKB/TrEMBL.
 
+ROOT_PATH=File.dirname(__FILE__)
+$: << File.expand_path(File.join(ROOT_PATH, "../lib/full_lengther_next/classes/"))
+
+require 'bio'
 require 'net/ftp'
 require 'open-uri'
+require 'scbi_fasta'
+require 'optparse'
+require 'cdhit'
+require 'handle_db'
+
+############################################################################################## 
+## METHODS
+#############################################################################################
+def download_ncrna(formatted_db_path, no_download)
 
-################################################### Functions
+	ncrna_zip = File.join(formatted_db_path, 'ncrna.zip')
+	ncrna_fasta = File.join(formatted_db_path, 'ncrna.fasta')
+	db_path = File.join(formatted_db_path, 'nc_rna_db')
+	source_file = File.join(db_path, ncrna_fasta)
 
-def download_ncrna(formatted_db_path)
 	
-	if !File.exists?(File.join(formatted_db_path, "nc_rna_db"))
-		Dir.mkdir(File.join(formatted_db_path, "nc_rna_db"))
+	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
+		end
+		puts "\nncRNA database downloaded"
+		system("unzip", ncrna_zip, "-d", ncrna_fasta)
+		system("rm", ncrna_zip)
 	end
 	
-	puts "Downloading ncRNA database"
-	open(File.join(formatted_db_path, "nc_rna_db/ncrna_fln_100.fasta.zip"), "wb") do |my_file|
-	  my_file.print open('http://www.scbi.uma.es/downloads/FLNDB/ncrna_fln_100.fasta.zip').read
+	if  File.exists?(ncrna_fasta)
+		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")
+		puts "\nncRNA database decompressed and cleaned"
+		do_makeblastdb(filtered_fasta, db_files, 'nucl')
+		system("rm #{ncrna_fasta}")
+		puts "\nncRNA database completed"
 	end
-	puts "\nncRNA database downloaded"
-	
-	ncrna_zip=File.join(formatted_db_path,'nc_rna_db','ncrna_fln_100.fasta.zip')
-	ncrna_out_dir=File.join(formatted_db_path,'nc_rna_db')
-	system("unzip", ncrna_zip, "-d", ncrna_out_dir)
-	system("rm", ncrna_zip)
-	
-	puts "\nncRNA database decompressed"
-	
-	ncrna_fasta=File.join(formatted_db_path,'nc_rna_db','ncrna_fln_100.fasta')
-	system("makeblastdb", "-in", ncrna_fasta, "-dbtype", "nucl", "-parse_seqids")
-	
-	puts "\nncRNA database completed"
+end
+
+def filtering_ncbi_seqs(fasta_file, max_length)
+    fasta = FastaQualFile.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"
+        end
+    end
+    return filtered_fasta
 end
 
 def conecta_uniprot(my_array, formatted_db_path)
 	
+	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()
-	
-	if !File.exists?(formatted_db_path)
-		Dir.mkdir(formatted_db_path)
-	end
-	
-	$ftp.connect('ftp.uniprot.org')
-	
+	$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)
 	end
-	
-	varsplic_out=File.join(formatted_db_path,'uniprot_sprot_varsplic.fasta.gz')
+
+	#archivo de variantes de splicing. POR QUE?
 	$ftp.chdir("/pub/databases/uniprot/current_release/knowledgebase/complete")
 	$ftp.getbinaryfile("uniprot_sprot_varsplic.fasta.gz", varsplic_out)
-	
-	puts "isoform files downloaded"
-	
 	$ftp.close
 	
+	puts "isoform files downloaded"
 end
 
 def download_uniprot(uniprot_group, formatted_db_path)
@@ -70,156 +98,280 @@ def download_uniprot(uniprot_group, formatted_db_path)
 	$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)
-	
+
 	puts "#{uniprot_group} files downloaded"
 	
 end
 
-def filter_incomplete_seqs(file_name, isoform_hash, formatted_db_path)
-	
-	puts "filtering sequences from #{file_name}"
-	
-	# UniProtKB fragments with FT NON_CONS and FT NON_TER features.
-	# 
-	#     * FT 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. Examples of NON_TER key feature lines:
-	#       FT NON_TER 1 1
-	#       FT NON_TER 29 29
-	#     * FT 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. Example of a NON_CONS key feature line:
-	#       FT NON_CONS 1683 1684
-	# 
-	# NON_CONS fragments are not indicated as non-consecutive in InterPro and being non-consecutive the match to methods may be incorrect if the method spans the 'break'.
-	
-	newseq=false
-	print_seq=true
-	id=''
-	description = ''
-	organism_name = ''
-	seq = ''
-	organelle = ''
-	
-	file_name =~ /uniprot_([a-z]+)_([a-z]+).dat/
-	db_name = $1
-	output_name = $2
-	db_name.sub!('sprot','sp')
-	db_name.sub!('trembl','tr')
-	
-	if !File.exists?(File.join(formatted_db_path, "#{db_name}_#{output_name}"))
-		Dir.mkdir(File.join(formatted_db_path, "#{db_name}_#{output_name}"))
-	end
-	
-	output_file = File.new(File.join(formatted_db_path, "#{db_name}_#{output_name}/#{db_name}_#{output_name}.fasta"), "w")
-	
-	File.open(file_name).each_line do |line|
-		if (newseq == false)
-			if (line =~ /^AC\s+(\w+);/)
-				id=$1
-				newseq = true
-				description = ''
-				organism_name = ''
-				seq = ''
-				print_seq = true
-				organelle = ''
-			end
-		else
-			if (line =~ /^DE\s+(.+)\;*/)
-				if (description == '')
-					description = $1
-					description.sub!(/RecName: Full=/,'sp=')
-					description.sub!(/SubName: Full=/,'tr=')
-				end
-				if (line =~ /Flags: Fragment/)
-					# puts "#{id} #{line}"
-					print_seq=false
-				end
-			elsif (line =~ /^OS\s+(.+)/)
-				organism_name = $1
-			elsif (line =~ /^OG\s+(.+)/)
-				organelle = $1
-			elsif (line =~ /^FT\s+NON_TER\s+/)
-				print_seq=false
-				# puts "#{id}   NON_TER"
-			elsif (line =~ /^FT\s+NON_CONS\s+(\d+)\s+/)
-				print_seq=false
-				# puts "#{id}   NON_CONS"
-			elsif (line =~ /^\s+([\w\s]+)/)
-				seq += $1
-			elsif (line =~ /^\/\//)
-				seq.gsub!(/\s*/,'')
-				if (seq !~ /^M/i)
-					print_seq=false
-				end
-				newseq = false
-				
-				if (print_seq)
-					output_file.puts ">#{id} #{description} #{organism_name} #{organelle}\n#{seq}"
-					if (!isoform_hash[id].nil?)
-						output_file.puts isoform_hash[id]
-					end
-				end
+
+
+def filter_and_makeDB(formatted_db_path, dbtype, db_group, isoform_hash, prefix, options)
+	file_name = prefix +'_' + db_group
+	puts 'Building ' + file_name
+	fasta = File.join(formatted_db_path,"#{file_name}","#{file_name}.fasta")
+	blastdb_input = fasta.gsub('.fasta', '') 
+	current_db_source = File.join(formatted_db_path, "uniprot_#{dbtype}_#{db_group}.dat")
+	if File.exists?(current_db_source)
+		seqs = filter_incomplete_seqs(current_db_source, isoform_hash, formatted_db_path, file_name, options)
+		if !options[:only_index]
+			if options[:cdhit] > 0
+				output_file = File.open(fasta, 'w')
+				output_file.puts seqs
+				output_file.close
+				system("cd-hit -i #{fasta} -o /dev/stderr -c #{options[:cdhit]} -M 0 -s 0.95 2>&1 >/dev/null| makeblastdb -in - -out #{blastdb_input} -title #{File.basename(blastdb_input)} -dbtype 'prot' -parse_seqids")
+			else
+				do_makeblastdb(seqs, blastdb_input, 'prot')
 			end
 		end
 	end
-	output_file.close
 end
 
-def load_isoform_hash(file)
+def complete?(uniprot_record)
+	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
+	end
+	return complete	
+end
+
+def fln_record(uniprot_record, seqs, index, isoform_hash)
+	index_record = []
+	# Primary data
+	accession_number = uniprot_record.accession
+	description_data = uniprot_record.description.split(';')
+	description = description_data.first
+	description.sub!(/RecName: Full=/,'sp=')
+	description.sub!(/SubName: Full=/,'tr=')
+	description.sub!(/{\S*}/,'')
+
+	organism = uniprot_record.os.first.values.reverse.join(' ')
+	organelle = uniprot_record.og.join(' ')
+	sequence = uniprot_record.seq.gsub('U','X')
+
+	# Secondary data
+	index_record << accession_number
+	index_record << description
+	taxonomy = uniprot_record.oc.join(';')
+	index_record << taxonomy
+	index_record << organism
+	index_record << sequence
+	if !organelle.empty?
+		index_record << organelle
+	else
+		index_record << '-'
+	end
+	go_data = uniprot_record.dr['GO']
+	if !go_data.nil?
+		index_record << go_data.map{|go| go[0]}.join(';') # GO ID
+		index_record << go_data.map{|go| go[1]}.join(';') # GO Description
+	else
+		index_record << '-'
+		index_record << '-'
+	end
+	kegg_data = uniprot_record.dr['KEGG']
+	if !kegg_data.nil?
+		index_record << kegg_data.map{|kegg| kegg[0]}.join(';')
+	else
+		index_record << '-'
+	end
+	interpro_data = uniprot_record.dr['InterPro']
+	if !interpro_data.nil?
+		index_record << interpro_data.map{|ip| ip[0]}.join(';') # interpro ID
+		index_record << interpro_data.map{|ip| ip[1]}.join(';') # ip Description
+	else
+		index_record << '-'
+		index_record << '-'
+	end
+
+	if !description_data[1].nil? && description_data[1].include?('EC=')
+		index_record << description_data[1].split(' ').first.gsub('=',':')
+	else
+		index_record << '-'
+	end
+
+	pfam_data = uniprot_record.dr['Pfam']
+	if !pfam_data.nil?
+		index_record << pfam_data.map!{|pf| pf[0]}.join(';') # pfam ID
+		index_record << pfam_data.map!{|pf| pf[1]}.join(';') # pfam description
+	else
+		index_record << '-'
+		index_record << '-'
+	end
+	
+	unipathway_data = uniprot_record.dr['UniPathway']
+	if !unipathway_data.nil?
+		index_record << unipathway_data.map!{|pf| pf[0]}.join(';') # unipathway ID
+	else
+		index_record << '-'
+	end
+
+	seqs << ">#{[accession_number, description, organism, organelle].join(' ')}\n#{sequence}\n"			
+	index.puts index_record.join("\t")
+	seqs << isoform_hash[accession_number]+"\n" if !isoform_hash.nil? && !isoform_hash[accession_number].nil?
+end
+
+def	ncbi_record(uniprot_record, seqs)
+	accession_number = uniprot_record.accession
+	id = uniprot_record.entry_id
+	organism = uniprot_record.os.first.values.reverse.join(' ')
+	sequence = uniprot_record.seq
+	description = uniprot_record.description.split(';').first
+	gene_name = nil
+	gn_field = uniprot_record.gn.first
+	gene_name = gn_field[:name] if !gn_field.nil?
+	prediction_field = uniprot_record.get('PE')
+	prediction_field =~ /PE\s+(\d+):/
+	prediction_status = $1
+	sequence_version_field = uniprot_record.dt['sequence']
+	sequence_version_field =~ /sequence version (\d+)./
+	sequence_version = $1
+	db = nil
+	if description.include?('RecName: Full=')
+		db = 'sp'
+		description.sub!(/RecName: Full=/,'')
+	elsif description.include?('SubName: Full=')
+		db = 'tr'
+		description.sub!(/SubName: Full=/,'')
+	end
+	taxonomy = uniprot_record.oc.join(';')
+
+	seqs << ">#{db}|#{accession_number}|#{id} #{description} OS=#{organism} GN=#{gene_name} PE=#{prediction_status} SV=#{sequence_version}\n#{sequence}\n"			
+end
+
+def filter_incomplete_seqs(file_name, isoform_hash, formatted_db_path, db_name, options)
 	
-	isoform_hash = {}
-	my_fasta = ''
-	acc = ''
-	File.open(file).each do |line|
-		line.chomp!
-		if (line =~ /(^>\w+\|(\w+)\-\d\|.+)/)
-			if (isoform_hash[acc].nil?)
-				isoform_hash[acc]= "#{my_fasta}\n"
+	puts "filtering sequences from #{file_name}"
+	
+	db_folder = File.join(formatted_db_path, db_name)	
+	Dir.mkdir(db_folder) if !File.exists?(db_folder)
+
+	main_name = File.join(db_folder, db_name)
+	index = File.open(main_name + '.index', 'w') if !options[:all]
+	seqs = ''
+	Bio::FlatFile.auto(file_name).each_entry {|uniprot_record|
+		if !options[:all] && !complete?(uniprot_record)
+			next
+		else #Get attributes of full length records
+			if options[:all]
+				ncbi_record(uniprot_record, seqs)
 			else
-				isoform_hash[acc]+= "#{my_fasta}\n"
+				fln_record(uniprot_record, seqs, index, isoform_hash)
 			end
-			my_fasta = "#{$1}\n"
-			acc = $2
-		else
-			my_fasta += line
 		end
-	end
-	
-	return isoform_hash
+	}
+
+	index.close if !options[:all]
+	return seqs
 end
 
-################################################### MAIN
 
-ROOT_PATH=File.dirname(__FILE__)
+
+##########################################################################################
+## OPTIONS
+##########################################################################################
+
+options = {}
+
+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
+		if !check_valid_ids.empty?
+			puts 'This uniprot division not exists', check_valid_ids
+			process.exit
+		else
+			options[:uniprot_div] = temp_divs
+		end         
+  end
+
+  options[:no_download] = FALSE
+  opts.on( '-d', '--no_download', 'Only parse downloaded files without download them again') do 
+		options[:no_download] = TRUE
+  end
+
+  options[:no_ncrna] = FALSE
+  opts.on( '-n', '--no_ncrna', 'No use ncrna sequences') do 
+		options[:no_ncrna] = TRUE
+  end
+
+  options[:only_index] = FALSE
+  opts.on( '-i', '--only_index', 'Build annotation index only without blast DB') do 
+		options[:only_index] = TRUE
+  end
+
+  options[:no_trembl] = FALSE
+  opts.on( '-t', '--no_trembl', 'No use trembl sequences') do 
+		options[:no_trembl] = TRUE
+  end
+
+  options[:all] = FALSE
+  opts.on( '-a', '--all_sequences', 'Generate databaeses with all sequences') do 
+		options[:all] = TRUE
+  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
+  end
+
+	options[:no_uniprot] = FALSE
+  opts.on( '-p', '--no_uniprot', 'No use uniprot sequences') do 
+		options[:no_uniprot] = TRUE
+  end
+
+
+  # Set a banner, displayed at the top of the help screen.
+  opts.banner = "Usage: #{File.basename(__FILE__)} [options]  \n\n"
+
+  # This displays the help screen
+  opts.on( '-h', '--help', 'Display this screen' ) do
+    puts opts
+    exit
+  end
+
+end # End opts
+
+# parse options and remove from ARGV
+optparse.parse!
+
+
+############################################################################################## 
+## MAIN
+##############################################################################################
+
 
 if ENV['BLASTDB'] && File.exists?(ENV['BLASTDB'])
   formatted_db_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
 
-ENV['BLASTDB']=formatted_db_path
+puts 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"
 
-my_array = ["human","fungi","invertebrates","mammals","plants","rodents","vertebrates"]
-# my_array = ["plants","human"] # used for a shoter test
-
-conecta_uniprot(my_array, formatted_db_path)
-system('gunzip '+formatted_db_path+'*.gz')
-
-isoform_hash = {}
-isoform_hash = load_isoform_hash(File.join(formatted_db_path, "uniprot_sprot_varsplic.fasta"))
+download_ncrna(formatted_db_path, options[:no_download]) if !options[:no_ncrna]
 
-download_ncrna(formatted_db_path)
-
-my_array.each do |db_group|
-
-	filter_incomplete_seqs(File.join(formatted_db_path, "uniprot_sprot_#{db_group}.dat"), isoform_hash, formatted_db_path)
-	filter_incomplete_seqs(File.join(formatted_db_path, "uniprot_trembl_#{db_group}.dat"), isoform_hash, formatted_db_path)
-	
-	sp_fasta=File.join(formatted_db_path,"sp_#{db_group}","sp_#{db_group}.fasta")
-	tr_fasta=File.join(formatted_db_path,"tr_#{db_group}","tr_#{db_group}.fasta")
-	system("makeblastdb -in #{sp_fasta} -dbtype 'prot' -parse_seqids")
-	system("makeblastdb -in #{tr_fasta} -dbtype 'prot' -parse_seqids")
-	
+if !options[:no_download]
+	conecta_uniprot(options[:uniprot_div], formatted_db_path) 
+	system('gunzip '+formatted_db_path+'*.gz')
 end
 
-puts "download_fln_dbs.rb has finished"
+if !options[:no_uniprot]
+	isoform_hash = load_isoform_hash(File.join(formatted_db_path, "uniprot_sprot_varsplic.fasta"))  #archivo de variantes de splicing. POR QUE?
+	options[:uniprot_div].each do |db_group|
+		filter_and_makeDB(formatted_db_path, 'sprot', db_group, isoform_hash, 'sp', options)
+		filter_and_makeDB(formatted_db_path, 'trembl', db_group, nil, 'tr', options) if !options[:no_trembl]
+	end
+end
+puts "download_fln_dbs.rb has finished"