full_lengther_next 0.6.1 → 0.6.2

data/bin/download_fln_dbs.rb

@@ -125,7 +125,7 @@ def filter_and_makeDB(formatted_db_path, dbtype, db_group, isoform_hash, prefix,
 	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")
+	current_db_source = File.join(formatted_db_path, "uniprot_#{dbtype}_#{db_group}.dat.gz")
 	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]
@@ -267,7 +267,8 @@ def filter_incomplete_seqs(file_name, isoform_hash, formatted_db_path, db_name,
 	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|
+	#Bio::FlatFile.auto(file_name).each_entry {|uniprot_record|
+	Bio::FlatFile.auto(IO.popen("gzip -dc #{file_name}")).each_entry {|uniprot_record|
 		if !options[:all] && !complete?(uniprot_record)
 			next
 		else #Get attributes of full length records
@@ -292,7 +293,7 @@ end
 options = {}
 
 divs = %w{fungi invertebrates mammals plants rodents vertebrates}
-all_divs = %w{human fungi invertebrates mammals plants rodents vertebrates}
+all_divs = %w{human fungi invertebrates mammals plants rodents vertebrates archaea viruses unclassified}
 
 optparse = OptionParser.new do |opts|
   options[:uniprot_div] = divs
@@ -380,12 +381,12 @@ download_ncrna(formatted_db_path, options[:no_download]) if !options[:no_ncrna]
 if !options[:no_download]
 	if !options[:no_uniprot]
 		conecta_uniprot(options[:uniprot_div], formatted_db_path) 
-		system('gunzip '+formatted_db_path+'*.gz')
+		#system('gunzip '+formatted_db_path+'*.gz')
 	end
 end
 
 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?
+	isoform_hash = load_isoform_hash(File.join(formatted_db_path, "uniprot_sprot_varsplic.fasta.gz"))  #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]

data/bin/make_user_db.rb

@@ -64,7 +64,7 @@ optparse = OptionParser.new do |opts|
   end
 
   options[:user_fasta] = nil
-  opts.on( '-f', '--user_fasta FILE', 'Use a cutom fasta file to build the user database') do |file|
+  opts.on( '-f', '--user_fasta FILE', 'Use a custom fasta file to build the user database') do |file|
 		options[:user_fasta] = file
   end
 
@@ -119,7 +119,7 @@ output_file_path.gsub!(' ', '_')
 
 seqs = ''
 if options[:user_fasta].nil?
-	isoform_hash = load_isoform_hash(File.join(formatted_db_path, 'uniprot_sprot_varsplic.fasta'))
+	isoform_hash = load_isoform_hash(File.join(formatted_db_path, 'uniprot_sprot_varsplic.fasta.gz'))
 	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)

data/lib/full_lengther_next.rb

@@ -7,7 +7,7 @@ $: << File.expand_path(File.join(File.dirname(__FILE__), 'full_lengther_next', '
 
 
 module FullLengtherNext
-  VERSION = '0.6.1'
+  VERSION = '0.6.2'
   
   FULL_LENGHTER_VERSION = VERSION
 end

data/lib/full_lengther_next/classes/handle_db.rb

@@ -1,23 +1,37 @@
-require 'scbi_fasta'
-
+require 'scbi_zcat'
 
 def load_isoform_hash(file)
 	isoform_hash = {}
 	if File.exists?(file)
-		fasta = FastaQualFile.new(file)
-		fasta.each do |name, seq, desc|
-			name =~ /(\w+\|(\w+)\-\d+\|)/
-			if isoform_hash[$2].nil?
-				isoform_hash[$2] = ">#{$1}#{desc}\n#{seq}"
-			else
-				isoform_hash[$2] += "\n>#{$1}#{desc}\n#{seq}"
-			end
+		fasta = ScbiZcatFile.new(file)
+	    filtered_fasta = ''
+		seq_name = nil
+		seq = ''
+		while !fasta.eof
+		        line = fasta.readline.chomp
+		        if line[0] == '>'		                
+						load_seq_in_hash(seq_name, seq, isoform_hash) if !seq_name.nil?
+		                seq_name = line
+		                seq = ''
+		        else
+		                seq << line
+		        end
 		end
-		fasta.close
+		load_seq_in_hash(seq_name, seq, isoform_hash)
 	end
 	return isoform_hash
 end
 
+def load_seq_in_hash(seq_name, seq, isoform_hash)
+	name, desc = seq_name.split(' ', 2) 
+	name =~ /(\w+\|(\w+)\-\d+\|)/
+	if isoform_hash[$2].nil?
+		isoform_hash[$2] = ">#{$1}#{desc}\n#{seq}"
+	else
+		isoform_hash[$2] += "\n>#{$1}#{desc}\n#{seq}"
+	end
+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|

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: full_lengther_next
 version: !ruby/object:Gem::Version
-  version: 0.6.1
+  version: 0.6.2
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-05-03 00:00:00.000000000 Z
+date: 2016-05-04 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: xml-simple