public inbox for gentoo-commits@lists.gentoo.org
 help / color / mirror / Atom feed
* [gentoo-commits] proj/sci:master commit in: sci-biology/full_lengther_next/files/, sci-biology/full_lengther_next/
@ 2016-04-26 12:08 Martin Mokrejs
  0 siblings, 0 replies; only message in thread
From: Martin Mokrejs @ 2016-04-26 12:08 UTC (permalink / raw
  To: gentoo-commits

commit:     85fe7624385b5d424a1d250106a55c4aad74217f
Author:     Martin Mokrejš <mmokrejs <AT> fold <DOT> natur <DOT> cuni <DOT> cz>
AuthorDate: Tue Apr 26 12:07:50 2016 +0000
Commit:     Martin Mokrejs <mmokrejs <AT> fold <DOT> natur <DOT> cuni <DOT> cz>
CommitDate: Tue Apr 26 12:07:50 2016 +0000
URL:        https://gitweb.gentoo.org/proj/sci.git/commit/?id=85fe7624

sci-biology/full_lengther_next: version bump

Package-Manager: portage-2.2.28

 .../full_lengther_next/files/download_fln_dbs.rb   | 260 ---------------------
 ....5.7.ebuild => full_lengther_next-0.6.0.ebuild} |   7 +-
 2 files changed, 1 insertion(+), 266 deletions(-)

diff --git a/sci-biology/full_lengther_next/files/download_fln_dbs.rb b/sci-biology/full_lengther_next/files/download_fln_dbs.rb
deleted file mode 100644
index 90eacbb..0000000
--- a/sci-biology/full_lengther_next/files/download_fln_dbs.rb
+++ /dev/null
@@ -1,260 +0,0 @@
-#!/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.
-
-require 'net/ftp'
-require 'open-uri'
-
-class FtpClient
-
-def initialize
-end
-
-def connect(server)
-	@server=server
-end
-
-def login
-
-end
-
-def chdir(dir)
-  @dir=dir
-end
-
-def getbinaryfile(file,output_file)
-	if !File.exists?(output_file) && !File.exists?(output_file.gsub('.gz',''))
-   		puts " - Downloading"
-   		cmd="wget #{@server}/#{@dir}/#{file} -O #{output_file}"
-   		system(cmd)
-    else
-    	puts "File #{output_file}, or #{output_file.gsub('.gz','')} already exists. Skip download"
-    end
-   
-end
-
-def close
-end
-
-end
-################################################### Functions
-
-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"))
-	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
-	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 conecta_uniprot(my_array, formatted_db_path)
-	
-	#$ftp = Net::FTP.new()
-	$ftp = FtpClient.new()
-	
-	if !File.exists?(formatted_db_path)
-		Dir.mkdir(formatted_db_path)
-	end
-	
-	$ftp.connect('ftp://ftp.uniprot.org')
-	
-	$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')
-	$ftp.chdir("/pub/databases/uniprot/current_release/knowledgebase/complete")
-	$ftp.getbinaryfile("uniprot_sprot_varsplic.fasta.gz", varsplic_out)
-	
-	puts "isoform files downloaded"
-	
-	$ftp.close
-	
-end
-
-def download_uniprot(uniprot_group, formatted_db_path)
-	
-	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")
-	puts "   from ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/taxonomic_divisions/uniprot_sprot_#{uniprot_group}.dat.gz"
-	puts "   from ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/taxonomic_divisions/uniprot_trembl_#{uniprot_group}.dat.gz"
-	$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
-			end
-		end
-	end
-	output_file.close
-end
-
-def load_isoform_hash(file)
-	
-	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"
-			else
-				isoform_hash[acc]+= "#{my_fasta}\n"
-			end
-			my_fasta = "#{$1}\n"
-			acc = $2
-		else
-			my_fasta += line
-		end
-	end
-	
-	return isoform_hash
-end
-
-################################################### MAIN
-
-ROOT_PATH=File.dirname(__FILE__)
-
-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"))
-end
-
-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 '+File.join(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)
-
-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")
-	
-end
-
-puts "download_fln_dbs.rb has finished"

diff --git a/sci-biology/full_lengther_next/full_lengther_next-0.5.7.ebuild b/sci-biology/full_lengther_next/full_lengther_next-0.6.0.ebuild
similarity index 82%
rename from sci-biology/full_lengther_next/full_lengther_next-0.5.7.ebuild
rename to sci-biology/full_lengther_next/full_lengther_next-0.6.0.ebuild
index 1f3476f..64d300a 100644
--- a/sci-biology/full_lengther_next/full_lengther_next-0.5.7.ebuild
+++ b/sci-biology/full_lengther_next/full_lengther_next-0.6.0.ebuild
@@ -1,4 +1,4 @@
-# Copyright 1999-2015 Gentoo Foundation
+# Copyright 1999-2016 Gentoo Foundation
 # Distributed under the terms of the GNU General Public License v2
 # $Id$
 
@@ -32,8 +32,3 @@ RDEPEND="${DEPEND}
 	>=sci-biology/scbi_plot-0.0.6
 	>=dev-ruby/xml-simple-1.0.12
 	>=dev-ruby/gnuplot-2.3.0"
-
-#src_prepare(){
-#	cp "${FILESDIR}"/download_fln_dbs.rb all/full_lengther_next-0.0.8/bin || die
-#	chmod a+rx all/full_lengther_next-0.0.8/bin/*.rb || die
-#}


^ permalink raw reply related	[flat|nested] only message in thread

only message in thread, other threads:[~2016-04-26 12:08 UTC | newest]

Thread overview: (only message) (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2016-04-26 12:08 [gentoo-commits] proj/sci:master commit in: sci-biology/full_lengther_next/files/, sci-biology/full_lengther_next/ Martin Mokrejs

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox