bio 0.7.0

data/sample/tdiary.rb

@@ -0,0 +1,158 @@
+#
+# tDiary : plugin/bio.rb
+#
+#   Copyright (C) 2003 KATAYAMA Toshiaki <k@bioruby.org>
+#                      Mitsuteru C. Nakao <n@bioruby.org>
+#                      Itoshi NIKAIDO  <itoshi@gsc.riken.go.jp>
+#                      Takeya KASUKAWA <kasukawa@gsc.riken.go.jp>
+#
+#  This library is free software; you can redistribute it and/or
+#  modify it under the terms of the GNU Lesser General Public
+#  License as published by the Free Software Foundation; either
+#  version 2 of the License, or (at your option) any later version.
+#
+#  This library is distributed in the hope that it will be useful,
+#  but WITHOUT ANY WARRANTY; without even the implied warranty of
+#  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+#  Lesser General Public License for more details.
+#
+#  You should have received a copy of the GNU Lesser General Public
+#  License along with this library; if not, write to the Free Software
+#  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307  USA
+#
+#  $Id: tdiary.rb,v 1.3 2003/03/17 04:24:47 k Exp $
+#
+
+=begin
+
+== What's this?
+
+This is a plugin for the ((<tDiary|URL:http://www.tdiary.org/>)) to create
+various links for biological resources from your diary.
+
+tDiary is an extensible web diary application written in Ruby.
+
+== How to install
+
+Just copy this file under the tDiary's plugin directory as bio.rb.
+
+== Usage
+
+--- pubmed(pmid, comment = nil)
+
+Create a link to NCBI Entrez reference database by using PubMed ID.
+See ((<URL:http://www.ncbi.nlm.nih.gov/entrez/query.fcgi>)) for more
+information.
+
+  * tDiary style
+     * <%= pubmed 12345 %>
+     * <%= pubmed 12345, 'hogehoge' %>
+  * RD style
+     * ((% pubmed 12345 %))
+     * ((% pubmed 12345, 'hogehoge' %))
+
+--- biofetch(db, entry_id)
+
+Create a link to the BioFetch detabase entry retrieval system.
+See ((<URL:http://biofetch.bioruby.org/>)) for more information.
+
+  * tDiary style
+    * <%= biofetch 'genbank', 'AA2CG' %>
+  * RD style
+    * ((% biofetch 'genbank', 'AA2CG' %))
+
+--- amigo(go_id, comment = nil)
+
+Create a link to the AmiGO GO term browser by using GO ID.
+See ((<URL:http://www.godatabase.org/cgi-bin/go.cgi>)) for more 
+information.
+
+  * tDiary style
+    * <%= amigo '0003673' %>
+    * <%= amigo '0003673', 'The root of GO' %>
+  * RD style
+    * ((% amigo 0003673 %))
+    * ((% amigo 0003673, 'The root of GO' %))
+
+--- fantom(id, comment = nil)
+
+Create a link to FANTOM database by using Clone ID.
+You can use RIKEN clone ID, Rearray ID, Seq ID and Accession Number.
+See ((<URL:http://fantom2.gsc.riken.go.jp/db/>)) for more information.
+
+  * tDiary style
+     * <%= fantom 12345 %>
+     * <%= fantom 12345, 'hogehoge' %>
+  * RD style
+    * ((% fantom 12345 %))
+    * ((% fantom 12345, 'hogehoge' %))
+
+--- rtps(id, comment = nil)
+
+Create a link to FANTOM RTPS database by using Clone ID. 
+You can use only RTPS ID.
+See ((<URL:http://fantom2.gsc.riken.go.jp/RTPS/>)) for more information.
+
+  * tDiary style
+     * <%= rtps 12345 %>
+     * <%= rtps 12345, 'hogehoge' %>
+  * RD style
+    * ((% rtps 12345 %))
+    * ((% rtps 12345, 'hogehoge' %))
+
+== References
+
+* Analysis of the mouse transcriptome based on functional annotation of
+  60,770 full-length cDNAs, The FANTOM Consortium and the RIKEN Genome
+  Exploration Research Group Phase I & II Team, Nature 420:563-573, 2002
+
+* Functional annotation of a full-length mouse cDNA collection,
+  The RIKEN Genome Exploration Research Group Phase II Team and 
+  the FANTOM Consortium, Nature 409:685-690, 2001
+
+=end
+
+def pubmed(pmid, comment = nil)
+  pmid = pmid.to_s.strip
+  url = "http://www.ncbi.nlm.nih.gov/entrez/query.fcgi"
+  url << "?cmd=Retrieve&db=PubMed&dopt=Abstract&list_uids=#{pmid}"
+  if comment
+    %Q[<a href="#{url}">#{comment.to_s.strip}</a>]
+  else
+    %Q[<a href="#{url}">PMID:#{pmid}</a>]
+  end
+end
+
+def biofetch(db, entry_id) 
+  url = "http://biofetch.bioruby.org/"
+  %Q[<a href="#{url}?db=#{db};id=#{entry_id};style=raw">#{db}:#{entry_id}</a>] 
+end
+
+def amigo(go_id = '0003673', comment = nil)
+  go_id = go_id.to_s.strip
+  url = "http://www.godatabase.org/cgi-bin/go.cgi?query=#{go_id};view=query;action=query;search_constraint=terms"
+  comment = "AmiGO:#{go_id}" unless comment
+  %Q[<a href="#{url}">#{comment}</a>]
+end
+
+def fantom(id, comment = nil)
+  id = id.to_s.strip
+  url = "http://fantom2.gsc.riken.go.jp/db/link/id.cgi"
+  url << "?id=#{id}"
+  if comment
+    %Q[<a href="#{url}">#{comment.to_s.strip}</a>]
+  else
+    %Q[<a href="#{url}">FANTOM DB:#{id}</a>]
+  end
+end
+
+def rtps(id, comment = nil)
+  id = id.to_s.strip
+  url = "http://fantom2.gsc.riken.go.jp/RTPS/link/id.cgi"
+  url << "?id=#{id}"
+  if comment
+    %Q[<a href="#{url}">#{comment.to_s.strip}</a>]
+  else
+    %Q[<a href="#{url}">FANTOM RTPS DB:#{id}</a>]
+  end
+end

data/sample/tfastx2tab.rb

@@ -0,0 +1,100 @@
+#!/usr/bin/env ruby
+#
+# tfastx2tab.rb - convert TFASTX (-m 6) output into tab delimited data for MySQL
+#
+#  Usage:
+#
+#    % tfastx2tab.rb TFASTX-output-file[s] > tfastx_results.tab
+#    % mysql < tfastx_results.sql  (use sample at the end of this file)
+#
+#  Format accepted:
+#
+#    % tfastx3[3][_t] -Q -H -m 6 query.f target.f ktup > TFASTX-output-file
+#
+#   Copyright (C) 2001 KATAYAMA Toshiaki <k@bioruby.org>
+#
+#  This program is free software; you can redistribute it and/or modify
+#  it under the terms of the GNU General Public License as published by
+#  the Free Software Foundation; either version 2 of the License, or
+#  (at your option) any later version.
+#
+#  This program is distributed in the hope that it will be useful,
+#  but WITHOUT ANY WARRANTY; without even the implied warranty of
+#  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+#  GNU General Public License for more details.
+#
+#  $Id: tfastx2tab.rb,v 0.1 2001/06/21 08:26:14 katayama Exp $
+#
+
+while gets
+
+  # query
+  if /^\S+: (\d+) aa$/
+    q_len = $1
+  end
+
+  # each hit
+  if /^>>([^>]\S+).*\((\d+) aa\)$/
+    target = $1
+    t_len = $2
+
+    # d = dummy variable
+    d, frame, d, initn, d, init1, d, opt, d, zscore, d, bits, d, evalue =
+      gets.split(/\s+/)
+    d, d, sw, ident, d, ugident, d, d, overlap, d, d, lap =
+      gets.split(/\s+/)
+
+    # query-hit pair
+    print "#{$FILENAME}\t#{q_len}\t#{target}\t#{t_len}"
+
+    # pick up values
+    ary = [
+      initn,
+      init1,
+      opt,
+      zscore,
+      bits,
+      evalue,
+      sw,
+      ident,
+      ugident,
+      overlap,
+      lap
+    ]
+
+    # print values
+    for i in ary
+      i.tr!('^0-9.:e\-','')
+      print "\t#{i}"
+    end
+
+    print "\t#{frame}\n"
+
+  end
+end
+
+=begin MySQL tfastx_results.sql sample
+
+CREATE DATABASE IF NOT EXISTS db_name;
+CREATE TABLE IF NOT EXISTS db_name.table_name (
+	query	varchar(25)	not NULL,
+	q_len	integer		unsigned default 0,
+	target	varchar(25)	not NULL,
+	t_len	integer		unsigned default 0,
+	initn	integer		unsigned default 0,
+	init1	integer		unsigned default 0,
+	opt	integer		unsigned default 0,
+	zscore	float		default 0.0,
+	bits	float		default 0.0,
+	evalue	float		default 0.0,
+	sw	integer		unsigned default 0,
+	ident	float		default 0.0,
+	ugident	float		default 0.0,
+	overlap	integer		unsigned default 0,
+	lap_at	varchar(25)	default NULL,
+	frame	varchar(5)	default NULL
+);
+LOAD DATA LOCAL INFILE 'tfastx_results.tab' INTO TABLE db_name.table_name;
+
+=end
+

data/sample/vs-genes.rb

@@ -0,0 +1,212 @@
+#!/usr/bin/env ruby
+#
+# vs-genes.rb - homology/motif search wrapper
+#
+#  FASTA/BLAST/Pfam interface for the multiple query in the FASTA format
+#
+#   Copyright (C) 2001 KATAYAMA Toshiaki <k@bioruby.org>
+#
+#  This program is free software; you can redistribute it and/or modify
+#  it under the terms of the GNU General Public License as published by
+#  the Free Software Foundation; either version 2 of the License, or
+#  (at your option) any later version.
+#
+#  This program is distributed in the hope that it will be useful,
+#  but WITHOUT ANY WARRANTY; without even the implied warranty of
+#  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+#  GNU General Public License for more details.
+#
+#  $Id: vs-genes.rb,v 0.1 2001/06/21 08:26:31 katayama Exp $
+#
+
+def usage(cpu, ktup, skip, resultdir, verbose)
+  print <<-END
+
+  Usage:
+
+    % #{$0} -p PROG -q QUERY -t TARGET [-c #] [-k #] [-s #] [-d DIR] [-v on]
+
+  options
+    -p PROG   : (fasta3|ssearch3|tfasta3|fastx3|tfastx3)[3]
+                  or
+                (blastp|blastn|blastx|tblastn|tblastx)
+                  or
+                (hmmpfam|hmmpfam_n)
+    -q QUERY  : query nucleotide or peptide sequences in the FASTA format
+    -t TARGET : target DB (FASTA or BLAST2 formatdb or Pfam format)
+
+  optional arguments
+    -c num    : number of CPUs (for the SMP machines, default is #{cpu})
+    -k num    : FASTA ktup value (2 for pep, 6 for nuc, default is #{ktup})
+    -s num    : skip query (for the resume session, default is #{skip})
+    -d DIR    : result output directory (default is "#{resultdir}")
+    -v on/off : verbose output of processing if on (default is "#{verbose}")
+
+  END
+
+  exit 1
+end
+
+
+### initialize
+
+def init
+  arg = {}
+
+  # default values
+  arg['c'] = 1			# num of CPUs
+  arg['k'] = 2			# ktup value for FASTA
+  arg['s'] = 0			# skip query
+  arg['d'] = "./result"		# result directory
+  arg['v'] = 'off'		# verbose mode
+
+  # parse options
+  ARGV.join(' ').scan(/-(\w) (\S+)/).each do |key, val|
+    arg[key] = val
+  end
+
+  # check program, query, target or print usage
+  unless arg['p'] and arg['q'] and arg['t']
+    usage(arg['c'], arg['k'], arg['s'], arg['d'], arg['v'])
+  end
+
+  # create result output directory
+  unless test(?d, "#{arg['d']}")
+    Dir.mkdir("#{arg['d']}", 0755)
+  end
+
+  # print status
+  if arg['v'] != 'off'
+    puts "PROG   : #{arg['p']}"
+    puts "  ktup : #{arg['k']}" if arg['p'] =~ /fast/
+    puts "QUERY  : #{arg['q']}"
+    puts "  skip : #{arg['s']}"
+    puts "TARGET : #{arg['t']}"
+    puts "RESULT : #{arg['d']}"
+  end
+
+  return arg
+end
+
+
+### generate command line
+
+def cmd_line(arg, orf)
+  # program with default command line options	# query -> target DB
+  opt = {
+    # FASTA : "-b n" for best n scores, "-d n" for best n alignment
+    'fasta3'	=> "fasta3    -Q -H -m 6",	# pep -> pep or nuc -> nuc
+    'ssearch3'	=> "ssearch3  -Q -H -m 6",	# pep -> pep or nuc -> nuc
+    'tfasta3'	=> "tfasta3   -Q -H -m 6",	# pep -> nuc 
+    'fastx3'	=> "fastx3    -Q -H -m 6",	# nuc -> pep 
+    'tfastx3'	=> "tfastx3   -Q -H -m 6",	# pep -> nuc (with frameshifts)
+					
+    'fasta33'	=> "fasta33   -Q -H -m 6",	# pep -> pep or nuc -> nuc
+    'ssearch33'	=> "ssearch33 -Q -H -m 6",	# pep -> pep or nuc -> nuc
+    'tfasta33'	=> "tfasta33  -Q -H -m 6",	# pep -> nuc 
+    'fastx33'	=> "fastx33   -Q -H -m 6",	# nuc -> pep 
+    'tfastx33'	=> "tfastx33  -Q -H -m 6",	# pep -> nuc (with frameshifts)
+
+    # BLAST : outputs XML
+    'blastp'	=> "blastall -m 7 -p blastp  -d",	# pep -> pep 
+    'blastn'	=> "blastall -m 7 -p blastn  -d",	# nuc -> nuc 
+    'blastx'	=> "blastall -m 7 -p blastx  -d",	# nuc -> pep 
+    'tblastn'	=> "blastall -m 7 -p tblastn -d",	# pep -> nuc 
+    'tblastx'	=> "blastall -m 7 -p tblastx -d",	# nuc -> nuc (by trans)
+
+    # Pfam : "-A n" for best n alignment, "-E n" for E value cutoff etc.
+    'hmmpfam'	=> "hmmpfam",			# pep -> Pfam DB
+    'hmmpfam_n'	=> "hmmpfam -n",		# nuc -> Pfam DB
+  }
+
+  # arguments used in the command line
+  cpu    = arg['c'].to_i
+  ktup   = arg['k']
+  target = arg['t']
+  query  = arg['d'] + "/query." + orf
+  result = arg['d'] + "/" + orf
+
+  prog   = opt[arg['p']]
+
+  if cpu > 1					# use multiple CPUs
+    case arg['p']
+    when /(fast|ssearch)/
+      prog += " -T #{cpu}"
+      prog.sub!(' ', '_t ')			# rename program with "_t"
+    when /pfam/
+      prog += " --cpu #{cpu}"
+    end
+  end
+
+  # generate complete command line to execute
+  case arg['p']
+  when /fast/
+    command  = "#{prog} #{query} #{target} #{ktup} > #{result}"
+  when /ssearch/
+    command  = "#{prog} #{query} #{target} > #{result}"
+  when /blast/
+    command  = "#{prog} #{target} -i #{query} > #{result}"
+  when /pfam/
+    command  = "#{prog} #{target} #{query} > #{result}"
+  end
+
+  return command
+end
+
+
+### main
+
+begin
+  arg = init
+  count = 0
+
+  open(arg['q'], "r") do |f|
+    while seq = f.gets("\n>")
+      count += 1
+
+      # skip (-s option)
+      next unless count > arg['s'].to_i
+
+      # clean up
+      seq.sub!(/^>?[ \t]*/, '')	# delete '>' and SPACEs or TABs at the head
+      seq.sub!(/>$/, '')	# delete '>' at the tail (separator)
+
+      # get ORF name
+      if seq[/^$/]		# no definition (e.g. ">\nSEQ>" or ">\n>")
+	next			#  -> useless for the multiple query
+      else
+	orf = seq[/^\S+/]	# the first word in the definition line
+      end
+
+      # KEGG uses ">DB:ENTRY" format in the definition line
+      if orf =~ /:/
+	db,orf = orf.split(/:/)
+      end
+
+      # add time if the same ORF name was already used
+      if test(?f, "#{arg['d']}/#{orf}")
+	orf = "#{orf}.#{Time.now.to_f.to_s}"
+      end
+
+      # create temporal file of the query
+      open("#{arg['d']}/query.#{orf}", "w+") do |tmp|
+	tmp.print(">#{seq}")
+      end
+
+      command = cmd_line(arg, orf)
+
+      # print status
+      if arg['v'] != 'off'
+	puts "#{count} : #{orf} ..."
+	puts "  #{command}"
+      end
+
+      # execute
+      system("#{command}")
+
+      # remove temporal file
+      File.delete("#{arg['d']}/query.#{orf}")
+    end
+  end
+end
+