bio 0.7.0

data/sample/gt2fasta.rb

@@ -0,0 +1,47 @@
+#!/usr/bin/env ruby
+#
+# gt2fasta.rb - convert GenBank translations into FASTA format (pep)
+#
+#   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: gt2fasta.rb,v 0.3 2002/04/15 03:06:17 k Exp $
+#
+
+require 'bio/io/flatfile'
+require 'bio/feature'
+require 'bio/db/genbank'
+
+include Bio
+
+ff = FlatFile.new(GenBank, ARGF)
+
+while gb = ff.next_entry
+
+  orf = 0
+  gb.features.each do |f|
+    f = f.assoc
+    if aaseq = f['translation']
+      orf += 1
+      gene = [
+        f['gene'],
+        f['product'],
+        f['note'],
+        f['function']
+      ].compact.join(', ')
+      definition = "gp:#{gb.entry_id}_#{orf} #{gene} [#{gb.organism}]"
+      print aaseq.to_fasta(definition, 70)
+    end
+  end
+
+end
+

data/sample/pmfetch.rb

@@ -0,0 +1,42 @@
+#!/usr/bin/env ruby 
+#
+# pmfetch.rb - generate BibTeX format reference list by PubMed ID list
+#
+#   Copyright (C) 2002 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.
+#
+#  You should have received a copy of the GNU General Public License
+#  along with this program; if not, write to the Free Software
+#  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+#
+#  $Id: pmfetch.rb,v 1.2 2002/07/23 04:52:03 k Exp $
+#
+
+require 'bio' 
+
+if ARGV[0] =~ /-f/
+  ARGV.shift
+  form = ARGV.shift
+else
+  form = 'bibtex'
+end
+
+ARGV.each do |id| 
+  entry = Bio::PubMed.query(id) 
+  case form
+  when 'medline'
+    puts entry
+  else
+    puts Bio::MEDLINE.new(entry).reference.send(form)
+  end
+end 
+

data/sample/pmsearch.rb

@@ -0,0 +1,42 @@
+#!/usr/bin/env ruby
+#
+# pmsearch.rb - generate BibTeX format reference list by PubMed keyword search
+#
+#   Copyright (C) 2002 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.
+#
+#  You should have received a copy of the GNU General Public License
+#  along with this program; if not, write to the Free Software
+#  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+#
+#  $Id: pmsearch.rb,v 1.2 2002/07/23 04:52:03 k Exp $
+#
+
+require 'bio'
+
+if ARGV[0] =~ /-f/
+  ARGV.shift
+  form = ARGV.shift
+else
+  form = 'bibtex'
+end
+
+entries = Bio::PubMed.search(ARGV.join(' '))
+entries.each do |entry| 
+  case form
+  when 'medline'
+    puts entry
+  else
+    puts Bio::MEDLINE.new(entry).reference.send(form)
+  end
+end
+

data/sample/psortplot_html.rb

@@ -0,0 +1,222 @@
+#!/usr/bin/env ruby
+#
+# psortplot_html.rb - A KEGG API demo script. Generates a HTML file of 
+#                     genes marked by PSORT II predictions onto a 
+#                     KEGG/PATHWAY map.
+#
+#  Usage:
+#
+#   % ruby psortplot_html.rb
+#   % cat sce00010_psort2.html
+#   % ruby psortplot_html.rb path:eco00010
+#   % cat eco00010_psort2.html
+#
+# Copyright (C) 2005 Mitsuteru C. Nakao <n@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: psortplot_html.rb,v 1.1 2005/10/12 02:10:11 nakao Exp $
+#
+
+require 'bio'
+
+class KEGG
+  DBGET_BASEURI = 'http://kegg.com/dbget-bin'
+  WWW_BGET_BASEURI = DBGET_BASEURI + '/www_bget'
+  WWW_PATHWAY_BASEURI = DBGET_BASEURI + '/get_pathway'
+
+  # path := path:sce00010
+  def self.link_pathway(path0)
+    path, path = path0.split(':')
+    org_name = path.scan(/(^\w{3})/).to_s
+    mapno = path.sub(org_name, '')
+    str = "<a href='#{WWW_PATHWAY_BASEURI}?org_name=#{org_name}&mapno=#{mapno}'>#{path0}</a>"
+  end
+  
+  # ec_num := ec:1.2.3.4
+  def self.link_ec(ec_num)
+    ec = ec_num.sub(/^ec:/, '')
+    str = "<a href='#{WWW_BGET_BASEURI}?enzyme+#{ec}'>#{ec_num}</a>"
+    return str
+  end
+
+  # gene := eco:b0002
+  def self.link_genes(gene)
+    org_name, gene_name = gene.split(':')
+    str = "<a href='#{WWW_BGET_BASEURI}?#{org_name}+#{gene_name}'>#{gene}</a>"
+    return str
+  end
+end
+
+
+class PSORT
+  COLOR_Palette = {
+    'csk' => "#FF0000",   # 'cytoskeletal'
+    'cyt' => "#FF8000",   # 'cytoplasmic'
+    'nuc' => "#FFFF00",   # 'nuclear'
+    'mit' => "#80FF00",   # 'mitochondrial'
+    'ves' => "#00FF00",	# 'vesicles of secretory system'
+    'end' => "#00FF80",	# 'endoplasmic reticulum'
+    'gol' => "#00FFFF",	# 'Golgi'
+    'vac' => "#0080FF",	# 'vacuolar'
+    'pla' => "#0000FF",	# 'plasma membrane'
+    'pox' => "#8000FF",	# 'peroxisomal'
+    'exc' => "#FF00FF",	# 'extracellular, including cell wall'
+    '---' => "#FF0080"	# 'other'
+  }
+end
+
+
+
+
+keggapi = Bio::KEGG::API.new
+psort2serv = Bio::PSORT::PSORT2.imsut
+
+# Obtains a list of genes on specified pathway
+pathway = ARGV.shift || "path:sce00010"
+genes = keggapi.get_genes_by_pathway(pathway)
+
+scl = Hash.new # protein subcelluler localizations
+ec = Hash.new  # EC numbers
+
+serial = 0
+sync_default = $stdout.sync
+$stdout.sync = true
+genes.each do |gene|
+  print "#{(serial += 1).to_s.rjust(genes.size.to_s.size)}\t#{gene}\t"
+  # Obtains amino acid sequence from KEGG GENES entry
+  aaseq = keggapi.get_aaseqs([gene])
+
+  # Predicts protein subcellualr localization
+  result = psort2serv.exec(aaseq)
+  scl[gene] = result.pred
+  print "#{scl[gene]}\t"
+
+  # Obtains the EC number from KEGG GENES entry
+  ec[gene] = keggapi.get_enzymes_by_gene(gene)
+  puts "#{ec[gene].inspect}"
+end
+$stdout.sync = sync_default
+
+
+
+
+fg_list = Array.new
+bg_list = Array.new
+
+genes.each do |gene|
+  fg_list << "#FF0000"
+  bg_list << PSORT::COLOR_Palette[scl[gene]]
+end
+
+# coloring KEGG pathway according to gene's localization
+url = keggapi.color_pathway_by_objects(pathway, genes, fg_list, bg_list)
+puts "#{url} downloaded."
+
+# remove "path:" prefix from pathway_id
+path_code = pathway.sub(/^path:/, '')
+
+# save the result image
+image_file = "#{path_code}_psort2.gif"
+begin
+  keggapi.save_image(url, image_file)
+end
+
+
+# create html with a color palette
+html = <<END
+<html>
+<head>
+<title>PSORT II prediction protein subcellular localization map of KEGG/PATHWAY (#{pathway})</title>
+<style>
+table { border-collapse: collapse; }
+td { border: 1px solid black; padding: 5px; }
+td.outer { border: none; vertical-align: top; }
+</style>
+</head>
+<body>
+<h1><li><a href="http://psort.ims.u-tokyo.ac.jp/helpwww2.html">PSORT II</a> prediction protein subcellular localization map of <a href="http://kegg.com/kegg/pathway.html">KEGG/PATHWAY</a> (<a href="">#{KEGG.link_pathway(pathway)})</h1>
+
+<table>
+<tr>
+  <td class=outer>
+    <table>
+    <tr>
+      <th></th>
+      <th>EC</th>
+      <th>Gene</th>
+      <th>Localization</th>
+    </tr>
+END
+
+
+# generate gene table with localization
+names = Bio::PSORT::PSORT2::SclNames
+multi_genes = Hash.new(0)
+
+ec.values.flatten.sort.uniq.each do |ec_num|
+  ec.find_all {|x| x[1].include?(ec_num) }.each do |gene|
+    gene = gene[0]
+    loc = scl[gene]
+    color = PSORT::COLOR_Palette[loc]
+    name = names[loc]
+    multi_genes[gene] += 1
+
+    html += <<END
+    <tr>
+      <td>#{multi_genes[gene]}</td>
+      <td>#{KEGG.link_ec(ec_num)}</td>
+      <td>#{KEGG.link_genes(gene)}</td>
+      <td bgcolor="#{color}">#{name}</td>
+    </tr>
+END
+  end
+end
+
+html += <<END
+    </table>
+  </td>
+  <td class=outer>
+    <table>
+    <tr>
+      <th>Code</th>
+      <th>Color</th>
+    </tr>
+END
+
+# generate color code table also
+PSORT::COLOR_Palette.sort.each do |code, color|
+  html += <<END
+    <tr>
+      <td>#{code}</td>
+      <td bgcolor="#{color}">#{names[code]}</td>
+    </tr>
+END
+end
+
+html += <<END
+    </table>
+  </td>
+</tr>
+</table>
+<br>
+<img src="#{image_file}">
+</body>
+</html>
+END
+
+# save generated HTML file
+html_file = "#{path_code}_psort2.html" 
+File.open(html_file, "w+") do |file|
+  file.puts html
+end
+
+puts "Open #{html_file}"

data/sample/ssearch2tab.rb

@@ -0,0 +1,96 @@
+#!/usr/bin/env ruby
+#
+# ssearch2tab.rb - convert SSEARCH output into tab delimited data for MySQL
+#
+#  Usage:
+#
+#    % ssearch2tab.rb SSEARCH-output-file[s] > ssearch_results.tab
+#    % mysql < ssearch_results.sql  (use sample at the end of this file)
+#
+#  Format accepted:
+#
+#    % ssearch3[3][_t] -Q -H -m 6 query.f target.f > SSEARCH-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: ssearch2tab.rb,v 0.1 2001/06/21 08:25:58 katayama Exp $
+#
+
+while gets
+
+  # query
+  if /^\S+: (\d+) aa$/
+    q_len = $1
+  end
+
+  # each hit
+  if /^>>([^>]\S+).*\((\d+) aa\)$/
+    target = $1
+    t_len = $2
+
+    # d = dummy variable
+    d, d, d, swopt, d, zscore, d, bits, d, evalue =
+      gets.split(/\s+/)
+    d, d, sw, ident, d, ugident, d, d, overlap, d, d, lap =
+      gets.split(/\s+/)
+
+    # query-hit pair
+    print "#{$FILENAME}\t#{q_len}\t#{target}\t#{t_len}"
+
+    # pick up values
+    ary = [
+      swopt,
+      zscore,
+      bits,
+      evalue,
+      sw,
+      ident,
+      ugident,
+      overlap,
+      lap
+    ]
+
+    # print values
+    for i in ary
+      i.tr!('^0-9.:e\-','')
+      print "\t#{i}"
+    end
+
+    print "\n"
+
+  end
+end
+
+=begin MySQL ssearch_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,
+	swopt	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
+);
+LOAD DATA LOCAL INFILE 'ssearch_results.tab' INTO TABLE db_name.table_name;
+
+=end
+
+