ngoto-bio 1.2.9.9001

data/sample/gb2tab.rb

@@ -0,0 +1,325 @@
+#!/usr/bin/env ruby
+#
+# gb2tab.rb - convert GenBank into tab delimited data for MySQL
+#
+#  Usage:
+#
+#    % gb2tab.rb gb*.seq
+#
+#   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: gb2tab.rb,v 0.11 2002/04/22 09:10:10 k Exp $
+#
+
+require 'bio'
+
+$stderr.puts Time.now
+
+ARGV.each do |gbkfile|
+
+  gbk = open("#{gbkfile}")
+  ent = open("#{gbkfile}.ent.tab", "w")
+  ft  = open("#{gbkfile}.ft.tab", "w")
+  ref = open("#{gbkfile}.ref.tab", "w")
+  seq = open("#{gbkfile}.seq.tab", "w")
+  
+  while entry = gbk.gets(Bio::GenBank::DELIMITER)
+  
+    gb = Bio::GenBank.new(entry)
+  
+    ### MAIN BODY
+
+    ary = [
+      gb.entry_id,
+      gb.nalen,
+      gb.strand,
+      gb.natype,
+      gb.circular,
+      gb.division,
+      gb.date,
+      gb.definition,
+      gb.accession,
+      gb.versions.inspect,
+      gb.keywords.inspect,
+      gb.segment.inspect,
+      gb.common_name,
+      gb.organism,
+      gb.taxonomy,
+      gb.comment,
+      gb.basecount.inspect,
+      gb.origin,
+    ]
+  
+    ent.puts ary.join("\t")
+  
+    ### FEATURES
+  
+    num = 0
+  
+    gb.features.each do |f|
+      num += 1
+
+      span_min, span_max = f.locations.span
+
+      if f.qualifiers.empty?
+	ary = [
+	    gb.entry_id,
+	    num,
+	    f.feature,
+	    f.position,
+	    span_min,
+	    span_max,
+	    '',
+	    '',
+	]
+	ft.puts ary.join("\t")
+      else
+	f.each do |q|
+	  ary = [
+	    gb.entry_id,
+	    num,
+	    f.feature,
+	    f.position,
+	    span_min,
+	    span_max,
+	    q.qualifier,
+	    q.value,
+	  ]
+	  ft.puts ary.join("\t")
+	end
+      end
+
+    end
+
+    ### REFERENCE
+  
+    num = 0
+
+    gb.references.each do |r|
+      num += 1
+  
+      ary = [
+	gb.entry_id,
+	num,
+	r.authors.inspect,
+	r.title,
+	r.journal,
+	r.medline,
+	r.pubmed,
+      ]
+  
+      ref.puts ary.join("\t")
+    end
+
+    ### SEQUENCE
+
+    maxlen = 16 * 10 ** 6
+
+    num = 0
+
+    0.step(gb.nalen, maxlen) do |i|
+      num += 1
+
+      ary = [
+	gb.entry_id,
+	num,
+	gb.naseq[i, maxlen]
+      ]
+
+      seq.puts ary.join("\t")
+
+    end
+
+  end
+
+  gbk.close
+  ent.close
+  ft.close
+  ref.close
+  seq.close
+
+end
+
+$stderr.puts Time.now
+
+=begin
+
+Example usage in zsh:
+
+  % gb2tab.rb *.seq
+  % for i in *.seq
+  > do
+  >   base=`basename $i .seq`
+  >   ruby -pe "gsub(/%HOGE%/,'$base')" gb2tab.sql | mysql
+  > done
+
+gb2tab.sql:
+
+CREATE DATABASE IF NOT EXISTS genbank;
+USE genbank;
+
+CREATE TABLE IF NOT EXISTS %HOGE% (
+	id		varchar(16)	NOT NULL PRIMARY KEY,
+	nalen		integer,
+	strand		varchar(5),
+	natype		varchar(5),
+	circular	varchar(10),
+	division	varchar(5),
+	date		varchar(12),
+	definition	varchar(255),
+	accession	varchar(30),
+	versions	varchar(30),
+	keywords	varchar(255),
+	segment		varchar(255),
+	source		varchar(255),
+	organism	varchar(255),
+	taxonomy	varchar(255),
+	comment		text,
+	basecount	varchar(255),
+	origin		varchar(255),
+	KEY (nalen),
+	KEY (division),
+	KEY (accession),
+	KEY (organism),
+	KEY (taxonomy)
+);
+LOAD DATA LOCAL INFILE '%HOGE%.seq.ent.tab' INTO TABLE %HOGE%;
+
+CREATE TABLE IF NOT EXISTS %HOGE%ft (
+	id		varchar(16)	NOT NULL,
+	num		integer,
+	feature		varchar(30),
+	position	text,
+	span_min	integer,
+	span_max	integer,
+	qualifier	varchar(30),
+	value		text,
+	KEY (id),
+	KEY (num),
+	KEY (feature),
+	KEY (span_min),
+	KEY (span_max),
+	KEY (qualifier)
+);
+LOAD DATA LOCAL INFILE '%HOGE%.seq.ft.tab' INTO TABLE %HOGE%ft;
+
+CREATE TABLE IF NOT EXISTS %HOGE%ref (
+	id		varchar(16)	NOT NULL,
+	num		integer,
+	authors		text,
+	title		text,
+	journal		text,
+	medline		varchar(255),
+	pubmed		varchar(255),
+	KEY (id),
+	KEY (medline),
+	KEY (pubmed)
+);
+LOAD DATA LOCAL INFILE '%HOGE%.seq.ref.tab' INTO TABLE %HOGE%ref;
+
+CREATE TABLE IF NOT EXISTS %HOGE%seq (
+	id		varchar(16)	NOT NULL,
+	num		integer,
+	naseq		mediumtext,
+	KEY (id)
+);
+LOAD DATA LOCAL INFILE '%HOGE%.seq.seq.tab' INTO TABLE %HOGE%seq;
+
+
+gbmerge.sql sample:
+
+CREATE TABLE IF NOT EXISTS ent (
+	id		varchar(16)	NOT NULL PRIMARY KEY,
+	nalen		integer,
+	strand		varchar(5),
+	natype		varchar(5),
+	circular	varchar(10),
+	division	varchar(5),
+	date		varchar(12),
+	definition	varchar(255),
+	accession	varchar(30),
+	versions	varchar(30),
+	keywords	varchar(255),
+	segment		varchar(255),
+	source		varchar(255),
+	organism	varchar(255),
+	taxonomy	varchar(255),
+	comment		text,
+	basecount	varchar(255),
+	origin		varchar(255),
+	KEY (nalen),
+	KEY (division),
+	KEY (accession),
+	KEY (organism),
+	KEY (taxonomy)
+) TYPE=MERGE UNION=(
+	gbbct1,
+	gbbct2,
+	...,		# list up all tables by yourself
+	gbvrt
+);
+
+CREATE TABLE IF NOT EXISTS ft (
+	id		varchar(16)	NOT NULL,
+	num		integer,
+	feature		varchar(30),
+	position	text,
+	span_min	integer,
+	span_max	integer,
+	qualifier	varchar(30),
+	value		text,
+	KEY (id),
+	KEY (num),
+	KEY (feature),
+	KEY (span_min),
+	KEY (span_max),
+	KEY (qualifier)
+) TYPE=MERGE UNION=(
+	gbbct1ft,
+	gbbct2ft,
+	...,		# list up all ft tables by yourself
+	gbvrtft
+);
+
+CREATE TABLE IF NOT EXISTS ref (
+	id		varchar(16)	NOT NULL,
+	num		integer,
+	authors		text,
+	title		text,
+	journal		text,
+	medline		varchar(255),
+	pubmed		varchar(255),
+	KEY (id),
+	KEY (medline),
+	KEY (pubmed)
+) TYPE=MERGE UNION=(
+	gbbct1ref,
+	gbbct2ref,
+	...,		# list up all ref tables by yourself
+	gbvrtref
+);
+
+CREATE TABLE IF NOT EXISTS seq (
+	id		varchar(16)	NOT NULL,
+	num		integer,
+	naseq		mediumtext,
+	KEY (id)
+) TYPE=MERGE UNION=(
+	gbbct1seq,
+	gbbct2seq,
+	...,		# list up all seq tables by yourself
+	gbvrtseq
+);
+
+=end
+

data/sample/gbtab2mysql.rb

@@ -0,0 +1,161 @@
+#!/usr/bin/env ruby
+#
+# gbtab2mysql.rb - load tab delimited GenBank data files into MySQL
+#
+#   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: gbtab2mysql.rb,v 1.3 2002/06/25 19:30:26 k Exp $
+#
+
+require 'dbi'
+
+$schema_ent = <<END
+	id		varchar(16)	NOT NULL PRIMARY KEY,
+	nalen		integer,
+	strand		varchar(5),
+	natype		varchar(5),
+	circular	varchar(10),
+	division	varchar(5),
+	date		varchar(12),
+	definition	varchar(255),
+	accession	varchar(30),
+	versions	varchar(30),
+	keywords	varchar(255),
+	segment		varchar(255),
+	source		varchar(255),
+	organism	varchar(255),
+	taxonomy	varchar(255),
+	comment		text,
+	basecount	varchar(255),
+	origin		varchar(255),
+	KEY (nalen),
+	KEY (division),
+	KEY (accession),
+	KEY (organism),
+	KEY (taxonomy)
+END
+
+$schema_ft = <<END
+	id		varchar(16)	NOT NULL,
+	num		integer,
+	feature		varchar(30),
+	position	text,
+	span_min	integer,
+	span_max	integer,
+	qualifier	varchar(30),
+	value		text,
+	KEY (id),
+	KEY (num),
+	KEY (feature),
+	KEY (span_min),
+	KEY (span_max),
+	KEY (qualifier)
+END
+
+$schema_ref = <<END
+	id		varchar(16)	NOT NULL,
+	num		integer,
+	authors		text,
+	title		text,
+	journal		text,
+	medline		varchar(255),
+	pubmed		varchar(255),
+	KEY (id),
+	KEY (medline),
+	KEY (pubmed)
+END
+
+$schema_seq = <<END
+	id		varchar(16)	NOT NULL,
+	num		integer,
+	naseq		mediumtext,
+	KEY (id)
+END
+
+
+def create_table(dbh, table)
+  $stderr.puts("create tables on #{table}") if $DEBUG
+
+  query = "CREATE TABLE IF NOT EXISTS #{table} ( #{$schema_ent} )"
+  dbh.execute(query)
+  query = "CREATE TABLE IF NOT EXISTS #{table}ft ( #{$schema_ft} )"
+  dbh.execute(query)
+  query = "CREATE TABLE IF NOT EXISTS #{table}ref ( #{$schema_ref} )"
+  dbh.execute(query)
+  query = "CREATE TABLE IF NOT EXISTS #{table}seq ( #{$schema_seq} )"
+  dbh.execute(query)
+end
+
+
+def load_tab(dbh, base, table)
+  $stderr.puts("load #{base} into #{table}") if $DEBUG
+
+  query = "LOAD DATA LOCAL INFILE '#{base}.seq.ent.tab' INTO TABLE #{table}"
+  dbh.execute(query)
+  query = "LOAD DATA LOCAL INFILE '#{base}.seq.ft.tab' INTO TABLE #{table}ft"
+  dbh.execute(query)
+  query = "LOAD DATA LOCAL INFILE '#{base}.seq.ref.tab' INTO TABLE #{table}ref"
+  dbh.execute(query)
+  query = "LOAD DATA LOCAL INFILE '#{base}.seq.seq.tab' INTO TABLE #{table}seq"
+  dbh.execute(query)
+end
+
+
+def merge_table(dbh, tables)
+  query = "CREATE TABLE IF NOT EXISTS ent ( #{$schema_ent} )" +
+		" TYPE=MERGE UNION=( #{tables.join(', ')} )"
+  dbh.execute(query)
+  query = "CREATE TABLE IF NOT EXISTS ft ( #{$schema_ft} )" +
+		" TYPE=MERGE UNION=( #{tables.join('ft, ') + 'ft' } )"
+  dbh.execute(query)
+  query = "CREATE TABLE IF NOT EXISTS ref ( #{$schema_ref} )" +
+		" TYPE=MERGE UNION=( #{tables.join('ref, ') + 'ref' } )"
+  dbh.execute(query)
+  query = "CREATE TABLE IF NOT EXISTS seq ( #{$schema_seq} )" +
+		" TYPE=MERGE UNION=( #{tables.join('seq, ') + 'seq' } )"
+  dbh.execute(query)
+end
+
+
+$stderr.puts Time.now
+
+DBI.connect('dbi:Mysql:genbank:localhost', 'root') do |dbh|
+  tables = Array.new
+
+  Dir.glob("*.seq").sort.each do |gbk|
+    base = File.basename(gbk, '.seq')
+
+    div = base[/gb.../]
+    num = base[/\d+/].to_i
+
+    table = div
+    table = "%s%d" % [ div, (num - 1) / 20 + 1 ] if num > 20
+
+    unless dbh.tables.include?(table)
+      create_table(dbh, table)
+      tables.push(table)
+    end
+
+    load_tab(dbh, base, table)
+  end
+
+  merge_table(dbh, tables)
+end
+
+$stderr.puts Time.now
+
+

data/sample/genes2nuc.rb

@@ -0,0 +1,33 @@
+#!/usr/bin/env ruby
+#
+# genes2nuc.rb - convert KEGG/GENES entry into FASTA format (nuc)
+#
+#   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: genes2nuc.rb,v 0.4 2002/06/23 20:21:56 k Exp $
+#
+
+require 'bio/db/kegg/genes'
+require 'bio/extend'
+
+include Bio
+
+while gets(KEGG::GENES::DELIMITER)
+  genes = KEGG::GENES.new($_)
+
+  next if genes.nalen == 0
+
+  puts ">#{genes.entry_id}  #{genes.definition}"
+  puts genes.naseq.fold(60+12, 12)
+end
+

data/sample/genes2pep.rb

@@ -0,0 +1,33 @@
+#!/usr/bin/env ruby
+#
+# genes2nuc.rb - convert KEGG/GENES entry into FASTA format (nuc)
+#
+#   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: genes2pep.rb,v 0.4 2002/06/23 20:21:56 k Exp $
+#
+
+require 'bio/db/kegg/genes'
+require 'bio/extend'
+
+include Bio
+
+while gets(KEGG::GENES::DELIMITER)
+  genes = KEGG::GENES.new($_)
+
+  next if genes.aalen == 0
+
+  puts ">#{genes.entry_id}  #{genes.definition}"
+  puts genes.aaseq.fold(60+12, 12)
+end
+

data/sample/genes2tab.rb

@@ -0,0 +1,81 @@
+#!/usr/bin/env ruby
+#
+# genes2tab.rb - convert KEGG/GENES into tab delimited data for MySQL
+#
+#  Usage:
+#
+#    % genes2tab.rb /bio/db/kegg/genes/e.coli > genes_eco.tab
+#
+#   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: genes2tab.rb,v 0.5 2002/06/23 20:21:56 k Exp $
+#
+
+require 'bio/db/kegg/genes'
+
+include Bio
+
+while entry = gets(KEGG::GENES::DELIMITER)
+
+  genes = KEGG::GENES.new(entry)
+
+  db = genes.dblinks.inspect
+
+  if genes.codon_usage.length == 64
+    cu = genes.codon_usage.join(' ')
+  else
+    cu = '\N'
+  end
+
+  ary = [
+    genes.entry_id,
+    genes.division,
+    genes.organism,
+    genes.name,
+    genes.definition,
+    genes.keggclass,
+    genes.position,
+    db,
+    cu,
+    genes.aalen,
+    genes.aaseq,
+    genes.nalen,
+    genes.naseq
+  ]
+
+  puts ary.join("\t")
+
+end
+
+=begin
+
+CREATE DATABASE IF NOT EXISTS db_name;
+CREATE TABLE IF NOT EXISTS db_name.genes (
+	id		varchar(30)	not NULL,	# ENTRY ID
+	division	varchar(30),			# CDS, tRNA etc.
+	organism	varchar(255),
+	gene		varchar(255),
+	definition	varchar(255),
+	keggclass	varchar(255),
+	position	varchar(255),
+	dblinks		varchar(255),
+	codon_usage	text,
+	aalen		integer,
+	aaseq		text,
+	nalen		integer,
+	naseq		text
+);
+LOAD DATA LOCAL INFILE 'genes.tab' INTO TABLE db_name.genes;
+
+=end
+

data/sample/genome2rb.rb

@@ -0,0 +1,29 @@
+#!/usr/bin/env ruby
+#
+# genome2rb.rb - used to generate contents of the bio/data/keggorg.rb
+#
+#  Usage:
+#
+#    % genome2rb.rb genome | sort
+#
+#   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.
+#
+#  $Id: genome2rb.rb,v 1.1 2002/03/04 08:14:45 katayama Exp $
+#
+
+require 'bio'
+
+Bio::FlatFile.new(Bio::KEGG::GENOME,ARGF).each do |x|
+  puts "    '#{x.entry_id}' => [ '#{x.name}', '#{x.definition}' ],"
+end
+