bio 0.7.0

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
+

data/sample/genome2tab.rb

@@ -0,0 +1,76 @@
+#!/usr/bin/env ruby
+#
+# genome2tab.rb - convert KEGG/GENOME into tab delimited data for MySQL
+#
+#  Usage:
+#
+#    % genome2tab.rb /bio/db/kegg/genome/genome > genome.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: genome2tab.rb,v 0.5 2002/06/23 20:21:56 k Exp $
+#
+
+require 'bio/db/kegg/genome'
+
+include Bio
+
+while entry = gets(KEGG::GENOME::DELIMITER)
+
+  genome = KEGG::GENOME.new(entry)
+
+  ref = genome.references.inspect
+  chr = genome.chromosomes.inspect
+
+  ary = [
+    genome.entry_id,
+    genome.name,
+    genome.definition,
+    genome.taxid,
+    genome.taxonomy,
+    genome.comment,
+    ref,
+    chr,
+    genome.nalen,
+    genome.num_gene,
+    genome.num_rna,
+    genome.gc,
+    genome.genomemap,
+  ]
+
+  puts ary.join("\t")
+
+end
+
+=begin
+
+CREATE DATABASE IF NOT EXISTS db_name;
+CREATE TABLE IF NOT EXISTS db_name.genome (
+	id		varchar(30)	not NULL,
+	name		varchar(80),
+	definition	varchar(255),
+	taxid		varchar(30),
+	taxonomy	varchar(255),
+	comment		varchar(255),
+	reference	text,
+	chromosome	text,
+	nalen		integer,
+	num_gene	integer,
+	num_rna		integer,
+	gc		float,
+	genomemap	varchar(30),
+);
+LOAD DATA LOCAL INFILE 'genome.tab' INTO TABLE db_name.genome;
+
+=end
+

data/sample/goslim.rb

@@ -0,0 +1,311 @@
+#!/usr/bin/env ruby
+#
+# goslim.rb - making a GO slim histgram
+#
+#  Usage:
+#
+#    % goslim.rb -p process.ontology -f function.ontology \
+#       -c component.ontology -s goslim_goa.2002 -g gene_association.mgi \
+#       -o mgi -r
+#    % R < mgi.R
+#    % gv mgi.pdf
+#
+#   Copyright (C) 2003 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: goslim.rb,v 1.3 2003/05/13 10:45:42 n Exp $
+#
+
+
+
+SCRIPT_VERSION = '$Id: goslim.rb,v 1.3 2003/05/13 10:45:42 n Exp $'
+
+USAGE = "${__FILE__} - GO slim
+Usage:
+  #{__FILE__} -p process.ontology -f function.ontology \
+     -c component.ontolgy -g gene_association.mgi -s goslim_goa.2002 \
+     -o goslim.uniqued.out -r
+
+  #{__FILE__} -p process.ontology -f function.ontology \
+     -c component.ontolgy -l gene_association.list -s goslim_goa.2002 \
+     -o mgi.out -r
+
+  #{__FILE__} -p process.ontology -f function.ontology \
+     -c component.ontolgy -g gene_association.mgi -s goslim_goa.2002 >\
+     go_goslit.paired.list
+
+
+
+Options;
+ -p,--process <go/ontology/process.ontology>
+ -f,--function <go/ontology/function.ontolgoy>
+ -c,--component <go/ontology/component.ontology>
+ -g,--ga <go/gene-associations/gene_association.someone>
+ -l,--galist <a GO_ID list>
+ -s,--goslim <go/GO_slim/goslim_someone>
+ -o,--output <file_name> -- output file name.
+ -r,--r_script -- Writing a R script in <file_name>.R to plot a barplot.
+ -h,--help
+ -v,--version
+
+Format:
+  GO ID list: /^GO:\d{7}/ for each line
+
+Mitsuteru C. Nakao <n@bioruby.org>
+"
+
+
+
+require 'getoptlong'
+parser = GetoptLong.new
+parser.set_options(
+		   ['--process',   '-p', GetoptLong::REQUIRED_ARGUMENT],
+		   ['--function',  '-f', GetoptLong::REQUIRED_ARGUMENT],
+		   ['--component', '-c', GetoptLong::REQUIRED_ARGUMENT],
+		   ['--ga',        '-g', GetoptLong::REQUIRED_ARGUMENT],
+		   ['--galist',    '-l', GetoptLong::REQUIRED_ARGUMENT],
+		   ['--goslim',    '-s', GetoptLong::REQUIRED_ARGUMENT],
+		   ['--output',    '-o', GetoptLong::REQUIRED_ARGUMENT],
+		   ['--r_script',  '-r', GetoptLong::NO_ARGUMENT],
+		   ['--help',      '-h', GetoptLong::NO_ARGUMENT],
+		   ['--version',   '-v', GetoptLong::NO_ARGUMENT])
+
+begin
+  parser.each_option do |name, arg|
+    eval "$OPT_#{name.sub(/^--/, '').gsub(/-/, '_').upcase} = '#{arg}'"
+  end
+rescue
+  exit(1)
+end
+
+if $OPT_VERSION
+  puts SCRIPT_VERSION
+  exit(0)
+end
+
+if $OPT_HELP or !($OPT_PROCESS or $OPT_FUNCTION or $OPT_COMPONENT or 
+		  ($OPT_GA or $OPT_GALIST))
+  puts USAGE
+  exit(0)
+end
+
+
+
+
+# subroutines
+
+def slim2r(datname)
+  tmp = "# usage: % R --vanilla < #{datname}.R
+data <- read.delim2('#{datname}')
+dat <- data$count
+names(dat) <- paste(data$GO.Term, dat)
+# set graphc format
+pdf('#{datname}.pdf') 
+#postscript('#{datname}.ps') 
+# outside margins
+par(mai = c(1,2.8,1,0.7))
+barplot(dat, 
+        cex.names = 0.6,  # row names font size
+        las = 2,          # set horizontal row names
+        horiz = T,        # set horizontal 
+        main = 'GO slim', # main title
+        # set color schema, proc, blue(3); func, red(2); comp, green(4)
+        col = cbind(c(data$aspect == 'process'), 
+		    c(data$aspect == 'function'), 
+                    c(data$aspect == 'component')) %*% c(4,2,3)) # color
+dev.off()
+"
+end
+
+
+# build GOslim uniqued list
+def slim(ontology, slim_ids, tmp, ga, aspect)
+  tmp[aspect] = Hash.new(0)
+  slim_ids.each {|slim_id|
+    term = ontology.goid2term(slim_id)
+    if term
+      tmp[aspect][term] = 0
+    else
+      next
+    end
+
+    ga.each {|gaid|
+      begin 
+	res = ontology.bfs_shortest_path(slim_id, gaid)
+	tmp[aspect][term] += 1 if res[0]
+      rescue NameError 
+	$stderr.puts "Warnning: GO:#{slim_id} (#{term}) doesn't exist in the #{aspect}.ontology."
+	tmp[aspect].delete(term)
+	break
+      end
+    }
+  }
+end
+
+
+# build GO-GOslim uniqued list
+def slim2(ontology, slim_ids, tmp, ga, aspect)
+  tmp[aspect] = Hash.new
+  slim_ids.each {|slim_id|
+    term = ontology.goid2term(slim_id)
+    if term
+      begin
+	unless tmp[aspect][term]['GOslim'].index(slim_id)
+	  tmp[aspect][term]['GOslim'] << slim_id
+	end
+      rescue NameError
+	tmp[aspect][term] = {'GOslim'=>[slim_id], 'GO'=>[]}
+      end
+    else
+      next
+    end
+
+    ga.each {|gaid|
+      begin 
+	res = ontology.bfs_shortest_path(slim_id, gaid)
+	tmp[aspect][term]['GO'] << gaid if res[0]
+      rescue NameError
+
+	break
+      end
+    }
+  }
+end
+
+
+
+#
+# main
+#
+
+require 'bio/db/go'
+
+aspects = ['process', 'function', 'component']
+rootids = {
+  'process'   => '0008150', 
+  'function'  => '0003674', 
+  'component' => '0005575'}
+
+# files open
+
+ios = {}
+files = {
+  'process'   => $OPT_PROCESS, 
+  'function'  => $OPT_FUNCTION, 
+  'component' => $OPT_COMPONENT,  
+  'ga'   => $OPT_GA,            # gene-association
+  'list' => $OPT_GALIST,        # gene-association list
+  'slim' => $OPT_GOSLIM}        # GO slim
+
+files.each {|k, file_name|
+  next if file_name == nil
+  ios[k] = File.open(file_name)
+}
+
+if $OPT_OUTPUT
+  ios['output']   = File.new($OPT_OUTPUT, "w+")
+  ios['r_script'] = File.new("#{$OPT_OUTPUT}.R", "w+")
+else
+  ios['r_script'] = ios['output'] = $stdout
+end
+
+
+# start
+
+# ontology
+ontology = {}
+aspects.each {|aspect|
+  ontology[aspect] = Bio::GO::Ontology.new(ios[aspect].read)
+}
+
+
+# GO slim
+goslim = Bio::GO::Ontology.new(ios['slim'].read)
+
+# assign a aspect to terms in the GO slim.
+slim_ids = Hash.new([])
+goslim.to_list.map {|ent| ent.node }.flatten.uniq.each {|goid|
+  rootids.each {|aspect, rootid|
+    begin
+      a,b = ontology[aspect].bfs_shortest_path(rootid, goid)
+      slim_ids[aspect] << goid
+    rescue NameError
+      $stderr.puts "Error: (#{rootid}, #{goid})"
+    end
+  }
+}
+
+
+
+
+# gene-associations
+
+ga_ids = []
+if $OPT_GA
+  ga = Bio::GO::GeneAssociation.parser(ios['ga'].read)
+  ga_ids = ga.map {|ent| ent.goid }
+
+elsif $OPT_GALIST
+  while line = ios['list'].gets
+    if /^GO:(\d{7})/ =~ line
+      goid = $1
+      ga_ids << goid
+    end
+  end
+else
+  puts "Error: -l or -g options"
+  exit
+end
+
+
+# count number
+
+count = Hash.new(0)
+
+aspects.each {|aspect|
+  slim2(ontology[aspect], slim_ids[aspect], count, ga_ids, aspect)
+}
+
+
+
+
+# output
+
+if $OPT_R_SCRIPT and $OPT_OUTPUT
+  tmp = [['aspect', 'count', 'GO Term'].join("\t")]
+else
+  tmp = [['aspect', 'GO ID', 'GOslim Term', 'GOslim ID'].join("\t")]
+end
+
+['component','function','process'].each {|aspect|
+  count[aspect].sort {|a, b| b[1]['GO'].size <=> a[1]['GO'].size }.each {|term, value|
+    next if term == ""
+
+    if $OPT_R_SCRIPT and $OPT_OUTPUT
+      tmp << [aspect, value['GO'].size, term].join("\t") 
+    else
+      value['GO'].each {|goid|
+	tmp << [aspect, "GO:#{goid}", term, 
+	  value['GOslim'].map {|e| "GO:#{e}" }.join(' ')].join("\t") 
+      }
+    end
+  }
+}
+ios['output'].puts tmp.join("\n")
+
+
+if $OPT_R_SCRIPT and $OPT_OUTPUT
+  ios['r_script'].puts slim2r($OPT_OUTPUT)
+end
+
+
+#