bio 1.3.1 → 1.4.0

data/sample/demo_prosite.rb

@@ -0,0 +1,120 @@
+#
+# = sample/demo_prosite.rb - demonstration of Bio::PROSITE
+#
+# Copyright::  Copyright (C) 2001 Toshiaki Katayama <k@bioruby.org>
+# License::    The Ruby License
+#
+#
+# == Description
+#
+# Demonstration of Bio::PROSITE, parser class for PROSITE database entry.
+#
+# == Usage
+#
+# Specify files containing PROSITE data.
+#
+#  $ ruby demo_prosite.rb files...
+#
+# Example usage using test data:
+#
+#  $ ruby -Ilib sample/demo_prosite.rb test/data/prosite/prosite.dat
+#
+# == Development information
+#
+# The code was moved from lib/bio/db/prosite.rb.
+#
+
+require 'bio'
+
+  begin
+    require 'pp'
+    alias p pp
+  rescue LoadError
+  end
+
+Bio::FlatFile.foreach(Bio::PROSITE, ARGF) do |ps|
+  puts "### ps = Bio::PROSITE.new(str)"
+
+  list = %w(
+    name
+    division
+    ac
+    entry_id
+    dt
+    date
+    de
+    definition
+    pa
+    pattern
+    ma
+    profile
+    ru
+    rule
+    nr
+    statistics
+    release
+    swissprot_release_number
+    swissprot_release_sequences
+    total
+    total_hits
+    total_sequences
+    positive
+    positive_hits
+    positive_sequences
+    unknown
+    unknown_hits
+    unknown_sequences
+    false_pos
+    false_positive_hits
+    false_positive_sequences
+    false_neg
+    false_negative_hits
+    partial
+    cc
+    comment
+    max_repeat
+    site
+    skip_flag
+    dr
+    sp_xref
+    pdb_xref
+    pdoc_xref
+  )
+
+  list.each do |method|
+    puts ">>> #{method}"
+    p ps.__send__(method)
+  end
+
+  puts ">>> taxon_range"
+  p ps.taxon_range
+  puts ">>> taxon_range(expand)"
+  p ps.taxon_range(true)
+
+  puts ">>> list_truepositive"
+  p ps.list_truepositive
+  puts ">>> list_truepositive(by_name)"
+  p ps.list_truepositive(true)
+
+  puts ">>> list_falsenegative"
+  p ps.list_falsenegative
+  puts ">>> list_falsenegative(by_name)"
+  p ps.list_falsenegative(true)
+
+  puts ">>> list_falsepositive"
+  p ps.list_falsepositive
+  puts ">>> list_falsepositive(by_name)"
+  p ps.list_falsepositive(true)
+
+  puts ">>> list_potentialhit"
+  p ps.list_potentialhit
+  puts ">>> list_potentialhit(by_name)"
+  p ps.list_potentialhit(true)
+
+  puts ">>> list_unknown"
+  p ps.list_unknown
+  puts ">>> list_unknown(by_name)"
+  p ps.list_unknown(true)
+
+  puts "=" * 78
+end

data/sample/demo_psort.rb

@@ -0,0 +1,138 @@
+#
+# = sample/demo_psort.rb - demonstration of Bio::PSORT, client for PSORT WWW server
+#
+# Copyright::   Copyright (C) 2003-2006
+#               Mitsuteru C. Nakao <n@bioruby.org>
+# License::     The Ruby License
+#
+#
+# == Description
+#
+# Demonstration of Bio::PSORT, client for PSORT (protein sorting site
+# prediction systems) WWW server.
+#
+# == Requirements
+#
+# Internet connection is needed.
+#
+# == Usage
+#
+# Simply run this script.
+#
+#  $ ruby demo_psort.rb
+#
+# == Development information
+#
+# The code was moved from lib/bio/appl/psort.rb.
+#
+
+require 'bio'
+
+#if __FILE__ == $0
+
+  #begin
+  #  require 'psort/report.rb'
+  #rescue LoadError
+  #end
+
+
+  seq = ">hoge mit
+MALEPIDYTT RDEDDLDENE LLMKISNAAG SSRVNDNNDD LTFVENDKII 
+ARYSIQTSSK QQGKASTPPV EEAEEAAPQL PSRSSAAPPP PPRRATPEKK 
+DVKDLKSKFE GLAASEKEEE EMENKFAPPP KKSEPTIISP KPFSKPQEPV
+FKGYHVQVTA HSREIDAEYL KIVRGSDPDT TWLIISPNAK KEYEPESTGS 
+KKSFTPSKSP APVSKKEPVK TPSPAPAAKI PKENPWATAE YDYDAAEDNE
+NIEFVDDDWW LGELEKDGSK GLFPSNYVSL LPSRNVASGA PVQKEEPEQE 
+SFHDFLQLFD ETKVQYGLAR RKAKQNSGNA ETKAEAPKPE VPEDEPEGEP
+DDWNEPELKE RDFDQAPLKP NQSSYKPIGK IDLQKVIAEE KAKEDPRLVQ
+DYKKIGNPLP GMHIEADNEE EPEENDDDWD DDEDEAAQPP ANFAAVANNL 
+KPTAAGSKID DDKVIKGFRN EKSPAQLWAE VSPPGSDVEK IIIIGWCPDS 
+APLKTRASFA PSSDIANLKN ESKLKRDSEF NSFLGTTKPP SMTESSLKND
+KAEEAEQPKT EIAPSLPSRN SIPAPKQEEA PEQAPEEEIE GN
+"
+  Seq1 = ">hgoe
+LTFVENDKII NI
+"
+
+  puts "\n Bio::PSORT::PSORT"
+  
+  puts "\n ==> p serv = Bio::PSORT::PSORT.imsut"
+  p serv = Bio::PSORT::PSORT1.imsut
+
+  puts "\n ==> p serv.class "  
+  p serv.class
+
+  puts "\n ==> p serv.title = 'Query_title_splited_by_white space'"
+  p serv.title = 'Query_title_splited_by_white space'
+
+  puts "\n ==> p serv.exec(seq, false) "  
+  p serv.exec(seq, false)
+
+  puts "\n ==> p serv.exec(seq) "  
+  p serv.exec(seq)
+
+  puts "\n ==> p report = serv.exec(Bio::FastaFormat.new(seq)) "  
+  p report = serv.exec(Bio::FastaFormat.new(seq))
+
+  puts "\n ==> p report.class"
+  p report.class
+
+
+  puts "\n ==> p report_raw = serv.exec(Bio::FastaFormat.new(seq), false) "  
+  p report_raw = serv.exec(Bio::FastaFormat.new(seq), false)
+
+  puts "\n ==> p report_raw.class"
+  p report_raw.class
+
+
+  puts "\n ==> p report.methods" 
+  p report.methods
+
+  methods = ['entry_id', 'origin', 'title', 'sequence','result_info',
+             'reasoning', 'final_result', 'raw']
+  methods.each do |method|
+    puts "\n ==> p report.#{method}"
+    p eval("report.#{method}")
+  end
+
+
+
+  puts "\n Bio::PSORT::PSORT2"
+
+  puts "\n ==> p serv = Bio::PSORT::PSORT2.imsut"
+  p serv = Bio::PSORT::PSORT2.imsut
+
+  puts "\n ==> p serv.class "
+  p serv.class
+
+  puts "\n ==> p seq "
+  p seq
+
+  puts "\n ==> p serv.title = 'Query_title_splited_by_white space'"
+  p serv.title = 'Query_title_splited_by_white space'
+
+  puts "\n ==> p serv.exec(seq) # parsed report" 
+  p serv.exec(seq)
+
+  puts "\n ==> p report = serv.exec(Bio::FastaFormat.new(seq)) # parsed report" 
+  p report = serv.exec(Bio::FastaFormat.new(seq))
+
+
+
+  puts "\n ==> p serv.exec(seq, false) # report in plain text"
+  p serv.exec(seq, false)
+
+  puts "\n ==> p report_raw = serv.exec(Bio::FastaFormat.new(seq), false) # report in plain text"
+  p report_raw = serv.exec(Bio::FastaFormat.new(seq), false)
+
+
+  puts "\n ==> p report.methods"
+  p report.methods
+
+  methods = ['entry_id', 'scl', 'definition', 'seq', 'features', 'prob', 'pred', 'k', 'raw']
+  methods.each do |method|
+    puts "\n ==> p report.#{method}"
+    p eval("report.#{method}")
+  end
+
+#end

data/sample/demo_psort_report.rb

@@ -0,0 +1,70 @@
+#
+# = sample/demo_psort_report.rb - demonstration of Bio::PSORT::PSORT2::Report
+#
+# Copyright::   Copyright (C) 2003 
+#               Mitsuteru C. Nakao <n@bioruby.org>
+# License::     The Ruby License
+#
+#
+# == IMPORTANT NOTE
+#
+# The sample may not work because it has not been tested for a long time.
+#
+# == Description
+#
+# Demonstration of Bio::PSORT::PSORT2::Report, parser class for the PSORT
+# systems output.
+#
+# == Usage
+#
+# Specify a file containing PSORT2 output.
+#
+#  $ ruby demo_psort_report.rb
+#
+# == Development information
+#
+# The code was moved from lib/bio/appl/psort/report.rb.
+#
+
+require 'bio'
+
+# testing code
+
+#if __FILE__ == $0
+
+
+  while entry = $<.gets(Bio::PSORT::PSORT2::Report::DELIMITER)
+
+    puts "\n ==> a = Bio::PSORT::PSORT2::Report.parser(entry)"
+    a = Bio::PSORT::PSORT2::Report.parser(entry)
+
+    puts "\n ==> a.entry_id "
+    p a.entry_id
+    puts "\n ==> a.scl "
+    p a.scl
+    puts "\n ==> a.pred "
+    p a.pred
+    puts "\n ==> a.prob "
+    p a.prob
+    p a.prob.keys.sort.map {|k| k.rjust(4)}.inspect.gsub('"','')
+    p a.prob.keys.sort.map {|k| a.prob[k].to_s.rjust(4) }.inspect.gsub('"','')
+
+    puts "\n ==> a.k "
+    p a.k
+    puts "\n ==> a.definition"
+    p a.definition
+    puts "\n ==> a.seq"
+    p a.seq
+
+    puts "\n ==> a.features.keys.sort "
+    p a.features.keys.sort
+
+    a.features.keys.sort.each do |key|
+      puts "\n ==> a.features['#{key}'] "
+      puts a.features[key]
+    end
+
+    
+  end
+
+#end

data/sample/demo_pubmed.rb

@@ -0,0 +1,118 @@
+#
+# = sample/demo_pubmed.rb - demonstration of Bio::PubMed
+#
+# Copyright::  Copyright (C) 2001, 2007, 2008 Toshiaki Katayama <k@bioruby.org>
+# Copyright::  Copyright (C) 2006 Jan Aerts <jan.aerts@bbsrc.ac.uk>
+# License::    The Ruby License
+#
+#
+# == Description
+#
+# Demonstration of Bio::PubMed, NCBI Entrez/PubMed client module.
+#
+# == Requirements
+#
+# Internet connection is needed.
+#
+# == Usage
+#
+# Simply run this script.
+#
+#  $ ruby demo_pubmed.rb
+#
+# == Development information
+#
+# The code was moved from lib/bio/io/pubmed.rb and modified as below:
+# * Codes using Entrez CGI are disabled.
+
+require 'bio'
+
+Bio::NCBI.default_email = 'staff@bioruby.org'
+
+#if __FILE__ == $0
+
+  puts "=== instance methods ==="
+
+  pubmed = Bio::PubMed.new
+
+  puts "--- Search PubMed by E-Utils ---"
+  opts = {"rettype" => "count"}
+  puts Time.now
+  puts pubmed.esearch("(genome AND analysis) OR bioinformatics", opts)
+  puts Time.now
+  puts pubmed.esearch("(genome AND analysis) OR bioinformatics", opts)
+  puts Time.now
+  puts pubmed.esearch("(genome AND analysis) OR bioinformatics", opts)
+  puts Time.now
+  pubmed.esearch("(genome AND analysis) OR bioinformatics").each do |x|
+    puts x
+  end
+
+  puts "--- Retrieve PubMed entry by E-Utils ---"
+  puts Time.now
+  puts pubmed.efetch(16381885)
+  puts Time.now
+  puts pubmed.efetch("16381885")
+  puts Time.now
+  puts pubmed.efetch("16381885")
+  puts Time.now
+  opts = {"retmode" => "xml"}
+  puts pubmed.efetch([10592173, 14693808], opts)
+  puts Time.now
+  puts pubmed.efetch(["10592173", "14693808"], opts)
+
+  #puts "--- Search PubMed by Entrez CGI ---"
+  #pubmed.search("(genome AND analysis) OR bioinformatics").each do |x|
+  #  p x
+  #end
+
+  #puts "--- Retrieve PubMed entry by Entrez CGI ---"
+  #puts pubmed.query("16381885")
+
+
+  puts "--- Retrieve PubMed entry by PMfetch ---"
+  puts pubmed.pmfetch("16381885")
+
+
+  puts "=== class methods ==="
+
+
+  puts "--- Search PubMed by E-Utils ---"
+  opts = {"rettype" => "count"}
+  puts Time.now
+  puts Bio::PubMed.esearch("(genome AND analysis) OR bioinformatics", opts)
+  puts Time.now
+  puts Bio::PubMed.esearch("(genome AND analysis) OR bioinformatics", opts)
+  puts Time.now
+  puts Bio::PubMed.esearch("(genome AND analysis) OR bioinformatics", opts)
+  puts Time.now
+  Bio::PubMed.esearch("(genome AND analysis) OR bioinformatics").each do |x|
+    puts x
+  end
+
+  puts "--- Retrieve PubMed entry by E-Utils ---"
+  puts Time.now
+  puts Bio::PubMed.efetch(16381885)
+  puts Time.now
+  puts Bio::PubMed.efetch("16381885")
+  puts Time.now
+  puts Bio::PubMed.efetch("16381885")
+  puts Time.now
+  opts = {"retmode" => "xml"}
+  puts Bio::PubMed.efetch([10592173, 14693808], opts)
+  puts Time.now
+  puts Bio::PubMed.efetch(["10592173", "14693808"], opts)
+
+  #puts "--- Search PubMed by Entrez CGI ---"
+  #Bio::PubMed.search("(genome AND analysis) OR bioinformatics").each do |x|
+  #  p x
+  #end
+
+  #puts "--- Retrieve PubMed entry by Entrez CGI ---"
+  #puts Bio::PubMed.query("16381885")
+
+
+  puts "--- Retrieve PubMed entry by PMfetch ---"
+  puts Bio::PubMed.pmfetch("16381885")
+
+#end

data/sample/demo_sirna.rb

@@ -0,0 +1,63 @@
+#
+# = sample/demo_sirna.rb - demonstration of Bio::SiRNA
+#
+# Copyright::   Copyright (C) 2004, 2005
+#               Itoshi NIKAIDO <dritoshi@gmail.com>
+# License::     The Ruby License
+#
+#
+# == Description
+#
+# Demonstration of Bio::SiRNA, class for designing small inhibitory RNAs.
+#
+# == Usage
+#
+# Specify files containing nucleotide sequences.
+#
+#  $ ruby demo_sirna.rb files...
+#
+# Example usage using test data:
+#
+#  $ ruby -Ilib sample/demo_sirna.rb test/data/fasta/example1.txt
+#
+# == Development information
+#
+# The code was moved from lib/bio/util/sirna.rb, and modified for reading
+# normal sequence files.
+#
+
+require 'bio'
+
+if ARGV.size <= 0 then
+  puts "Demonstration of designing SiRNA for each sequence."
+  puts "Usage: #{$0} files..."
+  exit(0)
+end
+
+ARGV.each do |filename|
+Bio::FlatFile.foreach(filename) do |entry|
+  puts "##entry.entry_id: #{entry.entry_id}"
+  puts "##entry.definition: #{entry.definition}"
+  seq = entry.naseq
+  puts "##entry.naseq.length: #{seq.length}"
+
+  sirna = Bio::SiRNA.new(seq)
+  pairs = sirna.design # or .design('uitei') or .uitei or .reynolds
+
+  pairs.each do |pair|
+    puts pair.report
+
+    shrna = Bio::SiRNA::ShRNA.new(pair)
+    shrna.design # or .design('BLOCK-iT') or .block_it
+    puts shrna.report
+
+    puts "# as DNA"
+    puts shrna.top_strand.dna
+    puts shrna.bottom_strand.dna
+  end
+
+  puts "=" * 78
+
+end #Bio::FlatFile.foreach
+end #ARGV.each
+