bio-bigbio 0.1.1

data/Gemfile

@@ -0,0 +1,15 @@
+source "http://rubygems.org"
+# Add dependencies required to use your gem here.
+# Example:
+#   gem "activesupport", ">= 2.3.5"
+gem "bio", ">= 1.4.1"
+gem "bio-logger", ">= 0.9.0"
+
+# Add dependencies to develop your gem here.
+# Include everything needed to run rake, tests, features, etc.
+group :development do
+  gem "rspec", "~> 2.3.0"
+  gem "bundler", "~> 1.0.0"
+  gem "jeweler", "~> 1.5.2"
+  gem "rcov", ">= 0"
+end

data/Gemfile.lock

@@ -0,0 +1,34 @@
+GEM
+  remote: http://rubygems.org/
+  specs:
+    bio (1.4.1)
+    bio-logger (0.9.0)
+      log4r (>= 1.1.9)
+    diff-lcs (1.1.2)
+    git (1.2.5)
+    jeweler (1.5.2)
+      bundler (~> 1.0.0)
+      git (>= 1.2.5)
+      rake
+    log4r (1.1.9)
+    rake (0.8.7)
+    rcov (0.9.9)
+    rspec (2.3.0)
+      rspec-core (~> 2.3.0)
+      rspec-expectations (~> 2.3.0)
+      rspec-mocks (~> 2.3.0)
+    rspec-core (2.3.1)
+    rspec-expectations (2.3.0)
+      diff-lcs (~> 1.1.2)
+    rspec-mocks (2.3.0)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  bio (>= 1.4.1)
+  bio-logger (>= 0.9.0)
+  bundler (~> 1.0.0)
+  jeweler (~> 1.5.2)
+  rcov
+  rspec (~> 2.3.0)

data/LICENSE

@@ -0,0 +1,34 @@
+If a license is not specified the code contributed to BioBig defaults to the
+BSD license:
+
+Copyright (c) 2008, 2009 The BioLib Project
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+    * Redistributions of source code must retain the above copyright notice,
+      this list of conditions and the following disclaimer.
+
+    * Redistributions in binary form must reproduce the above copyright notice,
+      this list of conditions and the following disclaimer in the documentation
+      and/or other materials provided with the distribution.
+
+    * Neither the name of the The BioLib Project nor the names of
+      its contributors may be used to endorse or promote products derived from
+      this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
+ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR
+ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
+ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+For more information on opensource software licenses see
+http://www.opensource.org/licenses/bsd-license.php,
+http://www.gnu.org/licenses/gpl.html and http://www.fsf.org/.

data/README.rdoc

@@ -0,0 +1,28 @@
+= BIGBIO
+
+BigBio = BIG DATA for Ruby
+
+BigBio is an initiative to a create high performance libraries for big data
+computing in biology.
+
+BigBio may use BioLib C/C++/D functions for increasing performance and
+reducing memory consumption.
+
+This is an experimental project. If you wish to contribute subscribe
+to the BioRuby and/or BioLib mailing lists.
+
+== Functionality
+
+* BigBio can translate nucleotide sequences to amino acid
+  sequences using an EMBOSS C function, or BioRuby's translator.
+
+* BigBio has an ORF emitter which parses DNA/RNA sequences and emits
+  ORFs between START_STOP or STOP_STOP codons.
+
+* BigBio has a FASTA file emitter, with iterates FASTA files and
+  iterates sequences without loading everything in memory.
+
+== Copyright
+
+Copyright (c) 2011-2012 Pjotr Prins. See LICENSE for further details.
+

data/Rakefile

@@ -0,0 +1,50 @@
+require 'rubygems'
+require 'bundler'
+begin
+  Bundler.setup(:default, :development)
+rescue Bundler::BundlerError => e
+  $stderr.puts e.message
+  $stderr.puts "Run `bundle install` to install missing gems"
+  exit e.status_code
+end
+require 'rake'
+
+require 'jeweler'
+Jeweler::Tasks.new do |gem|
+  # gem is a Gem::Specification... see http://docs.rubygems.org/read/chapter/20 for more options
+  gem.name = "bio-bigbio"
+  gem.homepage = "http://github.com/pjotrp/bioruby-bigbioruby"
+  gem.license = "MIT"
+  gem.summary = %Q{Low memory sequence emitters}
+  gem.description = %Q{Fasta reader, ORF emitter, sequence translation}
+  gem.email = "pjotr.public01@thebird.nl"
+  gem.authors = ["Pjotr Prins"]
+  # Include your dependencies below. Runtime dependencies are required when using your gem,
+  # and development dependencies are only needed for development (ie running rake tasks, tests, etc)
+  #  gem.add_runtime_dependency 'jabber4r', '> 0.1'
+  #  gem.add_development_dependency 'rspec', '> 1.2.3'
+end
+Jeweler::RubygemsDotOrgTasks.new
+
+require 'rspec/core'
+require 'rspec/core/rake_task'
+RSpec::Core::RakeTask.new(:spec) do |spec|
+  spec.pattern = FileList['spec/**/*_spec.rb']
+end
+
+RSpec::Core::RakeTask.new(:rcov) do |spec|
+  spec.pattern = 'spec/**/*_spec.rb'
+  spec.rcov = true
+end
+
+task :default => :spec
+
+require 'rake/rdoctask'
+Rake::RDocTask.new do |rdoc|
+  version = File.exist?('VERSION') ? File.read('VERSION') : ""
+
+  rdoc.rdoc_dir = 'rdoc'
+  rdoc.title = "bio-bigbio #{version}"
+  rdoc.rdoc_files.include('README*')
+  rdoc.rdoc_files.include('lib/**/*.rb')
+end

data/VERSION

@@ -0,0 +1 @@
+0.1.1

data/bin/getorf

@@ -0,0 +1,118 @@
+#! /usr/bin/ruby
+#
+# Predict ORF's from nucleotide sequences using the BigBio predictors. 
+# The input is a fasta file, the output consists of
+# a FASTA amino acid sequence file with matching nucleotide sequences
+# (aa_heuristic.fa and nt_heuristic.fa respectively)
+#
+# You can choose the heuristic on the command line (default stopstop).
+#
+# Author:: Pjotr Prins
+# Copyright:: 2009-2011
+# License:: Ruby License
+#
+# Copyright (C) 2009-2011 Pjotr Prins <pjotr.prins@thebird.nl>
+
+rootpath = File.dirname(File.dirname(__FILE__))
+$: << File.join(rootpath,'lib')
+
+BIGBIO_VERSION = File.new(File.join(rootpath,'VERSION')).read.chomp
+
+USAGE =<<EOM
+  ruby #{__FILE__} [-h stopstop] [--min-size 30] inputfile(s)
+
+  Use --help for more options
+
+EOM
+
+# require 'biolib/emboss'
+require 'bigbio'
+require 'optparse'
+
+$stderr.print "getorf BioRuby BigBio Plugin "+BIGBIO_VERSION+" Copyright (C) 2009-2011 Pjotr Prins <pjotr.prins@thebird.nl>\n\n"
+
+Bio::Log::CLI.logger('stderr')
+Bio::Log::CLI.trace('info')
+
+heuristic = 'stopstop'
+minsize   = 30
+longest_match = false
+
+opts = OptionParser.new() { |opts|
+  opts.on_tail("-?", "--help", "Print this message") {
+    print(USAGE)
+    print(opts)
+    print <<EXAMPLE
+   
+EXAMPLE
+    exit()
+  }
+   
+  opts.on("-h heuristic", String, "Heuristic (stopstop)") do | s |
+    heuristic = s
+  end
+  opts.on("-s size", "--min-size", Integer, "Minimal sequence size") do | n |
+    minsize = n
+  end
+  opts.on("--longest", "Only get longest ORF match") do 
+    longest_match = true
+  end
+
+  opts.on("--logger filename",String,"Log to file (default stderr)") do | name |
+    Bio::Log::CLI.logger(name)
+  end
+
+  opts.on("--trace options",String,"Set log level (default INFO, see bio-logger)
+") do | s |
+    Bio::Log::CLI.trace(s)
+  end
+
+  opts.on("-q", "--quiet", "Run quietly") do |q|
+    Bio::Log::CLI.trace('error')
+  end
+
+  opts.on("-v", "--verbose", "Run verbosely") do |v|
+    Bio::Log::CLI.trace('info')
+  end
+
+  opts.on("--debug", "Show debug messages") do |v|
+    Bio::Log::CLI.trace('debug')
+    options.debug = true
+  end
+}
+opts.parse!(ARGV)
+if ARGV.size == 0
+  print USAGE
+  exit 1
+end
+
+Bio::Log::CLI.configure('bigbio')
+
+# print "Heuristic is #{heuristic}\n"
+# print "Minsize #{minsize}\n"
+
+ARGV.each do | fn |
+  raise "File #{fn} does not exist" if !File.exist?(fn)
+  nt = Bio::Big::FastaEmitter.new(fn)
+
+  include Bio::Big::TranslationAdapter
+  trn_table = Bio::Big::TranslationAdapter.translation_table(1)
+
+  id = 0
+  nt.emit_seq do | where, location, tag, seq |
+    id += 1
+    # p [where, location, tag, seq]
+    predict = PredictORF.new(id,tag,seq,trn_table)
+    orflist = predict.send(heuristic,minsize)
+    orflist.each do | orf |
+      print '>',orf.descr,"\n"
+      print orf.nt.to_s,"\n"
+      # p orf
+    end
+  end
+end
+
+
+
+
+

data/bin/nt2aa.rb

@@ -0,0 +1,56 @@
+#! /usr/bin/ruby
+#
+# Translate nucleotide sequences into aminoacids sequences in all 
+# reading frames.
+#
+#
+# (: pjotrp 2009, 2012 rblicense :)
+#
+# Copyright (C) 2012 Pjotr Prins <pjotr.prins@thebird.nl> 
+
+USAGE =<<EOM
+  ruby #{__FILE__} [--six-frame] inputfile(s)
+EOM
+
+$: << File.dirname(__FILE__)+'/../lib'
+
+require 'bigbio'
+
+if ARGV.size < 1
+  print USAGE
+  exit 1
+end
+
+do_sixframes = false
+frames = [1]
+if ARGV[0] == '--six-frame'
+  ARGV.shift!
+  do_sixframes = true
+  frames = [-3,-2,-1,1,2,3]
+end
+
+require 'bigbio/adapters/translate'
+
+ARGV.each do | fn |
+  raise "File #{fn} does not exist" if !File.exist?(fn)
+  nt = FastaReader.new(fn)
+  trn_table = Bio::Big::TranslationAdapter.translation_table(1)
+  
+  nt.each { | rec |
+      ajpseq   = Bio::Big::TranslationAdapter.pre_translate(rec.seq,"Test sequence")
+
+      frames.each do | frame |
+        aa  = Bio::Big::TranslationAdapter.translate(trn_table,frame, rec.seq, ajpseq)
+
+        # ajpseqt  = Biolib::Emboss.ajTrnSeqOrig(trnTable,ajpseq,frame)
+        # aa       = Biolib::Emboss.ajSeqGetSeqCopyC(ajpseqt)
+        print "> ",rec.descr," [",frame.to_s,"]\n"
+        print aa,"\n"
+    end
+  }
+end
+
+
+
+
+

data/bio-bigbio.gemspec

@@ -0,0 +1,102 @@
+# Generated by jeweler
+# DO NOT EDIT THIS FILE DIRECTLY
+# Instead, edit Jeweler::Tasks in Rakefile, and run 'rake gemspec'
+# -*- encoding: utf-8 -*-
+
+Gem::Specification.new do |s|
+  s.name = "bio-bigbio"
+  s.version = "0.1.1"
+
+  s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
+  s.authors = ["Pjotr Prins"]
+  s.date = "2012-01-30"
+  s.description = "Fasta reader, ORF emitter, sequence translation"
+  s.email = "pjotr.public01@thebird.nl"
+  s.executables = ["getorf", "nt2aa.rb"]
+  s.extra_rdoc_files = [
+    "LICENSE",
+    "README.rdoc"
+  ]
+  s.files = [
+    "Gemfile",
+    "Gemfile.lock",
+    "LICENSE",
+    "README.rdoc",
+    "Rakefile",
+    "VERSION",
+    "bin/getorf",
+    "bin/nt2aa.rb",
+    "bio-bigbio.gemspec",
+    "doc/bigbio_getorf.wtex",
+    "lib/bigbio.rb",
+    "lib/bigbio/adapters/translate.rb",
+    "lib/bigbio/db/blast.rb",
+    "lib/bigbio/db/blast/blastclust.rb",
+    "lib/bigbio/db/emitters/fasta_emitter.rb",
+    "lib/bigbio/db/emitters/orf_emitter.rb",
+    "lib/bigbio/db/fasta.rb",
+    "lib/bigbio/db/fasta/fastaindex.rb",
+    "lib/bigbio/db/fasta/fastapairedreader.rb",
+    "lib/bigbio/db/fasta/fastapairedwriter.rb",
+    "lib/bigbio/db/fasta/fastareader.rb",
+    "lib/bigbio/db/fasta/fastarecord.rb",
+    "lib/bigbio/db/fasta/fastawriter.rb",
+    "lib/bigbio/db/fasta/indexer.rb",
+    "lib/bigbio/environment.rb",
+    "lib/bigbio/sequence/predictorf.rb",
+    "lib/bigbio/sequence/translate.rb",
+    "spec/emitter_spec.rb",
+    "spec/predictorf_spec.rb",
+    "test/data/EMBOSS/EGC.1",
+    "test/data/fasta/nt.fa",
+    "test/doctest/test_fasta.rb",
+    "test/doctest/test_frames.rb",
+    "test/doctest/test_getorf.rb",
+    "test/doctest/test_paired.rb",
+    "test/performance/translate_with_biolib.rb",
+    "test/performance/translate_with_bioruby.rb"
+  ]
+  s.homepage = "http://github.com/pjotrp/bioruby-bigbioruby"
+  s.licenses = ["MIT"]
+  s.require_paths = ["lib"]
+  s.rubygems_version = "1.8.10"
+  s.summary = "Low memory sequence emitters"
+  s.test_files = [
+    "spec/emitter_spec.rb",
+    "spec/predictorf_spec.rb",
+    "test/doctest/test_fasta.rb",
+    "test/doctest/test_frames.rb",
+    "test/doctest/test_getorf.rb",
+    "test/doctest/test_paired.rb",
+    "test/performance/translate_with_biolib.rb",
+    "test/performance/translate_with_bioruby.rb"
+  ]
+
+  if s.respond_to? :specification_version then
+    s.specification_version = 3
+
+    if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
+      s.add_runtime_dependency(%q<bio>, [">= 1.4.1"])
+      s.add_runtime_dependency(%q<bio-logger>, [">= 0.9.0"])
+      s.add_development_dependency(%q<rspec>, ["~> 2.3.0"])
+      s.add_development_dependency(%q<bundler>, ["~> 1.0.0"])
+      s.add_development_dependency(%q<jeweler>, ["~> 1.5.2"])
+      s.add_development_dependency(%q<rcov>, [">= 0"])
+    else
+      s.add_dependency(%q<bio>, [">= 1.4.1"])
+      s.add_dependency(%q<bio-logger>, [">= 0.9.0"])
+      s.add_dependency(%q<rspec>, ["~> 2.3.0"])
+      s.add_dependency(%q<bundler>, ["~> 1.0.0"])
+      s.add_dependency(%q<jeweler>, ["~> 1.5.2"])
+      s.add_dependency(%q<rcov>, [">= 0"])
+    end
+  else
+    s.add_dependency(%q<bio>, [">= 1.4.1"])
+    s.add_dependency(%q<bio-logger>, [">= 0.9.0"])
+    s.add_dependency(%q<rspec>, ["~> 2.3.0"])
+    s.add_dependency(%q<bundler>, ["~> 1.0.0"])
+    s.add_dependency(%q<jeweler>, ["~> 1.5.2"])
+    s.add_dependency(%q<rcov>, [">= 0"])
+  end
+end
+

data/doc/bigbio_getorf.wtex

@@ -0,0 +1,14 @@
+
+== ORF Prediction ==
+
+The ORF 'predictor' is of the simple kind. It detects ORFs by
+identifying start and stop signals in the same frame.
+
+The main feature is that it does not consume real memory through the
+use of a Sequence 'emitter', which scans a large input sequence and
+yields open reading frames from STOP to STOP codon, with adjoining
+nucleotides. This allows scanning the sequence in a *single* pass.
+
+The input file maybe Fasta, as long as the reader yields chunks of
+sequence data.
+

data/lib/bigbio/adapters/translate.rb

@@ -0,0 +1,64 @@
+# TranslationAdapter will translate using EMBOSS, or BioRuby
+# when the first is not available
+
+module Bio
+  module Big
+    module TranslationAdapter
+
+      VALID_FRAME_VALUES = [ 0, -1, -2, -3, 1, 2, 3 ]
+
+      def self.translation_table num
+        if Environment.instance.biolib
+          Biolib::Emboss.ajTrnNewI(num)
+        end
+      end
+
+      # Precompile sequence for EMBOSS
+      def self.pre_translate seq,label
+        if Environment.instance.biolib
+          Biolib::Emboss.ajSeqNewNameC(seq,"Test sequence")
+        else
+          nil
+        end
+      end
+
+      # Translate using frame (pre_seq is only used for EMBOSS)
+      # 
+      # Valid frame values are 0,1,2,3 and -1,-2,-3, where 0 and 1 are the
+      # standard reading frame. The negative values translate the reverse
+      # complement of the strand.
+      def self.translate trn_table, frame, seq, pre_seq = nil
+        raise "Illegal frame #{frame}" if VALID_FRAME_VALUES.index(frame) == nil
+        frame = 1 if frame == 0
+        if Environment.instance.biolib
+          # Using EMBOSS for translation
+          ajpseq = pre_seq
+          if not pre_seq
+            ajpseq = Biolib::Emboss.ajSeqNewNameC(seq,"Test sequence")
+          end
+          ajpseqt  = Biolib::Emboss.ajTrnSeqOrig(trn_table,ajpseq,frame)
+          Biolib::Emboss.ajSeqGetSeqCopyC(ajpseqt)
+        else
+          # Using BioRuby for translation
+          ntseq = if frame > 0 
+            Bio::Sequence::NA.new(seq[frame-1..-1])
+          else
+            # This to match EMBOSS frames
+            rframe =
+              case frame
+                when -2 
+                  -3 
+                when -3
+                  -2
+                else 
+                  -1
+              end
+            Bio::Sequence::NA.new(seq[0..rframe]).reverse_complement
+          end
+          # pp ntseq
+          ntseq.translate.to_s
+        end
+      end
+    end
+  end
+end

data/lib/bigbio/db/blast/blastclust.rb

@@ -0,0 +1,16 @@
+# Parse BLAST cluster file
+#
+
+class BlastClust
+
+  def initialize fn
+    @fn = fn
+  end
+
+  def each
+    File.new(@fn).each_line do | line |
+      yield line.split
+    end
+  end
+
+end

data/lib/bigbio/db/blast.rb

@@ -0,0 +1,2 @@
+require 'bigbio/db/blast/blastclust'
+

data/lib/bigbio/db/emitters/fasta_emitter.rb

@@ -0,0 +1,48 @@
+
+module Bio
+  module Big
+    class FastaEmitter
+
+      def initialize fn, max_size = 100000
+        @fn = fn
+        @max_size = max_size
+      end
+
+      # Yield sequence information in sections of a maximum
+      # size - usually iterators load the full sequence, but
+      # without penalty it is possible to use a lot less 
+      # memory.
+      def emit_seq 
+        f = File.open(@fn)
+        tag = tag_digest(f.gets.strip)
+        seq = ""
+        index = 0
+        begin
+          line = f.gets.strip
+          if line =~ /^>/
+            yield :tail,index,tag,seq
+            tag = tag_digest(line)
+            seq = ""
+            index += 1
+          else
+            seq += line
+          end
+          while seq.size > @max_size
+            yield :mid,index,tag,seq[0..@max_size-1]
+            seq = seq[@max_size..-1]
+          end
+        end while !f.eof
+        yield :tail,index,tag,seq
+      end
+
+      def tag_digest tag 
+        if tag[0..0] == '>'
+          tag[1..-1]
+        else
+          raise "Tag error in '#{tag}'"
+        end
+      end
+    end
+
+  end # Big
+end # Bio