genfrag 0.0.0.1

data/.bnsignore

@@ -0,0 +1,16 @@
+# The list of files that should be ignored by Mr Bones.
+# Lines that start with '#' are comments.
+#
+# A .gitignore file can be used instead by setting it as the ignore
+# file in your Rakefile:
+#
+#   PROJ.ignore_file = '.gitignore'
+#
+# For a project with a C extension, the following would be a good set of
+# exclude patterns (uncomment them if you want to use them):
+# *.[oa]
+# *~
+announcement.txt
+coverage
+doc
+pkg

data/History.txt

@@ -0,0 +1,4 @@
+== 0.1.0 / 2009-02-04
+
+* 1 major enhancement
+  - initialize

data/LICENSE.txt

@@ -0,0 +1,58 @@
+Ruby is copyrighted free software by Yukihiro Matsumoto <matz@netlab.co.jp>.
+You can redistribute it and/or modify it under either the terms of the GPL
+(see COPYING.txt file), or the conditions below:
+
+  1. You may make and give away verbatim copies of the source form of the
+     software without restriction, provided that you duplicate all of the
+     original copyright notices and associated disclaimers.
+
+  2. You may modify your copy of the software in any way, provided that
+     you do at least ONE of the following:
+
+       a) place your modifications in the Public Domain or otherwise
+          make them Freely Available, such as by posting said
+	  modifications to Usenet or an equivalent medium, or by allowing
+	  the author to include your modifications in the software.
+
+       b) use the modified software only within your corporation or
+          organization.
+
+       c) rename any non-standard executables so the names do not conflict
+	  with standard executables, which must also be provided.
+
+       d) make other distribution arrangements with the author.
+
+  3. You may distribute the software in object code or executable
+     form, provided that you do at least ONE of the following:
+
+       a) distribute the executables and library files of the software,
+	  together with instructions (in the manual page or equivalent)
+	  on where to get the original distribution.
+
+       b) accompany the distribution with the machine-readable source of
+	  the software.
+
+       c) give non-standard executables non-standard names, with
+          instructions on where to get the original software distribution.
+
+       d) make other distribution arrangements with the author.
+
+  4. You may modify and include the part of the software into any other
+     software (possibly commercial).  But some files in the distribution
+     are not written by the author, so that they are not under this terms.
+
+     They are gc.c(partly), utils.c(partly), regex.[ch], st.[ch] and some
+     files under the ./missing directory.  See each file for the copying
+     condition.
+
+  5. The scripts and library files supplied as input to or produced as 
+     output from the software do not automatically fall under the
+     copyright of the software, but belong to whomever generated them, 
+     and may be sold commercially, and may be aggregated with this
+     software.
+
+  6. THIS SOFTWARE IS PROVIDED "AS IS" AND WITHOUT ANY EXPRESS OR
+     IMPLIED WARRANTIES, INCLUDING, WITHOUT LIMITATION, THE IMPLIED
+     WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+     PURPOSE.
+

data/README.rdoc

@@ -0,0 +1,40 @@
+Genfrag version 0.0.0.1
+    by Pjotr Prins and Trevor Wennblom
+    http://genfrag.rubyforge.org
+    (the "Rough Draught" release)
+
+
+== DESCRIPTION:
+
+This is a development release. Few features are functional at this time.
+
+Genfrag allows for rapid in-silico searching of fragments cut by
+different restriction enzymes in large nucleotide acid databases,
+followed by matching specificity adapters which allow a further data
+reduction when looking for differential expression of genes and
+markers.
+
+
+== USAGE:
+
+This works
+  genfrag index -f example.fasta --re5 BstYI --re3 MseI
+  genfrag search -f example.fasta --re5 BstYI --re3 MseI --adapter5 tt
+
+
+== REQUIREMENTS:
+
+* bioruby
+* sqlite3-ruby
+
+
+== INSTALL:
+
+* sudo gem install genfrag
+
+
+== LICENSE:
+
+Copyright (c) 2009 Pjotr Prins and Trevor Wennblom
+
+Distributed under the same terms as the Ruby License - see LICENSE.txt

data/Rakefile

@@ -0,0 +1,53 @@
+# Look in the tasks/setup.rb file for the various options that can be
+# configured in this Rakefile. The .rake files in the tasks directory
+# are where the options are used.
+
+begin
+  require 'bones'
+  Bones.setup
+rescue LoadError
+  begin
+    load 'tasks/setup.rb'
+  rescue LoadError
+    raise RuntimeError, '### please install the "bones" gem ###'
+  end
+end
+
+ensure_in_path 'lib'
+require 'genfrag'
+
+#task :default => 'spec:specdoc'
+task :default => 'spec:run'
+
+PROJ.name = 'genfrag'
+PROJ.authors = 'Pjotr Prins and Trevor Wennblom'
+PROJ.email = 'trevor@corevx.com'
+PROJ.url = 'http://genfrag.rubyforge.org'
+PROJ.version = Genfrag::VERSION
+PROJ.release_name = 'Rough Draught'
+PROJ.ruby_opts = %w[-W0]
+PROJ.readme_file = 'README.rdoc'
+PROJ.ignore_file = '.gitignore'
+PROJ.exclude << 'genfrag.gemspec'
+PROJ.exclude << '.git'
+
+PROJ.rubyforge.name = 'genfrag'
+
+PROJ.spec.opts << '--color'
+
+PROJ.gem.extras[:post_install_message] = <<-MSG
+--------------------------------------------
+ Genfrag installed
+   Type 'genfrag -h' for a list of commands
+--------------------------------------------
+MSG
+
+task 'ann:prereqs' do
+  PROJ.name = 'Genfrag'
+end
+
+depend_on 'bioruby'
+depend_on 'rake'
+
+
+# EOF

data/bin/genfrag

@@ -0,0 +1,8 @@
+#!/usr/bin/env ruby
+
+require File.expand_path(
+    File.join(File.dirname(__FILE__), %w[.. lib genfrag]))
+
+Genfrag::App.cli_run ARGV
+
+# EOF

data/lib/genfrag.rb

@@ -0,0 +1,129 @@
+
+module Genfrag
+
+  # :stopdoc:
+  VERSION = '0.0.0.1'
+  LIBPATH = ::File.expand_path(::File.dirname(__FILE__)) + ::File::SEPARATOR
+  PATH = ::File.dirname(LIBPATH) + ::File::SEPARATOR
+  # :startdoc:
+
+  # Returns the version string for the library.
+  #
+  def self.version
+    VERSION
+  end
+
+  # Returns the library path for the module. If any arguments are given,
+  # they will be joined to the end of the libray path using
+  # <tt>File.join</tt>.
+  #
+  def self.libpath( *args )
+    args.empty? ? LIBPATH : ::File.join(LIBPATH, args.flatten)
+  end
+
+  # Returns the lpath for the module. If any arguments are given,
+  # they will be joined to the end of the path using
+  # <tt>File.join</tt>.
+  #
+  def self.path( *args )
+    args.empty? ? PATH : ::File.join(PATH, args.flatten)
+  end
+
+  # Utility method used to require all files ending in .rb that lie in the
+  # directory below this file that has the same name as the filename passed
+  # in. Optionally, a specific _directory_ name can be passed in such that
+  # the _filename_ does not have to be equivalent to the directory.
+  #
+  def self.require_all_libs_relative_to( fname, dir = nil )
+    dir ||= ::File.basename(fname, '.*')
+    search_me = ::File.expand_path(
+        ::File.join(::File.dirname(fname), dir, '**', '*.rb'))
+
+    Dir.glob(search_me).sort.each {|rb| require rb}
+  end
+
+  def self.tracktime verbose=true, f=nil
+  # Info:: Pjotr's shared Ruby modules
+  # Author:: Pjotr Prins
+  # mail:: pjotr.public05@thebird.nl
+  # Copyright:: July 2007
+  # License:: Ruby License
+    begin
+      t1 = Time.now
+      yield
+
+    ensure
+      t2 = Time.now
+      dt = t2 - t1
+      if verbose
+        if f == nil
+          f = $stdout
+        end
+        f.print "\nElapsed time "
+        hours = dt.to_i/3600
+        dt -= hours*3600
+        mins  = dt.to_i/60
+        dt -= mins*60
+        secs  = dt
+        secs = secs.to_i if secs > 25
+        if hours > 0
+          f.print hours.to_i," hours "
+        end
+        if mins > 0
+          f.print mins.to_i," minutes "
+        end
+        f.print secs," seconds\n" 
+      end
+    end
+  end
+  
+# Create a unique filename for the frequency file out of a combination of filenames
+#
+  def self.name_freq_lookup(input_filenames=[],filefasta=nil,filelookup=nil,re5=nil,re3=nil)
+    input_filenames = [] if input_filenames.nil?
+    if filelookup
+      # FIXME used to be gsub! - make sure it still works in code
+      return filelookup.gsub(/\.(db|tdf)$/, '')
+    elsif !input_filenames.empty?
+      if re5 and re3
+        [input_filenames.sort,re5.downcase,re3.downcase,'index'].join('_').gsub(/\//,'x')
+      else
+        raise "re5 or re3 is undefined"
+      end
+    elsif filefasta
+    # construct default name
+      if re5 and re3
+        [name_normalized_fasta(nil,filefasta),re5.downcase,re3.downcase,'index'].join('_').gsub(/\//,'x')
+      else
+        raise "re5 or re3 is undefined"
+      end
+    else
+      raise "--lookup undefined and no default filenames passed"
+    end
+  end
+
+# Create a unique filename out of a combination of filenames
+#
+  def self.name_normalized_fasta(input_filenames=[],filefasta=nil)
+    if filefasta
+      # FIXME used to be gsub! - make sure it still works in code
+      return filefasta.gsub(/\.(db|tdf)$/, '')
+    elsif !input_filenames.empty?
+      return [input_filenames.sort, 'normalized'].join('_').gsub(/\//,'x')
+    else
+      raise "--fasta undefined and no default filenames passed"
+    end
+  end
+
+# Return the name of the adapters file without its extension
+#
+  def self.name_adapters(fileadapters=nil)
+    return nil if !fileadapters
+    return fileadapters.gsub(/\.(db|tdf)$/, '')
+  end
+  
+end  # module Genfrag
+
+Genfrag.require_all_libs_relative_to(__FILE__)
+
+# EOF

data/lib/genfrag/app.rb

@@ -0,0 +1,105 @@
+if ENV['BIORUBY_HOME']
+  $: << File.join(ENV['BIORUBY_HOME'],'lib')
+else
+  require 'rubygems'
+end
+
+begin
+  require 'sqlite3'
+rescue LoadError
+  $stderr.print "Warning: no sqlite installed"
+end
+
+require 'fileutils'
+require 'optparse'
+require 'ostruct'
+require 'bio'
+require 'csv'
+
+
+module Genfrag
+class App
+
+
+  # Create a new instance of App, and run the +genfrag+ application given
+  # the command line _args_.
+  #
+  def self.cli_run( args )
+    self.new.cli_run args
+  end
+
+  # Create a new main instance using _io_ for standard output and _err_ for
+  # error messages.
+  #
+  def initialize( out = STDOUT, err = STDERR )
+    @out = out
+    @err = err
+  end
+
+  # Parse the desired user command and run that command object.
+  #
+  def cli_run( args )
+    cmd_str = args.shift
+    cmd = case cmd_str
+      when 'index';     IndexCommand.new(@out, @err)
+      when 'search';    SearchCommand.new(@out, @err)
+      when 'info';      InfoCommand.new(@out, @err)
+      when nil, '-h', '--help'
+        help
+      when '-V', '--version'
+        @out.puts "Genfrag #{::Genfrag::VERSION}"
+        nil
+      else
+        raise "Unknown command #{cmd_str.inspect}"
+      end
+
+    cmd.cli_run args if cmd
+
+  rescue StandardError => err
+    @err.puts "ERROR:  While executing genfrag ... (#{err.class})"
+    @err.puts "    #{err.to_s}"
+    @err.puts %Q(    #{err.backtrace.join("\n\t")})
+    exit 1
+  end
+
+  # Show the toplevel help message.
+  #
+  def help
+    @out.puts <<-MSG
+
+  GenFrag allows for rapid in-silico searching of fragments cut by
+  different restriction enzymes in large nucleotide acid databases,
+  followed by matching specificity adapters which allow a further data
+  reduction when looking for differential expression of genes and
+  markers.
+    
+  Usage:
+    genfrag -h/--help
+    genfrag -V/--version
+    genfrag command [options] [arguments]
+
+  Examples:
+    genfrag index -f example.fasta --RE5 BstYI --RE3 MseI
+    genfrag search -f example.fasta --RE5 BstYI --RE3 MseI --adapter5 ct
+
+  Commands:
+    genfrag index           initialize the index
+    genfrag search          search FIXME
+    genfrag info            show information about FIXME
+
+  Further Help:
+    Each command has a '--help' option that will provide detailed
+    information for that command.
+
+    http://genfrag.rubyforge.org/
+
+    MSG
+    nil
+  end
+
+end  # class App
+end  # module Genfrag
+
+Genfrag.require_all_libs_relative_to(__FILE__)
+
+# EOF

data/lib/genfrag/app/command.rb

@@ -0,0 +1,145 @@
+
+module Genfrag
+class App
+
+class Command
+
+  attr_accessor :options  # a Hash used by optparse
+  attr_accessor :ops      # an OpenStruct of the options
+
+  def initialize( out = STDOUT, err = STDERR )
+    @out = out
+    @err = err
+    @options = {
+    #  :skeleton_dir => File.join(mrbones_dir, 'data'),
+    #  :with_tasks => false,
+    #  :verbose => false,
+    #  :name => nil,
+    #  :output_dir => nil
+    }
+    @ops = OpenStruct.new
+    #@options[:skeleton_dir] = ::Bones.path('data') unless test(?d, skeleton_dir)
+  end
+
+  def cli_run( args )
+    raise NotImplementedError
+  end
+  
+  def run( args )
+    raise NotImplementedError
+  end
+
+# Print running output when used in command-line mode
+#
+  def cli_p(cli=true, str='')
+    return false if !cli or @ops.quiet
+    @out.puts str
+  end
+
+# Print an error from the command-line options
+#
+  def clierr_p(str)
+    @out.puts
+    @err.puts "Error: #{str}"
+    @out.puts
+    @out.puts opt_parser
+  end
+
+# Define the command-line option available
+#
+  def standard_options
+    {
+      :verbose => ['-v', '--verbose', 'enable verbose output',
+          lambda {
+            options[:verbose] = true
+          }],
+      :tracktime => ['-m', '--tracktime', 'track execution time',
+          lambda {
+            options[:tracktime] = true
+          }],
+      :quiet => ['-q', '--quiet', 'silence output',
+          lambda {
+            options[:quiet] = true
+          }],
+      :indir => ['-i', '--in DIR', String, 'input directory', "(default #{Dir.pwd})",
+          lambda{ |value|
+            options[:indir] = value
+          }],
+      :outdir => ['-o', '--out DIR', String, 'output directory', "(default #{Dir.pwd})",
+          lambda{ |value|
+            options[:outdir] = value
+          }],
+      :re5 => ['-5', '--re5 ENZYME', String, "5' restriction enzyme",
+          lambda { |value|
+            options[:re5] = value
+          }],
+      :re3 => ['-3', '--re3 ENZYME', String, "3' restriction enzyme",
+          lambda { |value|
+            options[:re3] = value
+          }],
+      :sqlite => ['-t', '--sqlite', 'use sqlite', '(default is CSV)',
+          lambda {
+            options[:sqlite] = true
+          }],
+      :filelookup => ['-l', '--lookup FILE', String, "name of the frequency lookup file generated by 'index'",
+          lambda { |value|
+            options[:filelookup] = value
+          }],
+      :filefasta => ['-f', '--fasta FILE', String, 'name of the Fasta sequences file',
+          lambda { |value|
+            options[:filefasta] = value
+          }],
+      :size => ['-s', '--size SIZE', Array, '',
+          lambda { |value|
+            options[:size] = value
+          }],
+          
+      :adapter5 => ['-y', '--adapter5 ADAPTER', String, '',
+          lambda { |value|
+            options[:adapter5] = value
+          }],
+      :adapter3 => ['-z', '--adapter3 ADAPTER', String, '',
+          lambda { |value|
+            options[:adapter3] = value
+          }],
+          
+      :named_adapter5 => ['-b', '--named-adapter5 NAME', String, '',
+          lambda { |value|
+            options[:named_adapter5] = value
+          }],
+      :named_adapter3 => ['-c', '--named-adapter3 NAME', String, '',
+          lambda { |value|
+            options[:named_adapter3] = value
+          }],
+          
+      :adapter5_size => ['-d', '--adapter5-size SIZE', Integer, '',
+          lambda { |value|
+            options[:adapter5_size] = value
+          }],
+      :adapter3_size => ['-e', '--adapter3-size SIZE', Integer, '',
+          lambda { |value|
+            options[:adapter3_size] = value
+          }],
+          
+      :adapter5_sequence => ['-w', '--adapter5-sequence SEQUENCE', String, '',
+          lambda { |value|
+            options[:adapter5_sequence] = value
+          }],
+      :adapter3_sequence => ['-x', '--adapter3-sequence SEQUENCE', String, '',
+          lambda { |value|
+            options[:adapter3_sequence] = value
+          }],
+          
+      :fileadapters => ['-a', '--adapters FILE', String, '',
+          lambda { |value|
+            options[:fileadapters] = value
+          }]
+
+    }
+  end
+
+end  # class Command
+end  # class App
+end  # module Genfrag
+
+# EOF