bio-polymarker_db_batch 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: ee5ff333221f066ab5de033a6344672cf152b587
+  data.tar.gz: 9a940c4c6f79cff4877cc43b70572ce405ad02fe
+SHA512:
+  metadata.gz: feb868e237d4ec8759a563df9d89abb4a8b123c419edd43833a8c3115b3a37b7a3ecd5b329d88980f3c91afa1ae0112005b048760263a9a58da22e8756378e08
+  data.tar.gz: 163c4fc4b2943988a1003cbd3b4855900abe09b06c2d7a65d2b45e6b762c2ae17b1f09fd97ca1ad08b6c0be68ec3de2802d2019d206ee63152f99826f13f0155

data/.document

@@ -0,0 +1,5 @@
+lib/**/*.rb
+bin/*
+- 
+features/**/*.feature
+LICENSE.txt

data/.travis.yml

@@ -0,0 +1,13 @@
+language: ruby
+rvm:
+  - 1.9.2
+  - 1.9.3
+  - jruby-19mode # JRuby in 1.9 mode
+
+# - rbx-19mode
+#  - 1.8.7
+#  - jruby-18mode # JRuby in 1.8 mode
+#  - rbx-18mode
+
+# uncomment this line if your project needs to run something other than `rake`:
+# script: bundle exec rspec spec

data/Gemfile

@@ -0,0 +1,17 @@
+source "http://rubygems.org"
+# Add dependencies required to use your gem here.
+# Example:
+#   gem "activesupport", ">= 2.3.5"
+gem "bio-polyploid-tools"
+gem "mysql"
+
+# Add dependencies to develop your gem here.
+# Include everything needed to run rake, tests, features, etc.
+group :development do
+  gem "shoulda", ">= 0"
+  gem "rdoc", "~> 3.12"
+  gem "simplecov", ">= 0"
+  gem "jeweler", "~> 2", :git => "https://github.com/technicalpickles/jeweler.git"
+  gem "bundler", ">= 1.0.21"
+  gem "bio", ">= 1.4.2"
+end

data/LICENSE.txt

@@ -0,0 +1,20 @@
+Copyright (c) 2014 homonecloco
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.md

@@ -0,0 +1,47 @@
+# bio-polymarker_db_batch
+
+[![Build Status](https://secure.travis-ci.org/homonecloco/bioruby-polymarker_db_batch.png)](http://travis-ci.org/homonecloco/bioruby-polymarker_db_batch)
+
+Full description goes here
+
+Note: this software is under active development!
+
+## Installation
+
+```sh
+gem install bio-polymarker_db_batch
+```
+
+## Usage
+
+```ruby
+require 'bio-polymarker_db_batch'
+```
+
+The API doc is online. For more code examples see the test files in
+the source tree.
+        
+## Project home page
+
+Information on the source tree, documentation, examples, issues and
+how to contribute, see
+
+  http://github.com/homonecloco/bioruby-polymarker_db_batch
+
+The BioRuby community is on IRC server: irc.freenode.org, channel: #bioruby.
+
+## Cite
+
+If you use this software, please cite one of
+  
+* [BioRuby: bioinformatics software for the Ruby programming language](http://dx.doi.org/10.1093/bioinformatics/btq475)
+* [Biogem: an effective tool-based approach for scaling up open source software development in bioinformatics](http://dx.doi.org/10.1093/bioinformatics/bts080)
+
+## Biogems.info
+
+This Biogem is published at (http://biogems.info/index.html#bio-polymarker_db_batch)
+
+## Copyright
+
+Copyright (c) 2014 homonecloco. See LICENSE.txt for further details.
+

data/README.rdoc

@@ -0,0 +1,48 @@
+= bio-polymarker_db_batch
+
+{<img
+src="https://secure.travis-ci.org/homonecloco/bioruby-polymarker_db_batch.png"
+/>}[http://travis-ci.org/#!/homonecloco/bioruby-polymarker_db_batch]
+
+Full description goes here
+
+Note: this software is under active development!
+
+== Installation
+
+        gem install bio-polymarker_db_batch
+
+== Usage
+
+== Developers
+
+To use the library 
+
+        require 'bio-polymarker_db_batch'
+
+The API doc is online. For more code examples see also the test files in
+the source tree.
+        
+== Project home page
+
+Information on the source tree, documentation, issues and how to contribute, see
+
+  http://github.com/homonecloco/bioruby-polymarker_db_batch
+
+The BioRuby community is on IRC server: irc.freenode.org, channel: #bioruby.
+
+== Cite
+
+  If you use this software, please cite one of
+ 
+* [BioRuby: bioinformatics software for the Ruby programming language](http://dx.doi.org/10.1093/bioinformatics/btq475)
+* [Biogem: an effective tool-based approach for scaling up open source software development in bioinformatics](http://dx.doi.org/10.1093/bioinformatics/bts080)
+
+== Biogems.info
+
+This Biogem is published at http://biogems.info/index.html#bio-polymarker_db_batch
+
+== Copyright
+
+Copyright (c) 2014 homonecloco. See LICENSE.txt for further details.
+

data/Rakefile

@@ -0,0 +1,51 @@
+ # encoding: utf-8
+
+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://guides.rubygems.org/specification-reference/ for more options
+  gem.name = "bio-polymarker_db_batch"
+  gem.homepage = "http://github.com/homonecloco/bioruby-polymarker_db_batch"
+  gem.license = "MIT"
+  gem.summary = %Q{Server for polymarker. To be used with cron}
+  gem.description = %Q{Server for polymarker. To be used with cron}
+  gem.email = "ricardo.ramirez-gonzalez@tgac.ac.uk"
+  gem.authors = ["Ricardo H.  Ramirez-Gonzalez"]
+  # dependencies defined in Gemfile
+end
+Jeweler::RubygemsDotOrgTasks.new
+
+require 'rake/testtask'
+Rake::TestTask.new(:test) do |test|
+  test.libs << 'lib' << 'test'
+  test.pattern = 'test/**/test_*.rb'
+  test.verbose = true
+end
+
+desc "Code coverage detail"
+task :simplecov do
+  ENV['COVERAGE'] = "true"
+  Rake::Task['test'].execute
+end
+
+task :default => :test
+
+require 'rdoc/task'
+Rake::RDocTask.new do |rdoc|
+  version = File.exist?('VERSION') ? File.read('VERSION') : ""
+
+  rdoc.rdoc_dir = 'rdoc'
+  rdoc.title = "bio-polymarker_db_batch #{version}"
+  rdoc.rdoc_files.include('README*')
+  rdoc.rdoc_files.include('lib/**/*.rb')
+end

data/VERSION

@@ -0,0 +1 @@
+0.1.0

data/bin/monitor_running_polymarker.rb

@@ -0,0 +1,41 @@
+#!/usr/bin/env ruby
+require 'bioruby-polyploid-tools'
+require 'optparse'
+require 'mysql'
+$: << File.expand_path(File.dirname(__FILE__) + '/../lib')
+$: << File.expand_path('.')
+path=File.expand_path(File.dirname(__FILE__) + '/../lib/bio-polymarker_db_batch.rb')
+#$stderr.puts "Loading: #{path}"
+require path
+
+options = {}
+
+
+OptionParser.new do |opts|
+  opts.banner = "Usage: run_pending_polymarker.rb [options]"
+  
+  opts.on("-p", "--preferences FILE" "File with the preferences") do |o|
+     options[:preferences] = o
+   end
+      
+end.parse!
+
+pol=Bio::DB::Polymarker.new(options[:preferences])
+
+
+pol.mysql_version
+pol.each_running do |row|
+  puts row.join(",")
+  puts row.inspect
+  pol.review_running_status(row[0], row[1])
+#  pol.write_output_file_and_execute(row[0], row[1]);
+#  pol.each_snp_in_file(row[0]) do |snp|
+ #    puts snp.inspect
+     
+  #    pol.
+   #end
+  
+end
+
+
+

data/bin/run_pending_polymarker.rb

@@ -0,0 +1,41 @@
+#!/usr/bin/env ruby
+require 'bioruby-polyploid-tools'
+require 'optparse'
+require 'mysql'
+$: << File.expand_path(File.dirname(__FILE__) + '/../lib')
+$: << File.expand_path('.')
+path=File.expand_path(File.dirname(__FILE__) + '/../lib/bio-polymarker_db_batch.rb')
+#$stderr.puts "Loading: #{path}"
+require path
+
+options = {}
+
+
+OptionParser.new do |opts|
+  opts.banner = "Usage: run_pending_polymarker.rb [options]"
+  
+  opts.on("-p", "--preferences FILE" "File with the preferences") do |o|
+     options[:preferences] = o
+   end
+      
+end.parse!
+
+pol=Bio::DB::Polymarker.new(options[:preferences])
+
+
+pol.mysql_version
+pol.each_to_run do |row|
+  puts row.join(",")
+  puts row.inspect
+  pol.write_output_file_and_execute(row[0], row[1]);
+#  pol.each_snp_in_file(row[0]) do |snp|
+ #    puts snp.inspect
+     
+  #    pol.
+   #end
+  
+end
+
+
+
+

data/lib/bio-polymarker_db_batch.rb

@@ -0,0 +1,12 @@
+# Please require your code below, respecting the naming conventions in the
+# bioruby directory tree.
+#
+# For example, say you have a plugin named bio-plugin, the only uncommented
+# line in this file would be 
+#
+#   require 'bio/bio-plugin/plugin'
+#
+# In this file only require other files. Avoid other source code.
+
+require 'bio-polymarker_db_batch/polymarker_db_batch.rb'
+

data/lib/bio-polymarker_db_batch/polymarker_db_batch.rb

@@ -0,0 +1,184 @@
+
+class Bio::DB::Polymarker
+
+
+  def initialize( props)
+    @properties =Hash[*File.read(props).split(/[=\n]+/)]
+    puts @properties.inspect
+  end
+
+  def mysql_version
+    con.get_server_info
+  end
+
+  def each_to_run
+    query="SELECT snp_file_id, filename FROM snp_file WHERE status = 'NEW';"
+    ret = 0
+    if block_given?
+      ret = execute_query(query){|row| yield row }
+    else
+      ret = execute_query(query)
+    end
+    ret
+  end
+
+  def each_running
+    query="SELECT snp_file_id, filename FROM snp_file WHERE status NOT IN ('NEW', 'DONE', 'LOADED');"
+    ret = 0
+    if block_given?
+      ret = execute_query(query){|row| yield row }
+    else
+      ret = execute_query(query)
+    end
+    ret
+  end
+
+  def each_snp_in_file(file_id)
+    query="SELECT name, chromosome, sequence FROM snp, snp_file_snp WHERE snp_file_snp.snpList_snpId = snp.snpId AND snp_file_snp.snp_file_snp_file_id = '#{file_id}';"
+    ret = 0
+    puts query
+    if block_given?
+      ret = execute_query(query){|row| yield row }
+    else
+      ret = execute_query(query)
+    end
+    ret
+  end
+
+  def write_output_file_and_execute(file_id, filename)
+    path =@properties["execution_path"]+"/#{file_id}_#{filename}"
+    puts "Writting: #{path}"
+    f=File.open(path, "w")
+
+    each_snp_in_file(file_id) do |row|
+      f.puts(row.join(","))
+    end
+    execute_polymarker(path)
+    update_status(file_id, "SUBMITTED")
+    f.close
+  end
+
+  def execute_polymarker(snp_file)
+    cmd="#{@properties['wrapper_prefix'] } polymarker.rb -m #{snp_file} -o #{snp_file}_out -c #{@properties['path_to_chromosomes']} #{@properties['wrapper_suffix'] }"
+    #polymarker.rb -m 1_GWAS_SNPs.csv -o 1_test -c /Users/ramirezr/Documents/TGAC/references/Triticum_aestivum.IWGSP1.21.dna_rm.genome.fa
+    execute_command(cmd)
+  end
+
+  def update_status(snp_file_id, new_status)
+    raise "Invalid status #{new_status}" unless ["NEW", "SUBMITTED", "RUNNING", "DONE", "ERROR"].include?(new_status)
+    pst = con.prepare "UPDATE snp_file SET status = ? WHERE snp_file_id = ?"
+    pst.execute new_status, snp_file_id
+    con.commit
+  end
+
+  def send_email(to,opts={})
+    opts[:server]      ||= 'localhost'
+    opts[:from]        ||= 'polymarker@tgac.ac.uk'
+    opts[:from_alias]  ||= 'Example Emailer'
+    opts[:subject]     ||= "You need to see this"
+    opts[:body]        ||= "Important stuff!"
+
+    msg = <<END_OF_MESSAGE
+From: #{opts[:from_alias]} <#{opts[:from]}>
+To: <#{to}>
+Subject: #{opts[:subject]}
+
+#{opts[:body]}
+END_OF_MESSAGE
+    Net::SMTP.start(opts[:server]) do |smtp|
+      smtp.send_message msg, opts[:from], to
+    end
+  end
+  
+  def review_running_status(file_id, filename)
+    out_folder=@properties["execution_path"]+"/#{file_id}_#{filename}_out"
+    started=File.exist?(out_folder)
+    done=false
+    
+    if started
+      lines = IO.readlines("#{out_folder}/status.txt")
+    #  puts lines.inspect
+      done = lines.last.split(",").include?("DONE\n") if lines.size > 1
+    end
+    if done 
+      exons_filename="#{out_folder}/exons_genes_and_contigs.fa"
+      output_primers="#{out_folder}/primers.csv"
+      read_file_to_snp_file("mask_fasta", file_id, exons_filename )
+      read_file_to_snp_file("polymarker_output", file_id, output_primers )
+      update_status(file_id, "DONE")
+    elsif started
+      update_status(file_id, "RUNNING")
+    end
+  end
+
+  private
+
+  def read_file_to_snp_file(column, id, filename )
+    pst = con.prepare "UPDATE snp_file SET #{column} = ? WHERE snp_file_id = ?"
+    puts "Reading: #{filename}"
+    text = File.read(filename)
+    pst.execute text, id
+  end
+
+  #TODO:Exception handling
+  def connect
+    @con = Mysql.new @properties["mysql_host"], @properties["mysql_user"], @properties["mysql_pwd"], @properties["mysql_db"]
+    @con.autocommit false
+    return @con
+  end
+  def close
+    @con.close if @con
+    @con = nil
+  end
+
+  def con     #TODO: reconnect if connection lost
+    connect unless @con 
+    @con
+  end
+
+  def execute_query(query)
+    $stderr.puts query if $VERBOSE
+   
+   
+    
+    if query.start_with?( 'SELECT')
+      rs = con.query(query)
+      n_rows = rs.num_rows
+      ret = Array.new unless block_given?
+      n_rows.times do
+        row = rs.fetch_row
+        yield row if block_given?
+        ret << row unless block_given?
+      end
+      close
+      return n_rows unless block_given?
+      return ret
+    end
+    raise "Unsuported query #{query}"
+    
+  end
+
+  def execute_command(command, type=:text, skip_comments=true, comment_char="#", &block)
+    puts "Executing #{command}"
+    stdin, pipe, stderr, wait_thr = Open3.popen3(command)
+    pid = wait_thr[:pid]  # pid of the started process.       
+    if type == :text
+      while (line = pipe.gets)
+        next if skip_comments and line[0] == comment_char
+        yield line.chomp if block_given?
+      end
+    elsif type == :binary
+      while (c = pipe.gets(nil))
+        yield c if block_given?
+      end
+    end
+    exit_status = wait_thr.value  # Process::Status object returned.
+    puts stderr.read 
+    stdin.close
+    pipe.close
+    stderr.close
+    return exit_status
+  end
+
+end
+

data/test/helper.rb

@@ -0,0 +1,34 @@
+require 'simplecov'
+
+module SimpleCov::Configuration
+  def clean_filters
+    @filters = []
+  end
+end
+
+SimpleCov.configure do
+  clean_filters
+  load_adapter 'test_frameworks'
+end
+
+ENV["COVERAGE"] && SimpleCov.start do
+  add_filter "/.rvm/"
+end
+require 'rubygems'
+require 'bundler'
+begin
+  Bundler.setup(:default, :development)
+rescue Bundler::BundlerError => e
+  $stderr.puts e.message
+  $stderr.puts "Run `bundle install` to install missing gems"
+  exit e.status_code
+end
+require 'test/unit'
+require 'shoulda'
+
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
+$LOAD_PATH.unshift(File.dirname(__FILE__))
+require 'bio-polymarker_db_batch'
+
+class Test::Unit::TestCase
+end

data/test/test_bio-polymarker_db_batch.rb

@@ -0,0 +1,7 @@
+require 'helper'
+
+class TestBioPolymarkerDbBatch < Test::Unit::TestCase
+  should "probably rename this file and start testing for real" do
+    flunk "hey buddy, you should probably rename this file and start testing for real"
+  end
+end

metadata

@@ -0,0 +1,174 @@
+--- !ruby/object:Gem::Specification
+name: bio-polymarker_db_batch
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Ricardo H.  Ramirez-Gonzalez
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2014-07-18 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bio-polyploid-tools
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: mysql
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: shoulda
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rdoc
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.12'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.12'
+- !ruby/object:Gem::Dependency
+  name: simplecov
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: jeweler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2'
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.0.21
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.0.21
+- !ruby/object:Gem::Dependency
+  name: bio
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.4.2
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.4.2
+description: Server for polymarker. To be used with cron
+email: ricardo.ramirez-gonzalez@tgac.ac.uk
+executables:
+- monitor_running_polymarker.rb
+- run_pending_polymarker.rb
+extensions: []
+extra_rdoc_files:
+- LICENSE.txt
+- README.md
+- README.rdoc
+files:
+- ".document"
+- ".travis.yml"
+- Gemfile
+- LICENSE.txt
+- README.md
+- README.rdoc
+- Rakefile
+- VERSION
+- bin/monitor_running_polymarker.rb
+- bin/run_pending_polymarker.rb
+- lib/bio-polymarker_db_batch.rb
+- lib/bio-polymarker_db_batch/polymarker_db_batch.rb
+- test/helper.rb
+- test/test_bio-polymarker_db_batch.rb
+homepage: http://github.com/homonecloco/bioruby-polymarker_db_batch
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.2.1
+signing_key: 
+specification_version: 4
+summary: Server for polymarker. To be used with cron
+test_files: []