genecache 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 15de64a20d8f2335e5c101e3d93045ad3a78c6be
+  data.tar.gz: 35c7e5cdb8309c2ac1d1ce775ee8bad258d3128f
+SHA512:
+  metadata.gz: 7e95d8bc1be6881cb5464c70ee6d0c5d7ee41a9bf15bf99d762c283f89f8d6926786030a1ae623fe7cd33036e26b846059b12fbab6f070c37f0b4e63e374f8a4
+  data.tar.gz: 129d3188032666eafa3903ad92092a6bb03f2139c66f7a1537e436bc4f72088fea453598d1819c9af2b6b1af0b01f24b30f16c557185747336a485bad78e207c

data/.gitignore

@@ -0,0 +1,17 @@
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in genecache.gemspec
+gemspec

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2013 Fedor Gusev
+
+MIT License
+
+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 +1,32 @@
+# Genecache
+
+Simple and fast conversion of GENE IDs. Major source of data is http://biodb.jp. Conversion tables are downloaded and stored in local SQLite database for very fast access.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+    gem 'genecache'
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install genecache
+
+## Usage
+
+    require 'genecache'
+
+    GeneCache.convert('hsa', 'ensg_id', 'omim_id', 'ENSG00000142192') # APP 
+    # returns ['104300', '104760', '605714']
+
+## Contributing
+
+1. Fork it
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Add some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create new Pull Request

data/Rakefile

@@ -0,0 +1 @@
+require "bundler/gem_tasks"

data/genecache.gemspec

@@ -0,0 +1,27 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'genecache/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "genecache"
+  spec.version       = Genecache::VERSION
+  spec.authors       = ["Fedor Gusev"]
+  spec.email         = ["gusevfe@gmail.com"]
+  spec.description   = %q{Very simple GENE ID conversion tool with a local SQLite3 DB for caching}
+  spec.summary       = %q{Simple and fast conversion of GENE IDs. Major source of data is http://biodb.jp. Conversion tables are downloaded and stored in local SQLite database for very fast access.}
+  spec.homepage      = ""
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files`.split($/)
+  spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "bundler", "~> 1.3"
+  spec.add_development_dependency "rake"
+  spec.add_development_dependency "rspec"
+
+  spec.add_dependency 'sqlite3'
+  spec.add_dependency 'zipruby'
+end

data/lib/genecache.rb

@@ -0,0 +1,65 @@
+require "genecache/version"
+require 'open-uri'
+require 'zipruby'
+require 'csv'
+require 'tempfile'
+require 'sqlite3'
+require 'logger'
+require 'fileutils'
+
+$log = Logger.new STDERR
+
+# TODO: check we have working sqlite3 executable for fast import of data
+
+class GeneCache
+  def self.db_path
+    FileUtils.mkdir_p ENV['HOME'] + "/.genecache"
+    return ENV['HOME'] + "/.genecache/db.sqlite3"
+  end
+
+  @@db = SQLite3::Database.new GeneCache.db_path
+  @@tables = @@db.execute("SELECT name FROM sqlite_master where type = 'table'")
+
+  def self.convert(species, from, to, id)
+    table = "#{species}_#{from}_#{to}"
+    unless @@tables.include?([table])
+      # TODO: Update table sometimes!
+      self.download!(species, from, to)
+    end
+
+    r = @@db.execute "select #{to} from #{table} where #{from} = '#{id}'"
+    r.flatten
+  end
+
+  def self.download!(species, from, to)
+    table = "#{species}_#{from}_#{to}"
+    $log.info "Downloading table: #{table}"
+    @@db.execute "drop table if exists #{table}"
+    @@db.execute "drop index if exists from_index"
+    @@db.execute "drop index if exists to_index"
+
+    url = "http://biodb.jp/tmp/#{table}.zip"
+    zip_data = open(url).read
+
+    Zip::Archive.open_buffer(zip_data) do |ar|
+      ar.fopen(0) do |f|
+        tmp = Tempfile.new 'biodb'
+        data = f.read.split("\n")
+        header = data.first.split
+        throw "Invalid header!" if header.sort != [from, to].sort
+        @@db.execute "create table #{table} (#{header.first} VARCHAR(255), #{header.last} VARCHAR(255))"
+
+        rest = data[1..-5] * "\n"
+        tmp.write rest
+        tmp.close
+
+        system(%$echo -e ".mode tabs \\n.import #{File.expand_path(tmp.path)} #{table}" | sqlite3 #{self.db_path}$)
+        @@db.execute "create index from_index on #{table} (#{header.first})"
+        @@db.execute "create index to_index on #{table} (#{header.last})"
+      end
+
+      # Update local list of tables
+      @@tables = @@db.execute("SELECT name FROM sqlite_master where type = 'table' and name = '#{table}'")
+    end
+  end
+end

data/lib/genecache/version.rb

@@ -0,0 +1,3 @@
+module Genecache
+  VERSION = "0.0.1"
+end

data/spec/genecache_spec.rb

@@ -0,0 +1,8 @@
+require 'spec_helper'
+
+describe GeneCache do
+  it "does the job" do 
+    r = GeneCache.convert('hsa', 'ensg_id', 'omim_id', 'ENSG00000142192') # APP
+    expect(r.sort).to eq(%w{104300 104760 605714}.sort)
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,8 @@
+require 'rubygems'
+require 'bundler/setup'
+
+require 'genecache' # and any other gems you need
+
+RSpec.configure do |config|
+    # some (optional) config here
+end

metadata

@@ -0,0 +1,129 @@
+--- !ruby/object:Gem::Specification
+name: genecache
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Fedor Gusev
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2013-12-22 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.3'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.3'
+- !ruby/object:Gem::Dependency
+  name: rake
+  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: rspec
+  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: sqlite3
+  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: zipruby
+  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'
+description: Very simple GENE ID conversion tool with a local SQLite3 DB for caching
+email:
+- gusevfe@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- genecache.gemspec
+- lib/genecache.rb
+- lib/genecache/version.rb
+- spec/genecache_spec.rb
+- spec/spec_helper.rb
+homepage: ''
+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: 2.0.2
+signing_key: 
+specification_version: 4
+summary: Simple and fast conversion of GENE IDs. Major source of data is http://biodb.jp.
+  Conversion tables are downloaded and stored in local SQLite database for very fast
+  access.
+test_files:
+- spec/genecache_spec.rb
+- spec/spec_helper.rb
+has_rdoc: