ms-unimod 0.1.0

data/History

@@ -0,0 +1,5 @@
+== 0.1.0 / 2009-05-28
+
+Initial release with a generator to setup a unimod
+database and a task to calculate peptide masses
+with variable n- and c-term modifications.

data/README

@@ -0,0 +1,35 @@
+= {Ms-Unimod}[http://mspire.rubyforge.org/projects/ms-unimod]
+
+An {Mspire}[http://mspire.rubyforge.org] library for utilizing Unimod[http://www.unimod.org].
+
+== Description
+
+Ms-Unimod allows easy setup of a Unimod database (using Sqlite[http://www.sqlite.org/]) that can be used to calculate the masses of peptides with modifications.
+
+* Lighthouse[http://bahuvrihi.lighthouseapp.com/projects/16692-mspire/tickets]
+* Github[http://github.com/bahuvrihi/ms-unimod/tree/master]
+* {Google Group}[http://groups.google.com/group/mspire-forum]
+
+== Usage
+
+First generate the Unimod database:
+
+  % tap generate unimod_db
+  
+Then use the pepmass task to calculate a peptide mass, with or without n- or c-term modifications:
+
+  % tap run -- pepmass :RPPGFSPFR: --: dump 
+  % tap run -- pepmass Acetyl:RPPGFSPFR:Hydroxyl% --: dump 
+
+== Installation
+
+Ms-Unimod is available as a gem on RubyForge[http://rubyforge.org/projects/mspire].  Use:
+
+  % gem install ms-unimod
+
+== Info 
+
+Copyright (c) 2008-2009, Regents of the University of Colorado.
+Developer:: {Simon Chiang}[http://bahuvrihi.wordpress.com], {Biomolecular Structure Program}[http://biomol.uchsc.edu/], {Hansen Lab}[http://hsc-proteomics.uchsc.edu/hansenlab/] 
+Support:: CU Denver School of Medicine Deans Academic Enrichment Fund
+Licence:: {MIT-Style}[link:files/MIT-LICENSE.html]

data/lib/ms/calc/pepmass.rb

@@ -0,0 +1,85 @@
+require 'molecules/calc'
+require 'sqlite3'
+
+module Ms
+  module Calc
+    # :startdoc::task a peptide mass calculator
+    #
+    # Calculates the mass of a molecule or peptide.  Molecules are entered
+    # as simple or compound formulae; polypeptides can be specified using 
+    # the one-letter residue codes bracketed by semicolons.  The options can
+    # be used to alter the output (precision, mass calculation method etc.) 
+    #
+    #   % tap run -- pepmass H2O --: dump
+    #   18.0106 Da
+    #
+    #   % tap run -- pepmass :RPPGFSPFR: --: dump
+    #   1059.56 Da
+    #
+    # Unimod modifcations may be specified by name at the polypeptide termini,
+    # provided a unimod database is available.  Use '%' signs as in a SQL 
+    # query to shorten the name.  The Unimod generator may be used to generate
+    # a unimod database if needed:
+    #
+    #   % tap generate unimod
+    #   % tap run -- pepmass Acetyl:RPPGFSPFR:Hydroxyl% -p 2 --: dump
+    #   1117.57 Da
+    #
+    # Sequel and sqlite3-ruby must be installed for this feature to work.
+    # 
+    #   * Sequel[http://sequel.rubyforge.org/rdoc/]
+    #   * sqlite3-ruby[http://rubyforge.org/projects/sqlite-ruby/]
+    #  
+    class Pepmass < Molecules::Calc
+      EmpiricalFormula = Molecules::EmpiricalFormula
+      WATER = EmpiricalFormula.parse "H2O"
+
+      config :unimod, 'unimod.sqlite'          # the path to the unimod database
+      
+      # Formulates a query for a modification matching code_name 
+      # for the unimod database.  If the code_name contains a '%'
+      # then the query will use a LIKE syntax, otherwise the 
+      # code_name will be searced for exactly.
+      def mod_query(code_name)
+        # should do a rails-like escape on code_name
+        "SELECT code_name, composition FROM modifications WHERE code_name #{code_name.include?('%') ? 'LIKE' : '='} '#{code_name}'"
+      end
+      
+      # Attempts to find and instantiate an EmpiricalFormula for
+      # a unimod modification matching code_name.
+      def find_mod(code_name)
+        raise ArgumentError, "the unimod database does not exist" unless File.exists?(unimod)
+
+        results = []
+        db = SQLite3::Database.new(unimod)
+        db.execute(mod_query(code_name)) do |row|
+          results << row
+        end
+        db.close
+        
+        case results.length
+        when 1 then EmpiricalFormula.parse_simple(results[0][1])
+        when 0 then raise "could not find modification: #{code_name}"
+        else raise ArgumentError, "multiple modifications found for: '#{code_name}' (#{results.collect {|result| result[0]}.join(', ')})"
+        end
+      end
+      
+      # Parses the formula string into an EmpiricalFormula.
+      # Can be used as a hook for more complicated formulae
+      # in subclases.
+      def parse(formula)
+        EmpiricalFormula.parse(formula) do |str|
+          case str
+          when /^(.*?):([A-Z]+):?(.*)$/
+            peptide = Molecules::Libraries::Polypeptide.new($2) + WATER
+            peptide += find_mod($1) unless $1.to_s.empty? 
+            peptide += find_mod($3) unless $3.to_s.empty?
+            peptide
+          else nil
+          end
+        end
+      end
+    
+    end
+  end
+end

data/lib/ms/generators/unimod_db.rb

@@ -0,0 +1,61 @@
+require 'open-uri'
+require 'sequel'
+require 'hpricot'
+require 'ms/unimod'
+
+module Ms
+  module Generators
+  
+    # :startdoc::generator generate a new unimod database
+    #
+    # Downloads and generates a Unimod database (sqlite):
+    # 
+    #   % tap generate unimod
+    #   % sqlite3 unimod.sqlite
+    #   sqlite> select * from elements;
+    #   1|H|Hydrogen|1.007825035|1.00794
+    #   2|2H|Deuterium|2.014101779|2.014101779
+    #   3|Li|Lithium|7.016003|6.941
+    #   ...
+    #
+    # The database data is downloaded from the unimod website.
+    #
+    # * {website}[http://www.unimod.org]
+    # * {data}[http://www.unimod.org/xml/unimod_tables.xml]
+    #
+    class UnimodDb < Tap::Generator::Base
+      
+      config :uri, "http://www.unimod.org/xml/unimod_tables.xml"  # the update uri
+      
+      def manifest(m, database="unimod.sqlite")
+        m.file database do |db|
+          db.close
+          db = Sequel.sqlite(db.path)
+          
+          log :get, uri
+          doc = Hpricot.XML(open(uri))
+          
+          db.transaction do
+            Ms::Unimod::TABLES.each_pair do |table_name, schema|
+              log :create_table, table_name
+              db.create_table(table_name, &schema)
+              table = db[table_name]
+          
+              rows = doc.search("unimod/#{table_name}/#{table_name}_row")
+              rows.each do |row|
+                attributes = row.attributes
+                record_id = attributes["record_id"]
+            
+                log(:insert, record_id)
+                table.insert(attributes)
+              end
+            end
+          end
+          
+          db.disconnect
+        end
+      end
+      
+    end
+  end
+end

data/lib/ms/unimod.rb

@@ -0,0 +1,147 @@
+module Ms
+  module Unimod
+    TABLES = {}
+    
+    TABLES[:alt_names] = lambda do
+      primary_key :record_id
+      integer :mod_key
+      string  :alt_name
+    end
+    
+    TABLES[:amino_acids] = lambda do
+      primary_key :record_id
+      string  :one_letter
+      string  :three_letter
+      string  :full_name
+      integer :num_H
+      integer :num_C
+      integer :num_N
+      integer :num_O
+      integer :num_S
+    end
+    
+    TABLES[:brick2element] = lambda do
+      primary_key :record_id
+      integer :brick_key
+      string  :element
+      integer :num_element
+    end
+    
+    TABLES[:bricks] = lambda do
+      primary_key :record_id
+      string  :brick
+      string  :full_name
+    end
+    
+    TABLES[:classifications] = lambda do
+      primary_key :record_id
+      string  :classification
+    end
+    
+    TABLES[:elements] = lambda do
+      primary_key :record_id
+      string  :element
+      string  :full_name
+      decimal :mono_mass #, :precision => 12, :scale => 9, :default => 0.0, :null => false
+      decimal :avge_mass #, :precision => 12, :scale => 9, :default => 0.0, :null => false
+    end
+    
+    TABLES[:fragment_comp] = lambda do
+      primary_key :record_id
+      integer :fragments_key
+      string  :brick
+      integer :num_brick
+    end
+    
+    TABLES[:fragments] = lambda do
+      primary_key :record_id
+      integer :mod_key
+    end
+    
+    TABLES[:log] = lambda do
+      primary_key  :record_id
+      datetime :timestamp
+      text     :query
+    end
+    
+    TABLES[:mod2brick] = lambda do
+      primary_key :record_id
+      integer :mod_key
+      string  :brick
+      integer :num_brick
+    end
+    
+    TABLES[:modifications] = lambda do
+      primary_key  :record_id
+      string   :full_name
+      string   :code_name
+      decimal  :mono_mass#,:precision => 12, :scale => 6
+      decimal  :avge_mass#,:precision => 12, :scale => 4
+      string   :composition
+      text     :misc_notes
+      string   :username_of_poster
+      string   :group_of_poster
+      datetime :date_time_posted
+      datetime :date_time_modified
+      string   :ex_code_name
+      integer  :approved
+    end
+    
+    TABLES[:neutral_losses] = lambda do
+      primary_key :record_id
+      integer :spec_key
+      string  :brick
+      integer :num_brick
+    end
+    
+    TABLES[:positions] = lambda do
+      primary_key :record_id
+      string  :position
+    end
+    
+    TABLES[:spec2nl] = lambda do
+      primary_key :record_id
+      integer :spec_key
+      integer :is_pep_nl
+      integer :is_req_pep_nl
+      integer :is_slave_nl
+      decimal :nl_mono_mass#,:precision => 12, :scale => 6
+      decimal :nl_avge_mass#,:precision => 12, :scale => 4
+      string  :nl_composition
+    end
+    
+    TABLES[:specificity] = lambda do
+      primary_key :record_id
+      integer :mod_key
+      string  :one_letter
+      integer :position_key
+      integer :hidden
+      integer :spec_group
+      integer :classifications_key
+      text    :misc_notes
+    end
+    
+    TABLES[:users] = lambda do
+      primary_key :record_id
+      string  :UserName
+      string  :Password
+      string  :GroupID
+      string  :FullName
+      string  :Email
+    end
+    
+    TABLES[:xref_sources] = lambda do
+      primary_key :record_id
+      string  :xref_source
+    end
+    
+    TABLES[:xrefs] = lambda do
+      primary_key :record_id
+      integer :mod_key
+      integer :xref_source_key
+      text    :xref_text
+      string  :xref_url
+    end
+
+  end
+end

metadata

@@ -0,0 +1,93 @@
+--- !ruby/object:Gem::Specification 
+name: ms-unimod
+version: !ruby/object:Gem::Version 
+  version: 0.1.0
+platform: ruby
+authors: 
+- Simon Chiang
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2009-05-28 00:00:00 -06:00
+default_executable: 
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: tap
+  type: :runtime
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 0.17.0
+    version: 
+- !ruby/object:Gem::Dependency 
+  name: sequel
+  type: :runtime
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 3.0.0
+    version: 
+- !ruby/object:Gem::Dependency 
+  name: molecules
+  type: :runtime
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 0.2.0
+    version: 
+description: 
+email: simon.a.chiang@gmail.com
+executables: []
+
+extensions: []
+
+extra_rdoc_files: 
+- History
+- README
+files: 
+- lib/ms/generators/unimod_db.rb
+- lib/ms/unimod.rb
+- lib/ms/calc/pepmass.rb
+- tap.yml
+- History
+- README
+has_rdoc: true
+homepage: http://mspire.rubyforge.org/projects/ms-unimod/
+post_install_message: 
+rdoc_options: 
+- --main
+- README
+- -S
+- -N
+- --title
+- Ms-Unimod
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+requirements: []
+
+rubyforge_project: mspire
+rubygems_version: 1.3.1
+signing_key: 
+specification_version: 2
+summary: Tasks to setup and utilize a Unimod database.
+test_files: []
+