bio 0.7.0

data/lib/bio/db/kegg/reaction.rb

@@ -0,0 +1,97 @@
+#
+# bio/db/kegg/reaction.rb - KEGG REACTION database class
+#
+#   Copyright (C) 2004 KATAYAMA Toshiaki <k@bioruby.org>
+#
+#  This library is free software; you can redistribute it and/or
+#  modify it under the terms of the GNU Lesser General Public
+#  License as published by the Free Software Foundation; either
+#  version 2 of the License, or (at your option) any later version.
+#
+#  This library is distributed in the hope that it will be useful,
+#  but WITHOUT ANY WARRANTY; without even the implied warranty of
+#  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+#  Lesser General Public License for more details.
+#
+#  You should have received a copy of the GNU Lesser General Public
+#  License along with this library; if not, write to the Free Software
+#  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307  USA
+#
+#  $Id: reaction.rb,v 1.3 2005/09/08 01:22:11 k Exp $
+#
+
+require 'bio/db'
+
+module Bio
+
+  class KEGG
+
+    class REACTION < KEGGDB
+
+      DELIMITER	= RS = "\n///\n"
+      TAGSIZE	= 12
+
+      def initialize(entry)
+        super(entry, TAGSIZE)
+      end
+
+      # ENTRY
+      def entry_id
+        field_fetch('ENTRY')
+      end
+
+      # NAME
+      def name
+        field_fetch('NAME') 
+      end
+
+      # DEFINITION
+      def definition
+        field_fetch('DEFINITION')
+      end
+
+      # EQUATION
+      def equation
+        field_fetch('EQUATION')
+      end
+
+      # RPAIR
+      def rpairs
+        unless @data['RPAIR']
+          @data['RPAIR'] = fetch('RPAIR').split(/\s+/)
+        end
+        @data['RPAIR']
+      end
+
+      # PATHWAY
+      def pathways
+        lines_fetch('PATHWAY') 
+      end
+
+      # ENZYME
+      def enzymes
+        unless @data['ENZYME']
+          @data['ENZYME'] = fetch('ENZYME').scan(/\S+/)
+        end
+        @data['ENZYME']
+      end
+
+    end
+
+  end
+
+end
+
+
+if __FILE__ == $0
+  entry = ARGF.read
+  rn = Bio::KEGG::REACTION.new(entry)
+  p rn.entry_id
+  p rn.name
+  p rn.definition
+  p rn.equation
+  p rn.rpairs
+  p rn.pathways
+  p rn.enzymes
+end
+

data/lib/bio/db/litdb.rb

@@ -0,0 +1,131 @@
+#
+# = bio/db/litdb.rb - LITDB database class
+#
+# Copyright::  Copyright (C) 2001 KATAYAMA Toshiaki <k@bioruby.org>
+# License::    LGPL
+#
+#  $Id: litdb.rb,v 0.7 2005/12/18 15:58:41 k Exp $
+#
+# == Description
+#
+#
+# == Example
+# == References
+#
+#--
+#
+#  This library is free software; you can redistribute it and/or
+#  modify it under the terms of the GNU Lesser General Public
+#  License as published by the Free Software Foundation; either
+#  version 2 of the License, or (at your option) any later version.
+#
+#  This library is distributed in the hope that it will be useful,
+#  but WITHOUT ANY WARRANTY; without even the implied warranty of
+#  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+#  Lesser General Public License for more details.
+#
+#  You should have received a copy of the GNU Lesser General Public
+#  License along with this library; if not, write to the Free Software
+#  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307  USA
+#
+#++
+#
+
+require 'bio/db'
+
+module Bio
+
+  # = LITDB class
+  class LITDB < NCBIDB
+
+    # Delimiter
+    DELIMITER = "\nEND\n"
+
+    # Delimiter
+    RS = DELIMITER
+
+    #
+    TAGSIZE = 12
+
+    #
+    def initialize(entry)
+      super(entry, TAGSIZE)
+    end
+
+    # Returns
+    def reference
+      hash = Hash.new('') 
+
+      hash['authors'] = author.split(/;/).map {|x| x.sub(/,/, ', ')}
+      hash['title']   = title 
+      hash['journal'] = journal.gsub(/\./, '. ').strip
+
+      vol = volume.split(/,\s+/)
+      if vol.size > 1
+        hash['volume'] = vol.shift.sub(/Vol\./, '')
+        hash['pages'],
+        hash['year'] = vol.pop.split(' ')
+        hash['issue'] = vol.shift.sub(/No\./, '') unless vol.empty?
+      end
+
+      return Reference.new(hash) 
+    end
+
+    # CODE
+    def entry_id
+      field_fetch('CODE')
+    end
+
+    # TITLE
+    def title
+      field_fetch('TITLE')
+    end
+
+    # FIELD
+    def field
+      field_fetch('FIELD')
+    end
+
+    # JOURNAL
+    def journal
+      field_fetch('JOURNAL')
+    end
+
+    # VOLUME
+    def volume
+      field_fetch('VOLUME')
+    end
+
+    # KEYWORD ';;'
+    def keyword
+      unless @data['KEYWORD']
+        @data['KEYWORD'] = fetch('KEYWORD').split(/;;\s*/)
+      end
+      @data['KEYWORD']
+    end
+
+    # AUTHOR
+    def author
+      field_fetch('AUTHOR')
+    end
+
+  end
+
+end
+
+
+if __FILE__ == $0
+  require 'bio/io/fetch'
+
+  entry = Bio::Fetch.query('litdb', '0308004') 
+  puts entry
+  p Bio::LITDB.new(entry).reference
+
+  entry = Bio::Fetch.query('litdb', '0309094')
+  puts entry
+  p Bio::LITDB.new(entry).reference
+
+  entry = Bio::Fetch.query('litdb', '0309093')
+  puts entry
+  p Bio::LITDB.new(entry).reference
+end

data/lib/bio/db/medline.rb

@@ -0,0 +1,317 @@
+#
+# bio/db/medline.rb - NCBI PubMed/MEDLINE database class
+#
+#   Copyright (C) 2001, 2005 KATAYAMA Toshiaki <k@bioruby.org>
+#
+#  This library is free software; you can redistribute it and/or
+#  modify it under the terms of the GNU Lesser General Public
+#  License as published by the Free Software Foundation; either
+#  version 2 of the License, or (at your option) any later version.
+#
+#  This library is distributed in the hope that it will be useful,
+#  but WITHOUT ANY WARRANTY; without even the implied warranty of
+#  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+#  Lesser General Public License for more details.
+#
+#  You should have received a copy of the GNU Lesser General Public
+#  License along with this library; if not, write to the Free Software
+#  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307  USA
+#
+#  $Id: medline.rb,v 1.12 2005/09/08 01:22:11 k Exp $
+#
+
+require 'bio/db'
+
+module Bio
+
+  class MEDLINE < NCBIDB
+
+    def initialize(entry)
+      @pubmed = Hash.new('')
+
+      tag = ''
+      entry.each_line do |line|
+        if line =~ /^\w/
+          tag = line[0,4].strip
+        end
+        @pubmed[tag] += line[6..-1] if line.length > 6
+      end
+    end
+
+
+    # Reference object
+    def reference
+      hash = Hash.new('')
+
+      hash['authors']	= authors
+      hash['title']	= title
+      hash['journal']	= journal
+      hash['volume']	= volume
+      hash['issue']	= issue
+      hash['pages']	= pages
+      hash['year']	= year
+      hash['pubmed']	= pmid
+      hash['medline']  	= ui
+      hash['abstract']	= abstract
+      hash['mesh']	= mesh
+      hash['affiliations'] = affiliations
+
+      hash.delete_if { |k, v| v.nil? or v.empty? }
+
+      return Reference.new(hash)
+    end
+
+
+    ### Common MEDLINE tags
+
+    # PMID - PubMed Unique Identifier
+    #   Unique number assigned to each PubMed citation.
+    def pmid
+      @pubmed['PMID'].strip
+    end
+    alias entry_id pmid
+
+    # UI   - MEDLINE Unique Identifier
+    #   Unique number assigned to each MEDLINE citation.
+    def ui
+      @pubmed['UI'].strip
+    end
+
+    # TA   - Journal Title Abbreviation
+    #   Standard journal title abbreviation.
+    def ta
+      @pubmed['TA'].gsub(/\s+/, ' ').strip
+    end
+    alias journal ta
+
+    # VI   - Volume
+    #   Journal volume.
+    def vi
+      @pubmed['VI'].strip
+    end
+    alias volume vi
+
+    # IP   - Issue
+    #   The number of the issue, part, or supplement of the journal in which
+    #   the article was published.
+    def ip
+      @pubmed['IP'].strip
+    end
+    alias issue ip
+
+    # PG   - Page Number
+    #   The full pagination of the article.
+    def pg
+      @pubmed['PG'].strip
+    end
+
+    def pages
+      pages = pg
+      if pages =~ /-/
+        from, to = pages.split('-')
+        if (len = from.length - to.length) > 0
+          to = from[0,len] + to
+        end
+        pages = "#{from}-#{to}"
+      end
+      return pages
+    end
+
+    # DP   - Publication Date
+    #   The date the article was published.
+    def dp
+      @pubmed['DP'].strip
+    end
+    alias date dp
+
+    def year
+      dp[0,4]
+    end
+
+    # TI   - Title Words
+    #   The title of the article.
+    def ti
+      @pubmed['TI'].gsub(/\s+/, ' ').strip
+    end
+    alias title ti
+
+    # AB   - Abstract
+    #   Abstract.
+    def ab
+      @pubmed['AB'].gsub(/\s+/, ' ').strip
+    end
+    alias abstract ab
+
+    # AU   - Author Name
+    #   Authors' names.
+    def au
+      @pubmed['AU'].strip
+    end
+
+    def authors
+      authors = []
+      au.split(/\n/).each do |author|
+        if author =~ / /
+          name = author.split(/\s+/)
+          suffix = name[-2] =~ /^[A-Z]+$/ ? name.pop : nil	# Jr etc.
+          initial = name.pop.split(//).join('. ')
+          author = "#{name.join(' ')}, #{initial}."
+        end
+        if suffix
+          author << " " + suffix
+        end
+        authors.push(author)
+      end
+      return authors
+    end
+
+    # SO   - Source
+    #   Composite field containing bibliographic information.
+    def so
+      @pubmed['SO'].strip
+    end
+    alias source so
+
+    # MH   - MeSH Terms
+    #   NLM's controlled vocabulary.
+    def mh
+      @pubmed['MH'].strip.split(/\n/)
+    end
+    alias mesh mh
+
+    # AD   - Affiliation
+    #   Institutional affiliation and address of the first author, and grant
+    #   numbers.
+    def ad
+      @pubmed['AD'].strip.split(/\n/)
+    end
+    alias affiliations ad
+
+
+    ### Other MEDLINE tags
+
+    # AID  - Article Identifier
+    #   Article ID values may include the pii (controlled publisher identifier)
+    #   or doi (Digital Object Identifier).
+
+    # CI   - Copyright Information
+    #   Copyright statement.
+
+    # CIN  - Comment In
+    #   Reference containing a comment about the article.
+
+    # CN   - Collective Name
+    #   Corporate author or group names with authorship responsibility.
+
+    # CON  - Comment On
+    #   Reference upon which the article comments.
+
+    # CY   - Country
+    #   The place of publication of the journal.
+
+    # DA   - Date Created
+    #   Used for internal processing at NLM.
+
+    # DCOM - Date Completed
+    #   Used for internal processing at NLM.
+
+    # DEP  - Date of Electronic Publication
+    #   Electronic publication date.
+
+    # EDAT - Entrez Date
+    #   The date the citation was added to PubMed.
+
+    # EIN  - Erratum In
+    #   Reference containing a published erratum to the article.
+
+    # GS   - Gene Symbol
+    #   Abbreviated gene names (used 1991 through 1996).
+
+    # ID   - Identification Number 
+    #   Research grant numbers, contract numbers, or both that designate
+    #   financial support by any agency of the US PHS (Public Health Service).
+
+    # IS   - ISSN
+    #   International Standard Serial Number of the journal.
+
+    # JC   - Journal Title Code
+    #   MEDLINE unique three-character code for the journal.
+
+    # JID  - NLM Unique ID
+    #   Unique journal ID in NLM's catalog of books, journals, and audiovisuals.
+
+    # LA   - Language
+    #   The language in which the article was published.
+
+    # LR   - Last Revision Date
+    #   The date a change was made to the record during a maintenance procedure.
+
+    # MHDA - MeSH Date
+    #   The date MeSH terms were added to the citation. The MeSH date is the
+    #   same as the Entrez date until MeSH are added.
+
+    # PHST - Publication History Status Date
+    #   History status date.
+
+    # PS   - Personal Name as Subject
+    #   Individual is the subject of the article.
+
+    # PST  - Publication Status
+    #   Publication status.
+
+    # PT   - Publication Type
+    #   The type of material the article represents.
+    def pt
+      @pubmed['PT'].strip.split(/\n/)   
+    end
+    alias publication_type pt
+
+    # RF   - Number of References
+    #   Number of bibliographic references for Review articles.
+
+    # RIN  - Retraction In
+    #   Retraction of the article
+
+    # RN   - EC/RN Number
+    #   Number assigned by the Enzyme Commission to designate a particular
+    #   enzyme or by the Chemical Abstracts Service for Registry Numbers.
+
+    # ROF  - Retraction Of
+    #   Article being retracted.
+
+    # RPF  - Republished From
+    #   Original article.
+
+    # SB   - Journal Subset
+    #   Code for a specific set of journals.
+
+    # SI   - Secondary Source Identifier
+    #   Identifies a secondary source that supplies information, e.g., other
+    #   data sources, databanks and accession numbers of molecular sequences
+    #   discussed in articles.
+
+    # TT   - Transliterated / Vernacular Title 
+    #   Non-Roman alphabet language titles are transliterated.
+
+    # UIN  - Update In
+    #   Update to the article.
+
+    # UOF  - Update Of
+    #   The article being updated.
+
+    # URLF - URL Full-Text
+    #   Link to the full-text of article at provider's website. Links are
+    #   incomplete. Use PmLink for the complete set of available links.
+    #   [PmLink] http://www.ncbi.nlm.nih.gov/entrez/utils/pmlink_help.html
+
+    # URLS - URL Summary
+    #   Link to the article summary at provider's website. Links are
+    #   incomplete. Use PmLink for the complete set of available links.
+    #   [PmLink] http://www.ncbi.nlm.nih.gov/entrez/utils/pmlink_help.html
+
+  end
+
+end
+
+
+