wwood-bioruby 1.2.11

data/lib/bio/db/litdb.rb

@@ -0,0 +1,107 @@
+#
+# = bio/db/litdb.rb - LITDB database class
+#
+# Copyright::  Copyright (C) 2001 Toshiaki Katayama <k@bioruby.org>
+# License::    The Ruby License
+#
+# $Id: litdb.rb,v 0.10 2007/04/05 23:35:40 trevor Exp $
+#
+
+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 +1,326 @@
+#
+# = bio/db/medline.rb - NCBI PubMed/MEDLINE database class
+#
+# Copyright::  Copyright (C) 2001, 2005
+#              Toshiaki Katayama <k@bioruby.org>
+# License::    The Ruby License
+#
+# $Id: medline.rb,v 1.17 2007/12/21 05:12:41 k Exp $
+#
+
+require 'bio/db'
+
+module Bio
+
+# == Description
+#
+# NCBI PubMed/MEDLINE database class.
+#
+# == Examples
+#
+#   medline = Bio::MEDLINE.new(txt)
+#   medline.reference
+#   medline.pmid == medline.entry_id
+#   medilne.mesh
+#
+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
+  attr_reader :pubmed
+
+
+  # returns a 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 = nil
+        if name.length > 2 && name[-2] =~ /^[A-Z]+$/ # second to last are the initials
+          suffix = name.pop
+        end
+        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
+
+  # AID  - Article Identifier
+  #   Article ID values may include the pii (controlled publisher identifier)
+  #   or doi (Digital Object Identifier).
+  def doi
+    @pubmed['AID'][/(\S+) \[doi\]/, 1]
+  end
+
+  def pii
+    @pubmed['AID'][/(\S+) \[pii\]/, 1]
+  end
+
+  ### Other MEDLINE tags
+
+  # 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 # MEDLINE
+
+end # Bio
+
+
+

data/lib/bio/db/nbrf.rb

@@ -0,0 +1,191 @@
+#
+# = bio/db/nbrf.rb - NBRF/PIR format sequence data class
+#
+# Copyright:: Copyright (C) 2001-2003,2006 Naohisa Goto <ng@bioruby.org>
+#             Copyright (C) 2001-2002 Toshiaki Katayama <k@bioruby.org>
+# License::   The Ruby License
+#
+#  $Id: nbrf.rb,v 1.10 2007/04/05 23:35:40 trevor Exp $
+#
+# Sequence data class for NBRF/PIR flatfile format.
+#
+# = References
+#
+# * http://pir.georgetown.edu/pirwww/otherinfo/doc/techbulletin.html
+# * http://www.sander.embl-ebi.ac.uk/Services/webin/help/webin-align/align_format_help.html#pir
+# * http://www.cmbi.kun.nl/bioinf/tools/crab_pir.html
+#
+
+require 'bio/db'
+require 'bio/sequence'
+
+module Bio
+
+  # Sequence data class for NBRF/PIR flatfile format.
+  class NBRF < DB
+    #--
+    # based on Bio::FastaFormat class
+    #++
+
+    # Delimiter of each entry. Bio::FlatFile uses it.
+    DELIMITER	= RS = "\n>"
+
+    # (Integer) excess read size included in DELIMITER.
+    DELIMITER_OVERRUN = 1 # '>'
+
+    #--
+    # Note: DELIMITER is changed due to the change of Bio::FlatFile.
+    # DELIMITER	= RS = "*\n"
+    #++
+
+    # Creates a new NBRF object. It stores the comment and sequence
+    # information from one entry of the NBRF/PIR format string.
+    # If the argument contains more than one
+    # entry, only the first entry is used.
+    def initialize(str)
+      str = str.sub(/\A[\r\n]+/, '') # remove first void lines
+      line1, line2, rest = str.split(/^/, 3)
+
+      rest = rest.to_s
+      rest.sub!(/^>.*/m, '') # remove trailing entries for sure
+      @entry_overrun = $&
+      rest.sub!(/\*\s*\z/, '') # remove last '*' and "\n"
+      @data = rest
+
+      @definition = line2.to_s.chomp
+      if /^>?([A-Za-z0-9]{2})\;(.*)/ =~ line1.to_s then
+        @seq_type = $1
+        @entry_id = $2
+      end
+    end
+
+    # Returns sequence type described in the entry.
+    #  P1 (protein), F1 (protein fragment)
+    #  DL (DNA linear), DC (DNA circular)
+    #  RL (DNA linear), RC (DNA circular)
+    #  N3 (tRNA), N1 (other functional RNA)
+    attr_accessor :seq_type
+
+    # Returns ID described in the entry.
+    attr_accessor :entry_id
+    alias accession entry_id
+
+    # Returns the description line of the NBRF/PIR formatted data.
+    attr_accessor :definition
+
+    # sequence data of the entry (???)
+    attr_accessor :data
+
+    # piece of next entry. Bio::FlatFile uses it.
+    attr_reader :entry_overrun
+
+
+    # Returns the stored one entry as a NBRF/PIR format. (same as to_s)
+    def entry
+      @entry = ">#{@seq_type or 'XX'};#{@entry_id}\n#{definition}\n#{@data}*\n"
+    end
+    alias to_s entry
+
+    # Returns Bio::Sequence::AA, Bio::Sequence::NA, or Bio::Sequence,
+    # depending on sequence type.
+    def seq_class
+      case @seq_type
+      when /[PF]1/
+        # protein
+        Sequence::AA
+      when /[DR][LC]/, /N[13]/
+        # nucleic
+        Sequence::NA
+      else
+        Sequence
+      end
+    end
+
+    # Returns sequence data.
+    # Returns Bio::Sequence::NA, Bio::Sequence::AA or Bio::Sequence,
+    # according to the sequence type.
+    def seq
+      unless defined?(@seq)
+        @seq = seq_class.new(@data.tr(" \t\r\n0-9", '')) # lazy clean up
+      end
+      @seq
+    end
+
+    # Returns sequence length.
+    def length
+      seq.length
+    end
+
+    # Returens the nucleic acid sequence.
+    # If you call naseq for protein sequence, RuntimeError will be occurred.
+    # Use the method if you know whether the sequence is NA or AA.
+    def naseq
+      if seq.is_a?(Bio::Sequence::AA) then
+        raise 'not nucleic but protein sequence'
+      elsif seq.is_a?(Bio::Sequence::NA) then
+        seq
+      else
+        Bio::Sequence::NA.new(seq)
+      end
+    end
+      
+    # Returens the length of sequence.
+    # If you call nalen for protein sequence, RuntimeError will be occurred.
+    # Use the method if you know whether the sequence is NA or AA.
+    def nalen
+      naseq.length
+    end
+
+    # Returens the protein (amino acids) sequence.
+    # If you call aaseq for nucleic acids sequence,
+    # RuntimeError will be occurred.
+    # Use the method if you know whether the sequence is NA or AA.
+    def aaseq
+      if seq.is_a?(Bio::Sequence::NA) then
+        raise 'not nucleic but protein sequence'
+      elsif seq.is_a?(Bio::Sequence::AA) then
+        seq
+      else
+        Bio::Sequence::AA.new(seq)
+      end
+    end
+
+    # Returens the length of protein (amino acids) sequence.
+    # If you call aaseq for nucleic acids sequence,
+    # RuntimeError will be occurred.
+    # Use the method if you know whether the sequence is NA or AA.
+    def aalen
+      aaseq.length
+    end
+
+    #--
+    #class method
+    #++
+
+    # Creates a NBRF/PIR formatted text.
+    # Parameters can be omitted.
+    def self.to_nbrf(hash)
+      seq_type = hash[:seq_type]
+      seq = hash[:seq]
+      unless seq_type
+        if seq.is_a?(Bio::Sequence::AA) then
+          seq_type = 'P1'
+        elsif seq.is_a?(Bio::Sequence::NA) then
+          seq_type = /u/i =~ seq ? 'RL' : 'DL'
+        else
+          seq_type = 'XX'
+        end
+      end
+      width = hash.has_key?(:width) ? hash[:width] : 70
+      if width then
+        seq = seq.to_s + "*"
+        seq.gsub!(Regexp.new(".{1,#{width}}"), "\\0\n")
+      else
+        seq = seq.to_s + "*\n"
+      end
+      ">#{seq_type};#{hash[:entry_id]}\n#{hash[:definition]}\n#{seq}"
+    end
+
+  end #class NBRF
+end #module Bio
+