bio 1.2.1 → 1.3.0

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

@@ -4,7 +4,7 @@
 # Copyright::  Copyright (C) 2004 Toshiaki Katayama <k@bioruby.org>
 # License::    The Ruby License
 #
-# $Id: glycan.rb,v 1.7 2007/12/14 16:20:38 k Exp $
+# $Id:$
 #
 
 require 'bio/db'
@@ -46,11 +46,7 @@ class GLYCAN < KEGGDB
   # MASS
   def mass
     unless @data['MASS']
-      hash = Hash.new
-      fetch('MASS').scan(/(\S+)\s+\((\S+)\)/).each do |val, key|
-        hash[key] = val.to_f
-      end
-      @data['MASS'] = hash
+      @data['MASS'] = field_fetch('MASS')[/[\d\.]+/].to_f
     end
     @data['MASS']
   end

data/lib/bio/db/lasergene.rb

@@ -5,10 +5,10 @@
 # Copyright:: Copyright (c) 2007 Center for Biomedical Research Informatics, University of Minnesota (http://cbri.umn.edu)
 # License::   The Ruby License
 #
-#  $Id: lasergene.rb,v 1.3 2007/04/05 23:35:40 trevor Exp $
+#  $Id:$
 #
 
-module Bio #:nodoc:
+module Bio
 
 #
 # bio/db/lasergene.rb - Interface for DNAStar Lasergene sequence file format
@@ -206,4 +206,4 @@ class Lasergene
     @sequence = Bio::Sequence.auto( lines[ (delimiter_2_indices[0] + 1) .. -1 ].join('') )
   end
 end # Lasergene
-end # Bio
+end # Bio

data/lib/bio/db/medline.rb

@@ -153,7 +153,10 @@ class MEDLINE < NCBIDB
     au.split(/\n/).each do |author|
       if author =~ / /
         name = author.split(/\s+/)
-        suffix = name[-2] =~ /^[A-Z]+$/ ? name.pop : nil	# Jr etc.
+        suffix = nil
+        if name.length > 2 && name[-2] =~ /^[A-Z]+$/ # second to last are the initials
+          suffix = name.pop
+        end
         initial = name.pop.split(//).join('. ')
         author = "#{name.join(' ')}, #{initial}."
       end

data/lib/bio/db/newick.rb

@@ -6,7 +6,7 @@
 #               Daniel Amelang <dan@amelang.net>
 # License::     The Ruby License
 #
-# $Id: newick.rb,v 1.8 2007/12/12 16:06:22 ngoto Exp $
+# $Id:$
 #
 # == Description
 #
@@ -606,9 +606,9 @@ module Bio
         # If all of the internal node's names are numeric,
         # the names are regarded as bootstrap values.
         flag = false
-        internal_nodes.each do |node|
-          if node.name and !node.name.to_s.strip.empty? then
-            if /\A[\+\-]?\d*\.?\d*\z/ =~ node.name
+        internal_nodes.each do |inode|
+          if inode.name and !inode.name.to_s.strip.empty? then
+            if /\A[\+\-]?\d*\.?\d*\z/ =~ inode.name
               flag = true
             else
               flag = false
@@ -619,17 +619,17 @@ module Bio
         if flag then
           @options[:bootstrap_style] = :traditional
           @options[:original_format] = :traditional
-          internal_nodes.each do |node|
-            if node.name then
-              node.bootstrap_string = node.name
-              node.name = nil
+          internal_nodes.each do |inode|
+            if inode.name then
+              inode.bootstrap_string = inode.name
+              inode.name = nil
             end
           end
         end
       end
       # Sets nodes order numbers
-      nodes.each_with_index do |node, i|
-        node.order_number = i
+      nodes.each_with_index do |xnode, i|
+        xnode.order_number = i
       end
       # If the root implicitly prepared by the program is a leaf and
       # there are no additional information for the edge from the root to

data/lib/bio/db/pdb/chain.rb

@@ -6,7 +6,7 @@
 #             Naohisa Goto <ng@bioruby.org>
 # License::   The Ruby License
 # 
-# $Id: chain.rb,v 1.9 2007/12/18 13:48:42 ngoto Exp $
+# $Id: chain.rb,v 1.10 2008/04/01 10:36:44 ngoto Exp $
 #
 # = Bio::PDB::Chain
 # 
@@ -189,7 +189,11 @@ module Bio
               x.times { string << 'X' }
             end
             tlc = residue.resName.capitalize
-            olc = (Bio::AminoAcid.three2one(tlc) or 'X')
+            olc = (begin
+                     Bio::AminoAcid.three2one(tlc)
+                   rescue ArgumentError
+                     nil
+                   end || 'X')
             string << olc
           end
           @aaseq = Bio::Sequence::AA.new(string)

data/lib/bio/db/pdb/pdb.rb

@@ -6,7 +6,7 @@
 #             Alex Gutteridge <alexg@ebi.ac.uk>
 # License::   The Ruby License
 #
-#  $Id: pdb.rb,v 1.27 2007/12/28 14:43:44 ngoto Exp $
+#  $Id: pdb.rb,v 1.28 2008/04/01 10:36:44 ngoto Exp $
 #
 # = About Bio::PDB
 #
@@ -1497,6 +1497,9 @@ module Bio
               cChain = newChain
               chain = newChain
             end
+            # chain might be changed, clearing cResidue and cLigand
+            cResidue = nil
+            cLigand = nil
           end
         end
 
@@ -1550,6 +1553,8 @@ module Bio
         when 'MODEL'
           c_atom = nil
           cChain = nil
+          cResidue = nil
+          cLigand = nil
           if cModel.model_serial or cModel.chains.size > 0 then
             self.addModel(cModel)
           end
@@ -1809,13 +1814,17 @@ module Bio
               #aa is three letter code: i.e. ALA
               #need to look up with Ala
               aa = aa.capitalize
-              (Bio::AminoAcid.three2one(aa) or 'X')
+              (begin
+                 Bio::AminoAcid.three2one(aa)
+               rescue ArgumentError
+                 nil
+               end || 'X')
             end
             seq = Bio::Sequence::AA.new(a.to_s)
           else
             # nucleic acid sequence
             a.collect! do |na|
-              na = na.strip
+              na = na.delete('^a-zA-Z')
               na.size == 1 ? na : 'n'
             end
             seq = Bio::Sequence::NA.new(a.to_s)

data/lib/bio/db/rebase.rb

@@ -5,14 +5,13 @@
 # Copyright:: Copyright (c) 2005-2007 Midwinter Laboratories, LLC (http://midwinterlabs.com)
 # License::   The Ruby License
 #
-#  $Id: rebase.rb,v 1.8 2007/04/05 23:35:40 trevor Exp $
+#  $Id:$
 #
 
-autoload :YAML, 'yaml'
+require 'yaml'
+require 'bio/reference'
 
-module Bio #:nodoc:
-
-autoload :Reference, 'bio/reference'
+module Bio
 
 #
 # bio/db/rebase.rb - Interface for EMBOSS formatted REBASE files
@@ -316,7 +315,7 @@ class REBASE
   def parse_enzymes( lines )
     data = {}
     return data if lines == nil
-    lines.each do |line|
+    lines.each_line do |line|
       next if line[0].chr == '#'
       line.chomp!
       
@@ -347,7 +346,7 @@ class REBASE
     h = {}
     references_left = 0
 
-    lines.each do |line|
+    lines.each_line do |line|
       next if line[0].chr == '#'  # Comment
       next if line[0..1] == '//'  # End of entry marker
       line.chomp!
@@ -389,7 +388,7 @@ class REBASE
   def parse_suppliers( lines )
     data = {}
     return data if lines == nil
-    lines.each do |line|
+    lines.each_line do |line|
       next if line[0].chr == '#'
       data[$1] = $2 if line =~ %r{(.+?)\s(.+)}
     end

data/lib/bio/db/soft.rb

@@ -5,10 +5,10 @@
 # Copyright:: Copyright (c) 2007 Midwinter Laboratories, LLC (http://midwinterlabs.com)
 # License::   The Ruby License
 #
-#  $Id: soft.rb,v 1.2 2007/04/05 23:35:40 trevor Exp $
+#  $Id:$
 #
 
-module Bio #:nodoc:
+module Bio
 
 #
 # bio/db/soft.rb - Interface for SOFT formatted files
@@ -401,4 +401,4 @@ class SOFT
   end
 
 end # SOFT
-end # Bio
+end # Bio

data/lib/bio/feature.rb

@@ -5,7 +5,7 @@
 #                             2006        Jan Aerts <jan.aerts@bbsrc.ac.uk>
 # License::	The Ruby License
 #
-# $Id: feature.rb,v 1.13 2007/04/05 23:35:39 trevor Exp $
+# $Id: feature.rb,v 1.13.2.1 2008/03/04 10:12:22 ngoto Exp $
 
 require 'bio/location'
 
@@ -135,92 +135,5 @@ class Feature
 
 end #Feature
 
-
-# = DESCRIPTION
-# Container for a list of Feature objects.
-#
-# = USAGE
-#  # First, create some Bio::Feature objects
-#  feature1 = Bio::Feature.new('intron','3627..4059')
-#  feature2 = Bio::Feature.new('exon','4060..4236')
-#  feature3 = Bio::Feature.new('intron','4237..4426')
-#  feature4 = Bio::Feature.new('CDS','join(2538..3626,4060..4236)',
-#                   [ Bio::Feature::Qualifier.new('gene', 'CYP2D6'),
-#                     Bio::Feature::Qualifier.new('translation','MGXXTVMHLL...')
-#                   ])
-#
-#  # And create a container for them
-#  feature_container = Bio::Features.new([ feature1, feature2, feature3, feature4 ])
-#
-#  # Iterate over all features and print
-#  feature_container.each do |feature|
-#    puts feature.feature + "\t" + feature.position
-#    feature.each do |qualifier|
-#      puts "- " + qualifier.qualifier + ": " + qualifier.value
-#    end
-#  end
-#
-#  # Iterate only over CDS features and extract translated amino acid sequences
-#  features.each("CDS") do |feature|
-#    hash = feature.to_hash
-#    name = hash["gene"] || hash["product"] || hash["note"] 
-#    aaseq  = hash["translation"]
-#    pos  = feature.position
-#    if name and seq
-#      puts ">#{gene} #{feature.position}"
-#      puts aaseq
-#    end
-#  end
-class Features
-  # Create a new Bio::Features object.
-  #
-  # *Arguments*:
-  # * (optional) _list of features_: list of Bio::Feature objects
-  # *Returns*:: Bio::Features object
-  def initialize(ary = [])
-    @features = ary
-  end
-
-  # Returns an Array of Feature objects.
-  attr_accessor :features
-
-  # Appends a Feature object to Features.
-  # 
-  # *Arguments*:
-  # * (required) _feature_: Bio::Feature object
-  # *Returns*:: Bio::Features object
-  def append(a)
-    @features.push(a) if a.is_a? Feature
-    return self
-  end
-
-  # Iterates on each feature object.
-  #
-  # *Arguments*:
-  # * (optional) _key_: if specified, only iterates over features with this key
-  def each(arg = nil)
-    @features.each do |x|
-      next if arg and x.feature != arg
-      yield x
-    end
-  end
-
-  # Short cut for the Features#features[n]
-  def [](*arg)
-    @features[*arg]
-  end
-
-  # Short cut for the Features#features.first
-  def first
-    @features.first
-  end
-
-  # Short cut for the Features#features.last
-  def last
-    @features.last
-  end
-
-end # Features
-
 end # Bio
 

data/lib/bio/io/biosql/biodatabase.rb

@@ -0,0 +1,64 @@
+module Bio
+		class SQL
+			class Biodatabase < DummyBase
+				has_many :bioentries, :class_name =>"Bioentry", :foreign_key => "biodatabase_id"
+				validates_uniqueness_of :name
+			end
+		end #SQL
+end #Bio	
+
+
+if __FILE__ == $0
+  require 'rubygems'
+  require 'composite_primary_keys'
+  require 'bio'
+  require 'pp'
+  
+  #  pp connection = Bio::SQL.establish_connection('bio/io/biosql/config/database.yml','development')
+  pp connection = Bio::SQL.establish_connection({'test'=>{'database'=>"bio_test", 'adapter'=>"postgresql", 'username'=>"rails", 'password'=>nil}},'test')
+  #pp YAML::load(ERB.new(IO.read('bio/io/biosql/config/database.yml')).result)
+  if true
+    pp Bio::SQL.list_entries
+
+    puts "### GenBank"
+    if ARGV.size > 0
+	gb = Bio::GenBank.new(ARGF.read)
+    else
+	require 'bio/io/fetch'
+	gb = Bio::GenBank.new(Bio::Fetch.query('gb', 'AJ224122'))
+    end
+
+   	biosequence = gb.to_biosequence
+	db=Bio::SQL::Biodatabase.new(:biodatabase_id=>3,:name=>"JEFF", :authority=>"ME", :description=>"YOU")
+	db.save!
+	
+	#sqlseq = Bio::SQL::Sequence.new(:biosequence=>biosequence,:biodatabase_id=>db.id)
+
+	#    bioseq = Bio::SQL.fetch_accession('AJ224122')   
+	#    pp bioseq
+	#    pp bioseq.entry_id    
+    #TODO create a test only for tables not sequence here
+#    pp bioseq.molecule_type
+    #pp  bioseq.molecule_type.class
+    #bioseq.molecule_type_update('dna', 1)
+    pp Bio::SQL::Taxon.find(8121).taxon_names
+    
+	    #sqlseq.to_biosequence
+	
+	#sqlseq.delete
+  end
+  #pp  bioseq.molecule_type
+  #term = Bio::SQL::Term.find_by_name('mol_type')
+  #pp term
+  #pp bioseq.entry.bioentry_qualifier_values.create(:term=>term, :rank=>2, :value=>'pippo')
+  #pp bioseq.entry.bioentry_qualifier_values.inspect
+  #pp bioseq.entry.bioentry_qualifier_values.find_all_by_term_id(26)
+  #pp primo.class
+  #  pp primo.value='dna'
+  #  pp primo.save
+  #pp bioseq.molecule_type= 'prova'
+  
+  #Bio::SQL::BioentryQualifierValue.delete(delete.bioentry_id,delete.term_id,delete.rank)
+  
+  
+end

data/lib/bio/io/biosql/bioentry.rb

@@ -0,0 +1,29 @@
+module Bio
+    class SQL
+			class Bioentry < DummyBase
+				belongs_to :biodatabase, :class_name => "Biodatabase"
+				belongs_to :taxon, :class_name => "Taxon"
+				has_one :biosequence
+				#, :class_name => "Biosequence", :foreign_key => "bioentry_id"
+				has_many :comments, :class_name =>"Comment", :order =>'rank'
+				has_many :seqfeatures, :class_name => "Seqfeature", :order=>'rank'
+				has_many :bioentry_references, :class_name=>"BioentryReference" #, :foreign_key => "bioentry_id"
+				has_many :bioentry_dbxrefs, :class_name => "BioentryDbxref"
+				has_many :object_bioentry_relationships, :class_name=>"BioentryRelationship", :foreign_key=>"object_bioentry_id" #non mi convince molto credo non funzioni nel modo corretto
+				has_many :subject_bioentry_relationships, :class_name=>"BioentryRelationship", :foreign_key=>"subject_bioentry_id" #non mi convince molto credo non funzioni nel modo corretto
+
+				has_many :cdsfeatures, :class_name=>"Seqfeature", :foreign_key =>"bioentry_id", :conditions=>["term.name='CDS'"], :include=>"type_term"
+        
+        has_many :terms, :through=>:bioentry_qualifier_values, :class_name => "Term"
+        #NOTE: added order_by for multiple hit and manage ranks correctly
+        has_many :bioentry_qualifier_values, :order=>"bioentry_id,term_id,rank", :class_name => "BioentryQualifierValue"
+        
+				#per la creazione richiesti:
+				#name, accession, version
+#				validates_uniqueness_of :accession, :scope=>[:biodatabase_id]
+#				validates_uniqueness_of :name, :scope=>[:biodatabase_id] 
+			#	validates_uniqueness_of :identifier, :scope=>[:biodatabase_id]
+				
+			end
+		end #SQL
+end #Bio

data/lib/bio/io/biosql/bioentry_dbxref.rb

@@ -0,0 +1,11 @@
+module Bio
+		class SQL
+			class BioentryDbxref < DummyBase
+#delete				set_sequence_name nil
+				set_primary_key nil #bioentry_id,dbxref_id
+				belongs_to :bioentry, :class_name => "Bioentry"
+				belongs_to :dbxref, :class_name => "Dbxref"
+			end
+    		end #SQL
+end #Bio	
+

data/lib/bio/io/biosql/bioentry_path.rb

@@ -0,0 +1,12 @@
+module Bio
+    class SQL
+			class BioentryPath < DummyBase
+				set_primary_key nil
+#delete				set_sequence_name nil
+				belongs_to :term, :class_name => "Term"
+				#da sistemare per poter procedere.
+				belongs_to :object_bioentry, :class_name=>"Bioentry"
+				belongs_to :subject_bioentry, :class_name=>"Bioentry"
+			end #BioentryPath
+		end #SQL
+end #Bio