bio 1.4.1 → 1.4.2

data/lib/bio/io/ncbirest.rb

@@ -127,6 +127,7 @@ class REST
   def ncbi_post_form(serv, opts)
     ncbi_check_parameters(opts)
     ncbi_access_wait
+    #$stderr.puts opts.inspect
     response = Bio::Command.post_form(serv, opts)
     response
   end
@@ -485,7 +486,7 @@ class REST
       #  nucleotide = nuccore + nucest + nucgss
       #
       # format (rettype):
-      # * native       all but Gene    Default format for viewing sequences
+      # * native       all but Gene    ASN Default format for viewing sequences
       # * fasta        all sequence    FASTA view of a sequence
       # * gb           NA sequence     GenBank view for sequences
       # * gbc          NA sequence     INSDSeq structured flat file
@@ -540,6 +541,125 @@ class REST
         Bio::NCBI::REST.efetch(ids, opts)
       end
 
+      # Retrieve nucleotide sequence entries by given IDs using E-Utils
+      # (efetch).
+      #
+      # * http://eutils.ncbi.nlm.nih.gov/entrez/query/static/efetchseq_help.html
+      #  nucleotide = nuccore + nucest + nucgss
+      #
+      # format (rettype):
+      # * native       all but Gene    ASN Default format for viewing sequences
+      # * fasta        all sequence    FASTA view of a sequence
+      # * gb           NA sequence     GenBank view for sequences
+      # * gbc          NA sequence     INSDSeq structured flat file
+      # * gbwithparts  NA sequence     GenBank CON division with sequences
+      # * est          dbEST sequence  EST Report
+      # * gss          dbGSS sequence  GSS Report
+      # * gp           AA sequence     GenPept view
+      # * gpc          AA sequence     INSDSeq structured flat file
+      # * seqid        all sequence    Convert GIs into seqids
+      # * acc          all sequence    Convert GIs into accessions
+      # * chr          dbSNP only      SNP Chromosome Report
+      # * flt          dbSNP only      SNP Flat File report
+      # * rsr          dbSNP only      SNP RS Cluster report
+      # * brief        dbSNP only      SNP ID list
+      # * docset       dbSNP only      SNP RS summary
+      #
+      # == Usage
+      #
+      #  Bio::NCBI::REST::EFetch.nucleotide("123,U12345,U12345.1,gb|U12345|")
+      #
+      #  list = [123, "U12345.1", "gb|U12345|"]
+      #  Bio::NCBI::REST::EFetch.nucleotide(list)
+      #  Bio::NCBI::REST::EFetch.nucleotide(list, "fasta")
+      #  Bio::NCBI::REST::EFetch.nucleotide(list, "acc")
+      #  Bio::NCBI::REST::EFetch.nucleotide(list, "xml")
+      #
+      #  Bio::NCBI::REST::EFetch.nucleotide("AE009950")
+      #  Bio::NCBI::REST::EFetch.nucleotide("AE009950", "gbwithparts")
+      #
+      #  ncbi = Bio::NCBI::REST::EFetch.new
+      #  ncbi.nucleotide("123,U12345,U12345.1,gb|U12345|")
+      #  ncbi.nucleotide(list)
+      #  ncbi.nucleotide(list, "fasta")
+      #  ncbi.nucleotide(list, "acc")
+      #  ncbi.nucleotide(list, "xml")
+      #  ncbi.nucleotide("AE009950")
+      #  ncbi.nucleotide("AE009950", "gbwithparts")
+      #
+      # ---
+      #
+      # *Arguments*:
+      # * _ids_: list of NCBI entry IDs (required)
+      # * _format_: "gb", "gbc", "fasta", "acc", "xml" etc.
+      # *Returns*:: String
+      def nucleotide(ids, format = "gb", hash = {})
+        case format
+        when "xml"
+          format = "gbc"
+        end
+        opts = { "db" => "nucleotide", "rettype" => format }
+        opts.update(hash)
+        Bio::NCBI::REST.efetch(ids, opts)
+      end
+
+      # Retrieve protein sequence entries by given IDs using E-Utils
+      # (efetch).
+      #
+      # * http://eutils.ncbi.nlm.nih.gov/entrez/query/static/efetchseq_help.html
+      #  protein
+      #
+      # format (rettype):
+      # * native       all but Gene    ASN Default format for viewing sequences
+      # * fasta        all sequence    FASTA view of a sequence
+      # * gb           NA sequence     GenBank view for sequences
+      # * gbc          NA sequence     INSDSeq structured flat file
+      # * gbwithparts  NA sequence     GenBank CON division with sequences
+      # * est          dbEST sequence  EST Report
+      # * gss          dbGSS sequence  GSS Report
+      # * gp           AA sequence     GenPept view
+      # * gpc          AA sequence     INSDSeq structured flat file
+      # * seqid        all sequence    Convert GIs into seqids
+      # * acc          all sequence    Convert GIs into accessions
+      # * chr          dbSNP only      SNP Chromosome Report
+      # * flt          dbSNP only      SNP Flat File report
+      # * rsr          dbSNP only      SNP RS Cluster report
+      # * brief        dbSNP only      SNP ID list
+      # * docset       dbSNP only      SNP RS summary
+      #
+      # == Usage
+      #
+      #  Bio::NCBI::REST::EFetch.protein("7527480,AAF63163.1,AAF63163")
+      #
+      #  list = [ 7527480, "AAF63163.1", "AAF63163"]
+      #  Bio::NCBI::REST::EFetch.protein(list)
+      #  Bio::NCBI::REST::EFetch.protein(list, "fasta")
+      #  Bio::NCBI::REST::EFetch.protein(list, "acc")
+      #  Bio::NCBI::REST::EFetch.protein(list, "xml")
+      #
+      #  ncbi = Bio::NCBI::REST::EFetch.new
+      #  ncbi.protein("7527480,AAF63163.1,AAF63163")
+      #  ncbi.protein(list)
+      #  ncbi.protein(list, "fasta")
+      #  ncbi.protein(list, "acc")
+      #  ncbi.protein(list, "xml")
+      #
+      # ---
+      #
+      # *Arguments*:
+      # * _ids_: list of NCBI entry IDs (required)
+      # * _format_: "gp", "gpc", "fasta", "acc", "xml" etc.
+      # *Returns*:: String
+      def protein(ids, format = "gp", hash = {})
+        case format
+        when "xml"
+          format = "gpc"
+        end
+        opts = { "db" => "protein", "rettype" => format }
+        opts.update(hash)
+        Bio::NCBI::REST.efetch(ids, opts)
+      end
+
       # Retrieve PubMed entries by given IDs using E-Utils (efetch).
       #
       # * http://eutils.ncbi.nlm.nih.gov/entrez/query/static/efetchlit_help.html

data/lib/bio/location.rb

@@ -632,8 +632,8 @@ class Locations
         end
       end
 
-      join_list.each do |position|
-        ary << gbl_pos2loc(position)
+      join_list.each do |pos|
+        ary << gbl_pos2loc(pos)
       end
 
     when /^complement\((.*)\)$/				# (J) complement()

data/lib/bio/reference.rb

@@ -272,7 +272,7 @@ module Bio
       lines << "%N #{@issue}" unless @issue.to_s.empty?
       lines << "%P #{@pages}" unless @pages.empty?
       lines << "%M #{@pubmed}" unless @pubmed.to_s.empty?
-      u = @url.empty? ? pubmed_url : @url
+      u = @url.to_s.empty? ? pubmed_url : @url
       lines << "%U #{u}" unless u.empty?
       lines << "%X #{@abstract}" unless @abstract.empty?
       @mesh.each do |term|
@@ -587,9 +587,8 @@ module Bio
     # *Returns*:: String
     def pubmed_url
       unless @pubmed.to_s.empty?
-        cgi = "http://www.ncbi.nlm.nih.gov/entrez/query.fcgi"
-        opts = "cmd=Retrieve&db=PubMed&dopt=Citation&list_uids"
-        return "#{cgi}?#{opts}=#{@pubmed}"
+        head = "http://www.ncbi.nlm.nih.gov/pubmed"
+        return "#{head}/#{@pubmed}"
       end
       ''
     end

data/lib/bio/shell/plugin/entry.rb

@@ -62,7 +62,7 @@ module Bio::Shell
   #   * "db:entry"  -- local BioFlat, OBDA, EMBOSS, KEGG API
   def getent(arg)
     entry = ""
-    db, entry_id = arg.to_s.strip.split(/:/)
+    db, entry_id = arg.to_s.strip.split(/\:/, 2)
 
     # local file
     if arg.respond_to?(:gets) or File.exists?(arg)
@@ -81,8 +81,12 @@ module Bio::Shell
 
     else
       # EMBOSS USA in ~/.embossrc
-      str = entret(arg)
-      if $?.exitstatus == 0 and str.length != 0
+      begin
+        str = entret(arg)
+      rescue SystemCallError
+        str = ''
+      end
+      if $? and $?.exitstatus == 0 and str.length != 0
         puts "Retrieving entry from EMBOSS (#{arg})"
         entry = str
 

data/lib/bio/shell/plugin/ncbirest.rb

@@ -31,7 +31,11 @@ module Bio::Shell
   # Otherwise, it acts the same as Bio::NCBI::REST.efetch.
   def efetch(ids, *arg)
     if arg.empty? then
-      Bio::NCBI::REST::EFetch.sequence(ids)
+      ret = Bio::NCBI::REST::EFetch.nucleotide(ids)
+      unless /^LOCUS       / =~ ret.to_s then
+        ret = Bio::NCBI::REST::EFetch.protein(ids)
+      end
+      ret
     elsif arg[0].kind_of?(Symbol)
       meth = arg[0]
       case meth.to_s

data/lib/bio/util/restriction_enzyme.rb

@@ -125,6 +125,9 @@ class RestrictionEnzyme
   autoload :Analysis,                'bio/util/restriction_enzyme/analysis'
   autoload :Range,                   'bio/util/restriction_enzyme/range/sequence_range'
 
+  autoload :SortedNumArray,          'bio/util/restriction_enzyme/sorted_num_array'
+  autoload :DenseIntArray,          'bio/util/restriction_enzyme/dense_int_array'
+
   include CutSymbol
   extend CutSymbol
 

data/lib/bio/util/restriction_enzyme/dense_int_array.rb

@@ -0,0 +1,195 @@
+#
+# bio/util/restriction_enzyme/dense_int_array.rb - Internal data storage for Bio::RestrictionEnzyme::Range::SequenceRange
+#
+# Copyright::   Copyright (C) 2011
+#               Naohisa Goto <ng@bioruby.org>
+#               Tomoaki NISHIYAMA
+# License::     The Ruby License
+#
+
+module Bio
+class RestrictionEnzyme
+
+  # a class to store integer numbers, containing many contiguous
+  # integral numbers.
+  #
+  # Bio::RestrictionEnzyme internal use only.
+  # Please do not create the instance outside Bio::RestrictionEnzyme.
+  class DenseIntArray
+    MutableRange = Struct.new(:first, :last)
+
+    include Enumerable
+
+    # Same usage as Array.[]
+    def self.[](*args)
+      a = self.new
+      args.each do |elem|
+        a.push elem
+      end
+      a
+    end
+
+    # creates a new object
+    def initialize
+      @data = []
+    end
+
+    # initialize copy
+    def initialize_copy(other)
+      super(other)
+      @data = @data.collect { |elem| elem.dup }
+    end
+
+    # sets internal data object
+    def internal_data=(a)
+      #clear_cache
+      @data = a
+      self
+    end
+    protected :internal_data=
+
+    # gets internal data object
+    def internal_data
+      @data
+    end
+    protected :internal_data
+
+    # Same usage as Array#[]
+    def [](*arg)
+      #$stderr.puts "SortedIntArray#[]"
+      to_a[*arg]
+    end
+
+    # Not implemented
+    def []=(*arg)
+      raise NotImplementedError, 'DenseIntArray#[]= is not implemented.'
+    end
+
+    # Same usage as Array#each
+    def each
+      @data.each do |elem|
+        elem.first.upto(elem.last) { |num| yield num }
+      end
+      self
+    end
+
+    # Same usage as Array#reverse_each
+    def reverse_each
+      @data.reverse_each do |elem|
+        elem.last.downto(elem.first) { |num| yield num }
+      end
+      self
+    end
+
+    # Same usage as Array#+, but accepts only the same classes instance.
+    def +(other)
+      unless other.is_a?(self.class) then
+        raise TypeError, 'unsupported data type'
+      end
+      tmpdata = @data + other.internal_data
+      tmpdata.sort! { |a,b| a.first <=> b.first }
+      result = self.class.new
+      return result if tmpdata.empty?
+      newdata = result.internal_data
+      newdata.push tmpdata[0].dup
+      (1...(tmpdata.size)).each do |i|
+        if (x = newdata[-1].last) >= tmpdata[i].first then
+          newdata[-1].last = tmpdata[i].last if tmpdata[i].last > x
+        else
+          newdata.push tmpdata[i].dup
+        end
+      end
+      result
+    end
+
+    # Same usage as Array#==
+    def ==(other)
+      if r = super(other) then
+        r
+      elsif other.is_a?(self.class) then
+        other.internal_data == @data
+      else
+        false
+      end
+    end
+
+    # Same usage as Array#concat
+    def concat(ary)
+      ary.each { |elem| self.<<(elem) }
+      self
+    end
+
+    # Same usage as Array#push
+    def push(*args)
+      args.each do |elem|
+        self.<<(elem)
+      end
+      self
+    end
+
+    # Same usage as Array#unshift
+    def unshift(*arg)
+      raise NotImplementedError, 'DenseIntArray#unshift is not implemented.'
+    end
+
+    # Same usage as Array#<<
+    def <<(elem)
+      if !@data.empty? and
+          @data[-1].last + 1 == elem then
+        @data[-1].last = elem
+      else
+        @data << MutableRange.new(elem, elem)
+      end
+      self
+    end
+
+    # Same usage as Array#include?
+    def include?(elem)
+      return false if @data.empty? or elem < self.first or self.last < elem
+      @data.any? do |range|
+        range.first <= elem && elem <= range.last
+      end
+    end
+
+    # Same usage as Array#first
+    def first
+      elem = @data.first
+      elem ? elem.first : nil
+    end
+
+    # Same usage as Array#last
+    def last
+      elem = @data.last
+      elem ? elem.last : nil
+    end
+
+    # Same usage as Array#size
+    def size
+      sum = 0
+      @data.each do |range|
+        sum += (range.last - range.first + 1)
+      end
+      sum
+    end
+    alias length size
+
+    # Same usage as Array#delete
+    def delete(elem)
+      raise NotImplementedError, 'DenseIntArray#delete is not implemented.'
+    end
+
+    # Does nothing
+    def sort!(&block)
+      # does nothing
+      self
+    end
+
+    # Does nothing
+    def uniq!
+      # does nothing
+      self
+    end
+  end #class DenseIntArray
+
+end #class RestrictionEnzyme
+end #module Bio

data/lib/bio/util/restriction_enzyme/range/sequence_range.rb

@@ -5,7 +5,7 @@
 # Copyright:: Copyright (c) 2005-2007 Midwinter Laboratories, LLC (http://midwinterlabs.com)
 # License::   The Ruby License
 #
-#  $Id: sequence_range.rb,v 1.9 2007/07/16 19:28:48 k Exp $
+#  $Id:$
 #
 
 require 'bio/util/restriction_enzyme'
@@ -160,7 +160,7 @@ class SequenceRange
     @__fragments_current = true
     
     num_txt = '0123456789'
-    num_txt_repeat = (num_txt * ( @size / num_txt.size.to_f ).ceil)[0..@size-1]
+    num_txt_repeat = (num_txt * ( @size.div(num_txt.size) + 1))[0..@size-1]
     fragments = Fragments.new(num_txt_repeat, num_txt_repeat)
 
     cc = Bio::RestrictionEnzyme::Range::SequenceRange::CalculatedCuts.new(@size)
@@ -193,9 +193,9 @@ class SequenceRange
   # * +cc+: Bio::RestrictionEnzyme::Range::SequenceRange::CalculatedCuts
   # *Returns*:: +Hash+ Keys are unique, values are Bio::RestrictionEnzyme::Range::SequenceRange::Bin objects filled with indexes of the sequence locations they represent.
   def create_bins(cc)
-    p_cut = cc.vc_primary
-    c_cut = cc.vc_complement
-    h_cut = cc.hc_between_strands
+    p_cut = cc.vc_primary_as_original_class
+    c_cut = cc.vc_complement_as_original_class
+    h_cut = cc.hc_between_strands_as_original_class
     
     if @circular
       # NOTE
@@ -247,8 +247,8 @@ class SequenceRange
   # initializing the bin.
   def setup_new_bin(bins, bin_id)
     bins[ bin_id ] = Bin.new
-    bins[ bin_id ].p = []
-    bins[ bin_id ].c = []
+    bins[ bin_id ].p = DenseIntArray[] #could be replaced by SortedNumArray[]
+    bins[ bin_id ].c = DenseIntArray[] #could be replaced by SortedNumArray[] 
   end
   
 end # SequenceRange