bio 1.5.1 → 2.0.2

data/lib/bio/db/gff.rb

@@ -359,7 +359,9 @@ module Bio
         # Parses a GFF2-formatted line and returns a new
         # Bio::GFF::GFF2::Record object.
         def self.parse(str)
-          self.new.parse(str)
+          ret = self.new
+          ret.parse(str)
+          ret
         end
        
         # Creates a Bio::GFF::GFF2::Record object.

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

@@ -210,6 +210,20 @@ class KEGG
       private :strings_as_hash
     end #module StringsAsHash
 
+    # This module provides diseases_as_hash method.
+    #
+    # Bio::KEGG::* internal use only.
+    module DiseasesAsHash 
+      include StringsAsHash
+      # Returns a Hash of the disease ID and its definition
+      def diseases_as_hash
+        unless (defined? @diseases_as_hash) && @diseases_as_hash
+          @diseases_as_hash = strings_as_hash(diseases_as_strings)
+        end
+        @diseases_as_hash
+      end
+    end #module DiseasesAsHash
+
   end #module Common
 end #class KEGG
 end #module Bio

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

@@ -107,6 +107,11 @@ class GENES < KEGGDB
   def orthologs_as_hash; super; end if false #dummy for RDoc
   alias orthologs orthologs_as_hash
 
+  include Common::DiseasesAsHash
+  # Returns a Hash of the disease ID and its definition
+  def diseases_as_hash; super; end if false #dummy for RDoc
+  alias diseases diseases_as_hash
+
   # Creates a new Bio::KEGG::GENES object.
   # ---
   # *Arguments*:
@@ -238,6 +243,27 @@ class GENES < KEGGDB
     lines_fetch('PATHWAY')
   end
 
+  # Networks described in the NETWORK lines.
+  # ---
+  # *Returns*:: Array containing String
+  def networks_as_strings
+    lines_fetch('NETWORK')
+  end
+
+  # Diseases described in the DISEASE lines.
+  # ---
+  # *Returns*:: Array containing String
+  def diseases_as_strings
+    lines_fetch('DISEASE')
+  end
+  
+  # Drug targets described in the DRUG_TARGET lines.
+  # ---
+  # *Returns*:: Array containing String
+  def drug_targets_as_strings
+    lines_fetch('DRUG_TARGET')
+  end
+
   # Returns CLASS field of the entry.
   def keggclass
     field_fetch('CLASS')

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

@@ -42,6 +42,11 @@ class PATHWAY < KEGGDB
   def orthologs_as_hash; super; end if false #dummy for RDoc
   alias orthologs orthologs_as_hash
 
+  include Common::DiseasesAsHash
+  # Returns a Hash of the disease ID and its definition
+  def diseases_as_hash; super; end if false #dummy for RDoc
+  alias diseases diseases_as_hash
+
   include Common::References
   # REFERENCE -- Returns contents of the REFERENCE records as an Array of
   # Bio::Reference objects.
@@ -122,17 +127,6 @@ class PATHWAY < KEGGDB
     lines_fetch('DISEASE')
   end
 
-  # Diseases described in the DISEASE lines.
-  # ---
-  # *Returns*:: Hash of disease ID and its definition
-  def diseases_as_hash
-    unless (defined? @diseases_as_hash) && @diseases_as_hash
-      @diseases_as_hash = strings_as_hash(diseases_as_strings)
-    end
-    @diseases_as_hash
-  end
-  alias diseases diseases_as_hash
-
   # Returns an Array of a database name and entry IDs in DBLINKS field.
   # ---
   # *Returns*:: Array containing String

data/lib/bio/db/soft.rb

@@ -217,13 +217,13 @@ class SOFT
       end
       
       def [](x)
-        if x.kind_of?( Fixnum )
+        if x.kind_of?( Integer )
           super(x)
         else
           begin
             x = x.to_s.downcase.to_sym
             z = @header_object.column_index[x]
-            unless z.kind_of?( Fixnum )
+            unless z.kind_of?( Integer )
               raise IndexError, "#{x.inspect} is not a valid index.  Contents of @header_object.column_index: #{@header_object.column_index.inspect}"
             end
             self[ z ]

data/lib/bio/io/flatfile/autodetection.rb

@@ -547,6 +547,11 @@ module Bio
         #BottomRule.is_prior_to(debug_last)
         #fastaformat.is_prior_to(debug_last)
 
+        ## for suppressing warnings
+        p medline, aaindex, litdb, fantom, clustal,
+          gcg_msf, gcg_seq, blastxml, rpsblast, blat,
+          spidey, hmmer, sim4 if false
+
         a.rehash
         return a
       end

data/lib/bio/io/togows.rb

@@ -107,14 +107,14 @@ module Bio
     # 
     # For light users, class methods can be used.
     #
-    #   print Bio::TogoWS::REST.entry('genbank', 'AF237819')
+    #   print Bio::TogoWS::REST.entry('ncbi-nucleotide', 'AF237819')
     #   print Bio::TogoWS::REST.search('uniprot', 'lung cancer')
     #
     # For heavy users, an instance of the REST class can be created, and
     # using the instance is more efficient than using class methods.
     #
     #   t = Bio::TogoWS::REST.new
-    #   print t.entry('genbank', 'AF237819')
+    #   print t.entry('ncbi-nucleotide', 'AF237819')
     #   print t.search('uniprot', 'lung cancer')
     #
     # == References
@@ -222,9 +222,9 @@ module Bio
       #
       # Example:
       #   t = Bio::TogoWS::REST.new
-      #   kuma = t.entry('genbank', 'AF237819')
+      #   kuma = t.entry('ncbi-nucleotide', 'AF237819')
       #   # multiple IDs at a time
-      #   misc = t.entry('genbank', [ 'AF237819', 'AF237820' ])
+      #   misc = t.entry('ncbi-nucleotide', [ 'AF237819', 'AF237820' ])
       #   # with format change
       #   p53 = t.entry('uniprot', 'P53_HUMAN', 'fasta')
       #
@@ -366,7 +366,7 @@ module Bio
       # Access to the TogoWS by using GET method.
       #
       # Example 1:
-      #   get('entry', 'genbank', AF209156')
+      #   get('entry', 'ncbi-nucleotide', AF209156')
       # Example 2:
       #   get('search', 'uniprot', 'lung cancer')
       #

data/lib/bio/map.rb

@@ -90,7 +90,7 @@ module Bio
     #   class MyMapThing
     #     include Bio::Map::ActsLikeMap
     #     
-    #     def initialize (name)
+    #     def initialize(name)
     #       @name = name
     #       @mappings_as_maps = Array.new
     #     end
@@ -177,7 +177,7 @@ module Bio
     #   class MyMarkerThing
     #     include Bio::Map::ActsLikeMarker
     #     
-    #     def initialize (name)
+    #     def initialize(name)
     #       @name = name
     #       @mappings_as_marker = Array.new
     #     end
@@ -301,7 +301,7 @@ module Bio
       # * _map_: a Bio::Map::SimpleMap object
       # * _marker_: a Bio::Map::Marker object
       # * _location_: a Bio::Locations object
-      def initialize (map, marker, location = nil)
+      def initialize(map, marker, location = nil)
         @map, @marker, @location = map, marker, location
       end
       attr_accessor :map, :marker, :location
@@ -350,7 +350,7 @@ module Bio
       # * type: type of the map (e.g. linkage, radiation_hybrid, cytogenetic, ...)
       # * units: unit of the map (e.g. cM, cR, ...)
       # *Returns*:: new Bio::Map::SimpleMap object
-      def initialize (name = nil, type = nil, length = nil, units = nil)
+      def initialize(name = nil, type = nil, length = nil, units = nil)
         @name, @type, @length, @units = name, type, length, units
         @mappings_as_map = Array.new
       end

data/lib/bio/sequence/format.rb

@@ -10,6 +10,7 @@
 #
 
 require 'erb'
+require 'date'
 
 module Bio
 

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

@@ -151,7 +151,7 @@ class CalculatedCuts
   def remove_incomplete_cuts(size=nil)
     @strands_for_display_current = false
     @size = size if size
-    raise IndexError, "Size of the strand must be provided here or during initalization." if !@size.kind_of?(Fixnum) and not @circular
+    raise IndexError, "Size of the strand must be provided here or during initalization." if !@size.kind_of?(Integer) and not @circular
 
     vcuts = @vc_primary + @vc_complement
     hcuts = @hc_between_strands

data/lib/bio/util/sirna.rb

@@ -278,6 +278,8 @@ module Bio
       
       # human readable report
       def report
+        # raise NomethodError for compatibility
+        raise NoMethodError if !defined?(@top_strand) || !@top_strand
         report = "### shRNA\n"
         report << "Top strand shRNA (#{@top_strand.length} nt):\n"
         report << "  5'-#{@top_strand.upcase}-3'\n"

data/lib/bio/version.rb

@@ -10,19 +10,17 @@
 module Bio
 
   # BioRuby version (Array containing Integer)
-  BIORUBY_VERSION = [1, 5, 1].extend(Comparable).freeze
+  BIORUBY_VERSION = [2, 0, 2].extend(Comparable).freeze
 
   # Extra version specifier (String or nil).
   # Existance of the value indicates development version.
   #
-  # nil                 :: Release version.
-  # "-dev"              :: Development version (with YYYYMMDD digits).
-  # ".20150630"         :: Development version (specify the date digits).
+  # nil             :: Release version.
+  # ".pre           :: Pre-release version.
   #
-  # By default, if the third digit (teeny) of BIORUBY_VERSION is 0,
-  # the version is regarded as a development version.
-  BIORUBY_EXTRA_VERSION =
-    nil #"-dev" #(BIORUBY_VERSION[2] == 0) ? "-dev" : nil
+  # References: https://guides.rubygems.org/patterns/#prerelease-gems
+  BIORUBY_EXTRA_VERSION = nil
+    #".pre"
 
   # Version identifier, including extra version string (String)
   # Unlike BIORUBY_VERSION, it is not comparable.

data/sample/color_scheme_aa.rb

@@ -0,0 +1,82 @@
+#!/usr/bin/env ruby
+#
+# color_scheme_aa.rb - A Bio::ColorScheme demo script for Amino Acid sequences.
+#
+#  Usage:
+#
+#   % ruby color_scheme_aa.rb > cs-seq-faa.html
+#
+#   % cat seq.faa
+#   >AA_sequence
+#   MKRISTTITTTITITTGNGAG
+#   % ruby color_scheme_aa.rb seq.faa > colored-seq-faa.html
+#
+#
+# Copyright::  Copyright (C) 2005
+#              Mitsuteru C. Nakao <n@bioruby.org>
+# License::    The Ruby License
+#
+
+require 'bio'
+
+
+# returns folded sequence with <br>.
+def br(i, width = 80)
+  return "<br\n>"  if i % width == 0
+  ""
+end
+
+
+# returns sequence html doc
+def display(seq, cs)
+  html = '<p style="font-family: monospace">'
+  postfix = '</span>'
+  i = 0
+  seq.each_char do |c|
+    color = cs[c]
+    prefix = %Q(<span style="background:\##{color};">)
+    html += prefix + c + postfix
+    html += br(i += 1)
+  end
+  html + '</p>'
+end
+
+
+# returns scheme wise html doc
+def display_scheme(scheme, aaseq)
+  html = ''
+  cs = Bio::ColorScheme.const_get(scheme.intern)
+  [aaseq].each do |seq|
+    html += display(seq, cs)
+  end
+  return  ['<div>', "<h3>#{cs}</h3>", html, '</div>']
+end
+
+
+
+if fna = ARGV.shift
+  aaseq = Bio::FlatFile.open(fna) { |ff| ff.next_entry.aaseq }
+else
+  aaseq = Bio::Sequence::AA.new('ARNDCQEGHILKMFPSTWYV' * 20).randomize
+end
+
+title =  'Bio::ColorScheme for amino acid sequences'
+doc = ['<html>',
+       '<header>', '<title>', title, '</title>', '</header>',
+       '<body>',  '<h1>', title, '</h1>']
+
+doc << ['<div>', '<h2>', 'Simple colors', '</h2>']
+
+['Zappo', 'Taylor' ].each do |scheme|
+  doc << display_scheme(scheme, aaseq)
+end
+doc << ['</div>']
+
+
+doc << ['<div>', '<h2>', 'Score colors', '</h2>']
+['Buried', 'Helix', 'Hydropathy', 'Strand', 'Turn'].each do |score|
+  doc << display_scheme(score, aaseq)
+end
+doc << ['</div>']
+
+puts doc + ['</body>','</html>']

data/sample/color_scheme_na.rb

@@ -17,7 +17,6 @@
 #              Mitsuteru C. Nakao <n@bioruby.org>
 # License::    The Ruby License
 #
-#  $Id: color_scheme_na.rb,v 1.3 2007/04/05 23:35:42 trevor Exp $
 #
 
 require 'bio'
@@ -35,10 +34,10 @@ def display(seq, cs)
   html = '<p style="font-family: monospace">'
   postfix = '</span>'
   i = 0
-  seq.each_byte do |c|
-    color = cs[c.chr]
+  seq.each_char do |c|
+    color = cs[c]
     prefix = %Q(<span style="background:\##{color};">)
-    html += prefix + c.chr + postfix
+    html += prefix + c + postfix
     html += br(i += 1)
   end
   html + '</p>'
@@ -48,7 +47,7 @@ end
 # returns scheme wise html doc
 def display_scheme(scheme, naseq, aaseq)
   html = ''
-  cs = eval("Bio::ColorScheme::#{scheme}")
+  cs = Bio::ColorScheme.const_get(scheme.intern)
   [naseq, aaseq].each do |seq|
     html += display(seq, cs)
   end
@@ -58,7 +57,7 @@ end
 
 
 if fna = ARGV.shift
-  naseq = Bio::FastaFormat.new(File.open(fna, 'r').read).naseq
+  naseq = Bio::FlatFile.open(fna) { |ff| ff.next_entry.naseq }
   aaseq = naseq.translate
 else
   naseq = Bio::Sequence::NA.new('acgtu' * 20).randomize

data/sample/fastq2html.cwl

@@ -0,0 +1,23 @@
+#!/usr/bin/env cwl-runner
+
+cwlVersion: v1.0
+class: CommandLineTool
+baseCommand: [ruby]
+
+inputs:
+ - id: script
+   type: File
+   default:
+     class: File
+     location: fastq2html.rb
+   inputBinding:
+     position: -1
+ - id: fastq
+   type: File[]
+   inputBinding:
+     position: 1
+
+outputs:
+ - id: out
+   type: stdout
+stdout: $(inputs.script.nameroot)-$(inputs.fastq[0].nameroot).html

data/sample/fastq2html.rb

@@ -0,0 +1,94 @@
+#!/usr/bin/env ruby
+#
+# fastq2html.rb - HTML visualization of FASTQ sequences
+#
+#  Usage:
+#
+#   % ruby fastq2html.rb seq00.fastq > seq00.html
+#
+#
+# Copyright::  Copyright (C) 2019 BioRuby Project
+#              Copyright (C) 2005 Mitsuteru C. Nakao <n@bioruby.org>
+# License::    The Ruby License
+#
+#
+
+require 'bio'
+
+# thickness to color
+def thickness2color(t)
+  c = "%02X" % ((t * 255.0).to_i)
+  c * 3
+end
+
+# Creates 
+def create_score2color_hashes
+  h_bg = {}
+  h_char = {}
+  cutoff_low = 0
+  cutoff_high = 50
+  range = cutoff_high - cutoff_low
+  sc_min = -5
+  sc_max = 100
+  (sc_min..sc_max).each do |i|
+    t = if i <= cutoff_low then
+          0.0
+        elsif i >= cutoff_high then
+          1.0
+        else
+          (i - cutoff_low).to_f / range
+        end
+    h_bg[i] = thickness2color(t)
+    h_char[i] = thickness2color((t > 0.3) ? 0.0 : 0.55)
+  end
+  h_bg.default = h_bg[cutoff_low]
+  h_char.default = h_char[cutoff_low]
+  [h_bg, h_char]
+end
+
+# Color code from quality score
+SCORE2COLOR_BG, SCORE2COLOR_CHAR = create_score2color_hashes
+
+# returns folded sequence with <br>.
+def br(i, width = 80)
+  return "<br\n>"  if i % width == 0
+  ""
+end
+
+# returns sequence html doc
+def display(naseq, scores)
+  html = '<p style="font-family: monospace">'
+  postfix = '</span>'
+  i = 0
+  naseq.each_char.with_index do |c, i|
+    sc = scores[i]
+    bgcol = SCORE2COLOR_BG[sc]
+    col = SCORE2COLOR_CHAR[sc]
+    prefix = %Q(<span style="color:\##{col}; background:\##{bgcol};">)
+    html += prefix + c + postfix
+    html += br(i += 1)
+  end
+  html + '</p>'
+end
+
+# returns colorized html doc
+def fastq2html(definition, naseq, scores)
+  html = display(naseq, scores)
+  return  ['<div>', "<div>&gt;#{CGI.escapeHTML(definition)}</div>", html, '</div>']
+end
+
+title =  'Sequences with quality scores'
+puts ['<html>',
+       '<header>', '<title>', title, '</title>', '</header>',
+       '<body>',  '<h1>', title, '</h1>']
+
+#main loop
+ARGV.each do |filename|
+  Bio::FlatFile.open(filename) do |ff|
+    ff.each do |e|
+      puts fastq2html(e.definition, e.naseq, e.quality_scores)
+    end
+  end
+end
+
+puts ['</body>','</html>']