bio 1.6.0.pre.20181210 → 2.0.3

data/gemfiles/Gemfile.travis-rbx

@@ -3,8 +3,6 @@ source "https://rubygems.org"
 gem "rake"
 gem "rdoc"
 
-gem "xmlparser"
-
 platforms :rbx do
   gem 'racc'
   gem 'rubysl', '~> 2.0'

data/gemfiles/Gemfile.travis-ruby1.8

@@ -4,5 +4,3 @@ gem "rake", "~>10.4"
 # rdoc 4.3.0 requires Ruby >= 1.9.3
 gem "rdoc", "~>4.2.0"
 
-gem "xmlparser", "~>0.7.2"
-

data/gemfiles/Gemfile.travis-ruby1.9

@@ -3,5 +3,3 @@ source "https://rubygems.org"
 gem "rake"
 gem "rdoc"
 
-gem "xmlparser"
-

data/gemfiles/Gemfile.windows

@@ -0,0 +1,6 @@
+source "https://rubygems.org"
+
+gem "rake"
+gem "rdoc"
+gem "test-unit"
+

data/lib/bio/appl/blast/report.rb

@@ -43,18 +43,20 @@ class Report
   #--
   # require lines moved here to avoid circular require
   #++
-  require 'bio/appl/blast/xmlparser'
   require 'bio/appl/blast/rexml'
   require 'bio/appl/blast/format8'
 
+  #--
+  # loading bio-blast-xmlparser plugin if available
+  #++
+  begin
+    require 'bio-blast-xmlparser'
+  rescue LoadError
+  end
+
   # for Bio::FlatFile support (only for XML data)
   DELIMITER = RS = "</BlastOutput>\n"
 
-  # Specify to use XMLParser to parse XML (-m 7) output.
-  def self.xmlparser(data)
-    self.new(data, :xmlparser)
-  end
-
   # Specify to use REXML to parse XML (-m 7) output.
   def self.rexml(data)
     self.new(data, :rexml)
@@ -67,7 +69,7 @@ class Report
 
   def auto_parse(data)
     if /<?xml/.match(data[/.*/])
-      if defined?(XMLParser)
+      if defined? xmlparser_parse
         xmlparser_parse(data)
         @reports = blastxml_split_reports
       else
@@ -87,7 +89,11 @@ class Report
     @parameters = {}
     case parser
     when :xmlparser		# format 7
-      xmlparser_parse(data)
+      if defined? xmlparser_parse
+        xmlparser_parse(data)
+      else
+        raise NameError, "xmlparser_parse does not defined"
+      end
       @reports = blastxml_split_reports
     when :rexml		# format 7
       rexml_parse(data)
@@ -383,6 +389,32 @@ class Report
   attr_reader :reports
  
   private
+  # set parameter of the key as val
+  def xml_set_parameter(key, val)
+    #labels = { 
+    #  'matrix'       => 'Parameters_matrix',
+    #  'expect'       => 'Parameters_expect',
+    #  'include'      => 'Parameters_include',
+    #  'sc-match'     => 'Parameters_sc-match',
+    #  'sc-mismatch'  => 'Parameters_sc-mismatch',
+    #  'gap-open'     => 'Parameters_gap-open',
+    #  'gap-extend'   => 'Parameters_gap-extend',
+    #  'filter'       => 'Parameters_filter',
+    #  'pattern'      => 'Parameters_pattern',
+    #  'entrez-query' => 'Parameters_entrez-query',
+    #}
+    k = key.sub(/\AParameters\_/, '')
+    @parameters[k] =
+      case k
+      when 'expect', 'include'
+        val.to_f
+      when /\Agap\-/, /\Asc\-/
+        val.to_i
+      else
+        val
+      end
+  end
+
   # (private method)
   # In new BLAST XML (blastall >= 2.2.14), results of multiple queries
   # are stored in <Iteration>. This method splits iterations into

data/lib/bio/appl/iprscan/report.rb

@@ -83,7 +83,7 @@ module Bio
         yield Bio::Iprscan::Report.parse_raw_entry(entry) if entry != ''
       end
     
-      # Parser method for a raw formated entry. Retruns a Bio::Iprscan::Report 
+      # Parser method for a raw formated entry. Returns a Bio::Iprscan::Report 
       # object.
       def self.parse_raw_entry(str)
         report = self.new
@@ -113,7 +113,7 @@ module Bio
 
 
 
-      # Parser method for a xml formated entry. Retruns a Bio::Iprscan::Report 
+      # Parser method for a xml formated entry. Returns a Bio::Iprscan::Report 
       # object.
 #      def self.parse_xml(str)
 #      end
@@ -196,7 +196,7 @@ module Bio
         end
       end
 
-      # Parser method for a pseudo-txt formated entry. Retruns a Bio::Iprscan::Report 
+      # Parser method for a pseudo-txt formated entry. Returns a Bio::Iprscan::Report 
       # object.
       # 
       # == Usage

data/lib/bio/appl/sosui/report.rb

@@ -78,7 +78,7 @@ module Bio
         # Returns aRng of transmembrane helix
         attr_reader :range
         
-        # Retruns ``PRIMARY'' or ``SECONDARY'' of helix.
+        # Returns ``PRIMARY'' or ``SECONDARY'' of helix.
         attr_reader :grade
 
         # Returns the sequence. of transmembrane helix. 

data/lib/bio/db/embl/uniprotkb.rb

@@ -174,7 +174,7 @@ class UniProtKB < EMBLDB
   #
   # http://www.uniprot.org/docs/sp_news.htm
   def parse_DE_line_rel14(str)
-    # Retruns if it is not the new format since Rel.14
+    # Returns if it is not the new format since Rel.14
     return nil unless /^DE   (RecName|AltName|SubName)\: / =~ str
     ret = []
     cur = nil

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/go.rb

@@ -193,7 +193,7 @@ class GO
     # Delimiter
     RS = DELIMITER 
 
-    # Retruns an Array of parsed gene_association flatfile.
+    # Returns an Array of parsed gene_association flatfile.
     # Block is acceptable.  
     def self.parser(str)
       if block_given?
@@ -226,7 +226,7 @@ class GO
     # Returns Db_Reference variable.
     attr_reader :db_reference      # -> []
 
-    # Retruns Evidence code variable.
+    # Returns Evidence code variable.
     attr_reader :evidence
 
     # Returns the entry is associated with this value.

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/sequence/common.rb

@@ -303,6 +303,118 @@ module Common
   end
   alias splicing splice
 
+#--
+# Workaround for Ruby 3.0.0 incompatible changes
+if ::RUBY_VERSION > "3"
+
+  # Acts almost the same as String#split.
+  def split(*arg)
+    if block_given?
+      super
+    else
+      ret = super(*arg)
+      ret.collect! { |x| self.class.new('').replace(x) }
+      ret
+    end
+  end
+
+  %w( * ljust rjust center ).each do |w|
+    module_eval %Q{
+      def #{w}(*arg)
+        self.class.new('').replace(super)
+      end
+    }
+  end
+
+  %w( chomp chop
+      delete delete_prefix delete_suffix
+      lstrip rstrip strip
+      reverse
+      squeeze
+      succ next
+      tr tr_s
+      capitalize upcase downcase swapcase
+  ).each do |w|
+    module_eval %Q{
+      def #{w}(*arg)
+        s = self.dup
+        s.#{w}!(*arg)
+        s
+      end
+    }
+  end
+
+  %w( sub gsub ).each do |w|
+    module_eval %Q{
+      def #{w}(*arg, &block)
+        s = self.dup
+        s.#{w}!(*arg, &block)
+        s
+      end
+    }
+  end
+
+  #Reference: https://nacl-ltd.github.io/2018/11/08/gsub-wrapper.html
+  #(Title: Is it possible to implement gsub wrapper?)
+  %w( sub! gsub! ).each do |w|
+    module_eval %Q{
+      def #{w}(*arg, &block)
+        if block_given? then
+          super(*arg) do |m|
+            b = Thread.current[:_backref]
+            Thread.current[:_backref] = ::Regexp.last_match
+            block.binding.eval("$~ = Thread.current[:_backref]")
+            Thread.current[:_backref] = b
+            block.call(self.class.new('').replace(m))
+          end
+        else
+          super
+        end
+      end
+    }
+  end
+
+  %w( each_char each_grapheme_cluster each_line ).each do |w|
+    module_eval %Q{
+      def #{w}
+        if block_given?
+          super { |c| yield(self.class.new('').replace(c)) }
+        else
+          enum_for(:#{w})
+        end
+     end
+    }
+  end
+
+  %w( slice [] slice! ).each do |w|
+    module_eval %Q{
+      def #{w}(*arg)
+        r = super
+        r ? self.class.new('').replace(r) : r
+      end
+    }
+  end
+
+  %w( partition rpartition ).each do |w|
+    module_eval %Q{
+      def #{w}(sep)
+        r = super
+        if r.kind_of?(Array)
+          r[1] == sep ?
+            [ self.class.new('').replace(r[0]),
+              r[1],
+              self.class.new('').replace(r[2]) ] :
+            r.collect { |x| self.class.new('').replace(x) }
+        else
+          r
+        end
+      end
+    }
+  end
+#++
+
+end # if ::RUBY_VERSION > "3"
+
 end # Common
 
 end # Sequence

data/lib/bio/sequence/format.rb

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

data/lib/bio/tree.rb

@@ -605,7 +605,7 @@ module Bio
     end
 
     # Gets path from node1 to node2.
-    # Retruns an array of nodes, including node1 and node2.
+    # Returns an array of nodes, including node1 and node2.
     # If node1 and/or node2 do not exist, IndexError is raised.
     # If node1 and node2 are not connected, NoPathError is raised.
     # The result is unspecified for cyclic trees.

data/lib/bio/version.rb

@@ -10,7 +10,7 @@
 module Bio
 
   # BioRuby version (Array containing Integer)
-  BIORUBY_VERSION = [1, 6, 0].extend(Comparable).freeze
+  BIORUBY_VERSION = [2, 0, 3].extend(Comparable).freeze
 
   # Extra version specifier (String or nil).
   # Existance of the value indicates development version.
@@ -19,8 +19,8 @@ module Bio
   # ".pre           :: Pre-release version.
   #
   # References: https://guides.rubygems.org/patterns/#prerelease-gems
-  BIORUBY_EXTRA_VERSION = #nil
-    ".pre"
+  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>']

data/sample/fastq2html.testdata.yaml

@@ -0,0 +1,5 @@
+fastq:
+  - class: File
+    location: ../test/data/fastq/longreads_as_sanger.fastq
+  - class: File
+    location: ../test/data/fastq/sanger_full_range_original_sanger.fastq