rubabel 0.1.5 → 0.1.6

data/Rakefile

@@ -16,7 +16,8 @@ interface attempts to be a ruby-ish analogue of pybel.}
   gem.authors = ["John T. Prince"]
   [
     ["openbabel", "~> 2.3.1.2"],
-    ["andand", "~> 1.3.3"]
+    ["andand", "~> 1.3.3"],
+    ["mini_magick", "~> 3.4"]
   ].each do |args|
     gem.add_dependency(*args)
   end

data/VERSION

@@ -1 +1 @@
-0.1.5
+0.1.6

data/lib/rubabel.rb

@@ -66,7 +66,7 @@ module Rubabel
       (obmol, obconv, not_at_end) = read_first_obmol(filename, type)
       # the obmol is not valid if we are already at the end!
       while not_at_end
-        block.call Rubabel::Molecule.new(obmol, obconv)
+        block.call Rubabel::Molecule.new(obmol)
         obmol = OpenBabel::OBMol.new
         not_at_end = obconv.read(obmol)
       end
@@ -77,19 +77,14 @@ module Rubabel
     # determines the type from the extension if type is nil.
     def molecule_from_file(filename, type=nil)
       (obmol, obconv, not_at_end) = read_first_obmol(filename, type).first
-      Rubabel::Molecule.new(obmol, obconv)
+      Rubabel::Molecule.new(obmol)
     end
 
     # reads one molecule from the string
-    def molecule_from_string(string, type=:smi)
-      obmol = OpenBabel::OBMol.new
-      obconv = OpenBabel::OBConversion.new
-      obconv.set_in_format(type.to_s) || raise(ArgumentError, "invalid format #{type}")
-      obconv.read_string(obmol, string) || raise(ArgumentError, "invalid string" )
-      Rubabel::Molecule.new(obmol, obconv)
+    def molecule_from_string(string, type=Rubabel::Molecule::DEFAULT_IN_TYPE)
+      Rubabel::Molecule.from_string(string, type)
     end
 
-    private
     # reads the first entry and returns the OBMol object, the OBConversion object,
     # and the boolean not_at_end.  This method is not intended for public usage
     # but is necessary based on discrepancies between accessing the first

data/lib/rubabel/atom.rb

@@ -14,11 +14,12 @@ module Rubabel
     include Enumerable
 
     class << self
-      # takes an element symbol and creates that atom
-      def [](el_sym=:h, id=0)
+      # takes an element symbol and creates that atom.  If el_sym is set to
+      # nil or 0, then an atom of atomic number 0 is used
+      def [](el_sym=:h, id=nil)
         ob_atom = OpenBabel::OBAtom.new
-        ob_atom.set_id(id)
-        ob_atom.set_atomic_num(Rubabel::EL_TO_NUM[el_sym])
+        ob_atom.set_id(id) if id
+        ob_atom.set_atomic_num(Rubabel::EL_TO_NUM[el_sym] || 0)
         self.new(ob_atom)
       end
     end

data/lib/rubabel/molecule.rb

@@ -3,6 +3,8 @@ require 'rubabel'
 require 'rubabel/atom'
 require 'rubabel/bond'
 require 'rubabel/molecule/fragmentable'
+require 'stringio'
+require 'mini_magick'
 
 class OpenBabel::OBMol
   def upcast
@@ -10,11 +12,65 @@ class OpenBabel::OBMol
   end
 end
 
+class OpenBabel::OBConversion
+  OUT_OPTS_SHORT = {
+    no_element_coloring: :u,
+    no_internal_specified_color: :U,
+    black_bkg: :b,
+    no_terminal_c: :C,
+    draw_all_carbon: :a,
+    no_molecule_name: :d,
+    embed_mol_as_cml: :e,
+    scale_to_bondlength_pixels: :p,
+    size: :P, # single number of pixels (e.g., 300, but will take dims for png: ('300x250'))
+    add_atom_index: :i,
+    no_javascript: :j,
+    wedge_hash_bonds: :w,
+    no_xml_declaration: :x,
+    aliases: :A,
+  }
+
+  # adds the opts to the type, where type is :gen, :out, or :in.
+  # takes opts as either a hash or a list:
+  #
+  #     # hash
+  #     obconv.add_opts!(:out, d: true, u: true, p: 10 ) 
+  #
+  #     # list
+  #     obconv.add_opts!(:out, :d, :u, [:p, 10] )
+  #
+  # returns self
+  def add_opts!(type=:gen, *opts)
+    opt_type = OpenBabel::OBConversion.const_get(type.to_s.upcase.<<("OPTIONS"))
+    hash = 
+      if opts.first.is_a?(Hash)
+        opts.first
+      else
+        opts.inject({}) do |hsh,v| 
+          if v.is_a?(Array)
+            hsh[v[0]] = v[1]
+          else
+            hsh[v] = true
+          end
+          hsh
+        end
+      end
+    hash.each do |k,v|
+      next if v == false
+      args = [ (OUT_OPTS_SHORT[k] || k).to_s, opt_type ]
+      if v && (v != true)
+        args << v
+      end
+      self.add_option(*args)
+    end
+    self
+  end
+end
+
 class OpenBabelUnableToSetupForceFieldError < RuntimeError
 end
 
 module Rubabel
-    # yet to implement: 
   class Molecule
     include Enumerable
 
@@ -25,9 +81,6 @@ module Rubabel
     # the OpenBabel::OBmol object
     attr_accessor :ob
 
-    # the OpenBabel::OBConversion object
-    attr_accessor :obconv
-
     class << self
 
       def tanimoto(mol1, mol2, type=DEFAULT_FINGERPRINT)
@@ -35,11 +88,16 @@ module Rubabel
       end
 
       def from_file(file, type=nil)
-        Rubabel.molecule_from_file(file, type)
+        (obmol, obconv, not_at_end) = Rubabel.read_first_obmol(file, type).first
+        Rubabel::Molecule.new(obmol)
       end
 
       def from_string(string, type=DEFAULT_IN_TYPE)
-        Rubabel.molecule_from_string(string, type)
+        obmol = OpenBabel::OBMol.new
+        obconv = OpenBabel::OBConversion.new
+        obconv.set_in_format(type.to_s) || raise(ArgumentError, "invalid format #{type}")
+        obconv.read_string(obmol, string) || raise(ArgumentError, "invalid string" )
+        self.new(obmol)
       end
 
       def from_atoms_and_bonds(atoms=[], bonds=[])
@@ -50,8 +108,13 @@ module Rubabel
       end
     end
 
-    def add_atom(atom)
-      @ob.add_atom(atom.ob)
+    # arg is an atomic number. returns the newly created atom
+    def add_atom!(atomic_num=1)
+      # jtp implementation:
+      # @ob.add_atom(atom.ob)
+      new_a = @ob.new_atom
+      new_a.set_atomic_num(atomic_num)
+      Rubabel::Atom.new(new_a)
     end
 
     def delete_atom(atom)
@@ -82,34 +145,35 @@ module Rubabel
     def formula() @ob.get_formula end
 
 
-    def initialize(obmol, obconv=nil)
+    def initialize(obmol)
       @ob = obmol
-      @obconv = obconv
     end
 
-    # returns a list of atom indices matching the patterns (corresponds to
-    # the OBSmartsPattern::GetUMapList() method).  Note that the original
-    # GetUMapList returns atom *numbers* (i.e., the index + 1).  This method
-    # returns the zero indexed indices.
-    def smarts_indices(smarts_or_string)
+    # returns a list of atom indices matching the patterns (corresponds to the
+    # OBSmartsPattern::GetUMapList() method if uniq==true and GetMapList
+    # method if uniq==false).  Note that the original GetUMapList returns atom
+    # *numbers* (i.e., the index + 1).  This method returns the zero indexed
+    # indices.
+    def smarts_indices(smarts_or_string, uniq=true)
+      mthd = uniq ? :get_umap_list : :get_map_list
       pattern = smarts_or_string.is_a?(Rubabel::Smarts) ? smarts_or_string : Rubabel::Smarts.new(smarts_or_string)
       pattern.ob.match(@ob)
-      pattern.ob.get_umap_list.map {|atm_indices| atm_indices.map {|i| i - 1 } }
+      pattern.ob.send(mthd).map {|atm_indices| atm_indices.map {|i| i - 1 } }
     end
 
     # yields atom arrays matching the pattern.  returns an enumerator if no
     # block is given
-    def each_match(smarts_or_string, &block)
-      block or return enum_for(__method__, smarts_or_string)
+    def each_match(smarts_or_string, uniq=true, &block)
+      block or return enum_for(__method__, smarts_or_string, uniq)
       _atoms = self.atoms
-      smarts_indices(smarts_or_string).each do |ar|
+      smarts_indices(smarts_or_string, uniq).each do |ar|
         block.call(_atoms.values_at(*ar))
       end
     end
 
     # returns an array of matching atom sets.  Consider using each_match.
-    def matches(smarts_or_string)
-      each_match(smarts_or_string).map.to_a
+    def matches(smarts_or_string, uniq=true)
+      each_match(smarts_or_string, uniq).map.to_a
     end
 
     def matches?(smarts_or_string)
@@ -123,11 +187,11 @@ module Rubabel
     end
 
     #def conformers
-      # Currently returns an object of type
-      # SWIG::TYPE_p_std__vectorT_double_p_std__allocatorT_double_p_t_t
-      #vec = @ob.get_conformers
+    # Currently returns an object of type
+    # SWIG::TYPE_p_std__vectorT_double_p_std__allocatorT_double_p_t_t
+    #vec = @ob.get_conformers
     #end
-    
+
     # are there hydrogens added yet
     def hydrogens_added?
       @ob.has_hydrogens_added
@@ -145,6 +209,12 @@ module Rubabel
       self
     end
 
+    # only adds polar hydrogens. returns self
+    def add_polar_h!
+      @ob.add_polar_hydrogens
+      self
+    end
+
     # returns self.  If ph is nil, then #neutral! is called
     def correct_for_ph!(ph=7.4)
       ph.nil? ? neutral! : @ob.correct_for_ph(ph)
@@ -170,13 +240,13 @@ module Rubabel
     #  # creates a new molecule (currently writes to smiles and uses babel
     #  # commandline to get hydrogens at a given pH; this is because no pH model
     #  # in ruby bindings currently).
-#
-#      ## write the file with the molecule
-#      #self.write_file("tmp.smi")
-#      #system "#{Rubabel::CMD[:babel]} -i smi tmp.smi -p #{ph} -o can tmp.can"
-#      #Molecule.from_file("tmp.can")
-#    end
-#    #alias_method :add_h!, :add_hydrogens!
+    #
+    #      ## write the file with the molecule
+    #      #self.write_file("tmp.smi")
+    #      #system "#{Rubabel::CMD[:babel]} -i smi tmp.smi -p #{ph} -o can tmp.can"
+    #      #Molecule.from_file("tmp.can")
+    #    end
+    #    #alias_method :add_h!, :add_hydrogens!
 
     # returns self
     def remove_h!
@@ -235,7 +305,6 @@ module Rubabel
     def initialize_copy(source)
       super
       @ob = OpenBabel::OBMol.new(source.ob)
-      @obconv = OpenBabel::OBConversion.new(source.obconv)
       self
     end
 
@@ -265,7 +334,7 @@ module Rubabel
     #end
 
     def tanimoto(other, type=DEFAULT_FINGERPRINT)
-      Rubabel::Molecule.tanimoto(self, other, type)
+      other.nil? ? 0 : Rubabel::Molecule.tanimoto(self, other, type)
     end
 
     # returns a  std::vector<unsigned int> that can be passed directly into
@@ -281,9 +350,9 @@ module Rubabel
     def delete(obj)
       case obj
       when Rubabel::Bond
-        delete_bond(obj, false)
+        delete_bond(obj)
       when Rubabel::Atom
-        delete_atom(obj, false)
+        delete_atom(obj)
       else 
         raise(ArgumentError, "don't know how to delete objects of type: #{obj.class}")
       end
@@ -305,7 +374,7 @@ module Rubabel
     end
 
     # takes a Rubabel::Bond object or a pair of Rubabel::Atom objects
-    def add_bond(*args)
+    def add_bond!(*args)
       case args.size
       when 1
         ob_bond = args.first.ob
@@ -313,10 +382,11 @@ module Rubabel
         ob_bond.get_begin_atom.add_bond(ob_bond)
         ob_bond.get_end_atom.add_bond(ob_bond)
       when 2
-        ob_bond = Rubabel::Bond[ *args ].ob
-        ob_bond.get_begin_atom.add_bond(ob_bond)
-        ob_bond.get_end_atom.add_bond(ob_bond)
-        @ob.add_bond(ob_bond)
+        @ob.add_bond(args[0].idx, args[1].idx, args[2] || 1)
+        #ob_bond = Rubabel::Bond[ *args ].ob
+        #ob_bond.get_begin_atom.add_bond(ob_bond)
+        #ob_bond.get_end_atom.add_bond(ob_bond)
+        #@ob.add_bond(ob_bond)
       end
     end
 
@@ -372,11 +442,11 @@ module Rubabel
     # If filename_or_type is a symbol, then it will return a string of that type.
     # If filename_or_type is a string, will write to the filename
     # given no args, returns a DEFAULT_OUT_TYPE string
-    def write(filename_or_type=:can)
+    def write(filename_or_type=:can, out_options={})
       if filename_or_type.is_a?(Symbol)
-        write_string(filename_or_type)
+        write_string(filename_or_type, out_options)
       else
-        write_file(filename_or_type)
+        write_file(filename_or_type, out_options)
       end
     end
 
@@ -413,23 +483,116 @@ module Rubabel
     end
     alias_method :make3d!, :make_3d!
 
-    def write_string(type=DEFAULT_OUT_TYPE)
-      @obconv ||= OpenBabel::OBConversion.new
-      @obconv.set_out_format(type.to_s)
-      @obconv.write_string(@ob)
+    # yields the type of object.  Expects the block to yield the image string.
+    def png_transformer(type_s, out_options={}, &block)
+      orig_out_options = out_options[:size]
+      if type_s == 'png'
+        png_output = true
+        type_s = 'svg'
+        if out_options[:size]
+          unless out_options[:size].to_s =~ /x/i
+            out_options[:size] = out_options[:size].to_s + 'x' + out_options[:size].to_s
+          end
+        end
+      else
+        if out_options[:size].is_a?(String) && (out_options[:size] =~ /x/i)
+          warn 'can only use the width dimension for this format'
+          out_options[:size] = out_options[:size].split(/x/i).first
+        end
+      end
+      image_blob = block.call(type_s, out_options)
+      if png_output
+        st = StringIO.new
+        image = MiniMagick::Image.read(image_blob, 'svg')
+        image.format('png')
+        # would like to resize as an svg, then output the png of proper
+        # granularity...
+        image.resize(out_options[:size]) if out_options[:size]
+        image_blob = image.write(st).string
+      end
+      out_options[:size] = orig_out_options
+      image_blob
+    end
+
+    # out_options include any of those defined 
+    def write_string(type=DEFAULT_OUT_TYPE, out_options={})
+      png_transformer(type.to_s, out_options) do |type_s, _out_opts|
+        obconv = out_options[:obconv] || OpenBabel::OBConversion.new
+        obconv.set_out_format(type_s)
+        obconv.add_opts!(:out, _out_opts)
+        obconv.write_string(@ob)
+      end
     end
 
     # writes to the file based on the extension given.  If type is given
-    # explicitly, then it is used.
-    def write_file(filename, type=nil)
-      type ||= Rubabel.filetype(filename)
-      File.write(filename, write_string(type))
+    # explicitly, then it is used.  If png is the extension or format, the
+    # png is generated from an svg.
+    def write_file(filename, out_options={})
+      type = Rubabel.filetype(filename)
+      File.write(filename, write_string(type, out_options))
     end
 
     def inspect
       "#<Mol #{to_s}>"
     end
 
+    # returns self
+    def convert_dative_bonds!
+      @ob.convert_dative_bonds
+      self
+    end
+
+    # centers the molecule (deals with the atomic coordinate systems for 2D or
+    # 3D molecules). returns self.
+    def center!
+      @ob.center
+      self
+    end
+
+    # returns self
+    def kekulize!
+      @ob.kekulize
+      self
+    end
+
+    # returns self
+    def strip_salts!
+      @ob.strip_salts!
+      self
+    end
+
+    # returns self
+    def highlight_substructure!(substructure, color='red')
+      tmpconv = OpenBabel::OBConversion.new
+      tmpconv.add_option("s",OpenBabel::OBConversion::GENOPTIONS, "#{substructure} #{color}")
+      self.ob.do_transformations(tmpconv.get_options(OpenBabel::OBConversion::GENOPTIONS), tmpconv)
+      self
+    end
+
+    ## returns self
+    #def highlight_substructure!(substructure)
+    #  #obabel benzodiazepine.sdf.gz -O out.svg --filter "title=3016" -s "c1ccc2c(c1)C(=NCCN2)c3ccccc3 red" -xu -d
+    #  obconv.set_out_format('svg')
+
+    #  obconv.add_option("s",OpenBabel::OBConversion::GENOPTIONS, "#{substructure} red")
+    #  obconv.add_option("d",OpenBabel::OBConversion::GENOPTIONS) 	
+    #  self.ob.do_transformations(obconv.get_options(OpenBabel::OBConversion::GENOPTIONS), obconv)
+
+    #  obconv.add_option("u",OpenBabel::OBConversion::OUTOPTIONS)
+    #  self
+    #end
+
+    def graph_diameter
+      distance_matrix = Array.new
+      self.atoms.each do |a|
+        iter = OpenBabel::OBMolAtomBFSIter.new(self.ob, a.idx)
+        while iter.inc.deref do
+          distance_matrix << iter.current_depth - 1
+        end
+      end
+      distance_matrix.max
+    end
+
   end
 end
 
@@ -470,3 +633,81 @@ TPSA    topological polar surface area
 
 =end
 
+
+=begin
+  e.g., -xu
+ u no element-specific atom coloring
+    Use this option to produce a black and white diagram
+ U do not use internally-specified color
+    e.g. atom color read from cml or generated by internal code
+ b black background
+    The default is white. The atom colors work with both.
+ C do not draw terminal C (and attached H) explicitly
+    The default is to draw all hetero atoms and terminal C explicitly,
+    together with their attched hydrogens.
+ a draw all carbon atoms
+    So propane would display as H3C-CH2-CH3
+ d do not display molecule name
+ e embed molecule as CML
+    OpenBabel can read the resulting svg file as a cml file.
+ p# scale to bondlength in pixels(single mol only)
+ i add index to each atom
+    These indices are those in sd or mol files and correspond to the
+    order of atoms in a SMILES string.
+ j do not embed javascript
+    Javascript is not usually embedded if there is one one molecule,
+    but it is if the rows and columns have been specified as 1: ``-xr1 -xc1``
+ w generate wedge/hash bonds(experimental)
+ x omit XML declaration (not displayed in GUI)
+    Useful if the output is to be embedded in another xml file.
+ A display aliases, if present
+    This applies to structures which have an alternative, usually
+    shorter, representation already present. This might have been input
+    from an A or S superatom entry in an sd or mol file, or can be
+    generated using the --genalias option. For example::
+
+      echo "c1cc(C=O)ccc1C(=O)O" | babel -ismi out.svg --genalias -xA
+
+    would add a aliases COOH and CHO to represent the carboxyl and
+    aldehyde groups and would display them as such in the svg diagram.
+    The aliases which are recognized are in data/superatom.txt, which
+    can be edited.
+
+## SPECIFIC TO JUST MULTIPLE MOLS:
+
+ c# number of columns in table
+ r# number of rows in table
+ N# max number objects to be output
+ l draw grid lines
+
+=end
+
+# things JTP is playing with:
+=begin
+      opts = DEFAULT_DRAW_OPTS.merge( opts )
+      self.title = opts[:title] if opts[:title]
+      self.obconv.set_out_format(opts[:format].to_s)
+      p OpenBabel::OBConversion::OUTOPTIONS
+      p OpenBabel::OBConversion::OUTOPTIONS.class
+      p self.obconv.get_options(OpenBabel::OBConversion::OUTOPTIONS).methods - Object.new.methods
+      abort 'here'
+      p self.obconv.get_options(OpenBabel::OBConversion::GENOPTIONS)
+      self.obconv.add_option("P", OpenBabel::OBConversion::OUTOPTIONS, opts[:size].to_s) #sets image size to 300X300
+      p self.obconv.get_options(OpenBabel::OBConversion::OUTOPTIONS)
+      p self.obconv.get_options(OpenBabel::OBConversion::GENOPTIONS)
+      p OpenBabel::OBConversion::OUTOPTIONS
+      p OpenBabel::OBConversion::OUTOPTIONS.class
+      #self.obconv.add_option("gen2D",OpenBabel::OBConversion::GENOPTIONS)
+      #self.obconv.add_option("h",OpenBabel::OBConversion::GENOPTIONS)
+      #self.ob.do_transformations(self.obconv.get_options(OpenBabel::OBConversion::GENOPTIONS), self.obconv)
+      self.obconv.write_file(self.ob, opts[:filename])
+=end
+
+#opts = DEFAULT_DRAW_OPTS.merge( opts )
+#self.title = opts[:title] if opts[:title]
+##self.title = (opts[:title]==nil ? "" : opts[:title])
+#self.obconv.set_in_and_out_formats('smi',opts[:format])
+#self.obconv.add_option("P",OpenBabel::OBConversion::OUTOPTIONS, opts[:size].to_s) #sets image size to 300X300
+#self.obconv.do_transformations(self.obconv
+#self.obconv.write_file(self.ob, opts[:filename])
+

data/spec/chemistry_toolkit_rosetta/chemistry_toolkit_rosetta_spec.rb

@@ -1,4 +1,5 @@
 require 'spec_helper'
+require 'fileutils'
 
 # http://ctr.wikia.com/wiki/Chemistry_Toolkit_Rosetta_Wiki
 
@@ -23,6 +24,10 @@ end
 
 describe 'Chemistry Toolkit Rosetta Wiki' do
 
+  def equivalent_pngs(png1, png2)
+    (png1.size - png2.size < 50) && (png1[0..100] == png2[0..100])
+  end
+
   before(:each) do
     @orig_dir = Dir.pwd
     @wiki_spec_dir = File.dirname(__FILE__)
@@ -34,7 +39,7 @@ describe 'Chemistry Toolkit Rosetta Wiki' do
     Dir.chdir(@orig_dir)
   end
 
-  it 'gets Heavy atom counts from an SD file' do
+  specify 'Heavy atom counts from an SD file' do
     #http://ctr.wikia.com/wiki/Heavy_atom_counts_from_an_SD_file
     output = wiki_code_capture_stdout do
       require 'rubabel'
@@ -43,7 +48,7 @@ describe 'Chemistry Toolkit Rosetta Wiki' do
     output.should == IO.read( @keydir + "/" + "benzodiazepine_heavy_atom_counts.output.10.txt" )
   end
 
-  it 'gets Ring counts in a SMILES file' do
+  specify 'Ring counts in a SMILES file' do
     # http://ctr.wikia.com/wiki/Ring_counts_in_a_SMILES_file
     output = wiki_code_capture_stdout do
       require 'rubabel'
@@ -52,7 +57,7 @@ describe 'Chemistry Toolkit Rosetta Wiki' do
     output.should == IO.read( @keydir + '/' + "benzodiazepine_ring_counts.output.10.txt" )
   end
 
-  it 'Converts a SMILES string to canonical SMILES' do
+  specify 'Convert a SMILES string to canonical SMILES' do
     # http://ctr.wikia.com/wiki/Convert_a_SMILES_string_to_canonical_SMILES
     wiki_code do
       require 'rubabel'
@@ -62,7 +67,7 @@ describe 'Chemistry Toolkit Rosetta Wiki' do
     end
   end
 
-  it 'Works with SD tag data' do
+  specify 'Working with SD tag data' do
     # http://ctr.wikia.com/wiki/Working_with_SD_tag_data
     wiki_code do
       require 'rubabel'
@@ -94,7 +99,7 @@ describe 'Chemistry Toolkit Rosetta Wiki' do
     unlink "RULE5.sdf"
   end
 
-  it 'Detects and reports SMILES and SDF parsing errors' do
+  specify 'Detect and report SMILES and SDF parsing errors' do
     # http://ctr.wikia.com/wiki/Detect_and_report_SMILES_and_SDF_parsing_errors
     wiki_code do
       require 'rubabel'
@@ -114,7 +119,7 @@ describe 'Chemistry Toolkit Rosetta Wiki' do
     unlink("log.txt")
   end
 
-  it 'Reports how many SD file records are within a certain molecular weight range' do
+  specify 'Report how many SD file records are within a certain molecular weight range' do
     # http://ctr.wikia.com/wiki/Report_how_many_SD_file_records_are_within_a_certain_molecular_weight_range
     output = wiki_code_capture_stdout do
       require 'rubabel'
@@ -124,7 +129,7 @@ describe 'Chemistry Toolkit Rosetta Wiki' do
     # checked with large file and it came out to 3916, which is correct
   end
 
-  it 'Converts SMILES file to SD file' do
+  specify 'Convert SMILES file to SD file' do
     # http://ctr.wikia.com/wiki/Convert_SMILES_file_to_SD_file
     wiki_code do
       require 'rubabel'
@@ -143,21 +148,48 @@ describe 'Chemistry Toolkit Rosetta Wiki' do
     unlink "benzodiazepine.smi.sdf"
   end
 
-  it 'Reports the similarity between two structures' do
+  specify 'Report the similarity between two structures' do
     # http://ctr.wikia.com/wiki/Report_the_similarity_between_two_structures
     output = wiki_code_capture_stdout do
       require 'rubabel'
-      (mol1, mol2) = %w{CC(C)C=CCCCCC(=O)NCc1ccc(c(c1)OC)O COC1=C(C=CC(=C1)C=O)O}.map do |smile| 
-        Rubabel[smile]
-      end
+      (mol1, mol2) = %w{CC(C)C=CCCCCC(=O)NCc1ccc(c(c1)OC)O COC1=C(C=CC(=C1)C=O)O}.map{|smile| Rubabel[smile]}
       puts mol1.tanimoto(mol2)
     end
     output.should == "0.36046511627906974\n"
     # notes: reports similarity of 0.36046511627906974
   end
 
-  it 'Finds the 10 nearest neighbors in a data set' do
+  specify 'Find the 10 nearest neighbors in a data set' do
     # http://ctr.wikia.com/wiki/Find_the_10_nearest_neighbors_in_a_data_set
+
+    output = wiki_code_capture_stdout do
+      require 'rubabel'
+
+      prev = nil
+      comp = []
+      Rubabel.foreach("benzodiazepine.sdf.gz").map do |mol|
+        prev = mol if prev.nil?
+        comp << [prev.tanimoto(mol), mol.title]
+      end
+      puts comp.sort.reverse[1,11].map {|v| "#{v[0].round(3)} #{v[1]}" }
+    end
+    output.should == "0.979 3016\n0.979 2997\n0.909 3369\n0.874 2809\n0.769 3299\n0.74 2802\n0.379 3261\n0.377 2118\n0.368 1963\n"
+    # output when run on entire benzodiazepine.sdf.gz:
+    #1.0 450820
+    #1.0 1688
+    #0.993 20351792
+    #0.986 9862446
+    #0.979 398658
+    #0.979 398657
+    #0.979 6452650
+    #0.979 450830
+    #0.979 44353759
+    #0.979 3016
+    #0.979 2997
+  end
+
+# jtp original implementation
+=begin
     output = wiki_code_capture_stdout do
       require 'rubabel'
       fp1 = nil
@@ -194,24 +226,122 @@ describe 'Chemistry Toolkit Rosetta Wiki' do
     #end
     #puts comparisons.sort.reverse.map {|pair| pair.join(" ") }
   end
+=end
 
-  xit 'Depicts a compound as an image' do
+  specify 'Depict a compound as an image' do
     # http://ctr.wikia.com/wiki/Depict_a_compound_as_an_image
     wiki_code do
-      # still need to work on this!
-      #require 'rubabel'
-      #Rubabel["CN1C=NC2=C1C(=O)N(C(=O)N2C)C"].write_file("caffeine.svg")
+      require 'rubabel'
+      mol = Rubabel["CN1C=NC2=C1C(=O)N(C(=O)N2C)C"]
+      mol.title = 'Caffeine'
+      mol.write('caffeine.png')
+      # NOTE: use svg and convert to png to change image size
+    end
+    png_out = IO.read(@wiki_spec_dir + "/caffeine.png")
+    key_out = IO.read(@keydir + "/caffeine.frozen.png")
+    equivalent_pngs(png_out, key_out).should be_true
+    File.unlink('caffeine.png')
+  end
+  #OR, using commandline
+  #%x{obabel -:"CN1C=NC2=C1C(=O)N(C(=O)N2C)C" -O "mol.png" -xP 300}
+
+  specify 'Highlight a substructure in the depiction' do
+    # http://ctr.wikia.com/wiki/Highlight_a_substructure_in_the_depiction
+
+    # when we fix the draw function, this should work like a charm!
+    wiki_code do
+      require 'rubabel'
+      mol = Rubabel.foreach("benzodiazepine.sdf.gz").find {|mol| mol.title == "3016" }
+      mol.highlight_substructure!("c1ccc2c(c1)C(=NCCN2)c3ccccc3").remove_h!
+      mol.write("3016_highlighted.rubabel.png", u: true)
+      # NOTE: use svg and convert to png to change image size
+    end
+    png_out = IO.read(@wiki_spec_dir + "/3016_highlighted.rubabel.png")
+    key_out = IO.read(@keydir + "/3016_highlighted.rubabel.frozen.png")
+    equivalent_pngs(png_out, key_out)
+    File.unlink('3016_highlighted.rubabel.png')
+  end
+
+  xspecify 'Align the depiction using a fixed substructure' do
+    # http://ctr.wikia.com/wiki/Align_the_depiction_using_a_fixed_substructure
+		#TODO
+	end
+
+  specify 'Unique SMARTS matches against a SMILES string' do
+    # http://ctr.wikia.com/wiki/Unique_SMARTS_matches_against_a_SMILES_string
+    output = wiki_code_capture_stdout do
+      require 'rubabel'
+      mol = Rubabel["C1CC12C3(C24CC4)CC3"]
+      [false, true].map {|uniq| puts mol.matches("*1**1", uniq).size }
     end
+    output.should == "24\n4\n"
   end
 
-  xit 'Highlight a substructure in the depiction' do
-    smarts = "c1ccc2c(c1)C(=NCCN2)c3ccccc3"
-    mol = Rubabel.foreach("benzodiazepine.sdf.gz").find {|mol| mol.title == "3016" }
-    p OpenBabel::OBConversion.constants
-    p mol.obconv.get_options(OpenBabel::OBConversion.(:ALL))
-    #mol.write("hello.svg")
+  specify 'Calculate TPSA' do
+    output = wiki_code_capture_stdout do
+      require 'rubabel'
+      lines = IO.readlines("tpsa.tab")
+      header = lines.shift
+      @patterns = lines.map {|line| line.chomp.split("\t") }
+
+      def TPSA(mol)
+        @patterns.inject(0.0) {|s,p| s + p[0].to_f * mol.matches(p[1], false).size }
+      end
+      puts TPSA( Rubabel["CN2C(=O)N(C)C(=O)C1=C2N=CN1C"] )
+    end
+    output.should == "61.82\n"
+  end
+
+  specify 'Find the graph diameter' do
+    output = wiki_code_capture_stdout do
+      require 'rubabel'
+      puts Rubabel["CC(C)C(C(=O)NC(=O)C1CCCN1C(=O)C(C)NC(=O)C(C)NC(=O)CCC(=O)OC)NC2=CC=C(C=C2)[N+](=O)[O-]"].graph_diameter
+    end
+    output.should == "24\n"
+  end
+
+  specify 'Break rotatable bonds and report the fragments' do
+    output = wiki_code_capture_stdout do
+      smarts = "[!$([NH]!@C(=O))&!D1&!$(*#*)]-&!@[!$([NH]!@C(=O))&!D1&!$(*#*)]"
+      mol = Rubabel["c1ccc2c(c1)C(=NC(C(=O)N2CC(=O)O)Cc3ccc(cc3)O)c4cccc(c4)O"]
+      mol.matches(smarts).each do |atom1, atom2|
+        mol.delete(atom1.get_bond(atom2))
+        [atom1, atom2].each do |old_a|
+          mol.add_bond!(old_a, mol.add_atom!(0))
+        end
+      end
+      puts "#{mol.to_s.gsub('.',"\n")}"
+    end
+    output.should == "*C*\n*C*\n*C(=O)O\nO=C1C(*)N=C(c2c(N1*)cccc2)*\n*c1cccc(c1)O\n*c1ccc(cc1)O\n"
+  end
+
+  xit 'Perform a substructure search on SDF file and report the number of false positives' do
+    output = wiki_code_capture_stdout do
+      require 'rubabel'
+      smart = Rubabel::Smarts.new("C1C=C(NC=O)C=CC=1")
+      sm_mol = Rubabel[smart.to_s]
+      count = 0
+      Rubabel.foreach("benzodiazepine.sdf.gz").map do |mol|
+        count += 1 if sm_mol.to_s == mol.ob_fingerprint.to_s
+      end
+      #aromatize should be automatic for converstion from smarts??
+      #fingerprint search
+      #bitTest/full substructure match
+      puts count
+      #		puts "#{mols.size} total\n#{num_true_matches} matches\n#{num_matches - num_true_matches}"
+    end
+
+
+    #   output.should == "12386 total\n8836 matches\n1 false positives\n"
+    output.should == ""
   end
 
+  xit 'Change stereochemistry of certain atoms in SMILES file' do
+    #TODO
+  end
+
+
+
 
 end
 

data/spec/chemistry_toolkit_rosetta/tpsa.tab

@@ -0,0 +1,44 @@
+psa	SMARTS	description
+23.79	[N+0;H0;D1;v3]	N#
+23.85	[N+0;H1;D1;v3]	[NH]=
+26.02	[N+0;H2;D1;v3]	[NH2]-
+25.59	[N+1;H2;D1;v4]	[NH2+]=
+27.64	[N+1;H3;D1;v4]	[NH3+]-
+12.36	[N+0;H0;D2;v3]	=N-
+13.6	[N+0;H0;D2;v5]	=N#
+12.03	[N+0;H1;D2;v3;!r3]	-[NH]- not in 3-ring
+21.94	[N+0;H1;D2;v3;r3]	-[NH]- in 3-ring
+4.36	[N+1;H0;D2;v4]	-[N+]#
+13.97	[N+1;H1;D2;v4]	-[NH+]=
+16.61	[N+1;H2;D2;v4]	-[NH2+]-
+12.89	[n+0;H0;D2;v3]	:[n]:
+15.79	[n+0;H1;D2;v3]	:[nH]:
+3.24	[N+0;H0;D3;v3;!r3]	-N(-)-
+3.01	[N+0;H0;D3;v3;r3]	-N(-)- in 3-ring
+11.68	[N+0;H0;D3;v5]	-N(=)=
+3.01	[N+1;H0;D3;v4]	=[N+](-)-
+4.44	[N+1;H1;D3;v4]	-[NH+](-)-
+0	[N+1;H0;D4;v4]	-[N+](-)(-)-
+17.07	[O+0;H0;D1;v2]	O=
+23.06	[O-1;H0;D1;v1]	[O-]-
+9.23	[O+0;H0;D2;!r3;v2]	-O- not in 3-ring
+12.53	[O+0;H0;D2;r3;v2]	-O- in 3-ring
+13.14	[o+0;H0;D2;v2]	:o:
+14.14	[n+1;H1;D2;v4]	:[nH+]:
+20.23	[O+0;H1;D1]	[OH]-
+4.93	[n+0;H0;D3;$(n-*)]	-[n](:):
+4.41	[n+0;H0;D3;$(n(:*)(:*):*)]	:[n](:):
+4.10	[n+1;H0;D3;v4;$(n(:*)(:*):*)]	:[n+](:):
+3.88	[n+1;H0;D3;v4;$(n-*)]	-[n+](:):
+8.39	[n+0;H0;D3;v5;$(n=*)]	=[n](:):
+11.3	[#8+1;H0;D2]	28.5 - 2*8.6; non-standard valency
+12.8	[#8+1;H1;D2]	28.5 - 2*8.6 + 1.5; non-standard valency
+11.3	[#8;H0;D2;v4]	28.5 - 2*8.6; non-standard valency
+2.7	[#8;H0;D3;v4]	28.5 - 3 *8.6; non-standard valency
+2.7	[#8+1;H0;D3;v3]	28.5 - 3*8.6; non-standard valency
+7.4	[NH+0;v5;D3]	=N(-)-; 30.5 - 8.2*3 + 1.5; non-standard valency
+14.10	[#7;v2;D2]	30.5 - 2*8.2; -[N]-; non-standard valency
+15.6	[NH+0;v5;D2]	30.5 - 2*8.2 + 1.5; -N#, =N=; non-standard valency
+35.00	[NH3]	30.5 + 3*1.5 non-standard valency?
+2.68	O=[N+][O-]	17.07 - 23.06 - 3.01 + 11.68; (O=) - ([O-])- - (-N(-)-) + (N(=)=) ; fix to make charge-separated spelling work
+33.03	N=[N+]=[N-]	23.79 + 13.6 - 4.36; (N#) + (=N#) - (-[N+]#); fix to make charged-separated spelling work

data/spec/rubabel/atom_spec.rb

@@ -8,11 +8,9 @@ describe Rubabel::Atom do
   it 'can be created given an element symbol' do
     hydrogen = Rubabel::Atom[:h]
     hydrogen.el.should == :h
-    hydrogen.id.should == 0
 
     carbon = Rubabel::Atom[:c]
     carbon.el.should == :c
-    carbon.id.should == 0
 
     chlorine = Rubabel::Atom[:cl, 3]
     chlorine.el.should == :cl

data/spec/rubabel/molecule_spec.rb

@@ -10,6 +10,20 @@ describe Rubabel::Molecule do
     end
   end
 
+  describe 'png output' do
+    it 'creates a png image (corresponds to the svg)' do
+      mol = Rubabel["NCC(=O)O"]
+      #mol.write("mol1.svg", size: '300x200') 
+      #mol.write("mol1.png", size: '300x280')
+      mol.write("mol1.svg")
+      mol.write("mol1.png")
+      %w(mol1.svg mol1.png).each do |file|
+        File.exist?(file).should be_true
+        File.unlink(file)
+      end
+    end
+  end
+
   before(:each) do
     @mol = Rubabel::Molecule.from_file( TESTFILES + '/cholesterol.sdf' )
   end
@@ -25,6 +39,24 @@ describe Rubabel::Molecule do
     end
   end
 
+  specify '#add_atom! adds an atom given an atomic number and returns it' do
+    mol = Rubabel["CCO"]
+    before_size = mol.atoms.size
+    atom = mol.add_atom!(6)
+    atom.el.should == :c
+    (mol.atoms.size - before_size).should == 1
+    mol.csmiles.should == "CCO.C"
+  end
+
+  specify '#add_atom! with a Rubabel::Atom'
+
+  specify '#add_bond! adds a bond (and updates atoms)' do
+    mol = Rubabel["CCO"]
+    atom = mol.add_atom!(0)
+    mol.add_bond!(mol.atoms[1], atom)
+    mol.csmiles.should == '*C(O)C'
+  end
+
 #  specify '#add_bond adds a bond (and updates atoms)' do
 #    c = Rubabel::Atom[:c]
 #    o = Rubabel::Atom[:o]
@@ -244,4 +276,8 @@ describe Rubabel::Molecule do
     end
 
   end
+
+  describe 'using output format options' do
+
+  end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: rubabel
 version: !ruby/object:Gem::Version
-  version: 0.1.5
+  version: 0.1.6
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-08-08 00:00:00.000000000 Z
+date: 2012-09-06 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: openbabel
@@ -43,6 +43,22 @@ dependencies:
     - - ~>
       - !ruby/object:Gem::Version
         version: 1.3.3
+- !ruby/object:Gem::Dependency
+  name: mini_magick
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '3.4'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '3.4'
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
@@ -128,14 +144,16 @@ files:
 - reference/fragmentation_rules_.pdf
 - reference/get_methods.rb
 - reference/mol_methods.txt
-- rubabel.gemspec
 - spec/chemistry_toolkit_rosetta/README.txt
 - spec/chemistry_toolkit_rosetta/benzodiazepine.sdf.gz
 - spec/chemistry_toolkit_rosetta/benzodiazepine.smi.gz
 - spec/chemistry_toolkit_rosetta/chemistry_toolkit_rosetta_spec.rb
+- spec/chemistry_toolkit_rosetta/key/3016_highlighted.rubabel.frozen.png
 - spec/chemistry_toolkit_rosetta/key/benzodiazepine_heavy_atom_counts.output.10.txt
 - spec/chemistry_toolkit_rosetta/key/benzodiazepine_ring_counts.output.10.txt
+- spec/chemistry_toolkit_rosetta/key/caffeine.frozen.png
 - spec/chemistry_toolkit_rosetta/key/rule5.10.sdf
+- spec/chemistry_toolkit_rosetta/tpsa.tab
 - spec/rubabel/atom_spec.rb
 - spec/rubabel/bond_spec.rb
 - spec/rubabel/molecule/fragmentable_spec.rb

data/rubabel.gemspec

@@ -1,100 +0,0 @@
-# Generated by jeweler
-# DO NOT EDIT THIS FILE DIRECTLY
-# Instead, edit Jeweler::Tasks in Rakefile, and run 'rake gemspec'
-# -*- encoding: utf-8 -*-
-
-Gem::Specification.new do |s|
-  s.name = "rubabel"
-  s.version = "0.1.5"
-
-  s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
-  s.authors = ["John T. Prince"]
-  s.date = "2012-08-08"
-  s.description = "Ruby interface to the openbabel ruby bindings (or the openbabel gem).  The\ninterface attempts to be a ruby-ish analogue of pybel."
-  s.email = "jtprince@gmail.com"
-  s.executables = ["fragmenter.rb"]
-  s.extra_rdoc_files = [
-    "LICENSE",
-    "README.rdoc"
-  ]
-  s.files = [
-    ".document",
-    ".rspec",
-    "LICENSE",
-    "README.rdoc",
-    "Rakefile",
-    "VERSION",
-    "bin/fragmenter.rb",
-    "lib/rubabel.rb",
-    "lib/rubabel/atom.rb",
-    "lib/rubabel/bond.rb",
-    "lib/rubabel/core_ext/enumerable.rb",
-    "lib/rubabel/core_ext/putsv.rb",
-    "lib/rubabel/fingerprint.rb",
-    "lib/rubabel/molecule.rb",
-    "lib/rubabel/molecule/fragmentable.rb",
-    "lib/rubabel/molecule_data.rb",
-    "lib/rubabel/pm.rb",
-    "lib/rubabel/smarts.rb",
-    "reference/OBConversion_methods.txt",
-    "reference/arity_method_list.txt",
-    "reference/arity_method_list_CLASS.txt",
-    "reference/atom_methods.txt",
-    "reference/bond_methods.txt",
-    "reference/fragmentation_rules_.pdf",
-    "reference/get_methods.rb",
-    "reference/mol_methods.txt",
-    "rubabel.gemspec",
-    "spec/chemistry_toolkit_rosetta/README.txt",
-    "spec/chemistry_toolkit_rosetta/benzodiazepine.sdf.gz",
-    "spec/chemistry_toolkit_rosetta/benzodiazepine.smi.gz",
-    "spec/chemistry_toolkit_rosetta/chemistry_toolkit_rosetta_spec.rb",
-    "spec/chemistry_toolkit_rosetta/key/benzodiazepine_heavy_atom_counts.output.10.txt",
-    "spec/chemistry_toolkit_rosetta/key/benzodiazepine_ring_counts.output.10.txt",
-    "spec/chemistry_toolkit_rosetta/key/rule5.10.sdf",
-    "spec/rubabel/atom_spec.rb",
-    "spec/rubabel/bond_spec.rb",
-    "spec/rubabel/molecule/fragmentable_spec.rb",
-    "spec/rubabel/molecule_data_spec.rb",
-    "spec/rubabel/molecule_spec.rb",
-    "spec/rubabel_spec.rb",
-    "spec/spec_helper.rb",
-    "spec/testfiles/7-oxocholesterol-d7.mol",
-    "spec/testfiles/7-oxocholesterol-d7.sdf",
-    "spec/testfiles/Samples.sdf",
-    "spec/testfiles/Samples.sdf.gz",
-    "spec/testfiles/cholesterol.mol",
-    "spec/testfiles/cholesterol.sdf",
-    "spec/testfiles/two.sdf"
-  ]
-  s.homepage = "http://github.com/princelab/rubabel"
-  s.licenses = ["MIT"]
-  s.require_paths = ["lib"]
-  s.rubygems_version = "1.8.23"
-  s.summary = "Ruby interface to the OpenBabel ruby bindings similar to pybel"
-
-  if s.respond_to? :specification_version then
-    s.specification_version = 3
-
-    if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
-      s.add_runtime_dependency(%q<openbabel>, ["~> 2.3.1.2"])
-      s.add_runtime_dependency(%q<andand>, ["~> 1.3.3"])
-      s.add_development_dependency(%q<rspec>, ["~> 2.8.0"])
-      s.add_development_dependency(%q<rdoc>, ["~> 3.12"])
-      s.add_development_dependency(%q<jeweler>, ["~> 1.8.3"])
-    else
-      s.add_dependency(%q<openbabel>, ["~> 2.3.1.2"])
-      s.add_dependency(%q<andand>, ["~> 1.3.3"])
-      s.add_dependency(%q<rspec>, ["~> 2.8.0"])
-      s.add_dependency(%q<rdoc>, ["~> 3.12"])
-      s.add_dependency(%q<jeweler>, ["~> 1.8.3"])
-    end
-  else
-    s.add_dependency(%q<openbabel>, ["~> 2.3.1.2"])
-    s.add_dependency(%q<andand>, ["~> 1.3.3"])
-    s.add_dependency(%q<rspec>, ["~> 2.8.0"])
-    s.add_dependency(%q<rdoc>, ["~> 3.12"])
-    s.add_dependency(%q<jeweler>, ["~> 1.8.3"])
-  end
-end
-