hydrogen_bondifier 0.0.2 → 0.0.3

data/VERSION

@@ -1 +1 @@
-0.0.2
+0.0.3

data/bin/hydrogen_bondifier.rb

@@ -6,6 +6,7 @@
 # see this on hydrogen bond finding in pymol:
 # http://www.mail-archive.com/pymol-users@lists.sourceforge.net/msg06680.html
 
+
 require 'yaml'
 require 'narray'
 require 'optparse'
@@ -60,13 +61,12 @@ if ARGV.size == 0
   exit
 end
 
-files = ARGV.map
+files = ARGV.dup
 ARGV.clear
 
 categories = %w(D_id H_id A_id H_name D_res D_res_id D_name A_res A_res_id A_name angle D_A_dist H_A_dist H_dist_to_surf)
 
 files.each do |file|
-  
   ####################
   # need to implement copying of file, etc......
   ####################

data/spec/pymol_spec.rb

@@ -13,7 +13,6 @@ describe 'pymol running basic tests' do
 
   after do
     File.unlink @file if File.exist?(@file)
-    File.unlink @file if File.exist?(@file)
   end
 
   it 'can run commands and wait for a file to be written' do

metadata

@@ -1,7 +1,12 @@
 --- !ruby/object:Gem::Specification 
 name: hydrogen_bondifier
 version: !ruby/object:Gem::Version 
-  version: 0.0.2
+  prerelease: false
+  segments: 
+  - 0
+  - 0
+  - 3
+  version: 0.0.3
 platform: ruby
 authors: 
 - John T. Prince
@@ -9,19 +14,22 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-02-10 00:00:00 -07:00
+date: 2010-11-30 00:00:00 -07:00
 default_executable: hydrogen_bondifier.rb
 dependencies: 
 - !ruby/object:Gem::Dependency 
   name: spec-more
-  type: :development
-  version_requirement: 
-  version_requirements: !ruby/object:Gem::Requirement 
+  prerelease: false
+  requirement: &id001 !ruby/object:Gem::Requirement 
+    none: false
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
+        segments: 
+        - 0
         version: "0"
-    version: 
+  type: :development
+  version_requirements: *id001
 description: uses pymol
 email: jtprince@gmail.com
 executables: 
@@ -32,46 +40,20 @@ extra_rdoc_files:
 - LICENSE
 - README.rdoc
 files: 
-- .gitignore
-- History
+- VERSION
 - LICENSE
 - README.rdoc
-- Rakefile
-- VERSION
-- bin/hydrogen_bondifier.rb
-- lib/hydrogen_bondifier/utils.rb
-- lib/pymol.rb
-- lib/pymol/connections.rb
-- lib/pymol/hydrogen_bonds.rb
-- lib/pymol/orientation.rb
-- lib/pymol/surface.rb
-- reference/all_connections.py
-- reference/campbell_find_hb.py
-- reference/list_hbonds.py
-- reference/test_pymol.rb
-- spec/pymol/connections_spec.rb
-- spec/pymol/hydrogen_bonds_spec.rb
-- spec/pymol/surface_spec.rb
-- spec/pymol_spec.rb
-- spec/scripts/confirm_angle_and_h_dist.rb
-- spec/scripts/confirm_distances.rb
 - spec/scripts/mins.rb
+- spec/scripts/confirm_distances.rb
+- spec/scripts/confirm_angle_and_h_dist.rb
 - spec/scripts/obj_ranges.rb
 - spec/scripts/pdb_ranges.rb
+- spec/pymol_spec.rb
+- spec/pymol/hydrogen_bonds_spec.rb
+- spec/pymol/connections_spec.rb
+- spec/pymol/surface_spec.rb
 - spec/spec_helper.rb
-- spec/testfiles/1YQS.pdb
-- spec/testfiles/1YQS_h_added.pdb
-- spec/testfiles/2ERK_Hbond.out
-- spec/testfiles/2pERK2_HBOND.out
-- spec/testfiles/2pERK2_Hadded.pdb
-- spec/testfiles/2pERK2_dis-surf.txt
-- spec/testfiles/little.pdb
-- validation/jtp_vs_insight_angles.png
-- validation/jtp_vs_insight_distances.png
-- validation/jtp_vs_insight_surface_distances.png
-- validation/jtp_vs_insight_surface_distances_aa_geometric.png
-- validation/jtp_vs_insight_surface_distances_center_of_grav.png
-- validation/jtp_vs_insight_surface_distances_closest_atom.png
+- bin/hydrogen_bondifier.rb
 has_rdoc: true
 homepage: http://jtprince.github.com/hydrogen_bondifier
 licenses: []
@@ -82,32 +64,36 @@ rdoc_options:
 require_paths: 
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
+      segments: 
+      - 0
       version: "0"
-  version: 
 required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
+      segments: 
+      - 0
       version: "0"
-  version: 
 requirements: []
 
 rubyforge_project: 
-rubygems_version: 1.3.5
+rubygems_version: 1.3.7
 signing_key: 
 specification_version: 3
 summary: finds hydrogen bonds using pymol
 test_files: 
-- spec/scripts/obj_ranges.rb
-- spec/scripts/pdb_ranges.rb
 - spec/scripts/mins.rb
-- spec/scripts/confirm_angle_and_h_dist.rb
 - spec/scripts/confirm_distances.rb
+- spec/scripts/confirm_angle_and_h_dist.rb
+- spec/scripts/obj_ranges.rb
+- spec/scripts/pdb_ranges.rb
 - spec/pymol_spec.rb
-- spec/spec_helper.rb
 - spec/pymol/hydrogen_bonds_spec.rb
 - spec/pymol/connections_spec.rb
 - spec/pymol/surface_spec.rb
+- spec/spec_helper.rb

data/.gitignore

@@ -1,3 +0,0 @@
-.*.swp
-*.gemspec
-pkg

data/History

@@ -1,9 +0,0 @@
-== 0.0.2 / 2010-02-10
-
-* switched to system calls using temp files.  Note that Tempfiles on windows do not work at least the way I am trying to use them.
-
-== 0.0.1 / 2009-12
-
-* using pipes
-
-

data/Rakefile

@@ -1,54 +0,0 @@
-
-require 'rubygems'
-require 'rake'
-require 'jeweler'
-require 'rake/testtask'
-# require 'rcov/rcovtask'
-
-NAME = "hydrogen_bondifier"
-WEBSITE_BASE = "website"
-WEBSITE_OUTPUT = WEBSITE_BASE + "/output"
-
-gemspec = Gem::Specification.new do |s|
-  s.name = NAME
-  s.authors = ["John T. Prince"]
-  s.email = "jtprince@gmail.com"
-  s.homepage = "http://jtprince.github.com/" + NAME
-  s.summary = "finds hydrogen bonds using pymol"
-  s.description = "uses pymol"
-  #s.rubyforge_project = 'mspire'
-  # s.add_dependency("ms-core", ">= 0.0.2")
-  # s.add_development_dependency("ms-testdata", ">= 0.18.0")
-  s.add_development_dependency("spec-more")
-  s.files << "VERSION"
-end
-
-Jeweler::Tasks.new(gemspec)
-
-Rake::TestTask.new(:spec) do |spec|
-  spec.libs << 'lib' << 'spec'
-  spec.pattern = 'spec/**/*_spec.rb'
-  spec.verbose = true
-end
-
-#Rcov::RcovTask.new do |spec|
-#  spec.libs << 'spec'
-#  spec.pattern = 'spec/**/*_spec.rb'
-#  spec.verbose = true
-#end
-
-require 'rake/rdoctask'
-Rake::RDocTask.new do |rdoc|
-  base_rdoc_output_dir = WEBSITE_OUTPUT + '/rdoc'
-  version = File.read('VERSION')
-  rdoc.rdoc_dir = base_rdoc_output_dir + "/#{version}"
-  rdoc.title = NAME + ' ' + version
-  rdoc.rdoc_files.include('README*')
-  rdoc.rdoc_files.include('lib/**/*.rb')
-end
-
-task :default => :spec
-
-task :build => :gemspec
-
-# credit: Rakefile modeled after Jeweler's

data/lib/hydrogen_bondifier/utils.rb

@@ -1,39 +0,0 @@
-require 'narray'
-
-module Bio
-  class PDB
-    module Utils
-
-      module_function
-      # calculates the angle between 2 Narray vecs (in radians)
-      def angle_between_vectors(vec1, vec2)
-        vec1 = NArray.to_na(vec1.to_a) unless vec1.is_a?(NArray)
-        vec2 = NArray.to_na(vec2.to_a) unless vec2.is_a?(NArray)
-        nil_vec = NArray[0.0, 0.0, 0.0]
-        return nil if (vec1 == nil_vec or vec2 == nil_vec)
-        (mag_a, mag_b) = [vec1,vec2].map {|vec| Math::sqrt((vec*vec).sum) }
-        # acos(dotprod / |a||b|)
-        Bio::PDB::Utils.acos( (vec1 * vec2).sum.to_f  /  (mag_a * mag_b) )
-      end
-
-      def angle_from_coords(triplet)
-        a = triplet.last - triplet[1]
-        b = triplet.first - triplet[1]
-        angle_between_vectors(a,b)
-      end
-
-      # other is 3 parallel NArray objects with the x, y and z coordinates
-      # or a triplet like coord
-      def distance_to_many(coord, other)
-        # distance may be another narray or an array of vecs
-        sq_diffs = []
-        (0...(coord.size)).each do |i|
-          pos = coord[i]
-          oth = other[i]
-          sq_diffs << (oth - pos)**2
-        end
-        NMath.sqrt(sq_diffs.inject {|sum, vec| sum + vec  })
-      end
-    end
-  end
-end

data/lib/pymol.rb

@@ -1,93 +0,0 @@
-require 'tempfile'
-
-
-class Pymol
-
-  TMP_PYTHON_SCRIPT_FILENAME = "python_script_for_pymol"
-  TMP_PYMOL_SCRIPT_FILENAME = "pymol_script"
-  TMP_PYMOL_REPLY_FILENAME = "pymol_reply"
-
-  PYMOL_SCRIPT_POSTFIX = '.pml'  # <- very freaking important
-  PYTHON_SCRIPT_POSTFIX = '.py'  # <- very freaking important
-
-  attr_accessor :cmds
-
-  def self.run(opt={}, &block)
-    self.new.run(opt, &block)
-  end
-
-  def initialize
-    @cmds = [] 
-  end
-
-  def cmd(string)
-    @cmds << string
-  end
-
-  def tmp_file(base, postfix)
-    [base, $$, Time.now.to_f].join('-') << postfix
-  end
-
-  # you can add your path to pymol to this array if you need to 
-  # or with a commandline flag
-  PYMOL_EXE_TO_TRY = ['PyMOL.exe', 'pymol']
-
-  ####################################################
-  # determine if we have pymol and how to execute it
-  ####################################################
-  PYMOL_EXE_TO_TRY.unshift(ENV['PYMOL_EXE']) if ENV['PYMOL_EXE']
-  to_use = false
-  PYMOL_EXE_TO_TRY.each do |name|
-    begin
-      _cmd = "#{name} -cq"
-      if system(_cmd)
-        to_use = _cmd
-        break
-      end
-    rescue
-    end
-  end
-
-  if to_use
-    PYMOL_QUIET = to_use
-    puts "pymol executable looks good: '#{PYMOL_QUIET}'" if $VERBOSE
-  else
-    abort "pymol not installed or can't find path, specify with --path-to-pymol" if !to_use
-  end
-
-  def run(opt={}, &block)
-    puts( "[working in pymol]: " + opt[:msg] + " ...") if (opt[:msg] && $VERBOSE)
-
-    block.call(self)
-
-    cmds_to_run = self.cmds.map
-
-    tmpfiles = []
-    if script = opt[:script]
-      script_tmpfn = tmp_file TMP_PYTHON_SCRIPT_FILENAME, PYTHON_SCRIPT_POSTFIX
-      File.open(script_tmpfn, 'w') {|out| out.print script }
-      tmpfiles << script_tmpfn
-      cmds_to_run.unshift( "run #{script_tmpfn}" )
-    end
-
-    to_run = cmds_to_run.map {|v| v + "\n" }.join
-
-    pymol_tmpfn = tmp_file TMP_PYMOL_SCRIPT_FILENAME, PYMOL_SCRIPT_POSTFIX
-    File.open(pymol_tmpfn, 'w') {|out| out.print to_run }
-    tmpfiles << pymol_tmpfn
-
-    # much more suave to open a pipe, but python does not play well with pipes
-    # and this is *MUCH* more compatible with windows
-    pymol_reply_tmpfn = tmp_file TMP_PYMOL_REPLY_FILENAME, '.pmolreply'
-    tmpfiles << pymol_reply_tmpfn
-    system_cmd = "#{PYMOL_QUIET} #{pymol_tmpfn} > #{pymol_reply_tmpfn}"
-    system system_cmd
-
-    reply = IO.read(pymol_reply_tmpfn)
-    
-    tmpfiles.each {|tmpf| File.unlink tmpf } 
-    self.cmds.clear
-    reply
-  end
-
-end

data/lib/pymol/connections.rb

@@ -1,55 +0,0 @@
-require 'pymol'
-
-class Pymol
-  module Connections
-    module Script
-      module_function
-
-      def all_connections_script
-        %Q{
-from pymol import cmd
-
-def all_connections(selection):
-  """
-  USAGE
-
-  all_connections selection
-
-  returns lines: "CONNECTION: id - id"
-  """
-  stored.xs = []
-  cmd.iterate(selection, 'stored.xs.append( index )')
-  for i in stored.xs:
-    selName = "neighbor%s" % i
-    ids = cmd.select(selName, ("%s and neighbor id %s" % (selection, i)))
-    base = "CONNECTION: %s - " % i 
-    to_print = base + "%s"
-    print_string = 'print "' + to_print + '" % index'
-    cmd.iterate(selName, print_string )
-
-cmd.extend("all_connections", all_connections)
-}
-      end
-
-      # returns an array of all pairs of atom IDs with no redundancy
-      def all_connections_parser(reply_from_all_connections, flag=/^CONNECTION: /)
-        pairs = reply_from_all_connections.split("\n").select {|v| v =~ flag }.map do |line|
-          line.split(':').last.split(' - ').map {|v| v.to_i }.sort
-        end
-        pairs.uniq
-      end
-
-    end
-
-    module_function
-
-    # returns all connections as pairs of ID's (all uniq)
-    def from_pdb(pdb)
-      reply = Pymol.run(:msg => 'getting all atom connections', :script => Pymol::Connections::Script.all_connections_script) do |pm|
-        pm.cmd "load #{pdb}, mymodel"
-        pm.cmd "all_connections mymodel"
-      end
-      Pymol::Connections::Script.all_connections_parser(reply)
-    end
-  end
-end

data/lib/pymol/hydrogen_bonds.rb

@@ -1,157 +0,0 @@
-require 'pymol'
-require 'pymol/connections'
-
-require 'bio/db/pdb'
-require 'hydrogen_bondifier/utils'
-
-class Pymol
-  EXCLUDE_WATER_FILTER = " &! resn hoh"
-  module HydrogenBonds
-
-    DEFAULT_FIND_PAIRS_OPTS = {:max_dist => 3.2, :max_angle => 60, :exclude_water => true }
-    DEFAULT_H_BOND_OPTS = {
-      :select_donor => "and (elem n,o and (neighbor hydro))",
-      :select_acceptor => "and (elem o or (elem n and not (neighbor hydro)))",
-    }
-
-    module_function
-
-    def pdb_with_hydrogens(pdb_filename, newname=nil)
-      pfile = pdb_filename
-      newname = pfile.chomp(File.extname(pfile)) + "_plus_h.pdb" unless newname
-      Pymol.run(:msg => 'creating pdb with hydrogens') do |pm|
-        pm.cmd "load #{pfile}, mymodel"
-        pm.cmd "h_add"
-        pm.cmd "save #{newname}"
-      end
-      newname
-    end
-
-    # returns [id1, id2, distance] for each atom
-    def find_pairs(file, sel1, sel2, opt={})
-      opt = DEFAULT_FIND_PAIRS_OPTS.merge( opt )
-      exclude_water_command = opt[:exclude_water] ? EXCLUDE_WATER_FILTER : ""
-      hbond_script = Pymol::HydrogenBonds.list_hb_script(sel1, sel2)
-      reply = Pymol.run(:msg => "getting hydrogen bonds", :script => hbond_script) do |pm|
-        pm.cmd "load #{file}, mymodel"
-        pm.cmd "list_hb mymodel#{exclude_water_command}, cutoff=#{opt[:max_dist]}, angle=#{opt[:max_angle]}"
-      end
-      Pymol::HydrogenBonds.list_hb_parser(reply)
-    end
-
-
-    # returns [donor, hydrogen, acceptor, angle, don_to_acc_dist, h_to_acc_dist]
-    # The first three are Bio::PDB::Record::ATOM structs.
-    # respects DEFAULT_FIND_PAIRS_OPTS and DEFAULT_H_BOND_OPTS
-    # expects that hydrogen bonds are already specified in the PDB file
-    # returns an array triplet atom IDs [donor, hydrogen, acceptor]
-    # :connections can be passed in (an array of arrays of all unique pairwise
-    # connections [by ID])
-    def from_pdb(file, opt={})
-      opt = DEFAULT_H_BOND_OPTS.merge(opt)
-
-      pairs = find_pairs(file, opt[:select_donor], opt[:select_acceptor], opt)
-
-      connection_pairs = Pymol::Connections.from_pdb(file)
-      connection_index = Hash.new {|h,k| h[k] = [] }
-      connection_pairs.each do |pair|
-        connection_index[pair.first] << pair.last
-        connection_index[pair.last] << pair.first
-      end
-
-      # make an index of the atoms
-      pdb = Bio::PDB.new(IO.read(file)) 
-      pdb.extend(Bio::PDB::AtomFinder)
-      atom_index = []
-      pdb.each_atom do |atom|
-        atom_index[atom.serial] = atom
-      end
-
-      max_angle = opt[:max_angle] || DEFAULT_FIND_PAIRS_OPTS[:max_angle]
-      cutoff_in_degress = max_angle
-
-      hbonds = []
-      puts "calculating angles and distances" if $VERBOSE
-      pairs.each do |don_id, acc_id, don_to_acc_dist|
-        donor = atom_index[don_id]
-        acceptor = atom_index[acc_id]  
-        next if (acceptor.element == 'H' or donor.element == 'H') # check for sloppy queries
-        acceptor_xyz = acceptor.xyz
-        donor_xyz = donor.xyz
-        connection_index[don_id].each do |id|
-          hydrogen = atom_index[id]
-          next if hydrogen.element != 'H'
-
-          #puts "ACCEPT ID: "
-          #puts acc_id
-          #p acceptor_xyz
-          #puts "HYDRO ID: "
-          #p id
-          #p hydrogen.xyz
-
-          angle = Bio::PDB::Utils.angle_from_coords([donor_xyz, hydrogen.xyz, acceptor_xyz])
-          h_to_acc_dist = Bio::PDB::Utils.distance(hydrogen.xyz, acceptor_xyz)
-
-          #puts "DISTANCES: "
-          #p don_to_acc_dist
-          #p h_to_acc_dist
-          # abort 'here'
-          
-          # I'm not sure why the angle cutoff is not being respected, but we
-          # can enforce it right here since we want the angles anyway
-          if (180.0 - Bio::PDB::Utils.rad2deg(angle)) <= cutoff_in_degress
-            hbonds << [donor, hydrogen, acceptor, angle, don_to_acc_dist, h_to_acc_dist]
-          end
-        end
-      end
-      hbonds
-    end
-
-    def list_hb_script(select1, select2)
-      %Q{
-# modified by JTP from here:
-# Dr. Robert L. Campbell
-# http://pldserver1.biochem.queensu.ca/~rlc/work/pymol/
-# find_pairs is an undocumented method but mode==1 is hydrogen bond finding
-
-from pymol import cmd
-
-def list_hb(selection,cutoff=3.2,angle=55,hb_list_name='hbonds'):
-  """
-  USAGE
-
-  list_hb selection, [cutoff (default=3.2)], [angle (default=55)], [hb_list_name]
-
-  e.g.
-    list_hb 1abc & c. a &! r. hoh, cutoff=3.2, hb_list_name=abc-hbonds
-  """
-  cutoff=float(cutoff)
-  angle=float(angle)
-  hb = cmd.find_pairs("((byres "+selection+") #{select1})","((byres "+selection+") #{select2})",mode=1,cutoff=cutoff,angle=angle)
-# sort the list for easier reading
-  hb.sort(lambda x,y:(cmp(x[0][1],y[0][1])))
-
-  for pairs in hb:
-    print "PAIR:",
-    for ind in [0,1]:
-      cmd.iterate("%s and index %s" % (pairs[ind][0],pairs[ind][1]), 'print "%s/%3s`%s/%s/%s " % (chain,resn,resi,name,index),')
-    print "%.2f" % cmd.distance(hb_list_name,"%s and index %s" % (pairs[0][0],pairs[0][1]),"%s and index %s" % (pairs[1][0],pairs[1][1]))
-
-cmd.extend("list_hb",list_hb)
-}
-    end
-
-    # takes output of hb_script and returns an array of triplets [id1, id2, distance]
-    def list_hb_parser(pymol_hb_script_reply, flag=/^PAIR: /)
-      # grab each line of output with specified header, then remove the header
-      hbond_lines = pymol_hb_script_reply.split("\n").select {|line| line =~ flag }.map {|line| line.sub(flag,'') }
-
-      ids_and_distances = hbond_lines.map do |line|
-        # A/THR`325/N/2478  A/ALA`323/O/2468  3.05
-        (first, second, dist) = line.split(/\s+/)
-        (id1, id2) = [first, second].map {|v| v.split('/').last.to_i }
-        [id1, id2, dist.to_f]
-      end
-    end
-  end
-end