|
0
|
1 package MolecularDescriptors::TPSADescriptors;
|
|
|
2 #
|
|
|
3 # $RCSfile: TPSADescriptors.pm,v $
|
|
|
4 # $Date: 2015/02/28 20:49:20 $
|
|
|
5 # $Revision: 1.18 $
|
|
|
6 #
|
|
|
7 # Author: Manish Sud <msud@san.rr.com>
|
|
|
8 #
|
|
|
9 # Copyright (C) 2015 Manish Sud. All rights reserved.
|
|
|
10 #
|
|
|
11 # This file is part of MayaChemTools.
|
|
|
12 #
|
|
|
13 # MayaChemTools is free software; you can redistribute it and/or modify it under
|
|
|
14 # the terms of the GNU Lesser General Public License as published by the Free
|
|
|
15 # Software Foundation; either version 3 of the License, or (at your option) any
|
|
|
16 # later version.
|
|
|
17 #
|
|
|
18 # MayaChemTools is distributed in the hope that it will be useful, but without
|
|
|
19 # any warranty; without even the implied warranty of merchantability of fitness
|
|
|
20 # for a particular purpose. See the GNU Lesser General Public License for more
|
|
|
21 # details.
|
|
|
22 #
|
|
|
23 # You should have received a copy of the GNU Lesser General Public License
|
|
|
24 # along with MayaChemTools; if not, see <http://www.gnu.org/licenses/> or
|
|
|
25 # write to the Free Software Foundation Inc., 59 Temple Place, Suite 330,
|
|
|
26 # Boston, MA, 02111-1307, USA.
|
|
|
27 #
|
|
|
28
|
|
|
29 use strict;
|
|
|
30 use Carp;
|
|
|
31 use Exporter;
|
|
|
32 use Scalar::Util ();
|
|
|
33 use TextUtil ();
|
|
|
34 use MathUtil ();
|
|
|
35 use Atom;
|
|
|
36 use Molecule;
|
|
|
37 use MolecularDescriptors::MolecularDescriptors;
|
|
|
38 use AtomTypes::TPSAAtomTypes;
|
|
|
39
|
|
|
40 use vars qw(@ISA @EXPORT @EXPORT_OK %EXPORT_TAGS);
|
|
|
41
|
|
|
42 @ISA = qw(MolecularDescriptors::MolecularDescriptors Exporter);
|
|
|
43 @EXPORT = qw();
|
|
|
44 @EXPORT_OK = qw(GetDescriptorNames);
|
|
|
45
|
|
|
46 %EXPORT_TAGS = (all => [@EXPORT, @EXPORT_OK]);
|
|
|
47
|
|
|
48 # Setup class variables...
|
|
|
49 my($ClassName, @DescriptorNames);
|
|
|
50 _InitializeClass();
|
|
|
51
|
|
|
52 # Overload Perl functions...
|
|
|
53 use overload '""' => 'StringifyTPSADescriptors';
|
|
|
54
|
|
|
55 # Class constructor...
|
|
|
56 sub new {
|
|
|
57 my($Class, %NamesAndValues) = @_;
|
|
|
58
|
|
|
59 # Initialize object...
|
|
|
60 my $This = $Class->SUPER::new();
|
|
|
61 bless $This, ref($Class) || $Class;
|
|
|
62 $This->_InitializeTPSADescriptors();
|
|
|
63
|
|
|
64 $This->_InitializeTPSADescriptorsProperties(%NamesAndValues);
|
|
|
65
|
|
|
66 return $This;
|
|
|
67 }
|
|
|
68
|
|
|
69 # Initialize class ...
|
|
|
70 sub _InitializeClass {
|
|
|
71 #Class name...
|
|
|
72 $ClassName = __PACKAGE__;
|
|
|
73
|
|
|
74 # Descriptor names...
|
|
|
75 @DescriptorNames = ('TPSA');
|
|
|
76
|
|
|
77 }
|
|
|
78
|
|
|
79 # Get descriptor names as an array.
|
|
|
80 #
|
|
|
81 # This functionality can be either invoked as a class function or an
|
|
|
82 # object method.
|
|
|
83 #
|
|
|
84 sub GetDescriptorNames {
|
|
|
85 return @DescriptorNames;
|
|
|
86 }
|
|
|
87
|
|
|
88 # Initialize object data...
|
|
|
89 #
|
|
|
90 sub _InitializeTPSADescriptors {
|
|
|
91 my($This) = @_;
|
|
|
92
|
|
|
93 # Type of MolecularDescriptor...
|
|
|
94 $This->{Type} = 'TPSA';
|
|
|
95
|
|
|
96 # By default, TPSA atom contributions from Phosphorus and Sulfur atoms
|
|
|
97 # are not included during TPSA calculations. [ Ref 91 ]
|
|
|
98 #
|
|
|
99 $This->{IgnorePhosphorus} = 1;
|
|
|
100 $This->{IgnoreSulfur} = 1;
|
|
|
101
|
|
|
102 # TPSA atom types assigned to appropriate atoms...
|
|
|
103 %{$This->{AtomTypes}} = ();
|
|
|
104
|
|
|
105 # Intialize descriptor names and values...
|
|
|
106 $This->_InitializeDescriptorNamesAndValues(@DescriptorNames);
|
|
|
107
|
|
|
108 return $This;
|
|
|
109 }
|
|
|
110
|
|
|
111 # Initialize object properties...
|
|
|
112 #
|
|
|
113 sub _InitializeTPSADescriptorsProperties {
|
|
|
114 my($This, %NamesAndValues) = @_;
|
|
|
115
|
|
|
116 my($Name, $Value, $MethodName);
|
|
|
117 while (($Name, $Value) = each %NamesAndValues) {
|
|
|
118 $MethodName = "Set${Name}";
|
|
|
119 $This->$MethodName($Value);
|
|
|
120 }
|
|
|
121
|
|
|
122 return $This;
|
|
|
123 }
|
|
|
124
|
|
|
125 # Calculate Topological Polar Surface Area (TPSA) value [ Ref 90-91 ] for molecule...
|
|
|
126 #
|
|
|
127 # Methodology:
|
|
|
128 # . Assign TPSA atom types [ Ref 90-91 ] to Nitrogen and Oxygen
|
|
|
129 # atoms with optional assignment to Phosphorus and Sulfur atoms.
|
|
|
130 # . Calculate TPSA value adding contribution of appropriate atom types.
|
|
|
131 #
|
|
|
132 sub GenerateDescriptors {
|
|
|
133 my($This) = @_;
|
|
|
134
|
|
|
135 # Initialize descriptor values...
|
|
|
136 $This->_InitializeDescriptorValues();
|
|
|
137
|
|
|
138 # Check availability of molecule...
|
|
|
139 if (!$This->{Molecule}) {
|
|
|
140 carp "Warning: ${ClassName}->GenerateDescriptors: $This->{Type} molecular descriptors generation didn't succeed: Molecule data is not available: Molecule object hasn't been set...";
|
|
|
141 return undef;
|
|
|
142 }
|
|
|
143
|
|
|
144 # Cache appropriate molecule data...
|
|
|
145 $This->_SetupMoleculeDataCache();
|
|
|
146
|
|
|
147 # Assign TPSA atom types...
|
|
|
148 if (!$This->_AssignAtomTypes()) {
|
|
|
149 carp "Warning: ${ClassName}->GenerateDescriptors: $This->{Type} molecular descriptors generation didn't succeed: Couldn't assign valid TPSA atom types to appropriate atoms...";
|
|
|
150 return undef;
|
|
|
151 }
|
|
|
152
|
|
|
153 # Calculate descriptor values...
|
|
|
154 if (!$This->_CalculateDescriptorValues()) {
|
|
|
155 carp "Warning: ${ClassName}->GenerateDescriptors: $This->{Type} molecular descriptors generation didn't succeed: Couldn't calculate TPSA values corresponding to assigned TPSA atom types...";
|
|
|
156 return undef;
|
|
|
157 }
|
|
|
158
|
|
|
159 # Set final descriptor values...
|
|
|
160 $This->_SetFinalDescriptorValues();
|
|
|
161
|
|
|
162 # Clear cached molecule data...
|
|
|
163 $This->_ClearMoleculeDataCache();
|
|
|
164
|
|
|
165 return $This;
|
|
|
166 }
|
|
|
167
|
|
|
168 # Assign TPSA atom types..
|
|
|
169 #
|
|
|
170 sub _AssignAtomTypes {
|
|
|
171 my($This) = @_;
|
|
|
172 my($TPSAAtomTypes, $Atom, $AtomID);
|
|
|
173
|
|
|
174 %{$This->{AtomTypes}} = ();
|
|
|
175
|
|
|
176 # Assign atom types...
|
|
|
177 $TPSAAtomTypes = new AtomTypes::TPSAAtomTypes('Molecule' => $This->{Molecule}, 'IgnorePhosphorus' => $This->{IgnorePhosphorus}, 'IgnoreSulfur' => $This->{IgnoreSulfur});
|
|
|
178 $TPSAAtomTypes->AssignAtomTypes();
|
|
|
179
|
|
|
180 # Make sure TPSA atom types assignment is successful...
|
|
|
181 if (!$TPSAAtomTypes->IsAtomTypesAssignmentSuccessful()) {
|
|
|
182 return undef;
|
|
|
183 }
|
|
|
184
|
|
|
185 # Collect assigned atom types...
|
|
|
186 for $Atom (@{$This->{Atoms}}) {
|
|
|
187 $AtomID = $Atom->GetID();
|
|
|
188 $This->{AtomTypes}{$AtomID} = $TPSAAtomTypes->GetAtomType($Atom);
|
|
|
189 }
|
|
|
190
|
|
|
191 return $This;
|
|
|
192 }
|
|
|
193
|
|
|
194 # Calculate TPSA value...
|
|
|
195 #
|
|
|
196 sub _CalculateDescriptorValues {
|
|
|
197 my($This) = @_;
|
|
|
198 my($Atom, $AtomID, $TPSA, $TPSAContribution, $TPSADataRef, $AtomType);
|
|
|
199
|
|
|
200 $TPSA = 0;
|
|
|
201
|
|
|
202 # Get TPSA atom types data...
|
|
|
203 $TPSADataRef = AtomTypes::TPSAAtomTypes::GetTPSAAtomTypesData();
|
|
|
204
|
|
|
205 ATOM: for $Atom (@{$This->{Atoms}}) {
|
|
|
206 $AtomID = $Atom->GetID();
|
|
|
207 $AtomType = $This->{AtomTypes}{$AtomID};
|
|
|
208
|
|
|
209 # Ignore inappropriate atoms...
|
|
|
210 if ($AtomType =~ /^None$/i) {
|
|
|
211 next ATOM;
|
|
|
212 }
|
|
|
213
|
|
|
214 $TPSAContribution = 0.0;
|
|
|
215
|
|
|
216 if ($AtomType =~ /^(N|O)$/i) {
|
|
|
217 # TPSA contributions for Nitrogen and Oxygen atoms not explicity defined using atom
|
|
|
218 # environments in Table 1 [ Ref 90 ]
|
|
|
219 if ($AtomType =~ /^N$/i) {
|
|
|
220 # N = 30.5 - X*8.2 + H*1.5 or 0.0 for negative value
|
|
|
221 $TPSAContribution = 30.5 - $Atom->GetAtomicInvariantValue('X') * 8.2 + $Atom->GetAtomicInvariantValue('H') * 1.5;
|
|
|
222 }
|
|
|
223 elsif ($AtomType =~ /^O$/i) {
|
|
|
224 # O = 28.5 - X*8.6 + H*1.5 or 0.0 for negative value
|
|
|
225 $TPSAContribution = 28.5 - $Atom->GetAtomicInvariantValue('X') * 8.6 + $Atom->GetAtomicInvariantValue('H') * 1.5;
|
|
|
226 }
|
|
|
227 if ($TPSAContribution < 0.0) {
|
|
|
228 $TPSAContribution = 0.0;
|
|
|
229 }
|
|
|
230 }
|
|
|
231 elsif (exists $TPSADataRef->{DataCol3}{$AtomType}) {
|
|
|
232 # Data for TPSA contribution is in column number 3...
|
|
|
233 $TPSAContribution = $TPSADataRef->{DataCol3}{$AtomType};
|
|
|
234 }
|
|
|
235 else {
|
|
|
236 # No TPSA data for assigned atom type...
|
|
|
237 return undef;
|
|
|
238 }
|
|
|
239 $TPSA += $TPSAContribution;
|
|
|
240 }
|
|
|
241
|
|
|
242 # Track the calculated values...
|
|
|
243 $This->{TPSA} = MathUtil::round($TPSA, 2);
|
|
|
244
|
|
|
245 return $This;
|
|
|
246 }
|
|
|
247
|
|
|
248 # Setup final descriptor values...
|
|
|
249 #
|
|
|
250 sub _SetFinalDescriptorValues {
|
|
|
251 my($This) = @_;
|
|
|
252
|
|
|
253 $This->{DescriptorsGenerated} = 1;
|
|
|
254
|
|
|
255 $This->SetDescriptorValues($This->{TPSA});
|
|
|
256
|
|
|
257 return $This;
|
|
|
258 }
|
|
|
259
|
|
|
260 # Cache appropriate molecule data...
|
|
|
261 #
|
|
|
262 sub _SetupMoleculeDataCache {
|
|
|
263 my($This) = @_;
|
|
|
264
|
|
|
265 @{$This->{Atoms}} = $This->GetMolecule()->GetAtoms();
|
|
|
266
|
|
|
267 return $This;
|
|
|
268 }
|
|
|
269
|
|
|
270 # Clear cached molecule data...
|
|
|
271 #
|
|
|
272 sub _ClearMoleculeDataCache {
|
|
|
273 my($This) = @_;
|
|
|
274
|
|
|
275 @{$This->{Atoms}} = ();
|
|
|
276
|
|
|
277 return $This;
|
|
|
278 }
|
|
|
279
|
|
|
280 # Return a string containg data for TPSADescriptors object...
|
|
|
281 #
|
|
|
282 sub StringifyTPSADescriptors {
|
|
|
283 my($This) = @_;
|
|
|
284 my($TPSADescriptorsString);
|
|
|
285
|
|
|
286 # Type of MolecularDescriptors...
|
|
|
287 $TPSADescriptorsString = "MolecularDescriptorType: $This->{Type}; IgnorePhosphorus: " . ($This->{IgnorePhosphorus} ? "Yes" : "No") . "; IgnoreSulfur: " . ($This->{IgnoreSulfur} ? "Yes" : "No");
|
|
|
288
|
|
|
289 # Setup molecular descriptor information...
|
|
|
290 $TPSADescriptorsString .= "; " . $This->_StringifyDescriptorNamesAndValues();
|
|
|
291
|
|
|
292 return $TPSADescriptorsString;
|
|
|
293 }
|
|
|
294
|
|
|
295 # Is it a TPSADescriptors object?
|
|
|
296 sub _IsTPSADescriptors {
|
|
|
297 my($Object) = @_;
|
|
|
298
|
|
|
299 return (Scalar::Util::blessed($Object) && $Object->isa($ClassName)) ? 1 : 0;
|
|
|
300 }
|
|
|
301
|
|
|
302 1;
|
|
|
303
|
|
|
304 __END__
|
|
|
305
|
|
|
306 =head1 NAME
|
|
|
307
|
|
|
308 TPSADescriptors
|
|
|
309
|
|
|
310 =head1 SYNOPSIS
|
|
|
311
|
|
|
312 use MolecularDescriptors::TPSADescriptors;
|
|
|
313
|
|
|
314 use MolecularDescriptors::TPSADescriptors qw(:all);
|
|
|
315
|
|
|
316 =head1 DESCRIPTION
|
|
|
317
|
|
|
318 B<TPSADescriptors> class provides the following methods:
|
|
|
319
|
|
|
320 new, GenerateDescriptors, GetDescriptorNames, StringifyTPSADescriptors
|
|
|
321
|
|
|
322 B<TPSADescriptors> is derived from B<MolecularDescriptors> class which in turn
|
|
|
323 is derived from B<ObjectProperty> base class that provides methods not explicitly defined
|
|
|
324 in B<TPSADescriptors>, B<MolecularDescriptors> or B<ObjectProperty> classes using Perl's
|
|
|
325 AUTOLOAD functionality. These methods are generated on-the-fly for a specified object property:
|
|
|
326
|
|
|
327 Set<PropertyName>(<PropertyValue>);
|
|
|
328 $PropertyValue = Get<PropertyName>();
|
|
|
329 Delete<PropertyName>();
|
|
|
330
|
|
|
331 After Topological Polar Surface Area (TPSA) atom types [ Ref 90-91 ] has been assigned
|
|
|
332 to appropriate atoms in a molecule using AtomTypes::TPSAAtomTypes.pm module, TPSA value
|
|
|
333 is calculated by adding up contributions of each appropriate atom type.
|
|
|
334
|
|
|
335 By default, MayaChemTools only uses nitrogen and oxygen atoms during calculation
|
|
|
336 of TPSA and ignores phosphorous and sulfur atoms. [ Ref 90 - 91 ]
|
|
|
337
|
|
|
338 =head2 METHODS
|
|
|
339
|
|
|
340 =over 4
|
|
|
341
|
|
|
342 =item B<new>
|
|
|
343
|
|
|
344 $NewTPSADescriptors = new MolecularDescriptors::TPSADescriptors(
|
|
|
345 %NamesAndValues);
|
|
|
346
|
|
|
347 Using specified I<TPSADescriptors> property names and values hash, B<new>
|
|
|
348 method creates a new object and returns a reference to newly created B<TPSADescriptors>
|
|
|
349 object. By default, the following properties are initialized:
|
|
|
350
|
|
|
351 Molecule = ''
|
|
|
352 Type = 'TPSA'
|
|
|
353 IgnorePhosphorus = 1
|
|
|
354 IgnoreSulfur = 1
|
|
|
355 @DescriptorNames = ('TPSA')
|
|
|
356 @DescriptorValues = ('None')
|
|
|
357
|
|
|
358 Examples:
|
|
|
359
|
|
|
360 $TPSADescriptors = new MolecularDescriptors::TPSADescriptors(
|
|
|
361 'Molecule' => $Molecule);
|
|
|
362
|
|
|
363 $TPSADescriptors = new MolecularDescriptors::TPSADescriptors();
|
|
|
364
|
|
|
365 $TPSADescriptors = new MolecularDescriptors::TPSADescriptors(
|
|
|
366 'IgnorePhosphorus' => 0,
|
|
|
367 'IgnoreSulfur' => 0);
|
|
|
368
|
|
|
369 $TPSADescriptors->SetMolecule($Molecule);
|
|
|
370 $TPSADescriptors->GenerateDescriptors();
|
|
|
371 print "TPSADescriptors: $TPSADescriptors\n";
|
|
|
372
|
|
|
373
|
|
|
374 =item B<GenerateDescriptors>
|
|
|
375
|
|
|
376 $TPSADescriptors->GenerateDescriptors();
|
|
|
377
|
|
|
378 Calculate TPSA value for a molecule and returns I<TPSADescriptors>.
|
|
|
379
|
|
|
380 =item B<GetDescriptorNames>
|
|
|
381
|
|
|
382 @DescriptorNames = $TPSADescriptors->GetDescriptorNames();
|
|
|
383 @DescriptorNames = MolecularDescriptors::TPSADescriptors::
|
|
|
384 GetDescriptorNames();
|
|
|
385
|
|
|
386 Returns all available descriptor names as an array.
|
|
|
387
|
|
|
388 =item B<StringifyTPSADescriptors>
|
|
|
389
|
|
|
390 $String = $TPSADescriptors->StringifyTPSADescriptors();
|
|
|
391
|
|
|
392 Returns a string containing information about I<TPSADescriptors> object.
|
|
|
393
|
|
|
394 =back
|
|
|
395
|
|
|
396 =head1 AUTHOR
|
|
|
397
|
|
|
398 Manish Sud <msud@san.rr.com>
|
|
|
399
|
|
|
400 =head1 SEE ALSO
|
|
|
401
|
|
|
402 MolecularDescriptors.pm, MolecularDescriptorsGenerator.pm
|
|
|
403
|
|
|
404 =head1 COPYRIGHT
|
|
|
405
|
|
|
406 Copyright (C) 2015 Manish Sud. All rights reserved.
|
|
|
407
|
|
|
408 This file is part of MayaChemTools.
|
|
|
409
|
|
|
410 MayaChemTools is free software; you can redistribute it and/or modify it under
|
|
|
411 the terms of the GNU Lesser General Public License as published by the Free
|
|
|
412 Software Foundation; either version 3 of the License, or (at your option)
|
|
|
413 any later version.
|
|
|
414
|
|
|
415 =cut
|
