0
|
1 .\" Automatically generated by Pod::Man 2.25 (Pod::Simple 3.22)
|
|
2 .\"
|
|
3 .\" Standard preamble:
|
|
4 .\" ========================================================================
|
|
5 .de Sp \" Vertical space (when we can't use .PP)
|
|
6 .if t .sp .5v
|
|
7 .if n .sp
|
|
8 ..
|
|
9 .de Vb \" Begin verbatim text
|
|
10 .ft CW
|
|
11 .nf
|
|
12 .ne \\$1
|
|
13 ..
|
|
14 .de Ve \" End verbatim text
|
|
15 .ft R
|
|
16 .fi
|
|
17 ..
|
|
18 .\" Set up some character translations and predefined strings. \*(-- will
|
|
19 .\" give an unbreakable dash, \*(PI will give pi, \*(L" will give a left
|
|
20 .\" double quote, and \*(R" will give a right double quote. \*(C+ will
|
|
21 .\" give a nicer C++. Capital omega is used to do unbreakable dashes and
|
|
22 .\" therefore won't be available. \*(C` and \*(C' expand to `' in nroff,
|
|
23 .\" nothing in troff, for use with C<>.
|
|
24 .tr \(*W-
|
|
25 .ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p'
|
|
26 .ie n \{\
|
|
27 . ds -- \(*W-
|
|
28 . ds PI pi
|
|
29 . if (\n(.H=4u)&(1m=24u) .ds -- \(*W\h'-12u'\(*W\h'-12u'-\" diablo 10 pitch
|
|
30 . if (\n(.H=4u)&(1m=20u) .ds -- \(*W\h'-12u'\(*W\h'-8u'-\" diablo 12 pitch
|
|
31 . ds L" ""
|
|
32 . ds R" ""
|
|
33 . ds C` ""
|
|
34 . ds C' ""
|
|
35 'br\}
|
|
36 .el\{\
|
|
37 . ds -- \|\(em\|
|
|
38 . ds PI \(*p
|
|
39 . ds L" ``
|
|
40 . ds R" ''
|
|
41 'br\}
|
|
42 .\"
|
|
43 .\" Escape single quotes in literal strings from groff's Unicode transform.
|
|
44 .ie \n(.g .ds Aq \(aq
|
|
45 .el .ds Aq '
|
|
46 .\"
|
|
47 .\" If the F register is turned on, we'll generate index entries on stderr for
|
|
48 .\" titles (.TH), headers (.SH), subsections (.SS), items (.Ip), and index
|
|
49 .\" entries marked with X<> in POD. Of course, you'll have to process the
|
|
50 .\" output yourself in some meaningful fashion.
|
|
51 .ie \nF \{\
|
|
52 . de IX
|
|
53 . tm Index:\\$1\t\\n%\t"\\$2"
|
|
54 ..
|
|
55 . nr % 0
|
|
56 . rr F
|
|
57 .\}
|
|
58 .el \{\
|
|
59 . de IX
|
|
60 ..
|
|
61 .\}
|
|
62 .\"
|
|
63 .\" Accent mark definitions (@(#)ms.acc 1.5 88/02/08 SMI; from UCB 4.2).
|
|
64 .\" Fear. Run. Save yourself. No user-serviceable parts.
|
|
65 . \" fudge factors for nroff and troff
|
|
66 .if n \{\
|
|
67 . ds #H 0
|
|
68 . ds #V .8m
|
|
69 . ds #F .3m
|
|
70 . ds #[ \f1
|
|
71 . ds #] \fP
|
|
72 .\}
|
|
73 .if t \{\
|
|
74 . ds #H ((1u-(\\\\n(.fu%2u))*.13m)
|
|
75 . ds #V .6m
|
|
76 . ds #F 0
|
|
77 . ds #[ \&
|
|
78 . ds #] \&
|
|
79 .\}
|
|
80 . \" simple accents for nroff and troff
|
|
81 .if n \{\
|
|
82 . ds ' \&
|
|
83 . ds ` \&
|
|
84 . ds ^ \&
|
|
85 . ds , \&
|
|
86 . ds ~ ~
|
|
87 . ds /
|
|
88 .\}
|
|
89 .if t \{\
|
|
90 . ds ' \\k:\h'-(\\n(.wu*8/10-\*(#H)'\'\h"|\\n:u"
|
|
91 . ds ` \\k:\h'-(\\n(.wu*8/10-\*(#H)'\`\h'|\\n:u'
|
|
92 . ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'^\h'|\\n:u'
|
|
93 . ds , \\k:\h'-(\\n(.wu*8/10)',\h'|\\n:u'
|
|
94 . ds ~ \\k:\h'-(\\n(.wu-\*(#H-.1m)'~\h'|\\n:u'
|
|
95 . ds / \\k:\h'-(\\n(.wu*8/10-\*(#H)'\z\(sl\h'|\\n:u'
|
|
96 .\}
|
|
97 . \" troff and (daisy-wheel) nroff accents
|
|
98 .ds : \\k:\h'-(\\n(.wu*8/10-\*(#H+.1m+\*(#F)'\v'-\*(#V'\z.\h'.2m+\*(#F'.\h'|\\n:u'\v'\*(#V'
|
|
99 .ds 8 \h'\*(#H'\(*b\h'-\*(#H'
|
|
100 .ds o \\k:\h'-(\\n(.wu+\w'\(de'u-\*(#H)/2u'\v'-.3n'\*(#[\z\(de\v'.3n'\h'|\\n:u'\*(#]
|
|
101 .ds d- \h'\*(#H'\(pd\h'-\w'~'u'\v'-.25m'\f2\(hy\fP\v'.25m'\h'-\*(#H'
|
|
102 .ds D- D\\k:\h'-\w'D'u'\v'-.11m'\z\(hy\v'.11m'\h'|\\n:u'
|
|
103 .ds th \*(#[\v'.3m'\s+1I\s-1\v'-.3m'\h'-(\w'I'u*2/3)'\s-1o\s+1\*(#]
|
|
104 .ds Th \*(#[\s+2I\s-2\h'-\w'I'u*3/5'\v'-.3m'o\v'.3m'\*(#]
|
|
105 .ds ae a\h'-(\w'a'u*4/10)'e
|
|
106 .ds Ae A\h'-(\w'A'u*4/10)'E
|
|
107 . \" corrections for vroff
|
|
108 .if v .ds ~ \\k:\h'-(\\n(.wu*9/10-\*(#H)'\s-2\u~\d\s+2\h'|\\n:u'
|
|
109 .if v .ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'\v'-.4m'^\v'.4m'\h'|\\n:u'
|
|
110 . \" for low resolution devices (crt and lpr)
|
|
111 .if \n(.H>23 .if \n(.V>19 \
|
|
112 \{\
|
|
113 . ds : e
|
|
114 . ds 8 ss
|
|
115 . ds o a
|
|
116 . ds d- d\h'-1'\(ga
|
|
117 . ds D- D\h'-1'\(hy
|
|
118 . ds th \o'bp'
|
|
119 . ds Th \o'LP'
|
|
120 . ds ae ae
|
|
121 . ds Ae AE
|
|
122 .\}
|
|
123 .rm #[ #] #H #V #F C
|
|
124 .\" ========================================================================
|
|
125 .\"
|
|
126 .IX Title "MACCSKEYS 1"
|
|
127 .TH MACCSKEYS 1 "2015-03-29" "perl v5.14.2" "MayaChemTools"
|
|
128 .\" For nroff, turn off justification. Always turn off hyphenation; it makes
|
|
129 .\" way too many mistakes in technical documents.
|
|
130 .if n .ad l
|
|
131 .nh
|
|
132 .SH "NAME"
|
|
133 MACCSKeys
|
|
134 .SH "SYNOPSIS"
|
|
135 .IX Header "SYNOPSIS"
|
|
136 use Fingerprints::MACCSKeys;
|
|
137 .PP
|
|
138 use Fingerprints::MACCSKeys qw(:all);
|
|
139 .SH "DESCRIPTION"
|
|
140 .IX Header "DESCRIPTION"
|
|
141 \&\fBMACCSKeys\fR [ Ref 45\-47 ] class provides the following methods:
|
|
142 .PP
|
|
143 new, GenerateFingerprints, GenerateMACCSKeys, GetDescription, SetSize, SetType,
|
|
144 StringifyMACCSKeys
|
|
145 .PP
|
|
146 \&\fBMACCSKeys\fR is derived from \fBFingerprints\fR class which in turn is derived from
|
|
147 \&\fBObjectProperty\fR base class that provides methods not explicitly defined in \fBMACCSKeys\fR,
|
|
148 \&\fBFingerprints\fR or \fBObjectProperty\fR classes using Perl's \s-1AUTOLOAD\s0 functionality. These
|
|
149 methods are generated on-the-fly for a specified object property:
|
|
150 .PP
|
|
151 .Vb 3
|
|
152 \& Set<PropertyName>(<PropertyValue>);
|
|
153 \& $PropertyValue = Get<PropertyName>();
|
|
154 \& Delete<PropertyName>();
|
|
155 .Ve
|
|
156 .PP
|
|
157 For each \s-1MACCS\s0 (Molecular ACCess System) keys definition, atoms are processed to
|
|
158 determine their membership to the key and the appropriate molecular fingerprints strings
|
|
159 are generated. An atom can belong to multiple \s-1MACCS\s0 keys.
|
|
160 .PP
|
|
161 For \fIMACCSKeyBits\fR value of \fBType\fR option, a fingerprint bit-vector string containing
|
|
162 zeros and ones is generated and for \fIMACCSKeyCount\fR value, a fingerprint vector string
|
|
163 corresponding to number of \s-1MACCS\s0 keys [ Ref 45\-47 ] is generated.
|
|
164 .PP
|
|
165 \&\fIMACCSKeyBits or MACCSKeyCount\fR values for \fBType\fR along with two possible
|
|
166 \&\fI166 | 322\fR values of \fBSize\fR supports generation of four different types of \s-1MACCS\s0
|
|
167 keys fingerprint: \fIMACCS166KeyBits, MACCS166KeyCount, MACCS322KeyBits, MACCS322KeyCount\fR.
|
|
168 .PP
|
|
169 The current release of MayaChemTools generates the following types of \s-1MACCS\s0 keys
|
|
170 fingerprints bit-vector and vector strings:
|
|
171 .PP
|
|
172 .Vb 4
|
|
173 \& FingerprintsBitVector;MACCSKeyBits;166;BinaryString;Ascending;00000000
|
|
174 \& 0000000000000000000000000000000001001000010010000000010010000000011100
|
|
175 \& 0100101010111100011011000100110110000011011110100110111111111111011111
|
|
176 \& 11111111111110111000
|
|
177 \&
|
|
178 \& FingerprintsBitVector;MACCSKeyBits;166;HexadecimalString;Ascending;000
|
|
179 \& 000000021210210e845f8d8c60b79dffbffffd1
|
|
180 \&
|
|
181 \& FingerprintsBitVector;MACCSKeyBits;322;BinaryString;Ascending;11101011
|
|
182 \& 1110011111100101111111000111101100110000000000000011100010000000000000
|
|
183 \& 0000000000000000000000000000000000000000000000101000000000000000000000
|
|
184 \& 0000000000000000000000000000000000000000000000000000000000000000000000
|
|
185 \& 0000000000000000000000000000000000000011000000000000000000000000000000
|
|
186 \& 0000000000000000000000000000000000000000
|
|
187 \&
|
|
188 \& FingerprintsBitVector;MACCSKeyBits;322;HexadecimalString;Ascending;7d7
|
|
189 \& e7af3edc000c1100000000000000500000000000000000000000000000000300000000
|
|
190 \& 000000000
|
|
191 \&
|
|
192 \& FingerprintsVector;MACCSKeyCount;166;OrderedNumericalValues;ValuesStri
|
|
193 \& ng;0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
|
|
194 \& 0 0 0 0 0 0 0 1 0 0 3 0 0 0 0 4 0 0 2 0 0 0 0 0 0 0 0 2 0 0 2 0 0 0 0
|
|
195 \& 0 0 0 0 1 1 8 0 0 0 1 0 0 1 0 1 0 1 0 3 1 3 1 0 0 0 1 2 0 11 1 0 0 0
|
|
196 \& 5 0 0 1 2 0 1 1 0 0 0 0 0 1 1 0 1 1 1 1 0 4 0 0 1 1 0 4 6 1 1 1 2 1 1
|
|
197 \& 3 5 2 2 0 5 3 5 1 1 2 5 1 2 1 2 4 8 3 5 5 2 2 0 3 5 4 1
|
|
198 \&
|
|
199 \& FingerprintsVector;MACCSKeyCount;322;OrderedNumericalValues;ValuesStri
|
|
200 \& ng;14 8 2 0 2 0 4 4 2 1 4 0 0 2 5 10 5 2 1 0 0 2 0 5 13 3 28 5 5 3 0 0
|
|
201 \& 0 4 2 1 1 0 1 1 0 0 2 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 22 5 3 0 0 0 1 0
|
|
202 \& 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
|
|
203 \& 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 11 0 2 0 0 0 0 0 0 0 0 0
|
|
204 \& 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 ...
|
|
205 .Ve
|
|
206 .SS "\s-1METHODS\s0"
|
|
207 .IX Subsection "METHODS"
|
|
208 .IP "\fBnew\fR" 4
|
|
209 .IX Item "new"
|
|
210 .Vb 1
|
|
211 \& $NewMACCSKeys = new MACCSKeys(%NamesAndValues);
|
|
212 .Ve
|
|
213 .Sp
|
|
214 Using specified \fIMACCSKeys\fR property names and values hash, \fBnew\fR method creates a new object
|
|
215 and returns a reference to newly created \fBPathLengthFingerprints\fR object. By default, the
|
|
216 following properties are initialized:
|
|
217 .Sp
|
|
218 .Vb 3
|
|
219 \& Molecule = \*(Aq\*(Aq;
|
|
220 \& Type = \*(Aq\*(Aq
|
|
221 \& Size = \*(Aq\*(Aq
|
|
222 .Ve
|
|
223 .Sp
|
|
224 Examples:
|
|
225 .Sp
|
|
226 .Vb 3
|
|
227 \& $MACCSKeys = new MACCSKeys(\*(AqMolecule\*(Aq => $Molecule,
|
|
228 \& \*(AqType\*(Aq => \*(AqMACCSKeyBits\*(Aq,
|
|
229 \& \*(AqSize\*(Aq => 166);
|
|
230 \&
|
|
231 \& $MACCSKeys = new MACCSKeys(\*(AqMolecule\*(Aq => $Molecule,
|
|
232 \& \*(AqType\*(Aq => \*(AqMACCSKeyCount\*(Aq,
|
|
233 \& \*(AqSize\*(Aq => 166);
|
|
234 \&
|
|
235 \& $MACCSKeys = new MACCSKeys(\*(AqMolecule\*(Aq => $Molecule,
|
|
236 \& \*(AqType\*(Aq => \*(AqMACCSKeyBit\*(Aq,
|
|
237 \& \*(AqSize\*(Aq => 322);
|
|
238 \&
|
|
239 \& $MACCSKeys = new MACCSKeys(\*(AqMolecule\*(Aq => $Molecule,
|
|
240 \& \*(AqType\*(Aq => \*(AqMACCSKeyCount\*(Aq,
|
|
241 \& \*(AqSize\*(Aq => 322);
|
|
242 \&
|
|
243 \& $MACCSKeys\->GenerateMACCSKeys();
|
|
244 \& print "$MACCSKeys\en";
|
|
245 .Ve
|
|
246 .IP "\fBGetDescription\fR" 4
|
|
247 .IX Item "GetDescription"
|
|
248 .Vb 1
|
|
249 \& $Description = $MACCSKeys\->GetDescription();
|
|
250 .Ve
|
|
251 .Sp
|
|
252 Returns a string containing description of \s-1MACCS\s0 keys fingerprints.
|
|
253 .IP "\fBGenerateMACCSKeys or GenerateFingerprints\fR" 4
|
|
254 .IX Item "GenerateMACCSKeys or GenerateFingerprints"
|
|
255 .Vb 1
|
|
256 \& $MACCSKeys = $MACCSKeys\->GenerateMACCSKeys();
|
|
257 .Ve
|
|
258 .Sp
|
|
259 Generates \s-1MACCS\s0 keys fingerprints and returns \fIMACCSKeys\fR.
|
|
260 .Sp
|
|
261 For \fIMACCSKeyBits\fR value of \fBType\fR, a fingerprint bit-vector string containing
|
|
262 zeros and ones is generated and for \fIMACCSKeyCount\fR value, a fingerprint vector string
|
|
263 corresponding to number of \s-1MACCS\s0 keys is generated.
|
|
264 .Sp
|
|
265 \&\fIMACCSKeyBits or MACCSKeyCount\fR values for \fBType\fR option along with two possible
|
|
266 \&\fI166 | 322\fR values of \fBSize\fR supports generation of four different types of \s-1MACCS\s0
|
|
267 keys fingerprint: \fIMACCS166KeyBits, MACCS166KeyCount, MACCS322KeyBits, MACCS322KeyCount\fR.
|
|
268 .Sp
|
|
269 Definition of \s-1MACCS\s0 keys uses the following atom and bond symbols to define atom and
|
|
270 bond environments:
|
|
271 .Sp
|
|
272 .Vb 1
|
|
273 \& Atom symbols for 166 keys [ Ref 47 ]:
|
|
274 \&
|
|
275 \& A : Any valid periodic table element symbol
|
|
276 \& Q : Hetro atoms; any non\-C or non\-H atom
|
|
277 \& X : Halogens; F, Cl, Br, I
|
|
278 \& Z : Others; other than H, C, N, O, Si, P, S, F, Cl, Br, I
|
|
279 \&
|
|
280 \& Atom symbols for 322 keys [ Ref 46 ]:
|
|
281 \&
|
|
282 \& A : Any valid periodic table element symbol
|
|
283 \& Q : Hetro atoms; any non\-C or non\-H atom
|
|
284 \& X : Others; other than H, C, N, O, Si, P, S, F, Cl, Br, I
|
|
285 \& Z is neither defined nor used
|
|
286 \&
|
|
287 \& Bond types:
|
|
288 \&
|
|
289 \& \- : Single
|
|
290 \& = : Double
|
|
291 \& T : Triple
|
|
292 \& # : Triple
|
|
293 \& ~ : Single or double query bond
|
|
294 \& % : An aromatic query bond
|
|
295 \&
|
|
296 \& None : Any bond type; no explicit bond specified
|
|
297 \&
|
|
298 \& $ : Ring bond; $ before a bond type specifies ring bond
|
|
299 \& ! : Chain or non\-ring bond; ! before a bond type specifies chain bond
|
|
300 \&
|
|
301 \& @ : A ring linkage and the number following it specifies the
|
|
302 \& atoms position in the line, thus @1 means linked back to the first
|
|
303 \& atom in the list.
|
|
304 \&
|
|
305 \& Aromatic: Kekule or Arom5
|
|
306 \&
|
|
307 \& Kekule: Bonds in 6\-membered rings with alternate single/double bonds
|
|
308 \& or perimeter bonds
|
|
309 \& Arom5: Bonds in 5\-membered rings with two double bonds and a hetro
|
|
310 \& atom at the apex of the ring.
|
|
311 .Ve
|
|
312 .Sp
|
|
313 \&\s-1MACCS\s0 166 keys [ Ref 45\-47 ] are defined as follows:
|
|
314 .Sp
|
|
315 .Vb 1
|
|
316 \& Key Description
|
|
317 \&
|
|
318 \& 1 ISOTOPE
|
|
319 \& 2 103 < ATOMIC NO. < 256
|
|
320 \& 3 GROUP IVA,VA,VIA PERIODS 4\-6 (Ge...)
|
|
321 \& 4 ACTINIDE
|
|
322 \& 5 GROUP IIIB,IVB (Sc...)
|
|
323 \& 6 LANTHANIDE
|
|
324 \& 7 GROUP VB,VIB,VIIB (V...)
|
|
325 \& 8 QAAA@1
|
|
326 \& 9 GROUP VIII (Fe...)
|
|
327 \& 10 GROUP IIA (ALKALINE EARTH)
|
|
328 \& 11 4M RING
|
|
329 \& 12 GROUP IB,IIB (Cu...)
|
|
330 \& 13 ON(C)C
|
|
331 \& 14 S\-S
|
|
332 \& 15 OC(O)O
|
|
333 \& 16 QAA@1
|
|
334 \& 17 CTC
|
|
335 \& 18 GROUP IIIA (B...)
|
|
336 \& 19 7M RING
|
|
337 \& 20 SI
|
|
338 \& 21 C=C(Q)Q
|
|
339 \& 22 3M RING
|
|
340 \& 23 NC(O)O
|
|
341 \& 24 N\-O
|
|
342 \& 25 NC(N)N
|
|
343 \& 26 C$=C($A)$A
|
|
344 \& 27 I
|
|
345 \& 28 QCH2Q
|
|
346 \& 29 P
|
|
347 \& 30 CQ(C)(C)A
|
|
348 \& 31 QX
|
|
349 \& 32 CSN
|
|
350 \& 33 NS
|
|
351 \& 34 CH2=A
|
|
352 \& 35 GROUP IA (ALKALI METAL)
|
|
353 \& 36 S HETEROCYCLE
|
|
354 \& 37 NC(O)N
|
|
355 \& 38 NC(C)N
|
|
356 \& 39 OS(O)O
|
|
357 \& 40 S\-O
|
|
358 \& 41 CTN
|
|
359 \& 42 F
|
|
360 \& 43 QHAQH
|
|
361 \& 44 OTHER
|
|
362 \& 45 C=CN
|
|
363 \& 46 BR
|
|
364 \& 47 SAN
|
|
365 \& 48 OQ(O)O
|
|
366 \& 49 CHARGE
|
|
367 \& 50 C=C(C)C
|
|
368 \& 51 CSO
|
|
369 \& 52 NN
|
|
370 \& 53 QHAAAQH
|
|
371 \& 54 QHAAQH
|
|
372 \& 55 OSO
|
|
373 \& 56 ON(O)C
|
|
374 \& 57 O HETEROCYCLE
|
|
375 \& 58 QSQ
|
|
376 \& 59 Snot%A%A
|
|
377 \& 60 S=O
|
|
378 \& 61 AS(A)A
|
|
379 \& 62 A$A!A$A
|
|
380 \& 63 N=O
|
|
381 \& 64 A$A!S
|
|
382 \& 65 C%N
|
|
383 \& 66 CC(C)(C)A
|
|
384 \& 67 QS
|
|
385 \& 68 QHQH (&...)
|
|
386 \& 69 QQH
|
|
387 \& 70 QNQ
|
|
388 \& 71 NO
|
|
389 \& 72 OAAO
|
|
390 \& 73 S=A
|
|
391 \& 74 CH3ACH3
|
|
392 \& 75 A!N$A
|
|
393 \& 76 C=C(A)A
|
|
394 \& 77 NAN
|
|
395 \& 78 C=N
|
|
396 \& 79 NAAN
|
|
397 \& 80 NAAAN
|
|
398 \& 81 SA(A)A
|
|
399 \& 82 ACH2QH
|
|
400 \& 83 QAAAA@1
|
|
401 \& 84 NH2
|
|
402 \& 85 CN(C)C
|
|
403 \& 86 CH2QCH2
|
|
404 \& 87 X!A$A
|
|
405 \& 88 S
|
|
406 \& 89 OAAAO
|
|
407 \& 90 QHAACH2A
|
|
408 \& 91 QHAAACH2A
|
|
409 \& 92 OC(N)C
|
|
410 \& 93 QCH3
|
|
411 \& 94 QN
|
|
412 \& 95 NAAO
|
|
413 \& 96 5M RING
|
|
414 \& 97 NAAAO
|
|
415 \& 98 QAAAAA@1
|
|
416 \& 99 C=C
|
|
417 \& 100 ACH2N
|
|
418 \& 101 8M RING
|
|
419 \& 102 QO
|
|
420 \& 103 CL
|
|
421 \& 104 QHACH2A
|
|
422 \& 105 A$A($A)$A
|
|
423 \& 106 QA(Q)Q
|
|
424 \& 107 XA(A)A
|
|
425 \& 108 CH3AAACH2A
|
|
426 \& 109 ACH2O
|
|
427 \& 110 NCO
|
|
428 \& 111 NACH2A
|
|
429 \& 112 AA(A)(A)A
|
|
430 \& 113 Onot%A%A
|
|
431 \& 114 CH3CH2A
|
|
432 \& 115 CH3ACH2A
|
|
433 \& 116 CH3AACH2A
|
|
434 \& 117 NAO
|
|
435 \& 118 ACH2CH2A > 1
|
|
436 \& 119 N=A
|
|
437 \& 120 HETEROCYCLIC ATOM > 1 (&...)
|
|
438 \& 121 N HETEROCYCLE
|
|
439 \& 122 AN(A)A
|
|
440 \& 123 OCO
|
|
441 \& 124 QQ
|
|
442 \& 125 AROMATIC RING > 1
|
|
443 \& 126 A!O!A
|
|
444 \& 127 A$A!O > 1 (&...)
|
|
445 \& 128 ACH2AAACH2A
|
|
446 \& 129 ACH2AACH2A
|
|
447 \& 130 QQ > 1 (&...)
|
|
448 \& 131 QH > 1
|
|
449 \& 132 OACH2A
|
|
450 \& 133 A$A!N
|
|
451 \& 134 X (HALOGEN)
|
|
452 \& 135 Nnot%A%A
|
|
453 \& 136 O=A > 1
|
|
454 \& 137 HETEROCYCLE
|
|
455 \& 138 QCH2A > 1 (&...)
|
|
456 \& 139 OH
|
|
457 \& 140 O > 3 (&...)
|
|
458 \& 141 CH3 > 2 (&...)
|
|
459 \& 142 N > 1
|
|
460 \& 143 A$A!O
|
|
461 \& 144 Anot%A%Anot%A
|
|
462 \& 145 6M RING > 1
|
|
463 \& 146 O > 2
|
|
464 \& 147 ACH2CH2A
|
|
465 \& 148 AQ(A)A
|
|
466 \& 149 CH3 > 1
|
|
467 \& 150 A!A$A!A
|
|
468 \& 151 NH
|
|
469 \& 152 OC(C)C
|
|
470 \& 153 QCH2A
|
|
471 \& 154 C=O
|
|
472 \& 155 A!CH2!A
|
|
473 \& 156 NA(A)A
|
|
474 \& 157 C\-O
|
|
475 \& 158 C\-N
|
|
476 \& 159 O > 1
|
|
477 \& 160 CH3
|
|
478 \& 161 N
|
|
479 \& 162 AROMATIC
|
|
480 \& 163 6M RING
|
|
481 \& 164 O
|
|
482 \& 165 RING
|
|
483 \& 166 FRAGMENTS
|
|
484 .Ve
|
|
485 .Sp
|
|
486 \&\s-1MACCS\s0 322 keys set as defined in tables 1, 2 and 3 [ Ref 46 ] include:
|
|
487 .Sp
|
|
488 .Vb 3
|
|
489 \& o 26 atom properties of type P, as listed in Table 1
|
|
490 \& o 32 one\-atom environments, as listed in Table 3
|
|
491 \& o 264 atom\-bond\-atom combinations listed in Table 4
|
|
492 .Ve
|
|
493 .Sp
|
|
494 Total number of keys in three tables is : 322
|
|
495 .Sp
|
|
496 Atom symbol, X, used for 322 keys [ Ref 46 ] doesn't refer to Halogens as it does for 166 keys. In
|
|
497 order to keep the definition of 322 keys consistent with the published definitions, the symbol X is
|
|
498 used to imply \*(L"others\*(R" atoms, but it's internally mapped to symbol X as defined for 166 keys
|
|
499 during the generation of key values.
|
|
500 .Sp
|
|
501 Atom properties-based keys (26):
|
|
502 .Sp
|
|
503 .Vb 10
|
|
504 \& Key Description
|
|
505 \& 1 A(AAA) or AA(A)A \- atom with at least three neighbors
|
|
506 \& 2 Q \- heteroatom
|
|
507 \& 3 Anot%not\-A \- atom involved in one or more multiple bonds, not aromatic
|
|
508 \& 4 A(AAAA) or AA(A)(A)A \- atom with at least four neighbors
|
|
509 \& 5 A(QQ) or QA(Q) \- atom with at least two heteroatom neighbors
|
|
510 \& 6 A(QQQ) or QA(Q)Q \- atom with at least three heteroatom neighbors
|
|
511 \& 7 QH \- heteroatom with at least one hydrogen attached
|
|
512 \& 8 CH2(AA) or ACH2A \- carbon with at least two single bonds and at least
|
|
513 \& two hydrogens attached
|
|
514 \& 9 CH3(A) or ACH3 \- carbon with at least one single bond and at least three
|
|
515 \& hydrogens attached
|
|
516 \& 10 Halogen
|
|
517 \& 11 A(\-A\-A\-A) or A\-A(\-A)\-A \- atom has at least three single bonds
|
|
518 \& 12 AAAAAA@1 > 2 \- atom is in at least two different six\-membered rings
|
|
519 \& 13 A($A$A$A) or A$A($A)$A \- atom has more than two ring bonds
|
|
520 \& 14 A$A!A$A \- atom is at a ring/chain boundary. When a comparison is done
|
|
521 \& with another atom the path passes through the chain bond.
|
|
522 \& 15 Anot%A%Anot%A \- atom is at an aromatic/nonaromatic boundary. When a
|
|
523 \& comparison is done with another atom the path
|
|
524 \& passes through the aromatic bond.
|
|
525 \& 16 A!A!A \- atom with more than one chain bond
|
|
526 \& 17 A!A$A!A \- atom is at a ring/chain boundary. When a comparison is done
|
|
527 \& with another atom the path passes through the ring bond.
|
|
528 \& 18 A%Anot%A%A \- atom is at an aromatic/nonaromatic boundary. When a
|
|
529 \& comparison is done with another atom the
|
|
530 \& path passes through the nonaromatic bond.
|
|
531 \& 19 HETEROCYCLE \- atom is a heteroatom in a ring.
|
|
532 \& 20 rare properties: atom with five or more neighbors, atom in
|
|
533 \& four or more rings, or atom types other than
|
|
534 \& H, C, N, O, S, F, Cl, Br, or I
|
|
535 \& 21 rare properties: atom has a charge, is an isotope, has two or
|
|
536 \& more multiple bonds, or has a triple bond.
|
|
537 \& 22 N \- nitrogen
|
|
538 \& 23 S \- sulfur
|
|
539 \& 24 O \- oxygen
|
|
540 \& 25 A(AA)A(A)A(AA) \- atom has two neighbors, each with three or
|
|
541 \& more neighbors (including the central atom).
|
|
542 \& 26 CHACH2 \- atom has two hydrocarbon (CH2) neighbors
|
|
543 .Ve
|
|
544 .Sp
|
|
545 Atomic environments properties-based keys (32):
|
|
546 .Sp
|
|
547 .Vb 10
|
|
548 \& Key Description
|
|
549 \& 27 C(CC)
|
|
550 \& 28 C(CCC)
|
|
551 \& 29 C(CN)
|
|
552 \& 30 C(CCN)
|
|
553 \& 31 C(NN)
|
|
554 \& 32 C(NNC)
|
|
555 \& 33 C(NNN)
|
|
556 \& 34 C(CO)
|
|
557 \& 35 C(CCO)
|
|
558 \& 36 C(NO)
|
|
559 \& 37 C(NCO)
|
|
560 \& 38 C(NNO)
|
|
561 \& 39 C(OO)
|
|
562 \& 40 C(COO)
|
|
563 \& 41 C(NOO)
|
|
564 \& 42 C(OOO)
|
|
565 \& 43 Q(CC)
|
|
566 \& 44 Q(CCC)
|
|
567 \& 45 Q(CN)
|
|
568 \& 46 Q(CCN)
|
|
569 \& 47 Q(NN)
|
|
570 \& 48 Q(CNN)
|
|
571 \& 49 Q(NNN)
|
|
572 \& 50 Q(CO)
|
|
573 \& 51 Q(CCO)
|
|
574 \& 52 Q(NO)
|
|
575 \& 53 Q(CNO)
|
|
576 \& 54 Q(NNO)
|
|
577 \& 55 Q(OO)
|
|
578 \& 56 Q(COO)
|
|
579 \& 57 Q(NOO)
|
|
580 \& 58 Q(OOO)
|
|
581 .Ve
|
|
582 .Sp
|
|
583 Note: The first symbol is the central atom, with atoms bonded to the central atom listed in
|
|
584 parentheses. Q is any non-C, non-H atom. If only two atoms are in parentheses, there is
|
|
585 no implication concerning the other atoms bonded to the central atom.
|
|
586 .Sp
|
|
587 Atom-Bond-Atom properties-based keys: (264)
|
|
588 .Sp
|
|
589 .Vb 10
|
|
590 \& Key Description
|
|
591 \& 59 C\-C
|
|
592 \& 60 C\-N
|
|
593 \& 61 C\-O
|
|
594 \& 62 C\-S
|
|
595 \& 63 C\-Cl
|
|
596 \& 64 C\-P
|
|
597 \& 65 C\-F
|
|
598 \& 66 C\-Br
|
|
599 \& 67 C\-Si
|
|
600 \& 68 C\-I
|
|
601 \& 69 C\-X
|
|
602 \& 70 N\-N
|
|
603 \& 71 N\-O
|
|
604 \& 72 N\-S
|
|
605 \& 73 N\-Cl
|
|
606 \& 74 N\-P
|
|
607 \& 75 N\-F
|
|
608 \& 76 N\-Br
|
|
609 \& 77 N\-Si
|
|
610 \& 78 N\-I
|
|
611 \& 79 N\-X
|
|
612 \& 80 O\-O
|
|
613 \& 81 O\-S
|
|
614 \& 82 O\-Cl
|
|
615 \& 83 O\-P
|
|
616 \& 84 O\-F
|
|
617 \& 85 O\-Br
|
|
618 \& 86 O\-Si
|
|
619 \& 87 O\-I
|
|
620 \& 88 O\-X
|
|
621 \& 89 S\-S
|
|
622 \& 90 S\-Cl
|
|
623 \& 91 S\-P
|
|
624 \& 92 S\-F
|
|
625 \& 93 S\-Br
|
|
626 \& 94 S\-Si
|
|
627 \& 95 S\-I
|
|
628 \& 96 S\-X
|
|
629 \& 97 Cl\-Cl
|
|
630 \& 98 Cl\-P
|
|
631 \& 99 Cl\-F
|
|
632 \& 100 Cl\-Br
|
|
633 \& 101 Cl\-Si
|
|
634 \& 102 Cl\-I
|
|
635 \& 103 Cl\-X
|
|
636 \& 104 P\-P
|
|
637 \& 105 P\-F
|
|
638 \& 106 P\-Br
|
|
639 \& 107 P\-Si
|
|
640 \& 108 P\-I
|
|
641 \& 109 P\-X
|
|
642 \& 110 F\-F
|
|
643 \& 111 F\-Br
|
|
644 \& 112 F\-Si
|
|
645 \& 113 F\-I
|
|
646 \& 114 F\-X
|
|
647 \& 115 Br\-Br
|
|
648 \& 116 Br\-Si
|
|
649 \& 117 Br\-I
|
|
650 \& 118 Br\-X
|
|
651 \& 119 Si\-Si
|
|
652 \& 120 Si\-I
|
|
653 \& 121 Si\-X
|
|
654 \& 122 I\-I
|
|
655 \& 123 I\-X
|
|
656 \& 124 X\-X
|
|
657 \& 125 C=C
|
|
658 \& 126 C=N
|
|
659 \& 127 C=O
|
|
660 \& 128 C=S
|
|
661 \& 129 C=Cl
|
|
662 \& 130 C=P
|
|
663 \& 131 C=F
|
|
664 \& 132 C=Br
|
|
665 \& 133 C=Si
|
|
666 \& 134 C=I
|
|
667 \& 135 C=X
|
|
668 \& 136 N=N
|
|
669 \& 137 N=O
|
|
670 \& 138 N=S
|
|
671 \& 139 N=Cl
|
|
672 \& 140 N=P
|
|
673 \& 141 N=F
|
|
674 \& 142 N=Br
|
|
675 \& 143 N=Si
|
|
676 \& 144 N=I
|
|
677 \& 145 N=X
|
|
678 \& 146 O=O
|
|
679 \& 147 O=S
|
|
680 \& 148 O=Cl
|
|
681 \& 149 O=P
|
|
682 \& 150 O=F
|
|
683 \& 151 O=Br
|
|
684 \& 152 O=Si
|
|
685 \& 153 O=I
|
|
686 \& 154 O=X
|
|
687 \& 155 S=S
|
|
688 \& 156 S=Cl
|
|
689 \& 157 S=P
|
|
690 \& 158 S=F
|
|
691 \& 159 S=Br
|
|
692 \& 160 S=Si
|
|
693 \& 161 S=I
|
|
694 \& 162 S=X
|
|
695 \& 163 Cl=Cl
|
|
696 \& 164 Cl=P
|
|
697 \& 165 Cl=F
|
|
698 \& 166 Cl=Br
|
|
699 \& 167 Cl=Si
|
|
700 \& 168 Cl=I
|
|
701 \& 169 Cl=X
|
|
702 \& 170 P=P
|
|
703 \& 171 P=F
|
|
704 \& 172 P=Br
|
|
705 \& 173 P=Si
|
|
706 \& 174 P=I
|
|
707 \& 175 P=X
|
|
708 \& 176 F=F
|
|
709 \& 177 F=Br
|
|
710 \& 178 F=Si
|
|
711 \& 179 F=I
|
|
712 \& 180 F=X
|
|
713 \& 181 Br=Br
|
|
714 \& 182 Br=Si
|
|
715 \& 183 Br=I
|
|
716 \& 184 Br=X
|
|
717 \& 185 Si=Si
|
|
718 \& 186 Si=I
|
|
719 \& 187 Si=X
|
|
720 \& 188 I=I
|
|
721 \& 189 I=X
|
|
722 \& 190 X=X
|
|
723 \& 191 C#C
|
|
724 \& 192 C#N
|
|
725 \& 193 C#O
|
|
726 \& 194 C#S
|
|
727 \& 195 C#Cl
|
|
728 \& 196 C#P
|
|
729 \& 197 C#F
|
|
730 \& 198 C#Br
|
|
731 \& 199 C#Si
|
|
732 \& 200 C#I
|
|
733 \& 201 C#X
|
|
734 \& 202 N#N
|
|
735 \& 203 N#O
|
|
736 \& 204 N#S
|
|
737 \& 205 N#Cl
|
|
738 \& 206 N#P
|
|
739 \& 207 N#F
|
|
740 \& 208 N#Br
|
|
741 \& 209 N#Si
|
|
742 \& 210 N#I
|
|
743 \& 211 N#X
|
|
744 \& 212 O#O
|
|
745 \& 213 O#S
|
|
746 \& 214 O#Cl
|
|
747 \& 215 O#P
|
|
748 \& 216 O#F
|
|
749 \& 217 O#Br
|
|
750 \& 218 O#Si
|
|
751 \& 219 O#I
|
|
752 \& 220 O#X
|
|
753 \& 221 S#S
|
|
754 \& 222 S#Cl
|
|
755 \& 223 S#P
|
|
756 \& 224 S#F
|
|
757 \& 225 S#Br
|
|
758 \& 226 S#Si
|
|
759 \& 227 S#I
|
|
760 \& 228 S#X
|
|
761 \& 229 Cl#Cl
|
|
762 \& 230 Cl#P
|
|
763 \& 231 Cl#F
|
|
764 \& 232 Cl#Br
|
|
765 \& 233 Cl#Si
|
|
766 \& 234 Cl#I
|
|
767 \& 235 Cl#X
|
|
768 \& 236 P#P
|
|
769 \& 237 P#F
|
|
770 \& 238 P#Br
|
|
771 \& 239 P#Si
|
|
772 \& 240 P#I
|
|
773 \& 241 P#X
|
|
774 \& 242 F#F
|
|
775 \& 243 F#Br
|
|
776 \& 244 F#Si
|
|
777 \& 245 F#I
|
|
778 \& 246 F#X
|
|
779 \& 247 Br#Br
|
|
780 \& 248 Br#Si
|
|
781 \& 249 Br#I
|
|
782 \& 250 Br#X
|
|
783 \& 251 Si#Si
|
|
784 \& 252 Si#I
|
|
785 \& 253 Si#X
|
|
786 \& 254 I#I
|
|
787 \& 255 I#X
|
|
788 \& 256 X#X
|
|
789 \& 257 C$C
|
|
790 \& 258 C$N
|
|
791 \& 259 C$O
|
|
792 \& 260 C$S
|
|
793 \& 261 C$Cl
|
|
794 \& 262 C$P
|
|
795 \& 263 C$F
|
|
796 \& 264 C$Br
|
|
797 \& 265 C$Si
|
|
798 \& 266 C$I
|
|
799 \& 267 C$X
|
|
800 \& 268 N$N
|
|
801 \& 269 N$O
|
|
802 \& 270 N$S
|
|
803 \& 271 N$Cl
|
|
804 \& 272 N$P
|
|
805 \& 273 N$F
|
|
806 \& 274 N$Br
|
|
807 \& 275 N$Si
|
|
808 \& 276 N$I
|
|
809 \& 277 N$X
|
|
810 \& 278 O$O
|
|
811 \& 279 O$S
|
|
812 \& 280 O$Cl
|
|
813 \& 281 O$P
|
|
814 \& 282 O$F
|
|
815 \& 283 O$Br
|
|
816 \& 284 O$Si
|
|
817 \& 285 O$I
|
|
818 \& 286 O$X
|
|
819 \& 287 S$S
|
|
820 \& 288 S$Cl
|
|
821 \& 289 S$P
|
|
822 \& 290 S$F
|
|
823 \& 291 S$Br
|
|
824 \& 292 S$Si
|
|
825 \& 293 S$I
|
|
826 \& 294 S$X
|
|
827 \& 295 Cl$Cl
|
|
828 \& 296 Cl$P
|
|
829 \& 297 Cl$F
|
|
830 \& 298 Cl$Br
|
|
831 \& 299 Cl$Si
|
|
832 \& 300 Cl$I
|
|
833 \& 301 Cl$X
|
|
834 \& 302 P$P
|
|
835 \& 303 P$F
|
|
836 \& 304 P$Br
|
|
837 \& 305 P$Si
|
|
838 \& 306 P$I
|
|
839 \& 307 P$X
|
|
840 \& 308 F$F
|
|
841 \& 309 F$Br
|
|
842 \& 310 F$Si
|
|
843 \& 311 F$I
|
|
844 \& 312 F$X
|
|
845 \& 313 Br$Br
|
|
846 \& 314 Br$Si
|
|
847 \& 315 Br$I
|
|
848 \& 316 Br$X
|
|
849 \& 317 Si$Si
|
|
850 \& 318 Si$I
|
|
851 \& 319 Si$X
|
|
852 \& 320 I$I
|
|
853 \& 321 I$X
|
|
854 \& 322 X$X
|
|
855 .Ve
|
|
856 .IP "\fBSetSize\fR" 4
|
|
857 .IX Item "SetSize"
|
|
858 .Vb 1
|
|
859 \& $MACCSKeys\->SetSize($Size);
|
|
860 .Ve
|
|
861 .Sp
|
|
862 Sets size of \s-1MACCS\s0 keys and returns \fIMACCSKeys\fR. Possible values: \fI166 or 322\fR.
|
|
863 .IP "\fBSetType\fR" 4
|
|
864 .IX Item "SetType"
|
|
865 .Vb 1
|
|
866 \& $MACCSKeys\->SetType($Type);
|
|
867 .Ve
|
|
868 .Sp
|
|
869 Sets type of \s-1MACCS\s0 keys and returns \fIMACCSKeys\fR. Possible values: \fIMACCSKeysBits or
|
|
870 MACCSKeysCount\fR.
|
|
871 .IP "\fBStringifyMACCSKeys\fR" 4
|
|
872 .IX Item "StringifyMACCSKeys"
|
|
873 .Vb 1
|
|
874 \& $String = $MACCSKeys\->StringifyMACCSKeys();
|
|
875 .Ve
|
|
876 .Sp
|
|
877 Returns a string containing information about \fIMACCSKeys\fR object.
|
|
878 .SH "AUTHOR"
|
|
879 .IX Header "AUTHOR"
|
|
880 Manish Sud <msud@san.rr.com>
|
|
881 .SH "SEE ALSO"
|
|
882 .IX Header "SEE ALSO"
|
|
883 Fingerprints.pm, FingerprintsStringUtil.pm, AtomNeighborhoodsFingerprints.pm,
|
|
884 AtomTypesFingerprints.pm, EStateIndiciesFingerprints.pm, ExtendedConnectivityFingerprints.pm,
|
|
885 PathLengthFingerprints.pm, TopologicalAtomPairsFingerprints.pm, TopologicalAtomTripletsFingerprints.pm,
|
|
886 TopologicalAtomTorsionsFingerprints.pm, TopologicalPharmacophoreAtomPairsFingerprints.pm,
|
|
887 TopologicalPharmacophoreAtomTripletsFingerprints.pm
|
|
888 .SH "COPYRIGHT"
|
|
889 .IX Header "COPYRIGHT"
|
|
890 Copyright (C) 2015 Manish Sud. All rights reserved.
|
|
891 .PP
|
|
892 This file is part of MayaChemTools.
|
|
893 .PP
|
|
894 MayaChemTools is free software; you can redistribute it and/or modify it under
|
|
895 the terms of the \s-1GNU\s0 Lesser General Public License as published by the Free
|
|
896 Software Foundation; either version 3 of the License, or (at your option)
|
|
897 any later version.
|