Mercurial > repos > marcel > caddsuite_linux_x86_64

comparison CADDSuite/data/OpenBabel/SMARTS_InteLigand.txt @ 0:bac3c274238f

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Migrated tool version 0.93 from old tool shed archive to new tool shed repository
author marcel
date Tue, 07 Jun 2011 16:43:30 -0400
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:bac3c274238f
1 #
2 # SMARTS Patterns for Functional Group Classification
3 #
4 # written by Christian Laggner
5 # Copyright 2005 Inte:Ligand Software-Entwicklungs und Consulting GmbH
6 #
7 # Released under the Lesser General Public License (LGPL license)
8 # see http://www.gnu.org/copyleft/lesser.html
9 # Modified from Version 221105
10 #####################################################################################################
11
12 # General Stuff:
13 # These patters were written in an attempt to represent the classification of organic compounds
14 # from the viewpoint of an organic chemist.
15 # They are often very restrictive. This may be generally a good thing, but it also takes some time
16 # for filtering/indexing large compound sets.
17 # For filtering undesired groups (in druglike compounds) one will want to have more general patterns
18 # (e.g. you don't want *any* halide of *any* acid, *neither* aldehyde *nor* formyl esters and amides, ...).
19 #
20
21 # Part I: Carbon
22 # ==============
23
24
25 # I.1: Carbon-Carbon Bonds
26 # ------------------------
27
28 # I.1.1 Alkanes:
29
30 Primary_carbon: [CX4H3][#6]
31
32 Secondary_carbon: [CX4H2]([#6])[#6]
33
34 Tertiary_carbon: [CX4H1]([#6])([#6])[#6]
35
36 Quaternary_carbon: [CX4]([#6])([#6])([#6])[#6]
37
38
39 # I.1.2 C-C double and Triple Bonds
40
41 Alkene: [CX3;$([H2]),$([H1][#6]),$(C([#6])[#6])]=[CX3;$([H2]),$([H1][#6]),$(C([#6])[#6])]
42 # sp2 C may be substituted only by C or H -
43 # does not hit ketenes and allenes, nor enamines, enols and the like
44
45 Alkyne: [CX2]#[CX2]
46 # non-carbon substituents (e.g. alkynol ethers) are rather rare, thus no further discrimination
47
48 Allene: [CX3]=[CX2]=[CX3]
49
50
51 # I.2: One Carbon-Hetero Bond
52 # ---------------------------
53
54
55 # I.2.1 Alkyl Halogenides
56
57 Alkylchloride: [ClX1][CX4]
58 # will also hit chloromethylethers and the like, but no chloroalkenes, -alkynes or -aromats
59 # a more restrictive version can be obtained by modifying the Alcohol string.
60
61 Alkylfluoride: [FX1][CX4]
62
63 Alkylbromide: [BrX1][CX4]
64
65 Alkyliodide: [IX1][CX4]
66
67
68 # I.2.2 Alcohols and Ethers
69
70 Alcohol: [OX2H][CX4;!$(C([OX2H])[O,S,#7,#15])]
71 # nonspecific definition, no acetals, aminals, and the like
72
73 Primary_alcohol: [OX2H][CX4H2;!$(C([OX2H])[O,S,#7,#15])]
74
75 Secondary_alcohol: [OX2H][CX4H;!$(C([OX2H])[O,S,#7,#15])]
76
77 Tertiary_alcohol: [OX2H][CX4D4;!$(C([OX2H])[O,S,#7,#15])]
78
79 Dialkylether: [OX2]([CX4;!$(C([OX2])[O,S,#7,#15,F,Cl,Br,I])])[CX4;!$(C([OX2])[O,S,#7,#15])]
80 # no acetals and the like; no enolethers
81
82 Dialkylthioether: [SX2]([CX4;!$(C([OX2])[O,S,#7,#15,F,Cl,Br,I])])[CX4;!$(C([OX2])[O,S,#7,#15])]
83 # no acetals and the like; no enolethers
84
85 Alkylarylether: [OX2](c)[CX4;!$(C([OX2])[O,S,#7,#15,F,Cl,Br,I])]
86 # no acetals and the like; no enolethers
87
88 Diarylether: [c][OX2][c]
89
90 Alkylarylthioether: [SX2](c)[CX4;!$(C([OX2])[O,S,#7,#15,F,Cl,Br,I])]
91
92 Diarylthioether: [c][SX2][c]
93
94 Oxonium: [O+;!$([O]~[!#6]);!$([S]*~[#7,#8,#15,#16])]
95 # can't be aromatic, thus O and not #8
96
97 # I.2.3 Amines
98
99 Amine: [NX3+0,NX4+;!$([N]~[!#6]);!$([N]*~[#7,#8,#15,#16])]
100 # hits all amines (prim/sec/tert/quart), including ammonium salts, also enamines, but not amides, imides, aminals, ...
101
102 # the following amines include also the protonated forms
103
104 Primary_aliph_amine: [NX3H2+0,NX4H3+;!$([N][!C]);!$([N]*~[#7,#8,#15,#16])]
105
106 Secondary_aliph_amine: [NX3H1+0,NX4H2+;!$([N][!C]);!$([N]*~[#7,#8,#15,#16])]
107
108 Tertiary_aliph_amine: [NX3H0+0,NX4H1+;!$([N][!C]);!$([N]*~[#7,#8,#15,#16])]
109
110 Quaternary_aliph_ammonium: [NX4H0+;!$([N][!C]);!$([N]*~[#7,#8,#15,#16])]
111
112 Primary_arom_amine: [NX3H2+0,NX4H3+]c
113
114 Secondary_arom_amine: [NX3H1+0,NX4H2+;!$([N][!c]);!$([N]*~[#7,#8,#15,#16])]
115
116 Tertiary_arom_amine: [NX3H0+0,NX4H1+;!$([N][!c]);!$([N]*~[#7,#8,#15,#16])]
117
118 Quaternary_arom_ammonium: [NX4H0+;!$([N][!c]);!$([N]*~[#7,#8,#15,#16])]
119
120 Secondary_mixed_amine: [NX3H1+0,NX4H2+;$([N]([c])[C]);!$([N]*~[#7,#8,#15,#16])]
121
122 Tertiary_mixed_amine: [NX3H0+0,NX4H1+;$([N]([c])([C])[#6]);!$([N]*~[#7,#8,#15,#16])]
123
124 Quaternary_mixed_ammonium: [NX4H0+;$([N]([c])([C])[#6][#6]);!$([N]*~[#7,#8,#15,#16])]
125
126 Ammonium: [N+;!$([N]~[!#6]);!$(N=*);!$([N]*~[#7,#8,#15,#16])]
127 # only C and H substituents allowed. Quaternary or protonated amines
128 # NX4+ or Nv4+ is not recognized by Daylight's depictmatch if less than four C are present
129
130
131 # I.2.4 Others
132
133 Alkylthiol: [SX2H][CX4;!$(C([SX2H])~[O,S,#7,#15])]
134
135 Dialkylthioether: [SX2]([CX4;!$(C([SX2])[O,S,#7,#15,F,Cl,Br,I])])[CX4;!$(C([SX2])[O,S,#7,#15])]
136
137 Alkylarylthioether: [SX2](c)[CX4;!$(C([SX2])[O,S,#7,#15])]
138
139 Disulfide: [SX2D2][SX2D2]
140
141 1,2-Aminoalcohol: [OX2H][CX4;!$(C([OX2H])[O,S,#7,#15,F,Cl,Br,I])][CX4;!$(C([N])[O,S,#7,#15])][NX3;!$(NC=[O,S,N])]
142 # does not hit alpha-amino acids, enaminoalcohols, 1,2-aminoacetals, o-aminophenols, etc.
143
144 1,2-Diol: [OX2H][CX4;!$(C([OX2H])[O,S,#7,#15])][CX4;!$(C([OX2H])[O,S,#7,#15])][OX2H]
145 # does not hit alpha-hydroxy acids, enolalcohols, 1,2-hydroxyacetals, 1,2-diphenols, etc.
146
147 1,1-Diol: [OX2H][CX4;!$(C([OX2H])([OX2H])[O,S,#7,#15])][OX2H]
148
149 Hydroperoxide: [OX2H][OX2]
150 #does not neccessarily have to be connected to a carbon atom, includes also hydrotrioxides
151
152 Peroxo: [OX2D2][OX2D2]
153
154 Organolithium_compounds: [LiX1][#6,#14]
155
156 Organomagnesium_compounds: [MgX2][#6,#14]
157 # not restricted to Grignard compounds, also dialkyl Mg
158
159 Organometallic_compounds: [!#1;!#5;!#6;!#7;!#8;!#9;!#14;!#15;!#16;!#17;!#33;!#34;!#35;!#52;!#53;!#85]~[#6;!-]
160 # very general, includes all metals covalently bound to carbon
161
162
163 # I.3: Two Carbon-Hetero Bonds (Carbonyl and Derivatives)
164 # ----------------------------
165
166 # I.3.1 Double Bond to Hetero
167
168 Aldehyde: [$([CX3H][#6]),$([CX3H2])]=[OX1]
169 # hits aldehydes including formaldehyde
170
171 Ketone: [#6][CX3](=[OX1])[#6]
172 # does not include oxo-groups connected to a (hetero-) aromatic ring
173
174 Thioaldehyde: [$([CX3H][#6]),$([CX3H2])]=[SX1]
175
176 Thioketone: [#6][CX3](=[SX1])[#6]
177 # does not include thioxo-groups connected to a (hetero-) aromatic ring
178
179 Imine: [NX2;$([N][#6]),$([NH]);!$([N][CX3]=[#7,#8,#15,#16])]=[CX3;$([CH2]),$([CH][#6]),$([C]([#6])[#6])]
180 # nitrogen is not part of an amidelike strukture, nor of an aromatic ring, but can be part of an aminal or similar
181
182 Immonium: [NX3+;!$([N][!#6]);!$([N][CX3]=[#7,#8,#15,#16])]
183
184 Oxime: [NX2](=[CX3;$([CH2]),$([CH][#6]),$([C]([#6])[#6])])[OX2H]
185
186 Oximether: [NX2](=[CX3;$([CH2]),$([CH][#6]),$([C]([#6])[#6])])[OX2][#6;!$(C=[#7,#8])]
187 # ether, not ester or amide; does not hit isoxazole
188
189
190 # I.3.2. Two Single Bonds to Hetero
191
192 Acetal: [OX2]([#6;!$(C=[O,S,N])])[CX4;!$(C(O)(O)[!#6])][OX2][#6;!$(C=[O,S,N])]
193 # does not hit hydroxy-methylesters, ketenacetals, hemiacetals, orthoesters, etc.
194
195 Hemiacetal: [OX2H][CX4;!$(C(O)(O)[!#6])][OX2][#6;!$(C=[O,S,N])]
196
197 Aminal: [NX3v3;!$(NC=[#7,#8,#15,#16])]([#6])[CX4;!$(C(N)(N)[!#6])][NX3v3;!$(NC=[#7,#8,#15,#16])][#6]
198 # Ns are not part of an amide or similar. v3 ist to exclude nitro and similar groups
199
200 Hemiaminal: [NX3v3;!$(NC=[#7,#8,#15,#16])]([#6])[CX4;!$(C(N)(N)[!#6])][OX2H]
201
202 Thioacetal: [SX2]([#6;!$(C=[O,S,N])])[CX4;!$(C(S)(S)[!#6])][SX2][#6;!$(C=[O,S,N])]
203
204 Thiohemiacetal: [SX2]([#6;!$(C=[O,S,N])])[CX4;!$(C(S)(S)[!#6])][OX2H]
205
206 Halogen_acetal_like: [NX3v3,SX2,OX2;!$(*C=[#7,#8,#15,#16])][CX4;!$(C([N,S,O])([N,S,O])[!#6])][FX1,ClX1,BrX1,IX1]
207 # hits chloromethylenethers and other reactive alkylating agents
208
209 Acetal_like: [NX3v3,SX2,OX2;!$(*C=[#7,#8,#15,#16])][CX4;!$(C([N,S,O])([N,S,O])[!#6])][FX1,ClX1,BrX1,IX1,NX3v3,SX2,OX2;!$(*C=[#7,#8,#15,#16])]
210 # includes all of the above and other combinations (S-C-N, hydrates, ...), but still no aminomethylenesters and similar
211
212 Halogenmethylen_ester_and_similar: [NX3v3,SX2,OX2;$(**=[#7,#8,#15,#16])][CX4;!$(C([N,S,O])([N,S,O])[!#6])][FX1,ClX1,BrX1,IX1]
213 # also reactive alkylating agents. Acid does not have to be carboxylic acid, also S- and P-based acids allowed
214
215 NOS_methylen_ester_and_similar: [NX3v3,SX2,OX2;$(**=[#7,#8,#15,#16])][CX4;!$(C([N,S,O])([N,S,O])[!#6])][NX3v3,SX2,OX2;!$(*C=[#7,#8,#15,#16])]
216 # Same as above, but N,O or S instead of halogen. Ester/amide allowed only on one side
217
218 Hetero_methylen_ester_and_similar: [NX3v3,SX2,OX2;$(**=[#7,#8,#15,#16])][CX4;!$(C([N,S,O])([N,S,O])[!#6])][FX1,ClX1,BrX1,IX1,NX3v3,SX2,OX2;!$(*C=[#7,#8,#15,#16])]
219 # Combination of the last two patterns
220
221 Cyanhydrine: [NX1]#[CX2][CX4;$([CH2]),$([CH]([CX2])[#6]),$(C([CX2])([#6])[#6])][OX2H]
222
223
224 # I.3.3 Single Bond to Hetero, C=C Double Bond (Enols and Similar)
225
226 Chloroalkene: [ClX1][CX3]=[CX3]
227
228 Fluoroalkene: [FX1][CX3]=[CX3]
229
230 Bromoalkene: [BrX1][CX3]=[CX3]
231
232 Iodoalkene: [IX1][CX3]=[CX3]
233
234 Enol: [OX2H][CX3;$([H1]),$(C[#6])]=[CX3]
235 # no phenols
236
237 Endiol: [OX2H][CX3;$([H1]),$(C[#6])]=[CX3;$([H1]),$(C[#6])][OX2H]
238 # no 1,2-diphenols, ketenacetals, ...
239
240 Enolether: [OX2]([#6;!$(C=[N,O,S])])[CX3;$([H0][#6]),$([H1])]=[CX3]
241 # finds also endiodiethers, but not enolesters, no aromats
242
243 Enolester: [OX2]([CX3]=[OX1])[#6X3;$([#6][#6]),$([H1])]=[#6X3;!$(C[OX2H])]
244
245
246 Enamine: [NX3;$([NH2][CX3]),$([NH1]([CX3])[#6]),$([N]([CX3])([#6])[#6]);!$([N]*=[#7,#8,#15,#16])][CX3;$([CH]),$([C][#6])]=[CX3]
247 # does not hit amines attached to aromatic rings, nor may the nitrogen be aromatic
248
249 Thioenol: [SX2H][CX3;$([H1]),$(C[#6])]=[CX3]
250
251 Thioenolether: [SX2]([#6;!$(C=[N,O,S])])[CX3;$(C[#6]),$([CH])]=[CX3]
252
253
254 # I.4: Three Carbon-Hetero Bonds (Carboxyl and Derivatives)
255 # ------------------------------
256
257 Acylchloride: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[ClX1]
258
259 Acylfluoride: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[FX1]
260
261 Acylbromide: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[BrX1]
262
263 Acyliodide: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[IX1]
264
265 Acylhalide: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[FX1,ClX1,BrX1,IX1]
266 # all of the above
267
268
269 # The following contains all simple carboxylic combinations of O, N, S, & Hal -
270 # - acids, esters, amides, ... as well as a few extra cases (anhydride, hydrazide...)
271 # Cyclic structures (including aromats) like lactones, lactames, ... got their own
272 # definitions. Structures where both heteroatoms are part of an aromatic ring
273 # (oxazoles, imidazoles, ...) were excluded.
274
275 Carboxylic_acid: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[$([OX2H]),$([OX1-])]
276 # includes carboxylate anions
277
278 Carboxylic_ester: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[OX2][#6;!$(C=[O,N,S])]
279 # does not hit anhydrides or lactones
280
281 Lactone: [#6][#6X3R](=[OX1])[#8X2][#6;!$(C=[O,N,S])]
282 # may also be aromatic
283
284 Carboxylic_anhydride: [CX3;$([H0][#6]),$([H1])](=[OX1])[#8X2][CX3;$([H0][#6]),$([H1])](=[OX1])
285 # anhydride formed by two carboxylic acids, no mixed anhydrides (e.g. between carboxylic acid and sulfuric acid); may be part of a ring, even aromatic
286
287 Carboxylic_acid_derivative: [$([#6X3H0][#6]),$([#6X3H])](=[!#6])[!#6]
288 # includes most of the structures of I.4 and many more, also 1,3-heteroaromatics such as isoxazole
289
290 Carbothioic_acid: [CX3;!R;$([C][#6]),$([CH]);$([C](=[OX1])[$([SX2H]),$([SX1-])]),$([C](=[SX1])[$([OX2H]),$([OX1-])])]
291 # hits both tautomeric forms, as well as anions
292
293 Carbothioic_S_ester: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[SX2][#6;!$(C=[O,N,S])]
294
295 Carbothioic_S_lactone: [#6][#6X3R](=[OX1])[#16X2][#6;!$(C=[O,N,S])]
296 # may also be aromatic
297
298 Carbothioic_O_ester: [CX3;$([H0][#6]),$([H1])](=[SX1])[OX2][#6;!$(C=[O,N,S])]
299
300 Carbothioic_O_lactone: [#6][#6X3R](=[SX1])[#8X2][#6;!$(C=[O,N,S])]
301
302 Carbothioic_halide: [CX3;$([H0][#6]),$([H1])](=[SX1])[FX1,ClX1,BrX1,IX1]
303
304 Carbodithioic_acid: [CX3;!R;$([C][#6]),$([CH]);$([C](=[SX1])[SX2H])]
305
306 Carbodithioic_ester: [CX3;!R;$([C][#6]),$([CH]);$([C](=[SX1])[SX2][#6;!$(C=[O,N,S])])]
307
308 Carbodithiolactone: [#6][#6X3R](=[SX1])[#16X2][#6;!$(C=[O,N,S])]
309
310
311 Amide: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]
312 # does not hit lactames
313
314 Primary_amide: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[NX3H2]
315
316 Secondary_amide: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[#7X3H1][#6;!$(C=[O,N,S])]
317
318 Tertiary_amide: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[#7X3H0]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])]
319
320 Lactam: [#6R][#6X3R](=[OX1])[#7X3;$([H1][#6;!$(C=[O,N,S])]),$([H0]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]
321 # cyclic amides, may also be aromatic
322
323 Alkyl_imide: [#6X3;$([H0][#6]),$([H1])](=[OX1])[#7X3H0]([#6])[#6X3;$([H0][#6]),$([H1])](=[OX1])
324 # may be part of a ring, even aromatic. only C allowed at central N. May also be triacyl amide
325
326 N_hetero_imide: [#6X3;$([H0][#6]),$([H1])](=[OX1])[#7X3H0]([!#6])[#6X3;$([H0][#6]),$([H1])](=[OX1])
327 # everything else than H or C at central N
328
329 Imide_acidic: [#6X3;$([H0][#6]),$([H1])](=[OX1])[#7X3H1][#6X3;$([H0][#6]),$([H1])](=[OX1])
330 # can be deprotonated
331
332 Thioamide: [$([CX3;!R][#6]),$([CX3H;!R])](=[SX1])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]
333 # does not hit thiolactames
334
335 Thiolactam: [#6R][#6X3R](=[SX1])[#7X3;$([H1][#6;!$(C=[O,N,S])]),$([H0]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]
336 # cyclic thioamides, may also be aromatic
337
338
339 Oximester: [#6X3;$([H0][#6]),$([H1])](=[OX1])[#8X2][#7X2]=,:[#6X3;$([H0]([#6])[#6]),$([H1][#6]),$([H2])]
340 # may also be part of a ring / aromatic
341
342 Amidine: [NX3;!$(NC=[O,S])][CX3;$([CH]),$([C][#6])]=[NX2;!$(NC=[O,S])]
343 # only basic amidines, not as part of aromatic ring (e.g. imidazole)
344
345 Hydroxamic_acid: [CX3;$([H0][#6]),$([H1])](=[OX1])[#7X3;$([H1]),$([H0][#6;!$(C=[O,N,S])])][$([OX2H]),$([OX1-])]
346
347 Hydroxamic_acid_ester: [CX3;$([H0][#6]),$([H1])](=[OX1])[#7X3;$([H1]),$([H0][#6;!$(C=[O,N,S])])][OX2][#6;!$(C=[O,N,S])]
348 # does not hit anhydrides of carboxylic acids withs hydroxamic acids
349
350
351 Imidoacid: [CX3R0;$([H0][#6]),$([H1])](=[NX2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[$([OX2H]),$([OX1-])]
352 # not cyclic
353
354 Imidoacid_cyclic: [#6R][#6X3R](=,:[#7X2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[$([OX2H]),$([OX1-])]
355 # the enamide-form of lactames. may be aromatic like 2-hydroxypyridine
356
357 Imidoester: [CX3R0;$([H0][#6]),$([H1])](=[NX2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[OX2][#6;!$(C=[O,N,S])]
358 # esters of the above structures. no anhydrides.
359
360 Imidolactone: [#6R][#6X3R](=,:[#7X2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[OX2][#6;!$(C=[O,N,S])]
361 # no oxazoles and similar
362
363 Imidothioacid: [CX3R0;$([H0][#6]),$([H1])](=[NX2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[$([SX2H]),$([SX1-])]
364 # not cyclic
365
366 Imidothioacid_cyclic: [#6R][#6X3R](=,:[#7X2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[$([SX2H]),$([SX1-])]
367 # the enamide-form of thiolactames. may be aromatic like 2-thiopyridine
368
369 Imidothioester: [CX3R0;$([H0][#6]),$([H1])](=[NX2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[SX2][#6;!$(C=[O,N,S])]
370 # thioesters of the above structures. no anhydrides.
371
372 Imidothiolactone: [#6R][#6X3R](=,:[#7X2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[SX2][#6;!$(C=[O,N,S])]
373 # no thioxazoles and similar
374
375 Amidine: [#7X3v3;!$(N([#6X3]=[#7X2])C=[O,S])][CX3R0;$([H1]),$([H0][#6])]=[NX2v3;!$(N(=[#6X3][#7X3])C=[O,S])]
376 # only basic amidines, not substituted by carbonyl or thiocarbonyl, not as part of a ring
377
378 Imidolactam: [#6][#6X3R;$([H0](=[NX2;!$(N(=[#6X3][#7X3])C=[O,S])])[#7X3;!$(N([#6X3]=[#7X2])C=[O,S])]),$([H0](-[NX3;!$(N([#6X3]=[#7X2])C=[O,S])])=,:[#7X2;!$(N(=[#6X3][#7X3])C=[O,S])])]
379 # one of the two C~N bonds is part of a ring (may be aromatic), but not both - thus no imidazole
380
381 Imidoylhalide: [CX3R0;$([H0][#6]),$([H1])](=[NX2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[FX1,ClX1,BrX1,IX1]
382 # not cyclic
383
384 Imidoylhalide_cyclic: [#6R][#6X3R](=,:[#7X2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[FX1,ClX1,BrX1,IX1]
385 # may also be aromatic
386
387 # may be ring, aromatic, substituted with carbonyls, hetero, ...
388 # (everything else would get too complicated)
389
390 Amidrazone: [$([$([#6X3][#6]),$([#6X3H])](=[#7X2v3])[#7X3v3][#7X3v3]),$([$([#6X3][#6]),$([#6X3H])]([#7X3v3])=[#7X2v3][#7X3v3])]
391 # hits both tautomers. as above, it may be ring, aromatic, substituted with carbonyls, hetero, ...
392
393
394 Alpha_aminoacid: [NX3,NX4+;!$([N]~[!#6]);!$([N]*~[#7,#8,#15,#16])][C][CX3](=[OX1])[OX2H,OX1-]
395 # N may be alkylated, but not part of an amide (as in peptides), ionic forms are included
396 # includes also non-natural aminoacids with double-bonded or two aliph./arom. substituents at alpha-C
397 # N may not be aromatic as in 1H-pyrrole-2-carboxylic acid
398
399 Alpha_hydroxyacid: [OX2H][C][CX3](=[OX1])[OX2H,OX1-]
400
401 Peptide_middle: [NX3;$([N][CX3](=[OX1])[C][NX3,NX4+])][C][CX3](=[OX1])[NX3;$([N][C][CX3](=[OX1])[NX3,OX2,OX1-])]
402 # finds peptidic structures which are neither C- nor N-terminal. Both neighbours must be amino-acids/peptides
403
404 Peptide_C_term: [NX3;$([N][CX3](=[OX1])[C][NX3,NX4+])][C][CX3](=[OX1])[OX2H,OX1-]
405 # finds C-terminal amino acids
406
407 Peptide_N_term: [NX3,NX4+;!$([N]~[!#6]);!$([N]*~[#7,#8,#15,#16])][C][CX3](=[OX1])[NX3;$([N][C][CX3](=[OX1])[NX3,OX2,OX1-])]
408 # finds N-terminal amino acids. As above, N may be substituted, but not part of an amide-bond.
409
410
411 Carboxylic_orthoester: [#6][OX2][CX4;$(C[#6]),$([CH])]([OX2][#6])[OX2][#6]
412 # hits also anhydride like struktures (e. g. HC(OMe)2-OC=O residues)
413
414 Ketene: [CX3]=[CX2]=[OX1]
415
416 Ketenacetal: [#7X2,#8X3,#16X2;$(*[#6,#14])][#6X3]([#7X2,#8X3,#16X2;$(*[#6,#14])])=[#6X3]
417 # includes aminals, silylacetals, ketenesters, etc. C=C DB is not aromatic, everything else may be
418
419 Nitrile: [NX1]#[CX2]
420 # includes cyanhydrines
421
422 Isonitrile: [CX1-]#[NX2+]
423
424
425 Vinylogous_carbonyl_or_carboxyl_derivative: [#6X3](=[OX1])[#6X3]=,:[#6X3][#7,#8,#16,F,Cl,Br,I]
426 # may be part of a ring, even aromatic
427
428 Vinylogous_acid: [#6X3](=[OX1])[#6X3]=,:[#6X3][$([OX2H]),$([OX1-])]
429
430 Vinylogous_ester: [#6X3](=[OX1])[#6X3]=,:[#6X3][#6;!$(C=[O,N,S])]
431
432 Vinylogous_amide: [#6X3](=[OX1])[#6X3]=,:[#6X3][#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]
433
434 Vinylogous_halide: [#6X3](=[OX1])[#6X3]=,:[#6X3][FX1,ClX1,BrX1,IX1]
435
436
437
438 # I.5: Four Carbon-Hetero Bonds (Carbonic Acid and Derivatives)
439 # -----------------------------
440
441 Carbonic_acid_dieester: [#6;!$(C=[O,N,S])][#8X2][#6X3](=[OX1])[#8X2][#6;!$(C=[O,N,S])]
442 # may be part of a ring, even aromatic
443
444 Carbonic_acid_esterhalide: [#6;!$(C=[O,N,S])][OX2;!R][CX3](=[OX1])[OX2][FX1,ClX1,BrX1,IX1]
445
446 Carbonic_acid_monoester: [#6;!$(C=[O,N,S])][OX2;!R][CX3](=[OX1])[$([OX2H]),$([OX1-])]
447 # unstable
448
449 Carbonic_acid_derivatives: [!#6][#6X3](=[!#6])[!#6]
450
451
452 Thiocarbonic_acid_dieester: [#6;!$(C=[O,N,S])][#8X2][#6X3](=[SX1])[#8X2][#6;!$(C=[O,N,S])]
453 # may be part of a ring, even aromatic
454
455 Thiocarbonic_acid_esterhalide: [#6;!$(C=[O,N,S])][OX2;!R][CX3](=[SX1])[OX2][FX1,ClX1,BrX1,IX1]
456
457 Thiocarbonic_acid_monoester: [#6;!$(C=[O,N,S])][OX2;!R][CX3](=[SX1])[$([OX2H]),$([OX1-])]
458
459
460 Urea:[#7X3;!$([#7][!#6])][#6X3](=[OX1])[#7X3;!$([#7][!#6])]
461 # no check whether part of imide, biuret, etc. Aromatic structures are only hit if
462 # both N share no double bonds, like in the dioxo-form of uracil
463
464 Thiourea: [#7X3;!$([#7][!#6])][#6X3](=[SX1])[#7X3;!$([#7][!#6])]
465
466 Isourea: [#7X2;!$([#7][!#6])]=,:[#6X3]([#8X2&!$([#8][!#6]),OX1-])[#7X3;!$([#7][!#6])]
467 # O may be substituted. no check whether further amide-like bonds are present. Aromatic
468 # structures are only hit if single bonded N shares no additional double bond, like in
469 # the 1-hydroxy-3-oxo form of uracil
470
471 Isothiourea: [#7X2;!$([#7][!#6])]=,:[#6X3]([#16X2&!$([#16][!#6]),SX1-])[#7X3;!$([#7][!#6])]
472
473 Guanidine: [N;v3X3,v4X4+][CX3](=[N;v3X2,v4X3+])[N;v3X3,v4X4+]
474 # also hits guanidinium salts. v3 and v4 to avoid nitroamidines
475
476 Carbaminic_acid: [NX3]C(=[OX1])[O;X2H,X1-]
477 # quite unstable, unlikely to be found. Also hits salts
478
479 Urethan: [#7X3][#6](=[OX1])[#8X2][#6]
480 # also hits when part of a ring, no check whether the last C is part of carbonyl
481
482 Biuret: [#7X3][#6](=[OX1])[#7X3][#6](=[OX1])[#7X3]
483
484 Semicarbazide: [#7X3][#7X3][#6X3]([#7X3;!$([#7][#7])])=[OX1]
485
486 Carbazide: [#7X3][#7X3][#6X3]([#7X3][#7X3])=[OX1]
487
488 Semicarbazone: [#7X2](=[#6])[#7X3][#6X3]([#7X3;!$([#7][#7])])=[OX1]
489
490 Carbazone: [#7X2](=[#6])[#7X3][#6X3]([#7X3][#7X3])=[OX1]
491
492 Thiosemicarbazide: [#7X3][#7X3][#6X3]([#7X3;!$([#7][#7])])=[SX1]
493
494 Thiocarbazide: [#7X3][#7X3][#6X3]([#7X3][#7X3])=[SX1]
495
496 Thiosemicarbazone: [#7X2](=[#6])[#7X3][#6X3]([#7X3;!$([#7][#7])])=[SX1]
497
498 Thiocarbazone: [#7X2](=[#6])[#7X3][#6X3]([#7X3][#7X3])=[SX1]
499
500
501 Isocyanate: [NX2]=[CX2]=[OX1]
502
503 Cyanate: [OX2][CX2]#[NX1]
504
505 Isothiocyanate: [NX2]=[CX2]=[SX1]
506
507 Thiocyanate: [SX2][CX2]#[NX1]
508
509 Carbodiimide: [NX2]=[CX2]=[NX2]
510
511 Orthocarbonic_derivatives: [CX4H0]([O,S,#7])([O,S,#7])([O,S,#7])[O,S,#7,F,Cl,Br,I]
512 # halogen allowed just once, to avoid mapping to -OCF3 and similar groups (much more
513 # stable as for example C(OCH3)4)
514
515
516 # I.6 Aromatics
517 # -------------
518
519 # I know that this classification is not very logical, arylamines are found under I.2 ...
520
521 Phenol: [OX2H][c]
522
523 1,2-Diphenol: [OX2H][c][c][OX2H]
524
525 Arylchloride: [Cl][c]
526
527 Arylfluoride: [F][c]
528
529 Arylbromide: [Br][c]
530
531 Aryliodide: [I][c]
532
533 Arylthiol: [SX2H][c]
534
535 Iminoarene: [c]=[NX2;$([H1]),$([H0][#6;!$([C]=[N,S,O])])]
536 # N may be substituted with H or C, but not carbonyl or similar
537 # aromatic atom is always C, not S or P (these are not planar when substituted)
538
539 Oxoarene: [c]=[OX1]
540
541 Thioarene: [c]=[SX1]
542
543 Hetero_N_basic_H: [nX3H1+0]
544 # as in pyrole. uncharged to exclude pyridinium ions
545
546 Hetero_N_basic_no_H: [nX3H0+0]
547 # as in N-methylpyrole. uncharged to exclude pyridinium ions
548
549 Hetero_N_nonbasic: [nX2,nX3+]
550 # as in pyridine, pyridinium
551
552 Hetero_O: [o]
553
554 Hetero_S: [sX2]
555 # X2 because Daylight's depictmatch falsely describes C1=CS(=O)C=C1 as aromatic
556 # (is not planar because of lonepair at S)
557
558 Heteroaromatic: [a;!c]
559
560
561 # Part II: N, S, P, Si, B
562 # =======================
563
564
565 # II.1 Nitrogen
566 # -------------
567
568 Nitrite: [NX2](=[OX1])[O;$([X2]),$([X1-])]
569 # hits nitrous acid, its anion, esters, and other O-substituted derivatives
570
571 Thionitrite: [SX2][NX2]=[OX1]
572
573 Nitrate: [$([NX3](=[OX1])(=[OX1])[O;$([X2]),$([X1-])]),$([NX3+]([OX1-])(=[OX1])[O;$([X2]),$([X1-])])]
574 # hits nitric acid, its anion, esters, and other O-substituted derivatives
575
576 Nitro: [$([NX3](=O)=O),$([NX3+](=O)[O-])][!#8]
577 # hits nitro groups attached to C,N, ... but not nitrates
578
579 Nitroso: [NX2](=[OX1])[!#7;!#8]
580 # no nitrites, no nitrosamines
581
582 Azide: [NX1]~[NX2]~[NX2,NX1]
583 # hits both mesomeric forms, also anion
584
585 Acylazide: [CX3](=[OX1])[NX2]~[NX2]~[NX1]
586
587 Diazo: [$([#6]=[NX2+]=[NX1-]),$([#6-]-[NX2+]#[NX1])]
588
589 Diazonium: [#6][NX2+]#[NX1]
590
591 Nitrosamine: [#7;!$(N*=O)][NX2]=[OX1]
592
593 Nitrosamide: [NX2](=[OX1])N-*=O
594 # includes nitrososulfonamides
595
596 N-Oxide: [$([#7+][OX1-]),$([#7v5]=[OX1]);!$([#7](~[O])~[O]);!$([#7]=[#7])]
597 # Hits both forms. Won't hit azoxy, nitro, nitroso, or nitrate.
598
599
600 Hydrazine: [NX3;$([H2]),$([H1][#6]),$([H0]([#6])[#6]);!$(NC=[O,N,S])][NX3;$([H2]),$([H1][#6]),$([H0]([#6])[#6]);!$(NC=[O,N,S])]
601 # no hydrazides
602
603 Hydrazone: [NX3;$([H2]),$([H1][#6]),$([H0]([#6])[#6]);!$(NC=[O,N,S])][NX2]=[#6]
604
605 Hydroxylamine: [NX3;$([H2]),$([H1][#6]),$([H0]([#6])[#6]);!$(NC=[O,N,S])][OX2;$([H1]),$(O[#6;!$(C=[N,O,S])])]
606 # no discrimination between O-, N-, and O,N-substitution
607
608
609 # II.2 Sulfur
610 # -----------
611
612 Sulfon: [$([SX4](=[OX1])(=[OX1])([#6])[#6]),$([SX4+2]([OX1-])([OX1-])([#6])[#6])]
613 # can't be aromatic, thus S and not #16
614
615 Sulfoxide: [$([SX3](=[OX1])([#6])[#6]),$([SX3+]([OX1-])([#6])[#6])]
616
617 Sulfonium: [S+;!$([S]~[!#6]);!$([S]*~[#7,#8,#15,#16])]
618 # can't be aromatic, thus S and not #16
619
620 Sulfuric_acid: [SX4](=[OX1])(=[OX1])([$([OX2H]),$([OX1-])])[$([OX2H]),$([OX1-])]
621 # includes anions
622
623 Sulfuric_monoester: [SX4](=[OX1])(=[OX1])([$([OX2H]),$([OX1-])])[OX2][#6;!$(C=[O,N,S])]
624
625 Sulfuric_diester: [SX4](=[OX1])(=[OX1])([OX2][#6;!$(C=[O,N,S])])[OX2][#6;!$(C=[O,N,S])]
626
627 Sulfuric_monoamide: [SX4](=[OX1])(=[OX1])([#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])])[$([OX2H]),$([OX1-])]
628
629 Sulfuric_diamide: [SX4](=[OX1])(=[OX1])([#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]
630
631 Sulfuric_esteramide: [SX4](=[OX1])(=[OX1])([#7X3][#6;!$(C=[O,N,S])])[OX2][#6;!$(C=[O,N,S])]
632
633 Sulfuric_derivative: [SX4D4](=[!#6])(=[!#6])([!#6])[!#6]
634 # everything else (would not be a "true" derivative of sulfuric acid, if one of the substituents were less electronegative
635 # than sulfur, but this should be very very rare, anyway)
636
637
638
639 #### sulfurous acid and derivatives missing!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
640
641
642
643
644 Sulfonic_acid: [SX4;$([H1]),$([H0][#6])](=[OX1])(=[OX1])[$([OX2H]),$([OX1-])]
645
646 Sulfonamide: [SX4;$([H1]),$([H0][#6])](=[OX1])(=[OX1])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]
647
648 Sulfonic_ester: [SX4;$([H1]),$([H0][#6])](=[OX1])(=[OX1])[OX2][#6;!$(C=[O,N,S])]
649
650 Sulfonic_halide: [SX4;$([H1]),$([H0][#6])](=[OX1])(=[OX1])[FX1,ClX1,BrX1,IX1]
651
652 Sulfonic_derivative: [SX4;$([H1]),$([H0][#6])](=[!#6])(=[!#6])[!#6]
653 # includes all of the above and many more
654 # for comparison: this is what "all sulfonic derivatives but not the ones above" would look like:
655 # [$([SX4;$([H1]),$([H0][#6])](=[!#6])(=[!#6;!O])[!#6]),$([SX4;$([H1]),$([H0][#6])](=[OX1])(=[OX1])[!$([FX1,ClX1,BrX1,IX1]);!$([#6]);!$([OX2H]);!$([OX1-]);!$([OX2][#6;!$(C=[O,N,S])]);!$([#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])])])]
656
657
658 Sulfinic_acid: [SX3;$([H1]),$([H0][#6])](=[OX1])[$([OX2H]),$([OX1-])]
659
660 Sulfinic_amide: [SX3;$([H1]),$([H0][#6])](=[OX1])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]
661
662 Sulfinic_ester: [SX3;$([H1]),$([H0][#6])](=[OX1])[OX2][#6;!$(C=[O,N,S])]
663
664 Sulfinic_halide: [SX3;$([H1]),$([H0][#6])](=[OX1])[FX1,ClX1,BrX1,IX1]
665
666 Sulfinic_derivative: [SX3;$([H1]),$([H0][#6])](=[!#6])[!#6]
667
668 Sulfenic_acid: [SX2;$([H1]),$([H0][#6])][$([OX2H]),$([OX1-])]
669
670 Sulfenic_amide: [SX2;$([H1]),$([H0][#6])][#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]
671
672 Sulfenic_ester: [SX2;$([H1]),$([H0][#6])][OX2][#6;!$(C=[O,N,S])]
673
674 Sulfenic_halide: [SX2;$([H1]),$([H0][#6])][FX1,ClX1,BrX1,IX1]
675
676 Sulfenic_derivative: [SX2;$([H1]),$([H0][#6])][!#6]
677
678
679 # II.3 Phosphorous
680 # ----------------
681
682 Phosphine: [PX3;$([H3]),$([H2][#6]),$([H1]([#6])[#6]),$([H0]([#6])([#6])[#6])]
683 # similar to amine, but less restrictive: includes also amide- and aminal-analogues
684
685 Phosphine_oxide: [PX4;$([H3]=[OX1]),$([H2](=[OX1])[#6]),$([H1](=[OX1])([#6])[#6]),$([H0](=[OX1])([#6])([#6])[#6])]
686
687 Phosphonium: [P+;!$([P]~[!#6]);!$([P]*~[#7,#8,#15,#16])]
688 # similar to Ammonium
689
690 Phosphorylen: [PX4;$([H3]=[CX3]),$([H2](=[CX3])[#6]),$([H1](=[CX3])([#6])[#6]),$([H0](=[CX3])([#6])([#6])[#6])]
691
692
693 # conventions for the following acids and derivatives:
694 # acids find protonated and deprotonated acids
695 # esters do not find mixed anhydrides ( ...P-O-C(=O))
696 # derivatives: subtituents which go in place of the OH and =O are not H or C (may also be O,
697 # thus including acids and esters)
698
699 Phosphonic_acid: [PX4;$([H1]),$([H0][#6])](=[OX1])([$([OX2H]),$([OX1-])])[$([OX2H]),$([OX1-])]
700 # includes anions
701
702 Phosphonic_monoester: [PX4;$([H1]),$([H0][#6])](=[OX1])([$([OX2H]),$([OX1-])])[OX2][#6;!$(C=[O,N,S])]
703
704 Phosphonic_diester: [PX4;$([H1]),$([H0][#6])](=[OX1])([OX2][#6;!$(C=[O,N,S])])[OX2][#6;!$(C=[O,N,S])]
705
706 Phosphonic_monoamide: [PX4;$([H1]),$([H0][#6])](=[OX1])([$([OX2H]),$([OX1-])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]
707
708 Phosphonic_diamide: [PX4;$([H1]),$([H0][#6])](=[OX1])([#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]
709
710 Phosphonic_esteramide: [PX4;$([H1]),$([H0][#6])](=[OX1])([OX2][#6;!$(C=[O,N,S])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]
711
712 Phosphonic_acid_derivative: [PX4;$([H1]),$([H0][#6])](=[!#6])([!#6])[!#6]
713 # all of the above and much more
714
715
716 Phosphoric_acid: [PX4D4](=[OX1])([$([OX2H]),$([OX1-])])([$([OX2H]),$([OX1-])])[$([OX2H]),$([OX1-])]
717 # includes anions
718
719 Phosphoric_monoester: [PX4D4](=[OX1])([$([OX2H]),$([OX1-])])([$([OX2H]),$([OX1-])])[OX2][#6;!$(C=[O,N,S])]
720
721 Phosphoric_diester: [PX4D4](=[OX1])([$([OX2H]),$([OX1-])])([OX2][#6;!$(C=[O,N,S])])[OX2][#6;!$(C=[O,N,S])]
722
723 Phosphoric_triester: [PX4D4](=[OX1])([OX2][#6;!$(C=[O,N,S])])([OX2][#6;!$(C=[O,N,S])])[OX2][#6;!$(C=[O,N,S])]
724
725 Phosphoric_monoamide: [PX4D4](=[OX1])([$([OX2H]),$([OX1-])])([$([OX2H]),$([OX1-])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]
726
727 Phosphoric_diamide: [PX4D4](=[OX1])([$([OX2H]),$([OX1-])])([#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]
728
729 Phosphoric_triamide: [PX4D4](=[OX1])([#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])])([#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]
730
731 Phosphoric_monoestermonoamide: [PX4D4](=[OX1])([$([OX2H]),$([OX1-])])([OX2][#6;!$(C=[O,N,S])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]
732
733 Phosphoric_diestermonoamide: [PX4D4](=[OX1])([OX2][#6;!$(C=[O,N,S])])([OX2][#6;!$(C=[O,N,S])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]
734
735 Phosphoric_monoesterdiamide: [PX4D4](=[OX1])([OX2][#6;!$(C=[O,N,S])])([#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]
736
737 Phosphoric_acid_derivative: [PX4D4](=[!#6])([!#6])([!#6])[!#6]
738
739
740 Phosphinic_acid: [PX4;$([H2]),$([H1][#6]),$([H0]([#6])[#6])](=[OX1])[$([OX2H]),$([OX1-])]
741
742 Phosphinic_ester: [PX4;$([H2]),$([H1][#6]),$([H0]([#6])[#6])](=[OX1])[OX2][#6;!$(C=[O,N,S])]
743
744 Phosphinic_amide: [PX4;$([H2]),$([H1][#6]),$([H0]([#6])[#6])](=[OX1])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]
745
746 Phosphinic_acid_derivative: [PX4;$([H2]),$([H1][#6]),$([H0]([#6])[#6])](=[!#6])[!#6]
747
748
749 Phosphonous_acid: [PX3;$([H1]),$([H0][#6])]([$([OX2H]),$([OX1-])])[$([OX2H]),$([OX1-])]
750
751 Phosphonous_monoester: [PX3;$([H1]),$([H0][#6])]([$([OX2H]),$([OX1-])])[OX2][#6;!$(C=[O,N,S])]
752
753 Phosphonous_diester: [PX3;$([H1]),$([H0][#6])]([OX2][#6;!$(C=[O,N,S])])[OX2][#6;!$(C=[O,N,S])]
754
755 Phosphonous_monoamide: [PX3;$([H1]),$([H0][#6])]([$([OX2H]),$([OX1-])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]
756
757 Phosphonous_diamide: [PX3;$([H1]),$([H0][#6])]([#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]
758
759 Phosphonous_esteramide: [PX3;$([H1]),$([H0][#6])]([OX2][#6;!$(C=[O,N,S])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]
760
761 Phosphonous_derivatives: [PX3;$([D2]),$([D3][#6])]([!#6])[!#6]
762
763
764 Phosphinous_acid: [PX3;$([H2]),$([H1][#6]),$([H0]([#6])[#6])][$([OX2H]),$([OX1-])]
765
766 Phosphinous_ester: [PX3;$([H2]),$([H1][#6]),$([H0]([#6])[#6])][OX2][#6;!$(C=[O,N,S])]
767
768 Phosphinous_amide: [PX3;$([H2]),$([H1][#6]),$([H0]([#6])[#6])][#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]
769
770 Phosphinous_derivatives: [PX3;$([H2]),$([H1][#6]),$([H0]([#6])[#6])][!#6]
771
772
773 # II.4 Silicon
774 # ------------
775
776 Quart_silane: [SiX4]([#6])([#6])([#6])[#6]
777 # four C-substituents. non-reactive, non-toxic, in experimental phase for drug development
778
779 Non-quart_silane: [SiX4;$([H1]([#6])([#6])[#6]),$([H2]([#6])[#6]),$([H3][#6]),$([H4])]
780 # has 1-4 hydride(s), reactive. Daylight's depictmatch does not add hydrogens automatically to
781 # the free positions at Si, thus Hs had to be added implicitly
782
783 Silylmonohalide: [SiX4]([FX1,ClX1,BrX1,IX1])([#6])([#6])[#6]
784 # reagents for inserting protection groups
785
786 Het_trialkylsilane: [SiX4]([!#6])([#6])([#6])[#6]
787 # mostly acid-labile protection groups such as trimethylsilyl-ethers
788
789 Dihet_dialkylsilane: [SiX4]([!#6])([!#6])([#6])[#6]
790
791 Trihet_alkylsilane: [SiX4]([!#6])([!#6])([!#6])[#6]
792
793 Silicic_acid_derivative: [SiX4]([!#6])([!#6])([!#6])[!#6]
794 # four substituent which are neither C nor H
795
796
797 # II.5 Boron
798 # ----------
799
800 Trialkylborane: [BX3]([#6])([#6])[#6]
801 # also carbonyls allowed
802
803 Boric_acid_derivatives: [BX3]([!#6])([!#6])[!#6]
804 # includes acids, esters, amides, ... H-substituent at B is very rare.
805
806 Boronic_acid_derivative: [BX3]([!#6])([!#6])[!#6]
807 # # includes acids, esters, amides, ...
808
809 Borohydride: [BH1,BH2,BH3,BH4]
810 # at least one H attached to B
811
812 Quaternary_boron: [BX4]
813 # mostly borates (negative charge), in complex with Lewis-base
814
815
816
817 # Part III: Some Special Patterns
818 # ===============================
819
820
821 # III.1 Chains
822 # ------------
823
824 # some simple chains
825
826
827
828 # III.2 Rings
829 # -----------
830
831 Aromatic: a
832
833 Heterocyclic: [!#6;!R0]
834 # may be aromatic or not
835
836 Epoxide: [OX2r3]1[#6r3][#6r3]1
837 # toxic/reactive. may be annelated to aromat, but must not be aromatic itself (oxirane-2,3-dione)
838
839 NH_aziridine: [NX3H1r3]1[#6r3][#6r3]1
840 # toxic/reactive according to Maybridge's garbage filter
841
842 Spiro: [D4R;$(*(@*)(@*)(@*)@*)]
843 # at least two different rings can be found which are sharing just one atom.
844 # these two rings can be connected by a third ring, so it matches also some
845 # bridged systems, like morphine
846
847 Annelated_rings: [R;$(*(@*)(@*)@*);!$([R2;$(*(@*)(@*)(@*)@*)])]@[R;$(*(@*)(@*)@*);!$([R2;$(*(@*)(@*)(@*)@*)])]
848 # two different rings sharing exactly two atoms
849
850 Bridged_rings: [R;$(*(@*)(@*)@*);!$([D4R;$(*(@*)(@*)(@*)@*)]);!$([R;$(*(@*)(@*)@*);!$([R2;$(*(@*)(@*)(@*)@*)])]@[R;$(*(@*)(@*)@*);!$([R2;$(*(@*)(@*)(@*)@*)])])]
851 # part of two or more rings, not spiro, not annelated -> finds bridgehead atoms,
852 # but only if they are not annelated at the same time - otherwise impossible (?)
853 # to distinguish from non-bridgehead annelated atoms
854
855 # some basic ring-patterns (just size, no other information):
856
857
858
859
860
861 # III.3 Sugars and Nucleosides/Nucleotides, Steroids
862 # --------------------------------------------------
863
864 # because of the large variety of sugar derivatives, different patterns can be applied.
865 # The choice of patterns and their combinations will depend on the contents of the database
866 # e.g. natural products, nucleoside analoges with modified sugars, ... as well as on the
867 # desired restriction
868
869
870 Sugar_pattern_1: [OX2;$([r5]1@C@C@C(O)@C1),$([r6]1@C@C@C(O)@C(O)@C1)]
871 # 5 or 6-membered ring containing one O and at least one (r5) or two (r6) oxygen-substituents.
872
873 Sugar_pattern_2: [OX2;$([r5]1@C(!@[OX2,NX3,SX2,FX1,ClX1,BrX1,IX1])@C@C@C1),$([r6]1@C(!@[OX2,NX3,SX2,FX1,ClX1,BrX1,IX1])@C@C@C@C1)]
874 # 5 or 6-membered ring containing one O and an acetal-like bond at postion 2.
875
876 Sugar_pattern_combi: [OX2;$([r5]1@C(!@[OX2,NX3,SX2,FX1,ClX1,BrX1,IX1])@C@C(O)@C1),$([r6]1@C(!@[OX2,NX3,SX2,FX1,ClX1,BrX1,IX1])@C@C(O)@C(O)@C1)]
877 # combination of the two above
878
879 Sugar_pattern_2_reducing: [OX2;$([r5]1@C(!@[OX2H1])@C@C@C1),$([r6]1@C(!@[OX2H1])@C@C@C@C1)]
880 # 5 or 6-membered cyclic hemi-acetal
881
882 Sugar_pattern_2_alpha: [OX2;$([r5]1@[C@@](!@[OX2,NX3,SX2,FX1,ClX1,BrX1,IX1])@C@C@C1),$([r6]1@[C@@](!@[OX2,NX3,SX2,FX1,ClX1,BrX1,IX1])@C@C@C@C1)]
883 # 5 or 6-membered cyclic hemi-acetal
884
885 Sugar_pattern_2_beta: [OX2;$([r5]1@[C@](!@[OX2,NX3,SX2,FX1,ClX1,BrX1,IX1])@C@C@C1),$([r6]1@[C@](!@[OX2,NX3,SX2,FX1,ClX1,BrX1,IX1])@C@C@C@C1)]
886 # 5 or 6-membered cyclic hemi-acetal
887
888 ##Poly_sugar_1: ([OX2;$([r5]1@C@C@C(O)@C1),$([r6]1@C@C@C(O)@C(O)@C1)].[OX2;$([r5]1@C@C@C(O)@C1),$([r6]1@C@C@C(O)@C(O)@C1)])
889 # pattern1 occours more than once (in same molecule, but moieties don't have to be adjacent!)
890
891 ##Poly_sugar_2: ([OX2;$([r5]1@C(!@[OX2,NX3,SX2,FX1,ClX1,BrX1,IX1])@C@C@C1),$([r6]1@C(!@[OX2,NX3,SX2,FX1,ClX1,BrX1,IX1])@C@C@C@C1)].[OX2;$([r5]1@C(!@[OX2,NX3,SX2,FX1,ClX1,BrX1,IX1])@C@C@C1),$([r6]1@C(!@[OX2,NX3,SX2,FX1,ClX1,BrX1,IX1])@C@C@C@C1)])
892 # pattern2 occours more than once (in same molecule, but moieties don't have to be adjacent!)
893
894
895 # III.4 Everything else...
896 # ------------------------
897
898 Conjugated_double_bond: *=*[*]=,#,:[*]
899
900 Conjugated_tripple_bond: *#*[*]=,#,:[*]
901
902 Cis_double_bond: */[D2]=[D2]\*
903 # only one single-bonded substituent on each DB-atom. no aromats.
904 # only found when character of DB is explicitely stated.
905
906 Trans_double_bond: */[D2]=[D2]/*
907 # analog
908
909 Mixed_anhydrides: [$(*=O),$([#16,#14,#5]),$([#7]([#6]=[OX1]))][#8X2][$(*=O),$([#16,#14,#5]),$([#7]([#6]=[OX1]))]
910 # should hits all combinations of two acids
911
912 Halogen_on_hetero: [FX1,ClX1,BrX1,IX1][!#6]
913
914 Halogen_multi_subst: [F,Cl,Br,I;!$([X1]);!$([X0-])]
915 # Halogen which is not mono-substituted nor an anion, e.g. chlorate.
916 # Most of these cases should be also filtered by Halogen_on_hetero.
917
918 Trifluoromethyl: [FX1][CX4;!$([H0][Cl,Br,I]);!$([F][C]([F])([F])[F])]([FX1])([FX1])
919 # C with three F attached, connected to anything which is not another halogen
920
921 C_ONS_bond: [#6]~[#7,#8,#16]
922 # probably all drug-like molecules have at least one O, N, or S connected to a C -> nice filter
923
924 ## Mixture: (*).(*)
925 # two or more seperate parts, may also be salt
926 # component-level grouping is not yet supported in Open Babel Version 2.0
927
928
929 Charged: [!+0]
930
931 Anion: [-1,-2,-3,-4,-5,-6,-7]
932
933 Kation: [+1,+2,+3,+4,+5,+6,+7]
934
935 Salt: ([-1,-2,-3,-4,-5,-6,-7]).([+1,+2,+3,+4,+5,+6,+7])
936 # two or more seperate components with opposite charges
937
938 ##Zwitterion: ([-1,-2,-3,-4,-5,-6,-7].[+1,+2,+3,+4,+5,+6,+7])
939 # both negative and positive charges somewhere within the same molecule.
940
941 1,3-Tautomerizable: [$([#7X2,OX1,SX1]=*[!H0;!$([a;!n])]),$([#7X3,OX2,SX2;!H0]*=*),$([#7X3,OX2,SX2;!H0]*:n)]
942 # 1,3 migration of H allowed. Includes keto/enol and amide/enamide.
943 # Aromatic rings must stay aromatic - no keto form of phenol
944
945 1,5-Tautomerizable: [$([#7X2,OX1,SX1]=,:**=,:*[!H0;!$([a;!n])]),$([#7X3,OX2,SX2;!H0]*=**=*),$([#7X3,OX2,SX2;!H0]*=,:**:n)]
946
947 Rotatable_bond: [!$(*#*)&!D1]-!@[!$(*#*)&!D1]
948 # taken from http://www.daylight.com/support/contrib/smarts/content.html
949
950 Michael_acceptor: [CX3]=[CX3][$([CX3]=[O,N,S]),$(C#[N]),$([S,P]=[OX1]),$([NX3]=O),$([NX3+](=O)[O-])]
951 # the classical case: C=C near carbonyl, nitrile, nitro, or similar
952 # Oxo-heteroaromats and similar are not included.
953
954 Dicarbodiazene: [CX3](=[OX1])[NX2]=[NX2][CX3](=[OX1])
955 # Michael-like acceptor, see Mitsunobu reaction
956
957 # H-Bond_donor:
958
959 # H-Bond_acceptor:
960
961 # Pos_ionizable:
962
963 # Neg_ionizable:
964
965 # Unlikely_ions:
966 # O+,N-,C+,C-, ...
967
968 CH-acidic: [$([CX4;!$([H0]);!$(C[!#6;!$([P,S]=O);!$(N(~O)~O)])][$([CX3]=[O,N,S]),$(C#[N]),$([S,P]=[OX1]),$([NX3]=O),$([NX3+](=O)[O-]);!$(*[S,O,N;H1,H2]);!$([*+0][S,O;X1-])]),$([CX4;!$([H0])]1[CX3]=[CX3][CX3]=[CX3]1)]
969 # C-H alpha to carbony, nitro or similar, C is not double-bonded, only C, H, S,P=O and nitro substituents allowed.
970 # pentadiene is included. acids, their salts, prim./sec. amides, and imides are excluded.
971 # hits also CH-acidic_strong
972
973 CH-acidic_strong: [CX4;!$([H0]);!$(C[!#6;!$([P,S]=O);!$(N(~O)~O)])]([$([CX3]=[O,N,S]),$(C#[N]),$([S,P]=[OX1]),$([NX3]=O),$([NX3+](=O)[O-]);!$(*[S,O,N;H1,H2]);!$([*+0][S,O;X1-])])[$([CX3]=[O,N,S]),$(C#[N]),$([S,P]=[OX1]),$([NX3]=O),$([NX3+](=O)[O-]);!$(*[S,O,N;H1,H2]);!$([*+0][S,O;X1-])]
974 # same as above (without pentadiene), but carbonyl or similar on two or three sides
975
976 Chiral_center_specified: [$([*@](~*)(~*)(*)*),$([*@H](*)(*)*),$([*@](~*)(*)*),$([*@H](~*)~*)]
977 # Hits atoms with tetrahedral chirality, if chiral center is specified in the SMILES string
978 # depictmach does not find oxonium, sulfonium, or sulfoxides!
979
980 # Chiral_center_unspecified: [$([*@?](~*)(~*)(*)*),$([*@?H](*)(*)*),$([*@?](~*)(*)*),$([*@?H](~*)~*)]
981 # Hits atoms with tetrahedral chirality, if chiral center is not specified in the SMILES string
982 # "@?" (unspecified chirality) is not yet supported in Open Babel Version 2.0
983