| 1 |
# |
| 2 |
# SMARTS Patterns for Functional Group Classification |
| 3 |
# |
| 4 |
# written by Christian Laggner |
| 5 |
# Copyright Inte:Ligand Software-Entwicklungs und Consulting GmbH |
| 6 |
# Released under the Lesser General Public License (LGPL license) |
| 7 |
# http://www.gnu.org/copyleft/lesser.html |
| 8 |
##################################################################################################### |
| 9 |
|
| 10 |
# General Stuff: |
| 11 |
# These patters were written in an attempt to represent the classification of organic compounds |
| 12 |
# from the viewpoint of an organic chemist. |
| 13 |
# They are often very restrictive. This may be generally a good thing, but it also takes some time |
| 14 |
# for filtering/indexing large compound sets. |
| 15 |
# For filtering undesired groups (in druglike compounds) one will want to have more general patterns |
| 16 |
# (e.g. you don't want *any* halide of *any* acid, *neither* aldehyde *nor* formyl esters and amides, ...). |
| 17 |
# |
| 18 |
|
| 19 |
# Part I: Carbon |
| 20 |
# ============== |
| 21 |
|
| 22 |
|
| 23 |
# I.1: Carbon-Carbon Bonds |
| 24 |
# ------------------------ |
| 25 |
|
| 26 |
# I.1.1 Alkanes: |
| 27 |
|
| 28 |
Primary_carbon: [CX4H3][#6] |
| 29 |
|
| 30 |
Secondary_carbon: [CX4H2]([#6])[#6] |
| 31 |
|
| 32 |
Tertiary_carbon: [CX4H1]([#6])([#6])[#6] |
| 33 |
|
| 34 |
Quartary_carbon: [CX4]([#6])([#6])([#6])[#6] |
| 35 |
|
| 36 |
|
| 37 |
# I.1.2 C-C double and Triple Bonds |
| 38 |
|
| 39 |
Alkene: [CX3;$([H2]),$([H1][#6]),$(C([#6])[#6])]=[CX3;$([H2]),$([H1][#6]),$(C([#6])[#6])] |
| 40 |
# sp2 C may be substituted only by C or H - |
| 41 |
# does not hit ketenes and allenes, nor enamines, enols and the like |
| 42 |
|
| 43 |
Alkyne: [CX2]#[CX2] |
| 44 |
# non-carbon substituents (e.g. alkynol ethers) are rather rare, thus no further discrimination |
| 45 |
|
| 46 |
Allene: [CX3]=[CX2]=[CX3] |
| 47 |
|
| 48 |
|
| 49 |
# I.2: One Carbon-Hetero Bond |
| 50 |
# --------------------------- |
| 51 |
|
| 52 |
|
| 53 |
# I.2.1 Alkyl Halogenides |
| 54 |
|
| 55 |
Alkylchloride: [ClX1][CX4] |
| 56 |
# will also hit chloromethylethers and the like, but no chloroalkenes, -alkynes or -aromats |
| 57 |
# a more restrictive version can be obtained by modifying the Alcohol string. |
| 58 |
|
| 59 |
Alkylfluoride: [FX1][CX4] |
| 60 |
|
| 61 |
Alkylbromide: [BrX1][CX4] |
| 62 |
|
| 63 |
Alkyliodide: [IX1][CX4] |
| 64 |
|
| 65 |
|
| 66 |
# I.2.2 Alcohols and Ethers |
| 67 |
|
| 68 |
Alcohol: [OX2H][CX4;!$(C([OX2H])[O,S,#7,#15])] |
| 69 |
# nonspecific definition, no acetals, aminals, and the like |
| 70 |
|
| 71 |
Primary_alcohol: [OX2H][CX4H2;!$(C([OX2H])[O,S,#7,#15])] |
| 72 |
|
| 73 |
Secondary_alcohol: [OX2H][CX4H;!$(C([OX2H])[O,S,#7,#15])] |
| 74 |
|
| 75 |
Tertiary_alcohol: [OX2H][CX4D4;!$(C([OX2H])[O,S,#7,#15])] |
| 76 |
|
| 77 |
Dialkylether: [OX2]([CX4;!$(C([OX2])[O,S,#7,#15,F,Cl,Br,I])])[CX4;!$(C([OX2])[O,S,#7,#15])] |
| 78 |
# no acetals and the like; no enolethers |
| 79 |
|
| 80 |
Dialkylthioether: [SX2]([CX4;!$(C([OX2])[O,S,#7,#15,F,Cl,Br,I])])[CX4;!$(C([OX2])[O,S,#7,#15])] |
| 81 |
# no acetals and the like; no enolethers |
| 82 |
|
| 83 |
Alkylarylether: [OX2](c)[CX4;!$(C([OX2])[O,S,#7,#15,F,Cl,Br,I])] |
| 84 |
# no acetals and the like; no enolethers |
| 85 |
|
| 86 |
Diarylether: [c][OX2][c] |
| 87 |
|
| 88 |
Alkylarylthioether: [SX2](c)[CX4;!$(C([OX2])[O,S,#7,#15,F,Cl,Br,I]) |
| 89 |
|
| 90 |
Diarylthioether: [c][SX2][c] |
| 91 |
|
| 92 |
Oxonium: [O+;!$([O]~[!#6]);!$([S]*~[#7,#8,#15,#16])] |
| 93 |
# can't be aromatic, thus O and not #8 |
| 94 |
|
| 95 |
# I.2.3 Amines |
| 96 |
|
| 97 |
Amine: [NX3,NX4+;!$([N]~[!#6]);!$([N]*~[#7,#8,#15,#16])] |
| 98 |
# hits all amines (prim/sec/tert/quart), including ammonium salts, also enamines, but not amides, imides, aminals, ... |
| 99 |
|
| 100 |
# the following amines include also the protonated forms |
| 101 |
|
| 102 |
Primary_aliph_amine: [NX3H2,NX4H3+;!$([N][!C]);!$([N]*~[#7,#8,#15,#16])] |
| 103 |
|
| 104 |
Secondary_aliph_amine: [NX3H1,NX4H2+;!$([N][!C]);!$([N]*~[#7,#8,#15,#16])] |
| 105 |
|
| 106 |
Tertiary_aliph_amine: [NX3H0,NX4H1+;!$([N][!C]);!$([N]*~[#7,#8,#15,#16])] |
| 107 |
|
| 108 |
Quartary_aliph_ammonium: [NX4H0+;!$([N][!C]);!$([N]*~[#7,#8,#15,#16])] |
| 109 |
|
| 110 |
Primary_arom_amine: [NX3H2,NX4H3+]c |
| 111 |
|
| 112 |
Secondary_arom_amine: [NX3H1,NX4H2+;!$([N][!c]);!$([N]*~[#7,#8,#15,#16])] |
| 113 |
|
| 114 |
Tertiary_arom_amine: [NX3H0,NX4H1+;!$([N][!c]);!$([N]*~[#7,#8,#15,#16])] |
| 115 |
|
| 116 |
Quartary_arom_ammonium: [NX4H0+;!$([N][!c]);!$([N]*~[#7,#8,#15,#16])] |
| 117 |
|
| 118 |
Secondary_mixed_amine: [NX3H1,NX4H2+;$([N]([c])[C]);!$([N]*~[#7,#8,#15,#16])] |
| 119 |
|
| 120 |
Tertiary_mixed_amine: [NX3H0,NX4H1+;$([N]([c])([C])[#6]);!$([N]*~[#7,#8,#15,#16])] |
| 121 |
|
| 122 |
Quartary_mixed_ammonium: [NX4H0+;$([N]([c])([C])[#6][#6]);!$([N]*~[#7,#8,#15,#16])] |
| 123 |
|
| 124 |
Ammonium: [N+;!$([N]~[!#6]);!$([N]*~[#7,#8,#15,#16])] |
| 125 |
# only C and H substituents allowed. NX4+ or Nv4+ is not recognized by Daylight's |
| 126 |
# depictmatch if less than four C are present... |
| 127 |
|
| 128 |
|
| 129 |
# I.2.4 Others |
| 130 |
|
| 131 |
Alkylthiol: [SX2H][CX4;!$(C([SX2H])~[O,S,#7,#15])] |
| 132 |
|
| 133 |
Dialkylthioether: [SX2]([CX4;!$(C([SX2])[O,S,#7,#15,F,Cl,Br,I])])[CX4;!$(C([SX2])[O,S,#7,#15])] |
| 134 |
|
| 135 |
Alkylarylthioether: [SX2](c)[CX4;!$(C([SX2])[O,S,#7,#15])] |
| 136 |
|
| 137 |
Disulfide: [SX2D2][SX2D2] |
| 138 |
|
| 139 |
1,2-Aminoalcohol: [OX2H][CX4;!$(C([OX2H])[O,S,#7,#15,F,Cl,Br,I])][CX4;!$(C([N])[O,S,#7,#15])][NX3;!$(NC=[O,S,N])] |
| 140 |
# does not hit alpha-amino acids, enaminoalcohols, 1,2-aminoacetals, o-aminophenols, etc. |
| 141 |
|
| 142 |
1,2-Diol: [OX2H][CX4;!$(C([OX2H])[O,S,#7,#15])][CX4;!$(C([OX2H])[O,S,#7,#15])][OX2H] |
| 143 |
# does not hit alpha-hydroxy acids, enolalcohols, 1,2-hydroxyacetals, 1,2-diphenols, etc. |
| 144 |
|
| 145 |
1,1-Diol: [OX2H][CX4;!$(C([OX2H])([OX2H])[O,S,#7,#15])][OX2H] |
| 146 |
|
| 147 |
Hydroperoxide: [OX2H][OX2] |
| 148 |
#does not neccessarily have to be connected to a carbon atom, includes also hydrotrioxides |
| 149 |
|
| 150 |
Peroxo: [OX2D2][OX2D2] |
| 151 |
|
| 152 |
Organolithium_compounds: [LiX1][#6,#14] |
| 153 |
|
| 154 |
Organomagnesium_compounds: [MgX2][#6,#14] |
| 155 |
# not restricted to Grignard compounds, also dialkyl Mg |
| 156 |
|
| 157 |
Organometallic_compounds: [!#1;!#5;!#6;!#7;!#8;!#9;!#14;!#15;!#16;!#17;!#33;!#34;!#35;!#52;!#53;!#85]~[#6;!-] |
| 158 |
# very general, includes all metals covalently bound to carbon |
| 159 |
|
| 160 |
|
| 161 |
# I.3: Two Carbon-Hetero Bonds (Carbonyl and Derivatives) |
| 162 |
# ---------------------------- |
| 163 |
|
| 164 |
# I.3.1 Double Bond to Hetero |
| 165 |
|
| 166 |
Aldehyde: [$([CX3H][#6]),$([CX3H2])]=[OX1] |
| 167 |
# hits aldehydes including formaldehyde |
| 168 |
|
| 169 |
Ketone: [#6][CX3](=[OX1])[#6] |
| 170 |
# does not include oxo-groups connected to a (hetero-) aromatic ring |
| 171 |
|
| 172 |
Thioaldehyde: [$([CX3H][#6]),$([CX3H2])]=[SX1] |
| 173 |
|
| 174 |
Thioketone: [#6][CX3](=[SX1])[#6] |
| 175 |
# does not include thioxo-groups connected to a (hetero-) aromatic ring |
| 176 |
|
| 177 |
Imine: [NX2;$([N][#6]),$([NH]);!$([N][CX3]=[#7,#8,#15,#16])]=[CX3;$([CH2]),$([CH][#6]),$([C]([#6])[#6])] |
| 178 |
# nitrogen is not part of an amidelike strukture, nor of an aromatic ring, but can be part of an aminal or similar |
| 179 |
|
| 180 |
Immonium: [N+;!$([N][!#6]);!$([N][CX3]=[#7,#8,#15,#16])]] |
| 181 |
|
| 182 |
Oxime: [NX2](=[CX3;$([CH2]),$([CH][#6]),$([C]([#6])[#6])])[OX2H] |
| 183 |
|
| 184 |
Oximether: [NX2](=[CX3;$([CH2]),$([CH][#6]),$([C]([#6])[#6])])[OX2][#6;!$(C=[#7,#8])] |
| 185 |
# ether, not ester or amide; does not hit isoxazole |
| 186 |
|
| 187 |
|
| 188 |
# I.3.2. Two Single Bonds to Hetero |
| 189 |
|
| 190 |
Acetal: [OX2]([#6;!$(C=[O,S,N])])[CX4;!$(C(O)(O)[!#6])][OX2][#6;!$(C=[O,S,N])] |
| 191 |
# does not hit hydroxy-methylesters, ketenacetals, hemiacetals, orthoesters, etc. |
| 192 |
|
| 193 |
Hemiacetal: [OX2H][CX4;!$(C(O)(O)[!#6])][OX2][#6;!$(C=[O,S,N])] |
| 194 |
|
| 195 |
Aminal: [NX3v3;!$(NC=[#7,#8,#15,#16])]([#6])[CX4;!$(C(N)(N)[!#6])][NX3v3;!$(NC=[#7,#8,#15,#16])][#6] |
| 196 |
# Ns are not part of an amide or similar. v3 ist to exclude nitro and similar groups |
| 197 |
|
| 198 |
Hemiaminal: [NX3v3;!$(NC=[#7,#8,#15,#16])]([#6])[CX4;!$(C(N)(N)[!#6])][OX2H] |
| 199 |
|
| 200 |
Thioacetal: [SX2]([#6;!$(C=[O,S,N])])[CX4;!$(C(S)(S)[!#6])][SX2][#6;!$(C=[O,S,N])] |
| 201 |
|
| 202 |
Thiohemiacetal: [SX2]([#6;!$(C=[O,S,N])])[CX4;!$(C(S)(S)[!#6])][OX2H] |
| 203 |
|
| 204 |
Halogen_acetal_like: [NX3v3,SX2,OX2;!$(*C=[#7,#8,#15,#16])][CX4;!$(C([N,S,O])([N,S,O])[!#6])][FX1,ClX1,BrX1,IX1] |
| 205 |
# hits chloromethylenethers and other reactive alkylating agents |
| 206 |
|
| 207 |
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;!$(*C=[#7,#8,#15,#16])] |
| 208 |
# includes all of the above and other combinations (S-C-N, hydrates, ...), but still no aminomethylenesters and similar |
| 209 |
|
| 210 |
Halogenmethylen_ester_and_similar: [NX3v3,SX2,OX2;$(**=[#7,#8,#15,#16])][CX4;!$(C([N,S,O])([N,S,O])[!#6])][FX1,ClX1,BrX1,IX1] |
| 211 |
# also reactive alkylating agents. Acid does not have to be carboxylic acid, also S- and P-based acids allowed |
| 212 |
|
| 213 |
NOS_methylen_ester_and_similar: [NX3v3,SX2,OX2;$(**=[#7,#8,#15,#16])][CX4;!$(C([N,S,O])([N,S,O])[!#6])][NX3v3,SX2,OX2;!$(*C=[#7,#8,#15,#16])] |
| 214 |
# Same as above, but N,O or S instead of halogen. Ester/amide allowed only on one side |
| 215 |
|
| 216 |
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;!$(*C=[#7,#8,#15,#16])] |
| 217 |
# Combination of the last two patterns |
| 218 |
|
| 219 |
Cyanhydrine: [NX1]#[CX2][CX4;$([CH2]),$([CH]([CX2])[#6]),$(C([CX2])([#6])[#6])][OX2H] |
| 220 |
|
| 221 |
|
| 222 |
# I.3.3 Single Bond to Hetero, C=C Double Bond (Enols and Similar) |
| 223 |
|
| 224 |
Chloroalkene: [ClX1][CX3]=[CX3] |
| 225 |
|
| 226 |
Fluoroalkene: [FX1][CX3]=[CX3] |
| 227 |
|
| 228 |
Bromoalkene: [BrX1][CX3]=[CX3] |
| 229 |
|
| 230 |
Iodoalkene: [IX1][CX3]=[CX3] |
| 231 |
|
| 232 |
Enol: [OX2H][CX3;$([H1]),$(C[#6])]=[CX3] |
| 233 |
# no phenols |
| 234 |
|
| 235 |
Endiol: [OX2H][CX3;$([H1]),$(C[#6])]=[CX3;$([H1]),$(C[#6])][OX2H] |
| 236 |
# no 1,2-diphenols, ketenacetals, ... |
| 237 |
|
| 238 |
Enolether: [OX2]([#6;!$(C=[N,O,S])])[CX3;$([H0][#6]),$([H1])]=[CX3] |
| 239 |
# finds also endiodiethers, but not enolesters, no aromats |
| 240 |
|
| 241 |
Enolester: [OX2]([CX3]=[OX1])[#6X3;$([#6][#6]),$([H1])]=[#6X3;!$(C[OX2H])] |
| 242 |
|
| 243 |
|
| 244 |
Enamine: [NX3;$([NH2][CX3]),$([NH1]([CX3])[#6]),$([N]([CX3])([#6])[#6]);!$([N]*=[#7,#8,#15,#16])][CX3;$([CH]),$([C][#6])]=[CX3] |
| 245 |
# does not hit amines attached to aromatic rings, nor may the nitrogen be aromatic |
| 246 |
|
| 247 |
Thioenol: [SX2H][CX3;$([H1]),$(C[#6])]=[CX3] |
| 248 |
|
| 249 |
Thioenolether: [SX2]([#6;!$(C=[N,O,S])])[CX3;$(C[#6]),$([CH])]=[CX3] |
| 250 |
|
| 251 |
|
| 252 |
# I.4: Three Carbon-Hetero Bonds (Carboxyl and Derivatives) |
| 253 |
# ------------------------------ |
| 254 |
|
| 255 |
Acylchloride: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[ClX1] |
| 256 |
|
| 257 |
Acylfluoride: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[FX1] |
| 258 |
|
| 259 |
Acylbromide: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[BrX1] |
| 260 |
|
| 261 |
Acyliodide: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[IX1] |
| 262 |
|
| 263 |
Acylhalide: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[FX1,ClX1,BrX1,IX1] |
| 264 |
# all of the above |
| 265 |
|
| 266 |
|
| 267 |
# The following contains all simple carboxylic combinations of O, N, S, & Hal - |
| 268 |
# - acids, esters, amides, ... as well as a few extra cases (anhydride, hydrazide...) |
| 269 |
# Cyclic structures (including aromats) like lactones, lactames, ... got their own |
| 270 |
# definitions. Structures where both heteroatoms are part of an aromatic ring |
| 271 |
# (oxazoles, imidazoles, ...) were excluded. |
| 272 |
|
| 273 |
Carboxylic_acid: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[$([OX2H]),$([OX1-])] |
| 274 |
# includes carboxylate anions |
| 275 |
|
| 276 |
Carboxylic_ester: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[OX2][#6;!$(C=[O,N,S])] |
| 277 |
# does not hit anhydrides or lactones |
| 278 |
|
| 279 |
Lactone: [#6][#6X3R](=[OX1])[#8X2][#6;!$(C=[O,N,S])] |
| 280 |
# may also be aromatic |
| 281 |
|
| 282 |
Carboxylic_anhydride: [CX3;$([H0][#6]),$([H1])](=[OX1])[#8X2][CX3;$([H0][#6]),$([H1])](=[OX1]) |
| 283 |
# anhydride formed by two carboxylic acids, no mixed anhydrides (e.g. between carboxylic acid and sulfuric acid); may be part of a ring, even aromatic |
| 284 |
|
| 285 |
Carboxylic_acid_derivative: [$([#6X3H0][#6]),$([#6X3H])](=[!#6])[!#6] |
| 286 |
# includes most of the structures of I.4 and many more, also 1,3-heteroaromatics such as isoxazole |
| 287 |
|
| 288 |
Carbothioic_acid: [CX3;!R;$([C][#6]),$([CH]);$([C](=[OX1])[$([SX2H]),$([SX1-])]),$([C](=[SX1])[$([OX2H]),$([OX1-])])] |
| 289 |
# hits both tautomeric forms, as well as anions |
| 290 |
|
| 291 |
Carbothioic_S_ester: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[SX2][#6;!$(C=[O,N,S])] |
| 292 |
|
| 293 |
Carbothioic_S_lactone: [#6][#6X3R](=[OX1])[#16X2][#6;!$(C=[O,N,S])] |
| 294 |
# may also be aromatic |
| 295 |
|
| 296 |
Carbothioic_O_ester: [CX3;$([H0][#6]),$([H1])](=[SX1])[OX2][#6;!$(C=[O,N,S])] |
| 297 |
|
| 298 |
Carbothioic_O_lactone: [#6][#6X3R](=[SX1])[#8X2][#6;!$(C=[O,N,S])] |
| 299 |
|
| 300 |
Carbothioic_halide: [CX3;$([H0][#6]),$([H1])](=[SX1])[FX1,ClX1,BrX1,IX1] |
| 301 |
|
| 302 |
Carbodithioic_acid: [CX3;!R;$([C][#6]),$([CH]);$([C](=[SX1])[SX2H])] |
| 303 |
|
| 304 |
Carbodithioic_ester: [CX3;!R;$([C][#6]),$([CH]);$([C](=[SX1])[SX2][#6;!$(C=[O,N,S])])] |
| 305 |
|
| 306 |
Carbodithiolactone: [#6][#6X3R](=[SX1])[#16X2][#6;!$(C=[O,N,S])] |
| 307 |
|
| 308 |
|
| 309 |
Amide: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] |
| 310 |
# does not hit lactames |
| 311 |
|
| 312 |
Primary_amide: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[NX3H2] |
| 313 |
|
| 314 |
Secondary_amide: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[#7X3H1][#6;!$(C=[O,N,S])] |
| 315 |
|
| 316 |
Tertiary_amide: [CX3;$([R0][#6]),$([H1R0])](=[OX1])[#7X3H0]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])] |
| 317 |
|
| 318 |
Lactam: [#6R][#6X3R](=[OX1])[#7X3;$([H1][#6;!$(C=[O,N,S])]),$([H0]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] |
| 319 |
# cyclic amides, may also be aromatic |
| 320 |
|
| 321 |
Alkyl_imide: [#6X3;$([H0][#6]),$([H1])](=[OX1])[#7X3H0]([#6])[#6X3;$([H0][#6]),$([H1])](=[OX1]) |
| 322 |
# may be part of a ring, even aromatic. only C allowed at central N. May also be triacyl amide |
| 323 |
|
| 324 |
N_hetero_imide: [#6X3;$([H0][#6]),$([H1])](=[OX1])[#7X3H0]([!#6])[#6X3;$([H0][#6]),$([H1])](=[OX1]) |
| 325 |
# everything else than H or C at central N |
| 326 |
|
| 327 |
Imide_acidic: [#6X3;$([H0][#6]),$([H1])](=[OX1])[#7X3H1][#6X3;$([H0][#6]),$([H1])](=[OX1]) |
| 328 |
# can be deprotonated |
| 329 |
|
| 330 |
Thioamide: [$([CX3;!R][#6]),$([CX3H;!R])](=[SX1])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] |
| 331 |
# does not hit thiolactames |
| 332 |
|
| 333 |
Thiolactam: [#6R][#6X3R](=[SX1])[#7X3;$([H1][#6;!$(C=[O,N,S])]),$([H0]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] |
| 334 |
# cyclic thioamides, may also be aromatic |
| 335 |
|
| 336 |
|
| 337 |
Oximester: [#6X3;$([H0][#6]),$([H1])](=[OX1])[#8X2][#7X2]=,:[#6X3;$([H0]([#6])[#6]),$([H1][#6]),$([H2])] |
| 338 |
# may also be part of a ring / aromatic |
| 339 |
|
| 340 |
Amidine: [NX3;!$(NC=[O,S])][CX3;$([CH],$([C][#6])]=[NX2;!$(NC=[O,S])] |
| 341 |
# only basic amidines, not as part of aromatic ring (e.g. imidazole) |
| 342 |
|
| 343 |
Hydroxamic_acid: [CX3;$([H0][#6]),$([H1])](=[OX1])[#7X3;$([H1]),$([H0][#6;!$(C=[O,N,S])])][$([OX2H]),$([OX1-])] |
| 344 |
|
| 345 |
Hydroxamic_acid_ester: [CX3;$([H0][#6]),$([H1])](=[OX1])[#7X3;$([H1]),$([H0][#6;!$(C=[O,N,S])])][OX2][#6;!$(C=[O,N,S])])] |
| 346 |
# #does not hit anhydrides of carboxylic acids withs hydroxamic acids |
| 347 |
|
| 348 |
|
| 349 |
Imidoacid: [CX3R0;$([H0][#6]),$([H1])](=[NX2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[$([OX2H]),$([OX1-])] |
| 350 |
# not cyclic |
| 351 |
|
| 352 |
Imidoacid_cyclic: [#6R][#6X3R](=,:[#7X2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[$([OX2H]),$([OX1-])] |
| 353 |
# the enamide-form of lactames. may be aromatic like 2-hydroxypyridine |
| 354 |
|
| 355 |
Imidoester: [CX3R0;$([H0][#6]),$([H1])](=[NX2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[OX2][#6;!$(C=[O,N,S])] |
| 356 |
# esters of the above structures. no anhydrides. |
| 357 |
|
| 358 |
Imidolactone: [#6R][#6X3R](=,:[#7X2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[OX2][#6;!$(C=[O,N,S])] |
| 359 |
# no oxazoles and similar |
| 360 |
|
| 361 |
Imidothioacid: [CX3R0;$([H0][#6]),$([H1])](=[NX2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[$([SX2H]),$([SX1-])] |
| 362 |
# not cyclic |
| 363 |
|
| 364 |
Imidothioacid_cyclic: [#6R][#6X3R](=,:[#7X2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[$([SX2H]),$([SX1-])] |
| 365 |
# the enamide-form of thiolactames. may be aromatic like 2-thiopyridine |
| 366 |
|
| 367 |
Imidothioester: [CX3R0;$([H0][#6]),$([H1])](=[NX2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[SX2][#6;!$(C=[O,N,S])] |
| 368 |
# thioesters of the above structures. no anhydrides. |
| 369 |
|
| 370 |
Imidothiolactone: [#6R][#6X3R](=,:[#7X2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[SX2][#6;!$(C=[O,N,S])] |
| 371 |
# no thioxazoles and similar |
| 372 |
|
| 373 |
Amidine: [#7X3v3;!$(N([#6X3]=[#7X2])C=[O,S])][CX3R0;$([H1]),$([H0][#6])]=[NX2v3;!$(N(=[#6X3][#7X3])C=[O,S])] |
| 374 |
# only basic amidines, not substituted by carbonyl or thiocarbonyl, not as part of a ring |
| 375 |
|
| 376 |
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])])] |
| 377 |
# one of the two C~N bonds is part of a ring (may be aromatic), but not both - thus no imidazole |
| 378 |
|
| 379 |
Imidoylhalide: [CX3R0;$([H0][#6]),$([H1])](=[NX2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[FX1,ClX1,BrX1,IX1] |
| 380 |
# not cyclic |
| 381 |
|
| 382 |
Imidoylhalide_cyclic: [#6R][#6X3R](=,:[#7X2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[FX1,ClX1,BrX1,IX1] |
| 383 |
# may also be aromatic |
| 384 |
|
| 385 |
# may be ring, aromatic, substituted with carbonyls, hetero, ... |
| 386 |
# (everything else would get too complicated) |
| 387 |
|
| 388 |
Amidrazone: [$([$([#6X3][#6]),$([#6X3H])](=[#7X2v3])[#7X3v3][#7X3v3]),$([$([#6X3][#6]),$([#6X3H])]([#7X3v3])=[#7X2v3][#7X3v3])] |
| 389 |
# hits both tautomers. as above, it may be ring, aromatic, substituted with carbonyls, hetero, ... |
| 390 |
|
| 391 |
|
| 392 |
Alpha_aminoacid: [NX3,NX4+;!$([N]~[!#6]);!$([N]*~[#7,#8,#15,#16])][C][CX3](=[OX1])[OX2H,OX1-] |
| 393 |
# N may be alkylated, but not part of an amide (as in peptides), ionic forms are included |
| 394 |
# includes also non-natural aminoacids with double-bonded or two aliph./arom. substituents at alpha-C |
| 395 |
# N may not be aromatic as in 1H-pyrrole-2-carboxylic acid |
| 396 |
|
| 397 |
Alpha_hydroxyacid: [OX2H][C][CX3](=[OX1])[OX2H,OX1-] |
| 398 |
|
| 399 |
Peptide_middle: [NX3;$([N][CX3](=[OX1])[C][NX3,NX4+])][C][CX3](=[OX1])[NX3;$([N][C][CX3](=[OX1])[NX3,OX2,OX1-])] |
| 400 |
# finds peptidic structures which are neither C- nor N-terminal. Both neighbours must be amino-acids/peptides |
| 401 |
|
| 402 |
Peptide_C_term: [NX3;$([N][CX3](=[OX1])[C][NX3,NX4+])][C][CX3](=[OX1])[OX2H,OX1-] |
| 403 |
# finds C-terminal amino acids |
| 404 |
|
| 405 |
Peptide_N_term: [NX3,NX4+;!$([N]~[!#6]);!$([N]*~[#7,#8,#15,#16])][C][CX3](=[OX1])[NX3;$([N][C][CX3](=[OX1])[NX3,OX2,OX1-])] |
| 406 |
# finds N-terminal amino acids. As above, N may be substituted, but not part of an amide-bond. |
| 407 |
|
| 408 |
|
| 409 |
Carboxylic_orthoester: [#6][OX2][CX4;$(C[#6]),$([CH])]([OX2][#6])[OX2][#6] |
| 410 |
# hits also anhydride like struktures (e. g. HC(OMe)2-OC=O residues) |
| 411 |
|
| 412 |
Ketene: [CX3]=[CX2]=[OX1] |
| 413 |
|
| 414 |
Ketenacetal: [#7X2,#8X3,#16X2;$(*[#6,#14])][#6X3]([#7X2,#8X3,#16X2;$(*[#6,#14])])=[#6X3] |
| 415 |
# includes aminals, silylacetals, ketenesters, etc. C=C DB is not aromatic, everything else may be |
| 416 |
|
| 417 |
Nitrile: [NX1]#[CX2] |
| 418 |
# includes cyanhydrines |
| 419 |
|
| 420 |
Isonitrile: [CX1-]#[NX2+] |
| 421 |
|
| 422 |
|
| 423 |
Vinylogous_carbonyl_or_carboxyl_derivative: [#6X3](=[OX1])[#6X3]=,:[#6X3][#7,#8,#16,F,Cl,Br,I] |
| 424 |
# may be part of a ring, even aromatic |
| 425 |
|
| 426 |
Vinylogous_acid: [#6X3](=[OX1])[#6X3]=,:[#6X3][$([OX2H]),$([OX1-])] |
| 427 |
|
| 428 |
Vinylogous_ester: [#6X3](=[OX1])[#6X3]=,:[#6X3][#6;!$(C=[O,N,S])] |
| 429 |
|
| 430 |
Vinylogous_amide: [#6X3](=[OX1])[#6X3]=,:[#6X3][#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] |
| 431 |
|
| 432 |
Vinylogous_halide: [#6X3](=[OX1])[#6X3]=,:[#6X3][FX1,ClX1,BrX1,IX1] |
| 433 |
|
| 434 |
|
| 435 |
|
| 436 |
# I.5: Four Carbon-Hetero Bonds (Carbonic Acid and Derivatives) |
| 437 |
# ----------------------------- |
| 438 |
|
| 439 |
Carbonic_acid_dieester: [#6;!$(C=[O,N,S])][#8X2][#6X3](=[OX1])[#8X2][#6;!$(C=[O,N,S])] |
| 440 |
# may be part of a ring, even aromatic |
| 441 |
|
| 442 |
Carbonic_acid_esterhalide: [#6;!$(C=[O,N,S])][OX2;!R][CX3](=[OX1])[OX2][FX1,ClX1,BrX1,IX1] |
| 443 |
|
| 444 |
Carbonic_acid_monoester: [#6;!$(C=[O,N,S])][OX2;!R][CX3](=[OX1])[$([OX2H]),$([OX1-])] |
| 445 |
# unstable |
| 446 |
|
| 447 |
Carbonic_acid_derivatives: [!#6][#6X3](=[!#6])[!#6] |
| 448 |
|
| 449 |
|
| 450 |
Thiocarbonic_acid_dieester: [#6;!$(C=[O,N,S])][#8X2][#6X3](=[SX1])[#8X2][#6;!$(C=[O,N,S])] |
| 451 |
# may be part of a ring, even aromatic |
| 452 |
|
| 453 |
Thiocarbonic_acid_esterhalide: [#6;!$(C=[O,N,S])][OX2;!R][CX3](=[SX1])[OX2][FX1,ClX1,BrX1,IX1] |
| 454 |
|
| 455 |
Thiocarbonic_acid_monoester: [#6;!$(C=[O,N,S])][OX2;!R][CX3](=[SX1])[$([OX2H]),$([OX1-])] |
| 456 |
|
| 457 |
|
| 458 |
Urea:[#7X3;!$([#7][!#6])][#6X3](=[OX1])[#7X3;!$([#7][!#6])] |
| 459 |
# no check whether part of imide, biuret, etc. Aromatic structures are only hit if |
| 460 |
# both N share no double bonds, like in the dioxo-form of uracil |
| 461 |
|
| 462 |
Thiourea: [#7X3;!$([#7][!#6])][#6X3](=[SX1])[#7X3;!$([#7][!#6])] |
| 463 |
|
| 464 |
Isourea: [#7X2;!$([#7][!#6])]=,:[#6X3]([#8X2&!$([#8][!#6]),OX1-])[#7X3;!$([#7][!#6])] |
| 465 |
# O may be substituted. no check whether further amide-like bonds are present. Aromatic |
| 466 |
# structures are only hit if single bonded N shares no additional double bond, like in |
| 467 |
# the 1-hydroxy-3-oxo form of uracil |
| 468 |
|
| 469 |
Isothiourea: [#7X2;!$([#7][!#6])]=,:[#6X3]([#16X2&!$([#16][!#6]),SX1-])[#7X3;!$([#7][!#6])] |
| 470 |
|
| 471 |
Guanidine: [N;v3X3,v4X4+][CX3](=[N;v3X2,v4X3+])[N;v3X3,v4X4+] |
| 472 |
# also hits guanidinium salts. v3 and v4 to avoid nitroamidines |
| 473 |
|
| 474 |
Carbaminic_acid: [NX3]C(=[OX1])[O;X2H,X1-] |
| 475 |
# quite unstable, unlikely to be found. Also hits salts |
| 476 |
|
| 477 |
Urethan: [#7X3][#6](=[OX1])[#8X2][#6] |
| 478 |
# also hits when part of a ring, no check whether the last C is part of carbonyl |
| 479 |
|
| 480 |
Biuret: [#7X3][#6](=[OX1])[#7X3][#6](=[OX1])[#7X3] |
| 481 |
|
| 482 |
Semicarbazide: [#7X3][#7X3][#6X3]([#7X3;!$([#7][#7])])=[OX1] |
| 483 |
|
| 484 |
Carbazide: [#7X3][#7X3][#6X3]([#7X3][#7X3])=[OX1] |
| 485 |
|
| 486 |
Semicarbazone: [#7X2](=[#6])[#7X3][#6X3]([#7X3;!$([#7][#7]))=[OX1] |
| 487 |
|
| 488 |
Carbazone: [#7X2](=[#6])[#7X3][#6X3]([#7X3][#7X3])=[OX1] |
| 489 |
|
| 490 |
Thiosemicarbazide: [#7X3][#7X3][#6X3]([#7X3;!$([#7][#7])=[SX1] |
| 491 |
|
| 492 |
Thiocarbazide: [#7X3][#7X3][#6X3]([#7X3][#7X3])=[SX1] |
| 493 |
|
| 494 |
Thiosemicarbazone: [#7X2](=[#6])[#7X3][#6X3]([#7X3;!$([#7][#7])=[SX1] |
| 495 |
|
| 496 |
Thiocarbazone: [#7X2](=[#6])[#7X3][#6X3]([#7X3][#7X3])=[SX1] |
| 497 |
|
| 498 |
|
| 499 |
Isocyanate: [NX2]=[CX2]=[OX1] |
| 500 |
|
| 501 |
Cyanate: [OX2][CX2]#[NX1] |
| 502 |
|
| 503 |
Isothiocyanate: [NX2]=[CX2]=[SX1] |
| 504 |
|
| 505 |
Thiocyanate: [SX2][CX2]#[NX1] |
| 506 |
|
| 507 |
Carbodiimide: [NX2]=[CX2]=[NX2] |
| 508 |
|
| 509 |
Orthocarbonic_derivatives: [CX4H0]([O,S,#7])([O,S,#7])([O,S,#7])[O,S,#7,F,Cl,Br,I] |
| 510 |
# halogen allowed just once, to avoid mapping to -OCF3 and similar groups (much more |
| 511 |
# stable as for example C(OCH3)4) |
| 512 |
|
| 513 |
|
| 514 |
# I.6 Aromatics |
| 515 |
# ------------- |
| 516 |
|
| 517 |
# I know that this classification is not very logical, arylamines are found under I.2 ... |
| 518 |
|
| 519 |
Phenol: [OX2H][c] |
| 520 |
|
| 521 |
1,2-Diphenol: [OX2H][c][c][OX2H] |
| 522 |
|
| 523 |
Arylchloride: [Cl][c] |
| 524 |
|
| 525 |
Arylfluoride: [F][c] |
| 526 |
|
| 527 |
Arylbromide: [Br][c] |
| 528 |
|
| 529 |
Aryliodide: [I][c] |
| 530 |
|
| 531 |
Arylthiol: [SX2H][c] |
| 532 |
|
| 533 |
Iminoarene: [c]=[NX2;$([H1]),$([H0][#6;!$([C]=[N,S,O])])] |
| 534 |
# N may be substituted with H or C, but not carbonyl or similar |
| 535 |
# aromatic atom is always C, not S or P (these are not planar when substituted) |
| 536 |
|
| 537 |
Oxoarene: [c]=[OX1] |
| 538 |
|
| 539 |
Thioarene: [c]=[SX1] |
| 540 |
|
| 541 |
Hetero_N_basic_H: [nX3H1+0] |
| 542 |
# as in pyrole. uncharged to exclude pyridinium ions |
| 543 |
|
| 544 |
Hetero_N_basic_no_H: [nX3H0+0] |
| 545 |
# as in N-methylpyrole. uncharged to exclude pyridinium ions |
| 546 |
|
| 547 |
Hetero_N_nonbasic: [nX2,nX3+] |
| 548 |
# as in pyridine, pyridinium |
| 549 |
|
| 550 |
Hetero_O: [o] |
| 551 |
|
| 552 |
Hetero_S: [sX2] |
| 553 |
# X2 because Daylight's depictmatch falsely describes C1=CS(=O)C=C1 as aromatic |
| 554 |
# (is not planar because of lonepair at S) |
| 555 |
|
| 556 |
Heteroaromatic: [a;!c] |
| 557 |
|
| 558 |
|
| 559 |
# Part II: N, S, P, Si, B |
| 560 |
# ======================= |
| 561 |
|
| 562 |
|
| 563 |
# II.1 Nitrogen |
| 564 |
# ------------- |
| 565 |
|
| 566 |
Nitrite: [NX2](=[OX1])[O;$([X2]),$([X1-])] |
| 567 |
# hits nitrous acid, its anion, esters, and other O-substituted derivatives |
| 568 |
|
| 569 |
Thionitrite: [SX2][NX2]=[OX1] |
| 570 |
|
| 571 |
Nitrate: [$([NX3](=[OX1])(=[OX1])[O;$([X2]),$([X1-])]),$([NX3+]([OX1-])(=[OX1])[O;$([X2]),$([X1-])])] |
| 572 |
# hits nitric acid, its anion, esters, and other O-substituted derivatives |
| 573 |
|
| 574 |
Nitro: [$([NX3](=O)=O),$([NX3+](=O)[O-])][!#8] |
| 575 |
# hits nitro groups attached to C,N, ... but not nitrates |
| 576 |
|
| 577 |
Nitroso: [NX2](=[OX1])[!#7;!#8] |
| 578 |
# no nitrites, no nitrosamines |
| 579 |
|
| 580 |
Azide: [NX1]~[NX2]~[NX2,NX1] |
| 581 |
# hits both mesomeric forms, also anion |
| 582 |
|
| 583 |
Acylazide: [CX3](=[OX1])[NX2]~[NX2]~[NX1] |
| 584 |
|
| 585 |
Diazo: [$([#6]=[NX2+]=[NX1-]),$([#6-]-[NX2+]#[NX1])] |
| 586 |
|
| 587 |
Diazonium: [#6][NX2+]#[NX1] |
| 588 |
|
| 589 |
Nitrosamine: [#7;!$(N*=O)][NX2]=[OX1] |
| 590 |
|
| 591 |
Nitrosamide: [NX2](=[OX1])[N-*=O] |
| 592 |
# includes nitrososulfonamides |
| 593 |
|
| 594 |
N-Oxide: [$([#7+][OX1-]),$([#7v5]=[OX1]);!$([#7](~[O])~[O]);!$([#7]=[#7])] |
| 595 |
# Hits both forms. Won't hit azoxy, nitro, nitroso, or nitrate. |
| 596 |
|
| 597 |
|
| 598 |
Hydrazine: [NX3;$([H2]),$([H1][#6]),$([H0]([#6])[#6]);!$(NC=[O,N,S])][NX3;$([H2]),$([H1][#6]),$([H0]([#6])[#6]);!$(NC=[O,N,S])] |
| 599 |
# no hydrazides |
| 600 |
|
| 601 |
Hydrazone: [NX3;$([H2]),$([H1][#6]),$([H0]([#6])[#6]);!$(NC=[O,N,S])][NX2]=[#6] |
| 602 |
|
| 603 |
Hydroxylamine: [NX3;$([H2]),$([H1][#6]),$([H0]([#6])[#6]);!$(NC=[O,N,S])][OX2;$([H1]),$(O[#6;!$(C=[N,O,S])])] |
| 604 |
# no discrimination between O-, N-, and O,N-substitution |
| 605 |
|
| 606 |
|
| 607 |
# II.2 Sulfur |
| 608 |
# ----------- |
| 609 |
|
| 610 |
Sulfon: [$([SX4](=[OX1])(=[OX1])([#6])[#6]),$([SX4+2]([OX1-])([OX1-])([#6])[#6])] |
| 611 |
# can't be aromatic, thus S and not #16 |
| 612 |
|
| 613 |
Sulfoxide: [$([SX3](=[OX1])([#6])[#6]),$([SX3+]([OX1-])([#6])[#6])] |
| 614 |
|
| 615 |
Sulfonium: [S+;!$([S]~[!#6]);!$([S]*~[#7,#8,#15,#16])] |
| 616 |
# can't be aromatic, thus S and not #16 |
| 617 |
|
| 618 |
Sulfuric_acid: [SX4](=[OX1])(=[OX1])([$([OX2H]),$([OX1-])])[$([OX2H]),$([OX1-])] |
| 619 |
# includes anions |
| 620 |
|
| 621 |
Sulfuric_monoester: [SX4](=[OX1])(=[OX1])([$([OX2H]),$([OX1-])])[OX2][#6;!$(C=[O,N,S])] |
| 622 |
|
| 623 |
Sulfuric_diester: [SX4](=[OX1])(=[OX1])([OX2][#6;!$(C=[O,N,S])])[OX2][#6;!$(C=[O,N,S])] |
| 624 |
|
| 625 |
Sulfuric_monoamide: [SX4](=[OX1])(=[OX1])([#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])])[$([OX2H]),$([OX1-])] |
| 626 |
|
| 627 |
Sulfuric_diamide: [SX4](=[OX1])(=[OX1])([#7X3;$([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;!$(C=[O,N,S])])] |
| 628 |
|
| 629 |
Sulfuric_esteramide: [SX4](=[OX1])(=[OX1])([#7X3][#6;!$(C=[O,N,S])])[OX2][#6;!$(C=[O,N,S])] |
| 630 |
|
| 631 |
Sulfuric_derivative: [SX4D4](=[!#6])(=[!#6])([!#6])[!#6] |
| 632 |
# everything else (would not be a "true" derivative of sulfuric acid, if one of the substituents were less electronegative |
| 633 |
# than sulfur, but this should be very very rare, anyway) |
| 634 |
|
| 635 |
|
| 636 |
|
| 637 |
#### sulfurous acid and derivatives missing!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! |
| 638 |
|
| 639 |
|
| 640 |
|
| 641 |
|
| 642 |
Sulfonic_acid: [SX4;$([H1]),$([H0][#6])](=[OX1])(=[OX1])[$([OX2H]),$([OX1-])] |
| 643 |
|
| 644 |
Sulfonamide: [SX4;$([H1]),$([H0][#6])](=[OX1])(=[OX1])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] |
| 645 |
|
| 646 |
Sulfonic_ester: [SX4;$([H1]),$([H0][#6])](=[OX1])(=[OX1])[OX2][#6;!$(C=[O,N,S])] |
| 647 |
|
| 648 |
Sulfonic_halide: [SX4;$([H1]),$([H0][#6])](=[OX1])(=[OX1])[FX1,ClX1,BrX1,IX1] |
| 649 |
|
| 650 |
Sulfonic_derivative: [SX4;$([H1]),$([H0][#6])](=[!#6])(=[!#6])[!#6] |
| 651 |
# includes all of the above and many more |
| 652 |
# for comparison: this is what "all sulfonic derivatives but not the ones above" would look like: |
| 653 |
# [$([SX4;$([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;!$(C=[O,N,S])])])])] |
| 654 |
|
| 655 |
|
| 656 |
Sulfinic_acid: [SX3;$([H1]),$([H0][#6])](=[OX1])[$([OX2H]),$([OX1-])] |
| 657 |
|
| 658 |
Sulfinic_amide: [SX3;$([H1]),$([H0][#6])](=[OX1])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] |
| 659 |
|
| 660 |
Sulfinic_ester: [SX3;$([H1]),$([H0][#6])](=[OX1])[OX2][#6;!$(C=[O,N,S])] |
| 661 |
|
| 662 |
Sulfinic_halide: [SX3;$([H1]),$([H0][#6])](=[OX1])[FX1,ClX1,BrX1,IX1] |
| 663 |
|
| 664 |
Sulfinic_derivative: [SX3;$([H1]),$([H0][#6])](=[!#6])[!#6] |
| 665 |
|
| 666 |
Sulfenic_acid: [SX2;$([H1]),$([H0][#6])][$([OX2H]),$([OX1-])] |
| 667 |
|
| 668 |
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])])] |
| 669 |
|
| 670 |
Sulfenic_ester: [SX2;$([H1]),$([H0][#6])][OX2][#6;!$(C=[O,N,S])] |
| 671 |
|
| 672 |
Sulfenic_halide: [SX2;$([H1]),$([H0][#6])][FX1,ClX1,BrX1,IX1] |
| 673 |
|
| 674 |
Sulfenic_derivative: [SX2;$([H1]),$([H0][#6])][!#6] |
| 675 |
|
| 676 |
|
| 677 |
# II.3 Phosphorous |
| 678 |
# ---------------- |
| 679 |
|
| 680 |
Phosphine: [PX3;$([H3]),$([H2][#6]),$([H1]([#6])[#6]),$([H0]([#6])([#6])[#6])] |
| 681 |
# similar to amine, but less restrictive: includes also amide- and aminal-analogues |
| 682 |
|
| 683 |
Phosphine_oxide: [PX4;$([H3]=[OX]),$([H2](=[OX])[#6]),$([H1](=[OX])([#6])[#6]),$([H0](=[OX])([#6])([#6])[#6])] |
| 684 |
|
| 685 |
Phosphonium: [P+;!$([P]~[!#6]);!$([P]*~[#7,#8,#15,#16])] |
| 686 |
# similar to Ammonium |
| 687 |
|
| 688 |
Phosphorylen: [PX4;$([H3]=[CX3]),$([H2](=[CX3])[#6]),$([H1](=[CX3])([#6])[#6]),$([H0](=[CX3])([#6])([#6])[#6])] |
| 689 |
|
| 690 |
|
| 691 |
# conventions for the following acids and derivatives: |
| 692 |
# acids find protonated and deprotonated acids |
| 693 |
# esters do not find mixed anhydrides ( ...P-O-C(=O)) |
| 694 |
# derivatives: subtituents which go in place of the OH and =O are not H or C (may also be O, |
| 695 |
# thus including acids and esters) |
| 696 |
|
| 697 |
Phosphonic_acid: [PX4;$([H1]),$([H0][#6])](=[OX1])([$([OX2H]),$([OX1-])])[$([OX2H]),$([OX1-])] |
| 698 |
# includes anions |
| 699 |
|
| 700 |
Phosphonic_monoester: [PX4;$([H1]),$([H0][#6])](=[OX1])([$([OX2H]),$([OX1-])])[OX2][#6;!$(C=[O,N,S])] |
| 701 |
|
| 702 |
Phosphonic_diester: [PX4;$([H1]),$([H0][#6])](=[OX1])([OX2][#6;!$(C=[O,N,S])])[OX2][#6;!$(C=[O,N,S])] |
| 703 |
|
| 704 |
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])])] |
| 705 |
|
| 706 |
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])])] |
| 707 |
|
| 708 |
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;!$(C=[O,N,S])])] |
| 709 |
|
| 710 |
Phosphonic_acid_derivative: [PX4;$([H1]),$([H0][#6])](=[!#6])([!#6])[!#6] |
| 711 |
# all of the above and much more |
| 712 |
|
| 713 |
|
| 714 |
Phosphoric_acid: [PX4D4](=[OX1])([$([OX2H]),$([OX1-])])([$([OX2H]),$([OX1-])])[$([OX2H]),$([OX1-])] |
| 715 |
# includes anions |
| 716 |
|
| 717 |
Phosphoric_monoester: [PX4D4](=[OX1])([$([OX2H]),$([OX1-])])([$([OX2H]),$([OX1-])])[OX2][#6;!$(C=[O,N,S])] |
| 718 |
|
| 719 |
Phosphoric_diester: [PX4D4](=[OX1])([$([OX2H]),$([OX1-])])([OX2][#6;!$(C=[O,N,S])])[OX2][#6;!$(C=[O,N,S])] |
| 720 |
|
| 721 |
Phosphoric_triester: [PX4D4](=[OX1])([OX2][#6;!$(C=[O,N,S])])([OX2][#6;!$(C=[O,N,S])])[OX2][#6;!$(C=[O,N,S])] |
| 722 |
|
| 723 |
Phosphoric_monoamide: [PX4D4](=[OX1])([$([OX2H]),$([OX1-])])([$([OX2H]),$([OX1-])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] |
| 724 |
|
| 725 |
Phosphoric_diamide: [PX4D4](=[OX1])([$([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;!$(C=[O,N,S])])] |
| 726 |
|
| 727 |
Phosphoric_triamide: [PX4D4](=[OX1])([#7X3;$([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;!$(C=[O,N,S])])] |
| 728 |
|
| 729 |
Phosphoric_monoestermonoamide: [PX4D4](=[OX1])([$([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])])] |
| 730 |
|
| 731 |
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])])] |
| 732 |
|
| 733 |
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;!$(C=[O,N,S])])] |
| 734 |
|
| 735 |
Phosphoric_acid_derivative: [PX4D4](=[!#6])([!#6])([!#6])[!#6] |
| 736 |
|
| 737 |
|
| 738 |
Phosphinic_acid: [PX4;$([H2]),$([H1][#6]),$([H0]([#6])[#6])](=[OX1])[$([OX2H]),$([OX1-])] |
| 739 |
|
| 740 |
Phosphinic_ester: [PX4;$([H2]),$([H1][#6]),$([H0]([#6])[#6])](=[OX1])[OX2][#6;!$(C=[O,N,S])] |
| 741 |
|
| 742 |
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;!$(C=[O,N,S])])] |
| 743 |
|
| 744 |
Phosphinic_acid_derivative: [PX4;$([H2]),$([H1][#6]),$([H0]([#6])[#6])](=[!#6])[!#6] |
| 745 |
|
| 746 |
|
| 747 |
Phosphonous_acid: [PX3;$([H1]),$([H0][#6])]([$([OX2H]),$([OX1-])])[$([OX2H]),$([OX1-])] |
| 748 |
|
| 749 |
Phosphonous_monoester: [PX3;$([H1]),$([H0][#6])]([$([OX2H]),$([OX1-])])[OX2][#6;!$(C=[O,N,S])] |
| 750 |
|
| 751 |
Phosphonous_diester: [PX3;$([H1]),$([H0][#6])]([OX2][#6;!$(C=[O,N,S])])[OX2][#6;!$(C=[O,N,S])] |
| 752 |
|
| 753 |
Phosphonous_monoamide: [PX3;$([H1]),$([H0][#6])]([$([OX2H]),$([OX1-])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])] |
| 754 |
|
| 755 |
Phosphonous_diamide: [PX3;$([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;!$(C=[O,N,S])])] |
| 756 |
|
| 757 |
Phosphonous_esteramide: [PX3;$([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])])] |
| 758 |
|
| 759 |
Phosphonous_derivatives: [PX3;$([D2]),$([D3][#6])]([!#6])[!#6] |
| 760 |
|
| 761 |
|
| 762 |
Phosphinous_acid: [PX3;$([H2]),$([H1][#6]),$([H0]([#6])[#6])][$([OX2H]),$([OX1-])] |
| 763 |
|
| 764 |
Phosphinous_ester: [PX3;$([H2]),$([H1][#6]),$([H0]([#6])[#6])][OX2][#6;!$(C=[O,N,S])] |
| 765 |
|
| 766 |
Phosphinous_amide: [PX3;$([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])])] |
| 767 |
|
| 768 |
Phosphinous_derivatives: [PX3;$([H2]),$([H1][#6]),$([H0]([#6])[#6])][!#6] |
| 769 |
|
| 770 |
|
| 771 |
# II.4 Silicon |
| 772 |
# ------------ |
| 773 |
|
| 774 |
Quart_silane: [SiX4]([#6])([#6])([#6])[#6] |
| 775 |
# four C-substituents. non-reactive, non-toxic, in experimental phase for drug development |
| 776 |
|
| 777 |
Non-quart_silane: [SiX4;$([H1]([#6])([#6])[#6]),$([H2]([#6])[#6]),$([H3][#6]),$([H4])] |
| 778 |
# has 1-4 hydride(s), reactive. Daylight's depictmatch does not add hydrogens automatically to |
| 779 |
# the free positions at Si, thus Hs had to be added implicitly |
| 780 |
|
| 781 |
Silylmonohalide: [SiX4]([FX1,ClX1,BrX1,IX1])([#6])([#6])[#6] |
| 782 |
# reagents for inserting protection groups |
| 783 |
|
| 784 |
Het_trialkylsilane: [SiX4]([!#6])([#6])([#6])[#6] |
| 785 |
# mostly acid-labile protection groups such as trimethylsilyl-ethers |
| 786 |
|
| 787 |
Dihet_dialkylsilane: [SiX4]([!#6])([!#6])([#6])[#6] |
| 788 |
|
| 789 |
Trihet_alkylsilane: [SiX4]([!#6])([!#6])([!#6])[#6] |
| 790 |
|
| 791 |
Silicic_acid_derivative: [SiX4]([!#6])([!#6])([!#6])[!#6] |
| 792 |
# four substituent which are neither C nor H |
| 793 |
|
| 794 |
|
| 795 |
# II.5 Boron |
| 796 |
# ---------- |
| 797 |
|
| 798 |
Trialkylborane: [BX3]([#6])([#6])[#6] |
| 799 |
# also carbonyls allowed |
| 800 |
|
| 801 |
Boric_acid_derivatives: [BX3]([!#6])([!#6])[!#6] |
| 802 |
# includes acids, esters, amides, ... H-substituent at B is very rare. |
| 803 |
|
| 804 |
Boronic_acid_derivative: [BX3]([!#6])([!#6])[!#6] |
| 805 |
# # includes acids, esters, amides, ... |
| 806 |
|
| 807 |
Borohydride: [BH1,BH2,BH3,BH4] |
| 808 |
# at least one H attached to B |
| 809 |
|
| 810 |
Quartary_boron: [BX4] |
| 811 |
# mostly borates (negative charge), in complex with Lewis-base |
| 812 |
|
| 813 |
|
| 814 |
|
| 815 |
# Part III: Some Special Patterns |
| 816 |
# =============================== |
| 817 |
|
| 818 |
|
| 819 |
# III.1 Chains |
| 820 |
# ------------ |
| 821 |
|
| 822 |
# some simple chains |
| 823 |
|
| 824 |
|
| 825 |
|
| 826 |
# III.2 Rings |
| 827 |
# ----------- |
| 828 |
|
| 829 |
Aromatic: a |
| 830 |
|
| 831 |
Heterocyclic: [!#6;!R0] |
| 832 |
# may be aromatic or not |
| 833 |
|
| 834 |
Epoxide: [OX2r3]1[#6r3][#6r3]1 |
| 835 |
# toxic/reactive. may be annelated to aromat, but must not be aromatic itself (oxirane-2,3-dione) |
| 836 |
|
| 837 |
NH_aziridine: [NX3H1r3]1[#6r3][#6r3]1 |
| 838 |
# toxic/reactive according to Maybridge's garbage filter |
| 839 |
|
| 840 |
Spiro: [D4R;$(*(@*)(@*)(@*)@*)] |
| 841 |
# at least two different rings can be found which are sharing just one atom |
| 842 |
|
| 843 |
Annelated_rings: [R;$(*(@*)(@*)@*);!$([R2;$(*(@*)(@*)(@*)@*)])]@[R;$(*(@*)(@*)@*);!$([R2;$(*(@*)(@*)(@*)@*)])] |
| 844 |
# two different rings sharing exactly two atoms |
| 845 |
|
| 846 |
Bridged_rings: [R;$(*(@*)(@*)@*);!$([D4R;$(*(@*)(@*)(@*)@*)]);!$([R;$(*(@*)(@*)@*);!$([R2;$(*(@*)(@*)(@*)@*)])]@[R;$(*(@*)(@*)@*);!$([R2;$(*(@*)(@*)(@*)@*)])])] |
| 847 |
# part of two or more rings, not spiro, not annelated -> finds bridgehead atoms, |
| 848 |
# but only if they are not annelated at the same time - otherwise impossible (?) |
| 849 |
# to distinguish from non-bridgehead annelated atoms |
| 850 |
|
| 851 |
# some basic ring-patterns (just size, no other information): |
| 852 |
|
| 853 |
|
| 854 |
|
| 855 |
|
| 856 |
|
| 857 |
# III.3 Sugars and Nucleosides/Nucleotides, Steroids |
| 858 |
# -------------------------------------------------- |
| 859 |
|
| 860 |
# because of the large variety of sugar derivatives, different patterns can be applied. |
| 861 |
# The choice of patterns and their combinations will depend on the contents of the database |
| 862 |
# e.g. natural products, nucleoside analoges with modified sugars, ... as well as on the |
| 863 |
# desired restriction |
| 864 |
|
| 865 |
|
| 866 |
Sugar_pattern_1: [OX2;$([r5]1@C@C@C(O)@C1),$([r6]1@C@C@C(O)@C(O)@C1)] |
| 867 |
# 5 or 6-membered ring containing one O and at least one (r5) or two (r6) oxygen-substituents. |
| 868 |
|
| 869 |
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)] |
| 870 |
# 5 or 6-membered ring containing one O and an acetal-like bond at postion 2. |
| 871 |
|
| 872 |
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)] |
| 873 |
# combination of the two above |
| 874 |
|
| 875 |
Sugar_pattern_2_reducing: [OX2;$([r5]1@C(!@[OX2H1])@C@C@C1),$([r6]1@C(!@[OX2H1])@C@C@C@C1)] |
| 876 |
# 5 or 6-membered cyclic hemi-acetal |
| 877 |
|
| 878 |
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)] |
| 879 |
# 5 or 6-membered cyclic hemi-acetal |
| 880 |
|
| 881 |
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)] |
| 882 |
# 5 or 6-membered cyclic hemi-acetal |
| 883 |
|
| 884 |
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)]) |
| 885 |
# pattern1 occours more than once (in same molecule, but moieties don't have to be adjacent!) |
| 886 |
|
| 887 |
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)]) |
| 888 |
# pattern2 occours more than once (in same molecule, but moieties don't have to be adjacent!) |
| 889 |
|
| 890 |
|
| 891 |
# III.4 Everything else... |
| 892 |
# ------------------------ |
| 893 |
|
| 894 |
Conjugated_double_bond: *=*[*]=,#,:[*] |
| 895 |
|
| 896 |
Conjugated_tripple_bond: *#*[*]=,#,:[*] |
| 897 |
|
| 898 |
Cis_double_bond: */[D2]=[D2]\* |
| 899 |
# only one single-bonded substituent on each DB-atom. no aromats. |
| 900 |
# only found when character of DB is explicitely stated. |
| 901 |
|
| 902 |
Trans_double_bond: */[D2]=[D2]/* |
| 903 |
# analog |
| 904 |
|
| 905 |
Mixed_anhydrides: [$(*=O),$([#16,#14,#5]),$([#7]([#6]=[OX1]))][#8X2][$(*=O),$([#16,#14,#5]),$([#7]([#6]=[OX1]))] |
| 906 |
# should hits all combinations of two acids |
| 907 |
|
| 908 |
Halogen_on_hetero: [FX1,ClX1,BrX1,IX1][!#6] |
| 909 |
|
| 910 |
Halogen_multi_subst: [F,Cl,Br,I;!$([X1]);!$([X0-])] |
| 911 |
# Halogen which is not mono-substituted nor an anion, e.g. chlorate. |
| 912 |
# Most of these cases should be also filtered by Halogen_on_hetero. |
| 913 |
|
| 914 |
Trifluoromethyl: [FX1][CX4;!$([H0][Cl,Br,I]);!$([F][C]([F])([F])[F])]([FX1])([FX1]) |
| 915 |
# C with three F attached, connected to anything which is not another halogen |
| 916 |
|
| 917 |
C_ONS_bond: [#6]~[#7,#8,#16] |
| 918 |
# probably all drug-like molecules have at least one O, N, or S connected to a C -> nice filter |
| 919 |
|
| 920 |
Mixture: (*).(*) |
| 921 |
# two or more seperate parts, may also be salt |
| 922 |
# Did not work with Openbabel 1.0 (no component-level grouping) |
| 923 |
|
| 924 |
|
| 925 |
Charged: [!+0] |
| 926 |
|
| 927 |
Anion: [-1,-2,-3,-4,-5,-6,-7] |
| 928 |
|
| 929 |
Kation: [+1,+2,+3,+4,+5,+6,+7] |
| 930 |
|
| 931 |
Salt: ([-1,-2,-3,-4,-5,-6,-7]).([+1,+2,+3,+4,+5,+6,+7]) |
| 932 |
# two or more seperate components with opposite charges |
| 933 |
|
| 934 |
Zwitterion: ([-1,-2,-3,-4,-5,-6,-7].[+1,+2,+3,+4,+5,+6,+7]) |
| 935 |
# both negative and positive charges somewhere within the same molecule. |
| 936 |
|
| 937 |
1,3-Tautomerizable: [$([#7X2,OX1,SX1]=*[!H0;!$([a;!n])]),$([#7X3,OX2,SX2;!H0]*=*),$([#7X3,OX2,SX2;!H0]*:n)] |
| 938 |
# 1,3 migration of H allowed. Includes keto/enol and amide/enamide. |
| 939 |
# Aromatic rings must stay aromatic - no keto form of phenol |
| 940 |
|
| 941 |
1,5-Tautomerizable: [$([#7X2,OX1,SX1]=,:**=,:*[!H0;!$([a;!n])]),$([#7X3,OX2,SX2;!H0]*=**=*),$([#7X3,OX2,SX2;!H0]*=,:**:n)] |
| 942 |
|
| 943 |
Rotatable_bond: [!$(*#*)&!D1]-!@[!$(*#*)&!D1] |
| 944 |
# taken from http://www.daylight.com/support/contrib/smarts/content.html |
| 945 |
|
| 946 |
Michael_acceptor: [CX3]=[CX3][$([CX3]=[O,N,S]),$(C#[N]),$([S,P]=[OX1]),$([NX3]=O),$([NX3+](=O)[O-])] |
| 947 |
# the classical case: C=C near carbonyl, nitrile, nitro, or similar |
| 948 |
# Oxo-heteroaromats and similar are not included. |
| 949 |
|
| 950 |
Dicarbodiazene: [CX3](=[OX1])[NX2]=[NX2][CX3](=[OX1]) |
| 951 |
# Michael-like acceptor, see Mitsunobu reaction |
| 952 |
|
| 953 |
# H-Bond_donor: |
| 954 |
|
| 955 |
# H-Bond_acceptor: |
| 956 |
|
| 957 |
# Pos_ionizable: |
| 958 |
|
| 959 |
# Neg_ionizable: |
| 960 |
|
| 961 |
# Unlikely_ions: |
| 962 |
# O+,N-,C+,C-, ... |
| 963 |
|
| 964 |
CH-acidic: [$([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;!$([H0])]1[CX3]=[CX3][CX3]=[CX3]1)] |
| 965 |
# C-H alpha to carbony, nitro or similar, C is not double-bonded, only C, H, S,P=O and nitro substituents allowed. |
| 966 |
# pentadiene is included. acids, their salts, prim./sec. amides, and imides are excluded. |
| 967 |
# hits also CH-acidic_strong |
| 968 |
|
| 969 |
CH-acidic_strong: [CX4;!$([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]);!$([*+0][S,O;X1-])] |
| 970 |
# same as above (without pentadiene), but carbonyl or similar on two or three sides |
| 971 |
|
| 972 |
Chiral_center_specified: [$([*@](~*)(~*)(*)*),$([*@H](*)(*)*),$([*@](~*)(*)*),$([*@H](~*)~*)] |
| 973 |
# Hits atoms with tetrahedral chirality, if chiral center is specified in the SMILES string |
| 974 |
# depictmach does not find oxonium, sulfonium, or sulfoxides! |
| 975 |
|
| 976 |
Chiral_center_unspecified: [$([*@?](~*)(~*)(*)*),$([*@?H](*)(*)*),$([*@?](~*)(*)*),$([*@?H](~*)~*)] |
| 977 |
# Hits atoms with tetrahedral chirality, even if chiral center is not specified in the SMILES string |
