Class SubstructureFingerprinter

  • All Implemented Interfaces:
    IFingerprinter
    Direct Known Subclasses:
    KlekotaRothFingerprinter

    public class SubstructureFingerprinter
    extends AbstractFingerprinter
    implements IFingerprinter
    IFingerprinter that gives a bit set which has a size equal to the number of substructures it was constructed from. A set bit indicates that that substructure was found at least once in the molecule for which the fingerprint was calculated. The fingerprint currently supports 307 substructures, listed below:
    Table: 1: Default substructure patterns (SMARTS) for each bit position
    Bit positionDescriptionPattern
    0Primary carbon[CX4H3][#6]
    1Secondary carbon[CX4H2]([#6])[#6]
    2Tertiary carbon[CX4H1]([#6])([#6])[#6]
    3Quaternary carbon[CX4]([#6])([#6])([#6])[#6]
    4Alkene[CX3;$([H2]),$([H1][#6]),$(C([#6])[#6])]=[CX3;$([H2]),$([H1][#6]),$(C([#6])[#6])]
    5Alkyne[CX2]#[CX2]
    6Allene[CX3]=[CX2]=[CX3]
    7Alkylchloride[ClX1][CX4]
    8Alkylfluoride[FX1][CX4]
    9Alkylbromide[BrX1][CX4]
    10Alkyliodide[IX1][CX4]
    11Alcohol[OX2H][CX4;!$(C([OX2H])[O,S,#7,#15])]
    12Primary alcohol[OX2H][CX4H2;!$(C([OX2H])[O,S,#7,#15])]
    13Secondary alcohol[OX2H][CX4H;!$(C([OX2H])[O,S,#7,#15])]
    14Tertiary alcohol[OX2H][CX4D4;!$(C([OX2H])[O,S,#7,#15])]
    15Dialkylether[OX2]([CX4;!$(C([OX2])[O,S,#7,#15,F,Cl,Br,I])])[CX4;!$(C([OX2])[O,S,#7,#15])]
    16Dialkylthioether[SX2]([CX4;!$(C([OX2])[O,S,#7,#15,F,Cl,Br,I])])[CX4;!$(C([OX2])[O,S,#7,#15])]
    17Alkylarylether[OX2](c)[CX4;!$(C([OX2])[O,S,#7,#15,F,Cl,Br,I])]
    18Diarylether[c][OX2][c]
    19Alkylarylthioether[SX2](c)[CX4;!$(C([OX2])[O,S,#7,#15,F,Cl,Br,I])]
    20Diarylthioether[c][SX2][c]
    21Oxonium[O+;!$([O]~[!#6]);!$([S]*~[#7,#8,#15,#16])]
    22Amine[NX3+0,NX4+;!$([N]~[!#6]);!$([N]*~[#7,#8,#15,#16])]
    23Primary aliph amine[NX3H2+0,NX4H3+;!$([N][!C]);!$([N]*~[#7,#8,#15,#16])]
    24Secondary aliph amine[NX3H1+0,NX4H2+;!$([N][!C]);!$([N]*~[#7,#8,#15,#16])]
    25Tertiary aliph amine[NX3H0+0,NX4H1+;!$([N][!C]);!$([N]*~[#7,#8,#15,#16])]
    26Quaternary aliph ammonium[NX4H0+;!$([N][!C]);!$([N]*~[#7,#8,#15,#16])]
    27Primary arom amine[NX3H2+0,NX4H3+]c
    28Secondary arom amine[NX3H1+0,NX4H2+;!$([N][!c]);!$([N]*~[#7,#8,#15,#16])]
    29Tertiary arom amine[NX3H0+0,NX4H1+;!$([N][!c]);!$([N]*~[#7,#8,#15,#16])]
    30Quaternary arom ammonium[NX4H0+;!$([N][!c]);!$([N]*~[#7,#8,#15,#16])]
    31Secondary mixed amine[NX3H1+0,NX4H2+;$([N]([c])[C]);!$([N]*~[#7,#8,#15,#16])]
    32Tertiary mixed amine[NX3H0+0,NX4H1+;$([N]([c])([C])[#6]);!$([N]*~[#7,#8,#15,#16])]
    33Quaternary mixed ammonium[NX4H0+;$([N]([c])([C])[#6][#6]);!$([N]*~[#7,#8,#15,#16])]
    34Ammonium[N+;!$([N]~[!#6]);!$(N=*);!$([N]*~[#7,#8,#15,#16])]
    35Alkylthiol[SX2H][CX4;!$(C([SX2H])~[O,S,#7,#15])]
    36Dialkylthioether[SX2]([CX4;!$(C([SX2])[O,S,#7,#15,F,Cl,Br,I])])[CX4;!$(C([SX2])[O,S,#7,#15])]
    37Alkylarylthioether[SX2](c)[CX4;!$(C([SX2])[O,S,#7,#15])]
    38Disulfide[SX2D2][SX2D2]
    391,2-Aminoalcohol[OX2H][CX4;!$(C([OX2H])[O,S,#7,#15,F,Cl,Br,I])][CX4;!$(C([N])[O,S,#7,#15])][NX3;!$(NC=[O,S,N])]
    401,2-Diol[OX2H][CX4;!$(C([OX2H])[O,S,#7,#15])][CX4;!$(C([OX2H])[O,S,#7,#15])][OX2H]
    411,1-Diol[OX2H][CX4;!$(C([OX2H])([OX2H])[O,S,#7,#15])][OX2H]
    42Hydroperoxide[OX2H][OX2]
    43Peroxo[OX2D2][OX2D2]
    44Organolithium compounds[LiX1][#6,#14]
    45Organomagnesium compounds[MgX2][#6,#14]
    46Organometallic compounds[!#1;!#5;!#6;!#7;!#8;!#9;!#14;!#15;!#16;!#17;!#33;!#34;!#35;!#52;!#53;!#85]~[#6;!-]
    47Aldehyde[$([CX3H][#6]),$([CX3H2])]=[OX1]
    48Ketone[#6][CX3](=[OX1])[#6]
    49Thioaldehyde[$([CX3H][#6]),$([CX3H2])]=[SX1]
    50Thioketone[#6][CX3](=[SX1])[#6]
    51Imine[NX2;$([N][#6]),$([NH]);!$([N][CX3]=[#7,#8,#15,#16])]=[CX3;$([CH2]),$([CH][#6]),$([C]([#6])[#6])]
    52Immonium[NX3+;!$([N][!#6]);!$([N][CX3]=[#7,#8,#15,#16])]
    53Oxime[NX2](=[CX3;$([CH2]),$([CH][#6]),$([C]([#6])[#6])])[OX2H]
    54Oximether[NX2](=[CX3;$([CH2]),$([CH][#6]),$([C]([#6])[#6])])[OX2][#6;!$(C=[#7,#8])]
    55Acetal[OX2]([#6;!$(C=[O,S,N])])[CX4;!$(C(O)(O)[!#6])][OX2][#6;!$(C=[O,S,N])]
    56Hemiacetal[OX2H][CX4;!$(C(O)(O)[!#6])][OX2][#6;!$(C=[O,S,N])]
    57Aminal[NX3v3;!$(NC=[#7,#8,#15,#16])]([#6])[CX4;!$(C(N)(N)[!#6])][NX3v3;!$(NC=[#7,#8,#15,#16])][#6]
    58Hemiaminal[NX3v3;!$(NC=[#7,#8,#15,#16])]([#6])[CX4;!$(C(N)(N)[!#6])][OX2H]
    59Thioacetal[SX2]([#6;!$(C=[O,S,N])])[CX4;!$(C(S)(S)[!#6])][SX2][#6;!$(C=[O,S,N])]
    60Thiohemiacetal[SX2]([#6;!$(C=[O,S,N])])[CX4;!$(C(S)(S)[!#6])][OX2H]
    61Halogen acetal like[NX3v3,SX2,OX2;!$(*C=[#7,#8,#15,#16])][CX4;!$(C([N,S,O])([N,S,O])[!#6])][FX1,ClX1,BrX1,IX1]
    62Acetal like[NX3v3,SX2,OX2;!$(*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])]
    63Halogenmethylen ester and similar[NX3v3,SX2,OX2;$(**=[#7,#8,#15,#16])][CX4;!$(C([N,S,O])([N,S,O])[!#6])][FX1,ClX1,BrX1,IX1]
    64NOS methylen ester and similar[NX3v3,SX2,OX2;$(**=[#7,#8,#15,#16])][CX4;!$(C([N,S,O])([N,S,O])[!#6])][NX3v3,SX2,OX2;!$(*C=[#7,#8,#15,#16])]
    65Hetero methylen ester and similar[NX3v3,SX2,OX2;$(**=[#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])]
    66Cyanhydrine[NX1]#[CX2][CX4;$([CH2]),$([CH]([CX2])[#6]),$(C([CX2])([#6])[#6])][OX2H]
    67Chloroalkene[ClX1][CX3]=[CX3]
    68Fluoroalkene[FX1][CX3]=[CX3]
    69Bromoalkene[BrX1][CX3]=[CX3]
    70Iodoalkene[IX1][CX3]=[CX3]
    71Enol[OX2H][CX3;$([H1]),$(C[#6])]=[CX3]
    72Endiol[OX2H][CX3;$([H1]),$(C[#6])]=[CX3;$([H1]),$(C[#6])][OX2H]
    73Enolether[OX2]([#6;!$(C=[N,O,S])])[CX3;$([H0][#6]),$([H1])]=[CX3]
    74Enolester[OX2]([CX3]=[OX1])[#6X3;$([#6][#6]),$([H1])]=[#6X3;!$(C[OX2H])]
    75Enamine[NX3;$([NH2][CX3]),$([NH1]([CX3])[#6]),$([N]([CX3])([#6])[#6]);!$([N]*=[#7,#8,#15,#16])][CX3;$([CH]),$([C][#6])]=[CX3]
    76Thioenol[SX2H][CX3;$([H1]),$(C[#6])]=[CX3]
    77Thioenolether[SX2]([#6;!$(C=[N,O,S])])[CX3;$(C[#6]),$([CH])]=[CX3]
    78Acylchloride[CX3;$([R0][#6]),$([H1R0])](=[OX1])[ClX1]
    79Acylfluoride[CX3;$([R0][#6]),$([H1R0])](=[OX1])[FX1]
    80Acylbromide[CX3;$([R0][#6]),$([H1R0])](=[OX1])[BrX1]
    81Acyliodide[CX3;$([R0][#6]),$([H1R0])](=[OX1])[IX1]
    82Acylhalide[CX3;$([R0][#6]),$([H1R0])](=[OX1])[FX1,ClX1,BrX1,IX1]
    83Carboxylic acid[CX3;$([R0][#6]),$([H1R0])](=[OX1])[$([OX2H]),$([OX1-])]
    84Carboxylic ester[CX3;$([R0][#6]),$([H1R0])](=[OX1])[OX2][#6;!$(C=[O,N,S])]
    85Lactone[#6][#6X3R](=[OX1])[#8X2][#6;!$(C=[O,N,S])]
    86Carboxylic anhydride[CX3;$([H0][#6]),$([H1])](=[OX1])[#8X2][CX3;$([H0][#6]),$([H1])](=[OX1])
    87Carboxylic acid derivative[$([#6X3H0][#6]),$([#6X3H])](=[!#6])[!#6]
    88Carbothioic acid[CX3;!R;$([C][#6]),$([CH]);$([C](=[OX1])[$([SX2H]),$([SX1-])]),$([C](=[SX1])[$([OX2H]),$([OX1-])])]
    89Carbothioic S ester[CX3;$([R0][#6]),$([H1R0])](=[OX1])[SX2][#6;!$(C=[O,N,S])]
    90Carbothioic S lactone[#6][#6X3R](=[OX1])[#16X2][#6;!$(C=[O,N,S])]
    91Carbothioic O ester[CX3;$([H0][#6]),$([H1])](=[SX1])[OX2][#6;!$(C=[O,N,S])]
    92Carbothioic O lactone[#6][#6X3R](=[SX1])[#8X2][#6;!$(C=[O,N,S])]
    93Carbothioic halide[CX3;$([H0][#6]),$([H1])](=[SX1])[FX1,ClX1,BrX1,IX1]
    94Carbodithioic acid[CX3;!R;$([C][#6]),$([CH]);$([C](=[SX1])[SX2H])]
    95Carbodithioic ester[CX3;!R;$([C][#6]),$([CH]);$([C](=[SX1])[SX2][#6;!$(C=[O,N,S])])]
    96Carbodithiolactone[#6][#6X3R](=[SX1])[#16X2][#6;!$(C=[O,N,S])]
    97Amide[CX3;$([R0][#6]),$([H1R0])](=[OX1])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]
    98Primary amide[CX3;$([R0][#6]),$([H1R0])](=[OX1])[NX3H2]
    99Secondary amide[CX3;$([R0][#6]),$([H1R0])](=[OX1])[#7X3H1][#6;!$(C=[O,N,S])]
    100Tertiary amide[CX3;$([R0][#6]),$([H1R0])](=[OX1])[#7X3H0]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])]
    101Lactam[#6R][#6X3R](=[OX1])[#7X3;$([H1][#6;!$(C=[O,N,S])]),$([H0]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]
    102Alkyl imide[#6X3;$([H0][#6]),$([H1])](=[OX1])[#7X3H0]([#6])[#6X3;$([H0][#6]),$([H1])](=[OX1])
    103N hetero imide[#6X3;$([H0][#6]),$([H1])](=[OX1])[#7X3H0]([!#6])[#6X3;$([H0][#6]),$([H1])](=[OX1])
    104Imide acidic[#6X3;$([H0][#6]),$([H1])](=[OX1])[#7X3H1][#6X3;$([H0][#6]),$([H1])](=[OX1])
    105Thioamide[$([CX3;!R][#6]),$([CX3H;!R])](=[SX1])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]
    106Thiolactam[#6R][#6X3R](=[SX1])[#7X3;$([H1][#6;!$(C=[O,N,S])]),$([H0]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]
    107Oximester[#6X3;$([H0][#6]),$([H1])](=[OX1])[#8X2][#7X2]=,:[#6X3;$([H0]([#6])[#6]),$([H1][#6]),$([H2])]
    108Amidine[NX3;!$(NC=[O,S])][CX3;$([CH]),$([C][#6])]=[NX2;!$(NC=[O,S])]
    109Hydroxamic acid[CX3;$([H0][#6]),$([H1])](=[OX1])[#7X3;$([H1]),$([H0][#6;!$(C=[O,N,S])])][$([OX2H]),$([OX1-])]
    110Hydroxamic acid ester[CX3;$([H0][#6]),$([H1])](=[OX1])[#7X3;$([H1]),$([H0][#6;!$(C=[O,N,S])])][OX2][#6;!$(C=[O,N,S])]
    111Imidoacid[CX3R0;$([H0][#6]),$([H1])](=[NX2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[$([OX2H]),$([OX1-])]
    112Imidoacid cyclic[#6R][#6X3R](=,:[#7X2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[$([OX2H]),$([OX1-])]
    113Imidoester[CX3R0;$([H0][#6]),$([H1])](=[NX2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[OX2][#6;!$(C=[O,N,S])]
    114Imidolactone[#6R][#6X3R](=,:[#7X2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[OX2][#6;!$(C=[O,N,S])]
    115Imidothioacid[CX3R0;$([H0][#6]),$([H1])](=[NX2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[$([SX2H]),$([SX1-])]
    116Imidothioacid cyclic[#6R][#6X3R](=,:[#7X2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[$([SX2H]),$([SX1-])]
    117Imidothioester[CX3R0;$([H0][#6]),$([H1])](=[NX2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[SX2][#6;!$(C=[O,N,S])]
    118Imidothiolactone[#6R][#6X3R](=,:[#7X2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[SX2][#6;!$(C=[O,N,S])]
    119Amidine[#7X3v3;!$(N([#6X3]=[#7X2])C=[O,S])][CX3R0;$([H1]),$([H0][#6])]=[NX2v3;!$(N(=[#6X3][#7X3])C=[O,S])]
    120Imidolactam[#6][#6X3R;$([H0](=[NX2;!$(N(=[#6X3][#7X3])C=[O,S])])[#7X3;!$(N([#6X3]=[#7X2])C=[O,S])]),$([H0](-[NX3;!$(N([#6X3]=[#7X2])C=[O,S])])=,:[#7X2;!$(N(=[#6X3][#7X3])C=[O,S])])]
    121Imidoylhalide[CX3R0;$([H0][#6]),$([H1])](=[NX2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[FX1,ClX1,BrX1,IX1]
    122Imidoylhalide cyclic[#6R][#6X3R](=,:[#7X2;$([H1]),$([H0][#6;!$(C=[O,N,S])])])[FX1,ClX1,BrX1,IX1]
    123Amidrazone[$([$([#6X3][#6]),$([#6X3H])](=[#7X2v3])[#7X3v3][#7X3v3]),$([$([#6X3][#6]),$([#6X3H])]([#7X3v3])=[#7X2v3][#7X3v3])]
    124Alpha aminoacid[NX3,NX4+;!$([N]~[!#6]);!$([N]*~[#7,#8,#15,#16])][C][CX3](=[OX1])[OX2H,OX1-]
    125Alpha hydroxyacid[OX2H][C][CX3](=[OX1])[OX2H,OX1-]
    126Peptide middle[NX3;$([N][CX3](=[OX1])[C][NX3,NX4+])][C][CX3](=[OX1])[NX3;$([N][C][CX3](=[OX1])[NX3,OX2,OX1-])]
    127Peptide C term[NX3;$([N][CX3](=[OX1])[C][NX3,NX4+])][C][CX3](=[OX1])[OX2H,OX1-]
    128Peptide N term[NX3,NX4+;!$([N]~[!#6]);!$([N]*~[#7,#8,#15,#16])][C][CX3](=[OX1])[NX3;$([N][C][CX3](=[OX1])[NX3,OX2,OX1-])]
    129Carboxylic orthoester[#6][OX2][CX4;$(C[#6]),$([CH])]([OX2][#6])[OX2][#6]
    130Ketene[CX3]=[CX2]=[OX1]
    131Ketenacetal[#7X2,#8X3,#16X2;$(*[#6,#14])][#6X3]([#7X2,#8X3,#16X2;$(*[#6,#14])])=[#6X3]
    132Nitrile[NX1]#[CX2]
    133Isonitrile[CX1-]#[NX2+]
    134Vinylogous carbonyl or carboxyl derivative[#6X3](=[OX1])[#6X3]=,:[#6X3][#7,#8,#16,F,Cl,Br,I]
    135Vinylogous acid[#6X3](=[OX1])[#6X3]=,:[#6X3][$([OX2H]),$([OX1-])]
    136Vinylogous ester[#6X3](=[OX1])[#6X3]=,:[#6X3][#6;!$(C=[O,N,S])]
    137Vinylogous amide[#6X3](=[OX1])[#6X3]=,:[#6X3][#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]
    138Vinylogous halide[#6X3](=[OX1])[#6X3]=,:[#6X3][FX1,ClX1,BrX1,IX1]
    139Carbonic acid dieester[#6;!$(C=[O,N,S])][#8X2][#6X3](=[OX1])[#8X2][#6;!$(C=[O,N,S])]
    140Carbonic acid esterhalide[#6;!$(C=[O,N,S])][OX2;!R][CX3](=[OX1])[OX2][FX1,ClX1,BrX1,IX1]
    141Carbonic acid monoester[#6;!$(C=[O,N,S])][OX2;!R][CX3](=[OX1])[$([OX2H]),$([OX1-])]
    142Carbonic acid derivatives[!#6][#6X3](=[!#6])[!#6]
    143Thiocarbonic acid dieester[#6;!$(C=[O,N,S])][#8X2][#6X3](=[SX1])[#8X2][#6;!$(C=[O,N,S])]
    144Thiocarbonic acid esterhalide[#6;!$(C=[O,N,S])][OX2;!R][CX3](=[SX1])[OX2][FX1,ClX1,BrX1,IX1]
    145Thiocarbonic acid monoester[#6;!$(C=[O,N,S])][OX2;!R][CX3](=[SX1])[$([OX2H]),$([OX1-])]
    146Urea[#7X3;!$([#7][!#6])][#6X3](=[OX1])[#7X3;!$([#7][!#6])]
    147Thiourea[#7X3;!$([#7][!#6])][#6X3](=[SX1])[#7X3;!$([#7][!#6])]
    148Isourea[#7X2;!$([#7][!#6])]=,:[#6X3]([#8X2&!$([#8][!#6]),OX1-])[#7X3;!$([#7][!#6])]
    149Isothiourea[#7X2;!$([#7][!#6])]=,:[#6X3]([#16X2&!$([#16][!#6]),SX1-])[#7X3;!$([#7][!#6])]
    150Guanidine[N;v3X3,v4X4+][CX3](=[N;v3X2,v4X3+])[N;v3X3,v4X4+]
    151Carbaminic acid[NX3]C(=[OX1])[O;X2H,X1-]
    152Urethan[#7X3][#6](=[OX1])[#8X2][#6]
    153Biuret[#7X3][#6](=[OX1])[#7X3][#6](=[OX1])[#7X3]
    154Semicarbazide[#7X3][#7X3][#6X3]([#7X3;!$([#7][#7])])=[OX1]
    155Carbazide[#7X3][#7X3][#6X3]([#7X3][#7X3])=[OX1]
    156Semicarbazone[#7X2](=[#6])[#7X3][#6X3]([#7X3;!$([#7][#7])])=[OX1]
    157Carbazone[#7X2](=[#6])[#7X3][#6X3]([#7X3][#7X3])=[OX1]
    158Thiosemicarbazide[#7X3][#7X3][#6X3]([#7X3;!$([#7][#7])])=[SX1]
    159Thiocarbazide[#7X3][#7X3][#6X3]([#7X3][#7X3])=[SX1]
    160Thiosemicarbazone[#7X2](=[#6])[#7X3][#6X3]([#7X3;!$([#7][#7])])=[SX1]
    161Thiocarbazone[#7X2](=[#6])[#7X3][#6X3]([#7X3][#7X3])=[SX1]
    162Isocyanate[NX2]=[CX2]=[OX1]
    163Cyanate[OX2][CX2]#[NX1]
    164Isothiocyanate[NX2]=[CX2]=[SX1]
    165Thiocyanate[SX2][CX2]#[NX1]
    166Carbodiimide[NX2]=[CX2]=[NX2]
    167Orthocarbonic derivatives[CX4H0]([O,S,#7])([O,S,#7])([O,S,#7])[O,S,#7,F,Cl,Br,I]
    168Phenol[OX2H][c]
    1691,2-Diphenol[OX2H][c][c][OX2H]
    170Arylchloride[Cl][c]
    171Arylfluoride[F][c]
    172Arylbromide[Br][c]
    173Aryliodide[I][c]
    174Arylthiol[SX2H][c]
    175Iminoarene[c]=[NX2;$([H1]),$([H0][#6;!$([C]=[N,S,O])])]
    176Oxoarene[c]=[OX1]
    177Thioarene[c]=[SX1]
    178Hetero N basic H[nX3H1+0]
    179Hetero N basic no H[nX3H0+0]
    180Hetero N nonbasic[nX2,nX3+]
    181Hetero O[o]
    182Hetero S[sX2]
    183Heteroaromatic[a;!c]
    184Nitrite[NX2](=[OX1])[O;$([X2]),$([X1-])]
    185Thionitrite[SX2][NX2]=[OX1]
    186Nitrate[$([NX3](=[OX1])(=[OX1])[O;$([X2]),$([X1-])]),$([NX3+]([OX1-])(=[OX1])[O;$([X2]),$([X1-])])]
    187Nitro[$([NX3](=O)=O),$([NX3+](=O)[O-])][!#8]
    188Nitroso[NX2](=[OX1])[!#7;!#8]
    189Azide[NX1]~[NX2]~[NX2,NX1]
    190Acylazide[CX3](=[OX1])[NX2]~[NX2]~[NX1]
    191Diazo[$([#6]=[NX2+]=[NX1-]),$([#6-]-[NX2+]#[NX1])]
    192Diazonium[#6][NX2+]#[NX1]
    193Nitrosamine[#7;!$(N*=O)][NX2]=[OX1]
    194Nitrosamide[NX2](=[OX1])N-*=O
    195N-Oxide[$([#7+][OX1-]),$([#7v5]=[OX1]);!$([#7](~[O])~[O]);!$([#7]=[#7])]
    196Hydrazine[NX3;$([H2]),$([H1][#6]),$([H0]([#6])[#6]);!$(NC=[O,N,S])][NX3;$([H2]),$([H1][#6]),$([H0]([#6])[#6]);!$(NC=[O,N,S])]
    197Hydrazone[NX3;$([H2]),$([H1][#6]),$([H0]([#6])[#6]);!$(NC=[O,N,S])][NX2]=[#6]
    198Hydroxylamine[NX3;$([H2]),$([H1][#6]),$([H0]([#6])[#6]);!$(NC=[O,N,S])][OX2;$([H1]),$(O[#6;!$(C=[N,O,S])])]
    199Sulfon[$([SX4](=[OX1])(=[OX1])([#6])[#6]),$([SX4+2]([OX1-])([OX1-])([#6])[#6])]
    200Sulfoxide[$([SX3](=[OX1])([#6])[#6]),$([SX3+]([OX1-])([#6])[#6])]
    201Sulfonium[S+;!$([S]~[!#6]);!$([S]*~[#7,#8,#15,#16])]
    202Sulfuric acid[SX4](=[OX1])(=[OX1])([$([OX2H]),$([OX1-])])[$([OX2H]),$([OX1-])]
    203Sulfuric monoester[SX4](=[OX1])(=[OX1])([$([OX2H]),$([OX1-])])[OX2][#6;!$(C=[O,N,S])]
    204Sulfuric diester[SX4](=[OX1])(=[OX1])([OX2][#6;!$(C=[O,N,S])])[OX2][#6;!$(C=[O,N,S])]
    205Sulfuric 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-])]
    206Sulfuric 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])])]
    207Sulfuric esteramide[SX4](=[OX1])(=[OX1])([#7X3][#6;!$(C=[O,N,S])])[OX2][#6;!$(C=[O,N,S])]
    208Sulfuric derivative[SX4D4](=[!#6])(=[!#6])([!#6])[!#6]
    209Sulfonic acid[SX4;$([H1]),$([H0][#6])](=[OX1])(=[OX1])[$([OX2H]),$([OX1-])]
    210Sulfonamide[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])])]
    211Sulfonic ester[SX4;$([H1]),$([H0][#6])](=[OX1])(=[OX1])[OX2][#6;!$(C=[O,N,S])]
    212Sulfonic halide[SX4;$([H1]),$([H0][#6])](=[OX1])(=[OX1])[FX1,ClX1,BrX1,IX1]
    213Sulfonic derivative[SX4;$([H1]),$([H0][#6])](=[!#6])(=[!#6])[!#6]
    214Sulfinic acid[SX3;$([H1]),$([H0][#6])](=[OX1])[$([OX2H]),$([OX1-])]
    215Sulfinic amide[SX3;$([H1]),$([H0][#6])](=[OX1])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]
    216Sulfinic ester[SX3;$([H1]),$([H0][#6])](=[OX1])[OX2][#6;!$(C=[O,N,S])]
    217Sulfinic halide[SX3;$([H1]),$([H0][#6])](=[OX1])[FX1,ClX1,BrX1,IX1]
    218Sulfinic derivative[SX3;$([H1]),$([H0][#6])](=[!#6])[!#6]
    219Sulfenic acid[SX2;$([H1]),$([H0][#6])][$([OX2H]),$([OX1-])]
    220Sulfenic amide[SX2;$([H1]),$([H0][#6])][#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]
    221Sulfenic ester[SX2;$([H1]),$([H0][#6])][OX2][#6;!$(C=[O,N,S])]
    222Sulfenic halide[SX2;$([H1]),$([H0][#6])][FX1,ClX1,BrX1,IX1]
    223Sulfenic derivative[SX2;$([H1]),$([H0][#6])][!#6]
    224Phosphine[PX3;$([H3]),$([H2][#6]),$([H1]([#6])[#6]),$([H0]([#6])([#6])[#6])]
    225Phosphine oxide[PX4;$([H3]=[OX1]),$([H2](=[OX1])[#6]),$([H1](=[OX1])([#6])[#6]),$([H0](=[OX1])([#6])([#6])[#6])]
    226Phosphonium[P+;!$([P]~[!#6]);!$([P]*~[#7,#8,#15,#16])]
    227Phosphorylen[PX4;$([H3]=[CX3]),$([H2](=[CX3])[#6]),$([H1](=[CX3])([#6])[#6]),$([H0](=[CX3])([#6])([#6])[#6])]
    228Phosphonic acid[PX4;$([H1]),$([H0][#6])](=[OX1])([$([OX2H]),$([OX1-])])[$([OX2H]),$([OX1-])]
    229Phosphonic monoester[PX4;$([H1]),$([H0][#6])](=[OX1])([$([OX2H]),$([OX1-])])[OX2][#6;!$(C=[O,N,S])]
    230Phosphonic diester[PX4;$([H1]),$([H0][#6])](=[OX1])([OX2][#6;!$(C=[O,N,S])])[OX2][#6;!$(C=[O,N,S])]
    231Phosphonic 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])])]
    232Phosphonic 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])])]
    233Phosphonic 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;!$(C=[O,N,S])])]
    234Phosphonic acid derivative[PX4;$([H1]),$([H0][#6])](=[!#6])([!#6])[!#6]
    235Phosphoric acid[PX4D4](=[OX1])([$([OX2H]),$([OX1-])])([$([OX2H]),$([OX1-])])[$([OX2H]),$([OX1-])]
    236Phosphoric monoester[PX4D4](=[OX1])([$([OX2H]),$([OX1-])])([$([OX2H]),$([OX1-])])[OX2][#6;!$(C=[O,N,S])]
    237Phosphoric diester[PX4D4](=[OX1])([$([OX2H]),$([OX1-])])([OX2][#6;!$(C=[O,N,S])])[OX2][#6;!$(C=[O,N,S])]
    238Phosphoric triester[PX4D4](=[OX1])([OX2][#6;!$(C=[O,N,S])])([OX2][#6;!$(C=[O,N,S])])[OX2][#6;!$(C=[O,N,S])]
    239Phosphoric monoamide[PX4D4](=[OX1])([$([OX2H]),$([OX1-])])([$([OX2H]),$([OX1-])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]
    240Phosphoric diamide[PX4D4](=[OX1])([$([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;!$(C=[O,N,S])])]
    241Phosphoric triamide[PX4D4](=[OX1])([#7X3;$([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;!$(C=[O,N,S])])]
    242Phosphoric monoestermonoamide[PX4D4](=[OX1])([$([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])])]
    243Phosphoric 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])])]
    244Phosphoric 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;!$(C=[O,N,S])])]
    245Phosphoric acid derivative[PX4D4](=[!#6])([!#6])([!#6])[!#6]
    246Phosphinic acid[PX4;$([H2]),$([H1][#6]),$([H0]([#6])[#6])](=[OX1])[$([OX2H]),$([OX1-])]
    247Phosphinic ester[PX4;$([H2]),$([H1][#6]),$([H0]([#6])[#6])](=[OX1])[OX2][#6;!$(C=[O,N,S])]
    248Phosphinic amide[PX4;$([H2]),$([H1][#6]),$([H0]([#6])[#6])](=[OX1])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]
    249Phosphinic acid derivative[PX4;$([H2]),$([H1][#6]),$([H0]([#6])[#6])](=[!#6])[!#6]
    250Phosphonous acid[PX3;$([H1]),$([H0][#6])]([$([OX2H]),$([OX1-])])[$([OX2H]),$([OX1-])]
    251Phosphonous monoester[PX3;$([H1]),$([H0][#6])]([$([OX2H]),$([OX1-])])[OX2][#6;!$(C=[O,N,S])]
    252Phosphonous diester[PX3;$([H1]),$([H0][#6])]([OX2][#6;!$(C=[O,N,S])])[OX2][#6;!$(C=[O,N,S])]
    253Phosphonous monoamide[PX3;$([H1]),$([H0][#6])]([$([OX2H]),$([OX1-])])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]
    254Phosphonous diamide[PX3;$([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;!$(C=[O,N,S])])]
    255Phosphonous esteramide[PX3;$([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])])]
    256Phosphonous derivatives[PX3;$([D2]),$([D3][#6])]([!#6])[!#6]
    257Phosphinous acid[PX3;$([H2]),$([H1][#6]),$([H0]([#6])[#6])][$([OX2H]),$([OX1-])]
    258Phosphinous ester[PX3;$([H2]),$([H1][#6]),$([H0]([#6])[#6])][OX2][#6;!$(C=[O,N,S])]
    259Phosphinous amide[PX3;$([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])])]
    260Phosphinous derivatives[PX3;$([H2]),$([H1][#6]),$([H0]([#6])[#6])][!#6]
    261Quart silane[SiX4]([#6])([#6])([#6])[#6]
    262Non-quart silane[SiX4;$([H1]([#6])([#6])[#6]),$([H2]([#6])[#6]),$([H3][#6]),$([H4])]
    263Silylmonohalide[SiX4]([FX1,ClX1,BrX1,IX1])([#6])([#6])[#6]
    264Het trialkylsilane[SiX4]([!#6])([#6])([#6])[#6]
    265Dihet dialkylsilane[SiX4]([!#6])([!#6])([#6])[#6]
    266Trihet alkylsilane[SiX4]([!#6])([!#6])([!#6])[#6]
    267Silicic acid derivative[SiX4]([!#6])([!#6])([!#6])[!#6]
    268Trialkylborane[BX3]([#6])([#6])[#6]
    269Boric acid derivatives[BX3]([!#6])([!#6])[!#6]
    270Boronic acid derivative[BX3]([!#6])([!#6])[!#6]
    271Borohydride[BH1,BH2,BH3,BH4]
    272Quaternary boron[BX4]
    273Aromatica
    274Heterocyclic[!#6;!R0]
    275Epoxide[OX2r3]1[#6r3][#6r3]1
    276NH aziridine[NX3H1r3]1[#6r3][#6r3]1
    277Spiro[D4R;$(*(@*)(@*)(@*)@*)]
    278Annelated rings[R;$(*(@*)(@*)@*);!$([R2;$(*(@*)(@*)(@*)@*)])]@[R;$(*(@*)(@*)@*);!$([R2;$(*(@*)(@*)(@*)@*)])]
    279Bridged rings[R;$(*(@*)(@*)@*);!$([D4R;$(*(@*)(@*)(@*)@*)]);!$([R;$(*(@*)(@*)@*);!$([R2;$(*(@*)(@*)(@*)@*)])]@[R;$(*(@*)(@*)@*);!$([R2;$(*(@*)(@*)(@*)@*)])])]
    280Sugar pattern 1[OX2;$([r5]1@C@C@C(O)@C1),$([r6]1@C@C@C(O)@C(O)@C1)]
    281Sugar 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)]
    282Sugar 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)]
    283Sugar pattern 2 reducing[OX2;$([r5]1@C(!@[OX2H1])@C@C@C1),$([r6]1@C(!@[OX2H1])@C@C@C@C1)]
    284Sugar 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)]
    285Sugar 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)]
    286Conjugated double bond*=*[*]=,#,:[*]
    287Conjugated tripple bond*#*[*]=,#,:[*]
    288Cis double bond*&#47[D2]=[D2]/*
    289Trans double bond*&#47[D2]=[D2]/*
    290Mixed anhydrides[$(*=O),$([#16,#14,#5]),$([#7]([#6]=[OX1]))][#8X2][$(*=O),$([#16,#14,#5]),$([#7]([#6]=[OX1]))]
    291Halogen on hetero[FX1,ClX1,BrX1,IX1][!#6]
    292Halogen multi subst[F,Cl,Br,I;!$([X1]);!$([X0-])]
    293Trifluoromethyl[FX1][CX4;!$([H0][Cl,Br,I]);!$([F][C]([F])([F])[F])]([FX1])([FX1])
    294C ONS bond[#6]~[#7,#8,#16]
    295Charged[!+0]
    296Anion[-1,-2,-3,-4,-5,-6,-7]
    297Kation[+1,+2,+3,+4,+5,+6,+7]
    298Salt([-1,-2,-3,-4,-5,-6,-7]).([+1,+2,+3,+4,+5,+6,+7])
    2991,3-Tautomerizable[$([#7X2,OX1,SX1]=*[!H0;!$([a;!n])]),$([#7X3,OX2,SX2;!H0]*=*),$([#7X3,OX2,SX2;!H0]*:n)]
    3001,5-Tautomerizable[$([#7X2,OX1,SX1]=,:**=,:*[!H0;!$([a;!n])]),$([#7X3,OX2,SX2;!H0]*=**=*),$([#7X3,OX2,SX2;!H0]*=,:**:n)]
    301Rotatable bond[!$(*#*)&!D1]-!@[!$(*#*)&!D1]
    302Michael acceptor[CX3]=[CX3][$([CX3]=[O,N,S]),$(C#[N]),$([S,P]=[OX1]),$([NX3]=O),$([NX3+](=O)[O-])]
    303Dicarbodiazene[CX3](=[OX1])[NX2]=[NX2][CX3](=[OX1])
    304CH-acidic[$([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;!$([H0])]1[CX3]=[CX3][CX3]=[CX3]1)]
    305CH-acidic strong[CX4;!$([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]);!$([*+0][S,O;X1-])]
    306Chiral center specified[$([*@](~*)(~*)(*)*),$([*@H](*)(*)*),$([*@](~*)(*)*),$([*@H](~*)~*)]
    Author:
    egonw
    Source code:
    main
    Belongs to CDK module:
    fingerprint
    Keywords:
    fingerprint, similarity
    Created on:
    2005-12-30
    • Constructor Detail

      • SubstructureFingerprinter

        public SubstructureFingerprinter​(String[] smarts)
        Set up the fingerprinter to use a user-defined set of fragments.
        Parameters:
        smarts - The collection of fragments to look for
      • SubstructureFingerprinter

        public SubstructureFingerprinter()
        Set up the fingerprinter to use the fragments from StandardSubstructureSets.
    • Method Detail

      • getRawFingerprint

        public Map<String,​Integer> getRawFingerprint​(IAtomContainer iAtomContainer)
                                                    throws CDKException
        Returns the raw representation of the fingerprint for the given IAtomContainer. The raw representation contains counts as well as the key strings.
        Specified by:
        getRawFingerprint in interface IFingerprinter
        Parameters:
        iAtomContainer - IAtomContainer for which the fingerprint should be calculated.
        Returns:
        the raw fingerprint
        Throws:
        CDKException
      • getSize

        public int getSize()
        Returns the size (or length) of the fingerprint.
        Specified by:
        getSize in interface IFingerprinter
        Returns:
        the size of the fingerprint
      • getSubstructure

        public String getSubstructure​(int bitIndex)
        Retrieves the SMARTS representation of a substructure for a given bit in the fingerprint.
        Parameters:
        bitIndex -
        Returns:
        SMARTS representation of substructure at index bitIndex.