chematic-chem 0.4.30

//! PAINS (Pan Assay Interference Compounds) structural alert filtering.
//
//! 480 SMARTS patterns from Baell & Holloway 2010 (J. Med. Chem. 53, 2719–2740)
//! as distributed in the RDKit FilterCatalog (pains_a/b/c.in).

use rustc_hash::FxHashMap;
use std::sync::OnceLock;

use chematic_core::{
    Atom, AtomIdx, BondOrder, Element, Molecule, MoleculeBuilder, implicit_hcount,
};
use chematic_perception::find_sssr;
use chematic_smarts::{
    MatchConfig, QueryMolecule, find_matches_with_rings_and_config, parse_smarts,
};

/// Return a copy of `mol` with all implicit H atoms materialized as explicit
/// graph nodes.  PAINS patterns (and many RDKit SMARTS) are written for
/// molecules in explicit-H form; this helper enables correct matching.
fn add_explicit_hs(mol: &Molecule) -> Molecule {
    let mut builder = MoleculeBuilder::new();

    for (_, atom) in mol.atoms() {
        builder.add_atom(atom.clone());
    }
    for (_, bond) in mol.bonds() {
        builder
            .add_bond(bond.atom1, bond.atom2, bond.order)
            .unwrap();
    }

    let h_elem = Element::from_symbol("H").unwrap();
    let n = mol.atom_count();
    for i in 0..n {
        let idx = AtomIdx(i as u32);
        let h_count = implicit_hcount(mol, idx) as usize;
        for _ in 0..h_count {
            let h_idx = builder.add_atom(Atom::new(h_elem));
            builder.add_bond(idx, h_idx, BondOrder::Single).unwrap();
        }
    }

    builder.build()
}

// (name, SMARTS)
const PAINS_SMARTS: &[(&str, &str)] = &[
    (
        "ene_six_het_A(483)",
        "[#6]-1(-[#6](~[!#6&!#1]~[#6]-[!#6&!#1]-[#6]-1=[!#6&!#1])~[!#6&!#1])=[#6;!R]-[#1]",
    ),
    (
        "hzone_phenol_A(479)",
        "c:1:c:c(:c(:c:c:1)-[#6]=[#7]-[#7])-[#8]-[#1]",
    ),
    (
        "anil_di_alk_A(478)",
        "[#6](-[#1])(-[#1])-[#7](-[#6](-[#1])-[#1])-c:1:c:c(:c(:[c;!H0,$(c-[#6](-[#1])-[#1]),$(c-[#8]-[#6](-[#1])(-[#1])-[#6](-[#1])-[#1])](:c:1))-[#7])-[#1]",
    ),
    (
        "indol_3yl_alk(461)",
        "[n;!H0,$(n-[#6;!H0;!H1])]:1(c(c(c:2:c:1:c:c:c:c:2-[#1])-[#6;X4]-[#1])-[$([#6](-[#1])-[#1]),$([#6]=,:[!#6&!#1]),$([#6](-[#1])-[#7]),$([#6](-[#1])(-[#6](-[#1])-[#1])-[#6](-[#1])(-[#1])-[#7](-[#1])-[#6](-[#1])-[#1])])",
    ),
    (
        "quinone_A(370)",
        "[!#6&!#1]=[#6]1[#6]=,:[#6][#6](=[!#6&!#1])[#6]=,:[#6]1",
    ),
    ("azo_A(324)", "[#7;!R]=[#7]"),
    (
        "imine_one_A(321)",
        "[#6]-[#6](=[!#6&!#1;!R])-[#6](=[!#6&!#1;!R])-[$([#6]),$([#16](=[#8])=[#8])]",
    ),
    ("mannich_A(296)", "[#7]-[#6;X4]-c:1:c:c:c:c:c:1-[#8]-[#1]"),
    (
        "anil_di_alk_B(251)",
        "c:1:c:c(:c:c:c:1-[#7](-[#6;X4])-[#6;X4])-[#6]=[#6]",
    ),
    (
        "anil_di_alk_C(246)",
        "c:1:c:c(:c:c:c:1-[#8]-[#6;X4])-[#7;$([#7!H0]-[#6;X4]),$([#7](-[#6;X4])-[#6;X4])]",
    ),
    (
        "ene_rhod_A(235)",
        "[#7]-1-[#6](=[#16])-[#16]-[#6](=[#6])-[#6]-1=[#8]",
    ),
    (
        "hzone_phenol_B(215)",
        "c:1(:c:c:c(:c:c:1)-[#6]=[#7]-[#7])-[#8]-[#1]",
    ),
    (
        "ene_five_het_A(201)",
        "[#6]-1(=[#6])-[#6]=[#7]-[!#6&!#1]-[#6]-1=[#8]",
    ),
    (
        "anil_di_alk_D(198)",
        "c:1:c:c(:c:c:c:1-[#7](-[#6;X4])-[#6;X4])-[#6;X4]-[$([#8]-[#1]),$([#6]=[#6]-[#1]),$([#7](-[#6X4])-[#6;X4])]",
    ),
    (
        "imine_one_isatin(189)",
        "[#8]=[#6]-2-[#6](=!@[#7]-[#7])-c:1:c:c:c:c:c:1-[#7]-2",
    ),
    (
        "anil_di_alk_E(186)",
        "[#6](-[#1])-[#7](-[#6](-[#1])-[#1])-c:1:c(:c(:c(:[c;!H0,$(c-[#6](-[#1])-[#1])](:c:1-[#1]))-[#6&!H0;!H1,$([#6]-[#6;!H0])])-[#1])-[#1]",
    ),
    (
        "thiaz_ene_A(128)",
        "[#6]-,:1(=,:[#6;!H0,$([#6]-[#6;!H0;!H1]),$([#6]-[#6]=[#8])]-,:[#16]-,:[#6](-,:[#7;!H0,$([#7]-[#6;!H0]),$([#7]-[#6]:[#6])]-,:1)=[#7;!R])-[$([#6](-[#1])-[#1]),$([#6]:[#6])]",
    ),
    (
        "pyrrole_A(118)",
        "n2(-[#6]:1:[!#1]:[#6]:[#6]:[#6]:[#6]:1)c(cc(c2-[#6;X4])-[#1])-[#6;X4]",
    ),
    ("catechol_A(92)", "c:1:c:c(:c(:c:c:1)-[#8]-[#1])-[#8]-[#1]"),
    (
        "ene_five_het_B(90)",
        "[#6]-1(=[#6])-[#6](-[#7]=[#6]-[#16]-1)=[#8]",
    ),
    (
        "imine_one_fives(89)",
        "[#6]-1=[!#1]-[!#6&!#1]-[#6](-[#6]-1=[!#6&!#1;!R])=[#8]",
    ),
    (
        "ene_five_het_C(85)",
        "[#6]-1(-[#6](-[#6]=[#6]-[!#6&!#1]-1)=[#6])=[!#6&!#1]",
    ),
    (
        "hzone_pipzn(79)",
        "[#6]-[#7]-1-[#6](-[#1])(-[#1])-[#6](-[#1])(-[#1])-[#7](-[#6](-[#1])(-[#1])-[#6]-1(-[#1])-[#1])-[#7]=[#6](-[#1])-[#6]:[!#1]",
    ),
    (
        "keto_keto_beta_A(68)",
        "c:1-2:c(:c:c:c:c:1)-[#6](=[#8])-[#6;X4]-[#6]-2=[#8]",
    ),
    (
        "hzone_pyrrol(64)",
        "n1(-[#6])c(c(-[#1])c(c1-[#6]=[#7]-[#7])-[#1])-[#1]",
    ),
    (
        "ene_one_ene_A(57)",
        "[#6]=!@[#6](-[!#1])-@[#6](=!@[!#6&!#1])-@[#6](=!@[#6])-[!#1]",
    ),
    (
        "cyano_ene_amine_A(56)",
        "[#6](-[#6]#[#7])(-[#6]#[#7])-[#6](-[#7](-[#1])-[#1])=[#6]-[#6]#[#7]",
    ),
    (
        "ene_five_one_A(55)",
        "c:1-2:c(:c:c:c:c:1)-[#6](=[#8])-[#6](=[#6])-[#6]-2=[#8]",
    ),
    (
        "cyano_pyridone_A(54)",
        "[#6]-,:1(=,:[!#1]-,:[!#1]=,:[!#1]-,:[#7](-,:[#6]-,:1=[#16])-[#1])-[#6]#[#7]",
    ),
    (
        "anil_alk_ene(51)",
        "c:1:c:c-2:c(:c:c:1)-[#6]-3-[#6](-[#6]-[#7]-2)-[#6]-[#6]=[#6]-3",
    ),
    (
        "amino_acridine_A(46)",
        "c:1:c:2:c(:c:c:c:1):n:c:3:c(:c:2-[#7]):c:c:c:c:3",
    ),
    (
        "ene_five_het_D(46)",
        "[#6]-1(=[#6])-[#6](=[#8])-[#7]-[#7]-[#6]-1=[#8]",
    ),
    (
        "thiophene_amino_Aa(45)",
        "[#7](-[#1])(-[#1])-c:1:c(:c(:c(:s:1)-[!#1])-[!#1])-[#6]=[#8]",
    ),
    (
        "ene_five_het_E(44)",
        "[#7]-[#6]=!@[#6]-2-[#6](=[#8])-c:1:c:c:c:c:c:1-[!#6&!#1]-2",
    ),
    (
        "sulfonamide_A(43)",
        "c:1(:c(:c(:c(:c(:c:1-[#8]-[#1])-[F,Cl,Br,I])-[#1])-[F,Cl,Br,I])-[#1])-[#16](=[#8])(=[#8])-[#7]",
    ),
    ("thio_ketone(43)", "[#6]-[#6](=[#16])-[#6]"),
    (
        "sulfonamide_B(41)",
        "c:1:c:c(:c:c:c:1-[#8]-[#1])-[#7](-[#1])-[#16](=[#8])=[#8]",
    ),
    (
        "anil_no_alk(40)",
        "c:1(:c(:c(:c(:c(:c:1-[#1])-[#1])-[$([#8]),$([#7]),$([#6](-[#1])-[#1])])-[#1])-[#1])-[#7](-[#1])-[#1]",
    ),
    (
        "thiophene_amino_Ab(40)",
        "[c;!H0,$(c-[#6](-[#1])-[#1]),$(c-[#6]:[#6])]:1:c(:c(:c(:s:1)-[#7](-[#1])-[#6](=[#8])-[#6])-[#6](=[#8])-[#8])-[$([#6]:1:[#6]:[#6]:[#6]:[#6]:[#6]:1),$([#6]:1:[#16]:[#6]:[#6]:[#6]:1)]",
    ),
    (
        "het_pyridiniums_A(39)",
        "[#7+]:1(:[#6]:[#6]:[!#1]:c:2:c:1:c(:[c;!H0,$(c-[#7])]:c:c:2)-[#1])-[$([#6](-[#1])(-[#1])-[#1]),$([#8;X1]),$([#6](-[#1])(-[#1])-[#6](-[#1])=[#6](-[#1])-[#1]),$([#6](-[#1])(-[#1])-[#6](-[#1])(-[#1])-[#8]-[#1]),$([#6](-[#1])(-[#1])-[#6](=[#8])-[#6]),$([#6](-[#1])(-[#1])-[#6](=[#8])-[#7](-[#1])-[#6]:[#6]),$([#6](-[#1])(-[#1])-[#6](-[#1])(-[#1])-[#1])]",
    ),
    (
        "anthranil_one_A(38)",
        "c:1:c:c:c:c(:c:1-[#7&!H0;!H1,!$([#7]-[#6]=[#8])])-[#6](-[#6]:[#6])=[#8]",
    ),
    (
        "cyano_imine_A(37)",
        "[#7](-[#1])-[#7]=[#6](-[#6]#[#7])-[#6]=[!#6&!#1;!R]",
    ),
    (
        "diazox_sulfon_A(36)",
        "[#7](-c:1:c:c:c:c:c:1)-[#16](=[#8])(=[#8])-[#6]:2:[#6]:[#6]:[#6]:[#6]:3:[#7]:[$([#8]),$([#16])]:[#7]:[#6]:2:3",
    ),
    (
        "hzone_anil_di_alk(35)",
        "[#6](-[#1])(-[#1])-[#7](-[#6](-[#1])-[#1])-c:1:c(:c(:c(:c(:c:1-[#1])-[#1])-[#6](-[#1])=[#7]-[#7]-[$([#6](=[#8])-[#6](-[#1])(-[#1])-[#16]-[#6]:[#7]),$([#6](=[#8])-[#6](-[#1])(-[#1])-[!#1]:[!#1]:[#7]),$([#6](=[#8])-[#6]:[#6]-[#8]-[#1]),$([#6]:[#7]),$([#6](-[#1])(-[#1])-[#6](-[#1])-[#8]-[#1])])-[#1])-[#1]",
    ),
    (
        "rhod_sat_A(33)",
        "[#7]-1-[#6](=[#16])-[#16]-[#6;X4]-[#6]-1=[#8]",
    ),
    (
        "hzone_enamin(30)",
        "[#7](-[#1])-[#7]=[#6]-[#6;!H0,$(*(-[#6])-[#6])]=[#6](-[#6])-!@[$([#7]),$([#8]-[#1])]",
    ),
    (
        "pyrrole_B(29)",
        "n2(-[#6]:1:[!#1]:[#6]:[#6]:[#6]:[#6]:1)c(cc(c2-[#6]:[#6])-[#1])-[#6;X4]",
    ),
    ("thiophene_hydroxy(28)", "s1ccc(c1)-[#8]-[#1]"),
    (
        "cyano_pyridone_B(27)",
        "[#6]-,:1(=,:[#6](-,:[#6](=[#8])-,:[#7]-,:[#6](=,:[#7]-,:1)-,:[!#6&!#1])-[#6]#[#7])-[#6]",
    ),
    (
        "imine_one_sixes(27)",
        "[#6]-1(-[#6](=[#8])-[#7]-[#6](=[#8])-[#7]-[#6]-1=[#8])=[#7]",
    ),
    (
        "dyes5A(27)",
        "[#6](-[#1])(-[#1])-[#7]([#6]:[#6])~[#6][#6]=,:[#6]-[#6]~[#6][#7]",
    ),
    (
        "naphth_amino_A(25)",
        "c:2:c:1:c:c:c:c-,:3:c:1:c(:c:c:2)-,:[#7]-,:[#6]=,:[#7]-,:3",
    ),
    (
        "naphth_amino_B(25)",
        "c:2:c:1:c:c:c:c-3:c:1:c(:c:c:2)-[#7](-[#6;X4]-[#7]-3-[#1])-[#1]",
    ),
    (
        "ene_one_ester(24)",
        "[#6]-[#6](=[#8])-[#6](-[#1])=[#6](-[#7](-[#1])-[#6])-[#6](=[#8])-[#8]-[#6]",
    ),
    (
        "thio_dibenzo(23)",
        "[#16]=[#6]-1-[#6]=,:[#6]-[!#6&!#1]-[#6]=,:[#6]-1",
    ),
    (
        "cyano_cyano_A(23)",
        "[#6](-[#6]#[#7])(-[#6]#[#7])-[#6](-[$([#6]#[#7]),$([#6]=[#7])])-[#6]#[#7]",
    ),
    (
        "hzone_acyl_naphthol(22)",
        "c:1:2:c(:c(:c(:c(:c:1:c(:c(:c(:c:2-[#1])-[#8]-[#1])-[#6](=[#8])-[#7](-[#1])-[#7]=[#6])-[#1])-[#1])-[#1])-[#1])-[#1]",
    ),
    (
        "het_65_A(21)",
        "[#8]=[#6]-c2c1nc(-[#6](-[#1])-[#1])cc(-[#8]-[#1])n1nc2",
    ),
    (
        "imidazole_A(19)",
        "n:1:c(:n(:c(:c:1-c:2:c:c:c:c:c:2)-c:3:c:c:c:c:c:3)-[#1])-[#6]:[!#1]",
    ),
    (
        "ene_cyano_A(19)",
        "[#6](-[#6]#[#7])(-[#6]#[#7])=[#6]-c:1:c:c:c:c:c:1",
    ),
    (
        "anthranil_acid_A(19)",
        "c:1(:c:c:c:c:c:1-[#7](-[#1])-[#7]=[#6])-[#6](=[#8])-[#8]-[#1]",
    ),
    (
        "dyes3A(19)",
        "[#7+]([#6]:[#6])=,:[#6]-[#6](-[#1])=[#6]-[#7](-[#6;X4])-[#6]",
    ),
    (
        "dhp_bis_amino_CN(19)",
        "[#7](-[#1])(-[#1])-[#6]-1=[#6](-[#6]#[#7])-[#6](-[#1])(-[#6]:[#6])-[#6](=[#6](-[#7](-[#1])-[#1])-[#16]-1)-[#6]#[#7]",
    ),
    (
        "het_6_tetrazine(18)",
        "[#7]~[#6]:1:[#7]:[#7]:[#6](:[$([#7]),$([#6]-[#1]),$([#6]-[#7]-[#1])]:[$([#7]),$([#6]-[#7])]:1)-[$([#7]-[#1]),$([#8]-[#6](-[#1])-[#1])]",
    ),
    (
        "ene_one_hal(17)",
        "[#6]-[#6]=[#6](-[F,Cl,Br,I])-[#6](=[#8])-[#6]",
    ),
    (
        "cyano_imine_B(17)",
        "[#6](-[#6]#[#7])(-[#6]#[#7])=[#7]-[#7](-[#1])-c:1:c:c:c:c:c:1",
    ),
    (
        "thiaz_ene_B(17)",
        "[#6]-,:1(=,:[#6](-!@[#6](=[#8])-[#7]-[#6](-[#1])-[#1])-,:[#16]-,:[#6](-,:[#7]-,:1-,:[$([#6](-[#1])(-[#1])-[#6](-[#1])=[#6](-[#1])-[#1]),$([#6]:[#6])])=[#16])-,:[$([#7]-[#6](=[#8])-[#6]:[#6]),$([#7](-[#1])-[#1])]",
    ),
    (
        "ene_rhod_B(16)",
        "[#16]-1-[#6](=[#8])-[#7]-[#6](=[#8])-[#6]-1=[#6](-[#1])-[$([#6]-[#35]),$([#6]:[#6](-[#1]):[#6](-[F,Cl,Br,I]):[#6]:[#6]-[F,Cl,Br,I]),$([#6]:[#6](-[#1]):[#6](-[#1]):[#6]-[#16]-[#6](-[#1])-[#1]),$([#6]:[#6]:[#6]:[#6]:[#6]:[#6]:[#6]:[#6]:[#6]:[#6]-[#8]-[#6](-[#1])-[#1]),$([#6]:1:[#6](-[#6](-[#1])-[#1]):[#7](-[#6](-[#1])-[#1]):[#6](-[#6](-[#1])-[#1]):[#6]:1)]",
    ),
    (
        "thio_carbonate_A(15)",
        "[#8]-,:1-,:[#6](-,:[#16]-,:c:2:c-,:1:c:c:c(:c:2)-,:[$([#7]),$([#8])])=[$([#8]),$([#16])]",
    ),
    (
        "anil_di_alk_furan_A(15)",
        "[#7](-[#6](-[#1])-[#1])(-[#6](-[#1])-[#1])-c:1:c(:c(:c(:o:1)-[#6]=[#7]-[#7](-[#1])-[#6]=[!#6&!#1])-[#1])-[#1]",
    ),
    (
        "ene_five_het_F(15)",
        "c:1(:c:c:c:c:c:1)-[#6](-[#1])=!@[#6]-3-[#6](=[#8])-c:2:c:c:c:c:c:2-[#16]-3",
    ),
    (
        "anil_di_alk_F(14)",
        "c:1:c:c(:c:c:c:1-[#6;X4]-c:2:c:c:c(:c:c:2)-[#7&H2,$([#7;!H0]-[#6;X4]),$([#7](-[#6X4])-[#6X4])])-[#7&H2,$([#7;!H0]-[#6;X4]),$([#7](-[#6X4])-[#6X4])]",
    ),
    (
        "hzone_anil(14)",
        "c:1(:c(:c(:c(:c(:c:1-[#1])-[#1])-[#7](-[#1])-[#1])-[#1])-[#1])-[#6]=[#7]-[#7]-[#1]",
    ),
    (
        "het_5_pyrazole_OH(14)",
        "c1(nn(c([c;!H0,$(c-[#6;!H0])]1)-[#8]-[#1])-c:2:c(:c(:c(:c(:c:2-[#1])-[#1])-[#1])-[#1])-[#1])-[#6;X4]",
    ),
    (
        "het_thio_666_A(13)",
        "c:2(:c:1-[#16]-c:3:c(-[#7;!H0,$([#7]-[CH3]),$([#7]-[#6;!H0;!H1]-[#6;!H0])](-c:1:c(:c(:c:2-[#1])-[#1])-[#1])):[c;!H0,$(c~[#7](-[#1])-[#6;X4]),$(c(cc)(cc)~[#6]:[#6])](:[c;!H0,$(c(cc)(cc)~[#6]:[#6])]:[c;!H0,$(c-[#7](-[#1])-[#1]),$(c-[#8]-[#6;X4])]:c:3-[#1]))-[#1]",
    ),
    (
        "styrene_A(13)",
        "[#6]-2-[#6]-c:1:c(:c:c:c:c:1)-[#6](-c:3:c:c:c:c:c-2:3)=[#6]-[#6]",
    ),
    (
        "ene_rhod_C(13)",
        "[#16]-1-[#6](=[#7]-[#6]:[#6])-[#7;!H0,$([#7]-[#6](-[#1])(-[#1])-[#6](-[#1])(-[#1])-[#8]),$([#7]-[#6]:[#6])]-[#6](=[#8])-[#6]-1=[#6](-[#1])-[$([#6]:[#6]:[#6]-[#17]),$([#6]:[!#6&!#1])]",
    ),
    (
        "dhp_amino_CN_A(13)",
        "[#7](-[#1])(-[#1])-[#6]-1=[#6](-[#6]#[#7])-[#6](-[#1])(-[#6]:[#6])-[#6](=[#6](-[#6]=[#6])-[#8]-1)-[#6](-[#1])-[#1]",
    ),
    (
        "cyano_imine_C(12)",
        "[#8]=[#16](=[#8])-[#6](-[#6]#[#7])=[#7]-[#7]-[#1]",
    ),
    (
        "thio_urea_A(12)",
        "c:1:c:c:c:c:c:1-[#7](-[#1])-[#6](=[#16])-[#7](-[#1])-[#6](-[#1])(-[#1])-[#6](-[#1])(-[#1])-[#6](-[#1])(-[#1])-[#7](-[#6](-[#1])-[#1])-c:2:c:c:c:c:c:2",
    ),
    (
        "thiophene_amino_B(12)",
        "c:1:c(:c:c:c:c:1)-[#7](-[#1])-c:2:c(:c(:c(:s:2)-[$([#6]=[#8]),$([#6]#[#7]),$([#6](-[#8]-[#1])=[#6])])-[#7])-[$([#6]#[#7]),$([#6](:[#7]):[#7])]",
    ),
    (
        "keto_keto_beta_B(12)",
        "[#6;X4]-1-[#6](=[#8])-[#7]-[#7]-[#6]-1=[#8]",
    ),
    (
        "keto_phenone_A(11)",
        "c:1:c-3:c(:c:c:c:1)-[#6]:2:[#7]:[!#1]:[#6]:[#6]:[#6]:2-[#6]-3=[#8]",
    ),
    (
        "cyano_pyridone_C(11)",
        "[#6]-1(-[#6](=[#6](-[#6]#[#7])-[#6](~[#8])~[#7]~[#6]-1~[#8])-[#6](-[#1])-[#1])=[#6](-[#1])-[#6]:[#6]",
    ),
    (
        "thiaz_ene_C(11)",
        "[#6]-,:1(=,:[#6](-!@[#6]=[#7])-,:[#16]-,:[#6](-,:[#7]-,:1)=[#8])-[$([F,Cl,Br,I]),$([#7+](:[#6]):[#6])]",
    ),
    (
        "hzone_thiophene_A(11)",
        "c:1:2:c(:c(:c(:c(:c:1-[#1])-[#1])-[#1])-[#1]):[!#6&!#1]:[#6;!H0,$([#6]-[OH]),$([#6]-[#6;H2,H3])](:[#6]:2-[#6](-[#1])=[#7]-[#7](-[#1])-[$([#6]:1:[#7]:[#6]:[#6](-[#1]):[#16]:1),$([#6]:[#6](-[#1]):[#6]-[#1]),$([#6]:[#7]:[#6]:[#7]:[#6]:[#7]),$([#6]:[#7]:[#7]:[#7]:[#7])])",
    ),
    (
        "ene_quin_methide(10)",
        "[!#1]:[!#1]-[#6;!H0,$([#6]-[#6]#[#7])]=[#6]-1-[#6]=,:[#6]-[#6](=[$([#8]),$([#7;!R])])-[#6]=,:[#6]-1",
    ),
    (
        "het_thio_676_A(10)",
        "c:1:c:c-2:c(:c:c:1)-[#6]-[#6](-c:3:c(-[#16]-2):c(:c(-[#1]):[c;!H0,$(c-[#8]),$(c-[#16;X2]),$(c-[#6;X4]),$(c-[#7;H2,H3,$([#7!H0]-[#6;X4]),$([#7](-[#6;X4])-[#6;X4])])](:c:3-[#1]))-[#1])-[#7;H2,H3,$([#7;!H0](-[#6])-[#6;X4]),$([#7](-[#6])(-[#6;X4])-[#6;X4])]",
    ),
    (
        "ene_five_het_G(10)",
        "[#6]-1(=[#8])-[#6](=[#6](-[#1])-[$([#6]:1:[#6]:[#6]:[#6]:[#6]:[#6]:1),$([#6]:1:[#6]:[#6]:[#6]:[!#6&!#1]:1)])-[#7]=[#6](-[!#1]:[!#1]:[!#1])-[$([#16]),$([#7]-[!#1]:[!#1])]-1",
    ),
    ("acyl_het_A(9)", "[#7+](:[!#1]:[!#1]:[!#1])-[!#1]=[#8]"),
    (
        "anil_di_alk_G(9)",
        "[#6;X4]-[#7](-[#6;X4])-c:1:c(:c(:c(:c(:c:1-[#1])-[#1])-[#6]2=,:[#7][#6]:[#6]:[!#1]2)-[#1])-[#1]",
    ),
    (
        "dhp_keto_A(9)",
        "[#7;!H0,$([#7]-[#6;X4])]-1-[#6]=,:[#6](-[#6](=[#8])-[#6]:[#6]:[#6])-[#6](-[#6])-[#6](=[#6]-1-[#6](-[#1])(-[#1])-[#1])-[$([#6]=[#8]),$([#6]#[#7])]",
    ),
    (
        "thio_urea_B(9)",
        "c:1:c:c:c:c:c:1-[#7](-[#1])-[#6](=[#16])-[#7](-[#1])-[#6](-[#1])(-[#1])-[#6](-[#1])(-[#1])-[#7](-[#6](-[#1])-[#1])-c:2:c:c:c:c:c:2",
    ),
    (
        "anil_alk_bim(9)",
        "c:1:3:c(:c(:c(:c(:c:1-[#1])-[#1])-[#7](-[#1])-[#6](-[#1])(-[#1])-c:2:c:c:c:c:c:2)-[#1]):n:c(-[#1]):n:3-[#6]",
    ),
    (
        "imine_imine_A(9)",
        "c:1:c:c-2:c(:c:c:1)-[#7]=[#6]-[#6]-2=[#7;!R]",
    ),
    (
        "thio_urea_C(9)",
        "c:1(:c:c:c:c:c:1)-[#7](-[#1])-[#6](=[#16])-[#7]-[#7](-[#1])-[#6](=[#8])-[#6]-,:2:[!#1]:[!#6&!#1]:[#6]:[#6]-,:2",
    ),
    (
        "imine_one_fives_B(9)",
        "[#7;!R]=[#6]-2-[#6](=[#8])-c:1:c:c:c:c:c:1-[#16]-2",
    ),
    (
        "dhp_amino_CN_B(9)",
        "[$([#7](-[#1])-[#1]),$([#8]-[#1])]-[#6]-2=[#6](-[#6]#[#7])-[#6](-[#1])(-[#6]:[#6])-c:1:c(:n(-[#6]):n:c:1)-[#8]-2",
    ),
    (
        "anil_OC_no_alk_A(8)",
        "[#7](-[#1])(-[#1])-c:1:c(:c(:c(:n:c:1-[#1])-[#8]-c:2:c:c:c:c:c:2)-[#1])-[#1]",
    ),
    (
        "het_thio_66_one(8)",
        "[#6](=[#8])-[#6]-1=[#6]-[#7]-c:2:c(-[#16]-1):c:c:c:c:2",
    ),
    (
        "styrene_B(8)",
        "c:1:c:c-2:c(:c:c:1)-[#6](-c:3:c(-[$([#16;X2]),$([#6;X4])]-2):c:c:[c;!H0,$(c-[#17]),$(c-[#6;X4])](:c:3))=[#6]-[#6]",
    ),
    (
        "het_thio_5_A(8)",
        "[#6](-[#1])(-[#1])-[#16;X2]-c:1:n:c(:c(:n:1-!@[#6](-[#1])-[#1])-c:2:c:c:c:c:c:2)-[#1]",
    ),
    (
        "anil_di_alk_ene_A(8)",
        "[#6](-[#1])(-[#1])-[#7](-[#6](-[#1])-[#1])-[#6]-2=[#6](-[#1])-c:1:c(:c:c:c:c:1)-[#16;X2]-c:3:c-2:c:c:c:c:3",
    ),
    (
        "ene_rhod_D(8)",
        "[#16]-1-[#6](=!@[#7;!H0,$([#7]-[#7](-[#1])-[#6]:[#6])])-[#7;!H0,$([#7]-[#6]:[#7]:[#6]:[#6]:[#16])]-[#6](=[#8])-[#6]-1=[#6](-[#1])-[#6]:[#6]-[$([#17]),$([#8]-[#6]-[#1])]",
    ),
    (
        "ene_rhod_E(8)",
        "[#16]-1-[#6](=[#8])-[#7]-[#6](=[#16])-[#6]-1=[#6](-[#1])-[#6]:[#6]",
    ),
    (
        "anil_OH_alk_A(8)",
        "c:1:c(:c:c:c:c:1)-[#6](-[#1])(-[#1])-[#7](-[#1])-c:2:c(:c(:c(:c(:c:2-[#1])-[#1])-[#8]-[#1])-[#1])-[#1]",
    ),
    (
        "pyrrole_C(8)",
        "n1(-[#6;X4])c(c(-[#1])c(c1-[#6]:[#6])-[#1])-[#6](-[#1])-[#1]",
    ),
    (
        "thio_urea_D(8)",
        "c:1(:c:c:c:c:c:1)-[#7](-[#1])-[#6](=[#16])-[#7]-[#7](-[#1])-c:2:c:c:c:c:c:2",
    ),
    (
        "thiaz_ene_D(8)",
        "[#7](-c:1:c:c:c:c:c:1)-c2[n+]c(cs2)-c:3:c:c:c:c:c:3",
    ),
    (
        "ene_rhod_F(8)",
        "n:1:c:c:c(:c:1-[#6](-[#1])-[#1])-[#6](-[#1])=[#6]-2-[#6](=[#8])-[#7]-[#6](=[!#6&!#1])-[#7]-2",
    ),
    (
        "thiaz_ene_E(8)",
        "[#6]-,:1(=,:[#6](-[#6](-[#1])(-[#6])-[#6])-,:[#16]-,:[#6](-,:[#7;!H0,$([#7]-[#6;!H0;!H1])]-,:1)=[#8])-[#16]-[#6;R]",
    ),
    (
        "het_65_B(7)",
        "[!#1]:,-1:[!#1]-,:2:[!#1](:[!#1]:[!#1]:[!#1]:,-1)-,:[#7](-[#1])-,:[#7](-,:[#6]-,:2=[#8])-[#6]",
    ),
    (
        "keto_keto_beta_C(7)",
        "c:1:c:c-2:c(:c:c:1)-[#6](=[#6](-[#6]-2=[#8])-[#6])-[#8]-[#1]",
    ),
    (
        "het_66_A(7)",
        "c:2:c:c:1:n:n:c(:n:c:1:c:c:2)-[#6](-[#1])(-[#1])-[#6]=[#8]",
    ),
    (
        "thio_urea_E(7)",
        "c:1:c:c:c:c:c:1-[#7](-[#1])-[#6](=[#16])-[#7](-[#1])-[#6](-[#1])(-[#1])-c:2:n:c:c:c:c:2",
    ),
    (
        "thiophene_amino_C(7)",
        "[#6](-[#1])-[#6](-[#1])(-[#1])-c:1:c(:c(:c(:s:1)-[#7](-[#1])-[#6](=[#8])-[#6]-[#6]-[#6]=[#8])-[$([#6](=[#8])-[#8]),$([#6]#[#7])])-[#6](-[#1])-[#1]",
    ),
    (
        "hzone_phenone(7)",
        "[#6](-c:1:c(:c(:[c;!H0,$(c-[#6;X4])]:c:c:1-[#1])-[#1])-[#1])(-c:2:c(:c(:[c;!H0,$(c-[#17])](:c(:c:2-[#1])-[#1]))-[#1])-[#1])=[$([#7]-[#8]-[#6](-[#1])(-[#1])-[#6](-[#1])(-[#1])-[#6](-[#1])(-[#1])-[#7](-[#6](-[#1])-[#1])-[#6](-[#1])-[#1]),$([#7]-[#8]-[#6](-[#1])(-[#1])-[#6](-[#1])(-[#1])-[#7](-[#6](-[#1])-[#1])-[#6](-[#1])-[#1]),$([#7]-[#7](-[#1])-[#6](=[#7]-[#1])-[#7](-[#1])-[#1]),$([#6](-[#1])-[#7])]",
    ),
    (
        "ene_rhod_G(7)",
        "[#8](-[#1])-[#6](=[#8])-c:1:c:c(:c:c:c:1)-[#6]:[!#1]:[#6]-[#6](-[#1])=[#6]-2-[#6](=[!#6&!#1])-[#7]-[#6](=[!#6&!#1])-[!#6&!#1]-2",
    ),
    (
        "ene_cyano_B(7)",
        "[#6]-1(=[#6]-[#6](-c:2:c:c(:c(:n:c-1:2)-[#7](-[#1])-[#1])-[#6]#[#7])=[#6])-[#6]#[#7]",
    ),
    (
        "dhp_amino_CN_C(7)",
        "[#7](-[#1])(-[#1])-[#6]-1=[#6](-[#6]#[#7])-[#6](-[#1])(-[#6]:[#6])-[#6](=[#6](-[#6]:[#6])-[#8]-1)-[#6]#[#7]",
    ),
    (
        "het_5_A(7)",
        "[#7]-2(-c:1:c:c:c:c:c:1)-[#7]=[#6](-[#6]=[#8])-[#6;X4]-[#6]-2=[#8]",
    ),
    (
        "ene_five_het_H(6)",
        "[#7]-1=[#6]-[#6](-[#6](-[#7]-1)=[#16])=[#6]",
    ),
    (
        "thio_amide_A(6)",
        "c1(coc(c1-[#1])-[#6](=[#16])-[#7]-2-[#6](-[#1])(-[#1])-[#6](-[#1])(-[#1])-[!#1]-[#6](-[#1])(-[#1])-[#6]-2(-[#1])-[#1])-[#1]",
    ),
    (
        "ene_cyano_C(6)",
        "[#6]=[#6](-[#6]#[#7])-[#6](=[#7]-[#1])-[#7]-[#7]",
    ),
    (
        "hzone_furan_A(6)",
        "c:1(:c(:c(:[c;!H0,$(c-[#6;!H0;!H1])](:o:1))-[#1])-[#1])-[#6;!H0,$([#6]-[#6;!H0;!H1])]=[#7]-[#7](-[#1])-c:2:n:c:c:s:2",
    ),
    (
        "anil_di_alk_H(6)",
        "c:1(:c(:c(:c(:c(:c:1-[#7](-[#1])-[#16](=[#8])(=[#8])-[#6]:2:[#6]:[!#1]:[#6]:[#6]:[#6]:2)-[#1])-[#7](-[#6](-[#1])-[#1])-[#6](-[#1])-[#1])-[#1])-[#1])-[#1]",
    ),
    (
        "het_65_C(6)",
        "n2c1ccccn1c(c2-[$([#6](-[!#1])=[#6](-[#1])-[#6]:[#6]),$([#6]:[#8]:[#6])])-[#7]-[#6]:[#6]",
    ),
    (
        "thio_urea_F(6)",
        "[#6]-1-[#7](-[#1])-[#7](-[#1])-[#6](=[#16])-[#7]-[#7]-1-[#1]",
    ),
    (
        "ene_five_het_I(6)",
        "c:1(:c:c:c:o:1)-[#6](-[#1])=!@[#6]-3-[#6](=[#8])-c:2:c:c:c:c:c:2-[!#6&!#1]-3",
    ),
    (
        "keto_keto_gamma(5)",
        "[#8]=[#6]-1-[#6;X4]-[#6]-[#6](=[#8])-c:2:c:c:c:c:c-1:2",
    ),
    (
        "quinone_B(5)",
        "c:1:c:c-2:c(:c:c:1)-[#6](-c3cccc4noc-2c34)=[#8]",
    ),
    (
        "het_6_pyridone_OH(5)",
        "[#8](-[#1])-c:1:n:c(:c:c:c:1)-[#8]-[#1]",
    ),
    (
        "hzone_naphth_A(5)",
        "c:1:2:c(:c(:c(:c(:c:1:c(:c(:c(:c:2-[#1])-[#1])-[#6]=[#7]-[#7](-[#1])-[$([#6]:[#6]),$([#6]=[#16])])-[#1])-[#1])-[#1])-[#1])-[#1]",
    ),
    (
        "thio_ester_A(5)",
        "[#6]-,:1=,:[#6](-,:[#16]-,:[#6](-,:[#6]=,:[#6]-,:1)=[#16])-,:[#7]",
    ),
    (
        "ene_misc_A(5)",
        "[#6]-1=[#6]-[#6](-[#8]-[#6]-1-[#8])(-[#8])-[#6]",
    ),
    (
        "cyano_pyridone_D(5)",
        "[#8]=[#6]-,:1-,:[#6](=,:[#6]-,:[#6](=,:[#7]-,:[#7]-,:1)-,:[#6]=[#8])-[#6]#[#7]",
    ),
    (
        "het_65_Db(5)",
        "c3cn1c(nc(c1-[#7]-[#6])-c:2:c:c:c:c:n:2)cc3",
    ),
    (
        "het_666_A(5)",
        "[#7]-2-c:1:c:c:c:c:c:1-[#6](=[#7])-c:3:c-2:c:c:c:c:3",
    ),
    (
        "diazox_sulfon_B(5)",
        "c:1:c(:c:c:c:c:1)-[#7]-2-[#6](-[#1])-[#6](-[#1])-[#7](-[#6](-[#1])-[#6]-2-[#1])-[#16](=[#8])(=[#8])-c:3:c:c:c:c:4:n:s:n:c:3:4",
    ),
    (
        "anil_NH_alk_A(5)",
        "c:1(:c(:c-,:2:c(:c(:c:1-[#1])-[#1])-,:[#7](-,:[#6](-,:[#7]-,:2-[#1])=[#8])-[#1])-[#1])-[#7](-[#1])-[#6](-[#1])-[#1]",
    ),
    (
        "sulfonamide_C(5)",
        "c:1(:c(:c-3:c(:c(:c:1-[#7](-[#1])-[#16](=[#8])(=[#8])-c:2:c:c:c(:c:c:2)-[!#6&!#1])-[#1])-[#8]-[#6](-[#8]-3)(-[#1])-[#1])-[#1])-[#1]",
    ),
    (
        "het_thio_N_55(5)",
        "[#6](-[#1])-[#6]:2:[#7]:[#7](-c:1:c:c:c:c:c:1):[#16]:3:[!#6&!#1]:[!#1]:[#6]:[#6]:2:3",
    ),
    (
        "keto_keto_beta_D(5)",
        "[#8]=[#6]-[#6]=[#6](-[#1])-[#8]-[#1]",
    ),
    (
        "ene_rhod_H(5)",
        "[#7]-,:1-,:2-,:[#6](=,:[#7]-,:[#6](=[#8])-,:[#6](=,:[#7]-,:1)-[#6](-[#1])-[#1])-,:[#16]-,:[#6](=[#6](-[#1])-[#6]:[#6])-,:[#6]-,:2=[#8]",
    ),
    (
        "imine_ene_A(5)",
        "[#6]:[#6]-[#6](-[#1])=[#6](-[#1])-[#6](-[#1])=[#7]-[#7](-[#6;X4])-[#6;X4]",
    ),
    (
        "het_thio_656a(5)",
        "c:1:3:c(:c:c:c:c:1):c:2:n:n:c(-[#16]-[#6](-[#1])(-[#1])-[#6]=[#8]):n:c:2:n:3-[#6](-[#1])(-[#1])-[#6](-[#1])=[#6](-[#1])-[#1]",
    ),
    (
        "pyrrole_D(5)",
        "n1(-[#6])c(c(-[#1])c(c1-[#6](-[#1])(-[#1])-[#7](-[#1])-[#6](=[#16])-[#7]-[#1])-[#1])-[#1]",
    ),
    (
        "pyrrole_E(5)",
        "n2(-[#6]:1:[!#1]:[!#6&!#1]:[!#1]:[#6]:1-[#1])c(c(-[#1])c(c2-[#6;X4])-[#1])-[#6;X4]",
    ),
    (
        "thio_urea_G(5)",
        "c:1(:c:c:c:c:c:1)-[#7](-[#1])-[#6](=[#16])-[#7]-[#7](-[#1])-[#6]([#7;R])[#7;R]",
    ),
    (
        "anisol_A(5)",
        "c:1(:c(:c(:c(:c(:[c;!H0,$(c-[#6](-[#1])-[#1])]:1)-[#1])-[#8]-[#6](-[#1])-[#1])-[#6](-[#1])(-[#1])-[$([#7](-[#1])-[#6](=[#8])-[#6](-[#1])(-[#1])-[#6](-[#1])(-[#1])-[#6](-[#1])-[#1]),$([#6](-[#1])(-[#6](-[#1])-[#1])-[#7](-[#1])-[#6](=[#16])-[#7]-[#1])])-[#1])-[#8]-[#6](-[#1])-[#1]",
    ),
    (
        "pyrrole_F(5)",
        "n2(-[#6]:1:[#6](-[#6]#[#7]):[#6]:[#6]:[!#6&!#1]:1)c(c(-[#1])c(c2)-[#1])-[#1]",
    ),
    (
        "dhp_amino_CN_D(5)",
        "[#7](-[#1])(-[#1])-[#6]-2=[#6](-[#6]#[#7])-[#6](-[#1])(-[#6]:[#6])-c:1:c(:c:c:s:1)-[#8]-2",
    ),
    (
        "thiazole_amine_A(4)",
        "[#7](-[#1])-c:1:n:c(:c:s:1)-c:2:c:n:c(-[#7](-[#1])-[#1]):s:2",
    ),
    (
        "het_6_imidate_A(4)",
        "[#7]=[#6]-,:1-,:[#7](-[#1])-,:[#6](=,:[#6](-[#7]-[#1])-,:[#7]=,:[#7]-,:1)-[#7]-[#1]",
    ),
    (
        "anil_OC_no_alk_B(4)",
        "c:1:c(:c:2:c(:c:c:1):c:c:c:c:2)-[#8]-c:3:c(:c(:c(:c(:c:3-[#1])-[#1])-[#7]-[#1])-[#1])-[#1]",
    ),
    (
        "styrene_C(4)",
        "c:1:c:c-2:c(:c:c:1)-[#6]-[#16]-c3c(-[#6]-2=[#6])ccs3",
    ),
    ("azulene(4)", "c:2:c:c:c:1:c(:c:c:c:1):c:c:2"),
    (
        "furan_acid_A(4)",
        "c:1(:c(:c(:c(:o:1)-[#6](-[#1])-[#1])-[#6](-[#1])(-[#1])-[#8]-[#6]:[#6])-[#1])-[#6](=[#8])-[#8]-[#1]",
    ),
    (
        "cyano_pyridone_E(4)",
        "[!#1]:[#6]-[#6]-,:1=,:[#6](-[#1])-,:[#6](=,:[#6](-[#6]#[#7])-,:[#6](=[#8])-,:[#7]-,:1-[#1])-[#6]:[#8]",
    ),
    (
        "anil_alk_thio(4)",
        "[#6]-1-3=[#6](-[#6](-[#7]-c:2:c:c:c:c:c-1:2)(-[#6])-[#6])-[#16]-[#16]-[#6]-3=[!#1]",
    ),
    (
        "anil_di_alk_I(4)",
        "c:1(:c(:c(:c(:c(:c:1-[#7](-[#1])-[#6](=[#8])-c:2:c:c:c:c:c:2)-[#1])-[#7](-[#6](-[#1])-[#1])-[#6](-[#1])-[#1])-[#1])-[#1])-[#1]",
    ),
    (
        "het_thio_6_furan(4)",
        "[#6](-[#1])(-[#1])-[#16;X2]-c:1:n:n:c(:c(:n:1)-c:2:c(:c(:c(:o:2)-[#1])-[#1])-[#1])-c:3:c(:c(:c(:o:3)-[#1])-[#1])-[#1]",
    ),
    (
        "anil_di_alk_ene_B(4)",
        "[#6](-[#1])(-[#1])-[#7](-[#6](-[#1])-[#1])-[#6]-2=[#6]-c:1:c(:c:c:c:c:1)-[#6]-2(-[#1])-[#1]",
    ),
    (
        "imine_one_B(4)",
        "[#7](-[#1])(-c:1:c:c:c:c:c:1)-[#7]=[#6](-[#6](=[#8])-[#6](-[#1])-[#1])-[#7](-[#1])-[$([#7]-[#1]),$([#6]:[#6])]",
    ),
    (
        "anil_OC_alk_A(4)",
        "c:1:2:c(:c(:c(:c(:c:1-[#1])-[#1])-[#1])-[#1]):o:c:3:c(-[#1]):c(:c(-[#8]-[#6](-[#1])-[#1]):c(:c:2:3)-[#1])-[#7](-[#1])-[#6](-[#1])-[#1]",
    ),
    (
        "ene_five_het_J(4)",
        "[#16]=[#6]-,:1-,:[#7](-[#1])-,:[#6]=,:[#6]-,:[#6]-2=,:[#6]-,:1-[#6](=[#8])-[#8]-[#6]-2=[#6]-[#1]",
    ),
    (
        "pyrrole_G(4)",
        "n2(-c:1:c(:c:c(:c(:c:1)-[#1])-[$([#7](-[#1])-[#1]),$([#6]:[#7])])-[#1])c(c(-[#1])c(c2-[#1])-[#1])-[#1]",
    ),
    (
        "ene_five_het_K(4)",
        "n1(-[#6])c(c(-[#1])c(c1-[#6](-[#1])=[#6]-2-[#6](=[#8])-[!#6&!#1]-[#6]=,:[!#1]-2)-[#1])-[#1]",
    ),
    (
        "cyano_ene_amine_B(4)",
        "[#6]=[#6]-[#6](-[#6]#[#7])(-[#6]#[#7])-[#6](-[#6]#[#7])=[#6]-[#7](-[#1])-[#1]",
    ),
    (
        "thio_ester_B(4)",
        "[#6]:[#6]-[#6](=[#16;X1])-[#16;X2]-[#6](-[#1])-[$([#6](-[#1])-[#1]),$([#6]:[#6])]",
    ),
    (
        "ene_five_het_L(4)",
        "[#8]=[#6]-3-[#6](=!@[#6](-[#1])-c:1:c:n:c:c:1)-c:2:c:c:c:c:c:2-[#7]-3",
    ),
    (
        "hzone_thiophene_B(4)",
        "c:1(:[c;!H0,$(c-[#6;!H0;!H1])](:c(:c(:s:1)-[#1])-[#1]))-[#6](-[#1])=[#7]-[#7](-[#1])-c:2:c:c:c:c:c:2",
    ),
    (
        "dhp_amino_CN_E(4)",
        "[#6](-[#1])(-[#1])-[#16;X2]-[#6]-1=[#6](-[#6]#[#7])-[#6](-[#1])(-[#6]:[#6])-[#6](-[#6]#[#7])-[#6](=[#8])-[#7]-1",
    ),
    (
        "het_5_B(4)",
        "[#7]-2(-c:1:c:c:c:c:c:1)-[#7]=[#6](-[#7](-[#1])-[#6]=[#8])-[#6](-[#1])(-[#1])-[#6]-2=[#8]",
    ),
    (
        "imine_imine_B(3)",
        "[#6]:[#6]-[#6](-[#1])=[#6](-[#1])-[#6](-[#1])=[#7]-[#7]=[#6]",
    ),
    (
        "thiazole_amine_B(3)",
        "c:1(:c:c:c(:c:c:1)-[#6](-[#1])-[#1])-c:2:c(:s:c(:n:2)-[#7](-[#1])-[#1])-[#6](-[#1])(-[#1])-[#1]",
    ),
    (
        "imine_ene_one_A(3)",
        "[#6]-2(-[#6]=[#7]-c:1:c:c:c:c:c:1-[#7]-2)=[#6](-[#1])-[#6]=[#8]",
    ),
    (
        "diazox_A(3)",
        "[#8](-c:1:c:c:c:c:c:1)-c:3:c:c:2:n:o:n:c:2:c:c:3",
    ),
    (
        "ene_one_A(3)",
        "[!#1]:1:[!#1]:[!#1]:[!#1](:[!#1]:[!#1]:1)-[#6](-[#1])=[#6](-[#1])-[#6](-[#7]-c:2:c:c:c:3:c(:c:2):c:c:c(:n:3)-[#7](-[#6])-[#6])=[#8]",
    ),
    (
        "anil_OC_no_alk_C(3)",
        "[#7](-[#1])(-[#1])-c:1:c(:c:c:c:n:1)-[#8]-[#6](-[#1])(-[#1])-[#6]:[#6]",
    ),
    ("thiazol_SC_A(3)", "[#6]-[#16;X2]-c:1:n:c(:c:s:1)-[#1]"),
    (
        "het_666_B(3)",
        "c:1:c-3:c(:c:c:c:1)-[#7](-c:2:c:c:c:c:c:2-[#8]-3)-[#6](-[#1])(-[#1])-[#6](-[#1])-[#1]",
    ),
    (
        "furan_A(3)",
        "c:1(:c(:c(:c(:o:1)-[#6](-[#1])-[#1])-[#1])-[#1])-[#6](-[#1])(-[#8]-[#1])-[#6]#[#6]-[#6;X4]",
    ),
    (
        "colchicine_A(3)",
        "[#6]-1(-[#6](=[#6]-[#6]=[#6]-[#6]=[#6]-1)-[#7]-[#1])=[#7]-[#6]",
    ),
    (
        "thiophene_C(3)",
        "[#6](-[#1])(-[#1])-[#7](-[#6](-[#1])-[#1])-[#6](-[#1])=[#6]-[#6](=[#8])-c:1:c(-[#16;X2]):s:c(:c:1)-[$([#6]#[#7]),$([#6]=[#8])]",
    ),
    (
        "anil_OC_alk_B(3)",
        "c:1:c(:c:c:c:c:1)-[#7]-2-[#6](=[#8])-[#6](=[#6](-[F,Cl,Br,I])-[#6]-2=[#8])-[#7](-[#1])-[#6]:3:[#6]:[#6]:[#6](-[#8]-[#6](-[#1])-[#1]):[#6]:[#6]:3",
    ),
    (
        "het_thio_66_A(3)",
        "c:1-2:c(:c:c:c:c:1)-[#6](-[#1])(-[#1])-[#6](-[#1])(-[#1])-[#7]=[#6]-2-[#16;X2]-[#6](-[#1])(-[#1])-[#6](=[#8])-c:3:c:c:c:c:c:3",
    ),
    (
        "rhod_sat_B(3)",
        "[#7]-2(-c:1:c:c:c:c:c:1-[#6](-[#1])-[#1])-[#6](=[#16])-[#7](-[#6](-[#1])(-[#1])-[!#1]:[!#1]:[!#1]:[!#1]:[!#1])-[#6](-[#1])(-[#1])-[#6]-2=[#8]",
    ),
    (
        "ene_rhod_I(3)",
        "[#7]-2(-[#6](-[#1])-[#1])-[#6](=[#16])-[#7](-[#1])-[#6](=[#6](-[#1])-c:1:c:c:c:c(:c:1)-[Br])-[#6]-2=[#8]",
    ),
    (
        "keto_thiophene(3)",
        "c:1(:c(:c:2:c(:s:1):c:c:c:c:2)-[#6](-[#1])-[#1])-[#6](=[#8])-[#6](-[#1])(-[#1])-[#6](-[#1])-[#1]",
    ),
    (
        "imine_imine_C(3)",
        "[#7](-[#6](-[#1])-[#1])(-[#6](-[#1])-[#1])-[#6](-[#1])=[#7]-[#6](-[#6](-[#1])-[#1])=[#7]-[#7](-[#6](-[#1])-[#1])-[#6]:[#6]",
    ),
    (
        "het_65_pyridone_A(3)",
        "[#6]:2(:[#6](-[#6](-[#1])-[#1]):[#6]-,:1:[#6](-,:[#7]=,:[#6;!H0,$([#6]-[#16]-[#6](-[#1])-[#1])](-,:[#7](-,:[#6]-,:1=[!#6&!#1;X1])-[#6](-[#1])-[$([#6](=[#8])-[#8]),$([#6]:[#6])])):[!#6&!#1;X2]:2)-[#6](-[#1])(-[#1])-[#6](-[#1])-[#1]",
    ),
    (
        "thiazole_amine_C(3)",
        "c:1(:n:c(:c(-[#1]):s:1)-[!#1]:[!#1]:[!#1](-[$([#8]-[#6](-[#1])-[#1]),$([#6](-[#1])-[#1])]):[!#1]:[!#1])-[#7](-[#1])-[#6](-[#1])(-[#1])-c:2:c(-[#1]):c(:c(-[#1]):o:2)-[#1]",
    ),
    (
        "het_thio_pyr_A(3)",
        "n:1:c(:c(:c(:c(:c:1-[#16]-[#6]-[#1])-[#6]#[#7])-c:2:c:c:c(:c:c:2)-[#8]-[#6](-[#1])-[#1])-[#1])-[#6]:[#6]",
    ),
    (
        "melamine_A(3)",
        "c:1:4:c(:n:c(:n:c:1-[#7](-[#1])-[#6](-[#1])(-[#1])-c:2:c(:c(:c(:o:2)-[#1])-[#1])-[#1])-[#7](-[#1])-c:3:c:[c;!H0,$(c-[#6](-[#1])-[#1]),$(c-[#16;X2]),$(c-[#8]-[#6]-[#1]),$(c-[#7;X3])](:[c;!H0,$(c-[#6](-[#1])-[#1]),$(c-[#16;X2]),$(c-[#8]-[#6]-[#1]),$(c-[#7;X3])](:c:[c;!H0,$(c-[#6](-[#1])-[#1]),$(c-[#16;X2]),$(c-[#8]-[#6]-[#1]),$(c-[#7;X3])]:3))):c:c:c:c:4",
    ),
    (
        "anil_NH_alk_B(3)",
        "[#7](-[#1])(-[#6]:1:[#6]:[#6]:[!#1]:[#6]:[#6]:1)-c:2:c:c:c(:c:c:2)-[#7](-[#1])-[#6]-[#1]",
    ),
    (
        "rhod_sat_C(3)",
        "[#7]-2(-c:1:c:c:c:c:c:1)-[#6](=[#7]-[#6]=[#8])-[#16]-[#6](-[#1])(-[#1])-[#6]-2=[#8]",
    ),
    (
        "thiophene_amino_D(3)",
        "[#6]=[#6]-[#6](=[#8])-[#7]-c:1:c(:c(:c(:s:1)-[#6](=[#8])-[#8])-[#6]-[#1])-[#6]#[#7]",
    ),
    (
        "anil_OC_alk_C(3)",
        "[#8;!H0,$([#8]-[#6](-[#1])-[#1])]-c:1:c(:c(:c(:c(:c:1-[#1])-[#1])-[#1])-[#1])-[#7](-[#1])-[#6](-[#1])(-[#1])-c:2:n:c:c:n:2",
    ),
    (
        "het_thio_65_A(3)",
        "[#6](-[#1])(-[#1])-[#16;X2]-c3nc1c(n(nc1-[#6](-[#1])-[#1])-c:2:c:c:c:c:c:2)nn3",
    ),
    (
        "het_thio_656b(3)",
        "[#6]-[#6](=[#8])-[#6](-[#1])(-[#1])-[#16;X2]-c:3:n:n:c:2:c:1:c(:c(:c(:c(:c:1:n(:c:2:n:3)-[#1])-[#1])-[#1])-[#1])-[#1]",
    ),
    (
        "thiazole_amine_D(3)",
        "s:1:c(:[n+](-[#6](-[#1])-[#1]):c(:c:1-[#1])-[#6])-[#7](-[#1])-c:2:c:c:c:c:c:2[$([#6](-[#1])-[#1]),$([#6]:[#6])]",
    ),
    (
        "thio_urea_H(3)",
        "[#6]-,:2(=[#16])-,:[#7](-[#6](-[#1])(-[#1])-c:1:c:c:c:o:1)-,:[#6](=,:[#7]-,:[#7]-,:2-[#1])-[#6]:[#6]",
    ),
    (
        "cyano_pyridone_F(3)",
        "[#7]-,:2(-c:1:c:c:c:c:c:1)-,:[#6](=[#8])-,:[#6](=,:[#6]-,:[#6](=,:[#7]-,:2)-[#6]#[#7])-[#6]#[#7]",
    ),
    (
        "rhod_sat_D(3)",
        "[#7]-2(-c:1:c:c:c:c:c:1)-[#6](=[#8])-[#16]-[#6](-[#1])(-[#6](-[#1])(-[#1])-[#6](=[#8])-[#7](-[#1])-[#6]:[#6])-[#6]-2=[#8]",
    ),
    (
        "ene_rhod_J(3)",
        "[#6](-[#1])(-[#1])-[#7]-2-[#6](=[$([#16]),$([#7])])-[!#6&!#1]-[#6](=[#6]-1-[#6](=[#6](-[#1])-[#6]:[#6]-[#7]-1-[#6](-[#1])-[#1])-[#1])-[#6]-2=[#8]",
    ),
    (
        "imine_phenol_A(3)",
        "[#6]=[#7;!R]-c:1:c:c:c:c:c:1-[#8]-[#1]",
    ),
    (
        "thio_carbonate_B(3)",
        "[#8]=[#6]-,:2-,:[#16]-,:c:1:c(:c(:c:c:c:1)-[#8]-[#6](-[#1])-[#1])-,:[#8]-,:2",
    ),
    (
        "het_thio_N_5A(3)",
        "[#7]=,:[#6]-,:1-,:[#7]=,:[#6]-,:[#7]-,:[#16]-,:1",
    ),
    (
        "het_thio_N_65A(3)",
        "[#7]-,:2-,:[#16]-,:[#6]-1=,:[#6](-[#6]:[#6]-[#7]-[#6]-1)-,:[#6]-,:2=[#16]",
    ),
    (
        "anil_di_alk_J(3)",
        "[#6](-[#1])(-[#1])-[#7](-[#6](-[#1])-[#1])-c:1:c(:c(:c(:c(:c:1-[#1])-[#1])-[#6](-[#1])=[#7]-[#7]=[#6](-[#6])-[#6]:[#6])-[#1])-[#1]",
    ),
    ("pyrrole_H(3)", "n1-2cccc1-[#6]=[#7](-[#6])-[#6]-[#6]-2"),
    (
        "ene_cyano_D(3)",
        "[#6](-[#6]#[#7])(-[#6]#[#7])=[#6](-[#16])-[#16]",
    ),
    (
        "cyano_cyano_B(3)",
        "[#6]-1(-[#6]#[#7])(-[#6]#[#7])-[#6](-[#1])(-[#6](=[#8])-[#6])-[#6]-1-[#1]",
    ),
    (
        "ene_five_het_M(3)",
        "[#6]-1=,:[#6]-[#6](-[#6](-[$([#8]),$([#16])]-1)=[#6]-[#6]=[#8])=[#8]",
    ),
    (
        "cyano_ene_amine_C(3)",
        "[#6]:[#6]-[#6](=[#8])-[#7](-[#1])-[#6](=[#8])-[#6](-[#6]#[#7])=[#6](-[#1])-[#7](-[#1])-[#6]:[#6]",
    ),
    (
        "thio_urea_I(3)",
        "c:1(:c:c:c:c:c:1)-[#7](-[#1])-[#6](=[#16])-[#7](-[#1])-[#7]=[#6]-c:2:c:n:c:c:2",
    ),
    (
        "dhp_amino_CN_F(3)",
        "[#7](-[#1])(-[#1])-[#6]-2=[#6](-[#6]#[#7])-[#6](-[#1])(-c:1:c:c:c:s:1)-[#6](=[#6](-[#6](-[#1])-[#1])-[#8]-2)-[#6](=[#8])-[#8]-[#6]",
    ),
    (
        "anthranil_acid_B(3)",
        "c:1:c-3:c(:c:c(:c:1)-[#6](=[#8])-[#7](-[#1])-c:2:c(:c:c:c:c:2)-[#6](=[#8])-[#8]-[#1])-[#6](-[#7](-[#6]-3=[#8])-[#6](-[#1])-[#1])=[#8]",
    ),
    ("diazox_B(3)", "[Cl]-c:2:c:c:1:n:o:n:c:1:c:c:2"),
    ("thio_aldehyd_A(3)", "[#6]-[#6](=[#16])-[#1]"),
    (
        "thio_amide_B(2)",
        "[#6;X4]-[#7](-[#1])-[#6](-[#6]:[#6])=[#6](-[#1])-[#6](=[#16])-[#7](-[#1])-c:1:c:c:c:c:c:1",
    ),
    (
        "imidazole_B(2)",
        "[#6](-[#1])(-[#1])-[#6](-[#1])(-[#1])-[#16]-[#6](-[#1])(-[#1])-c1cn(cn1)-[#1]",
    ),
    (
        "thiazole_amine_E(2)",
        "[#8]=[#6]-[#7](-[#1])-c:1:c(-[#6]:[#6]):n:c(-[#6](-[#1])(-[#1])-[#6]#[#7]):s:1",
    ),
    (
        "thiazole_amine_F(2)",
        "[#6](-[#1])-[#7](-[#1])-c:1:n:c(:c:s:1)-c2cnc3n2ccs3",
    ),
    (
        "thio_ester_C(2)",
        "[#7]-,:1-,:[#6](=[#8])-,:[#6](=,:[#6](-[#6])-,:[#16]-,:[#6]-,:1=[#16])-[#1]",
    ),
    (
        "ene_one_B(2)",
        "[#6](-[#16])(-[#7])=[#6](-[#1])-[#6]=[#6](-[#1])-[#6]=[#8]",
    ),
    (
        "quinone_C(2)",
        "[#8]=[#6]-3-c:1:c(:c:c:c:c:1)-[#6]-,:2=,:[#6](-[#8]-[#1])-,:[#6](=[#8])-,:[#7]-,:c:4:c-,:2:c-3:c:c:c:4",
    ),
    (
        "keto_naphthol_A(2)",
        "c:1:2:c:c:c:c(:c:1:c(:c:c:c:2)-[$([#8]-[#1]),$([#7](-[#1])-[#1])])-[#6](-[#6])=[#8]",
    ),
    (
        "thio_amide_C(2)",
        "[#6](-[#1])(-c:1:c:c:c:c:c:1)(-c:2:c:c:c:c:c:2)-[#6](=[#16])-[#7]-[#1]",
    ),
    (
        "phthalimide_misc(2)",
        "[#7]-2(-[#6](=[#8])-c:1:c(:c(:c(:c(:c:1-[#1])-[#6](=[#8])-[#8]-[#1])-[#1])-[#1])-[#6]-2=[#8])-c:3:c(:c:c(:c(:c:3)-[#1])-[#8])-[#1]",
    ),
    (
        "sulfonamide_D(2)",
        "c:1:c:c(:c:c:c:1-[#7](-[#1])-[#16](=[#8])=[#8])-[#7](-[#1])-[#16](=[#8])=[#8]",
    ),
    (
        "anil_NH_alk_C(2)",
        "[#6](-[#1])-[#7](-[#1])-c:1:c(:c(:c(:c(:c:1-[#1])-[#1])-[#1])-[#1])-[#7](-[#1])-[#6]-[#1]",
    ),
    (
        "het_65_E(2)",
        "s1c(c(c-,:2c1-,:[#7](-[#1])-,:[#6](-,:[#6](=,:[#6]-,:2-[#1])-[#6](=[#8])-[#8]-[#1])=[#8])-[#7](-[#1])-[#1])-[#6](=[#8])-[#7]-[#1]",
    ),
    (
        "hzide_naphth(2)",
        "c:2(:c:1:c(:c(:c(:c(:c:1:c(:c(:c:2-[#1])-[#1])-[#1])-[#1])-[#7](-[#1])-[#7](-[#1])-[#6]=[#8])-[#1])-[#1])-[#1]",
    ),
    (
        "anisol_B(2)",
        "[#6](-[#1])(-[#1])-c:1:c(:c(:c(:c(:c:1-[#8]-[#6](-[#1])-[#1])-[#1])-[#1])-[#6](-[#1])(-[#1])-[#7](-[#1])-[#6;X4])-[#1]",
    ),
    (
        "thio_carbam_ene(2)",
        "[#6]-1=[#6]-[#7]-[#6](-[#16]-[#6;X4]-1)=[#16]",
    ),
    (
        "thio_amide_D(2)",
        "[#6](-[#7](-[#6]-[#1])-[#6]-[#1]):[#6]-[#7](-[#1])-[#6](=[#16])-[#6]-[#1]",
    ),
    ("het_65_Da(2)", "n2nc(c1cccc1c2-[#6])-[#6]"),
    (
        "thiophene_D(2)",
        "s:1:c(:c(-[#1]):c(:c:1-[#6](=[#8])-[#7](-[#1])-[#7]-[#1])-[#8]-[#6](-[#1])-[#1])-[#1]",
    ),
    (
        "het_thio_6_ene(2)",
        "[#6]-1:[#6]-[#7]=[#6]-[#6](=[#6]-[#7]-[#6])-[#16]-1",
    ),
    (
        "cyano_keto_A(2)",
        "[#6](-[#1])(-[#1])-[#6](-[#1])(-[#6]#[#7])-[#6](=[#8])-[#6]",
    ),
    (
        "anthranil_acid_C(2)",
        "c2(c(-[#7](-[#1])-[#1])n(-c:1:c:c:c:c:c:1-[#6](=[#8])-[#8]-[#1])nc2-[#6]=[#8])-[$([#6]#[#7]),$([#6]=[#16])]",
    ),
    (
        "naphth_amino_C(2)",
        "c:2:c:1:c:c:c:c-,:3:c:1:c(:c:c:2)-,:[#7](-,:[#7]=,:[#6]-,:3)-[#1]",
    ),
    (
        "naphth_amino_D(2)",
        "c:2:c:1:c:c:c:c-,:3:c:1:c(:c:c:2)-,:[#7]-,:[#7]=,:[#7]-,:3",
    ),
    (
        "thiazole_amine_G(2)",
        "c1csc(n1)-[#7]-[#7]-[#16](=[#8])=[#8]",
    ),
    (
        "het_66_B(2)",
        "c:1:c:c:c:2:c(:c:1):n:c(:n:c:2)-[#7](-[#1])-[#6]-3=[#7]-[#6](-[#6]=[#6]-[#7]-3-[#1])(-[#6](-[#1])-[#1])-[#6](-[#1])-[#1]",
    ),
    (
        "coumarin_A(2)",
        "c:1-,:3:c(:c(:c(:c(:c:1)-[#8]-[#6]-[#1])-[#1])-[#1])-,:c:2:c(:c(:c(:c(:c:2-[#1])-[#1])-[#8]-[#6](-[#1])-[#1])-[#1])-,:[#6](=[#8])-,:[#8]-,:3",
    ),
    (
        "anthranil_acid_D(2)",
        "c:12:c(:c:c:c:n:1)c(c(-[#6](=[#8])~[#8;X1])s2)-[#7](-[#1])-[#1]",
    ),
    (
        "het_66_C(2)",
        "c:1:2:n:c(:c(:n:c:1:[#6]:[#6]:[#6]:[!#1]:2)-[#6](-[#1])=[#6](-[#8]-[#1])-[#6])-[#6](-[#1])=[#6](-[#8]-[#1])-[#6]",
    ),
    (
        "thiophene_amino_E(2)",
        "c1csc(c1-[#7](-[#1])-[#1])-[#6](-[#1])=[#6](-[#1])-c2cccs2",
    ),
    (
        "het_6666_A(2)",
        "c:2:c:c:1:n:c:3:c(:n:c:1:c:c:2):c:c:c:4:c:3:c:c:c:c:4",
    ),
    (
        "sulfonamide_E(2)",
        "[#6]:[#6]-[#7](-[#1])-[#16](=[#8])(=[#8])-[#7](-[#1])-[#6]:[#6]",
    ),
    (
        "anil_di_alk_K(2)",
        "c:1:c:c(:c:c:c:1-[#7](-[#1])-[#1])-[#7](-[#6;X3])-[#6;X3]",
    ),
    (
        "het_5_C(2)",
        "[#7]-2=[#6](-c:1:c:c:c:c:c:1)-[#6](-[#1])(-[#1])-[#6](-[#8]-[#1])(-[#6](-[#9])(-[#9])-[#9])-[#7]-2-[$([#6]:[#6]:[#6]:[#6]:[#6]:[#6]),$([#6](=[#16])-[#6]:[#6]:[#6]:[#6]:[#6]:[#6])]",
    ),
    (
        "ene_six_het_B(2)",
        "c:1:c(:c:c:c:c:1)-[#6](=[#8])-[#6](-[#1])=[#6]-,:3-,:[#6](=[#8])-,:[#7](-[#1])-,:[#6](=[#8])-,:[#6](=[#6](-[#1])-c:2:c:c:c:c:c:2)-,:[#7]-,:3-[#1]",
    ),
    (
        "steroid_A(2)",
        "[#8]=[#6]-4-[#6]-[#6]-[#6]-3-[#6]-2-[#6](=[#8])-[#6]-[#6]-1-[#6]-[#6]-[#6]-[#6]-1-[#6]-2-[#6]-[#6]-[#6]-3=[#6]-4",
    ),
    (
        "het_565_A(2)",
        "c:1:2:c:3:c(:c(-[#8]-[#1]):c(:c:1:c(:c:n:2-[#6])-[#6]=[#8])-[#1]):n:c:n:3",
    ),
    (
        "thio_imine_ium(2)",
        "[#6;X4]-[#7+](-[#6;X4]-[#8]-[#1])=[#6]-[#16]-[#6]-[#1]",
    ),
    (
        "anthranil_acid_E(2)",
        "[#6]-3(=[#8])-[#6](=[#6](-[#1])-[#7](-[#1])-c:1:c:c:c:c:c:1-[#6](=[#8])-[#8]-[#1])-[#7]=[#6](-c:2:c:c:c:c:c:2)-[#8]-3",
    ),
    (
        "hzone_furan_B(2)",
        "c:1(:c(:c(:[c;!H0,$(c-[#6;!H0;!H1])](:o:1))-[#1])-[#1])-[#6;!H0,$([#6]-[#6;!H0;!H1])]=[#7]-[#7](-[#1])-c:2:c:c:n:c:c:2",
    ),
    (
        "thiophene_E(2)",
        "c:1(:c(:c(:[c;!H0,$(c-[#6;!H0;!H1])](:s:1))-[#1])-[#1])-[#6;!H0,$([#6]-[#6;!H0;!H1])]-[#6](=[#8])-[#7](-[#1])-c:2:n:c:c:s:2",
    ),
    (
        "ene_misc_B(2)",
        "[#6]:[#6]-[#6](-[#1])(-[#1])-[#6](-[#1])(-[#6]=[#8])-[#7]-2-[#6](=[#8])-[#6]-1(-[#1])-[#6](-[#1])(-[#1])-[#6]=[#6]-[#6](-[#1])(-[#1])-[#6]-1(-[#1])-[#6]-2=[#8]",
    ),
    (
        "het_thio_5_B(2)",
        "[#6]-1(-[#6]=[#8])(-[#6]:[#6])-[#16;X2]-[#6]=[#7]-[#7]-1-[#1]",
    ),
    (
        "thiophene_amino_F(2)",
        "[#7](-[#1])(-[#1])-c:1:c(:c(:c(:s:1)-[#7](-[#1])-[#6](=[#8])-c:2:c:c:c:c:c:2)-[#6]#[#7])-[#6]:3:[!#1]:[!#1]:[!#1]:[!#1]:[!#1]:3",
    ),
    (
        "anil_OC_alk_D(2)",
        "[#6](-[#1])(-[#1])-[#8]-c:1:c(:c(:c(:c(:c:1-[#1])-[#1])-[#6](-[#1])-[#1])-[#1])-[#7](-[#1])-[#6](-[#1])(-[#1])-c:2:c:c:c:c:c:2-[$([#6](-[#1])-[#1]),$([#8]-[#6](-[#1])-[#1])]",
    ),
    (
        "tert_butyl_A(2)",
        "[#6](-[#1])(-[#1])(-[#1])-[#6](-[#6](-[#1])(-[#1])-[#1])(-[#6](-[#1])(-[#1])-[#1])-c:1:c(:c:c(:c(:c:1-[#1])-[#6](-[#6](-[#1])(-[#1])-[#1])(-[#6](-[#1])(-[#1])-[#1])-[#6](-[#1])(-[#1])-[#1])-[#8]-[#6](-[#1])-[#7])-[#1]",
    ),
    (
        "thio_urea_J(2)",
        "c:1(:c(:o:c:c:1)-[#6]-[#1])-[#6]=[#7]-[#7](-[#1])-[#6](=[#16])-[#7]-[#1]",
    ),
    (
        "het_thio_65_B(2)",
        "[#7](-[#1])-c1nc(nc2nnc(n12)-[#16]-[#6])-[#7](-[#1])-[#6]",
    ),
    (
        "coumarin_B(2)",
        "c:1-,:2:c(:c:c:c:c:1-[#6](-[#1])(-[#1])-[#6](-[#1])=[#6](-[#1])-[#1])-,:[#6](=,:[#6](-[#6](=[#8])-[#7](-[#1])-[#6]:[#6])-,:[#6](=[#8])-,:[#8]-,:2)-[#1]",
    ),
    (
        "thio_urea_K(2)",
        "[#6]-,:2(=[#16])-,:[#7]-,:1-,:[#6]=,:[#6]-,:[#7]=,:[#7]-,:[#6]-,:1=,:[#7]-,:[#7]-,:2-[#1]",
    ),
    (
        "thiophene_amino_G(2)",
        "[#6]:[#6]:[#6]:[#6]:[#6]:[#6]-c:1:c:c(:c(:s:1)-[#7](-[#1])-[#6](=[#8])-[#6])-[#6](=[#8])-[#8]-[#1]",
    ),
    (
        "anil_NH_alk_D(2)",
        "[#7](-[#1])(-[#1])-c:1:c(:c(:c(:c:c:1-[#7](-[#1])-[#6](-[#1])(-[#6])-[#6](-[#1])-[#6](-[#1])-[#1])-[#1])-[#1])-[#1]",
    ),
    (
        "het_thio_5_C(2)",
        "[#16]=[#6]-,:2-,:[#7](-[#1])-,:[#7]=,:[#6](-c:1:c(:c(:c(:c(:c:1-[#1])-[#1])-[#8]-[#6](-[#1])-[#1])-[#1])-[#1])-,:[#8]-,:2",
    ),
    ("thio_keto_het(2)", "[#16]=[#6]-c:1:c:c:c:2:c:c:c:c:n:1:2"),
    (
        "het_thio_N_5B(2)",
        "[#6]~1~[#6](~[#7]~[#7]~[#6](~[#6](-[#1])-[#1])~[#6](-[#1])-[#1])~[#7]~[#16]~[#6]~1",
    ),
    (
        "quinone_D(2)",
        "[#6]-1(-[#6]=,:[#6]-[#6]=,:[#6]-[#6]-1=[!#6&!#1])=[!#6&!#1]",
    ),
    (
        "anil_di_alk_furan_B(2)",
        "[#6](-[#1])(-[#1])-[#7](-[#6](-[#1])-[#1])-c:1:c(-[#1]):c(:c(:o:1)-[#6](-[#1])=[#6]-[#6]#[#7])-[#1]",
    ),
    (
        "ene_six_het_C(2)",
        "[#8]=[#6]-1-[#6]:[#6]-[#6](-[#1])(-[#1])-[#7]-[#6]-1=[#6]-[#1]",
    ),
    (
        "het_55_A(2)",
        "[#6]:[#6]-[#7]:2:[#7]:[#6]:1-[#6](-[#1])(-[#1])-[#16;X2]-[#6](-[#1])(-[#1])-[#6]:1:[#6]:2-[#7](-[#1])-[#6](=[#8])-[#6](-[#1])=[#6]-[#1]",
    ),
    (
        "het_thio_65_C(2)",
        "n:1:c(:n(:c:2:c:1:c:c:c:c:2)-[#6](-[#1])-[#1])-[#16]-[#6](-[#1])(-[#1])-[#6](=[#8])-[#7](-[#1])-[#7]=[#6](-[#1])-[#6](-[#1])=[#6]-[#1]",
    ),
    (
        "hydroquin_A(2)",
        "c:1(:c:c(:c(:c:c:1)-[#8]-[#1])-[#6](=!@[#6]-[#7])-[#6]=[#8])-[#8]-[#1]",
    ),
    (
        "anthranil_acid_F(2)",
        "c:1(:c:c(:c(:c:c:1)-[#7](-[#1])-[#6](=[#8])-[#6]:[#6])-[#6](=[#8])-[#8]-[#1])-[#8]-[#1]",
    ),
    (
        "pyrrole_I(2)",
        "n2(-[#6](-[#1])-[#1])c-1c(-[#6]:[#6]-[#6]-1=[#8])cc2-[#6](-[#1])-[#1]",
    ),
    (
        "thiophene_amino_H(2)",
        "[#6](-[#1])-[#7](-[#1])-c:1:c(:c(:c(:s:1)-[#6]-[#1])-[#6]-[#1])-[#6](=[#8])-[#7](-[#1])-[#6]:[#6]",
    ),
    (
        "imine_one_fives_C(2)",
        "[#6]:[#6]-[#7;!R]=[#6]-2-[#6](=[!#6&!#1])-c:1:c:c:c:c:c:1-[#7]-2",
    ),
    (
        "keto_phenone_zone_A(2)",
        "c:1:c:c:c:c:c:1-[#6](=[#8])-[#7](-[#1])-[#7]=[#6]-3-c:2:c:c:c:c:c:2-c:4:c:c:c:c:c-3:4",
    ),
    (
        "dyes7A(2)",
        "c:1:c(:c:c:c:c:1)-[#7](-[#6](-[#1])-[#1])-[#6](-[#1])=[#6](-[#1])-[#6]=!@[#6](-[#1])-[#6](-[#1])=[#6]-[#6]=@[#7]-c:2:c:c:c:c:c:2",
    ),
    (
        "het_pyridiniums_B(2)",
        "[#6]:1:2:[!#1]:[#7+](:[!#1]:[#6;!H0,$([#6]-[*])](:[!#1]:1:[#6]:[#6]:[#6]:[#6]:2))~[#6]:[#6]",
    ),
    (
        "het_5_D(2)",
        "[#7]-2(-c:1:c:c:c:c:c:1)-[#7]=[#6](-[#6](-[#1])-[#1])-[#6](-[#1])(-[#16]-[#6])-[#6]-2=[#8]",
    ),
    (
        "thiazole_amine_H(1)",
        "c:1:c:c:c(:c:c:1-[#7](-[#1])-c2nc(c(-[#1])s2)-c:3:c:c:c(:c:c:3)-[#6](-[#1])(-[#6]-[#1])-[#6]-[#1])-[#6](=[#8])-[#8]-[#1]",
    ),
    (
        "thiazole_amine_I(1)",
        "[#6](-[#1])(-[#1])-[#7](-[#1])-[#6]=[#7]-[#7](-[#1])-c1nc(c(-[#1])s1)-[#6]:[#6]",
    ),
    (
        "het_thio_N_5C(1)",
        "[#6]:[#6]-[#7](-[#1])-[#6](=[#8])-c1c(snn1)-[#7](-[#1])-[#6]:[#6]",
    ),
    (
        "sulfonamide_F(1)",
        "[#8]=[#16](=[#8])(-[#6]:[#6])-[#7](-[#1])-c1nc(cs1)-[#6]:[#6]",
    ),
    (
        "thiazole_amine_J(1)",
        "[#8]=[#16](=[#8])(-[#6]:[#6])-[#7](-[#1])-[#7](-[#1])-c1nc(cs1)-[#6]:[#6]",
    ),
    (
        "het_65_F(1)",
        "s2c:1:n:c:n:c(:c:1c(c2-[#6](-[#1])-[#1])-[#6](-[#1])-[#1])-[#7]-[#7]=[#6]-c3ccco3",
    ),
    (
        "keto_keto_beta_E(1)",
        "[#6](=[#8])-[#6](-[#1])=[#6](-[#8]-[#1])-[#6](-[#8]-[#1])=[#6](-[#1])-[#6](=[#8])-[#6]",
    ),
    (
        "ene_five_one_B(1)",
        "c:2(:c:1-[#6](-[#6](-[#6](-c:1:c(:c(:c:2-[#1])-[#1])-[#1])(-[#1])-[#1])=[#8])=[#6](-[#6](-[#1])-[#1])-[#6](-[#1])-[#1])-[#1]",
    ),
    (
        "keto_keto_beta_zone(1)",
        "[#6]:[#6]-[#7](-[#1])-[#7]=[#6](-[#6](-[#1])-[#1])-[#6](-[#1])(-[#1])-[#6](-[#6](-[#1])-[#1])=[#7]-[#7](-[#1])-[#6]:[#6]",
    ),
    (
        "thio_urea_L(1)",
        "[#6;X4]-[#16;X2]-[#6](=[#7]-[!#1]:[!#1]:[!#1]:[!#1])-[#7](-[#1])-[#7]=[#6]",
    ),
    (
        "het_thio_urea_ene(1)",
        "[#6]-1(=[#7]-[#7](-[#6](-[#16]-1)=[#6](-[#1])-[#6]:[#6])-[#6]:[#6])-[#6]=[#8]",
    ),
    (
        "cyano_amino_het_A(1)",
        "c:1(:c(:c:2:c(:n:c:1-[#7](-[#1])-[#1]):c:c:c(:c:2-[#7](-[#1])-[#1])-[#6]#[#7])-[#6]#[#7])-[#6]#[#7]",
    ),
    (
        "tetrazole_hzide(1)",
        "[!#1]:1:[!#1]:[!#1]:[!#1](:[!#1]:[!#1]:1)-[#6](-[#1])=[#6](-[#1])-[#6](-[#7](-[#1])-[#7](-[#1])-c2nnnn2-[#6])=[#8]",
    ),
    (
        "imine_naphthol_A(1)",
        "c:1:2:c(:c(:c(:c(:c:1:c(:c(:c(:c:2-[#1])-[#1])-[#6](=[#7]-[#6]:[#6])-[#6](-[#1])-[#1])-[#8]-[#1])-[#1])-[#1])-[#1])-[#1]",
    ),
    (
        "misc_anisole_A(1)",
        "c:1(:c(:c:2:c(:c(:c:1-[#8]-[#6](-[#1])-[#1])-[#1]):c(:c(:c(:c:2-[#7](-[#1])-[#6](-[#1])(-[#1])-[#1])-[#1])-c:3:c(:c(:c(:c(:c:3-[#1])-[#1])-[#8]-[#6](-[#1])-[#1])-[#8]-[#6](-[#1])-[#1])-[#1])-[#1])-[#1])-[#8]-[#6](-[#1])-[#1]",
    ),
    (
        "het_thio_665(1)",
        "c:1:c:c-2:c(:c:c:1)-[#16]-c3c(-[#7]-2)cc(s3)-[#6](-[#1])-[#1]",
    ),
    (
        "anil_di_alk_L(1)",
        "c:1:c:c:c-2:c(:c:1)-[#6](-[#6](-[#7]-2-[#6](-[#1])(-[#1])-[#6](-[#1])(-[#1])-[#7]-4-[#6](-c:3:c:c:c:c:c:3-[#6]-4=[#8])=[#8])(-[#1])-[#1])(-[#1])-[#1]",
    ),
    (
        "colchicine_B(1)",
        "c:1(:c:c:c(:c:c:1)-[#6]-,:3=,:[#6]-,:[#6](-,:c2cocc2-,:[#6](=,:[#6]-,:3)-[#8]-[#1])=[#8])-[#16]-[#6](-[#1])-[#1]",
    ),
    (
        "misc_aminoacid_A(1)",
        "[#6;X4]-c:1:c(:c(:c(:c(:c:1-[#1])-[#1])-[#6](=[#8])-[#7](-[#1])-[#6](-[#1])(-[#6](-[#1])(-[#1])-[#6](-[#1])(-[#1])-[#16]-[#6](-[#1])(-[#1])-[#1])-[#6](=[#8])-[#8]-[#1])-[#1])-[#1]",
    ),
    (
        "imidazole_amino_A(1)",
        "n:1:c(:n(:c(:c:1-c:2:c:c:c:c:c:2)-c:3:c:c:c:c:c:3)-[#7]=!@[#6])-[#7](-[#1])-[#1]",
    ),
    (
        "phenol_sulfite_A(1)",
        "[#6](-c:1:c:c:c(:c:c:1)-[#8]-[#1])(-c:2:c:c:c(:c:c:2)-[#8]-[#1])-[#8]-[#16](=[#8])=[#8]",
    ),
    (
        "het_66_D(1)",
        "c:2:c:c:1:n:c(:c(:n:c:1:c:c:2)-[#6](-[#1])(-[#1])-[#6](=[#8])-[#6]:[#6])-[#6](-[#1])(-[#1])-[#6](=[#8])-[#6]:[#6]",
    ),
    (
        "misc_anisole_B(1)",
        "c:1(:c(:c(:c(:c(:c:1-[#1])-[#8]-[#6](-[#1])-[#1])-[#8]-[#6](-[#1])-[#1])-[#1])-[#1])-[#6](=[#8])-[#6](-[#1])(-[#1])-[#7](-[#6](-[#1])-[#1])-c:2:c:c:c(-[#6](-[#1])-[#1])c:c:2",
    ),
    (
        "tetrazole_A(1)",
        "[#6](-[#1])(-[#1])-c1nnnn1-c:2:c(:c(:c(:c(:c:2-[#1])-[#1])-[#8]-[#6](-[#1])(-[#1])-[#1])-[#1])-[#1]",
    ),
    (
        "het_65_G(1)",
        "[#6]-2(=[#7]-c1c(c(nn1-[#6](-[#6]-2(-[#1])-[#1])=[#8])-[#7](-[#1])-[#1])-[#7](-[#1])-[#1])-[#6]",
    ),
    (
        "misc_trityl_A(1)",
        "[#6](-[#6]:[#6])(-[#6]:[#6])(-[#6]:[#6])-[#16]-[#6]:[#6]-[#6](=[#8])-[#8]-[#1]",
    ),
    (
        "misc_pyridine_OC(1)",
        "[#8]=[#6](-c:1:c(:c(:n:c(:c:1-[#1])-[#8]-[#6](-[#1])(-[#1])-[#1])-[#8]-[#6](-[#1])(-[#1])-[#1])-[#1])-[#7](-[#1])-[#6](-[#1])(-[#6](-[#1])-[#1])-[#6](-[#1])-[#1]",
    ),
    (
        "het_6_hydropyridone(1)",
        "[#7]-1=[#6](-[#7](-[#6](-[#6](-[#6]-1(-[#1])-[#6]:[#6])(-[#1])-[#1])=[#8])-[#1])-[#7]-[#1]",
    ),
    (
        "misc_stilbene(1)",
        "[#6]-1(=[#6](-[#6](-[#6](-[#6](-[#6]-1(-[#1])-[#1])(-[#1])-[#6](=[#8])-[#6])(-[#1])-[#6](=[#8])-[#8]-[#1])(-[#1])-[#1])-[#6]:[#6])-[#6]:[#6]",
    ),
    (
        "misc_imidazole(1)",
        "[#6](-[#1])(-c:1:c(:c(:c(:c(:c:1-[#1])-[#1])-[Cl])-[#1])-[#1])(-c:2:c(:c(:c(:c(:c:2-[#1])-[#1])-[Cl])-[#1])-[#1])-[#8]-[#6](-[#1])(-[#1])-[#6](-[#1])(-[#1])-[#6](-[#1])(-[#1])-c3nc(c(n3-[#6](-[#1])(-[#1])-[#1])-[#1])-[#1]",
    ),
    (
        "anil_NH_no_alk_A(1)",
        "n:1:c(:c(:c(:c(:c:1-[#1])-[#7](-[#1])-[#1])-[#1])-[#1])-[#7](-[#1])-[#6]:[#6]",
    ),
    (
        "het_6_imidate_B(1)",
        "[#7](-[#1])(-c:1:c(:c(:c(:c(:c:1-[#1])-[#1])-[#1])-[#1])-[#8]-[#1])-[#6]-,:2=,:[#6](-,:[#8]-,:[#6](-,:[#7]=,:[#7]-,:2)=[#7])-[#7](-[#1])-[#1]",
    ),
    (
        "anil_alk_B(1)",
        "[#7](-[#1])(-c:1:c(:c(:c(:c(:c:1-[#1])-[#1])-[#6](-[#1])-[#1])-[#1])-[#1])-[#6](-[#1])(-[#1])-[#6](-[#1])(-[#1])-c:2:c(:c(:c(:c(:c:2-[#1])-[#1])-[#8]-[#6](-[#1])-[#1])-[#1])-[#1]",
    ),
    (
        "styrene_anil_A(1)",
        "c:1:c:c-3:c(:c:c:1)-c:2:c:c:c(:c:c:2-[#6]-3=[#6](-[#1])-[#6])-[#7](-[#1])-[#1]",
    ),
    (
        "misc_aminal_acid(1)",
        "c:1:c:c-2:c(:c:c:1)-[#7](-[#6](-[#8]-[#6]-2)(-[#6](=[#8])-[#8]-[#1])-[#6](-[#1])-[#1])-[#6](=[#8])-[#6](-[#1])-[#1]",
    ),
    (
        "anil_no_alk_D(1)",
        "n:1:c(:c(:c(:c(:c:1-[#7](-[#1])-[#1])-[#6](-[#1])-[#1])-[#1])-[#6](-[#1])-[#1])-[#7](-[#1])-[#1]",
    ),
    (
        "anil_alk_C(1)",
        "[#7](-[#1])(-c:1:c:c:c:c:c:1)-[#6](-[#6])(-[#6])-c:2:c(:c(:c(:c(:c:2-[#1])-[#1])-[#8]-[#6](-[#1])-[#1])-[#1])-[#1]",
    ),
    (
        "misc_anisole_C(1)",
        "[#7](-[#1])(-c:1:c(:c(:c(:c(:c:1-[#1])-[#1])-[#8]-[#6](-[#1])(-[#1])-[#1])-[#8]-[#6]-[#1])-[#1])-[#6](=[#8])-[#7](-[#1])-[#6](-[#1])(-[#1])-[#6](-[#1])(-[#1])-[#6](-[#1])(-[#1])-[#7](-[#6](-[#1])(-[#1])-[#1])-[#6]:[#6]",
    ),
    (
        "het_465_misc(1)",
        "c:1-2:c:c-3:c(:c:c:1-[#8]-[#6]-[#8]-2)-[#6]-[#6]-3",
    ),
    (
        "anthranil_acid_G(1)",
        "c:1(:c(:c(:c(:c(:c:1-[#1])-[#1])-[#8]-[#6](-[#1])-[#1])-[#1])-[#6](=[#8])-[#8]-[#1])-[#7](-[#1])-[#6]:[#6]",
    ),
    (
        "anil_di_alk_M(1)",
        "c:1(:c:4:c(:n:c(:c:1-[#6](-[#1])(-[#1])-[#7]-3-c:2:c(:c(:c(:c(:c:2-[#6](-[#1])(-[#1])-[#6]-3(-[#1])-[#1])-[#1])-[#1])-[#1])-[#1])-[#1]):c(:c(:c(:c:4-[#1])-[#1])-[#1])-[#1])-[#1]",
    ),
    (
        "anthranil_acid_H(1)",
        "c:1:c(:c2:c(:c:c:1)c(c(n2-[#1])-[#6]:[#6])-[#6]:[#6])-[#6](=[#8])-[#8]-[#1]",
    ),
    (
        "thio_urea_M(1)",
        "[#6]:[#6]-[#7](-[#6](-[#1])-[#1])-[#6](-[#1])(-[#1])-[#6](-[#1])(-[#1])-[#6](-[#1])(-[#1])-[#7](-[#1])-[#6](=[#16])-[#7](-[#1])-c:1:c(:c(:c(:c(:c:1-[F,Cl,Br,I])-[#1])-[#6](-[#1])-[#1])-[#1])-[#1]",
    ),
    (
        "thiazole_amine_K(1)",
        "n:1:c3:c(:c:c2:c:1nc(s2)-[#7])sc(n3)-[#7]",
    ),
    (
        "het_thio_5_imine_A(1)",
        "[#7]=[#6]-1-[#16]-[#6](=[#7])-[#7]=[#6]-1",
    ),
    (
        "thio_amide_E(1)",
        "c:1:c(:n:c:c:c:1)-[#6](=[#16])-[#7](-[#1])-c:2:c(:c:c:c:c:2)-[#8]-[#6](-[#1])-[#1]",
    ),
    (
        "het_thio_676_B(1)",
        "c:1-2:c(:c(:c(:c(:c:1-[#6](-c:3:c(-[#16]-[#6]-2(-[#1])-[#1]):c(:c(-[#1]):c(:c:3-[#1])-[#1])-[#1])-[#8]-[#6]:[#6])-[#1])-[#1])-[#1])-[#1]",
    ),
    (
        "sulfonamide_G(1)",
        "[#6](-[#1])(-[#1])(-[#1])-c:1:c(:c(:c(:c(:n:1)-[#7](-[#1])-[#16](-c:2:c(:c(:c(:c(:c:2-[#1])-[#1])-[#8]-[#6](-[#1])(-[#1])-[#6](-[#1])(-[#1])-[#6](-[#1])-[#1])-[#1])-[#1])(=[#8])=[#8])-[#1])-[#1])-[#1]",
    ),
    (
        "thio_thiomorph_Z(1)",
        "[#6](=[#8])(-[#7]-1-[#6]-[#6]-[#16]-[#6]-[#6]-1)-c:2:c(:c(:c(:c(:c:2-[#16]-[#6](-[#1])-[#1])-[#1])-[#1])-[#1])-[#1]",
    ),
    (
        "naphth_ene_one_A(1)",
        "c:1:c:c:3:c:2:c(:c:1)-[#6](-[#6]=[#6](-c:2:c:c:c:3)-[#8]-[#6](-[#1])-[#1])=[#8]",
    ),
    (
        "naphth_ene_one_B(1)",
        "c:1-3:c:2:c(:c(:c:c:1)-[#7]):c:c:c:c:2-[#6](-[#6]=[#6]-3-[#6](-[F])(-[F])-[F])=[#8]",
    ),
    (
        "amino_acridine_A(1)",
        "c:1:c:c:c:c:2:c:1:c:c:3:c(:n:2):n:c:4:c(:c:3-[#7]):c:c:c:c:4",
    ),
    (
        "keto_phenone_B(1)",
        "c:1:c-3:c(:c:c:c:1)-[#6]-2=[#7]-[!#1]=[#6]-[#6]-[#6]-2-[#6]-3=[#8]",
    ),
    (
        "hzone_acid_A(1)",
        "c:1-3:c(:c(:c(:c(:c:1-[#1])-[#1])-[#8]-[#6](-[#1])-[#1])-[#1])-[#6](=[#7]-[#7](-[#1])-c:2:c(:c(:c(:c(:c:2-[#1])-[#1])-[#6](=[#8])-[#8]-[#1])-[#1])-[#1])-c:4:c-3:c(:c(:c(:c:4-[#1])-[#8]-[#6](-[#1])-[#1])-[#1])-[#1]",
    ),
    (
        "sulfonamide_H(1)",
        "c:1(:c(:c(:c(:c(:c:1-[#1])-[#1])-[#7](-[#1])-[#1])-[#1])-[#1])-[#16](=[#8])(=[#8])-[#7](-[#1])-c:2:n:n:c(:c(:c:2-[#1])-[#1])-[#1]",
    ),
    (
        "het_565_indole(1)",
        "c2(c(-[#1])n(-[#6](-[#1])-[#1])c:3:c(:c(:c:1n(c(c(c:1:c2:3)-[#1])-[#1])-[#6](-[#1])-[#1])-[#8]-[#6](-[#1])-[#1])-[#8]-[#6](-[#1])-[#1])-[#1]",
    ),
    (
        "pyrrole_J(1)",
        "c1(c-2c(c(n1-[#6](-[#8])=[#8])-[#6](-[#1])-[#1])-[#16]-[#6](-[#1])(-[#1])-[#16]-2)-[#6](-[#1])-[#1]",
    ),
    (
        "pyrazole_amino_B(1)",
        "s1ccnc1-c2c(n(nc2-[#1])-[#1])-[#7](-[#1])-[#1]",
    ),
    (
        "pyrrole_K(1)",
        "c1(c(c(c(n1-[#1])-c:2:c(:c(:c(:c(:c:2-[#1])-[#1])-[#1])-[#1])-[#1])-[#6](-[#1])-[#1])-[#1])-[#6](=[#8])-[#8]-[#1]",
    ),
    (
        "anthranil_acid_I(1)",
        "c:1(:c(:c(:c(:o:1)-[#6])-[#1])-[#1])-[#6](=[#8])-[#7](-[#1])-[#6]:2:[#6](-[#1]):[#6](-[#1]):[#6](-[#1]):[#6](-[#1]):[#6]:2-[#6](=[#8])-[#8]-[#1]",
    ),
    (
        "thio_amide_F(1)",
        "[!#1]:[#6]-[#6](=[#16])-[#7](-[#1])-[#7](-[#1])-[#6]:[!#1]",
    ),
    (
        "ene_one_C(1)",
        "[#6]-1(=[#8])-[#6](-[#6](-[#6]#[#7])=[#6](-[#1])-[#7])-[#6](-[#7])-[#6]=[#6]-1",
    ),
    (
        "het_65_H(1)",
        "c2(c-,:1n(-,:[#6](-,:[#6]=,:[#6]-,:[#7]-,:1)=[#8])nc2-c3cccn3)-[#6]#[#7]",
    ),
    (
        "cyano_imine_D(1)",
        "[#8]=[#6]-1-[#6](=[#7]-[#7]-[#6]-[#6]-1)-[#6]#[#7]",
    ),
    (
        "cyano_misc_A(1)",
        "c:2(:c:1:c:c:c:c:c:1:n:n:c:2)-[#6](-[#6]:[#6])-[#6]#[#7]",
    ),
    (
        "ene_misc_C(1)",
        "c:1:c:c-2:c(:c:c:1)-[#6]=[#6]-[#6](-[#7]-2-[#6](=[#8])-[#7](-[#1])-c:3:c:c(:c(:c:c:3)-[#8]-[#6](-[#1])-[#1])-[#8]-[#6](-[#1])-[#1])(-[#6](-[#1])-[#1])-[#6](-[#1])-[#1]",
    ),
    (
        "het_66_E(1)",
        "c:2:c:c:1:n:c(:c(:n:c:1:c:c:2)-c:3:c:c:c:c:c:3)-c:4:c:c:c:c:c:4-[#8]-[#1]",
    ),
    (
        "keto_keto_beta_F(1)",
        "[#6](-[#1])(-[#1])-[#6](-[#8]-[#1])=[#6](-[#6](=[#8])-[#6](-[#1])-[#1])-[#6](-[#1])-[#6]#[#6]",
    ),
    (
        "misc_naphthimidazole(1)",
        "c:1:c:4:c(:c:c2:c:1nc(n2-[#1])-[#6]-[#8]-[#6](=[#8])-c:3:c:c(:c:c(:c:3)-[#7](-[#1])-[#1])-[#7](-[#1])-[#1]):c:c:c:c:4",
    ),
    (
        "naphth_ene_one_C(1)",
        "c:2(:c:1:c:c:c:c-3:c:1:c(:c:c:2)-[#6]=[#6]-[#6]-3=[#7])-[#7]",
    ),
    (
        "keto_phenone_C(1)",
        "c:2(:c:1:c:c:c:c:c:1:c-3:c(:c:2)-[#6](-c:4:c:c:c:c:c-3:4)=[#8])-[#8]-[#1]",
    ),
    (
        "coumarin_C(1)",
        "[#6]-,:2(-,:[#6]=,:[#7]-,:c:1:c:c(:c:c:c:1-,:[#8]-,:2)-[Cl])=[#8]",
    ),
    (
        "thio_est_cyano_A(1)",
        "[#6]-1=[#6]-[#7](-[#6](-c:2:c-1:c:c:c:c:2)(-[#6]#[#7])-[#6](=[#16])-[#16])-[#6]=[#8]",
    ),
    (
        "het_65_imidazole(1)",
        "c2(nc:1:c(:c(:c(:c(:c:1-[#1])-[#1])-[#1])-[#1])n2-[#6])-[#7](-[#1])-[#6](-[#7](-[#1])-c:3:c(:c:c:c:c:3-[#1])-[#1])=[#8]",
    ),
    (
        "anthranil_acid_J(1)",
        "[#7](-[#1])(-[#6]:[#6])-c:1:c(-[#6](=[#8])-[#8]-[#1]):c:c:c(:n:1)-,:[#6]:[#6]",
    ),
    (
        "colchicine_het(1)",
        "c:1-,:3:c(:c:c:c:c:1)-,:[#16]-,:[#6](=[#7]-[#7]=[#6]-,:2-,:[#6]=,:[#6]-,:[#6]=,:[#6]-,:[#6]=,:[#6]-,:2)-,:[#7]-,:3-[#6](-[#1])-[#1]",
    ),
    (
        "ene_misc_D(1)",
        "c:1-2:c(:c(:c(:c(:c:1-[#1])-[#8]-[#6](-[#1])-[#1])-[#8]-[#6](-[#1])-[#1])-[#1])-[#6](=[#6](-[#6])-[#16]-[#6]-2(-[#1])-[#1])-[#6]",
    ),
    (
        "indole_3yl_alk_B(1)",
        "c:12:c(:c(:c(:c(:c:1-[#1])-[#1])-[#1])-[#1])c(c(-[#6]:[#6])n2-!@[#6]:[#6])-[#6](-[#1])-[#1]",
    ),
    (
        "anil_OH_no_alk_A(1)",
        "[#7](-[#1])(-[#1])-c:1:c:c:c(:c:c:1-[#8]-[#1])-[#16](=[#8])(=[#8])-[#8]-[#1]",
    ),
    (
        "thiazole_amine_L(1)",
        "s:1:c:c:c(:c:1-[#1])-c:2:c:s:c(:n:2)-[#7](-[#1])-[#1]",
    ),
    (
        "pyrazole_amino_A(1)",
        "c1c(-[#7](-[#1])-[#1])nnc1-c2c(-[#6](-[#1])-[#1])oc(c2-[#1])-[#1]",
    ),
    ("het_thio_N_5D(1)", "n1nscc1-c2nc(no2)-[#6]:[#6]"),
    (
        "anil_alk_indane(1)",
        "c:1(:c:c-3:c(:c:c:1)-[#7]-[#6]-4-c:2:c:c:c:c:c:2-[#6]-[#6]-3-4)-[#6;X4]",
    ),
    (
        "anil_di_alk_N(1)",
        "c:1-2:c(:c(:c(:c(:c:1-[#1])-[#1])-[#1])-[#1])-[#6](=[#6](-[#1])-[#6]-3-[#6](-[#6]#[#7])-[#6](-[#1])(-[#1])-[#6](-[#1])-[#7]-2-3)-[#1]",
    ),
    (
        "het_666_C(1)",
        "c:2-,:3:c(:c:c:1:c:c:c:c:c:1:c:2)-,:[#7](-[#6](-[#1])-[#1])-,:[#6](=[#8])-,:[#6](=,:[#7]-,:3)-[#6]:[#6]-[#7](-[#1])-[#6](-[#1])-[#1]",
    ),
    (
        "ene_one_D(1)",
        "[#6](-[#8]-[#1]):[#6]-[#6](=[#8])-[#6](-[#1])=[#6](-[#6])-[#6]",
    ),
    (
        "anil_di_alk_indol(1)",
        "c:1:2:c(:c(:c(:c(:c:1-[#1])-[#1])-[#7](-[#6](-[#1])-[#1])-[#6](-[#1])-[#1])-[#1]):c(:c(-[#1]):n:2-[#1])-[#16](=[#8])=[#8]",
    ),
    (
        "anil_no_alk_indol_A(1)",
        "c:1:2:c(:c(:c(:c(:c:1-[#1])-[#1])-[#7](-[#1])-[#1])-[#1]):c(:c(-[#1]):n:2-[#6](-[#1])-[#1])-[#1]",
    ),
    (
        "dhp_amino_CN_G(1)",
        "[#16;X2]-1-[#6]=[#6](-[#6]#[#7])-[#6](-[#6])(-[#6]=[#8])-[#6](=[#6]-1-[#7](-[#1])-[#1])-[$([#6]=[#8]),$([#6]#[#7])]",
    ),
    (
        "anil_di_alk_dhp(1)",
        "[#7]-2-[#6]=[#6](-[#6]=[#8])-[#6](-c:1:c:c:c(:c:c:1)-[#7](-[#6](-[#1])-[#1])-[#6](-[#1])-[#1])-[#6]~3=,:[#6]-2~[#7]~[#6](~[#16])~[#7]~[#6]~3~[#7]",
    ),
    (
        "anthranil_amide_A(1)",
        "c:1:c(:c:c:c:c:1)-[#6](=[#8])-[#7](-[#1])-c:2:c(:c:c:c:c:2)-[#6](=[#8])-[#7](-[#1])-[#7](-[#1])-c:3:n:c:c:s:3",
    ),
    (
        "hzone_anthran_Z(1)",
        "c:1:c:2:c(:c:c:c:1):c(:c:3:c(:c:2):c:c:c:c:3)-[#6]=[#7]-[#7](-[#1])-c:4:c:c:c:c:c:4",
    ),
    (
        "ene_one_amide_A(1)",
        "c:1:c(:c:c:c:c:1)-[#6](-[#1])-[#7]-[#6](=[#8])-[#6](-[#7](-[#1])-[#6](-[#1])-[#1])=[#6](-[#1])-[#6](=[#8])-c:2:c:c:c(:c:c:2)-[#8]-[#6](-[#1])-[#1]",
    ),
    (
        "het_76_A(1)",
        "s:1:c(:c(-[#1]):c(:c:1-[#6]-3=[#7]-c:2:c:c:c:c:c:2-[#6](=[#7]-[#7]-3-[#1])-c:4:c:c:n:c:c:4)-[#1])-[#1]",
    ),
    (
        "thio_urea_N(1)",
        "o:1:c(:c(-[#1]):c(:c:1-[#6](-[#1])(-[#1])-[#7](-[#1])-[#6](=[#16])-[#7](-[#6]-[#1])-[#6](-[#1])(-[#1])-c:2:c:c:c:c:c:2)-[#1])-[#1]",
    ),
    (
        "anil_di_alk_coum(1)",
        "c:1:c(:c:c:c:c:1)-[#7](-[#6]-[#1])-[#6](-[#1])-[#6](-[#1])-[#6](-[#1])-[#7](-[#1])-[#6](=[#8])-[#6]-,:2=,:[#6](-,:[#8]-,:[#6](-,:[#6](=,:[#6]-,:2-[#6](-[#1])-[#1])-[#1])=[#8])-[#6](-[#1])-[#1]",
    ),
    (
        "ene_one_amide_B(1)",
        "c2-3:c:c:c:1:c:c:c:c:c:1:c2-[#6](-[#1])-[#6;X4]-[#7]-[#6]-3=[#6](-[#1])-[#6](=[#8])-[#7](-[#6](-[#1])-[#1])-[#6](-[#1])-[#1]",
    ),
    (
        "het_thio_656c(1)",
        "c:1:c(:c:c:c:c:1)-[#6]-4=[#7]-[#7]:2:[#6](:[#7+]:c:3:c:2:c:c:c:c:3)-[#16]-[#6;X4]-4",
    ),
    (
        "het_5_ene(1)",
        "[#6]-2(=[#8])-[#6](=[#6](-[#6](-[#1])-[#1])-[#7](-[#1])-[#6](-[#1])(-[#1])-[#6](-[#1])(-[#1])-[#6](-[#1])-[#1])-[#7]=[#6](-c:1:c:c:c:c:c:1)-[#8]-2",
    ),
    (
        "thio_imide_A(1)",
        "c:1:c(:c:c:c:c:1)-[#7]-2-[#6](=[#8])-[#6](=[#6](-[#1])-[#6]-2=[#8])-[#16]-c:3:c:c:c:c:c:3",
    ),
    (
        "dhp_amidine_A(1)",
        "[#7]-,:1(-[#1])-,:[#7]=,:[#6](-[#7]-[#1])-,:[#16]-,:[#6](=,:[#6]-,:1-,:[#6]:[#6])-,:[#6]:[#6]",
    ),
    (
        "thio_urea_O(1)",
        "c:1(:c(:c-3:c(:c(:c:1-[#7](-[#1])-[#6](=[#16])-[#7](-[#1])-[#6](-[#1])-c:2:c(:c(:c(:o:2)-[#6]-[#1])-[#1])-[#1])-[#1])-[#8]-[#6](-[#8]-3)(-[#1])-[#1])-[#1])-[#1]",
    ),
    (
        "anil_di_alk_O(1)",
        "c:1(:c(:c(:c(:c(:c:1-[#7](-[#1])-[#6](=[#16])-[#7](-[#1])-c:2:c:c:c:c:c:2)-[#1])-[#7](-[#6](-[#1])-[#1])-[#6](-[#1])-[#1])-[#1])-[#1])-[#1]",
    ),
    (
        "thio_urea_P(1)",
        "[#8]=[#6]-!@n:1:c:c:c-,:2:c:1-,:[#7](-[#1])-,:[#6](=[#16])-,:[#7]-,:2-[#1]",
    ),
    (
        "het_pyraz_misc(1)",
        "[#6](-[F])(-[F])-[#6](=[#8])-[#7](-[#1])-c:1:c(-[#1]):n(-[#6](-[#1])(-[#1])-[#6](-[#1])(-[#1])-[#8]-[#6](-[#1])(-[#1])-[#6]:[#6]):n:c:1-[#1]",
    ),
    (
        "diazox_C(1)",
        "[#7]-2=[#7]-[#6]:1:[#7]:[!#6&!#1]:[#7]:[#6]:1-[#7]=[#7]-[#6]:[#6]-2",
    ),
    (
        "diazox_D(1)",
        "[#6]-2(-[#1])(-[#8]-[#1])-[#6]:1:[#7]:[!#6&!#1]:[#7]:[#6]:1-[#6](-[#1])(-[#8]-[#1])-[#6]=[#6]-2",
    ),
    (
        "misc_cyclopropane(1)",
        "[#6]-1(-[#6](-[#1])(-[#1])-[#6]-1(-[#1])-[#1])(-[#6](=[#8])-[#7](-[#1])-c:2:c:c:c(:c:c:2)-[#8]-[#6](-[#1])(-[#1])-[#8])-[#16](=[#8])(=[#8])-[#6]:[#6]",
    ),
    (
        "imine_ene_one_B(1)",
        "[#6]-1:[#6]-[#6](=[#8])-[#6]=[#6]-1-[#7]=[#6](-[#1])-[#7](-[#6;X4])-[#6;X4]",
    ),
    (
        "coumarin_D(1)",
        "c:1:c:c(:c:c-,:2:c:1-,:[#6](=,:[#6](-[#1])-,:[#6](=[#8])-,:[#8]-,:2)-c:3:c:c:c:c:c:3)-[#8]-[#6](-[#1])(-[#1])-[#6]:[#8]:[#6]",
    ),
    (
        "misc_furan_A(1)",
        "c:1:c(:o:c(:c:1-[#6](-[#1])-[#1])-[#6](-[#1])-[#1])-[#6](-[#1])(-[#1])-[#7]-[#6](-[#1])(-[#1])-[#6](-[#1])(-[#8]-[#6](-[#1])-[#1])-[#6](-[#1])(-[#1])-[#8]-c:2:c:c-3:c(:c:c:2)-[#8]-[#6](-[#8]-3)(-[#1])-[#1]",
    ),
    (
        "rhod_sat_E(1)",
        "[#7]-4(-c:1:c:c:c:c:c:1)-[#6](=[#8])-[#16]-[#6](-[#1])(-[#7](-[#1])-c:2:c:c:c:c:3:c:c:c:c:c:2:3)-[#6]-4=[#8]",
    ),
    (
        "rhod_sat_imine_A(1)",
        "[#7]-3(-[#6](=[#8])-c:1:c:c:c:c:c:1)-[#6](=[#7]-c:2:c:c:c:c:c:2)-[#16]-[#6](-[#1])(-[#1])-[#6]-3=[#8]",
    ),
    (
        "rhod_sat_F(1)",
        "[#7]-2(-c:1:c:c:c:c:c:1)-[#6](=[#8])-[#16]-[#6](-[#1])(-[#1])-[#6]-2=[#16]",
    ),
    (
        "het_thio_5_imine_B(1)",
        "[#7]-1(-[#6](-[#1])-[#1])-[#6](=[#16])-[#7](-[#6]:[#6])-[#6](=[#7]-[#6]:[#6])-[#6]-1=[#7]-[#6]:[#6]",
    ),
    (
        "het_thio_5_imine_C(1)",
        "[#16]-1-[#6](=[#7]-[#7]-[#1])-[#16]-[#6](=[#7]-[#6]:[#6])-[#6]-1=[#7]-[#6]:[#6]",
    ),
    (
        "ene_five_het_N(1)",
        "[#6]-2(=[#8])-[#6](=[#6](-[#1])-c:1:c(:c:c:c(:c:1)-[F,Cl,Br,I])-[#8]-[#6](-[#1])-[#1])-[#7]=[#6](-[#16]-[#6](-[#1])-[#1])-[#16]-2",
    ),
    (
        "thio_carbam_A(1)",
        "[#6](-[#1])(-[#1])-[#16]-[#6](=[#16])-[#7](-[#1])-[#6](-[#1])(-[#1])-[#6]:[#6]",
    ),
    (
        "misc_anilide_A(1)",
        "c:1(:c(:c(:c(:c(:c:1-[#1])-[#1])-[#6](-[#1])-[#1])-[#7](-[#1])-[#6](=[#8])-[#6](-[#1])(-[#1])-[#6](-[#1])(-[#1])-[#6]:[#6])-[#1])-[#7](-[#1])-[#6](=[#8])-[#6](-[#1])(-[#1])-[#6](-[#1])(-[#1])-[#6]:[#6]",
    ),
    (
        "misc_anilide_B(1)",
        "c:1(:c(:c(:c(:c(:c:1-[#6](-[#1])-[#1])-[#1])-[Br])-[#1])-[#6](-[#1])-[#1])-[#7](-[#1])-[#6](=[#8])-[#7](-[#1])-[#6](-[#1])(-[#1])-[#6](-[#1])(-[#1])-[#6](-[#1])-[#1]",
    ),
    (
        "mannich_B(1)",
        "c:1-2:c(:c:c:c(:c:1-[#8]-[#6](-[#1])(-[#1])-[#7](-[#6]:[#6]-[#8]-[#6](-[#1])-[#1])-[#6]-2(-[#1])-[#1])-[#1])-[#1]",
    ),
    (
        "mannich_catechol_A(1)",
        "c:1-2:c(:c(:c(:c(:c:1-[#8]-[#6](-[#1])(-[#1])-[#7](-[#6](-[#1])-[#1])-[#6]-2(-[#1])-[#1])-[#1])-[#8])-[#8])-[#1]",
    ),
    (
        "anil_alk_D(1)",
        "[#7](-[#1])(-c:1:c(:c(:c(:c(:c:1-[#1])-[#1])-[#6](-[#1])(-[#6](-[#1])-[#1])-[#6](-[#1])-[#1])-[#1])-[#1])-[#6](-[#1])(-[#1])-[#6](-[#1])(-[#1])-[#7](-[#6](-[#1])-[#1])-[#6](-[#1])-[#1]",
    ),
    (
        "het_65_I(1)",
        "n:1:2:c:c:c(:c:c:1:c:c(:c:2-[#6](=[#8])-[#6]:[#6])-[#6]:[#6])-[#6](~[#8])~[#8]",
    ),
    (
        "misc_urea_A(1)",
        "c:1(:c(:c(:c(:c(:c:1-[#1])-[#1])-[#1])-[#6](=[#6](-[#1])-[#1])-[#6](-[#1])-[#1])-[#1])-[#6](-[#6;X4])(-[#6;X4])-[#7](-[#1])-[#6](=[#8])-[#7](-[#6](-[#1])(-[#1])-[#6](-[#1])-[#1])-[#6](-[#1])(-[#1])-[#6](-[#1])(-[#1])-[#6](-[#1])-[#6](-[#1])(-[#1])-[#6]:[#6]",
    ),
    (
        "imidazole_C(1)",
        "[#6]-3(-[#1])(-n:1:c(:n:c(:c:1-[#1])-[#1])-[#1])-c:2:c(:c(:c(:c(:c:2-[#1])-[Br])-[#1])-[#1])-[#6](-[#1])(-[#1])-[#6](-[#1])(-[#1])-c:4:c-3:c(:c(:c(:c:4-[#1])-[#1])-[#1])-[#1]",
    ),
    (
        "styrene_imidazole_A(1)",
        "[#6](=[#6](-[#1])-[#6](-[#1])(-[#1])-n:1:c(:n:c(:c:1-[#1])-[#1])-[#1])(-[#6]:[#6])-[#6]:[#6]",
    ),
    (
        "thiazole_amine_M(1)",
        "c:1(:n:c(:c(-[#1]):s:1)-c:2:c:c:n:c:c:2)-[#7](-[#1])-[#6]:[#6]-[#6](-[#1])-[#1]",
    ),
    (
        "misc_pyrrole_thiaz(1)",
        "c:1(:n:c(:c(-[#1]):s:1)-c:2:c:c:c:c:c:2)-[#6](-[#1])(-[#6](-[#1])-[#1])-[#6](-[#1])(-[#1])-[#6](-[#1])(-[#1])-[#7]-[#6](-[#1])(-[#1])-c:3:c:c:c:n:3-[#1]",
    ),
    (
        "pyrrole_L(1)",
        "n:1(-[#1]):c(:c(-[#6](-[#1])-[#1]):c(:c:1-[#6](-[#1])(-[#1])-[#6](-[#1])-[#1])-[#6](-[#1])(-[#1])-[#6](-[#1])-[#1])-[#6](=[#8])-[#8]-[#6](-[#1])-[#1]",
    ),
    (
        "het_thio_65_D(1)",
        "c:2(:n:c:1:c(:c(:c:c(:c:1-[#1])-[F,Cl,Br,I])-[#1]):n:2-[#1])-[#16]-[#6](-[#1])(-[#1])-[#6](=[#8])-[#7](-[#1])-[#6]:[#6]",
    ),
    (
        "ene_misc_E(1)",
        "c:1(:c(:c-2:c(:c(:c:1-[#8]-[#6](-[#1])-[#1])-[#1])-[#6]=[#6]-[#6](-[#1])-[#16]-2)-[#1])-[#8]-[#6](-[#1])-[#1]",
    ),
    (
        "thio_cyano_A(1)",
        "[#7]-1(-[#1])-[#6](=[#16])-[#6](-[#1])(-[#6]#[#7])-[#6](-[#1])(-[#6]:[#6])-[#6](=[#6]-1-[#6]:[#6])-[#1]",
    ),
    (
        "cyano_amino_het_B(1)",
        "n:1:c(:c(:c(:c(:c:1-[#16;X2]-c:2:c:c:c:c:c:2-[#7](-[#1])-[#1])-[#6]#[#7])-c:3:c:c:c:c:c:3)-[#6]#[#7])-[#7](-[#1])-[#1]",
    ),
    (
        "cyano_pyridone_G(1)",
        "[#7]-,:2(-c:1:c:c:c(:c:c:1)-[#8]-[#6](-[#1])-[#1])-,:[#6](=[#8])-,:[#6](=,:[#6]-,:[#6](=,:[#7]-,:2)-n:3:c:n:c:c:3)-[#6]#[#7]",
    ),
    (
        "het_65_J(1)",
        "o:1:c(:c:c:2:c:1:c(:c(:c(:c:2-[#1])-[#8]-[#6](-[#1])-[#1])-[#8]-[#6](-[#1])-[#1])-[#1])-[#6](~[#8])~[#8]",
    ),
    ("ene_one_yne_A(1)", "[#6]#[#6]-[#6](=[#8])-[#6]#[#6]"),
    (
        "anil_OH_no_alk_B(1)",
        "c:2(:c:1:c(:c(:c(:c(:c:1:c(:c(:c:2-[#8]-[#1])-[#6]=[#8])-[#1])-[#1])-[#1])-[#1])-[#1])-[#7](-[#1])-[#1]",
    ),
    (
        "hzone_acyl_misc_A(1)",
        "c:1(:c(:c(:[c;!H0,$(c-[#6;!H0;!H1])](:o:1))-[#1])-[#1])-[#6](=[#8])-[#7](-[#1])-[#7]=[#6;!H0,$([#6]-[#6;!H0!H1])]-c:2:c:c:c:c(:c:2)-[*]-[*]-[*]-c:3:c:c:c:o:3",
    ),
    (
        "thiophene_F(1)",
        "[#16](=[#8])(=[#8])-[#7](-[#1])-c:1:c(:c(:c(:s:1)-[#6]-[#1])-[#6]-[#1])-[#6](=[#8])-[#7]-[#1]",
    ),
    (
        "anil_OC_alk_E(1)",
        "[#6](-[#1])(-[#1])-[#8]-c:1:c(:c(:c(:c(:c:1-[#1])-[#1])-[#1])-[#1])-[#7](-[#1])-[#6](-[#1])(-[#1])-[#6](-[#1])(-[#8]-[#1])-[#6](-[#1])-[#1]",
    ),
    (
        "anil_OC_alk_F(1)",
        "[#6](-[#1])(-[#1])-[#8]-c:1:c(:c(:c(:c(:c:1-[#1])-[#1])-[#1])-[#1])-[#7](-[#1])-[#6](-[#1])(-[#6]=[#8])-[#16]",
    ),
    ("het_65_K(1)", "n1nnnc2cccc12"),
    (
        "het_65_L(1)",
        "c:1-,:2:c(-[#1]):s:c(:c:1-,:[#6](=[#8])-,:[#7]-,:[#7]=,:[#6]-,:2-[#7](-[#1])-[#1])-[#6]=[#8]",
    ),
    (
        "coumarin_E(1)",
        "c:1-,:3:c(:c:2:c(:c:c:1-[Br]):o:c:c:2)-,:[#6](=,:[#6]-,:[#6](=[#8])-,:[#8]-,:3)-[#1]",
    ),
    (
        "coumarin_F(1)",
        "c:1-,:3:c(:c:c:c:c:1)-,:[#6](=,:[#6](-[#6](=[#8])-[#7](-[#1])-c:2:n:o:c:c:2-[Br])-,:[#6](=[#8])-,:[#8]-,:3)-[#1]",
    ),
    (
        "coumarin_G(1)",
        "c:1-,:2:c(:c:c(:c:c:1-[F,Cl,Br,I])-[F,Cl,Br,I])-,:[#6](=,:[#6](-[#6](=[#8])-[#7](-[#1])-[#1])-,:[#6](=[#7]-[#1])-,:[#8]-,:2)-[#1]",
    ),
    (
        "coumarin_H(1)",
        "c:1-,:3:c(:c:c:c:c:1)-,:[#6](=,:[#6](-[#6](=[#8])-[#7](-[#1])-c:2:n:c(:c:s:2)-[#6]:[#16]:[#6]-[#1])-,:[#6](=[#8])-,:[#8]-,:3)-[#1]",
    ),
    (
        "het_thio_67_A(1)",
        "[#6](-[#1])(-[#1])-[#16;X2]-c:2:n:n:c:1-[#6]:[#6]-[#7]=[#6]-[#8]-c:1:n:2",
    ),
    (
        "sulfonamide_I(1)",
        "[#16](=[#8])(=[#8])(-c:1:c:n(-[#6](-[#1])-[#1]):c:n:1)-[#7](-[#1])-c:2:c:n(:n:c:2)-[#6](-[#1])(-[#1])-[#6]:[#6]-[#8]-[#6](-[#1])-[#1]",
    ),
    (
        "het_65_mannich(1)",
        "c:1-2:c(:c(:c(:c(:c:1-[#8]-[#6](-[#1])(-[#1])-[#8]-2)-[#6](-[#1])(-[#1])-[#7]-3-[#6](-[#1])(-[#1])-[#6](-[#1])(-[#1])-[#6]:[#6]-3)-[#1])-[#1])-[#1]",
    ),
    (
        "anil_alk_A(1)",
        "[#6](-[#1])(-[#1])-[#8]-[#6]:[#6]-[#6](-[#1])(-[#1])-[#7](-[#1])-c:2:c(:c(:c:1:n(:c(:n:c:1:c:2-[#1])-[#1])-[#6]-[#1])-[#1])-[#1]",
    ),
    (
        "het_5_inium(1)",
        "[#7]-,:4(-c:1:c:c:c:c:c:1)-,:[#6](=,:[#7+](-c:2:c:c:c:c:c:2)-,:[#6](=[#7]-c:3:c:c:c:c:c:3)-,:[#7]-,:4)-[#1]",
    ),
    (
        "anil_di_alk_P(1)",
        "[#6](-[#1])(-[#1])-[#7](-[#6](-[#1])-[#1])-c:2:c:c:c:1:s:c(:n:c:1:c:2)-[#16]-[#6](-[#1])-[#1]",
    ),
    (
        "thio_urea_Q(1)",
        "c:1:2:c(:c(:c(:c(:c:1:c(:c(-[#1]):c(:c:2-[#1])-[#1])-[#6](-[#6](-[#1])-[#1])=[#7]-[#7](-[#1])-[#6](=[#16])-[#7](-[#1])-[#6]:[#6]:[#6])-[#1])-[#1])-[#1])-[#1]",
    ),
    (
        "thio_pyridine_A(1)",
        "[#6]:1(:[#7]:[#6](:[#7]:[!#1]:[#7]:1)-c:2:c(:c(:c(:o:2)-[#1])-[#1])-[#1])-[#16]-[#6;X4]",
    ),
    (
        "melamine_B(1)",
        "n:1:c(:n:c(:n:c:1-[#7](-[#6](-[#1])-[#1])-[#6](-[#1])-[#1])-[#7](-[#6](-[#1])-[#1])-[#6](-[#1])-[#1])-[#7](-[#6]-[#1])-[#6]=[#8]",
    ),
    (
        "misc_phthal_thio_N(1)",
        "c:1(:n:s:c(:n:1)-[#7](-[#6](-[#1])-[#1])-[#6](-[#1])(-[#1])-[#6](-[#1])(-[#1])-[#7]-[#6](=[#8])-c:2:c:c:c:c:c:2-[#6](=[#8])-[#8]-[#1])-c:3:c:c:c:c:c:3",
    ),
    (
        "hzone_acyl_misc_B(1)",
        "n:1:c(:c(:c(:c(:c:1-[#1])-[#1])-[#1])-[#1])-[#6](=[#8])-[#7](-[#1])-[#7]=[#6](-[#1])-c:2:c:c:c:c:c:2-[#8]-[#6](-[#1])(-[#1])-[#6](=[#8])-[#8]-[#1]",
    ),
    (
        "tert_butyl_B(1)",
        "[#6](-[#1])(-[#1])(-[#1])-[#6](-[#6](-[#1])(-[#1])-[#1])(-[#6](-[#1])(-[#1])-[#1])-c:1:c(:c(:c(:c(:c:1-[#8]-[#1])-[#6](-[#6](-[#1])(-[#1])-[#1])(-[#6](-[#1])(-[#1])-[#1])-[#6](-[#1])(-[#1])-[#1])-[#1])-[#6](-[#1])(-[#1])-c:2:c:c:c(:c(:c:2-[#1])-[#1])-[#8]-[#1])-[#1]",
    ),
    (
        "diazox_E(1)",
        "[#7](-[#1])(-[#1])-c:1:c(-[#7](-[#1])-[#1]):c(:c(-[#1]):c:2:n:o:n:c:1:2)-[#1]",
    ),
    (
        "anil_NH_no_alk_B(1)",
        "[#7](-[#1])(-[#1])-c:1:c(:c(:c(:c(:c:1-[#7](-[#1])-[#16](=[#8])=[#8])-[#1])-[#7](-[#1])-[#6](-[#1])-[#1])-[F,Cl,Br,I])-[#1]",
    ),
    (
        "anil_no_alk_A(1)",
        "[#7](-[#1])(-[#1])-c:1:c(:c(:c(:c(:c:1-[#7]=[#6]-2-[#6](=[#6]~[#6]~[#6]=[#6]-2)-[#1])-[#1])-[#1])-[#1])-[#1]",
    ),
    (
        "anil_no_alk_B(1)",
        "[#7](-[#1])(-[#1])-c:1:c(:c(:c(:c(:c:1-n:2:c:c:c:c:2)-[#1])-[#6](-[#1])-[#1])-[#6](-[#1])-[#1])-[#1]",
    ),
    (
        "thio_ene_amine_A(1)",
        "[#16]=[#6]-[#6](-[#6](-[#1])-[#1])=[#6](-[#6](-[#1])-[#1])-[#7](-[#6](-[#1])-[#1])-[#6](-[#1])-[#1]",
    ),
    (
        "het_55_B(1)",
        "[#6]-1:[#6]-[#8]-[#6]-2-[#6](-[#1])(-[#1])-[#6](=[#8])-[#8]-[#6]-1-2",
    ),
    (
        "cyanamide_A(1)",
        "[#8]-[#6](=[#8])-[#6](-[#1])(-[#1])-[#16;X2]-[#6](=[#7]-[#6]#[#7])-[#7](-[#1])-c:1:c:c:c:c:c:1",
    ),
    (
        "ene_one_one_A(1)",
        "[#8]=[#6]-[#6]-1=[#6](-[#16]-[#6](=[#6](-[#1])-[#6])-[#16]-1)-[#6]=[#8]",
    ),
    (
        "ene_six_het_D(1)",
        "[#8]=[#6]-1-[#7]-[#7]-[#6](=[#7]-[#6]-1=[#6]-[#1])-[!#1]:[!#1]",
    ),
    (
        "ene_cyano_E(1)",
        "[#8]=[#6]-[#6](-[#1])=[#6](-[#6]#[#7])-[#6]",
    ),
    (
        "ene_cyano_F(1)",
        "[#8](-[#1])-[#6](=[#8])-c:1:c(:c(:c(:c(:c:1-[#8]-[#1])-[#1])-c:2:c(-[#1]):c(:c(:o:2)-[#6](-[#1])=[#6](-[#6]#[#7])-c:3:n:c:c:n:3)-[#1])-[#1])-[#1]",
    ),
    (
        "hzone_furan_C(1)",
        "c:1:c(:c:c:c:c:1)-[#7](-c:2:c:c:c:c:c:2)-[#7]=[#6](-[#1])-[#6]:3:[#6](:[#6](:[#6](:[!#1]:3)-c:4:c:c:c:c(:c:4)-[#6](=[#8])-[#8]-[#1])-[#1])-[#1]",
    ),
    (
        "anil_no_alk_C(1)",
        "[#7](-[#1])(-[#1])-c:1:c(:c(:c(:c(:c:1-[#1])-[#1])-c:2:c(-[#1]):c(:c(-[#6](-[#1])-[#1]):o:2)-[#6]=[#8])-[#1])-[#1]",
    ),
    (
        "hzone_acid_D(1)",
        "[#8](-[#1])-[#6](=[#8])-c:1:c:c:c(:c:c:1)-[#7]-[#7]=[#6](-[#1])-[#6]:2:[#6](:[#6](:[#6](:[!#1]:2)-c:3:c:c:c:c:c:3)-[#1])-[#1]",
    ),
    (
        "hzone_furan_E(1)",
        "[#8](-[#1])-[#6](=[#8])-c:1:c:c:c:c(:c:1)-[#6]:[!#1]:[#6]-[#6]=[#7]-[#7](-[#1])-[#6](=[#8])-[#6](-[#1])(-[#1])-[#8]",
    ),
    (
        "het_6_pyridone_NH2(1)",
        "[#8](-[#1])-[#6]:1:[#6](:[#6]:[!#1]:[#6](:[#7]:1)-[#7](-[#1])-[#1])-[#6](-[#1])(-[#1])-[#6](=[#8])-[#8]",
    ),
    (
        "imine_one_fives_D(1)",
        "[#6]-1(=[!#6&!#1])-[#6](-[#7]=[#6]-[#16]-1)=[#8]",
    ),
    (
        "pyrrole_M(1)",
        "n2(-c:1:c:c:c:c:c:1)c(c(-[#1])c(c2-[#6]=[#7]-[#8]-[#1])-[#1])-[#1]",
    ),
    (
        "pyrrole_N(1)",
        "n2(-[#6](-[#1])-c:1:c(:c(:c:c(:c:1-[#1])-[#1])-[#1])-[#1])c(c(-[#1])c(c2-[#6]-[#1])-[#1])-[#6]-[#1]",
    ),
    (
        "pyrrole_O(1)",
        "n1(-[#6](-[#1])-[#1])c(c(-[#6](=[#8])-[#6])c(c1-[#6]:[#6])-[#6])-[#6](-[#1])-[#1]",
    ),
    (
        "ene_cyano_G(1)",
        "n1(-[#6])c(c(-[#1])c(c1-[#6](-[#1])=[#6](-[#6]#[#7])-c:2:n:c:c:s:2)-[#1])-[#1]",
    ),
    (
        "sulfonamide_J(1)",
        "n3(-c:1:c:c:c:c:c:1-[#7](-[#1])-[#16](=[#8])(=[#8])-c:2:c:c:c:s:2)c(c(-[#1])c(c3-[#1])-[#1])-[#1]",
    ),
    (
        "misc_pyrrole_benz(1)",
        "n2(-c:1:c(:c(:c(:c(:c:1-[#1])-[#1])-[#1])-[#1])-[#6](=[#8])-[#7](-[#1])-[#6](-[#1])(-[#6](-[#1])-[#1])-[#6](-[#1])(-[#1])-[#8]-[#6]:[#6])c(c(-[#1])c(c2-[#1])-[#1])-[#1]",
    ),
    (
        "thio_urea_R(1)",
        "c:1(:c:c:c:c:c:1)-[#7](-[#1])-[#6](=[#16])-[#7]-[#7](-[#1])-[#6](-[#1])=[#6](-[#1])-[#6]=[#8]",
    ),
    (
        "ene_one_one_B(1)",
        "[#6]-1(-[#6](=[#8])-[#6](-[#1])(-[#1])-[#6]-[#6](-[#1])(-[#1])-[#6]-1=[#8])=[#6](-[#7]-[#1])-[#6]=[#8]",
    ),
    (
        "dhp_amino_CN_H(1)",
        "[#7](-[#1])(-[#1])-[#6]-1=[#6](-[#6]#[#7])-[#6](-[#1])(-[#6]:[#6])-[#16]-[#6;X4]-[#16]-1",
    ),
    (
        "het_66_anisole(1)",
        "[#6](-[#1])(-[#1])-[#8]-c:1:c(:c(:c(:c(:c:1-[#1])-[#1])-[#1])-[#1])-[#7](-[#1])-c:2:c:c:n:c:3:c(:c:c:c(:c:2:3)-[#8]-[#6](-[#1])-[#1])-[#8]-[#6](-[#1])-[#1]",
    ),
    (
        "thiazole_amine_N(1)",
        "[#6](-[#1])(-[#1])-[#8]-c:1:c(:c(:c(:c(:c:1-[#1])-[#1])-[#8]-[#6](-[#1])-[#1])-[#1])-[#7](-[#1])-c:2:n:c(:c:s:2)-c:3:c:c:c(:c:c:3)-[#8]-[#6](-[#1])-[#1]",
    ),
    (
        "het_pyridiniums_C(1)",
        "[#6]~1~3~[#7](-[#6]:[#6])~[#6]~[#6]~[#6]~[#6]~1~[#6]~2~[#7]~[#6]~[#6]~[#6]~[#7+]~2~[#7]~3",
    ),
    (
        "het_5_E(1)",
        "[#7]-3(-c:2:c:1:c:c:c:c:c:1:c:c:c:2)-[#7]=[#6](-[#6](-[#1])-[#1])-[#6](-[#1])(-[#1])-[#6]-3=[#8]",
    ),
];

// Brenk et al. 2008 — full set of 105 structural alerts
// Source: J. Med. Chem. 2008, 51, 5149–5171
const BRENK_SMARTS: &[(&str, &str)] = &[
    // Reactive functional groups
    ("non_aromatic_C_C_triple_bond", "[#6]#[#6]"),
    ("thiol", "[#16][#1]"),
    ("sulfonyl_group", "[#16](=[#8])(=[#8])"),
    ("nitrile", "[#6]#[#7]"),
    ("aromatic_nitro", "c1ccccc1[N+](=O)[O-]"),
    ("azo", "[#7]=[#7]"),
    ("azoxy", "[#7][#16](=[#8])(=[#8])[#7]"),
    ("diazo", "[#7+]#[#7-]"),
    ("acyclic_isocyanate", "[#6]-[#7]=[#6]=[#8]"),
    ("acyclic_isothiocyanate", "[#6]-[#7]=[#6]=[#16]"),
    ("isourea", "[#7](-[#6])([#6])=[#7]"),
    ("Michael_acceptor_1", "[#6]=[#6]-[#6](=[#8])-[#6]"),
    ("Michael_acceptor_2", "[#6]=[#6]-[#7]"),
    ("Michael_acceptor_3", "[#6]=[#6]-[#16]"),
    ("boronic_acid", "[#5](-[#8])-[#8]"),
    ("boronic_ester", "[#5](-[#8]-[#6])-[#8]"),
    ("alkyl_halide", "[#6]-[#17]"),
    ("alkyl_halide_br", "[#6]-[#35]"),
    ("alkyl_halide_i", "[#6]-[#53]"),
    ("phosphoramidite", "[#15](=[#8])(-[#8]-[#6])-[#7]"),
    ("phosphinate", "[#15](=[#8])(-[#6])-[#8]"),
    ("phosphite", "[#15](-[#8])(-[#8])-[#8]"),
    ("carbodiimide", "[#6]=[#7]=[#7]"),
    ("sulfoxide", "[#16](=[#8])-[#6]"),
    ("sulfonamide", "[#16](=[#8])(=[#8])-[#7]"),
    ("sulfonyl_chloride", "[#16](=[#8])(=[#8])-[#17]"),
    ("sulfonyl_fluoride", "[#16](=[#8])(=[#8])-[#9]"),
    ("aldehyde", "[CH1,CH2]=O"),
    ("ketone_alpha", "[#6](-[#1])(-[#1])-[#6](=[#8])"),
    ("acyl_halide", "[#6](=[#8])-[#17]"),
    ("acyl_fluoride", "[#6](=[#8])-[#9]"),
    ("acid_anhydride", "[#6](=[#8])-[#8]-[#6](=[#8])"),
    ("N_acyl_imidazole", "c1[nH]c[nH]c1[#6](=[#8])"),
    ("hydrazine_1", "[#7]-[#7]"),
    ("peroxide", "[#8]-[#8]"),
    ("hydroxylamine", "[#7](-[#1])-[#8](-[#1])"),
    ("phenol", "c1ccccc1-[#8]"),
    ("aniline", "c1ccccc1-[#7]"),
    ("secondary_amine", "[#6]-[#7](-[#6])-[#1]"),
    ("primary_amine", "[#6]-[#7](-[#1])-[#1]"),
    ("ether_phenol", "c1c([#8])cc([#8])cc1"),
    ("anthracene", "c1ccc2cc3ccccc3cc2c1"),
    // Additional Brenk patterns (previously missing)
    ("epoxide", "C1OC1"),
    ("epoxide_aromatic", "c1ccc(C2OC2)cc1"),
    ("nitroso", "[#6][N;$(N=O)]"),
    ("nitroso_amine", "[#7][N;$(N=O)]"),
    ("halopyridine_2", "[#6]1:c(:c:c:c:n:1)-[#9,#17,#35,#53]"),
    ("halopyridine_3", "[#6]1:c(:c(-[#9,#17,#35,#53]):c:c:n:1)"),
    ("halopyridine_4", "[#6]1:c(:c:c(-[#9,#17,#35,#53]):c:n:1)"),
    ("beta_lactam", "C1(=O)NC1"),
    ("beta_lactam_substituted", "[#6]1(=[#8])-[#7]-[#6]-[#6]-1"),
    ("disulfide", "[#16]-[#16]"),
    ("sulfenic_acid", "[#16](=[#8])-[#8]"),
    ("sulfinic_acid", "[#16](=[#8])(=[#8])-[#8]"),
    ("N_halo", "[#7]-[#9,#17,#35,#53]"),
    ("N_halo_aromatic", "c1ccccc1[#7]-[#9,#17,#35,#53]"),
    (
        "alpha_haloamide",
        "[#6](-[#9,#17,#35,#53])-[#6](=[#8])-[#7]",
    ),
    ("active_methylene", "[#6](-[#6](=[#8]))-[#6](=[#8])"),
    ("thiocyanate", "[#6]-[#16]#[#7]"),
    ("isothiocyanate_aliphatic", "[#6](-[#6])-[#7]=[#6]=[#16]"),
    ("silyl_halide", "[#14]-[#9,#17,#35,#53]"),
    ("aluminum_compound", "[#13]"),
    ("metallic_phosphorus", "[#15](-[#6])(-[#6])(-[#6])-[#1]"),
    ("cyanamide", "[#6]#[#7](-[#6])"),
    ("diene", "[#6]=[#6]-[#6]=[#6]"),
    ("conjugated_nitro", "[#6]=[#6]-[N+](=O)[O-]"),
    ("quaternary_amine", "[#7+](-[#6])(-[#6])(-[#6])-[#6]"),
    ("ammonium_salt", "[#7+;H0](-[#6])(-[#6])(-[#6])-[#6]"),
    ("pyridinium", "c1cc[nH+]cc1"),
    ("thiophene_2_carboxaldehyde", "c1sccc1[#6]=[#8]"),
    ("thiophene_oxidized", "[#16]1ccc(=[#8])c1"),
    ("thioamide", "[#6](=[#16])-[#7]"),
    ("dithiocarbamate", "[#16]-[#6](=[#16])-[#7]"),
    ("xanthate", "[#16]-[#6](=[#16])-[#8]"),
    ("phenolic_aldehyde", "c1ccccc1[#8]-[#6]=[#8]"),
    ("phosphoramide", "[#15](=[#8])(-[#7])-[#7]"),
    ("N_acyl_hydrazone", "[#7](-[#7]=[#6])-[#6](=[#8])"),
    ("aryl_alkene", "c1ccccc1[#6]=[#6]"),
    ("benzofuran_carboxaldehyde", "c1ccc2c(c1)[#6]=[#8]C=C2"),
    ("indole_carboxaldehyde", "c1ccc(c2c1cc[nH]2)[#6]=[#8]"),
    ("azine_carboxaldehyde", "c1ccncc1[#6]=[#8]"),
    ("quinone_methide", "c1cc(=[#6])ccc1=[#6]"),
    ("heteroatom_at_bridgehead", "C1([#7,#8,#16])C=CC=C1"),
    ("strained_ring_three", "C1CC1"),
    ("strained_ring_four", "C1CCC1"),
    ("norbornene_subst", "C1CC2CCC1C=C2"),
    ("iminium_species", "[#6]=[#7+]"),
    ("vinyl_halide", "[#6]=[#6]-[#9,#17,#35,#53]"),
    ("allene_unsubstituted", "[#6]=[#6]=[#6]"),
    ("ynol_yne_ether", "[#6]#[#6]-[#8]-[#6]"),
    ("active_ester", "[#6](=[#8])-[#8]-c1ccccc1"),
    (
        "trifluoromethyl_ketone",
        "[#6](=[#8])-[#6](-[#9])(-[#9])-[#9]",
    ),
    ("oxirane_carboxylic", "[#6]1OC1[#6](=[#8])"),
    ("acetal_ketal", "[#8][#6]([#8])-[#6]"),
    ("amidine", "[#6](=[#7])-[#7]"),
    ("enamine", "[#6]=[#6]-[#7]"),
    ("amine_oxide", "[#7+](-[#6])-[#8-]"),
    ("N_oxide", "c1cc[nH+]([#8-])cc1"),
    (
        "triphosphate",
        "[#15](=[#8])(-[#8])-[#8]-[#15](=[#8])(-[#8])-[#8]",
    ),
    ("cyclopropane_fused", "C1CC1C"),
    ("tropylium_cation", "c1ccc2ccccc2c1[CH3+]"),
    ("acyl_nitrile", "[#6](=[#8])-[#6]#[#7]"),
    ("ketene", "[#6]=[#6]=[#8]"),
    ("ketenimine", "[#6]=[#6]=[#7]"),
];

static COMPILED_PAINS: OnceLock<Vec<(&'static str, QueryMolecule)>> = OnceLock::new();
static COMPILED_BRENK: OnceLock<Vec<(&'static str, QueryMolecule)>> = OnceLock::new();

fn compiled_pains_patterns() -> &'static [(&'static str, QueryMolecule)] {
    COMPILED_PAINS.get_or_init(|| {
        PAINS_SMARTS
            .iter()
            .filter_map(|&(name, smarts)| parse_smarts(smarts).ok().map(|q| (name, q)))
            .collect()
    })
}

fn compiled_brenk_patterns() -> &'static [(&'static str, QueryMolecule)] {
    COMPILED_BRENK.get_or_init(|| {
        BRENK_SMARTS
            .iter()
            .filter_map(|&(name, smarts)| parse_smarts(smarts).ok().map(|q| (name, q)))
            .collect()
    })
}

/// Returns the names of all PAINS patterns that match `mol`.
///
/// An empty vec means no PAINS alerts were triggered.
///
/// The molecule is expanded to explicit H form before matching because the
/// PAINS SMARTS patterns reference explicit hydrogen atoms (`[#1]`).
pub fn pains_matches(mol: &Molecule) -> Vec<&'static str> {
    let mol_h = add_explicit_hs(mol);
    let rings = find_sssr(&mol_h);
    // Each pattern only needs an existence check — only the name is kept,
    // never the match maps — so stop at the first embedding per pattern.
    let config = MatchConfig {
        max_matches: Some(1),
        uniquify: false,
        ..Default::default()
    };
    compiled_pains_patterns()
        .iter()
        .filter(|(_, q)| !find_matches_with_rings_and_config(q, &mol_h, &rings, &config).is_empty())
        .map(|(name, _)| *name)
        .collect()
}

/// Returns `true` when no PAINS alerts are triggered.
pub fn pains_passes(mol: &Molecule) -> bool {
    let mol_h = add_explicit_hs(mol);
    let rings = find_sssr(&mol_h);
    let config = MatchConfig {
        max_matches: Some(1),
        ..Default::default()
    };
    compiled_pains_patterns()
        .iter()
        .all(|(_, q)| find_matches_with_rings_and_config(q, &mol_h, &rings, &config).is_empty())
}

/// Returns the names of all Brenk structural alerts that match `mol`.
///
/// An empty vec means no Brenk alerts were triggered.
///
/// Brenk et al. 2008 structural alerts for drug design (J. Med. Chem. 51, 5149–5171).
/// These patterns identify problematic functional groups and structural features.
pub fn brenk_matches(mol: &Molecule) -> Vec<&'static str> {
    let mol_h = add_explicit_hs(mol);
    let rings = find_sssr(&mol_h);
    // Each pattern only needs an existence check — only the name is kept,
    // never the match maps — so stop at the first embedding per pattern.
    let config = MatchConfig {
        max_matches: Some(1),
        uniquify: false,
        ..Default::default()
    };
    compiled_brenk_patterns()
        .iter()
        .filter(|(_, q)| !find_matches_with_rings_and_config(q, &mol_h, &rings, &config).is_empty())
        .map(|(name, _)| *name)
        .collect()
}

/// Returns `true` when no Brenk structural alerts are triggered.
pub fn brenk_passes(mol: &Molecule) -> bool {
    let mol_h = add_explicit_hs(mol);
    let rings = find_sssr(&mol_h);
    let config = MatchConfig {
        max_matches: Some(1),
        ..Default::default()
    };
    compiled_brenk_patterns()
        .iter()
        .all(|(_, q)| find_matches_with_rings_and_config(q, &mol_h, &rings, &config).is_empty())
}

/// Returns `(passes, alert_names)` in a single explicit-H + SSSR + pattern pass.
///
/// Equivalent to calling `pains_passes(mol)` and `pains_matches(mol)` separately,
/// but avoids duplicating the expensive explicit-H conversion and 480-pattern scan.
pub fn pains_passes_and_matches(mol: &Molecule) -> (bool, Vec<&'static str>) {
    let mol_h = add_explicit_hs(mol);
    let rings = find_sssr(&mol_h);
    // Each pattern only needs an existence check — only the name is kept,
    // never the match maps — so stop at the first embedding per pattern.
    let config = MatchConfig {
        max_matches: Some(1),
        uniquify: false,
        ..Default::default()
    };
    let names: Vec<&'static str> = compiled_pains_patterns()
        .iter()
        .filter(|(_, q)| !find_matches_with_rings_and_config(q, &mol_h, &rings, &config).is_empty())
        .map(|(name, _)| *name)
        .collect();
    let passes = names.is_empty();
    (passes, names)
}

/// Returns `(passes, alert_names)` in a single explicit-H + SSSR + pattern pass.
///
/// Equivalent to calling `brenk_passes(mol)` and `brenk_matches(mol)` separately,
/// but avoids duplicating the expensive explicit-H conversion and ~300-pattern scan.
pub fn brenk_passes_and_matches(mol: &Molecule) -> (bool, Vec<&'static str>) {
    let mol_h = add_explicit_hs(mol);
    let rings = find_sssr(&mol_h);
    // Each pattern only needs an existence check — only the name is kept,
    // never the match maps — so stop at the first embedding per pattern.
    let config = MatchConfig {
        max_matches: Some(1),
        uniquify: false,
        ..Default::default()
    };
    let names: Vec<&'static str> = compiled_brenk_patterns()
        .iter()
        .filter(|(_, q)| !find_matches_with_rings_and_config(q, &mol_h, &rings, &config).is_empty())
        .map(|(name, _)| *name)
        .collect();
    let passes = names.is_empty();
    (passes, names)
}

// ---------------------------------------------------------------------------
// Detailed alert matches — returns atom indices for highlighting
// ---------------------------------------------------------------------------

/// Extract unique sorted heavy-atom indices from a set of SMARTS match mappings.
fn heavy_atoms_from_matches(
    matches: &[FxHashMap<usize, AtomIdx>],
    mol_h: &Molecule,
) -> Vec<AtomIdx> {
    use std::collections::BTreeSet;
    let mut set = BTreeSet::new();
    for mapping in matches {
        for &atom_idx in mapping.values() {
            if mol_h.atom(atom_idx).element.atomic_number() != 1 {
                set.insert(atom_idx);
            }
        }
    }
    set.into_iter().collect()
}

/// Shared implementation: scan `patterns` against `mol` and return matching
/// alert names with their heavy-atom indices.
fn matches_detailed_impl(
    mol: &Molecule,
    patterns: &'static [(&'static str, QueryMolecule)],
) -> Vec<(&'static str, Vec<AtomIdx>)> {
    let mol_h = add_explicit_hs(mol);
    let rings = find_sssr(&mol_h);
    let config = MatchConfig::default();
    patterns
        .iter()
        .filter_map(|(name, q)| {
            let ms = find_matches_with_rings_and_config(q, &mol_h, &rings, &config);
            if ms.is_empty() {
                return None;
            }
            Some((*name, heavy_atoms_from_matches(&ms, &mol_h)))
        })
        .collect()
}

/// Like [`pains_matches`] but also returns the matched heavy-atom indices.
///
/// Returns `Vec<(name, atom_indices)>` — one entry per triggered alert.
/// The `atom_indices` identify the heavy atoms in `mol` that are part of the
/// problematic substructure, suitable for use with
/// `chematic_depict::render_svg_highlighted`.
pub fn pains_matches_detailed(mol: &Molecule) -> Vec<(&'static str, Vec<AtomIdx>)> {
    matches_detailed_impl(mol, compiled_pains_patterns())
}

/// Like [`brenk_matches`] but also returns the matched heavy-atom indices.
///
/// Returns `Vec<(name, atom_indices)>` — one entry per triggered alert.
pub fn brenk_matches_detailed(mol: &Molecule) -> Vec<(&'static str, Vec<AtomIdx>)> {
    matches_detailed_impl(mol, compiled_brenk_patterns())
}

#[cfg(test)]
mod tests {
    use super::*;
    use chematic_smiles::parse;

    fn mol(s: &str) -> Molecule {
        parse(s).unwrap()
    }

    #[test]
    fn test_pains_caffeine_passes() {
        // Caffeine has no PAINS alerts
        assert!(
            pains_passes(&mol("Cn1cnc2c1c(=O)n(c(=O)n2C)C")),
            "caffeine should pass PAINS"
        );
    }

    #[test]
    fn test_pains_rhodanine_fails() {
        // Rhodanine scaffold triggers ene_rhod_A pattern
        let hits = pains_matches(&mol("O=C1CSC(=S)N1"));
        assert!(!hits.is_empty(), "rhodanine should trigger PAINS alert");
    }

    #[test]
    fn test_pains_azo_fails() {
        // Azo compound: R-N=N-R triggers azo_A
        let hits = pains_matches(&mol("c1ccc(cc1)N=Nc2ccccc2"));
        assert!(!hits.is_empty(), "azobenzene should trigger PAINS azo_A");
    }

    #[test]
    fn test_pains_count_at_most_480() {
        let n = compiled_pains_patterns().len();
        assert!(n <= 480, "at most 480 patterns expected, got {n}");
        assert!(
            n >= 470,
            "at least 470 of 480 patterns should compile, got {n}"
        );
    }

    #[test]
    fn test_brenk_count() {
        let n = compiled_brenk_patterns().len();
        assert!(n > 0, "at least 1 Brenk pattern expected");
        assert!(n <= 105, "at most 105 Brenk patterns expected, got {n}");
    }

    #[test]
    fn test_brenk_phenol_fails() {
        // Phenol is a Brenk alert (phenol pattern)
        let hits = brenk_matches(&mol("Oc1ccccc1"));
        assert!(!hits.is_empty(), "phenol should trigger Brenk alert");
    }

    #[test]
    fn test_brenk_thiol_fails() {
        // Thiol is a Brenk alert
        let hits = brenk_matches(&mol("Cc1ccccc1S"));
        assert!(!hits.is_empty(), "thiol should trigger Brenk alert");
    }

    #[test]
    fn test_aldehyde_formaldehyde_matches() {
        // BUG FIX #1: Formaldehyde should match aldehyde pattern [CH1,CH2]=O
        let hits = brenk_matches(&mol("C=O"));
        assert!(
            hits.contains(&"aldehyde"),
            "formaldehyde should match aldehyde alert"
        );
    }

    #[test]
    fn test_aldehyde_acetaldehyde_matches() {
        // BUG FIX #1 regression: acetaldehyde should still match
        let hits = brenk_matches(&mol("CC=O"));
        assert!(
            hits.contains(&"aldehyde"),
            "acetaldehyde should match aldehyde alert"
        );
    }

    #[test]
    fn test_brenk_aniline_fails() {
        // Aniline is a Brenk alert
        let hits = brenk_matches(&mol("Nc1ccccc1"));
        assert!(!hits.is_empty(), "aniline should trigger Brenk alert");
    }

    #[test]
    fn test_pains_catechol_fails() {
        // Catechol (ortho-dihydroxybenzene) → catechol_A pattern
        let hits = pains_matches(&mol("Oc1ccccc1O"));
        assert!(!hits.is_empty(), "catechol should trigger PAINS catechol_A");
    }

    #[test]
    fn test_pains_mannich_base_fails() {
        // Mannich base: N-CH2-ArOH pattern → mannich_A
        let hits = pains_matches(&mol("NCc1ccccc1O"));
        assert!(
            !hits.is_empty(),
            "Mannich base should trigger PAINS mannich_A"
        );
    }
}