johnmay

IChemObjectBuilder bldr = SilentChemObjectBuilder.getInstance();
IAtomContainer mol = new QueryAtomContainer(bldr);
if (!Smarts.parse(mol, "[C,N;H0,H1+]-*", Smarts.FLAVOR_LOOSE)) {
    System.err.println("ERROR - " + Smarts.getLastErrorMesg());
    System.err.println(Smarts.getLastErrorLocation());
    return;
}
QueryAtom qatom1 = (QueryAtom) mol.getAtom(0); // instanceof for safety
Expr expr = qatom1.getExpression();
System.err.println(expr); // AND(OR(ALIPHATIC_ELEMENT=6,ALIPHATIC_ELEMENT=7),OR(TOTAL_H_COUNT=0,AND(TOTAL_H_COUNT=1,FORMAL_CHARGE=1)))

johnmay

curl ftp://ftp.ncbi.nlm.nih.gov/pubchem/Compound/Weekly/2020-01-05/Extras/CID-SMILES.gz | \
 gunzip -c | \
 head -n 10000000 | \
 awk '{print $2 " " $1}' > pubchem_first10m.smi

johnmay

elements = {'H': 1, 'He': 2, etc}
def strtoelem(element):
    return elemements.get(element, 0)

johnmay

public static void alignMoleculeToSubstructure(IAtomContainer mol,
                                               IAtomContainer sub,
                                               boolean fixBonds) throws CDKException {
    Pattern substructurePattern = Pattern.findSubstructure(sub);
    Mappings mappings = substructurePattern.matchAll(mol);
    Set<IAtom> fixedAtoms = new HashSet<IAtom>();
    Set<IBond> fixedBonds = new HashSet<IBond>();
    for (Map<IChemObject, IChemObject> map : mappings.toAtomBondMap()) {

        GeometryUtil.scaleMolecule(sub,

johnmay

public static void main(String[] args) throws CDKException {
    IChemObjectBuilder    bldr   = SilentChemObjectBuilder.getInstance();
    SmilesParser          smipar = new SmilesParser(bldr);
    IAtomContainer        root   = smipar.parseSmiles("CC1=CC=NC2=C1C=CC(=C2)C1=CC([R1])=C([R2])C([R3])=C1");

    Map<IAtom, Map<Integer,IBond>> rootAttach = new HashMap<>();
    Map<Integer,RGroupList> rgrpMap = new HashMap<>();
    defineRgroup(root, rootAttach, rgrpMap, "R1", newRGroupList("[H].[CH2]CO.[CH2]Cl", 1));
    defineRgroup(root, rootAttach, rgrpMap, "R2", newRGroupList("[H].[CH2]CN.[CH2]F", 2));
    defineRgroup(root, rootAttach, rgrpMap, "R3", newRGroupList("[H].[CH2]CCl.[CH2]F", 3));

johnmay

Building on Sand: Standard InChIs on Non-Standard Molfiles
John Mayfield

The molfile serves as a de facto standard for chemical information exchange. It is perhaps the most
widely supported format with its core syntax being easy to understand, parse, and generate. Beyond
the core syntax, more advanced features such as sgroups and enhanced stereochemistry are rarely
supported, often only being partially implemented and used. Additionally, several vendors, 
toolkits, and service providers have added extended syntaxto their molfiles to solve particular
corner cases or representation problems.This talk will provide a brief summary of the less widely
supported features of the molfile including sgroups and enhanced stereochemistry. Additionally, 

johnmay

public static String toSmiles(CircularFingerprinter.FP fp, IAtomContainer mol) throws CDKException
  {
    IAtomContainer part = mol.getBuilder().newAtomContainer();
    Set<IAtom>     aset = new HashSet<>();
    int[] hcounts = new int[mol.getAtomCount()];
    for (int idx : fp.atoms) {
      IAtom atom = mol.getAtom(idx);
      aset.add(atom);
      part.addAtom(atom);
      hcounts[idx] = atom.getImplicitHydrogenCount();

johnmay

Aromaticity arom = new Aromaticity(ElectronDontation.cdk(),
                                   Cycles.cdkAromaticSet());

johnmay

    SmilesParser smipar = new SmilesParser(SilentChemObjectBuilder.getInstance());

    String smi = "*CCO*";
    IAtomContainer mol = smipar.parseSmiles(smi);

    Sgroup sgrp = new Sgroup();
    sgrp.addAtom(mol.getAtom(1));
    sgrp.addAtom(mol.getAtom(2));
    sgrp.addAtom(mol.getAtom(3));
    sgrp.addBond(mol.getBond(0)); // bond crossing bracket (xbond)

johnmay

public static void main(String[] args) throws CDKException, IOException {
    String rxnfile = "$RXN\n"
                     + "\n"
                     + "\n"
                     + "\n"
                     + "  2  1  0\n"
                     + "$MOL\n"
                     + "\n"
                     + "  Ketcher 01271718382D 1   1.00000     0.00000     0\n"
                     + "\n"