void testPaths2() {
std::cout << "-----------------------\n Path retrieval2" << std::endl;
// build: CCC(C)CC
RWMol mol;
bool updateLabel = true;
bool takeOwnership = true;
mol.addAtom(new Atom(6), updateLabel, takeOwnership);
mol.addAtom(new Atom(6), updateLabel, takeOwnership);
mol.addAtom(new Atom(6), updateLabel, takeOwnership);
mol.addAtom(new Atom(6), updateLabel, takeOwnership);
mol.addBond(0, 1, Bond::SINGLE);
mol.addBond(1, 2, Bond::SINGLE);
mol.addBond(2, 3, Bond::SINGLE);
mol.addBond(2, 0, Bond::SINGLE);
//
// Retrieve using bonds
//
PATH_LIST tmp = findAllPathsOfLengthN(mol, 3);
// std::cout << "\n3:" << std::endl;
// dumpVIV(tmp);
CHECK_INVARIANT(tmp.size() == 3, "");
std::cout << "Finished" << std::endl;
}
void CleanupMolecule() {
// an example of doing some cleaning up of a molecule before
// calling the sanitizeMol function()
// build: C1CC1C(:O):O
RWMol *mol = new RWMol();
// add atoms and bonds:
mol->addAtom(new Atom(6)); // atom 0
mol->addAtom(new Atom(6)); // atom 1
mol->addAtom(new Atom(6)); // atom 2
mol->addAtom(new Atom(6)); // atom 3
mol->addAtom(new Atom(8)); // atom 4
mol->addAtom(new Atom(8)); // atom 5
mol->addBond(3, 4, Bond::AROMATIC); // bond 0
mol->addBond(3, 5, Bond::AROMATIC); // bond 1
mol->addBond(3, 2, Bond::SINGLE); // bond 2
mol->addBond(2, 1, Bond::SINGLE); // bond 3
mol->addBond(1, 0, Bond::SINGLE); // bond 4
mol->addBond(0, 2, Bond::SINGLE); // bond 5
// instead of calling sanitize mol, which would generate an error,
// we'll perceive the rings, then take care of aromatic bonds
// that aren't in a ring, then sanitize:
MolOps::findSSSR(*mol);
for (ROMol::BondIterator bondIt = mol->beginBonds();
bondIt != mol->endBonds(); ++bondIt) {
if (((*bondIt)->getIsAromatic() ||
(*bondIt)->getBondType() == Bond::AROMATIC) &&
!mol->getRingInfo()->numBondRings((*bondIt)->getIdx())) {
// remove the aromatic flag on the bond:
(*bondIt)->setIsAromatic(false);
// and cleanup its attached atoms as well (they were
// also marked aromatic when the bond was added)
(*bondIt)->getBeginAtom()->setIsAromatic(false);
(*bondIt)->getEndAtom()->setIsAromatic(false);
// NOTE: this isn't really reasonable:
(*bondIt)->setBondType(Bond::SINGLE);
}
}
// now it's safe to sanitize:
RDKit::MolOps::sanitizeMol(*mol);
// Get the canonical SMILES, include stereochemistry:
std::string smiles;
smiles = MolToSmiles(*(static_cast<ROMol *>(mol)), true);
BOOST_LOG(rdInfoLog) << " fixed SMILES: " << smiles << std::endl;
}
void BuildSimpleMolecule() {
// build the molecule: C/C=C\C
RWMol *mol = new RWMol();
// add atoms and bonds:
mol->addAtom(new Atom(6)); // atom 0
mol->addAtom(new Atom(6)); // atom 1
mol->addAtom(new Atom(6)); // atom 2
mol->addAtom(new Atom(6)); // atom 3
mol->addBond(0, 1, Bond::SINGLE); // bond 0
mol->addBond(1, 2, Bond::DOUBLE); // bond 1
mol->addBond(2, 3, Bond::SINGLE); // bond 2
// setup the stereochem:
mol->getBondWithIdx(0)->setBondDir(Bond::ENDUPRIGHT);
mol->getBondWithIdx(2)->setBondDir(Bond::ENDDOWNRIGHT);
// do the chemistry perception:
RDKit::MolOps::sanitizeMol(*mol);
// Get the canonical SMILES, include stereochemistry:
std::string smiles;
smiles = MolToSmiles(*(static_cast<ROMol *>(mol)), true);
BOOST_LOG(rdInfoLog) << " sample 1 SMILES: " << smiles << std::endl;
}
void testUniqueSubgraphs() {
std::cout << "-----------------------\n Unique Subgraph retrieval"
<< std::endl;
// build: CCC(C)CC
RWMol mol;
bool updateLabel = true;
bool takeOwnership = true;
mol.addAtom(new Atom(6), updateLabel, takeOwnership);
mol.addAtom(new Atom(6), updateLabel, takeOwnership);
mol.addAtom(new Atom(6), updateLabel, takeOwnership);
mol.addAtom(new Atom(6), updateLabel, takeOwnership);
mol.addAtom(new Atom(6), updateLabel, takeOwnership);
mol.addAtom(new Atom(6), updateLabel, takeOwnership);
mol.addBond(0, 1, Bond::SINGLE);
mol.addBond(1, 2, Bond::SINGLE);
mol.addBond(2, 3, Bond::SINGLE);
mol.addBond(2, 4, Bond::SINGLE);
mol.addBond(3, 5, Bond::SINGLE);
PATH_LIST tmp;
PATH_LIST::iterator i;
tmp = findAllSubgraphsOfLengthN(mol, 1);
CHECK_INVARIANT(tmp.size() == 5, "");
tmp = findAllSubgraphsOfLengthN(mol, 2);
CHECK_INVARIANT(tmp.size() == 5, "");
tmp = findUniqueSubgraphsOfLengthN(mol, 2);
CHECK_INVARIANT(tmp.size() == 1, "");
tmp = findAllSubgraphsOfLengthN(mol, 3);
CHECK_INVARIANT(tmp.size() == 5, "");
tmp = findUniqueSubgraphsOfLengthN(mol, 3);
CHECK_INVARIANT(tmp.size() == 2, "");
tmp = findAllSubgraphsOfLengthN(mol, 4);
CHECK_INVARIANT(tmp.size() == 3, "");
tmp = findUniqueSubgraphsOfLengthN(mol, 4);
CHECK_INVARIANT(tmp.size() == 2, "");
tmp = findAllSubgraphsOfLengthN(mol, 5);
CHECK_INVARIANT(tmp.size() == 1, "");
tmp = findUniqueSubgraphsOfLengthN(mol, 5);
CHECK_INVARIANT(tmp.size() == 1, "");
tmp = findAllSubgraphsOfLengthN(mol, 6);
CHECK_INVARIANT(tmp.empty(), "");
tmp = findUniqueSubgraphsOfLengthN(mol, 6);
CHECK_INVARIANT(tmp.empty(), "");
// add an H and make sure things don't change:
mol.addAtom(new Atom(1), updateLabel, takeOwnership);
mol.addBond(5, 6, Bond::SINGLE);
tmp = findAllSubgraphsOfLengthN(mol, 2);
CHECK_INVARIANT(tmp.size() == 5, "");
tmp = findUniqueSubgraphsOfLengthN(mol, 2);
CHECK_INVARIANT(tmp.size() == 1, "");
tmp = findAllSubgraphsOfLengthN(mol, 3);
CHECK_INVARIANT(tmp.size() == 5, "");
tmp = findUniqueSubgraphsOfLengthN(mol, 3);
CHECK_INVARIANT(tmp.size() == 2, "");
tmp = findAllSubgraphsOfLengthN(mol, 4);
CHECK_INVARIANT(tmp.size() == 3, "");
tmp = findUniqueSubgraphsOfLengthN(mol, 4);
CHECK_INVARIANT(tmp.size() == 2, "");
tmp = findAllSubgraphsOfLengthN(mol, 5);
CHECK_INVARIANT(tmp.size() == 1, "");
tmp = findUniqueSubgraphsOfLengthN(mol, 5);
CHECK_INVARIANT(tmp.size() == 1, "");
tmp = findAllSubgraphsOfLengthN(mol, 6);
CHECK_INVARIANT(tmp.empty(), "");
tmp = findUniqueSubgraphsOfLengthN(mol, 6);
CHECK_INVARIANT(tmp.empty(), "");
std::cout << "Finished" << std::endl;
}
void testSubgraphs() {
std::cout << "-----------------------\n Subgraph retrieval" << std::endl;
// build: CCC(C)CC
RWMol mol;
bool updateLabel = true;
bool takeOwnership = true;
mol.addAtom(new Atom(6), updateLabel, takeOwnership);
mol.addAtom(new Atom(6), updateLabel, takeOwnership);
mol.addAtom(new Atom(6), updateLabel, takeOwnership);
mol.addAtom(new Atom(6), updateLabel, takeOwnership);
mol.addAtom(new Atom(6), updateLabel, takeOwnership);
mol.addAtom(new Atom(6), updateLabel, takeOwnership);
mol.addBond(0, 1, Bond::SINGLE);
mol.addBond(1, 2, Bond::SINGLE);
mol.addBond(2, 3, Bond::SINGLE);
mol.addBond(2, 4, Bond::SINGLE);
mol.addBond(3, 5, Bond::SINGLE);
PATH_LIST tmp;
PATH_LIST::iterator i;
int totPs = 0;
tmp = findAllSubgraphsOfLengthN(mol, 1);
CHECK_INVARIANT(tmp.size() == 5, "");
totPs += tmp.size();
tmp = findAllSubgraphsOfLengthN(mol, 2);
CHECK_INVARIANT(tmp.size() == 5, "");
totPs += tmp.size();
tmp = findAllSubgraphsOfLengthN(mol, 3);
CHECK_INVARIANT(tmp.size() == 5, "");
totPs += tmp.size();
tmp = findAllSubgraphsOfLengthN(mol, 4);
CHECK_INVARIANT(tmp.size() == 3, "");
totPs += tmp.size();
tmp = findAllSubgraphsOfLengthN(mol, 5);
CHECK_INVARIANT(tmp.size() == 1, "");
totPs += tmp.size();
tmp = findAllSubgraphsOfLengthN(mol, 6);
CHECK_INVARIANT(tmp.empty(), "");
totPs += tmp.size();
// now use the direct range function and check that we get the
// same anwswer
INT_PATH_LIST_MAP tmpm;
tmpm = findAllSubgraphsOfLengthsMtoN(mol, 1, 6);
int newTot, idx;
newTot = 0;
for (idx = 1; idx <= 6; idx++) {
newTot += tmpm[idx].size();
}
CHECK_INVARIANT(totPs == newTot, "");
// add an H and make sure things don't change:
mol.addAtom(new Atom(1), updateLabel, takeOwnership);
mol.addBond(5, 6, Bond::SINGLE);
tmp = findAllSubgraphsOfLengthN(mol, 1);
CHECK_INVARIANT(tmp.size() == 5, "");
tmp = findAllSubgraphsOfLengthN(mol, 2);
CHECK_INVARIANT(tmp.size() == 5, "");
tmp = findAllSubgraphsOfLengthN(mol, 3);
CHECK_INVARIANT(tmp.size() == 5, "");
tmp = findAllSubgraphsOfLengthN(mol, 4);
CHECK_INVARIANT(tmp.size() == 3, "");
tmp = findAllSubgraphsOfLengthN(mol, 5);
CHECK_INVARIANT(tmp.size() == 1, "");
tmp = findAllSubgraphsOfLengthN(mol, 6);
CHECK_INVARIANT(tmp.empty(), "");
std::cout << "Finished" << std::endl;
}
void testPaths() {
std::cout << "-----------------------\n Path retrieval" << std::endl;
// build: CCC(C)CC
RWMol mol;
bool updateLabel = true;
bool takeOwnership = true;
mol.addAtom(new Atom(6), updateLabel, takeOwnership);
mol.addAtom(new Atom(6), updateLabel, takeOwnership);
mol.addAtom(new Atom(6), updateLabel, takeOwnership);
mol.addAtom(new Atom(6), updateLabel, takeOwnership);
mol.addAtom(new Atom(6), updateLabel, takeOwnership);
mol.addAtom(new Atom(6), updateLabel, takeOwnership);
mol.addBond(0, 1, Bond::SINGLE);
mol.addBond(1, 2, Bond::SINGLE);
mol.addBond(2, 3, Bond::SINGLE);
mol.addBond(2, 4, Bond::SINGLE);
mol.addBond(3, 5, Bond::SINGLE);
PATH_LIST tmp;
//
// Retrieve using bonds
//
tmp = findAllPathsOfLengthN(mol, 1);
CHECK_INVARIANT(tmp.size() == 5, "");
tmp = findAllPathsOfLengthN(mol, 2);
CHECK_INVARIANT(tmp.size() == 5, "");
tmp = findAllPathsOfLengthN(mol, 3);
CHECK_INVARIANT(tmp.size() == 4, "");
tmp = findAllPathsOfLengthN(mol, 4);
CHECK_INVARIANT(tmp.size() == 1, "");
tmp = findAllPathsOfLengthN(mol, 5);
CHECK_INVARIANT(tmp.empty(), "");
tmp = findAllPathsOfLengthN(mol, 6);
CHECK_INVARIANT(tmp.empty(), "");
//
// Retrieve using atoms, which gives the results shifted by
// one (it takes two atoms to make one bond)
//
tmp = findAllPathsOfLengthN(mol, 1, false);
CHECK_INVARIANT(tmp.size() == 6, "");
tmp = findAllPathsOfLengthN(mol, 2, false);
CHECK_INVARIANT(tmp.size() == 5, "");
tmp = findAllPathsOfLengthN(mol, 3, false);
CHECK_INVARIANT(tmp.size() == 5, "");
tmp = findAllPathsOfLengthN(mol, 4, false);
CHECK_INVARIANT(tmp.size() == 4, "");
tmp = findAllPathsOfLengthN(mol, 5, false);
CHECK_INVARIANT(tmp.size() == 1, "");
tmp = findAllPathsOfLengthN(mol, 6, false);
CHECK_INVARIANT(tmp.empty(), "");
//
// try m->n
//
INT_PATH_LIST_MAP pths;
pths = findAllPathsOfLengthsMtoN(mol, 1, 6);
CHECK_INVARIANT(pths[1].size() == 5, "");
CHECK_INVARIANT(pths[2].size() == 5, "");
CHECK_INVARIANT(pths[3].size() == 4, "");
CHECK_INVARIANT(pths[4].size() == 1, "");
CHECK_INVARIANT(pths[5].empty(), "");
CHECK_INVARIANT(pths[6].empty(), "");
pths = findAllPathsOfLengthsMtoN(mol, 1, 6, false);
CHECK_INVARIANT(pths[1].size() == 6, "");
CHECK_INVARIANT(pths[2].size() == 5, "");
CHECK_INVARIANT(pths[3].size() == 5, "");
CHECK_INVARIANT(pths[4].size() == 4, "");
CHECK_INVARIANT(pths[5].size() == 1, "");
CHECK_INVARIANT(pths[6].empty(), "");
//
// add an atom, close the ring and re-check a couple indices:
// (leaves us with CC1CCCCC1)
//
mol.addAtom(new Atom(6), updateLabel, takeOwnership);
mol.addBond(5, 6, Bond::SINGLE);
mol.addBond(0, 6, Bond::SINGLE);
tmp = findAllPathsOfLengthN(mol, 4);
CHECK_INVARIANT(tmp.size() == 8, "");
tmp = findAllPathsOfLengthN(mol, 5, false);
CHECK_INVARIANT(tmp.size() == 8, "");
std::cout << "Finished" << std::endl;
}
void deletebonds(const ROMol &mol, String ftype, int hac){
RWMol *newMol = static_cast<RWMol*>(new ROMol(mol,false));
int total_acyclic = 0;
int total_cyclic = 0;
//find the relevant bonds to break
// Single acyclic Cuts
if(ftype == acyc_smarts){
acyclic_matching_atoms = mol.getSubstructMatches(acyc);
total_acyclic = acyclic_matching_atoms.size();
MatchVectType acyclic_matching_atoms;
std::vector<int> bonds_selected;
Match_Vect bonds_selected;
SubstructMatch(mol, acyc, acyclic_matching_atoms);
// if we didn't find any matches, there's nothing to be done here
// simply return a list with a copy of the starting molecule
if (acyclic_matching_atoms.size() == 0) {
newMol.push_back(ROMOL_SPTR(new ROMol(mol,false)));
newMol[0]->clearComputedProps(false);
return newMol;
for(MatchVectType::const_iterator mvit=acyclic_matching_atoms.begin();
mvit!=acyclic_matching_atoms.end(); mvit++){
bonds_selected.push_back(mvit->first);
bonds_selected.push_back(mvit->second);
bonds_selected[0] = mvit->first;
bonds_selected[1] = mvit->second;
Atom *at1 = newMol->getAtomWithIdx(bonds_selected[0]);
Atom *at2 = newMol->getAtomWithIdx(bonds_selected[1]);
Atom *atom0 = newMol->getAtomWithIdx(0);
Atom *atom1 = newMol->getAtomWithIdx(0);
newMol->removeBond(bonds_selected[0], bonds_selected[1]);// Break the bond with idx=at1, at2.
// Introduce two dummy atoms in the molecule
newMol->addAtom(atom0);
newMol->addAtom(atom1);
// Bond the dummy atoms to the new terminal atoms
Bond *oBond=newMol->getBondBetweenAtoms(bonds_selected[0],atom0->getIdx());
CHECK_INVARIANT(oBond,"required bond not found");
newMol->addBond(at1,
*atom0,Bond::SINGLE);
Bond *oBond=newMol->getBondBetweenAtoms(bonds_selected[1],atom1->getIdx());
CHECK_INVARIANT(oBond,"required bond not found");
newMol->addBond(at2,
*atom1,Bond::SINGLE);
break;
}
//Now get the modified fragment in smiles(i.e. smi2);
String smi2 = MolToSmiles(*newMol);
//printf (smi2);
}
}
//cyclic Cuts
if(ftype == cyc_smarts){
cyclic_matching_atoms = mol.getSubstructMatches(cyc);
int total_cyclic = cyclic_matching_atoms.size();
MatchVectType cyclic_matching_atoms;
std::vector<int> bonds_selected;
Match_Vect bonds_selected;
SubstructMatch(mol, cyc, cyclic_matching_atoms);
// if we didn't find any matches, there's nothing to be done here
// simply return a list with a copy of the starting molecule
if (cyclic_matching_atoms.size() == 0) {
newMol.push_back(ROMOL_SPTR(new ROMol(mol,false)));
newMol[0]->clearComputedProps(false);
return newMol;
for(MatchVectType::const_iterator mvit=cyclic_matching_atoms.begin();
mvit!=cyclic_matching_atoms.end(); mvit++){
bonds_selected.push_back(mvit->first);
bonds_selected.push_back(mvit->second);
bonds_selected[0] = mvit->first;
bonds_selected[1] = mvit->second;
Atom *at1 = newMol->getAtomWithIdx(bonds_selected[0]);
Atom *at2 = newMol->getAtomWithIdx(bonds_selected[1]);
Atom *atom0 = newMol->getAtomWithIdx(0);
Atom *atom1 = newMol->getAtomWithIdx(0);
newMol->removeBond(bonds_selected[0], bonds_selected[1]);// Break the bond with idx=at1, at2.
// Introduce two dummy atoms in the molecule
newMol->addAtom(atom0);
newMol->addAtom(atom1);
// Bond the dummy atoms to the new terminal atoms
Bond *oBond=newMol->getBondBetweenAtoms(bonds_selected[0],atom0->getIdx());
CHECK_INVARIANT(oBond,"required bond not found");
newMol->addBond(at1,
*atom0,Bond::SINGLE);
Bond *oBond=newMol->getBondBetweenAtoms(bonds_selected[1],atom1->getIdx());
CHECK_INVARIANT(oBond,"required bond not found");
newMol->addBond(at2,
*atom1,Bond::SINGLE);
continue;
}
//Now get the modified fragment in smiles(i.e. smi2);
String smi2 = MolToSmiles(*newMol);
//printf (smi2);
//now do an acyclic cut with the successful cyclic cut on the mol
for(MatchVectType::const_iterator mvit=acyclic_matching_atoms.begin();
mvit!=acyclic_matching_atoms.end(); mvit++){
bonds_selected.push_back(mvit->first);
bonds_selected.push_back(mvit->second);
bonds_selected[0] = mvit->first;
bonds_selected[1] = mvit->second;
Atom *at1 = newMol->getAtomWithIdx(bonds_selected[0]);
Atom *at2 = newMol->getAtomWithIdx(bonds_selected[1]);
Atom *atom0 = newMol->getAtomWithIdx(0);
Atom *atom1 = newMol->getAtomWithIdx(0);
newMol->removeBond(bonds_selected[0], bonds_selected[1]);// Break the bond with idx=at1, at2.
// Introduce two dummy atoms in the molecule
newMol->addAtom(atom0);
newMol->addAtom(atom1);
// Bond the dummy atoms to the new terminal atoms
Bond *oBond=newMol->getBondBetweenAtoms(bonds_selected[0],atom0->getIdx());
CHECK_INVARIANT(oBond,"required bond not found");
newMol->addBond(at1,
*nbrIdx,oBond->getBondType());
Bond *oBond=newMol->getBondBetweenAtoms(bonds_selected[1],atom1->getIdx());
CHECK_INVARIANT(oBond,"required bond not found");
newMol->addBond(at2,
*atom1,Bond::SINGLE);
continue;
}
//Now get the modified fragment in smiles(i.e. smi2);
String smi2 = MolToSmiles(*newMol);
//printf (smi2);
}
}
//determine whether ring cut is valid
String cSma1 = ("[#0][r].[r][#0]");
static ROMol *Sma1 = SmartsToMol("[#0][r].[r][#0]");
String cSma2 = ("[#0][r][#0]");
static ROMol *Sma2 = SmartsToMol("[#0][r][#0]");
void is_ring_cut_valid(ROMol *fMol, ROMol *Sma1, ROMol *Sma2){
//to check is a fragment is a valid ring cut, it needs to match the
//smarts: [$([#0][r].[r][#0]),$([#0][r][#0])]
boolean valid = false;
ROMol *m = new RWMol();
//if m is not None:
if (m != NULL){
//use global smarts
if(m->hasSubstructMatch(Sma1) || m->hasSubstructMatch(Sma2)){
int atom_count = m->getNumAtoms();
valid = true;
}
}
}
