feat: update OCL to v2024.10.0

src/com/actelion/research/gwt/chemlib/com/actelion/research/chem/AromaticityResolver.java

@@ -168,7 +168,13 @@ public boolean locateDelocalizedDoubleBonds(boolean[] isAromaticBond, boolean ma
                     }
                 }
 
-            if (!bondsPromoted) {
+
+			if (bondsPromoted) {
+				promoteObviousBonds();
+				continue;
+				}
+
+			if (!bondsPromoted) {
                 // find and promote one aromatic bond
                 // (should never happen, but to prevent an endless loop nonetheless)
                 for (int bond=0; bond<mMol.getBonds(); bond++) {

src/com/actelion/research/gwt/chemlib/com/actelion/research/chem/AtomFunctionAnalyzer.java

@@ -195,8 +195,12 @@ public static boolean hasUnbalancedAtomCharge(StereoMolecule mol, int atom) {
 	}
 
 	public static boolean isAcidicOxygen(StereoMolecule mol, int atom) {
+		return isAcidicOxygen(mol, atom, true);
+		}
+
+	public static boolean isAcidicOxygen(StereoMolecule mol, int atom, boolean considerCharge) {
 		if (mol.getAtomicNo(atom) != 8
-		 || mol.getAtomCharge(atom) != 0
+		 || (considerCharge && mol.getAtomCharge(atom) != 0)
 		 || mol.getConnAtoms(atom) != 1
 		 || mol.getConnBondOrder(atom, 0) != 1)
 			return false;
@@ -246,13 +250,18 @@ public static boolean isAcidicOxygen(StereoMolecule mol, int atom) {
 
 			if(nDoubleBondedO2S == 2)
 				return true;
-		} else if(isAcidicOxygenAtPhosphoricAcid(mol, atom)) // CP=O(OH)(OH)
+
+		} else if(isAcidicOxygenAtPhosphoricAcid(mol, atom, considerCharge)) // CP=O(OH)(OH)
 			return true;
 
 		return false;
 	}
-	
+
 	public static boolean isAcidicOxygenAtPhosphoricAcid(StereoMolecule mol, int atom) {
+		return isAcidicOxygenAtPhosphoricAcid(mol, atom, true);
+	}
+
+	public static boolean isAcidicOxygenAtPhosphoricAcid(StereoMolecule mol, int atom, boolean considerCharge) {
 		if (mol.getAtomicNo(atom) != 8)
 			return false;
 
@@ -351,11 +360,15 @@ public static boolean isNitroGroupN(StereoMolecule mol, int atom) {
 		return nitro;
 	}
 
-
-
+
 	public static boolean isBasicNitrogen(StereoMolecule mol, int atom) {
+		return isBasicNitrogen(mol, atom, true);
+	}
+
+
+	public static boolean isBasicNitrogen(StereoMolecule mol, int atom, boolean considerCharge) {
 		if (mol.getAtomicNo(atom) != 7
-		 || mol.getAtomCharge(atom) != 0
+		 || (considerCharge && mol.getAtomCharge(atom) != 0)
 		 || (mol.getConnAtoms(atom) + mol.getAtomPi(atom) > 3))
 			return false;
 
@@ -552,5 +565,23 @@ && getFakeOxoCount(mol, mol.getConnAtom(conn, j)) != 0)
 				}
 			}
 		return false;
+	}
+
+	public static boolean isAmphiphilic(StereoMolecule mol) {
+		boolean amphiphilic=true;
+
+		boolean acidic=false;
+		boolean basic=false;
+		for (int at = 0; at < mol.getAtoms(); at++) {
+			if(isAcidicOxygen(mol, at)){
+				acidic=true;
+			}
+			if(isBasicNitrogen(mol, at)){
+				basic=true;
+			}
 		}
+
+		amphiphilic = basic && acidic;
+		return amphiphilic;
 	}
+}

src/com/actelion/research/gwt/chemlib/com/actelion/research/chem/Canonizer.java

@@ -172,7 +172,7 @@ public class Canonizer {
 	private ArrayList<int[]> mTHParityNormalizationGroupList;
 	private int mMode,mNoOfRanks,mNoOfPseudoGroups;
 	private boolean mIsOddParityRound;
-	private boolean mZCoordinatesAvailable;
+	private boolean mZCoordinatesAvailable,mAllHydrogensAreExplicit;
 	private boolean mCIPParityNoDistinctionProblem;
 	private boolean mEncodeAvoid127;
 
@@ -226,6 +226,18 @@ public Canonizer(StereoMolecule mol, int mode) {
 
 		mZCoordinatesAvailable = ((mode & COORDS_ARE_3D) != 0) || mMol.is3D();
 
+		mAllHydrogensAreExplicit = false;
+		if (mMol.getAllAtoms() > mMol.getAtoms()
+		 && !mMol.isFragment()) {
+			mAllHydrogensAreExplicit = true;
+			for (int i=0; i<mMol.getAtoms(); i++) {
+				if (mMol.getImplicitHydrogens(i) != 0) {
+					mAllHydrogensAreExplicit = false;
+					break;
+					}
+				}
+			}
+
 		if ((mMode & NEGLECT_ANY_STEREO_INFORMATION) == 0) {
 			mTHParity = new byte[mMol.getAtoms()];
 			mTHParityIsPseudo = new boolean[mMol.getAtoms()];
@@ -3175,6 +3187,43 @@ private void idCodeCreate() {
 				}
 			}
 
+		if (mAllHydrogensAreExplicit && (mMode & ENCODE_ATOM_SELECTION) != 0) {
+			count = 0;
+			int connBits = 0;
+			for (int i=0; i<mMol.getAtoms(); i++) {
+				int atom = mGraphAtom[i];
+				int conns = 0;
+				for (int j=mMol.getConnAtoms(atom); j<mMol.getAllConnAtoms(atom); j++) {
+					if (mMol.isSelectedAtom(mMol.getConnAtom(atom, j))) {
+						int hIndex = j - mMol.getConnAtoms(atom);
+						conns |= (1 << hIndex);
+						connBits = Math.max(connBits, hIndex+1);
+						}
+					}
+				if (conns != 0)
+					count++;
+				}
+			if (count != 0) {
+				encodeFeatureNo(38);    // 38 = datatype 'selected hydrogens'
+				encodeBits(count, nbits);
+				encodeBits(connBits, 3);
+				for (int i=0; i<mMol.getAtoms(); i++) {
+					int atom = mGraphAtom[i];
+					int conns = 0;
+					for (int j=mMol.getConnAtoms(atom); j<mMol.getAllConnAtoms(atom); j++) {
+						if (mMol.isSelectedAtom(mMol.getConnAtom(atom, j))) {
+							int hIndex = j - mMol.getConnAtoms(atom);
+							conns |= (1 << hIndex);
+							}
+						}
+					if (conns != 0) {
+						encodeBits(atom, nbits);
+						encodeBits(conns, connBits);
+						}
+					}
+				}
+			}
+
 		encodeBits(0, 1);
 		mIDCode = encodeBitsEnd();
 		}
@@ -3370,18 +3419,7 @@ private void encodeCoordinates(boolean keepPositionAndScale, Coordinates[] coord
 			}
 
 		// if we have 3D-coords and explicit hydrogens and if all hydrogens are explicit then encode hydrogen coordinates
-		boolean includeHydrogenCoordinates = false;
-		if (mZCoordinatesAvailable
-		 && mMol.getAllAtoms() > mMol.getAtoms()
-		 && !mMol.isFragment()) {
-			includeHydrogenCoordinates = true;
-			for (int i=0; i<mMol.getAtoms(); i++) {
-				if (mMol.getImplicitHydrogens(i) != 0) {
-					includeHydrogenCoordinates = false;
-					break;
-					}
-				}
-			}
+		boolean includeHydrogenCoordinates = mZCoordinatesAvailable & mAllHydrogensAreExplicit;
 
 		int resolutionBits = mZCoordinatesAvailable ? 16 : 8;	// must be an even number
 		encodeBitsStart(true);

src/com/actelion/research/gwt/chemlib/com/actelion/research/chem/ExtendedMolecule.java

@@ -1437,7 +1437,7 @@ public int getSubstituentSize(int coreAtom, int firstAtom) {
 	public boolean supportsImplicitHydrogen(int atom) {
 		if ((mAtomFlags[atom] & cAtomFlagsValence) != 0)
 			return true;
-		if (mAtomicNo[atom] == 1)
+		if (mAtomicNo[atom] <= 1)
 			return false;
 		return isOrganicAtom(atom)
 				|| mAtomicNo[atom] == 13	// Al
@@ -1463,6 +1463,9 @@ public int getImplicitHydrogens(int atom) {
 		if (!supportsImplicitHydrogen(atom))
 			return 0;
 
+		if ("*".equals(getAtomCustomLabel(atom)))
+			return 0;
+
 		ensureHelperArrays(cHelperNeighbours);
 
 		int occupiedValence = 0;
@@ -3476,8 +3479,11 @@ public int getHelperArrayStatus() {
 	 * bonds leading to them are moved to the end of the bond table. This way algorithms can skip
 	 * hydrogen atoms easily. For every atom directly connected atoms and bonds (with and without
 	 * hydrogens) are determined. The number of pi electrons is counted.<br>
+	 * If this Molecule is a substructure (mFragment=true) and has no 3-dimensional atom coordinates,
+	 * then all explicit hydrogen atoms are converted into query features, unless setHydrogenProtection(true)
+	 * was called before on this Molecule.<br>
 	 * <i>cHelperRings</i>: Aromatic and non-aromatic rings are detected. Atom and bond ring
-	 * properties are set and a ring collection provides a total set of small rings (7 or less atoms).
+	 * properties are set and a ring collection provides a total set of small rings (7 or fewer atoms).
 	 * Atoms being in allylic/benzylic or stabilized (neighbor of a carbonyl or similar group) position
 	 * are flagged as such.<br>
 	 * <i>cHelperParities</i>: Atom (tetrahedral or axial) and bond (E/Z or atrop) parities are calculated
@@ -3501,7 +3507,7 @@ public void ensureHelperArrays(int required) {
 			calculateNeighbours();
 			mValidHelperArrays |= cHelperBitNeighbours;
 
-			if (convertHydrogenToQueryFeatures()) {
+			if (mIsFragment && !is3D() && convertHydrogenToQueryFeatures()) {
 				handleHydrogens();
 				calculateNeighbours();
 				mValidHelperArrays |= cHelperBitNeighbours;
@@ -3989,9 +3995,6 @@ else if (atomRingBondCount[atom] > 3)
 	 * @return true if hydrogens were deleted and, thus, mConnAtoms are invalid
 	 */
 	private boolean convertHydrogenToQueryFeatures() {
-		if (!mIsFragment)
-			return false;
-
 		// if an atom has no free valence then cAtomQFNoMoreNeighbours is not necessary
 		// and cAtomQFMoreNeighbours is not possible
 		// unless it is an uncharged N- or O-family atom that could be e.g. methylated
@@ -4001,12 +4004,15 @@ private boolean convertHydrogenToQueryFeatures() {
 				mAtomQueryFeatures[atom] &= ~(cAtomQFNoMoreNeighbours | cAtomQFMoreNeighbours);
 			}
 
-			// approximate explicit hydrogens by query features
-			// and remove explicit hydrogens except those with stereo bonds
+		if (mProtectHydrogen)
+			return false;
+
+		// approximate explicit hydrogens by query features
+		// and remove explicit hydrogens except those with stereo bonds
 		boolean deleteHydrogens = false;
 		for (int atom=0; atom<mAtoms; atom++) {
 			int explicitHydrogens = getExplicitHydrogens(atom);
-			if (!mProtectHydrogen && explicitHydrogens > 0) {
+			if (explicitHydrogens > 0) {
 				if ((mAtomQueryFeatures[atom] & cAtomQFNoMoreNeighbours) == 0) {
 						// add query feature hydrogen to explicit hydrogens
 					int queryFeatureHydrogens =
@@ -4048,6 +4054,7 @@ private boolean convertHydrogenToQueryFeatures() {
 					}
 				}
 			}
+
 		if (deleteHydrogens)
 			compressMolTable();
 

src/com/actelion/research/gwt/chemlib/com/actelion/research/chem/ExtendedMoleculeFunctions.java

@@ -66,6 +66,8 @@
 package com.actelion.research.chem;
 
 import com.actelion.research.calc.ArrayUtilsCalc;
+import com.actelion.research.calc.statistics.StatisticsOverview;
+import com.actelion.research.calc.statistics.median.MedianStatisticFunctions;
 import com.actelion.research.chem.descriptor.DescriptorEncoder;
 import com.actelion.research.chem.descriptor.DescriptorHandler;
 import com.actelion.research.util.BurtleHasher;
@@ -770,6 +772,23 @@ public final static boolean atomAtomSubStrucMatch(StereoMolecule molecule, int a
 		return arr;
 	}
 
+	public final static int [] getTopologicalDistances(int [][] topoDistMatrix, int [] at1, int [] at2) {
+
+		int [] d = new int[at1.length*at2.length];
+		int cc=0;
+		for (int i = 0; i < at1.length; i++) {
+			for (int j = 0; j < at2.length; j++) {
+				d[cc++]=topoDistMatrix[at1[i]][at2[j]];
+			}
+		}
+
+		return d;
+	}
+	public final static int getMedianTopologicalDistance(int [][] topoDistMatrix, int [] at1, int [] at2) {
+		int [] d = getTopologicalDistances(topoDistMatrix, at1, at2);
+		int medTopoDist = MedianStatisticFunctions.getMedianForInteger(d).median;
+		return medTopoDist;
+	}
 
 	public final static int getTopologicalDistance(ExtendedMolecule mol, int at1, int at2) {
 		int dist = 0;
@@ -1271,19 +1290,31 @@ public static int getNumCyanoGroups(StereoMolecule mol){
 	}
 
 
-	public static int getNumAlcoholicOxygen(StereoMolecule mol){
-
+	public static int getTotalCharge(StereoMolecule mol){
 		int n = 0;
-
 		for (int i = 0; i < mol.getAllAtoms(); i++) {
+			n+=mol.getAtomCharge(i);
+		}
+		return n;
+	}
+	public static int getNumAtomsCharged(StereoMolecule mol){
+		int n = 0;
+		for (int i = 0; i < mol.getAllAtoms(); i++) {
+			if(mol.getAtomCharge(i)!=0){
+				n++;
+			}
+		}
+		return n;
+	}
 
+	public static int getNumAlcoholicOxygen(StereoMolecule mol){
+		int n = 0;
+		for (int i = 0; i < mol.getAllAtoms(); i++) {
 			if(isAlcoholicOxygen(mol, i)){
 				n++;
 			}
 		}
-
 		return n;
-
 	}
 
 	public static int getNumThioEther(StereoMolecule mol){

src/com/actelion/research/gwt/chemlib/com/actelion/research/chem/IDCodeParserWithoutCoordinateInvention.java

@@ -75,7 +75,7 @@ public void neglectSpaceDelimitedCoordinates() {
 	 * @return
 	 */
 	public StereoMolecule getCompactMolecule(String idcode) {
-		return (idcode == null || idcode.isEmpty()) ? null : getCompactMolecule(idcode.getBytes(StandardCharsets.UTF_8), null);
+		return (idcode == null || idcode.isEmpty()) ? null : getCompactMolecule(idcode.getBytes(StandardCharsets.UTF_8));
 		}
 
 	/**
@@ -433,6 +433,7 @@ public void parse(StereoMolecule mol, byte[] idcode, byte[] coordinates, int idc
 		mMol.setFragment(decodeBits(1) == 1);
 
 		int[] aromaticSPBond = null;
+		int[] selectedHydrogenBits = null;
 
 		int offset = 0;
 		while (decodeBits(1) == 1) {
@@ -724,6 +725,13 @@ public void parse(StereoMolecule mol, byte[] idcode, byte[] coordinates, int idc
 					mMol.setBondType(bond, bondType);
 					}
 				break;
+			case 38:	//	datatype 'selected hydrogen'
+				no = decodeBits(abits);
+				int connBits = decodeBits(3);
+				selectedHydrogenBits = new int[allAtoms];
+				for (int i=0; i<no; i++)
+					selectedHydrogenBits[decodeBits(abits)] = decodeBits(connBits);
+				break;
 				}
 			}
 
@@ -786,6 +794,9 @@ public void parse(StereoMolecule mol, byte[] idcode, byte[] coordinates, int idc
 								mMol.setAtomY(hydrogen, mMol.getAtomY(atom) + (decodeBits(resolutionBits) - binCount / 2.0));
 								if (coordsAre3D)
 									mMol.setAtomZ(hydrogen, mMol.getAtomZ(atom) + (decodeBits(resolutionBits) - binCount / 2.0));
+
+								if (selectedHydrogenBits != null && (selectedHydrogenBits[atom] & (1 << i)) != 0)
+									mMol.setAtomSelection(hydrogen, true);
 								}
 							}
 

src/com/actelion/research/gwt/chemlib/com/actelion/research/chem/SmilesParser.java

@@ -812,7 +812,7 @@ else if (!mMakeHydrogenExplicit && (mSmartsFeatureFound || mSmartsMode == SMARTS
 
 			if (parityMap != null) {
 				for (THParity parity:parityMap.values())
-					mMol.setAtomParity(parity.mCentralAtom, parity.calculateParity(handleHydrogenAtomMap), false);
+					mMol.setAtomParity(handleHydrogenAtomMap[parity.mCentralAtom], parity.calculateParity(handleHydrogenAtomMap), false);
 
 				mMol.setParitiesValid(0);
 				}