Upgrade SMSD to 6.3.0, replace CDK fingerprints with SMSD, update README

- Bump SMSD 5.10.0 to 6.3.0, remove cdk-fingerprint dependency
- GameTheoryEngine: use SMSD.circularFingerprintFCFP with IdentityHashMap cache
- StandardizeReaction: use SMSD.circularFingerprintECFP + fingerprintTanimoto
- Add atom-balance guard to prevent filtering genuine reactants
- README: add RDT logo, update to v3.5.0, SMSD 6.3.0, 163 tests
- All 163 tests pass, no CDK fingerprint imports remain

Author: asad

README.md

@@ -1,7 +1,9 @@
+![RDT Logo](images/rdt-logo.svg)
+
 Introduction
 ============
 
-`Reaction Decoder Tool (RDT) v3.3.0`
+`Reaction Decoder Tool (RDT) v3.5.0`
 --------------------------------------
 
 **Toolkit-agnostic reaction mapping engine** with CDK adapter. Deterministic, no training data required.
@@ -109,7 +111,7 @@ The package namespace has changed from `uk.ac.ebi` to `com.bioinceptionlabs` in
 <!-- Old (v2.x) -->
 <groupId>uk.ac.ebi.rdt</groupId>
 
-<!-- New (v3.3.0+) -->
+<!-- New (v3.5.0+) -->
 <groupId>com.bioinceptionlabs</groupId>
 ```
 
@@ -147,10 +149,10 @@ Performance
 |--------|-------|
 | Mapping speed | 3.4 reactions/sec (USPTO 50K) |
 | RXN coverage | 598/599 (99.8%) |
-| Test suite | 156 tests, 100% pass |
+| Test suite | 163 tests, 100% pass |
 | Test time | ~120s (4x faster than v2.x) |
 | Codebase | 68 files (reduced from 345) |
-| Dependencies | SMSD 5.2.1, CDK 2.12 |
+| Dependencies | SMSD 6.3.0, CDK 2.12 (lightweight) |
 | Deterministic | Yes (no ML training needed) |
 
 How to Cite RDT?
@@ -183,7 +185,7 @@ Sub-commands
 `AAM using SMILES`
 
   ```
-  java -jar rdt-3.3.0-jar-with-dependencies.jar -Q SMI -q "CC(O)CC(=O)OC(C)CC(O)=O.O[H]>>[H]OC(=O)CC(C)O.CC(O)CC(O)=O" -g -c -j AAM -f TEXT
+  java -jar rdt-3.5.0-jar-with-dependencies.jar -Q SMI -q "CC(O)CC(=O)OC(C)CC(O)=O.O[H]>>[H]OC(=O)CC(C)O.CC(O)CC(O)=O" -g -c -j AAM -f TEXT
   ```
 
 `Perform AAM` for Transporters
@@ -192,14 +194,14 @@ Sub-commands
 `AAM using SMILES` (accept mapping with no bond changes -b)
 
   ```
-  java -jar rdt-3.3.0-jar-with-dependencies.jar -Q SMI -q "O=C(O)C(N)CC(=O)N.O=C(O)C(N)CS>>C(N)(CC(=O)N)C(=O)O.O=C(O)C(N)CS" -b -g -c -j AAM -f TEXT
+  java -jar rdt-3.5.0-jar-with-dependencies.jar -Q SMI -q "O=C(O)C(N)CC(=O)N.O=C(O)C(N)CS>>C(N)(CC(=O)N)C(=O)O.O=C(O)C(N)CS" -b -g -c -j AAM -f TEXT
   ```
 
 `Annotate Reaction using SMILES`
 ---------------------------------
 
   ```
-  java -jar rdt-3.3.0-jar-with-dependencies.jar -Q SMI -q "CC(O)CC(=O)OC(C)CC(O)=O.O[H]>>[H]OC(=O)CC(C)O.CC(O)CC(O)=O" -g -c -j ANNOTATE -f XML
+  java -jar rdt-3.5.0-jar-with-dependencies.jar -Q SMI -q "CC(O)CC(=O)OC(C)CC(O)=O.O[H]>>[H]OC(=O)CC(C)O.CC(O)CC(O)=O" -g -c -j ANNOTATE -f XML
   ```
 
 
@@ -209,12 +211,12 @@ Sub-commands
 `Compare Reactions using SMILES with precomputed AAM mappings`
 
   ```
-  java -jar rdt-3.3.0-jar-with-dependencies.jar -Q RXN -q example/ReactionDecoder_mapped.rxn  -T RXN -t example/ReactionDecoder_mapped.rxn -j COMPARE -f BOTH -u
+  java -jar rdt-3.5.0-jar-with-dependencies.jar -Q RXN -q example/ReactionDecoder_mapped.rxn  -T RXN -t example/ReactionDecoder_mapped.rxn -j COMPARE -f BOTH -u
   ```
 
 
 `Compare Reactions using RXN files`
 
   ```
-  java -jar rdt-3.3.0-jar-with-dependencies.jar -Q RXN -q example/ReactionDecoder_mapped.rxn  -T RXN -t example/ReactionDecoder_mapped.rxn -j COMPARE -f BOTH
+  java -jar rdt-3.5.0-jar-with-dependencies.jar -Q RXN -q example/ReactionDecoder_mapped.rxn  -T RXN -t example/ReactionDecoder_mapped.rxn -j COMPARE -f BOTH
   ```

pom.xml

@@ -181,16 +181,11 @@
             <artifactId>cdk-inchi</artifactId>
             <version>${cdk.version}</version>
         </dependency>
-        <dependency>
-            <groupId>org.openscience.cdk</groupId>
-            <artifactId>cdk-fingerprint</artifactId>
-            <version>${cdk.version}</version>
-        </dependency>
 
         <dependency>
             <groupId>com.bioinceptionlabs</groupId>
             <artifactId>smsd</artifactId>
-            <version>5.8.1</version>
+            <version>6.3.0</version>
         </dependency>
 
         <!-- https://mvnrepository.com/artifact/commons-cli/commons-cli -->

src/main/java/com/bioinceptionlabs/reactionblast/mapping/algorithm/GameTheoryEngine.java

@@ -47,8 +47,7 @@
 
 import org.openscience.cdk.PseudoAtom;
 import org.openscience.cdk.exception.CDKException;
-import org.openscience.cdk.fingerprint.CircularFingerprinter;
-import org.openscience.cdk.fingerprint.IBitFingerprint;
+import com.bioinception.smsd.core.SMSD;
 import org.openscience.cdk.graph.CycleFinder;
 import org.openscience.cdk.graph.Cycles;
 import org.openscience.cdk.interfaces.IAtom;
@@ -138,6 +137,9 @@ public abstract class GameTheoryEngine extends Debugger implements IGameTheory,
             = createLoggingTool(GameTheoryEngine.class);
     private static final long serialVersionUID = 1698688633678282L;
 
+    private final transient java.util.IdentityHashMap<IAtomContainer, int[]> circularFPCache
+            = new java.util.IdentityHashMap<>();
+
     // ---- BaseGameTheory methods inlined into outer class ----
 
     protected static boolean isPseudoAtoms(IAtomContainer atomContainer) {
@@ -500,10 +502,19 @@ String generateUniqueKey(
     }
 
     private int[] getCircularFP(IAtomContainer mol) throws CDKException {
-        CircularFingerprinter circularFingerprinter = new CircularFingerprinter(6, 1024);
-        circularFingerprinter.setPerceiveStereo(true);
-        IBitFingerprint bitFingerprint = circularFingerprinter.getBitFingerprint(mol);
-        return bitFingerprint.getSetbits();
+        int[] cached = circularFPCache.get(mol);
+        if (cached != null) {
+            return cached;
+        }
+        long[] fp = SMSD.circularFingerprintFCFP(mol, 1, 1024);
+        BitSet bs = SMSD.toBitSet(fp);
+        int[] bits = new int[bs.cardinality()];
+        int idx = 0;
+        for (int i = bs.nextSetBit(0); i >= 0; i = bs.nextSetBit(i + 1)) {
+            bits[idx++] = i;
+        }
+        circularFPCache.put(mol, bits);
+        return bits;
     }
 
     MCSSolution copyOldSolutionToNew(int queryPosition, int targetPosition,

src/main/java/com/bioinceptionlabs/reactionblast/tools/StandardizeReaction.java

@@ -28,12 +28,11 @@
 import java.util.Set;
 import java.util.logging.Level;
 
-import org.openscience.cdk.fingerprint.CircularFingerprinter;
+import com.bioinception.smsd.core.SMSD;
 import org.openscience.cdk.interfaces.IAtom;
 import org.openscience.cdk.interfaces.IAtomContainer;
 import org.openscience.cdk.interfaces.IAtomContainerSet;
 import org.openscience.cdk.interfaces.IReaction;
-import org.openscience.cdk.similarity.Tanimoto;
 import org.openscience.cdk.tools.ILoggingTool;
 import static org.openscience.cdk.tools.LoggingToolFactory.createLoggingTool;
 import com.bioinceptionlabs.reactionblast.mapping.ReactionContainer.CDKReactionBuilder;
@@ -172,14 +171,13 @@ public IReaction filterReagents(IReaction reaction) {
         }
 
         try {
-            CircularFingerprinter fp = new CircularFingerprinter();
             IAtomContainerSet products = reaction.getProducts();
 
-            // Pre-compute product fingerprints
-            List<org.openscience.cdk.fingerprint.IBitFingerprint> productFPs = new ArrayList<>();
+            // Pre-compute product fingerprints using SMSD ECFP4 (radius=2)
+            List<long[]> productFPs = new ArrayList<>();
             for (IAtomContainer prod : products.atomContainers()) {
                 try {
-                    productFPs.add(fp.getBitFingerprint(prod));
+                    productFPs.add(SMSD.circularFingerprintECFP(prod, 2, 1024));
                 } catch (Exception e) {
                     productFPs.add(null);
                 }
@@ -200,10 +198,14 @@ public IReaction filterReagents(IReaction reaction) {
                 boolean isReagent = false;
                 String reason = "";
 
+                // Check if this reactant is needed for atom balance
+                boolean neededForBalance = isNeededForBalance(
+                        reactant, reaction.getReactants(), productAtomCounts);
+
                 try {
                     // Check 1: Known solvent/reagent by canonical SMILES
                     String canSmiles = smiGen.create(reactant);
-                    if (KNOWN_REAGENT_SMILES.contains(canSmiles)) {
+                    if (!neededForBalance && KNOWN_REAGENT_SMILES.contains(canSmiles)) {
                         isReagent = true;
                         reason = "known reagent/solvent: " + canSmiles;
                     }
@@ -220,14 +222,13 @@ public IReaction filterReagents(IReaction reaction) {
                     }
 
                     // Check 3: Tanimoto fingerprint similarity
-                    if (!isReagent) {
-                        org.openscience.cdk.fingerprint.IBitFingerprint reactantFP =
-                                fp.getBitFingerprint(reactant);
+                    if (!isReagent && !neededForBalance) {
+                        long[] reactantFP = SMSD.circularFingerprintECFP(reactant, 2, 1024);
 
                         double maxSim = 0.0;
-                        for (org.openscience.cdk.fingerprint.IBitFingerprint prodFP : productFPs) {
+                        for (long[] prodFP : productFPs) {
                             if (prodFP != null) {
-                                double sim = Tanimoto.calculate(reactantFP, prodFP);
+                                double sim = SMSD.fingerprintTanimoto(reactantFP, prodFP);
                                 maxSim = Math.max(maxSim, sim);
                             }
                         }
@@ -310,6 +311,20 @@ public IReaction filterReagents(IReaction reaction) {
         }
     }
 
+    private boolean isNeededForBalance(IAtomContainer candidate,
+            IAtomContainerSet allReactants, Map<String, Integer> productAtomCounts) {
+        Map<String, Integer> remaining = new LinkedHashMap<>(countAtoms(allReactants));
+        for (IAtom atom : candidate.atoms()) {
+            remaining.merge(atom.getSymbol(), -1, Integer::sum);
+        }
+        for (Map.Entry<String, Integer> entry : productAtomCounts.entrySet()) {
+            if (remaining.getOrDefault(entry.getKey(), 0) < entry.getValue()) {
+                return true;
+            }
+        }
+        return false;
+    }
+
     private Map<String, Integer> countAtoms(IAtomContainerSet molSet) {
         Map<String, Integer> counts = new LinkedHashMap<>();
         for (IAtomContainer mol : molSet.atomContainers()) {