Even more efficient graph creation (my initial scheme, but this time without accidentally changing what's in the sequence records)

src/main/java/BiGpairSEQ.java

@@ -13,7 +13,7 @@ public class BiGpairSEQ {
     private static boolean cacheCells = false;
     private static boolean cachePlate = false;
     private static boolean cacheGraph = false;
-    private static AlgorithmType matchingAlgoritmType = AlgorithmType.HUNGARIAN;
+    private static AlgorithmType matchingAlgorithmType = AlgorithmType.HUNGARIAN;
     private static HeapType priorityQueueHeapType = HeapType.PAIRING;
     private static DistributionType distributionType = DistributionType.ZIPF;
     private static boolean outputBinary = true;
@@ -166,13 +166,13 @@ public class BiGpairSEQ {
         return priorityQueueHeapType;
     }
 
-    public static AlgorithmType getMatchingAlgoritmType() { return matchingAlgoritmType; }
+    public static AlgorithmType getMatchingAlgorithmType() { return matchingAlgorithmType; }
 
-    public static void setHungarianAlgorithm() { matchingAlgoritmType = AlgorithmType.HUNGARIAN; }
+    public static void setHungarianAlgorithm() { matchingAlgorithmType = AlgorithmType.HUNGARIAN; }
 
-    public static void setIntegerWeightScalingAlgorithm() { matchingAlgoritmType = AlgorithmType.INTEGER_WEIGHT_SCALING; }
+    public static void setIntegerWeightScalingAlgorithm() { matchingAlgorithmType = AlgorithmType.INTEGER_WEIGHT_SCALING; }
 
-    public static void setAuctionAlgorithm() { matchingAlgoritmType = AlgorithmType.AUCTION; }
+    public static void setAuctionAlgorithm() { matchingAlgorithmType = AlgorithmType.AUCTION; }
 
     public static void setPairingHeap() {
         priorityQueueHeapType = HeapType.PAIRING;

src/main/java/GraphModificationFunctions.java

@@ -1,72 +1,54 @@
 import org.jgrapht.graph.DefaultWeightedEdge;
 import org.jgrapht.graph.SimpleWeightedGraph;
 
-import java.util.ArrayList;
+import java.util.*;
-import java.util.HashMap;
-import java.util.List;
-import java.util.Map;
 
 public interface GraphModificationFunctions {
 
     //remove over- and under-weight edges, return removed edges
-    static Map<Vertex[], Integer> filterByOverlapThresholds(SimpleWeightedGraph<Vertex, DefaultWeightedEdge> graph,
+    static Map<DefaultWeightedEdge, Vertex[]> filterByOverlapThresholds(SimpleWeightedGraph<Vertex, DefaultWeightedEdge> graph,
-                                                            int low, int high, boolean saveEdges) {
+                                                              int low, int high, boolean saveEdges) {
-        Map<Vertex[], Integer> removedEdges = new HashMap<>();
+        Map<DefaultWeightedEdge, Vertex[]> removedEdges = new HashMap<>();
+        Set<DefaultWeightedEdge> edgesToRemove = new HashSet<>();
         for (DefaultWeightedEdge e : graph.edgeSet()) {
             if ((graph.getEdgeWeight(e) > high) || (graph.getEdgeWeight(e) < low)) {
                 if(saveEdges) {
-                    Vertex source = graph.getEdgeSource(e);
+                    Vertex[] vertices = {graph.getEdgeSource(e), graph.getEdgeTarget(e)};
-                    Vertex target = graph.getEdgeTarget(e);
+                    removedEdges.put(e, vertices);
-                    Integer weight = (int) graph.getEdgeWeight(e);
-                    Vertex[] edge = {source, target};
-                    removedEdges.put(edge, weight);
-                }
-                else {
-                    graph.setEdgeWeight(e, 0.0);
                 }
+                edgesToRemove.add(e);
             }
         }
-        if(saveEdges) {
+        edgesToRemove.forEach(graph::removeEdge);
-            for (Vertex[] edge : removedEdges.keySet()) {
-                graph.removeEdge(edge[0], edge[1]);
-            }
-        }
         return removedEdges;
     }
 
     //Remove edges for pairs with large occupancy discrepancy, return removed edges
-    static Map<Vertex[], Integer> filterByRelativeOccupancy(SimpleWeightedGraph<Vertex, DefaultWeightedEdge> graph,
+    static Map<DefaultWeightedEdge, Vertex[]> filterByRelativeOccupancy(SimpleWeightedGraph<Vertex, DefaultWeightedEdge> graph,
                                                   Integer maxOccupancyDifference, boolean saveEdges) {
-        Map<Vertex[], Integer> removedEdges = new HashMap<>();
+        Map<DefaultWeightedEdge, Vertex[]> removedEdges = new HashMap<>();
+        Set<DefaultWeightedEdge> edgesToRemove = new HashSet<>();
         for (DefaultWeightedEdge e : graph.edgeSet()) {
             Integer alphaOcc = graph.getEdgeSource(e).getOccupancy();
             Integer betaOcc = graph.getEdgeTarget(e).getOccupancy();
             if (Math.abs(alphaOcc - betaOcc) >= maxOccupancyDifference) {
                 if (saveEdges) {
-                    Vertex source = graph.getEdgeSource(e);
+                    Vertex[] vertices = {graph.getEdgeSource(e), graph.getEdgeTarget(e)};
-                    Vertex target = graph.getEdgeTarget(e);
+                    removedEdges.put(e, vertices);
-                    Integer weight = (int) graph.getEdgeWeight(e);
-                    Vertex[] edge = {source, target};
-                    removedEdges.put(edge, weight);
-                }
-                else {
-                    graph.setEdgeWeight(e, 0.0);
                 }
+                edgesToRemove.add(e);
             }
         }
-        if(saveEdges) {
+        edgesToRemove.forEach(graph::removeEdge);
-            for (Vertex[] edge : removedEdges.keySet()) {
-                graph.removeEdge(edge[0], edge[1]);
-            }
-        }
         return removedEdges;
     }
 
     //Remove edges for pairs where overlap size is significantly lower than the well occupancy, return removed edges
-    static Map<Vertex[], Integer> filterByOverlapPercent(SimpleWeightedGraph<Vertex, DefaultWeightedEdge> graph,
+    static Map<DefaultWeightedEdge, Vertex[]> filterByOverlapPercent(SimpleWeightedGraph<Vertex, DefaultWeightedEdge> graph,
                                                          Integer minOverlapPercent,
                                                          boolean saveEdges) {
-        Map<Vertex[], Integer> removedEdges = new HashMap<>();
+        Map<DefaultWeightedEdge, Vertex[]> removedEdges = new HashMap<>();
+        Set<DefaultWeightedEdge> edgesToRemove = new HashSet<>();
         for (DefaultWeightedEdge e : graph.edgeSet()) {
             Integer alphaOcc = graph.getEdgeSource(e).getOccupancy();
             Integer betaOcc = graph.getEdgeTarget(e).getOccupancy();
@@ -74,22 +56,13 @@ public interface GraphModificationFunctions {
             double min = minOverlapPercent / 100.0;
             if ((weight / alphaOcc < min) || (weight / betaOcc < min)) {
                 if (saveEdges) {
-                    Vertex source = graph.getEdgeSource(e);
+                    Vertex[] vertices = {graph.getEdgeSource(e), graph.getEdgeTarget(e)};
-                    Vertex target = graph.getEdgeTarget(e);
+                    removedEdges.put(e, vertices);
-                    Integer intWeight = (int) graph.getEdgeWeight(e);
-                    Vertex[] edge = {source, target};
-                    removedEdges.put(edge, intWeight);
-                }
-                else {
-                    graph.setEdgeWeight(e, 0.0);
                 }
+                edgesToRemove.add(e);
             }
         }
-        if(saveEdges) {
+        edgesToRemove.forEach(graph::removeEdge);
-            for (Vertex[] edge : removedEdges.keySet()) {
-                graph.removeEdge(edge[0], edge[1]);
-            }
-        }
         return removedEdges;
     }
 
@@ -126,10 +99,10 @@ public interface GraphModificationFunctions {
     }
 
     static void addRemovedEdges(SimpleWeightedGraph<Vertex, DefaultWeightedEdge> graph,
-                                Map<Vertex[], Integer> removedEdges) {
+                                Map<DefaultWeightedEdge, Vertex[]> removedEdges) {
-        for (Vertex[] edge : removedEdges.keySet()) {
+        for (DefaultWeightedEdge edge : removedEdges.keySet()) {
-            DefaultWeightedEdge e = graph.addEdge(edge[0], edge[1]);
+            Vertex[] vertices = removedEdges.get(edge);
-            graph.setEdgeWeight(e, removedEdges.get(edge));
+            graph.addEdge(vertices[0], vertices[1], edge);
         }
     }
 

src/main/java/Simulator.java

@@ -1,9 +1,7 @@
 import org.jgrapht.alg.interfaces.MatchingAlgorithm;
 import org.jgrapht.alg.matching.MaximumWeightBipartiteMatching;
-import org.jgrapht.generate.SimpleWeightedBipartiteGraphMatrixGenerator;
 import org.jgrapht.graph.DefaultWeightedEdge;
 import org.jgrapht.graph.SimpleWeightedGraph;
-import org.jheaps.tree.FibonacciHeap;
 import org.jheaps.tree.PairingHeap;
 
 import java.math.BigDecimal;
@@ -150,17 +148,22 @@ public class Simulator implements GraphModificationFunctions {
         }
         betaVertices.forEach(graph::addVertex);
         //add edges
-        for(Vertex alpha: alphaVertices){
+        for(Vertex a: alphaVertices) {
-            for(Vertex beta: betaVertices) {
+            for(Vertex b: betaVertices) {
-                Set<Integer> sharedWells = alpha.getRecord().getWells();
+                Set<Integer> sharedWells = new HashSet<>(a.getRecord().getWells());
-                sharedWells.retainAll(beta.getRecord().getWells());
+                sharedWells.retainAll(b.getRecord().getWells());
-                if(!sharedWells.isEmpty()) {
+                double weight = (double) sharedWells.size();
-                    DefaultWeightedEdge edge = graph.addEdge(alpha, beta);
+                if (weight != 0.0) {
-                    graph.setEdgeWeight(edge, sharedWells.size());
+                    System.out.println("Edge weight: " + weight);
+                    DefaultWeightedEdge edge = graph.addEdge(a, b);
+                    graph.setEdgeWeight(edge, weight);
+                }
+                else {
+                    System.out.println("No overlap");
+
                 }
             }
         }
-
         if(verbose){System.out.println("Graph created");}
         //stop timing
         Instant stop = Instant.now();
@@ -184,7 +187,7 @@ public class Simulator implements GraphModificationFunctions {
                                             Integer minOverlapPercent, boolean verbose, boolean calculatePValue) {
         Instant start = Instant.now();
         SimpleWeightedGraph<Vertex, DefaultWeightedEdge> graph = data.getGraph();
-        Map<Vertex[], Integer> removedEdges = new HashMap<>();
+        Map<DefaultWeightedEdge, Vertex[]> removedEdges = new HashMap<>();
         boolean saveEdges = BiGpairSEQ.cacheGraph();
         int numWells = data.getNumWells();
         //Integer alphaCount = data.getAlphaCount();
@@ -202,6 +205,7 @@ public class Simulator implements GraphModificationFunctions {
         }
         Integer graphAlphaCount = alphas.size();
         Integer graphBetaCount = betas.size();
+        Integer graphEdgeCount = graph.edgeSet().size();
 
         //remove edges with weights outside given overlap thresholds, add those to removed edge list
         if(verbose){System.out.println("Eliminating edges with weights outside overlap threshold values");}
@@ -221,12 +225,14 @@ public class Simulator implements GraphModificationFunctions {
         if(verbose){System.out.println("Edges between vertices of with excessively different occupancy values " +
                 "removed");}
 
+        Integer filteredGraphEdgeCount = graph.edgeSet().size();
+
         //Find Maximum Weight Matching
         if(verbose){System.out.println("Finding maximum weight matching");}
         //The matching object
         MatchingAlgorithm<Vertex, DefaultWeightedEdge> maxWeightMatching;
         //Determine algorithm type
-        AlgorithmType algorithm = BiGpairSEQ.getMatchingAlgoritmType();
+        AlgorithmType algorithm = BiGpairSEQ.getMatchingAlgorithmType();
         switch (algorithm) { //Only two options now, but I have room to add more algorithms in the future this way
             case AUCTION -> {
                 //create a new MaximumIntegerWeightBipartiteAuctionMatching
@@ -372,8 +378,10 @@ public class Simulator implements GraphModificationFunctions {
         metadata.put("real sequence collision rate", data.getRealSequenceCollisionRate().toString());
         metadata.put("total alphas read from plate", data.getAlphaCount().toString());
         metadata.put("total betas read from plate", data.getBetaCount().toString());
+        metadata.put("initial edges in graph", graphEdgeCount.toString());
         metadata.put("alphas in graph (after pre-filtering)", graphAlphaCount.toString());
         metadata.put("betas in graph (after pre-filtering)", graphBetaCount.toString());
+        metadata.put("final edges in graph (after pre-filtering)", filteredGraphEdgeCount.toString());
         metadata.put("high overlap threshold for pairing", highThreshold.toString());
         metadata.put("low overlap threshold for pairing", lowThreshold.toString());
         metadata.put("minimum overlap percent for pairing", minOverlapPercent.toString());