diff --git a/genomix/genomix-data/src/main/java/edu/uci/ics/genomix/type/NodeWritable.java b/genomix/genomix-data/src/main/java/edu/uci/ics/genomix/type/NodeWritable.java
index 19f6374..efa87f7 100644
--- a/genomix/genomix-data/src/main/java/edu/uci/ics/genomix/type/NodeWritable.java
+++ b/genomix/genomix-data/src/main/java/edu/uci/ics/genomix/type/NodeWritable.java
@@ -51,6 +51,7 @@
     }
     
     public void set(NodeWritable node){
+        this.kmerlength = node.kmerlength;
         set(node.nodeIdList, node.forwardForwardList, node.forwardReverseList, node.reverseForwardList, 
                 node.reverseReverseList, node.kmer);
     }
@@ -92,6 +93,14 @@
         this.kmer.set(kmer);
     }
     
+    public int getKmerlength() {
+        return kmerlength;
+    }
+
+    public void setKmerlength(int kmerlength) {
+        this.kmerlength = kmerlength;
+    }
+
     public int getCount() {
         return kmer.getKmerLength();
     }
diff --git a/genomix/genomix-data/src/test/java/edu/uci/ics/genomix/data/test/PositionWritableTest.java b/genomix/genomix-data/src/test/java/edu/uci/ics/genomix/data/test/PositionWritableTest.java
index 540c6eb..fc67245 100644
--- a/genomix/genomix-data/src/test/java/edu/uci/ics/genomix/data/test/PositionWritableTest.java
+++ b/genomix/genomix-data/src/test/java/edu/uci/ics/genomix/data/test/PositionWritableTest.java
@@ -1,4 +1,5 @@
 package edu.uci.ics.genomix.data.test;
+
 import java.util.Random;
 
 import junit.framework.Assert;
diff --git a/genomix/genomix-hadoop/data/webmap/8 b/genomix/genomix-hadoop/data/webmap/8
new file mode 100644
index 0000000..3959d4d
--- /dev/null
+++ b/genomix/genomix-hadoop/data/webmap/8
@@ -0,0 +1 @@
+1	AATAGAACTT
diff --git a/genomix/genomix-hadoop/src/main/java/edu/uci/ics/genomix/hadoop/contrailgraphbuilding/GenomixMapper.java b/genomix/genomix-hadoop/src/main/java/edu/uci/ics/genomix/hadoop/contrailgraphbuilding/GenomixMapper.java
index 3b615cb..98f561f 100644
--- a/genomix/genomix-hadoop/src/main/java/edu/uci/ics/genomix/hadoop/contrailgraphbuilding/GenomixMapper.java
+++ b/genomix/genomix-hadoop/src/main/java/edu/uci/ics/genomix/hadoop/contrailgraphbuilding/GenomixMapper.java
@@ -226,7 +226,7 @@
     public void setCurKmerByOldNextKmer(){
     	curKmerDir = nextKmerDir;
     	curForwardKmer.set(nextForwardKmer);
-    	preReverseKmer.set(nextReverseKmer);
+    	curReverseKmer.set(nextReverseKmer);
     }
     
     public void setMapperOutput(OutputCollector<KmerBytesWritable, NodeWritable> output) throws IOException{
diff --git a/genomix/genomix-hadoop/src/test/java/edu/uci/ics/genomix/hadoop/contrailgraphbuilding/GraphBuildingTest.java b/genomix/genomix-hadoop/src/test/java/edu/uci/ics/genomix/hadoop/contrailgraphbuilding/GraphBuildingTest.java
index 797efb2..42c43f8 100644
--- a/genomix/genomix-hadoop/src/test/java/edu/uci/ics/genomix/hadoop/contrailgraphbuilding/GraphBuildingTest.java
+++ b/genomix/genomix-hadoop/src/test/java/edu/uci/ics/genomix/hadoop/contrailgraphbuilding/GraphBuildingTest.java
@@ -22,13 +22,13 @@
     private JobConf conf = new JobConf();
     private static final String ACTUAL_RESULT_DIR = "actual";
     private static final String HADOOP_CONF_PATH = ACTUAL_RESULT_DIR + File.separator + "conf.xml";
-    private static final String DATA_PATH = "data/webmap/test.txt";
+    private static final String DATA_PATH = "data/webmap/8";
     private static final String HDFS_PATH = "/webmap";
     private static final String RESULT_PATH = "/result";
     
 //    private static final int COUNT_REDUCER = 2;
-    private static final int SIZE_KMER = 5;
-    private static final int READ_LENGTH = 8;
+    private static final int SIZE_KMER = 3;
+    private static final int READ_LENGTH = 10;
     
     private MiniDFSCluster dfsCluster;
     private MiniMRCluster mrCluster;
diff --git a/genomix/genomix-pregelix/data/PathMergeTestSet/8/part-00000 b/genomix/genomix-pregelix/data/PathMergeTestSet/8/part-00000
new file mode 100755
index 0000000..db653a7
--- /dev/null
+++ b/genomix/genomix-pregelix/data/PathMergeTestSet/8/part-00000
Binary files differ
diff --git a/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/format/DataCleanInputFormat.java b/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/format/GraphCleanInputFormat.java
similarity index 98%
rename from genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/format/DataCleanInputFormat.java
rename to genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/format/GraphCleanInputFormat.java
index 1d7bf4b..e36e344 100644
--- a/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/format/DataCleanInputFormat.java
+++ b/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/format/GraphCleanInputFormat.java
@@ -16,7 +16,7 @@
 import edu.uci.ics.genomix.pregelix.api.io.binary.BinaryDataCleanVertexInputFormat.BinaryDataCleanVertexReader;
 import edu.uci.ics.genomix.type.KmerBytesWritable;
 
-public class DataCleanInputFormat extends
+public class GraphCleanInputFormat extends
     BinaryDataCleanVertexInputFormat<KmerBytesWritable, VertexValueWritable, NullWritable, MessageWritable> {
     /**
      * Format INPUT
diff --git a/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/format/DataCleanOutputFormat.java b/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/format/GraphCleanOutputFormat.java
similarity index 97%
rename from genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/format/DataCleanOutputFormat.java
rename to genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/format/GraphCleanOutputFormat.java
index cbbdd9a..32f71be 100644
--- a/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/format/DataCleanOutputFormat.java
+++ b/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/format/GraphCleanOutputFormat.java
@@ -12,7 +12,7 @@
 import edu.uci.ics.pregelix.api.graph.Vertex;
 import edu.uci.ics.pregelix.api.io.VertexWriter;
 
-public class DataCleanOutputFormat extends
+public class GraphCleanOutputFormat extends
     BinaryDataCleanVertexOutputFormat<KmerBytesWritable, VertexValueWritable, NullWritable> {
 
     @Override
diff --git a/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/format/InitialGraphCleanInputFormat.java b/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/format/InitialGraphCleanInputFormat.java
index db751a5..0d685de 100644
--- a/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/format/InitialGraphCleanInputFormat.java
+++ b/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/format/InitialGraphCleanInputFormat.java
@@ -70,6 +70,7 @@
              * set the vertex value
              */
             node.set(getRecordReader().getCurrentValue());
+            vertexValue.setKmerlength(node.getKmerlength());
             vertexValue.setNodeIdList(node.getNodeIdList());
             vertexValue.setFFList(node.getFFList());
             vertexValue.setFRList(node.getFRList());
diff --git a/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/io/AdjacencyListWritable.java b/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/io/AdjacencyListWritable.java
index b23edaf..c35ad7f 100644
--- a/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/io/AdjacencyListWritable.java
+++ b/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/io/AdjacencyListWritable.java
@@ -17,6 +17,11 @@
         forwardList = new KmerListWritable();
         reverseList = new KmerListWritable();
     }
+    
+    public AdjacencyListWritable(int kmerSize){
+        forwardList = new KmerListWritable(kmerSize);
+        reverseList = new KmerListWritable(kmerSize);
+    }
 
     public void set(AdjacencyListWritable adjacencyList){
         forwardList.set(adjacencyList.getForwardList());
@@ -28,6 +33,11 @@
         reverseList.reset();
     }
     
+    public void reset(int kmerSize){
+        forwardList.reset(kmerSize);
+        reverseList.reset(kmerSize);
+    }
+    
     public int getCountOfPosition(){
     	return forwardList.getCountOfPosition() + reverseList.getCountOfPosition();
     }
diff --git a/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/io/MessageWritable.java b/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/io/MessageWritable.java
index adb1aac..1c5f325 100644
--- a/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/io/MessageWritable.java
+++ b/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/io/MessageWritable.java
@@ -21,6 +21,7 @@
     private AdjacencyListWritable neighberNode; //incoming or outgoing
     private byte flag;
     private boolean isFlip;
+    private int kmerlength = 0;
 
     private byte checkMessage;
 
@@ -33,7 +34,18 @@
         checkMessage = (byte) 0;
     }
     
+    public MessageWritable(int kmerSize) {
+        kmerlength = kmerSize;
+        sourceVertexId = new KmerBytesWritable();
+        kmer = new KmerBytesWritable(0);
+        neighberNode = new AdjacencyListWritable(kmerSize);
+        flag = Message.NON;
+        isFlip = false;
+        checkMessage = (byte) 0;
+    }
+    
     public void set(MessageWritable msg) {
+        this.kmerlength = msg.kmerlength;
         checkMessage = 0;
         if (sourceVertexId != null) {
             checkMessage |= CheckMessage.SOURCE;
@@ -51,7 +63,8 @@
         this.flag = msg.getFlag();
     }
 
-    public void set(KmerBytesWritable sourceVertexId, KmerBytesWritable chainVertexId, AdjacencyListWritable neighberNode, byte message) {
+    public void set(int kmerlength, KmerBytesWritable sourceVertexId, KmerBytesWritable chainVertexId, AdjacencyListWritable neighberNode, byte message) {
+        this.kmerlength = kmerlength;
         checkMessage = 0;
         if (sourceVertexId != null) {
             checkMessage |= CheckMessage.SOURCE;
@@ -74,6 +87,13 @@
         neighberNode.reset();
         flag = Message.NON;
     }
+    
+    public void reset(int kmerSize) {
+        checkMessage = 0;
+        kmer.reset(1);
+        neighberNode.reset(kmerSize);
+        flag = Message.NON;
+    }
 
     public KmerBytesWritable getSourceVertexId() {
         return sourceVertexId;
@@ -130,6 +150,7 @@
 
     @Override
     public void write(DataOutput out) throws IOException {
+        out.writeInt(kmerlength);
         out.writeByte(checkMessage);
         if ((checkMessage & CheckMessage.SOURCE) != 0)
             sourceVertexId.write(out);
@@ -138,12 +159,13 @@
         if ((checkMessage & CheckMessage.NEIGHBER) != 0)
             neighberNode.write(out);
         out.writeBoolean(isFlip);
-        out.write(flag);
+        out.writeByte(flag); 
     }
 
     @Override
     public void readFields(DataInput in) throws IOException {
-        this.reset();
+        kmerlength = in.readInt();
+        this.reset(kmerlength);
         checkMessage = in.readByte();
         if ((checkMessage & CheckMessage.SOURCE) != 0)
             sourceVertexId.readFields(in);
diff --git a/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/io/VertexValueWritable.java b/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/io/VertexValueWritable.java
index f2a90d0..c6a2c9a 100644
--- a/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/io/VertexValueWritable.java
+++ b/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/io/VertexValueWritable.java
@@ -41,14 +41,20 @@
     private byte state;
     private KmerBytesWritable kmer;
     private KmerBytesWritable mergeDest;
+    private int kmerlength = 0;
 
     public VertexValueWritable() {
+        this(0);
+    }
+    
+    public VertexValueWritable(int kmerSize){
+        kmerlength = kmerSize;
         nodeIdList = new PositionListWritable();
         incomingList = new AdjacencyListWritable();
         outgoingList = new AdjacencyListWritable();
         state = State.IS_NON;
-        kmer = new KmerBytesWritable(0);
-        mergeDest = new KmerBytesWritable(0);
+        kmer = new KmerBytesWritable(kmerSize);
+        mergeDest = new KmerBytesWritable(kmerSize);
     }
 
     public VertexValueWritable(PositionListWritable nodeIdList, KmerListWritable forwardForwardList, KmerListWritable forwardReverseList,
@@ -62,6 +68,7 @@
     public void set(PositionListWritable nodeIdList, KmerListWritable forwardForwardList, KmerListWritable forwardReverseList,
             KmerListWritable reverseForwardList, KmerListWritable reverseReverseList, 
             byte state, KmerBytesWritable kmer) {
+        this.kmerlength = kmer.kmerByteSize;
         this.incomingList.setForwardList(reverseForwardList);
         this.incomingList.setReverseList(reverseReverseList);
         this.outgoingList.setForwardList(forwardForwardList);
@@ -71,6 +78,7 @@
     }
     
     public void set(VertexValueWritable value) {
+        this.kmerlength = value.kmerlength;
         set(value.getNodeIdList(), value.getFFList(),value.getFRList(),value.getRFList(),value.getRRList(),value.getState(),
                 value.getKmer());
     }
@@ -159,25 +167,47 @@
     public void setMergeDest(KmerBytesWritable mergeDest) {
         this.mergeDest = mergeDest;
     }
+    
+    
+    public int getKmerlength() {
+        return kmerlength;
+    }
 
+    public void setKmerlength(int kmerlength) {
+        this.kmerlength = kmerlength;
+    }
+
+    public void reset(int kmerSize) {
+        this.kmerlength = kmerSize;
+        this.nodeIdList.reset();
+        this.incomingList.getForwardList().reset(kmerSize);
+        this.incomingList.getReverseList().reset(kmerSize);
+        this.outgoingList.getForwardList().reset(kmerSize);
+        this.outgoingList.getReverseList().reset(kmerSize);
+        this.kmer.reset(0);
+    }
+    
     @Override
     public void readFields(DataInput in) throws IOException {
-        nodeIdList.readFields(in);
-        incomingList.readFields(in);
-        outgoingList.readFields(in);
-        state = in.readByte();
-        kmer.readFields(in);
-        mergeDest.readFields(in);
+        this.kmerlength = in.readInt();
+        this.reset(kmerlength);
+        this.nodeIdList.readFields(in);
+        this.incomingList.readFields(in);
+        this.outgoingList.readFields(in);
+        this.state = in.readByte();
+        this.kmer.readFields(in);
+        this.mergeDest.readFields(in);
     }
 
     @Override
     public void write(DataOutput out) throws IOException {
-        nodeIdList.write(out);
-        incomingList.write(out);
-        outgoingList.write(out);
-        out.writeByte(state);
-        kmer.write(out);
-        mergeDest.write(out);
+        out.writeInt(this.kmerlength);
+        this.nodeIdList.write(out);
+        this.incomingList.write(out);
+        this.outgoingList.write(out);
+        out.writeByte(this.state);
+        this.kmer.write(out);
+        this.mergeDest.write(out);
     }
 
     @Override
diff --git a/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/bridgeremove/BridgeAddVertex.java b/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/bridgeremove/BridgeAddVertex.java
index 15b77bd..fa353d0 100644
--- a/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/bridgeremove/BridgeAddVertex.java
+++ b/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/bridgeremove/BridgeAddVertex.java
@@ -10,8 +10,8 @@
 import edu.uci.ics.genomix.oldtype.PositionListWritable;
 import edu.uci.ics.genomix.oldtype.PositionWritable;
 import edu.uci.ics.genomix.pregelix.client.Client;
-import edu.uci.ics.genomix.pregelix.format.DataCleanInputFormat;
-import edu.uci.ics.genomix.pregelix.format.DataCleanOutputFormat;
+import edu.uci.ics.genomix.pregelix.format.GraphCleanInputFormat;
+import edu.uci.ics.genomix.pregelix.format.GraphCleanOutputFormat;
 import edu.uci.ics.genomix.pregelix.io.MessageWritable;
 import edu.uci.ics.genomix.pregelix.io.VertexValueWritable;
 
@@ -112,8 +112,8 @@
         /**
          * BinaryInput and BinaryOutput
          */
-        job.setVertexInputFormatClass(DataCleanInputFormat.class);
-        job.setVertexOutputFormatClass(DataCleanOutputFormat.class);
+        job.setVertexInputFormatClass(GraphCleanInputFormat.class);
+        job.setVertexOutputFormatClass(GraphCleanOutputFormat.class);
         job.setDynamicVertexValueSize(true);
         job.setOutputKeyClass(PositionWritable.class);
         job.setOutputValueClass(VertexValueWritable.class);
diff --git a/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/bridgeremove/BridgeRemoveVertex.java b/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/bridgeremove/BridgeRemoveVertex.java
index 7bef7cf..9db9418 100644
--- a/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/bridgeremove/BridgeRemoveVertex.java
+++ b/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/bridgeremove/BridgeRemoveVertex.java
@@ -6,8 +6,8 @@
 import edu.uci.ics.pregelix.api.job.PregelixJob;
 import edu.uci.ics.genomix.oldtype.PositionWritable;
 import edu.uci.ics.genomix.pregelix.client.Client;
-import edu.uci.ics.genomix.pregelix.format.DataCleanInputFormat;
-import edu.uci.ics.genomix.pregelix.format.DataCleanOutputFormat;
+import edu.uci.ics.genomix.pregelix.format.GraphCleanInputFormat;
+import edu.uci.ics.genomix.pregelix.format.GraphCleanOutputFormat;
 import edu.uci.ics.genomix.pregelix.io.MessageWritable;
 import edu.uci.ics.genomix.pregelix.io.VertexValueWritable;
 import edu.uci.ics.genomix.pregelix.operator.pathmerge.BasicPathMergeVertex;
@@ -167,8 +167,8 @@
         /**
          * BinaryInput and BinaryOutput
          */
-        job.setVertexInputFormatClass(DataCleanInputFormat.class);
-        job.setVertexOutputFormatClass(DataCleanOutputFormat.class);
+        job.setVertexInputFormatClass(GraphCleanInputFormat.class);
+        job.setVertexOutputFormatClass(GraphCleanOutputFormat.class);
         job.setDynamicVertexValueSize(true);
         job.setOutputKeyClass(PositionWritable.class);
         job.setOutputValueClass(VertexValueWritable.class);
diff --git a/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/bubblemerge/BubbleAddVertex.java b/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/bubblemerge/BubbleAddVertex.java
index 5f30d23..ebb4f74 100644
--- a/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/bubblemerge/BubbleAddVertex.java
+++ b/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/bubblemerge/BubbleAddVertex.java
@@ -10,8 +10,8 @@
 import edu.uci.ics.genomix.oldtype.PositionListWritable;
 import edu.uci.ics.genomix.oldtype.PositionWritable;
 import edu.uci.ics.genomix.pregelix.client.Client;
-import edu.uci.ics.genomix.pregelix.format.DataCleanInputFormat;
-import edu.uci.ics.genomix.pregelix.format.DataCleanOutputFormat;
+import edu.uci.ics.genomix.pregelix.format.GraphCleanInputFormat;
+import edu.uci.ics.genomix.pregelix.format.GraphCleanOutputFormat;
 import edu.uci.ics.genomix.pregelix.io.MessageWritable;
 import edu.uci.ics.genomix.pregelix.io.VertexValueWritable;
 
@@ -108,8 +108,8 @@
         /**
          * BinaryInput and BinaryOutput
          */
-        job.setVertexInputFormatClass(DataCleanInputFormat.class);
-        job.setVertexOutputFormatClass(DataCleanOutputFormat.class);
+        job.setVertexInputFormatClass(GraphCleanInputFormat.class);
+        job.setVertexOutputFormatClass(GraphCleanOutputFormat.class);
         job.setDynamicVertexValueSize(true);
         job.setOutputKeyClass(PositionWritable.class);
         job.setOutputValueClass(VertexValueWritable.class);
diff --git a/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/bubblemerge/BubbleMergeVertex.java b/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/bubblemerge/BubbleMergeVertex.java
index 6ca08eb..40e3191 100644
--- a/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/bubblemerge/BubbleMergeVertex.java
+++ b/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/bubblemerge/BubbleMergeVertex.java
@@ -12,8 +12,8 @@
 import edu.uci.ics.pregelix.api.job.PregelixJob;
 import edu.uci.ics.genomix.oldtype.PositionWritable;
 import edu.uci.ics.genomix.pregelix.client.Client;
-import edu.uci.ics.genomix.pregelix.format.DataCleanInputFormat;
-import edu.uci.ics.genomix.pregelix.format.DataCleanOutputFormat;
+import edu.uci.ics.genomix.pregelix.format.GraphCleanInputFormat;
+import edu.uci.ics.genomix.pregelix.format.GraphCleanOutputFormat;
 import edu.uci.ics.genomix.pregelix.io.MergeBubbleMessageWritable;
 import edu.uci.ics.genomix.pregelix.io.VertexValueWritable;
 import edu.uci.ics.genomix.pregelix.type.AdjMessage;
@@ -356,8 +356,8 @@
         /**
          * BinaryInput and BinaryOutput
          */
-        job.setVertexInputFormatClass(DataCleanInputFormat.class);
-        job.setVertexOutputFormatClass(DataCleanOutputFormat.class);
+        job.setVertexInputFormatClass(GraphCleanInputFormat.class);
+        job.setVertexOutputFormatClass(GraphCleanOutputFormat.class);
         job.setDynamicVertexValueSize(true);
         job.setOutputKeyClass(PositionWritable.class);
         job.setOutputValueClass(VertexValueWritable.class);
diff --git a/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/pathmerge/BasicPathMergeVertex.java b/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/pathmerge/BasicPathMergeVertex.java
index 6b5562a..c44fb53 100644
--- a/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/pathmerge/BasicPathMergeVertex.java
+++ b/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/pathmerge/BasicPathMergeVertex.java
@@ -25,8 +25,8 @@
     public static int kmerSize = -1;
     protected int maxIteration = -1;
     
-    protected MessageWritable incomingMsg = new MessageWritable();
-    protected MessageWritable outgoingMsg = new MessageWritable();
+    protected MessageWritable incomingMsg = null; // = new MessageWritable();
+    protected MessageWritable outgoingMsg = null; // = new MessageWritable();
     protected KmerBytesWritable destVertexId = new KmerBytesWritable();
     protected Iterator<KmerBytesWritable> posIterator;
     private KmerBytesWritable kmer = new KmerBytesWritable();
@@ -315,10 +315,10 @@
      * @throws IOException 
      */
     public void broadcastUpdateMsg(){
-        if((getVertexValue().getState() & MessageFlag.IS_HEAD) > 0)
+        if((getVertexValue().getState() & State.IS_HEAD) > 0)
             outFlag |= MessageFlag.IS_HEAD;
-        switch(getVertexValue().getState() & MessageFlag.SHOULD_MERGE_MASK){
-            case MessageFlag.SHOULD_MERGEWITHPREV:
+        switch(getVertexValue().getState() & State.SHOULD_MERGE_MASK){
+            case State.SHOULD_MERGEWITHPREV:
                 setSuccessorAdjMsg();
                 if(ifFlipWithPredecessor())
                     outgoingMsg.setFlip(true);
@@ -328,7 +328,7 @@
                 if(getNextDestVertexId(getVertexValue()) != null)
                     sendMsg(getNextDestVertexId(getVertexValue()), outgoingMsg);
                 break;
-            case MessageFlag.SHOULD_MERGEWITHNEXT:
+            case State.SHOULD_MERGEWITHNEXT:
                 setPredecessorAdjMsg();
                 if(ifFilpWithSuccessor())
                     outgoingMsg.setFlip(true);
@@ -424,20 +424,13 @@
         getVertexValue().setState(state);
     }
     
-//    public byte isHeadShouldMergeWithPrev(){
-//    	return (byte) (getVertexValue().getState() & State.HEAD_SHOULD_MERGEWITHPREV);
-//    }
     /**
      * This vertex tries to merge with next vertex and send update msg to neighber
      * @throws IOException 
      */
     public void sendUpdateMsgToPredecessor(){
-    	setStateAsMergeWithNext();
     	if(hasNextDest(getVertexValue())){
-//		    if(getVertexValue().getFFList().getLength() > 0)
-//		        getVertexValue().setMergeDest(getVertexValue().getFFList().getPosition(0));
-//		    else
-//		        getVertexValue().setMergeDest(getVertexValue().getFRList().getPosition(0));
+    	    setStateAsMergeWithNext();
 		    broadcastUpdateMsg();
     	}
     }
@@ -448,20 +441,13 @@
         getVertexValue().setState(state);
     }
     
-//    public byte isHeadShouldMergeWithNext(){
-//    	return (byte) (getVertexValue().getState() & State.HEAD_SHOULD_MERGEWITHNEXT);
-//    }
     /**
      * This vertex tries to merge with next vertex and send update msg to neighber
      * @throws IOException 
      */
     public void sendUpdateMsgToSuccessor(){
-    	setStateAsMergeWithPrev();
-    	if(hasNextDest(getVertexValue())){
-//		    if(getVertexValue().getRFList().getLength() > 0)
-//		        getVertexValue().setMergeDest(getVertexValue().getRFList().getPosition(0));
-//		    else
-//		        getVertexValue().setMergeDest(getVertexValue().getRRList().getPosition(0));
+    	if(hasPrevDest(getVertexValue())){
+    	    setStateAsMergeWithPrev();
 		    broadcastUpdateMsg();
     	}
     }
diff --git a/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/pathmerge/P4ForPathMergeVertex.java b/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/pathmerge/P4ForPathMergeVertex.java
index 01fd71f..6768db6 100644
--- a/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/pathmerge/P4ForPathMergeVertex.java
+++ b/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/pathmerge/P4ForPathMergeVertex.java
@@ -7,11 +7,14 @@
 import edu.uci.ics.pregelix.api.job.PregelixJob;
 import edu.uci.ics.genomix.oldtype.PositionWritable;
 import edu.uci.ics.genomix.pregelix.client.Client;
+import edu.uci.ics.genomix.pregelix.format.GraphCleanOutputFormat;
+import edu.uci.ics.genomix.pregelix.format.InitialGraphCleanInputFormat;
 import edu.uci.ics.genomix.pregelix.io.MessageWritable;
 import edu.uci.ics.genomix.pregelix.io.VertexValueWritable;
 import edu.uci.ics.genomix.pregelix.io.VertexValueWritable.State;
 import edu.uci.ics.genomix.pregelix.type.MessageFlag;
 import edu.uci.ics.genomix.pregelix.util.VertexUtil;
+import edu.uci.ics.genomix.type.KmerBytesWritable;
 
 /*
  * vertexId: BytesWritable
@@ -53,9 +56,9 @@
     private float probBeingRandomHead = -1;
     private Random randGenerator;
     
-    private PositionWritable curID = new PositionWritable();
-    private PositionWritable nextID = new PositionWritable();
-    private PositionWritable prevID = new PositionWritable();
+    private KmerBytesWritable curKmer = new KmerBytesWritable();
+    private KmerBytesWritable nextKmer = new KmerBytesWritable();
+    private KmerBytesWritable prevKmer = new KmerBytesWritable();
     private boolean hasNext;
     private boolean hasPrev;
     private boolean curHead;
@@ -71,6 +74,10 @@
             kmerSize = getContext().getConfiguration().getInt(KMER_SIZE, 5);
         if (maxIteration < 0)
             maxIteration = getContext().getConfiguration().getInt(ITERATIONS, 1000000);
+        if(incomingMsg == null)
+            incomingMsg = new MessageWritable(kmerSize);
+        if(outgoingMsg == null)
+            outgoingMsg = new MessageWritable(kmerSize);
         //if (randSeed < 0)
         //    randSeed = getContext().getConfiguration().getLong("randomSeed", 0);
         randSeed = getSuperstep();
@@ -89,43 +96,45 @@
         outgoingMsg.reset();
     }
 
-    protected boolean isNodeRandomHead(PositionWritable nodeID) {
+    protected boolean isNodeRandomHead(KmerBytesWritable nodeKmer) {
         // "deterministically random", based on node id
         //randGenerator.setSeed(randSeed);
         //randSeed = randGenerator.nextInt();
-        randGenerator.setSeed((randSeed ^ nodeID.hashCode()) * 100000 * getSuperstep());//randSeed + nodeID.hashCode()
+        randGenerator.setSeed((randSeed ^ nodeKmer.hashCode()) * 100000 * getSuperstep());//randSeed + nodeID.hashCode()
+        for(int i = 0; i < 500; i++)
+            randGenerator.nextFloat();
         return randGenerator.nextFloat() < probBeingRandomHead;
     }
     
     /**
-     * set nextID to the element that's next (in the node's FF or FR list), returning true when there is a next neighbor
+     * set nextKmer to the element that's next (in the node's FF or FR list), returning true when there is a next neighbor
      */
     protected boolean setNextInfo(VertexValueWritable value) {
         if (value.getFFList().getCountOfPosition() > 0) {
-            nextID.set(value.getFFList().getPosition(0));
-            nextHead = isNodeRandomHead(nextID);
+            nextKmer.set(value.getFFList().getPosition(0));
+            nextHead = isNodeRandomHead(nextKmer);
             return true;
         }
         if (value.getFRList().getCountOfPosition() > 0) {
-            nextID.set(value.getFRList().getPosition(0));
-            nextHead = isNodeRandomHead(nextID);
+            nextKmer.set(value.getFRList().getPosition(0));
+            nextHead = isNodeRandomHead(nextKmer);
             return true;
         }
         return false;
     }
 
     /**
-     * set prevID to the element that's previous (in the node's RR or RF list), returning true when there is a previous neighbor
+     * set prevKmer to the element that's previous (in the node's RR or RF list), returning true when there is a previous neighbor
      */
     protected boolean setPrevInfo(VertexValueWritable value) {
         if (value.getRRList().getCountOfPosition() > 0) {
-            prevID.set(value.getRRList().getPosition(0));
-            prevHead = isNodeRandomHead(prevID);
+            prevKmer.set(value.getRRList().getPosition(0));
+            prevHead = isNodeRandomHead(prevKmer);
             return true;
         }
         if (value.getRFList().getCountOfPosition() > 0) {
-            prevID.set(value.getRFList().getPosition(0));
-            prevHead = isNodeRandomHead(prevID);
+            prevKmer.set(value.getRFList().getPosition(0));
+            prevHead = isNodeRandomHead(prevKmer);
             return true;
         }
         return false;
@@ -147,9 +156,9 @@
             setStateAsNoMerge();
             
             // only PATH vertices are present. Find the ID's for my neighbors
-            curID.set(getVertexId());
+            curKmer.set(getVertexId());
             
-            curHead = isNodeRandomHead(curID);
+            curHead = isNodeRandomHead(curKmer);
             
             
             // the headFlag and tailFlag's indicate if the node is at the beginning or end of a simple path. 
@@ -160,7 +169,7 @@
                 if (curHead) {
                     if (hasNext && !nextHead) {
                         // compress this head to the forward tail
-                		sendUpdateMsgToPredecessor(); //TODO up -> update  From -> to
+                		sendUpdateMsgToPredecessor(); 
                     } else if (hasPrev && !prevHead) {
                         // compress this head to the reverse tail
                         sendUpdateMsgToSuccessor();
@@ -169,20 +178,20 @@
             }else {
                     // I'm a tail
                     if (hasNext && hasPrev) {
-                         if ((!nextHead && !prevHead) && (curID.compareTo(nextID) < 0 && curID.compareTo(prevID) < 0)) {
+                         if ((!nextHead && !prevHead) && (curKmer.compareTo(nextKmer) < 0 && curKmer.compareTo(prevKmer) < 0)) {
                             // tails on both sides, and I'm the "local minimum"
                             // compress me towards the tail in forward dir
                             sendUpdateMsgToPredecessor();
                         }
                     } else if (!hasPrev) {
                         // no previous node
-                        if (!nextHead && curID.compareTo(nextID) < 0) {
+                        if (!nextHead && curKmer.compareTo(nextKmer) < 0) {
                             // merge towards tail in forward dir
                             sendUpdateMsgToPredecessor();
                         }
                     } else if (!hasNext) {
                         // no next node
-                        if (!prevHead && curID.compareTo(prevID) < 0) {
+                        if (!prevHead && curKmer.compareTo(prevKmer) < 0) {
                             // merge towards tail in reverse dir
                             sendUpdateMsgToSuccessor();
                         }
@@ -220,8 +229,8 @@
         /**
          * BinaryInput and BinaryOutput
          */
-        job.setVertexInputFormatClass(NaiveAlgorithmForPathMergeInputFormat.class);
-        job.setVertexOutputFormatClass(NaiveAlgorithmForPathMergeOutputFormat.class);
+        job.setVertexInputFormatClass(InitialGraphCleanInputFormat.class);
+        job.setVertexOutputFormatClass(GraphCleanOutputFormat.class);
         job.setDynamicVertexValueSize(true);
         job.setOutputKeyClass(PositionWritable.class);
         job.setOutputValueClass(VertexValueWritable.class);
diff --git a/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/tipremove/TipAddVertex.java b/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/tipremove/TipAddVertex.java
index b8d4098..519ffb9 100644
--- a/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/tipremove/TipAddVertex.java
+++ b/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/tipremove/TipAddVertex.java
@@ -10,8 +10,8 @@
 import edu.uci.ics.genomix.oldtype.PositionListWritable;
 import edu.uci.ics.genomix.oldtype.PositionWritable;
 import edu.uci.ics.genomix.pregelix.client.Client;
-import edu.uci.ics.genomix.pregelix.format.DataCleanInputFormat;
-import edu.uci.ics.genomix.pregelix.format.DataCleanOutputFormat;
+import edu.uci.ics.genomix.pregelix.format.GraphCleanInputFormat;
+import edu.uci.ics.genomix.pregelix.format.GraphCleanOutputFormat;
 import edu.uci.ics.genomix.pregelix.io.MessageWritable;
 import edu.uci.ics.genomix.pregelix.io.VertexValueWritable;
 
@@ -103,8 +103,8 @@
         /**
          * BinaryInput and BinaryOutput
          */
-        job.setVertexInputFormatClass(DataCleanInputFormat.class);
-        job.setVertexOutputFormatClass(DataCleanOutputFormat.class);
+        job.setVertexInputFormatClass(GraphCleanInputFormat.class);
+        job.setVertexOutputFormatClass(GraphCleanOutputFormat.class);
         job.setDynamicVertexValueSize(true);
         job.setOutputKeyClass(PositionWritable.class);
         job.setOutputValueClass(VertexValueWritable.class);
diff --git a/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/tipremove/TipRemoveVertex.java b/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/tipremove/TipRemoveVertex.java
index cecaa48..7141ae7 100644
--- a/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/tipremove/TipRemoveVertex.java
+++ b/genomix/genomix-pregelix/src/main/java/edu/uci/ics/genomix/pregelix/operator/tipremove/TipRemoveVertex.java
@@ -5,8 +5,8 @@
 import edu.uci.ics.pregelix.api.job.PregelixJob;
 import edu.uci.ics.genomix.oldtype.PositionWritable;
 import edu.uci.ics.genomix.pregelix.client.Client;
-import edu.uci.ics.genomix.pregelix.format.DataCleanInputFormat;
-import edu.uci.ics.genomix.pregelix.format.DataCleanOutputFormat;
+import edu.uci.ics.genomix.pregelix.format.GraphCleanInputFormat;
+import edu.uci.ics.genomix.pregelix.format.GraphCleanOutputFormat;
 import edu.uci.ics.genomix.pregelix.io.MessageWritable;
 import edu.uci.ics.genomix.pregelix.io.VertexValueWritable;
 import edu.uci.ics.genomix.pregelix.operator.pathmerge.BasicPathMergeVertex;
@@ -105,8 +105,8 @@
         /**
          * BinaryInput and BinaryOutput
          */
-        job.setVertexInputFormatClass(DataCleanInputFormat.class);
-        job.setVertexOutputFormatClass(DataCleanOutputFormat.class);
+        job.setVertexInputFormatClass(GraphCleanInputFormat.class);
+        job.setVertexOutputFormatClass(GraphCleanOutputFormat.class);
         job.setDynamicVertexValueSize(true);
         job.setOutputKeyClass(PositionWritable.class);
         job.setOutputValueClass(VertexValueWritable.class);
diff --git a/genomix/genomix-pregelix/src/test/java/edu/uci/ics/genomix/pregelix/JobGen/JobGenerator.java b/genomix/genomix-pregelix/src/test/java/edu/uci/ics/genomix/pregelix/JobGen/JobGenerator.java
index 488e23d..d2d3969 100644
--- a/genomix/genomix-pregelix/src/test/java/edu/uci/ics/genomix/pregelix/JobGen/JobGenerator.java
+++ b/genomix/genomix-pregelix/src/test/java/edu/uci/ics/genomix/pregelix/JobGen/JobGenerator.java
@@ -5,12 +5,9 @@
 import java.io.IOException;
 
 import edu.uci.ics.genomix.oldtype.PositionWritable;
-import edu.uci.ics.genomix.pregelix.format.DataCleanInputFormat;
-import edu.uci.ics.genomix.pregelix.format.DataCleanOutputFormat;
-import edu.uci.ics.genomix.pregelix.format.LogAlgorithmForPathMergeInputFormat;
-import edu.uci.ics.genomix.pregelix.format.LogAlgorithmForPathMergeOutputFormat;
-import edu.uci.ics.genomix.pregelix.format.NaiveAlgorithmForPathMergeInputFormat;
-import edu.uci.ics.genomix.pregelix.format.NaiveAlgorithmForPathMergeOutputFormat;
+import edu.uci.ics.genomix.pregelix.format.GraphCleanInputFormat;
+import edu.uci.ics.genomix.pregelix.format.GraphCleanOutputFormat;
+import edu.uci.ics.genomix.pregelix.format.InitialGraphCleanInputFormat;
 import edu.uci.ics.genomix.pregelix.io.VertexValueWritable;
 import edu.uci.ics.genomix.pregelix.operator.bridgeremove.BridgeAddVertex;
 import edu.uci.ics.genomix.pregelix.operator.bridgeremove.BridgeRemoveVertex;
@@ -28,67 +25,67 @@
 
     public static String outputBase = "src/test/resources/jobs/";
 
-    private static void generateNaiveAlgorithmForMergeGraphJob(String jobName, String outputPath) throws IOException {
-        PregelixJob job = new PregelixJob(jobName);
-        job.setVertexClass(NaiveAlgorithmForPathMergeVertex.class);
-        job.setVertexInputFormatClass(NaiveAlgorithmForPathMergeInputFormat.class); //DataCleanInputFormat
-        job.setVertexOutputFormatClass(DataCleanOutputFormat.class);
-        job.setDynamicVertexValueSize(true);
-        job.setOutputKeyClass(PositionWritable.class);
-        job.setOutputValueClass(VertexValueWritable.class);
-        job.getConfiguration().setInt(NaiveAlgorithmForPathMergeVertex.KMER_SIZE, 3);
-        job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
-    }
+//    private static void generateNaiveAlgorithmForMergeGraphJob(String jobName, String outputPath) throws IOException {
+//        PregelixJob job = new PregelixJob(jobName);
+//        job.setVertexClass(NaiveAlgorithmForPathMergeVertex.class);
+//        job.setVertexInputFormatClass(NaiveAlgorithmForPathMergeInputFormat.class); //GraphCleanInputFormat
+//        job.setVertexOutputFormatClass(GraphCleanOutputFormat.class);
+//        job.setDynamicVertexValueSize(true);
+//        job.setOutputKeyClass(PositionWritable.class);
+//        job.setOutputValueClass(VertexValueWritable.class);
+//        job.getConfiguration().setInt(NaiveAlgorithmForPathMergeVertex.KMER_SIZE, 3);
+//        job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
+//    }
+//
+//    private static void genNaiveAlgorithmForMergeGraph() throws IOException {
+//        generateNaiveAlgorithmForMergeGraphJob("NaiveAlgorithmForMergeGraph", outputBase
+//                + "NaiveAlgorithmForMergeGraph.xml");
+//    }
 
-    private static void genNaiveAlgorithmForMergeGraph() throws IOException {
-        generateNaiveAlgorithmForMergeGraphJob("NaiveAlgorithmForMergeGraph", outputBase
-                + "NaiveAlgorithmForMergeGraph.xml");
-    }
-
-    private static void generateLogAlgorithmForMergeGraphJob(String jobName, String outputPath) throws IOException {
-        PregelixJob job = new PregelixJob(jobName);
-        job.setVertexClass(LogAlgorithmForPathMergeVertex.class);
-        job.setVertexInputFormatClass(LogAlgorithmForPathMergeInputFormat.class);
-        job.setVertexOutputFormatClass(DataCleanOutputFormat.class); //LogAlgorithmForPathMergeOutputFormat
-        job.setDynamicVertexValueSize(true);
-        job.setOutputKeyClass(PositionWritable.class);
-        job.setOutputValueClass(VertexValueWritable.class);
-        job.getConfiguration().setInt(LogAlgorithmForPathMergeVertex.KMER_SIZE, 3);
-        job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
-    }
-
-    private static void genLogAlgorithmForMergeGraph() throws IOException {
-        generateLogAlgorithmForMergeGraphJob("LogAlgorithmForMergeGraph", outputBase + "LogAlgorithmForMergeGraph.xml");
-    }
-    
-    private static void generateP3ForMergeGraphJob(String jobName, String outputPath) throws IOException {
-        PregelixJob job = new PregelixJob(jobName);
-        job.setVertexClass(P3ForPathMergeVertex.class);
-        job.setVertexInputFormatClass(NaiveAlgorithmForPathMergeInputFormat.class);
-        job.setVertexOutputFormatClass(DataCleanOutputFormat.class);
-        job.setDynamicVertexValueSize(true);
-        job.setOutputKeyClass(PositionWritable.class);
-        job.setOutputValueClass(VertexValueWritable.class);
-        job.getConfiguration().setInt(P3ForPathMergeVertex.KMER_SIZE, 3);
-        job.getConfiguration().setFloat(P3ForPathMergeVertex.PSEUDORATE, 0.3f);
-        job.getConfiguration().setInt(P3ForPathMergeVertex.MAXROUND, 2);
-        job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
-    }
-
-    private static void genP3ForMergeGraph() throws IOException {
-        generateP3ForMergeGraphJob("P3ForMergeGraph", outputBase
-                + "P3ForMergeGraph.xml");
-    }
+//    private static void generateLogAlgorithmForMergeGraphJob(String jobName, String outputPath) throws IOException {
+//        PregelixJob job = new PregelixJob(jobName);
+//        job.setVertexClass(LogAlgorithmForPathMergeVertex.class);
+//        job.setVertexInputFormatClass(LogAlgorithmForPathMergeInputFormat.class);
+//        job.setVertexOutputFormatClass(GraphCleanOutputFormat.class); //LogAlgorithmForPathMergeOutputFormat
+//        job.setDynamicVertexValueSize(true);
+//        job.setOutputKeyClass(PositionWritable.class);
+//        job.setOutputValueClass(VertexValueWritable.class);
+//        job.getConfiguration().setInt(LogAlgorithmForPathMergeVertex.KMER_SIZE, 3);
+//        job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
+//    }
+//
+//    private static void genLogAlgorithmForMergeGraph() throws IOException {
+//        generateLogAlgorithmForMergeGraphJob("LogAlgorithmForMergeGraph", outputBase + "LogAlgorithmForMergeGraph.xml");
+//    }
+//    
+//    private static void generateP3ForMergeGraphJob(String jobName, String outputPath) throws IOException {
+//        PregelixJob job = new PregelixJob(jobName);
+//        job.setVertexClass(P3ForPathMergeVertex.class);
+//        job.setVertexInputFormatClass(NaiveAlgorithmForPathMergeInputFormat.class);
+//        job.setVertexOutputFormatClass(GraphCleanOutputFormat.class);
+//        job.setDynamicVertexValueSize(true);
+//        job.setOutputKeyClass(PositionWritable.class);
+//        job.setOutputValueClass(VertexValueWritable.class);
+//        job.getConfiguration().setInt(P3ForPathMergeVertex.KMER_SIZE, 3);
+//        job.getConfiguration().setFloat(P3ForPathMergeVertex.PSEUDORATE, 0.3f);
+//        job.getConfiguration().setInt(P3ForPathMergeVertex.MAXROUND, 2);
+//        job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
+//    }
+//
+//    private static void genP3ForMergeGraph() throws IOException {
+//        generateP3ForMergeGraphJob("P3ForMergeGraph", outputBase
+//                + "P3ForMergeGraph.xml");
+//    }
     
     private static void generateP4ForMergeGraphJob(String jobName, String outputPath) throws IOException {
         PregelixJob job = new PregelixJob(jobName);
         job.setVertexClass(P4ForPathMergeVertex.class);
-        job.setVertexInputFormatClass(DataCleanInputFormat.class); //NaiveAlgorithmForPathMergeInputFormat //
-        job.setVertexOutputFormatClass(DataCleanOutputFormat.class);
+        job.setVertexInputFormatClass(InitialGraphCleanInputFormat.class);
+        job.setVertexOutputFormatClass(GraphCleanOutputFormat.class);
         job.setDynamicVertexValueSize(true);
         job.setOutputKeyClass(PositionWritable.class);
         job.setOutputValueClass(VertexValueWritable.class);
-        job.getConfiguration().setInt(P4ForPathMergeVertex.KMER_SIZE, 5);
+        job.getConfiguration().setInt(P4ForPathMergeVertex.KMER_SIZE, 3);
         job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
     }
 
@@ -97,118 +94,118 @@
                 + "P4ForMergeGraph.xml");
     }
     
-    private static void generateTipAddGraphJob(String jobName, String outputPath) throws IOException {
-        PregelixJob job = new PregelixJob(jobName);
-        job.setVertexClass(TipAddVertex.class);
-        job.setVertexInputFormatClass(DataCleanOutputFormat.class);
-        job.setVertexOutputFormatClass(DataCleanOutputFormat.class);
-        job.setDynamicVertexValueSize(true);
-        job.setOutputKeyClass(PositionWritable.class);
-        job.setOutputValueClass(VertexValueWritable.class);
-        job.getConfiguration().setInt(TipAddVertex.KMER_SIZE, 3);
-        job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
-    }
-
-    private static void genTipAddGraph() throws IOException {
-        generateTipAddGraphJob("TipAddGraph", outputBase
-                + "TipAddGraph.xml");
-    }
-    
-    private static void generateTipRemoveGraphJob(String jobName, String outputPath) throws IOException {
-        PregelixJob job = new PregelixJob(jobName);
-        job.setVertexClass(TipRemoveVertex.class);
-        job.setVertexInputFormatClass(NaiveAlgorithmForPathMergeInputFormat.class);
-        job.setVertexOutputFormatClass(DataCleanOutputFormat.class);
-        job.setDynamicVertexValueSize(true);
-        job.setOutputKeyClass(PositionWritable.class);
-        job.setOutputValueClass(VertexValueWritable.class);
-        job.getConfiguration().setInt(TipRemoveVertex.KMER_SIZE, 5);
-        job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
-    }
-
-    private static void genTipRemoveGraph() throws IOException {
-        generateTipRemoveGraphJob("TipRemoveGraph", outputBase
-                + "TipRemoveGraph.xml");
-    }
-    
-    private static void generateBridgeAddGraphJob(String jobName, String outputPath) throws IOException {
-        PregelixJob job = new PregelixJob(jobName);
-        job.setVertexClass(BridgeAddVertex.class);
-        job.setVertexInputFormatClass(NaiveAlgorithmForPathMergeInputFormat.class);
-        job.setVertexOutputFormatClass(DataCleanOutputFormat.class);
-        job.setDynamicVertexValueSize(true);
-        job.setOutputKeyClass(PositionWritable.class);
-        job.setOutputValueClass(VertexValueWritable.class);
-        job.getConfiguration().setInt(BridgeAddVertex.KMER_SIZE, 3);
-        job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
-    }
-
-    private static void genBridgeAddGraph() throws IOException {
-        generateBridgeAddGraphJob("BridgeAddGraph", outputBase
-                + "BridgeAddGraph.xml");
-    }
-
-    private static void generateBridgeRemoveGraphJob(String jobName, String outputPath) throws IOException {
-        PregelixJob job = new PregelixJob(jobName);
-        job.setVertexClass(BridgeRemoveVertex.class);
-        job.setVertexInputFormatClass(DataCleanInputFormat.class);
-        job.setVertexOutputFormatClass(DataCleanOutputFormat.class);
-        job.setDynamicVertexValueSize(true);
-        job.setOutputKeyClass(PositionWritable.class);
-        job.setOutputValueClass(VertexValueWritable.class);
-        job.getConfiguration().setInt(TipRemoveVertex.KMER_SIZE, 5);
-        job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
-    }
-
-    private static void genBridgeRemoveGraph() throws IOException {
-        generateBridgeRemoveGraphJob("BridgeRemoveGraph", outputBase
-                + "BridgeRemoveGraph.xml");
-    }
-    
-    private static void generateBubbleAddGraphJob(String jobName, String outputPath) throws IOException {
-        PregelixJob job = new PregelixJob(jobName);
-        job.setVertexClass(BubbleAddVertex.class);
-        job.setVertexInputFormatClass(NaiveAlgorithmForPathMergeInputFormat.class);
-        job.setVertexOutputFormatClass(DataCleanOutputFormat.class);
-        job.setDynamicVertexValueSize(true);
-        job.setOutputKeyClass(PositionWritable.class);
-        job.setOutputValueClass(VertexValueWritable.class);
-        job.getConfiguration().setInt(BubbleAddVertex.KMER_SIZE, 3);
-        job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
-    }
-
-    private static void genBubbleAddGraph() throws IOException {
-        generateBubbleAddGraphJob("BubbleAddGraph", outputBase
-                + "BubbleAddGraph.xml");
-    }
-    
-    private static void generateBubbleMergeGraphJob(String jobName, String outputPath) throws IOException {
-        PregelixJob job = new PregelixJob(jobName);
-        job.setVertexClass(BubbleMergeVertex.class);
-        job.setVertexInputFormatClass(NaiveAlgorithmForPathMergeInputFormat.class);
-        job.setVertexOutputFormatClass(DataCleanOutputFormat.class);
-        job.setDynamicVertexValueSize(true);
-        job.setOutputKeyClass(PositionWritable.class);
-        job.setOutputValueClass(VertexValueWritable.class);
-        job.getConfiguration().setInt(BubbleMergeVertex.KMER_SIZE, 5);
-        job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
-    }
-
-    private static void genBubbleMergeGraph() throws IOException {
-        generateBubbleMergeGraphJob("BubbleMergeGraph", outputBase
-                + "BubbleMergeGraph.xml");
-    }
+//    private static void generateTipAddGraphJob(String jobName, String outputPath) throws IOException {
+//        PregelixJob job = new PregelixJob(jobName);
+//        job.setVertexClass(TipAddVertex.class);
+//        job.setVertexInputFormatClass(GraphCleanOutputFormat.class);
+//        job.setVertexOutputFormatClass(GraphCleanOutputFormat.class);
+//        job.setDynamicVertexValueSize(true);
+//        job.setOutputKeyClass(PositionWritable.class);
+//        job.setOutputValueClass(VertexValueWritable.class);
+//        job.getConfiguration().setInt(TipAddVertex.KMER_SIZE, 3);
+//        job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
+//    }
+//
+//    private static void genTipAddGraph() throws IOException {
+//        generateTipAddGraphJob("TipAddGraph", outputBase
+//                + "TipAddGraph.xml");
+//    }
+//    
+//    private static void generateTipRemoveGraphJob(String jobName, String outputPath) throws IOException {
+//        PregelixJob job = new PregelixJob(jobName);
+//        job.setVertexClass(TipRemoveVertex.class);
+//        job.setVertexInputFormatClass(NaiveAlgorithmForPathMergeInputFormat.class);
+//        job.setVertexOutputFormatClass(GraphCleanOutputFormat.class);
+//        job.setDynamicVertexValueSize(true);
+//        job.setOutputKeyClass(PositionWritable.class);
+//        job.setOutputValueClass(VertexValueWritable.class);
+//        job.getConfiguration().setInt(TipRemoveVertex.KMER_SIZE, 5);
+//        job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
+//    }
+//
+//    private static void genTipRemoveGraph() throws IOException {
+//        generateTipRemoveGraphJob("TipRemoveGraph", outputBase
+//                + "TipRemoveGraph.xml");
+//    }
+//    
+//    private static void generateBridgeAddGraphJob(String jobName, String outputPath) throws IOException {
+//        PregelixJob job = new PregelixJob(jobName);
+//        job.setVertexClass(BridgeAddVertex.class);
+//        job.setVertexInputFormatClass(NaiveAlgorithmForPathMergeInputFormat.class);
+//        job.setVertexOutputFormatClass(GraphCleanOutputFormat.class);
+//        job.setDynamicVertexValueSize(true);
+//        job.setOutputKeyClass(PositionWritable.class);
+//        job.setOutputValueClass(VertexValueWritable.class);
+//        job.getConfiguration().setInt(BridgeAddVertex.KMER_SIZE, 3);
+//        job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
+//    }
+//
+//    private static void genBridgeAddGraph() throws IOException {
+//        generateBridgeAddGraphJob("BridgeAddGraph", outputBase
+//                + "BridgeAddGraph.xml");
+//    }
+//
+//    private static void generateBridgeRemoveGraphJob(String jobName, String outputPath) throws IOException {
+//        PregelixJob job = new PregelixJob(jobName);
+//        job.setVertexClass(BridgeRemoveVertex.class);
+//        job.setVertexInputFormatClass(GraphCleanInputFormat.class);
+//        job.setVertexOutputFormatClass(GraphCleanOutputFormat.class);
+//        job.setDynamicVertexValueSize(true);
+//        job.setOutputKeyClass(PositionWritable.class);
+//        job.setOutputValueClass(VertexValueWritable.class);
+//        job.getConfiguration().setInt(TipRemoveVertex.KMER_SIZE, 5);
+//        job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
+//    }
+//
+//    private static void genBridgeRemoveGraph() throws IOException {
+//        generateBridgeRemoveGraphJob("BridgeRemoveGraph", outputBase
+//                + "BridgeRemoveGraph.xml");
+//    }
+//    
+//    private static void generateBubbleAddGraphJob(String jobName, String outputPath) throws IOException {
+//        PregelixJob job = new PregelixJob(jobName);
+//        job.setVertexClass(BubbleAddVertex.class);
+//        job.setVertexInputFormatClass(NaiveAlgorithmForPathMergeInputFormat.class);
+//        job.setVertexOutputFormatClass(GraphCleanOutputFormat.class);
+//        job.setDynamicVertexValueSize(true);
+//        job.setOutputKeyClass(PositionWritable.class);
+//        job.setOutputValueClass(VertexValueWritable.class);
+//        job.getConfiguration().setInt(BubbleAddVertex.KMER_SIZE, 3);
+//        job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
+//    }
+//
+//    private static void genBubbleAddGraph() throws IOException {
+//        generateBubbleAddGraphJob("BubbleAddGraph", outputBase
+//                + "BubbleAddGraph.xml");
+//    }
+//    
+//    private static void generateBubbleMergeGraphJob(String jobName, String outputPath) throws IOException {
+//        PregelixJob job = new PregelixJob(jobName);
+//        job.setVertexClass(BubbleMergeVertex.class);
+//        job.setVertexInputFormatClass(NaiveAlgorithmForPathMergeInputFormat.class);
+//        job.setVertexOutputFormatClass(GraphCleanOutputFormat.class);
+//        job.setDynamicVertexValueSize(true);
+//        job.setOutputKeyClass(PositionWritable.class);
+//        job.setOutputValueClass(VertexValueWritable.class);
+//        job.getConfiguration().setInt(BubbleMergeVertex.KMER_SIZE, 5);
+//        job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
+//    }
+//
+//    private static void genBubbleMergeGraph() throws IOException {
+//        generateBubbleMergeGraphJob("BubbleMergeGraph", outputBase
+//                + "BubbleMergeGraph.xml");
+//    }
     
     public static void main(String[] args) throws IOException {
         //genNaiveAlgorithmForMergeGraph();
         //genLogAlgorithmForMergeGraph();
         //genP3ForMergeGraph();
         //genTipAddGraph();
-        genTipRemoveGraph();
-        genBridgeAddGraph();
-        genBridgeRemoveGraph();
-        genBubbleAddGraph();
-        genBubbleMergeGraph();
+//        genTipRemoveGraph();
+//        genBridgeAddGraph();
+//        genBridgeRemoveGraph();
+//        genBubbleAddGraph();
+//        genBubbleMergeGraph();
         genP4ForMergeGraph();
     }
 
diff --git a/genomix/genomix-pregelix/src/test/java/edu/uci/ics/genomix/pregelix/JobRun/PathMergeSmallTestSuite.java b/genomix/genomix-pregelix/src/test/java/edu/uci/ics/genomix/pregelix/JobRun/PathMergeSmallTestSuite.java
index 79a13b3..2e67da2 100644
--- a/genomix/genomix-pregelix/src/test/java/edu/uci/ics/genomix/pregelix/JobRun/PathMergeSmallTestSuite.java
+++ b/genomix/genomix-pregelix/src/test/java/edu/uci/ics/genomix/pregelix/JobRun/PathMergeSmallTestSuite.java
@@ -43,9 +43,9 @@
 public class PathMergeSmallTestSuite extends TestSuite {
     private static final Logger LOGGER = Logger.getLogger(PathMergeSmallTestSuite.class.getName());
 
-    public static final String PreFix = "data/actual"; //"graphbuildresult";
+    public static final String PreFix = "data/PathMergeTestSet"; //"graphbuildresult";
     public static final String[] TestDir = { PreFix + File.separator
-    + "bubblemerge/BubbleMergeGraph/bin/small_bubble"};
+    + "8"};
     //+ "tipremove/TipRemoveGraph/bin/fr_with_tip"};
     //+ "graphs/pathmerge/singleread"};
     //+ "bridgeadd/BridgeAddGraph/bin/tworeads"};
diff --git a/genomix/genomix-pregelix/src/test/resources/jobs/BridgeAddGraph.xml b/genomix/genomix-pregelix/src/test/resources/jobs/BridgeAddGraph.xml
deleted file mode 100644
index 4739d59..0000000
--- a/genomix/genomix-pregelix/src/test/resources/jobs/BridgeAddGraph.xml
+++ /dev/null
@@ -1,142 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" standalone="no"?><configuration>
-<property><name>mapred.tasktracker.dns.nameserver</name><value>default</value></property>
-<property><name>mapred.queue.default.acl-administer-jobs</name><value>*</value></property>
-<property><name>mapred.skip.map.auto.incr.proc.count</name><value>true</value></property>
-<property><name>mapred.jobtracker.instrumentation</name><value>org.apache.hadoop.mapred.JobTrackerMetricsInst</value></property>
-<property><name>mapred.skip.reduce.auto.incr.proc.count</name><value>true</value></property>
-<property><name>fs.hsftp.impl</name><value>org.apache.hadoop.hdfs.HsftpFileSystem</value></property>
-<property><name>mapred.submit.replication</name><value>10</value></property>
-<property><name>ipc.server.tcpnodelay</name><value>false</value></property>
-<property><name>fs.checkpoint.dir</name><value>${hadoop.tmp.dir}/dfs/namesecondary</value></property>
-<property><name>mapred.output.compression.type</name><value>RECORD</value></property>
-<property><name>mapred.job.shuffle.merge.percent</name><value>0.66</value></property>
-<property><name>mapred.child.java.opts</name><value>-Xmx200m</value></property>
-<property><name>mapred.queue.default.acl-submit-job</name><value>*</value></property>
-<property><name>keep.failed.task.files</name><value>false</value></property>
-<property><name>mapred.jobtracker.job.history.block.size</name><value>3145728</value></property>
-<property><name>mapred.output.value.class</name><value>edu.uci.ics.genomix.pregelix.io.VertexValueWritable</value></property>
-<property><name>io.bytes.per.checksum</name><value>512</value></property>
-<property><name>mapred.task.tracker.report.address</name><value>127.0.0.1:0</value></property>
-<property><name>hadoop.util.hash.type</name><value>murmur</value></property>
-<property><name>fs.hdfs.impl</name><value>org.apache.hadoop.hdfs.DistributedFileSystem</value></property>
-<property><name>fs.ramfs.impl</name><value>org.apache.hadoop.fs.InMemoryFileSystem</value></property>
-<property><name>mapred.jobtracker.restart.recover</name><value>false</value></property>
-<property><name>fs.hftp.impl</name><value>org.apache.hadoop.hdfs.HftpFileSystem</value></property>
-<property><name>BridgeRemoveVertex.kmerSize</name><value>3</value></property>
-<property><name>fs.checkpoint.period</name><value>3600</value></property>
-<property><name>mapred.child.tmp</name><value>./tmp</value></property>
-<property><name>mapred.local.dir.minspacekill</name><value>0</value></property>
-<property><name>map.sort.class</name><value>org.apache.hadoop.util.QuickSort</value></property>
-<property><name>hadoop.logfile.count</name><value>10</value></property>
-<property><name>ipc.client.connection.maxidletime</name><value>10000</value></property>
-<property><name>io.map.index.skip</name><value>0</value></property>
-<property><name>mapred.tasktracker.expiry.interval</name><value>600000</value></property>
-<property><name>mapred.output.compress</name><value>false</value></property>
-<property><name>io.seqfile.lazydecompress</name><value>true</value></property>
-<property><name>mapred.reduce.parallel.copies</name><value>5</value></property>
-<property><name>fs.checkpoint.size</name><value>67108864</value></property>
-<property><name>mapred.job.reduce.input.buffer.percent</name><value>0.0</value></property>
-<property><name>mapred.job.name</name><value>BridgeAddGraph</value></property>
-<property><name>local.cache.size</name><value>10737418240</value></property>
-<property><name>fs.s3n.impl</name><value>org.apache.hadoop.fs.s3native.NativeS3FileSystem</value></property>
-<property><name>mapred.userlog.limit.kb</name><value>0</value></property>
-<property><name>fs.file.impl</name><value>org.apache.hadoop.fs.LocalFileSystem</value></property>
-<property><name>mapred.task.tracker.http.address</name><value>0.0.0.0:50060</value></property>
-<property><name>mapred.task.timeout</name><value>600000</value></property>
-<property><name>fs.kfs.impl</name><value>org.apache.hadoop.fs.kfs.KosmosFileSystem</value></property>
-<property><name>mapred.max.tracker.blacklists</name><value>4</value></property>
-<property><name>fs.s3.buffer.dir</name><value>${hadoop.tmp.dir}/s3</value></property>
-<property><name>mapred.job.tracker.persist.jobstatus.dir</name><value>/jobtracker/jobsInfo</value></property>
-<property><name>ipc.client.kill.max</name><value>10</value></property>
-<property><name>mapred.tasktracker.instrumentation</name><value>org.apache.hadoop.mapred.TaskTrackerMetricsInst</value></property>
-<property><name>mapred.reduce.tasks.speculative.execution</name><value>true</value></property>
-<property><name>io.sort.record.percent</name><value>0.05</value></property>
-<property><name>hadoop.security.authorization</name><value>false</value></property>
-<property><name>mapred.max.tracker.failures</name><value>4</value></property>
-<property><name>mapred.jobtracker.taskScheduler</name><value>org.apache.hadoop.mapred.JobQueueTaskScheduler</value></property>
-<property><name>mapred.tasktracker.dns.interface</name><value>default</value></property>
-<property><name>mapred.map.tasks</name><value>2</value></property>
-<property><name>mapred.job.tracker.persist.jobstatus.hours</name><value>0</value></property>
-<property><name>fs.s3.sleepTimeSeconds</name><value>10</value></property>
-<property><name>fs.default.name</name><value>file:///</value></property>
-<property><name>mapred.output.key.class</name><value>edu.uci.ics.genomix.type.PositionWritable</value></property>
-<property><name>tasktracker.http.threads</name><value>40</value></property>
-<property><name>mapred.tasktracker.taskmemorymanager.monitoring-interval</name><value>5000</value></property>
-<property><name>hadoop.rpc.socket.factory.class.default</name><value>org.apache.hadoop.net.StandardSocketFactory</value></property>
-<property><name>mapred.reduce.tasks</name><value>1</value></property>
-<property><name>topology.node.switch.mapping.impl</name><value>org.apache.hadoop.net.ScriptBasedMapping</value></property>
-<property><name>pregelix.vertexClass</name><value>edu.uci.ics.genomix.pregelix.operator.bridgeremove.BridgeAddVertex</value></property>
-<property><name>mapred.skip.reduce.max.skip.groups</name><value>0</value></property>
-<property><name>io.file.buffer.size</name><value>4096</value></property>
-<property><name>mapred.jobtracker.maxtasks.per.job</name><value>-1</value></property>
-<property><name>mapred.tasktracker.indexcache.mb</name><value>10</value></property>
-<property><name>mapred.tasktracker.map.tasks.maximum</name><value>2</value></property>
-<property><name>fs.har.impl.disable.cache</name><value>true</value></property>
-<property><name>mapred.task.profile.maps</name><value>0-2</value></property>
-<property><name>hadoop.native.lib</name><value>true</value></property>
-<property><name>fs.s3.block.size</name><value>67108864</value></property>
-<property><name>mapred.job.reuse.jvm.num.tasks</name><value>1</value></property>
-<property><name>mapred.job.tracker.http.address</name><value>0.0.0.0:50030</value></property>
-<property><name>mapred.tasktracker.reduce.tasks.maximum</name><value>2</value></property>
-<property><name>io.compression.codecs</name><value>org.apache.hadoop.io.compress.DefaultCodec,org.apache.hadoop.io.compress.GzipCodec,org.apache.hadoop.io.compress.BZip2Codec</value></property>
-<property><name>mapred.job.shuffle.input.buffer.percent</name><value>0.70</value></property>
-<property><name>io.seqfile.compress.blocksize</name><value>1000000</value></property>
-<property><name>mapred.queue.names</name><value>default</value></property>
-<property><name>fs.har.impl</name><value>org.apache.hadoop.fs.HarFileSystem</value></property>
-<property><name>io.mapfile.bloom.error.rate</name><value>0.005</value></property>
-<property><name>mapred.job.tracker</name><value>local</value></property>
-<property><name>io.skip.checksum.errors</name><value>false</value></property>
-<property><name>mapred.reduce.max.attempts</name><value>4</value></property>
-<property><name>fs.s3.maxRetries</name><value>4</value></property>
-<property><name>ipc.server.listen.queue.size</name><value>128</value></property>
-<property><name>fs.trash.interval</name><value>0</value></property>
-<property><name>mapred.local.dir.minspacestart</name><value>0</value></property>
-<property><name>fs.s3.impl</name><value>org.apache.hadoop.fs.s3.S3FileSystem</value></property>
-<property><name>io.seqfile.sorter.recordlimit</name><value>1000000</value></property>
-<property><name>io.mapfile.bloom.size</name><value>1048576</value></property>
-<property><name>io.sort.mb</name><value>100</value></property>
-<property><name>mapred.local.dir</name><value>${hadoop.tmp.dir}/mapred/local</value></property>
-<property><name>io.sort.factor</name><value>10</value></property>
-<property><name>mapred.task.profile</name><value>false</value></property>
-<property><name>job.end.retry.interval</name><value>30000</value></property>
-<property><name>mapred.tasktracker.procfsbasedprocesstree.sleeptime-before-sigkill</name><value>5000</value></property>
-<property><name>mapred.jobtracker.completeuserjobs.maximum</name><value>100</value></property>
-<property><name>mapred.task.profile.reduces</name><value>0-2</value></property>
-<property><name>webinterface.private.actions</name><value>false</value></property>
-<property><name>hadoop.tmp.dir</name><value>/tmp/hadoop-${user.name}</value></property>
-<property><name>mapred.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
-<property><name>mapred.skip.attempts.to.start.skipping</name><value>2</value></property>
-<property><name>mapred.temp.dir</name><value>${hadoop.tmp.dir}/mapred/temp</value></property>
-<property><name>mapred.merge.recordsBeforeProgress</name><value>10000</value></property>
-<property><name>mapred.map.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
-<property><name>mapred.compress.map.output</name><value>false</value></property>
-<property><name>io.sort.spill.percent</name><value>0.80</value></property>
-<property><name>fs.checkpoint.edits.dir</name><value>${fs.checkpoint.dir}</value></property>
-<property><name>mapred.userlog.retain.hours</name><value>24</value></property>
-<property><name>mapred.system.dir</name><value>${hadoop.tmp.dir}/mapred/system</value></property>
-<property><name>mapred.line.input.format.linespermap</name><value>1</value></property>
-<property><name>job.end.retry.attempts</name><value>0</value></property>
-<property><name>ipc.client.idlethreshold</name><value>4000</value></property>
-<property><name>pregelix.vertexOutputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.DataCleanOutputFormat</value></property>
-<property><name>mapred.reduce.copy.backoff</name><value>300</value></property>
-<property><name>mapred.map.tasks.speculative.execution</name><value>true</value></property>
-<property><name>mapred.inmem.merge.threshold</name><value>1000</value></property>
-<property><name>hadoop.logfile.size</name><value>10000000</value></property>
-<property><name>pregelix.vertexInputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.NaiveAlgorithmForPathMergeInputFormat</value></property>
-<property><name>mapred.job.queue.name</name><value>default</value></property>
-<property><name>mapred.job.tracker.persist.jobstatus.active</name><value>false</value></property>
-<property><name>pregelix.incStateLength</name><value>true</value></property>
-<property><name>mapred.reduce.slowstart.completed.maps</name><value>0.05</value></property>
-<property><name>topology.script.number.args</name><value>100</value></property>
-<property><name>mapred.skip.map.max.skip.records</name><value>0</value></property>
-<property><name>fs.ftp.impl</name><value>org.apache.hadoop.fs.ftp.FTPFileSystem</value></property>
-<property><name>mapred.task.cache.levels</name><value>2</value></property>
-<property><name>mapred.job.tracker.handler.count</name><value>10</value></property>
-<property><name>io.serializations</name><value>org.apache.hadoop.io.serializer.WritableSerialization</value></property>
-<property><name>ipc.client.connect.max.retries</name><value>10</value></property>
-<property><name>mapred.min.split.size</name><value>0</value></property>
-<property><name>mapred.map.max.attempts</name><value>4</value></property>
-<property><name>jobclient.output.filter</name><value>FAILED</value></property>
-<property><name>ipc.client.tcpnodelay</name><value>false</value></property>
-<property><name>mapred.acls.enabled</name><value>false</value></property>
-</configuration>
\ No newline at end of file
diff --git a/genomix/genomix-pregelix/src/test/resources/jobs/BridgeRemoveGraph.xml b/genomix/genomix-pregelix/src/test/resources/jobs/BridgeRemoveGraph.xml
deleted file mode 100644
index f9b801a..0000000
--- a/genomix/genomix-pregelix/src/test/resources/jobs/BridgeRemoveGraph.xml
+++ /dev/null
@@ -1,142 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" standalone="no"?><configuration>
-<property><name>mapred.tasktracker.dns.nameserver</name><value>default</value></property>
-<property><name>mapred.queue.default.acl-administer-jobs</name><value>*</value></property>
-<property><name>mapred.skip.map.auto.incr.proc.count</name><value>true</value></property>
-<property><name>mapred.jobtracker.instrumentation</name><value>org.apache.hadoop.mapred.JobTrackerMetricsInst</value></property>
-<property><name>mapred.skip.reduce.auto.incr.proc.count</name><value>true</value></property>
-<property><name>fs.hsftp.impl</name><value>org.apache.hadoop.hdfs.HsftpFileSystem</value></property>
-<property><name>mapred.submit.replication</name><value>10</value></property>
-<property><name>ipc.server.tcpnodelay</name><value>false</value></property>
-<property><name>fs.checkpoint.dir</name><value>${hadoop.tmp.dir}/dfs/namesecondary</value></property>
-<property><name>mapred.output.compression.type</name><value>RECORD</value></property>
-<property><name>mapred.job.shuffle.merge.percent</name><value>0.66</value></property>
-<property><name>mapred.child.java.opts</name><value>-Xmx200m</value></property>
-<property><name>mapred.queue.default.acl-submit-job</name><value>*</value></property>
-<property><name>keep.failed.task.files</name><value>false</value></property>
-<property><name>mapred.jobtracker.job.history.block.size</name><value>3145728</value></property>
-<property><name>mapred.output.value.class</name><value>edu.uci.ics.genomix.pregelix.io.VertexValueWritable</value></property>
-<property><name>io.bytes.per.checksum</name><value>512</value></property>
-<property><name>mapred.task.tracker.report.address</name><value>127.0.0.1:0</value></property>
-<property><name>hadoop.util.hash.type</name><value>murmur</value></property>
-<property><name>fs.hdfs.impl</name><value>org.apache.hadoop.hdfs.DistributedFileSystem</value></property>
-<property><name>fs.ramfs.impl</name><value>org.apache.hadoop.fs.InMemoryFileSystem</value></property>
-<property><name>mapred.jobtracker.restart.recover</name><value>false</value></property>
-<property><name>fs.hftp.impl</name><value>org.apache.hadoop.hdfs.HftpFileSystem</value></property>
-<property><name>fs.checkpoint.period</name><value>3600</value></property>
-<property><name>mapred.child.tmp</name><value>./tmp</value></property>
-<property><name>mapred.local.dir.minspacekill</name><value>0</value></property>
-<property><name>map.sort.class</name><value>org.apache.hadoop.util.QuickSort</value></property>
-<property><name>hadoop.logfile.count</name><value>10</value></property>
-<property><name>ipc.client.connection.maxidletime</name><value>10000</value></property>
-<property><name>io.map.index.skip</name><value>0</value></property>
-<property><name>mapred.tasktracker.expiry.interval</name><value>600000</value></property>
-<property><name>mapred.output.compress</name><value>false</value></property>
-<property><name>io.seqfile.lazydecompress</name><value>true</value></property>
-<property><name>mapred.reduce.parallel.copies</name><value>5</value></property>
-<property><name>fs.checkpoint.size</name><value>67108864</value></property>
-<property><name>mapred.job.reduce.input.buffer.percent</name><value>0.0</value></property>
-<property><name>mapred.job.name</name><value>BridgeRemoveGraph</value></property>
-<property><name>local.cache.size</name><value>10737418240</value></property>
-<property><name>fs.s3n.impl</name><value>org.apache.hadoop.fs.s3native.NativeS3FileSystem</value></property>
-<property><name>mapred.userlog.limit.kb</name><value>0</value></property>
-<property><name>fs.file.impl</name><value>org.apache.hadoop.fs.LocalFileSystem</value></property>
-<property><name>mapred.task.tracker.http.address</name><value>0.0.0.0:50060</value></property>
-<property><name>mapred.task.timeout</name><value>600000</value></property>
-<property><name>fs.kfs.impl</name><value>org.apache.hadoop.fs.kfs.KosmosFileSystem</value></property>
-<property><name>mapred.max.tracker.blacklists</name><value>4</value></property>
-<property><name>fs.s3.buffer.dir</name><value>${hadoop.tmp.dir}/s3</value></property>
-<property><name>mapred.job.tracker.persist.jobstatus.dir</name><value>/jobtracker/jobsInfo</value></property>
-<property><name>ipc.client.kill.max</name><value>10</value></property>
-<property><name>mapred.tasktracker.instrumentation</name><value>org.apache.hadoop.mapred.TaskTrackerMetricsInst</value></property>
-<property><name>mapred.reduce.tasks.speculative.execution</name><value>true</value></property>
-<property><name>io.sort.record.percent</name><value>0.05</value></property>
-<property><name>hadoop.security.authorization</name><value>false</value></property>
-<property><name>mapred.max.tracker.failures</name><value>4</value></property>
-<property><name>mapred.jobtracker.taskScheduler</name><value>org.apache.hadoop.mapred.JobQueueTaskScheduler</value></property>
-<property><name>mapred.tasktracker.dns.interface</name><value>default</value></property>
-<property><name>mapred.map.tasks</name><value>2</value></property>
-<property><name>mapred.job.tracker.persist.jobstatus.hours</name><value>0</value></property>
-<property><name>fs.s3.sleepTimeSeconds</name><value>10</value></property>
-<property><name>fs.default.name</name><value>file:///</value></property>
-<property><name>mapred.output.key.class</name><value>edu.uci.ics.genomix.type.PositionWritable</value></property>
-<property><name>tasktracker.http.threads</name><value>40</value></property>
-<property><name>mapred.tasktracker.taskmemorymanager.monitoring-interval</name><value>5000</value></property>
-<property><name>hadoop.rpc.socket.factory.class.default</name><value>org.apache.hadoop.net.StandardSocketFactory</value></property>
-<property><name>mapred.reduce.tasks</name><value>1</value></property>
-<property><name>topology.node.switch.mapping.impl</name><value>org.apache.hadoop.net.ScriptBasedMapping</value></property>
-<property><name>pregelix.vertexClass</name><value>edu.uci.ics.genomix.pregelix.operator.bridgeremove.BridgeRemoveVertex</value></property>
-<property><name>mapred.skip.reduce.max.skip.groups</name><value>0</value></property>
-<property><name>io.file.buffer.size</name><value>4096</value></property>
-<property><name>mapred.jobtracker.maxtasks.per.job</name><value>-1</value></property>
-<property><name>mapred.tasktracker.indexcache.mb</name><value>10</value></property>
-<property><name>mapred.tasktracker.map.tasks.maximum</name><value>2</value></property>
-<property><name>fs.har.impl.disable.cache</name><value>true</value></property>
-<property><name>mapred.task.profile.maps</name><value>0-2</value></property>
-<property><name>hadoop.native.lib</name><value>true</value></property>
-<property><name>fs.s3.block.size</name><value>67108864</value></property>
-<property><name>mapred.job.reuse.jvm.num.tasks</name><value>1</value></property>
-<property><name>mapred.job.tracker.http.address</name><value>0.0.0.0:50030</value></property>
-<property><name>mapred.tasktracker.reduce.tasks.maximum</name><value>2</value></property>
-<property><name>io.compression.codecs</name><value>org.apache.hadoop.io.compress.DefaultCodec,org.apache.hadoop.io.compress.GzipCodec,org.apache.hadoop.io.compress.BZip2Codec</value></property>
-<property><name>mapred.job.shuffle.input.buffer.percent</name><value>0.70</value></property>
-<property><name>io.seqfile.compress.blocksize</name><value>1000000</value></property>
-<property><name>mapred.queue.names</name><value>default</value></property>
-<property><name>fs.har.impl</name><value>org.apache.hadoop.fs.HarFileSystem</value></property>
-<property><name>io.mapfile.bloom.error.rate</name><value>0.005</value></property>
-<property><name>mapred.job.tracker</name><value>local</value></property>
-<property><name>io.skip.checksum.errors</name><value>false</value></property>
-<property><name>mapred.reduce.max.attempts</name><value>4</value></property>
-<property><name>fs.s3.maxRetries</name><value>4</value></property>
-<property><name>ipc.server.listen.queue.size</name><value>128</value></property>
-<property><name>fs.trash.interval</name><value>0</value></property>
-<property><name>mapred.local.dir.minspacestart</name><value>0</value></property>
-<property><name>fs.s3.impl</name><value>org.apache.hadoop.fs.s3.S3FileSystem</value></property>
-<property><name>io.seqfile.sorter.recordlimit</name><value>1000000</value></property>
-<property><name>io.mapfile.bloom.size</name><value>1048576</value></property>
-<property><name>io.sort.mb</name><value>100</value></property>
-<property><name>mapred.local.dir</name><value>${hadoop.tmp.dir}/mapred/local</value></property>
-<property><name>io.sort.factor</name><value>10</value></property>
-<property><name>BasicPathMergeVertex.kmerSize</name><value>5</value></property>
-<property><name>mapred.task.profile</name><value>false</value></property>
-<property><name>job.end.retry.interval</name><value>30000</value></property>
-<property><name>mapred.tasktracker.procfsbasedprocesstree.sleeptime-before-sigkill</name><value>5000</value></property>
-<property><name>mapred.jobtracker.completeuserjobs.maximum</name><value>100</value></property>
-<property><name>mapred.task.profile.reduces</name><value>0-2</value></property>
-<property><name>webinterface.private.actions</name><value>false</value></property>
-<property><name>hadoop.tmp.dir</name><value>/tmp/hadoop-${user.name}</value></property>
-<property><name>mapred.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
-<property><name>mapred.skip.attempts.to.start.skipping</name><value>2</value></property>
-<property><name>mapred.temp.dir</name><value>${hadoop.tmp.dir}/mapred/temp</value></property>
-<property><name>mapred.merge.recordsBeforeProgress</name><value>10000</value></property>
-<property><name>mapred.map.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
-<property><name>mapred.compress.map.output</name><value>false</value></property>
-<property><name>io.sort.spill.percent</name><value>0.80</value></property>
-<property><name>fs.checkpoint.edits.dir</name><value>${fs.checkpoint.dir}</value></property>
-<property><name>mapred.userlog.retain.hours</name><value>24</value></property>
-<property><name>mapred.system.dir</name><value>${hadoop.tmp.dir}/mapred/system</value></property>
-<property><name>mapred.line.input.format.linespermap</name><value>1</value></property>
-<property><name>job.end.retry.attempts</name><value>0</value></property>
-<property><name>ipc.client.idlethreshold</name><value>4000</value></property>
-<property><name>pregelix.vertexOutputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.DataCleanOutputFormat</value></property>
-<property><name>mapred.reduce.copy.backoff</name><value>300</value></property>
-<property><name>mapred.map.tasks.speculative.execution</name><value>true</value></property>
-<property><name>mapred.inmem.merge.threshold</name><value>1000</value></property>
-<property><name>hadoop.logfile.size</name><value>10000000</value></property>
-<property><name>pregelix.vertexInputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.DataCleanInputFormat</value></property>
-<property><name>mapred.job.queue.name</name><value>default</value></property>
-<property><name>mapred.job.tracker.persist.jobstatus.active</name><value>false</value></property>
-<property><name>pregelix.incStateLength</name><value>true</value></property>
-<property><name>mapred.reduce.slowstart.completed.maps</name><value>0.05</value></property>
-<property><name>topology.script.number.args</name><value>100</value></property>
-<property><name>mapred.skip.map.max.skip.records</name><value>0</value></property>
-<property><name>fs.ftp.impl</name><value>org.apache.hadoop.fs.ftp.FTPFileSystem</value></property>
-<property><name>mapred.task.cache.levels</name><value>2</value></property>
-<property><name>mapred.job.tracker.handler.count</name><value>10</value></property>
-<property><name>io.serializations</name><value>org.apache.hadoop.io.serializer.WritableSerialization</value></property>
-<property><name>ipc.client.connect.max.retries</name><value>10</value></property>
-<property><name>mapred.min.split.size</name><value>0</value></property>
-<property><name>mapred.map.max.attempts</name><value>4</value></property>
-<property><name>jobclient.output.filter</name><value>FAILED</value></property>
-<property><name>ipc.client.tcpnodelay</name><value>false</value></property>
-<property><name>mapred.acls.enabled</name><value>false</value></property>
-</configuration>
\ No newline at end of file
diff --git a/genomix/genomix-pregelix/src/test/resources/jobs/BubbleAddGraph.xml b/genomix/genomix-pregelix/src/test/resources/jobs/BubbleAddGraph.xml
deleted file mode 100644
index 452834a..0000000
--- a/genomix/genomix-pregelix/src/test/resources/jobs/BubbleAddGraph.xml
+++ /dev/null
@@ -1,142 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" standalone="no"?><configuration>
-<property><name>mapred.tasktracker.dns.nameserver</name><value>default</value></property>
-<property><name>mapred.queue.default.acl-administer-jobs</name><value>*</value></property>
-<property><name>mapred.skip.map.auto.incr.proc.count</name><value>true</value></property>
-<property><name>mapred.jobtracker.instrumentation</name><value>org.apache.hadoop.mapred.JobTrackerMetricsInst</value></property>
-<property><name>mapred.skip.reduce.auto.incr.proc.count</name><value>true</value></property>
-<property><name>fs.hsftp.impl</name><value>org.apache.hadoop.hdfs.HsftpFileSystem</value></property>
-<property><name>mapred.submit.replication</name><value>10</value></property>
-<property><name>ipc.server.tcpnodelay</name><value>false</value></property>
-<property><name>fs.checkpoint.dir</name><value>${hadoop.tmp.dir}/dfs/namesecondary</value></property>
-<property><name>mapred.output.compression.type</name><value>RECORD</value></property>
-<property><name>mapred.job.shuffle.merge.percent</name><value>0.66</value></property>
-<property><name>mapred.child.java.opts</name><value>-Xmx200m</value></property>
-<property><name>mapred.queue.default.acl-submit-job</name><value>*</value></property>
-<property><name>keep.failed.task.files</name><value>false</value></property>
-<property><name>mapred.jobtracker.job.history.block.size</name><value>3145728</value></property>
-<property><name>mapred.output.value.class</name><value>edu.uci.ics.genomix.pregelix.io.VertexValueWritable</value></property>
-<property><name>io.bytes.per.checksum</name><value>512</value></property>
-<property><name>mapred.task.tracker.report.address</name><value>127.0.0.1:0</value></property>
-<property><name>hadoop.util.hash.type</name><value>murmur</value></property>
-<property><name>fs.hdfs.impl</name><value>org.apache.hadoop.hdfs.DistributedFileSystem</value></property>
-<property><name>fs.ramfs.impl</name><value>org.apache.hadoop.fs.InMemoryFileSystem</value></property>
-<property><name>mapred.jobtracker.restart.recover</name><value>false</value></property>
-<property><name>fs.hftp.impl</name><value>org.apache.hadoop.hdfs.HftpFileSystem</value></property>
-<property><name>fs.checkpoint.period</name><value>3600</value></property>
-<property><name>mapred.child.tmp</name><value>./tmp</value></property>
-<property><name>mapred.local.dir.minspacekill</name><value>0</value></property>
-<property><name>map.sort.class</name><value>org.apache.hadoop.util.QuickSort</value></property>
-<property><name>hadoop.logfile.count</name><value>10</value></property>
-<property><name>ipc.client.connection.maxidletime</name><value>10000</value></property>
-<property><name>io.map.index.skip</name><value>0</value></property>
-<property><name>mapred.tasktracker.expiry.interval</name><value>600000</value></property>
-<property><name>mapred.output.compress</name><value>false</value></property>
-<property><name>io.seqfile.lazydecompress</name><value>true</value></property>
-<property><name>mapred.reduce.parallel.copies</name><value>5</value></property>
-<property><name>fs.checkpoint.size</name><value>67108864</value></property>
-<property><name>mapred.job.reduce.input.buffer.percent</name><value>0.0</value></property>
-<property><name>mapred.job.name</name><value>BubbleAddGraph</value></property>
-<property><name>local.cache.size</name><value>10737418240</value></property>
-<property><name>fs.s3n.impl</name><value>org.apache.hadoop.fs.s3native.NativeS3FileSystem</value></property>
-<property><name>mapred.userlog.limit.kb</name><value>0</value></property>
-<property><name>fs.file.impl</name><value>org.apache.hadoop.fs.LocalFileSystem</value></property>
-<property><name>mapred.task.tracker.http.address</name><value>0.0.0.0:50060</value></property>
-<property><name>mapred.task.timeout</name><value>600000</value></property>
-<property><name>fs.kfs.impl</name><value>org.apache.hadoop.fs.kfs.KosmosFileSystem</value></property>
-<property><name>mapred.max.tracker.blacklists</name><value>4</value></property>
-<property><name>fs.s3.buffer.dir</name><value>${hadoop.tmp.dir}/s3</value></property>
-<property><name>mapred.job.tracker.persist.jobstatus.dir</name><value>/jobtracker/jobsInfo</value></property>
-<property><name>ipc.client.kill.max</name><value>10</value></property>
-<property><name>mapred.tasktracker.instrumentation</name><value>org.apache.hadoop.mapred.TaskTrackerMetricsInst</value></property>
-<property><name>mapred.reduce.tasks.speculative.execution</name><value>true</value></property>
-<property><name>io.sort.record.percent</name><value>0.05</value></property>
-<property><name>hadoop.security.authorization</name><value>false</value></property>
-<property><name>mapred.max.tracker.failures</name><value>4</value></property>
-<property><name>mapred.jobtracker.taskScheduler</name><value>org.apache.hadoop.mapred.JobQueueTaskScheduler</value></property>
-<property><name>mapred.tasktracker.dns.interface</name><value>default</value></property>
-<property><name>mapred.map.tasks</name><value>2</value></property>
-<property><name>mapred.job.tracker.persist.jobstatus.hours</name><value>0</value></property>
-<property><name>fs.s3.sleepTimeSeconds</name><value>10</value></property>
-<property><name>fs.default.name</name><value>file:///</value></property>
-<property><name>mapred.output.key.class</name><value>edu.uci.ics.genomix.type.PositionWritable</value></property>
-<property><name>tasktracker.http.threads</name><value>40</value></property>
-<property><name>mapred.tasktracker.taskmemorymanager.monitoring-interval</name><value>5000</value></property>
-<property><name>hadoop.rpc.socket.factory.class.default</name><value>org.apache.hadoop.net.StandardSocketFactory</value></property>
-<property><name>mapred.reduce.tasks</name><value>1</value></property>
-<property><name>topology.node.switch.mapping.impl</name><value>org.apache.hadoop.net.ScriptBasedMapping</value></property>
-<property><name>pregelix.vertexClass</name><value>edu.uci.ics.genomix.pregelix.operator.bubblemerge.BubbleAddVertex</value></property>
-<property><name>mapred.skip.reduce.max.skip.groups</name><value>0</value></property>
-<property><name>io.file.buffer.size</name><value>4096</value></property>
-<property><name>mapred.jobtracker.maxtasks.per.job</name><value>-1</value></property>
-<property><name>mapred.tasktracker.indexcache.mb</name><value>10</value></property>
-<property><name>mapred.tasktracker.map.tasks.maximum</name><value>2</value></property>
-<property><name>fs.har.impl.disable.cache</name><value>true</value></property>
-<property><name>mapred.task.profile.maps</name><value>0-2</value></property>
-<property><name>hadoop.native.lib</name><value>true</value></property>
-<property><name>fs.s3.block.size</name><value>67108864</value></property>
-<property><name>mapred.job.reuse.jvm.num.tasks</name><value>1</value></property>
-<property><name>mapred.job.tracker.http.address</name><value>0.0.0.0:50030</value></property>
-<property><name>mapred.tasktracker.reduce.tasks.maximum</name><value>2</value></property>
-<property><name>io.compression.codecs</name><value>org.apache.hadoop.io.compress.DefaultCodec,org.apache.hadoop.io.compress.GzipCodec,org.apache.hadoop.io.compress.BZip2Codec</value></property>
-<property><name>mapred.job.shuffle.input.buffer.percent</name><value>0.70</value></property>
-<property><name>io.seqfile.compress.blocksize</name><value>1000000</value></property>
-<property><name>mapred.queue.names</name><value>default</value></property>
-<property><name>fs.har.impl</name><value>org.apache.hadoop.fs.HarFileSystem</value></property>
-<property><name>io.mapfile.bloom.error.rate</name><value>0.005</value></property>
-<property><name>mapred.job.tracker</name><value>local</value></property>
-<property><name>BubbleAddVertex.kmerSize</name><value>3</value></property>
-<property><name>io.skip.checksum.errors</name><value>false</value></property>
-<property><name>mapred.reduce.max.attempts</name><value>4</value></property>
-<property><name>fs.s3.maxRetries</name><value>4</value></property>
-<property><name>ipc.server.listen.queue.size</name><value>128</value></property>
-<property><name>fs.trash.interval</name><value>0</value></property>
-<property><name>mapred.local.dir.minspacestart</name><value>0</value></property>
-<property><name>fs.s3.impl</name><value>org.apache.hadoop.fs.s3.S3FileSystem</value></property>
-<property><name>io.seqfile.sorter.recordlimit</name><value>1000000</value></property>
-<property><name>io.mapfile.bloom.size</name><value>1048576</value></property>
-<property><name>io.sort.mb</name><value>100</value></property>
-<property><name>mapred.local.dir</name><value>${hadoop.tmp.dir}/mapred/local</value></property>
-<property><name>io.sort.factor</name><value>10</value></property>
-<property><name>mapred.task.profile</name><value>false</value></property>
-<property><name>job.end.retry.interval</name><value>30000</value></property>
-<property><name>mapred.tasktracker.procfsbasedprocesstree.sleeptime-before-sigkill</name><value>5000</value></property>
-<property><name>mapred.jobtracker.completeuserjobs.maximum</name><value>100</value></property>
-<property><name>mapred.task.profile.reduces</name><value>0-2</value></property>
-<property><name>webinterface.private.actions</name><value>false</value></property>
-<property><name>hadoop.tmp.dir</name><value>/tmp/hadoop-${user.name}</value></property>
-<property><name>mapred.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
-<property><name>mapred.skip.attempts.to.start.skipping</name><value>2</value></property>
-<property><name>mapred.temp.dir</name><value>${hadoop.tmp.dir}/mapred/temp</value></property>
-<property><name>mapred.merge.recordsBeforeProgress</name><value>10000</value></property>
-<property><name>mapred.map.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
-<property><name>mapred.compress.map.output</name><value>false</value></property>
-<property><name>io.sort.spill.percent</name><value>0.80</value></property>
-<property><name>fs.checkpoint.edits.dir</name><value>${fs.checkpoint.dir}</value></property>
-<property><name>mapred.userlog.retain.hours</name><value>24</value></property>
-<property><name>mapred.system.dir</name><value>${hadoop.tmp.dir}/mapred/system</value></property>
-<property><name>mapred.line.input.format.linespermap</name><value>1</value></property>
-<property><name>job.end.retry.attempts</name><value>0</value></property>
-<property><name>ipc.client.idlethreshold</name><value>4000</value></property>
-<property><name>pregelix.vertexOutputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.DataCleanOutputFormat</value></property>
-<property><name>mapred.reduce.copy.backoff</name><value>300</value></property>
-<property><name>mapred.map.tasks.speculative.execution</name><value>true</value></property>
-<property><name>mapred.inmem.merge.threshold</name><value>1000</value></property>
-<property><name>hadoop.logfile.size</name><value>10000000</value></property>
-<property><name>pregelix.vertexInputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.NaiveAlgorithmForPathMergeInputFormat</value></property>
-<property><name>mapred.job.queue.name</name><value>default</value></property>
-<property><name>mapred.job.tracker.persist.jobstatus.active</name><value>false</value></property>
-<property><name>pregelix.incStateLength</name><value>true</value></property>
-<property><name>mapred.reduce.slowstart.completed.maps</name><value>0.05</value></property>
-<property><name>topology.script.number.args</name><value>100</value></property>
-<property><name>mapred.skip.map.max.skip.records</name><value>0</value></property>
-<property><name>fs.ftp.impl</name><value>org.apache.hadoop.fs.ftp.FTPFileSystem</value></property>
-<property><name>mapred.task.cache.levels</name><value>2</value></property>
-<property><name>mapred.job.tracker.handler.count</name><value>10</value></property>
-<property><name>io.serializations</name><value>org.apache.hadoop.io.serializer.WritableSerialization</value></property>
-<property><name>ipc.client.connect.max.retries</name><value>10</value></property>
-<property><name>mapred.min.split.size</name><value>0</value></property>
-<property><name>mapred.map.max.attempts</name><value>4</value></property>
-<property><name>jobclient.output.filter</name><value>FAILED</value></property>
-<property><name>ipc.client.tcpnodelay</name><value>false</value></property>
-<property><name>mapred.acls.enabled</name><value>false</value></property>
-</configuration>
\ No newline at end of file
diff --git a/genomix/genomix-pregelix/src/test/resources/jobs/BubbleMergeGraph.xml b/genomix/genomix-pregelix/src/test/resources/jobs/BubbleMergeGraph.xml
deleted file mode 100644
index 605a004..0000000
--- a/genomix/genomix-pregelix/src/test/resources/jobs/BubbleMergeGraph.xml
+++ /dev/null
@@ -1,142 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" standalone="no"?><configuration>
-<property><name>mapred.tasktracker.dns.nameserver</name><value>default</value></property>
-<property><name>mapred.queue.default.acl-administer-jobs</name><value>*</value></property>
-<property><name>mapred.skip.map.auto.incr.proc.count</name><value>true</value></property>
-<property><name>mapred.jobtracker.instrumentation</name><value>org.apache.hadoop.mapred.JobTrackerMetricsInst</value></property>
-<property><name>mapred.skip.reduce.auto.incr.proc.count</name><value>true</value></property>
-<property><name>fs.hsftp.impl</name><value>org.apache.hadoop.hdfs.HsftpFileSystem</value></property>
-<property><name>mapred.submit.replication</name><value>10</value></property>
-<property><name>ipc.server.tcpnodelay</name><value>false</value></property>
-<property><name>fs.checkpoint.dir</name><value>${hadoop.tmp.dir}/dfs/namesecondary</value></property>
-<property><name>mapred.output.compression.type</name><value>RECORD</value></property>
-<property><name>mapred.job.shuffle.merge.percent</name><value>0.66</value></property>
-<property><name>mapred.child.java.opts</name><value>-Xmx200m</value></property>
-<property><name>mapred.queue.default.acl-submit-job</name><value>*</value></property>
-<property><name>keep.failed.task.files</name><value>false</value></property>
-<property><name>mapred.jobtracker.job.history.block.size</name><value>3145728</value></property>
-<property><name>mapred.output.value.class</name><value>edu.uci.ics.genomix.pregelix.io.VertexValueWritable</value></property>
-<property><name>io.bytes.per.checksum</name><value>512</value></property>
-<property><name>mapred.task.tracker.report.address</name><value>127.0.0.1:0</value></property>
-<property><name>hadoop.util.hash.type</name><value>murmur</value></property>
-<property><name>fs.hdfs.impl</name><value>org.apache.hadoop.hdfs.DistributedFileSystem</value></property>
-<property><name>fs.ramfs.impl</name><value>org.apache.hadoop.fs.InMemoryFileSystem</value></property>
-<property><name>mapred.jobtracker.restart.recover</name><value>false</value></property>
-<property><name>fs.hftp.impl</name><value>org.apache.hadoop.hdfs.HftpFileSystem</value></property>
-<property><name>fs.checkpoint.period</name><value>3600</value></property>
-<property><name>mapred.child.tmp</name><value>./tmp</value></property>
-<property><name>mapred.local.dir.minspacekill</name><value>0</value></property>
-<property><name>map.sort.class</name><value>org.apache.hadoop.util.QuickSort</value></property>
-<property><name>hadoop.logfile.count</name><value>10</value></property>
-<property><name>ipc.client.connection.maxidletime</name><value>10000</value></property>
-<property><name>io.map.index.skip</name><value>0</value></property>
-<property><name>mapred.tasktracker.expiry.interval</name><value>600000</value></property>
-<property><name>mapred.output.compress</name><value>false</value></property>
-<property><name>io.seqfile.lazydecompress</name><value>true</value></property>
-<property><name>mapred.reduce.parallel.copies</name><value>5</value></property>
-<property><name>fs.checkpoint.size</name><value>67108864</value></property>
-<property><name>mapred.job.reduce.input.buffer.percent</name><value>0.0</value></property>
-<property><name>mapred.job.name</name><value>BubbleMergeGraph</value></property>
-<property><name>local.cache.size</name><value>10737418240</value></property>
-<property><name>fs.s3n.impl</name><value>org.apache.hadoop.fs.s3native.NativeS3FileSystem</value></property>
-<property><name>mapred.userlog.limit.kb</name><value>0</value></property>
-<property><name>fs.file.impl</name><value>org.apache.hadoop.fs.LocalFileSystem</value></property>
-<property><name>mapred.task.tracker.http.address</name><value>0.0.0.0:50060</value></property>
-<property><name>mapred.task.timeout</name><value>600000</value></property>
-<property><name>fs.kfs.impl</name><value>org.apache.hadoop.fs.kfs.KosmosFileSystem</value></property>
-<property><name>mapred.max.tracker.blacklists</name><value>4</value></property>
-<property><name>fs.s3.buffer.dir</name><value>${hadoop.tmp.dir}/s3</value></property>
-<property><name>mapred.job.tracker.persist.jobstatus.dir</name><value>/jobtracker/jobsInfo</value></property>
-<property><name>ipc.client.kill.max</name><value>10</value></property>
-<property><name>mapred.tasktracker.instrumentation</name><value>org.apache.hadoop.mapred.TaskTrackerMetricsInst</value></property>
-<property><name>mapred.reduce.tasks.speculative.execution</name><value>true</value></property>
-<property><name>io.sort.record.percent</name><value>0.05</value></property>
-<property><name>hadoop.security.authorization</name><value>false</value></property>
-<property><name>mapred.max.tracker.failures</name><value>4</value></property>
-<property><name>mapred.jobtracker.taskScheduler</name><value>org.apache.hadoop.mapred.JobQueueTaskScheduler</value></property>
-<property><name>mapred.tasktracker.dns.interface</name><value>default</value></property>
-<property><name>mapred.map.tasks</name><value>2</value></property>
-<property><name>mapred.job.tracker.persist.jobstatus.hours</name><value>0</value></property>
-<property><name>fs.s3.sleepTimeSeconds</name><value>10</value></property>
-<property><name>fs.default.name</name><value>file:///</value></property>
-<property><name>mapred.output.key.class</name><value>edu.uci.ics.genomix.type.PositionWritable</value></property>
-<property><name>tasktracker.http.threads</name><value>40</value></property>
-<property><name>mapred.tasktracker.taskmemorymanager.monitoring-interval</name><value>5000</value></property>
-<property><name>hadoop.rpc.socket.factory.class.default</name><value>org.apache.hadoop.net.StandardSocketFactory</value></property>
-<property><name>mapred.reduce.tasks</name><value>1</value></property>
-<property><name>topology.node.switch.mapping.impl</name><value>org.apache.hadoop.net.ScriptBasedMapping</value></property>
-<property><name>pregelix.vertexClass</name><value>edu.uci.ics.genomix.pregelix.operator.bubblemerge.BubbleMergeVertex</value></property>
-<property><name>mapred.skip.reduce.max.skip.groups</name><value>0</value></property>
-<property><name>io.file.buffer.size</name><value>4096</value></property>
-<property><name>mapred.jobtracker.maxtasks.per.job</name><value>-1</value></property>
-<property><name>mapred.tasktracker.indexcache.mb</name><value>10</value></property>
-<property><name>mapred.tasktracker.map.tasks.maximum</name><value>2</value></property>
-<property><name>fs.har.impl.disable.cache</name><value>true</value></property>
-<property><name>mapred.task.profile.maps</name><value>0-2</value></property>
-<property><name>hadoop.native.lib</name><value>true</value></property>
-<property><name>fs.s3.block.size</name><value>67108864</value></property>
-<property><name>mapred.job.reuse.jvm.num.tasks</name><value>1</value></property>
-<property><name>mapred.job.tracker.http.address</name><value>0.0.0.0:50030</value></property>
-<property><name>mapred.tasktracker.reduce.tasks.maximum</name><value>2</value></property>
-<property><name>io.compression.codecs</name><value>org.apache.hadoop.io.compress.DefaultCodec,org.apache.hadoop.io.compress.GzipCodec,org.apache.hadoop.io.compress.BZip2Codec</value></property>
-<property><name>mapred.job.shuffle.input.buffer.percent</name><value>0.70</value></property>
-<property><name>io.seqfile.compress.blocksize</name><value>1000000</value></property>
-<property><name>mapred.queue.names</name><value>default</value></property>
-<property><name>fs.har.impl</name><value>org.apache.hadoop.fs.HarFileSystem</value></property>
-<property><name>io.mapfile.bloom.error.rate</name><value>0.005</value></property>
-<property><name>mapred.job.tracker</name><value>local</value></property>
-<property><name>io.skip.checksum.errors</name><value>false</value></property>
-<property><name>mapred.reduce.max.attempts</name><value>4</value></property>
-<property><name>fs.s3.maxRetries</name><value>4</value></property>
-<property><name>ipc.server.listen.queue.size</name><value>128</value></property>
-<property><name>fs.trash.interval</name><value>0</value></property>
-<property><name>mapred.local.dir.minspacestart</name><value>0</value></property>
-<property><name>fs.s3.impl</name><value>org.apache.hadoop.fs.s3.S3FileSystem</value></property>
-<property><name>io.seqfile.sorter.recordlimit</name><value>1000000</value></property>
-<property><name>io.mapfile.bloom.size</name><value>1048576</value></property>
-<property><name>io.sort.mb</name><value>100</value></property>
-<property><name>mapred.local.dir</name><value>${hadoop.tmp.dir}/mapred/local</value></property>
-<property><name>io.sort.factor</name><value>10</value></property>
-<property><name>mapred.task.profile</name><value>false</value></property>
-<property><name>job.end.retry.interval</name><value>30000</value></property>
-<property><name>mapred.tasktracker.procfsbasedprocesstree.sleeptime-before-sigkill</name><value>5000</value></property>
-<property><name>BubbleMergeVertex.kmerSize</name><value>5</value></property>
-<property><name>mapred.jobtracker.completeuserjobs.maximum</name><value>100</value></property>
-<property><name>mapred.task.profile.reduces</name><value>0-2</value></property>
-<property><name>webinterface.private.actions</name><value>false</value></property>
-<property><name>hadoop.tmp.dir</name><value>/tmp/hadoop-${user.name}</value></property>
-<property><name>mapred.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
-<property><name>mapred.skip.attempts.to.start.skipping</name><value>2</value></property>
-<property><name>mapred.temp.dir</name><value>${hadoop.tmp.dir}/mapred/temp</value></property>
-<property><name>mapred.merge.recordsBeforeProgress</name><value>10000</value></property>
-<property><name>mapred.map.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
-<property><name>mapred.compress.map.output</name><value>false</value></property>
-<property><name>io.sort.spill.percent</name><value>0.80</value></property>
-<property><name>fs.checkpoint.edits.dir</name><value>${fs.checkpoint.dir}</value></property>
-<property><name>mapred.userlog.retain.hours</name><value>24</value></property>
-<property><name>mapred.system.dir</name><value>${hadoop.tmp.dir}/mapred/system</value></property>
-<property><name>mapred.line.input.format.linespermap</name><value>1</value></property>
-<property><name>job.end.retry.attempts</name><value>0</value></property>
-<property><name>ipc.client.idlethreshold</name><value>4000</value></property>
-<property><name>pregelix.vertexOutputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.DataCleanOutputFormat</value></property>
-<property><name>mapred.reduce.copy.backoff</name><value>300</value></property>
-<property><name>mapred.map.tasks.speculative.execution</name><value>true</value></property>
-<property><name>mapred.inmem.merge.threshold</name><value>1000</value></property>
-<property><name>hadoop.logfile.size</name><value>10000000</value></property>
-<property><name>pregelix.vertexInputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.NaiveAlgorithmForPathMergeInputFormat</value></property>
-<property><name>mapred.job.queue.name</name><value>default</value></property>
-<property><name>mapred.job.tracker.persist.jobstatus.active</name><value>false</value></property>
-<property><name>pregelix.incStateLength</name><value>true</value></property>
-<property><name>mapred.reduce.slowstart.completed.maps</name><value>0.05</value></property>
-<property><name>topology.script.number.args</name><value>100</value></property>
-<property><name>mapred.skip.map.max.skip.records</name><value>0</value></property>
-<property><name>fs.ftp.impl</name><value>org.apache.hadoop.fs.ftp.FTPFileSystem</value></property>
-<property><name>mapred.task.cache.levels</name><value>2</value></property>
-<property><name>mapred.job.tracker.handler.count</name><value>10</value></property>
-<property><name>io.serializations</name><value>org.apache.hadoop.io.serializer.WritableSerialization</value></property>
-<property><name>ipc.client.connect.max.retries</name><value>10</value></property>
-<property><name>mapred.min.split.size</name><value>0</value></property>
-<property><name>mapred.map.max.attempts</name><value>4</value></property>
-<property><name>jobclient.output.filter</name><value>FAILED</value></property>
-<property><name>ipc.client.tcpnodelay</name><value>false</value></property>
-<property><name>mapred.acls.enabled</name><value>false</value></property>
-</configuration>
\ No newline at end of file
diff --git a/genomix/genomix-pregelix/src/test/resources/jobs/P4ForMergeGraph.xml b/genomix/genomix-pregelix/src/test/resources/jobs/P4ForMergeGraph.xml
index 5ef1509..f20a863 100644
--- a/genomix/genomix-pregelix/src/test/resources/jobs/P4ForMergeGraph.xml
+++ b/genomix/genomix-pregelix/src/test/resources/jobs/P4ForMergeGraph.xml
@@ -58,7 +58,7 @@
 <property><name>mapred.job.tracker.persist.jobstatus.hours</name><value>0</value></property>
 <property><name>fs.s3.sleepTimeSeconds</name><value>10</value></property>
 <property><name>fs.default.name</name><value>file:///</value></property>
-<property><name>mapred.output.key.class</name><value>edu.uci.ics.genomix.type.PositionWritable</value></property>
+<property><name>mapred.output.key.class</name><value>edu.uci.ics.genomix.oldtype.PositionWritable</value></property>
 <property><name>tasktracker.http.threads</name><value>40</value></property>
 <property><name>mapred.tasktracker.taskmemorymanager.monitoring-interval</name><value>5000</value></property>
 <property><name>hadoop.rpc.socket.factory.class.default</name><value>org.apache.hadoop.net.StandardSocketFactory</value></property>
@@ -96,7 +96,7 @@
 <property><name>io.sort.mb</name><value>100</value></property>
 <property><name>mapred.local.dir</name><value>${hadoop.tmp.dir}/mapred/local</value></property>
 <property><name>io.sort.factor</name><value>10</value></property>
-<property><name>BasicPathMergeVertex.kmerSize</name><value>5</value></property>
+<property><name>BasicPathMergeVertex.kmerSize</name><value>3</value></property>
 <property><name>mapred.task.profile</name><value>false</value></property>
 <property><name>job.end.retry.interval</name><value>30000</value></property>
 <property><name>mapred.tasktracker.procfsbasedprocesstree.sleeptime-before-sigkill</name><value>5000</value></property>
@@ -117,12 +117,12 @@
 <property><name>mapred.line.input.format.linespermap</name><value>1</value></property>
 <property><name>job.end.retry.attempts</name><value>0</value></property>
 <property><name>ipc.client.idlethreshold</name><value>4000</value></property>
-<property><name>pregelix.vertexOutputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.DataCleanOutputFormat</value></property>
+<property><name>pregelix.vertexOutputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.GraphCleanOutputFormat</value></property>
 <property><name>mapred.reduce.copy.backoff</name><value>300</value></property>
 <property><name>mapred.map.tasks.speculative.execution</name><value>true</value></property>
 <property><name>mapred.inmem.merge.threshold</name><value>1000</value></property>
 <property><name>hadoop.logfile.size</name><value>10000000</value></property>
-<property><name>pregelix.vertexInputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.DataCleanInputFormat</value></property>
+<property><name>pregelix.vertexInputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.InitialGraphCleanInputFormat</value></property>
 <property><name>mapred.job.queue.name</name><value>default</value></property>
 <property><name>mapred.job.tracker.persist.jobstatus.active</name><value>false</value></property>
 <property><name>pregelix.incStateLength</name><value>true</value></property>
diff --git a/genomix/genomix-pregelix/src/test/resources/jobs/TipAddGraph.xml b/genomix/genomix-pregelix/src/test/resources/jobs/TipAddGraph.xml
deleted file mode 100644
index 00c857e..0000000
--- a/genomix/genomix-pregelix/src/test/resources/jobs/TipAddGraph.xml
+++ /dev/null
@@ -1,142 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" standalone="no"?><configuration>
-<property><name>mapred.tasktracker.dns.nameserver</name><value>default</value></property>
-<property><name>mapred.queue.default.acl-administer-jobs</name><value>*</value></property>
-<property><name>mapred.skip.map.auto.incr.proc.count</name><value>true</value></property>
-<property><name>mapred.jobtracker.instrumentation</name><value>org.apache.hadoop.mapred.JobTrackerMetricsInst</value></property>
-<property><name>mapred.skip.reduce.auto.incr.proc.count</name><value>true</value></property>
-<property><name>fs.hsftp.impl</name><value>org.apache.hadoop.hdfs.HsftpFileSystem</value></property>
-<property><name>mapred.submit.replication</name><value>10</value></property>
-<property><name>ipc.server.tcpnodelay</name><value>false</value></property>
-<property><name>fs.checkpoint.dir</name><value>${hadoop.tmp.dir}/dfs/namesecondary</value></property>
-<property><name>mapred.output.compression.type</name><value>RECORD</value></property>
-<property><name>mapred.job.shuffle.merge.percent</name><value>0.66</value></property>
-<property><name>mapred.child.java.opts</name><value>-Xmx200m</value></property>
-<property><name>mapred.queue.default.acl-submit-job</name><value>*</value></property>
-<property><name>keep.failed.task.files</name><value>false</value></property>
-<property><name>mapred.jobtracker.job.history.block.size</name><value>3145728</value></property>
-<property><name>mapred.output.value.class</name><value>edu.uci.ics.genomix.pregelix.io.VertexValueWritable</value></property>
-<property><name>io.bytes.per.checksum</name><value>512</value></property>
-<property><name>mapred.task.tracker.report.address</name><value>127.0.0.1:0</value></property>
-<property><name>hadoop.util.hash.type</name><value>murmur</value></property>
-<property><name>fs.hdfs.impl</name><value>org.apache.hadoop.hdfs.DistributedFileSystem</value></property>
-<property><name>fs.ramfs.impl</name><value>org.apache.hadoop.fs.InMemoryFileSystem</value></property>
-<property><name>mapred.jobtracker.restart.recover</name><value>false</value></property>
-<property><name>fs.hftp.impl</name><value>org.apache.hadoop.hdfs.HftpFileSystem</value></property>
-<property><name>fs.checkpoint.period</name><value>3600</value></property>
-<property><name>TipAddVertex.kmerSize</name><value>3</value></property>
-<property><name>mapred.child.tmp</name><value>./tmp</value></property>
-<property><name>mapred.local.dir.minspacekill</name><value>0</value></property>
-<property><name>map.sort.class</name><value>org.apache.hadoop.util.QuickSort</value></property>
-<property><name>hadoop.logfile.count</name><value>10</value></property>
-<property><name>ipc.client.connection.maxidletime</name><value>10000</value></property>
-<property><name>io.map.index.skip</name><value>0</value></property>
-<property><name>mapred.tasktracker.expiry.interval</name><value>600000</value></property>
-<property><name>mapred.output.compress</name><value>false</value></property>
-<property><name>io.seqfile.lazydecompress</name><value>true</value></property>
-<property><name>mapred.reduce.parallel.copies</name><value>5</value></property>
-<property><name>fs.checkpoint.size</name><value>67108864</value></property>
-<property><name>mapred.job.reduce.input.buffer.percent</name><value>0.0</value></property>
-<property><name>mapred.job.name</name><value>TipAddGraph</value></property>
-<property><name>local.cache.size</name><value>10737418240</value></property>
-<property><name>fs.s3n.impl</name><value>org.apache.hadoop.fs.s3native.NativeS3FileSystem</value></property>
-<property><name>mapred.userlog.limit.kb</name><value>0</value></property>
-<property><name>fs.file.impl</name><value>org.apache.hadoop.fs.LocalFileSystem</value></property>
-<property><name>mapred.task.tracker.http.address</name><value>0.0.0.0:50060</value></property>
-<property><name>mapred.task.timeout</name><value>600000</value></property>
-<property><name>fs.kfs.impl</name><value>org.apache.hadoop.fs.kfs.KosmosFileSystem</value></property>
-<property><name>mapred.max.tracker.blacklists</name><value>4</value></property>
-<property><name>fs.s3.buffer.dir</name><value>${hadoop.tmp.dir}/s3</value></property>
-<property><name>mapred.job.tracker.persist.jobstatus.dir</name><value>/jobtracker/jobsInfo</value></property>
-<property><name>ipc.client.kill.max</name><value>10</value></property>
-<property><name>mapred.tasktracker.instrumentation</name><value>org.apache.hadoop.mapred.TaskTrackerMetricsInst</value></property>
-<property><name>mapred.reduce.tasks.speculative.execution</name><value>true</value></property>
-<property><name>io.sort.record.percent</name><value>0.05</value></property>
-<property><name>hadoop.security.authorization</name><value>false</value></property>
-<property><name>mapred.max.tracker.failures</name><value>4</value></property>
-<property><name>mapred.jobtracker.taskScheduler</name><value>org.apache.hadoop.mapred.JobQueueTaskScheduler</value></property>
-<property><name>mapred.tasktracker.dns.interface</name><value>default</value></property>
-<property><name>mapred.map.tasks</name><value>2</value></property>
-<property><name>mapred.job.tracker.persist.jobstatus.hours</name><value>0</value></property>
-<property><name>fs.s3.sleepTimeSeconds</name><value>10</value></property>
-<property><name>fs.default.name</name><value>file:///</value></property>
-<property><name>mapred.output.key.class</name><value>edu.uci.ics.genomix.type.PositionWritable</value></property>
-<property><name>tasktracker.http.threads</name><value>40</value></property>
-<property><name>mapred.tasktracker.taskmemorymanager.monitoring-interval</name><value>5000</value></property>
-<property><name>hadoop.rpc.socket.factory.class.default</name><value>org.apache.hadoop.net.StandardSocketFactory</value></property>
-<property><name>mapred.reduce.tasks</name><value>1</value></property>
-<property><name>topology.node.switch.mapping.impl</name><value>org.apache.hadoop.net.ScriptBasedMapping</value></property>
-<property><name>pregelix.vertexClass</name><value>edu.uci.ics.genomix.pregelix.operator.tipremove.TipAddVertex</value></property>
-<property><name>mapred.skip.reduce.max.skip.groups</name><value>0</value></property>
-<property><name>io.file.buffer.size</name><value>4096</value></property>
-<property><name>mapred.jobtracker.maxtasks.per.job</name><value>-1</value></property>
-<property><name>mapred.tasktracker.indexcache.mb</name><value>10</value></property>
-<property><name>mapred.tasktracker.map.tasks.maximum</name><value>2</value></property>
-<property><name>fs.har.impl.disable.cache</name><value>true</value></property>
-<property><name>mapred.task.profile.maps</name><value>0-2</value></property>
-<property><name>hadoop.native.lib</name><value>true</value></property>
-<property><name>fs.s3.block.size</name><value>67108864</value></property>
-<property><name>mapred.job.reuse.jvm.num.tasks</name><value>1</value></property>
-<property><name>mapred.job.tracker.http.address</name><value>0.0.0.0:50030</value></property>
-<property><name>mapred.tasktracker.reduce.tasks.maximum</name><value>2</value></property>
-<property><name>io.compression.codecs</name><value>org.apache.hadoop.io.compress.DefaultCodec,org.apache.hadoop.io.compress.GzipCodec,org.apache.hadoop.io.compress.BZip2Codec</value></property>
-<property><name>mapred.job.shuffle.input.buffer.percent</name><value>0.70</value></property>
-<property><name>io.seqfile.compress.blocksize</name><value>1000000</value></property>
-<property><name>mapred.queue.names</name><value>default</value></property>
-<property><name>fs.har.impl</name><value>org.apache.hadoop.fs.HarFileSystem</value></property>
-<property><name>io.mapfile.bloom.error.rate</name><value>0.005</value></property>
-<property><name>mapred.job.tracker</name><value>local</value></property>
-<property><name>io.skip.checksum.errors</name><value>false</value></property>
-<property><name>mapred.reduce.max.attempts</name><value>4</value></property>
-<property><name>fs.s3.maxRetries</name><value>4</value></property>
-<property><name>ipc.server.listen.queue.size</name><value>128</value></property>
-<property><name>fs.trash.interval</name><value>0</value></property>
-<property><name>mapred.local.dir.minspacestart</name><value>0</value></property>
-<property><name>fs.s3.impl</name><value>org.apache.hadoop.fs.s3.S3FileSystem</value></property>
-<property><name>io.seqfile.sorter.recordlimit</name><value>1000000</value></property>
-<property><name>io.mapfile.bloom.size</name><value>1048576</value></property>
-<property><name>io.sort.mb</name><value>100</value></property>
-<property><name>mapred.local.dir</name><value>${hadoop.tmp.dir}/mapred/local</value></property>
-<property><name>io.sort.factor</name><value>10</value></property>
-<property><name>mapred.task.profile</name><value>false</value></property>
-<property><name>job.end.retry.interval</name><value>30000</value></property>
-<property><name>mapred.tasktracker.procfsbasedprocesstree.sleeptime-before-sigkill</name><value>5000</value></property>
-<property><name>mapred.jobtracker.completeuserjobs.maximum</name><value>100</value></property>
-<property><name>mapred.task.profile.reduces</name><value>0-2</value></property>
-<property><name>webinterface.private.actions</name><value>false</value></property>
-<property><name>hadoop.tmp.dir</name><value>/tmp/hadoop-${user.name}</value></property>
-<property><name>mapred.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
-<property><name>mapred.skip.attempts.to.start.skipping</name><value>2</value></property>
-<property><name>mapred.temp.dir</name><value>${hadoop.tmp.dir}/mapred/temp</value></property>
-<property><name>mapred.merge.recordsBeforeProgress</name><value>10000</value></property>
-<property><name>mapred.map.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
-<property><name>mapred.compress.map.output</name><value>false</value></property>
-<property><name>io.sort.spill.percent</name><value>0.80</value></property>
-<property><name>fs.checkpoint.edits.dir</name><value>${fs.checkpoint.dir}</value></property>
-<property><name>mapred.userlog.retain.hours</name><value>24</value></property>
-<property><name>mapred.system.dir</name><value>${hadoop.tmp.dir}/mapred/system</value></property>
-<property><name>mapred.line.input.format.linespermap</name><value>1</value></property>
-<property><name>job.end.retry.attempts</name><value>0</value></property>
-<property><name>ipc.client.idlethreshold</name><value>4000</value></property>
-<property><name>pregelix.vertexOutputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.DataCleanOutputFormat</value></property>
-<property><name>mapred.reduce.copy.backoff</name><value>300</value></property>
-<property><name>mapred.map.tasks.speculative.execution</name><value>true</value></property>
-<property><name>mapred.inmem.merge.threshold</name><value>1000</value></property>
-<property><name>hadoop.logfile.size</name><value>10000000</value></property>
-<property><name>pregelix.vertexInputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.NaiveAlgorithmForPathMergeInputFormat</value></property>
-<property><name>mapred.job.queue.name</name><value>default</value></property>
-<property><name>mapred.job.tracker.persist.jobstatus.active</name><value>false</value></property>
-<property><name>pregelix.incStateLength</name><value>true</value></property>
-<property><name>mapred.reduce.slowstart.completed.maps</name><value>0.05</value></property>
-<property><name>topology.script.number.args</name><value>100</value></property>
-<property><name>mapred.skip.map.max.skip.records</name><value>0</value></property>
-<property><name>fs.ftp.impl</name><value>org.apache.hadoop.fs.ftp.FTPFileSystem</value></property>
-<property><name>mapred.task.cache.levels</name><value>2</value></property>
-<property><name>mapred.job.tracker.handler.count</name><value>10</value></property>
-<property><name>io.serializations</name><value>org.apache.hadoop.io.serializer.WritableSerialization</value></property>
-<property><name>ipc.client.connect.max.retries</name><value>10</value></property>
-<property><name>mapred.min.split.size</name><value>0</value></property>
-<property><name>mapred.map.max.attempts</name><value>4</value></property>
-<property><name>jobclient.output.filter</name><value>FAILED</value></property>
-<property><name>ipc.client.tcpnodelay</name><value>false</value></property>
-<property><name>mapred.acls.enabled</name><value>false</value></property>
-</configuration>
\ No newline at end of file
diff --git a/genomix/genomix-pregelix/src/test/resources/jobs/TipRemoveGraph.xml b/genomix/genomix-pregelix/src/test/resources/jobs/TipRemoveGraph.xml
deleted file mode 100644
index 588cc9f..0000000
--- a/genomix/genomix-pregelix/src/test/resources/jobs/TipRemoveGraph.xml
+++ /dev/null
@@ -1,142 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" standalone="no"?><configuration>
-<property><name>mapred.tasktracker.dns.nameserver</name><value>default</value></property>
-<property><name>mapred.queue.default.acl-administer-jobs</name><value>*</value></property>
-<property><name>mapred.skip.map.auto.incr.proc.count</name><value>true</value></property>
-<property><name>mapred.jobtracker.instrumentation</name><value>org.apache.hadoop.mapred.JobTrackerMetricsInst</value></property>
-<property><name>mapred.skip.reduce.auto.incr.proc.count</name><value>true</value></property>
-<property><name>fs.hsftp.impl</name><value>org.apache.hadoop.hdfs.HsftpFileSystem</value></property>
-<property><name>mapred.submit.replication</name><value>10</value></property>
-<property><name>ipc.server.tcpnodelay</name><value>false</value></property>
-<property><name>fs.checkpoint.dir</name><value>${hadoop.tmp.dir}/dfs/namesecondary</value></property>
-<property><name>mapred.output.compression.type</name><value>RECORD</value></property>
-<property><name>mapred.job.shuffle.merge.percent</name><value>0.66</value></property>
-<property><name>mapred.child.java.opts</name><value>-Xmx200m</value></property>
-<property><name>mapred.queue.default.acl-submit-job</name><value>*</value></property>
-<property><name>keep.failed.task.files</name><value>false</value></property>
-<property><name>mapred.jobtracker.job.history.block.size</name><value>3145728</value></property>
-<property><name>mapred.output.value.class</name><value>edu.uci.ics.genomix.pregelix.io.VertexValueWritable</value></property>
-<property><name>io.bytes.per.checksum</name><value>512</value></property>
-<property><name>mapred.task.tracker.report.address</name><value>127.0.0.1:0</value></property>
-<property><name>hadoop.util.hash.type</name><value>murmur</value></property>
-<property><name>fs.hdfs.impl</name><value>org.apache.hadoop.hdfs.DistributedFileSystem</value></property>
-<property><name>fs.ramfs.impl</name><value>org.apache.hadoop.fs.InMemoryFileSystem</value></property>
-<property><name>mapred.jobtracker.restart.recover</name><value>false</value></property>
-<property><name>fs.hftp.impl</name><value>org.apache.hadoop.hdfs.HftpFileSystem</value></property>
-<property><name>fs.checkpoint.period</name><value>3600</value></property>
-<property><name>mapred.child.tmp</name><value>./tmp</value></property>
-<property><name>mapred.local.dir.minspacekill</name><value>0</value></property>
-<property><name>map.sort.class</name><value>org.apache.hadoop.util.QuickSort</value></property>
-<property><name>hadoop.logfile.count</name><value>10</value></property>
-<property><name>ipc.client.connection.maxidletime</name><value>10000</value></property>
-<property><name>io.map.index.skip</name><value>0</value></property>
-<property><name>mapred.tasktracker.expiry.interval</name><value>600000</value></property>
-<property><name>mapred.output.compress</name><value>false</value></property>
-<property><name>io.seqfile.lazydecompress</name><value>true</value></property>
-<property><name>mapred.reduce.parallel.copies</name><value>5</value></property>
-<property><name>fs.checkpoint.size</name><value>67108864</value></property>
-<property><name>mapred.job.reduce.input.buffer.percent</name><value>0.0</value></property>
-<property><name>mapred.job.name</name><value>TipRemoveGraph</value></property>
-<property><name>local.cache.size</name><value>10737418240</value></property>
-<property><name>fs.s3n.impl</name><value>org.apache.hadoop.fs.s3native.NativeS3FileSystem</value></property>
-<property><name>mapred.userlog.limit.kb</name><value>0</value></property>
-<property><name>fs.file.impl</name><value>org.apache.hadoop.fs.LocalFileSystem</value></property>
-<property><name>mapred.task.tracker.http.address</name><value>0.0.0.0:50060</value></property>
-<property><name>mapred.task.timeout</name><value>600000</value></property>
-<property><name>fs.kfs.impl</name><value>org.apache.hadoop.fs.kfs.KosmosFileSystem</value></property>
-<property><name>mapred.max.tracker.blacklists</name><value>4</value></property>
-<property><name>fs.s3.buffer.dir</name><value>${hadoop.tmp.dir}/s3</value></property>
-<property><name>mapred.job.tracker.persist.jobstatus.dir</name><value>/jobtracker/jobsInfo</value></property>
-<property><name>ipc.client.kill.max</name><value>10</value></property>
-<property><name>mapred.tasktracker.instrumentation</name><value>org.apache.hadoop.mapred.TaskTrackerMetricsInst</value></property>
-<property><name>mapred.reduce.tasks.speculative.execution</name><value>true</value></property>
-<property><name>io.sort.record.percent</name><value>0.05</value></property>
-<property><name>hadoop.security.authorization</name><value>false</value></property>
-<property><name>mapred.max.tracker.failures</name><value>4</value></property>
-<property><name>mapred.jobtracker.taskScheduler</name><value>org.apache.hadoop.mapred.JobQueueTaskScheduler</value></property>
-<property><name>mapred.tasktracker.dns.interface</name><value>default</value></property>
-<property><name>mapred.map.tasks</name><value>2</value></property>
-<property><name>mapred.job.tracker.persist.jobstatus.hours</name><value>0</value></property>
-<property><name>fs.s3.sleepTimeSeconds</name><value>10</value></property>
-<property><name>fs.default.name</name><value>file:///</value></property>
-<property><name>mapred.output.key.class</name><value>edu.uci.ics.genomix.type.PositionWritable</value></property>
-<property><name>tasktracker.http.threads</name><value>40</value></property>
-<property><name>mapred.tasktracker.taskmemorymanager.monitoring-interval</name><value>5000</value></property>
-<property><name>hadoop.rpc.socket.factory.class.default</name><value>org.apache.hadoop.net.StandardSocketFactory</value></property>
-<property><name>mapred.reduce.tasks</name><value>1</value></property>
-<property><name>topology.node.switch.mapping.impl</name><value>org.apache.hadoop.net.ScriptBasedMapping</value></property>
-<property><name>pregelix.vertexClass</name><value>edu.uci.ics.genomix.pregelix.operator.tipremove.TipRemoveVertex</value></property>
-<property><name>mapred.skip.reduce.max.skip.groups</name><value>0</value></property>
-<property><name>io.file.buffer.size</name><value>4096</value></property>
-<property><name>mapred.jobtracker.maxtasks.per.job</name><value>-1</value></property>
-<property><name>mapred.tasktracker.indexcache.mb</name><value>10</value></property>
-<property><name>mapred.tasktracker.map.tasks.maximum</name><value>2</value></property>
-<property><name>fs.har.impl.disable.cache</name><value>true</value></property>
-<property><name>mapred.task.profile.maps</name><value>0-2</value></property>
-<property><name>hadoop.native.lib</name><value>true</value></property>
-<property><name>fs.s3.block.size</name><value>67108864</value></property>
-<property><name>mapred.job.reuse.jvm.num.tasks</name><value>1</value></property>
-<property><name>mapred.job.tracker.http.address</name><value>0.0.0.0:50030</value></property>
-<property><name>mapred.tasktracker.reduce.tasks.maximum</name><value>2</value></property>
-<property><name>io.compression.codecs</name><value>org.apache.hadoop.io.compress.DefaultCodec,org.apache.hadoop.io.compress.GzipCodec,org.apache.hadoop.io.compress.BZip2Codec</value></property>
-<property><name>mapred.job.shuffle.input.buffer.percent</name><value>0.70</value></property>
-<property><name>io.seqfile.compress.blocksize</name><value>1000000</value></property>
-<property><name>mapred.queue.names</name><value>default</value></property>
-<property><name>fs.har.impl</name><value>org.apache.hadoop.fs.HarFileSystem</value></property>
-<property><name>io.mapfile.bloom.error.rate</name><value>0.005</value></property>
-<property><name>mapred.job.tracker</name><value>local</value></property>
-<property><name>io.skip.checksum.errors</name><value>false</value></property>
-<property><name>mapred.reduce.max.attempts</name><value>4</value></property>
-<property><name>fs.s3.maxRetries</name><value>4</value></property>
-<property><name>ipc.server.listen.queue.size</name><value>128</value></property>
-<property><name>fs.trash.interval</name><value>0</value></property>
-<property><name>mapred.local.dir.minspacestart</name><value>0</value></property>
-<property><name>fs.s3.impl</name><value>org.apache.hadoop.fs.s3.S3FileSystem</value></property>
-<property><name>io.seqfile.sorter.recordlimit</name><value>1000000</value></property>
-<property><name>io.mapfile.bloom.size</name><value>1048576</value></property>
-<property><name>io.sort.mb</name><value>100</value></property>
-<property><name>mapred.local.dir</name><value>${hadoop.tmp.dir}/mapred/local</value></property>
-<property><name>io.sort.factor</name><value>10</value></property>
-<property><name>BasicPathMergeVertex.kmerSize</name><value>5</value></property>
-<property><name>mapred.task.profile</name><value>false</value></property>
-<property><name>job.end.retry.interval</name><value>30000</value></property>
-<property><name>mapred.tasktracker.procfsbasedprocesstree.sleeptime-before-sigkill</name><value>5000</value></property>
-<property><name>mapred.jobtracker.completeuserjobs.maximum</name><value>100</value></property>
-<property><name>mapred.task.profile.reduces</name><value>0-2</value></property>
-<property><name>webinterface.private.actions</name><value>false</value></property>
-<property><name>hadoop.tmp.dir</name><value>/tmp/hadoop-${user.name}</value></property>
-<property><name>mapred.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
-<property><name>mapred.skip.attempts.to.start.skipping</name><value>2</value></property>
-<property><name>mapred.temp.dir</name><value>${hadoop.tmp.dir}/mapred/temp</value></property>
-<property><name>mapred.merge.recordsBeforeProgress</name><value>10000</value></property>
-<property><name>mapred.map.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
-<property><name>mapred.compress.map.output</name><value>false</value></property>
-<property><name>io.sort.spill.percent</name><value>0.80</value></property>
-<property><name>fs.checkpoint.edits.dir</name><value>${fs.checkpoint.dir}</value></property>
-<property><name>mapred.userlog.retain.hours</name><value>24</value></property>
-<property><name>mapred.system.dir</name><value>${hadoop.tmp.dir}/mapred/system</value></property>
-<property><name>mapred.line.input.format.linespermap</name><value>1</value></property>
-<property><name>job.end.retry.attempts</name><value>0</value></property>
-<property><name>ipc.client.idlethreshold</name><value>4000</value></property>
-<property><name>pregelix.vertexOutputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.DataCleanOutputFormat</value></property>
-<property><name>mapred.reduce.copy.backoff</name><value>300</value></property>
-<property><name>mapred.map.tasks.speculative.execution</name><value>true</value></property>
-<property><name>mapred.inmem.merge.threshold</name><value>1000</value></property>
-<property><name>hadoop.logfile.size</name><value>10000000</value></property>
-<property><name>pregelix.vertexInputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.NaiveAlgorithmForPathMergeInputFormat</value></property>
-<property><name>mapred.job.queue.name</name><value>default</value></property>
-<property><name>mapred.job.tracker.persist.jobstatus.active</name><value>false</value></property>
-<property><name>pregelix.incStateLength</name><value>true</value></property>
-<property><name>mapred.reduce.slowstart.completed.maps</name><value>0.05</value></property>
-<property><name>topology.script.number.args</name><value>100</value></property>
-<property><name>mapred.skip.map.max.skip.records</name><value>0</value></property>
-<property><name>fs.ftp.impl</name><value>org.apache.hadoop.fs.ftp.FTPFileSystem</value></property>
-<property><name>mapred.task.cache.levels</name><value>2</value></property>
-<property><name>mapred.job.tracker.handler.count</name><value>10</value></property>
-<property><name>io.serializations</name><value>org.apache.hadoop.io.serializer.WritableSerialization</value></property>
-<property><name>ipc.client.connect.max.retries</name><value>10</value></property>
-<property><name>mapred.min.split.size</name><value>0</value></property>
-<property><name>mapred.map.max.attempts</name><value>4</value></property>
-<property><name>jobclient.output.filter</name><value>FAILED</value></property>
-<property><name>ipc.client.tcpnodelay</name><value>false</value></property>
-<property><name>mapred.acls.enabled</name><value>false</value></property>
-</configuration>
\ No newline at end of file