X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=forester%2Fjava%2Fsrc%2Forg%2Fforester%2Fevoinference%2FTestPhylogenyReconstruction.java;h=6db64530ccc2813c4885660fbe5f775bd99ec9ec;hb=73979ccd545aa73fa45321f7590f6d234b979e5e;hp=281861cf870b6d145f4ed9ea72e96ac28f2edc1e;hpb=88af7c059e5f19aae3b5a43003961b8689788a4b;p=jalview.git diff --git a/forester/java/src/org/forester/evoinference/TestPhylogenyReconstruction.java b/forester/java/src/org/forester/evoinference/TestPhylogenyReconstruction.java index 281861c..6db6453 100644 --- a/forester/java/src/org/forester/evoinference/TestPhylogenyReconstruction.java +++ b/forester/java/src/org/forester/evoinference/TestPhylogenyReconstruction.java @@ -32,11 +32,13 @@ import java.io.FileInputStream; import java.io.StringWriter; import java.util.Date; import java.util.List; +import java.util.SortedSet; import org.forester.evoinference.distance.NeighborJoining; import org.forester.evoinference.distance.NeighborJoiningF; import org.forester.evoinference.distance.NeighborJoiningR; import org.forester.evoinference.distance.PairwiseDistanceCalculator; +import org.forester.evoinference.distance.S; import org.forester.evoinference.matrix.character.BasicCharacterStateMatrix; import org.forester.evoinference.matrix.character.CharacterStateMatrix; import org.forester.evoinference.matrix.character.CharacterStateMatrix.BinaryStates; @@ -74,6 +76,13 @@ public class TestPhylogenyReconstruction { else { System.out.println( " failed." ); } + System.out.println( "S" ); + if ( testS() ) { + System.out.println( " OK." ); + } + else { + System.out.println( " failed." ); + } System.out.println( "NJR" ); if ( testNeighborJoiningR() ) { System.out.println( " OK." ); @@ -81,7 +90,7 @@ public class TestPhylogenyReconstruction { else { System.out.println( " failed." ); } - //timeNeighborJoining(); + timeNeighborJoining(); } public static boolean test( final File test_dir ) { @@ -109,6 +118,12 @@ public class TestPhylogenyReconstruction { return false; } System.out.println( "OK." ); + System.out.print( " Datastructure S: " ); + if ( !testS() ) { + System.out.println( "failed." ); + return false; + } + System.out.println( "OK." ); System.out.print( " Neighbor Joining: " ); if ( !testNeighborJoining() ) { System.out.println( "failed." ); @@ -2055,8 +2070,10 @@ public class TestPhylogenyReconstruction { m.setRow( "1.52430 1.44650 0.59580 0.46310 0.00000 0.34840 0.30830", 4 ); m.setRow( "1.60430 1.43890 0.61790 0.50610 0.34840 0.00000 0.26920", 5 ); m.setRow( "1.59050 1.46290 0.55830 0.47100 0.30830 0.26920 0.00000", 6 ); - nj = NeighborJoining.createInstance( false, 6 ); + //NeighborJoiningR njr = NeighborJoiningR.createInstance( true, 6 ); + nj = NeighborJoining.createInstance( true, 6 ); final Phylogeny p2 = nj.execute( m ); + // Archaeopteryx.createApplication( p2 ); p2.reRoot( p2.getNode( "Bovine" ) ); if ( isUnequal( p2.getNode( "Chimp" ).getDistanceToParent(), 0.151675 ) ) { return false; @@ -2174,7 +2191,7 @@ public class TestPhylogenyReconstruction { m.setRow( "1.52430 1.44650 0.59580 0.46310 0.00000 0.34840 0.30830", 4 ); m.setRow( "1.60430 1.43890 0.61790 0.50610 0.34840 0.00000 0.26920", 5 ); m.setRow( "1.59050 1.46290 0.55830 0.47100 0.30830 0.26920 0.00000", 6 ); - njf = NeighborJoiningF.createInstance( false, 5 ); + njf = NeighborJoiningF.createInstance( true, 5 ); final Phylogeny p2f = njf.execute( m ); p2f.reRoot( p2f.getNode( "Bovine" ) ); if ( isUnequal( p2f.getNode( "Chimp" ).getDistanceToParent(), 0.15168 ) ) { @@ -2226,9 +2243,146 @@ public class TestPhylogenyReconstruction { return true; } + private static boolean testS() { + try { + final S s0 = new S(); + s0.initialize( 1 ); + s0.addPairing( 0, 1, 0 ); + s0.addPairing( 7, 8, 0 ); + s0.addPairing( 4, 55, 0 ); + s0.addPairing( 2, 3, 0 ); + s0.addPairing( 4, 5, 0 ); + s0.addPairing( 5, 6666, 0 ); + s0.addPairing( 5, 666, 0 ); + s0.addPairing( 5, 66, 0 ); + s0.addPairing( 5, 6, 0 ); + s0.addPairing( 6, 7, 0 ); + s0.addPairing( 3, 4, 0 ); + s0.addPairing( 1, 2, 0 ); + if ( s0.size() != 1 ) { + return false; + } + if ( s0.getS( 0 ).size() != 8 ) { + return false; + } + if ( s0.getValues( 0, 0 ).size() != 1 ) { + return false; + } + if ( s0.getValues( 1, 0 ).size() != 1 ) { + return false; + } + if ( s0.getValues( 2, 0 ).size() != 1 ) { + return false; + } + if ( s0.getValues( 3, 0 ).size() != 1 ) { + return false; + } + if ( s0.getValues( 4, 0 ).size() != 2 ) { + return false; + } + if ( s0.getValues( 5, 0 ).size() != 4 ) { + return false; + } + if ( s0.getValues( 6, 0 ).size() != 1 ) { + return false; + } + if ( s0.getValues( 7, 0 ).size() != 1 ) { + return false; + } + if ( !s0.getValues( 0, 0 ).contains( 1 ) ) { + return false; + } + if ( !s0.getValues( 5, 0 ).contains( 6 ) ) { + return false; + } + if ( !s0.getValues( 5, 0 ).contains( 66 ) ) { + return false; + } + if ( !s0.getValues( 5, 0 ).contains( 666 ) ) { + return false; + } + if ( !s0.getValues( 5, 0 ).contains( 6666 ) ) { + return false; + } + s0.removePairing( 5, 6666, 0 ); + if ( s0.getValues( 5, 0 ).contains( 6666 ) ) { + return false; + } + s0.removePairing( 5, 666, 0 ); + if ( s0.getValues( 5, 0 ).contains( 666 ) ) { + return false; + } + s0.removePairing( 5, 66, 0 ); + if ( s0.getValues( 5, 0 ).contains( 66 ) ) { + return false; + } + if ( s0.getValues( 5, 0 ).size() != 1 ) { + return false; + } + if ( s0.getS( 0 ).size() != 8 ) { + return false; + } + s0.removePairing( 5, 6, 0 ); + if ( s0.getS( 0 ).size() != 7 ) { + return false; + } + s0.addPairing( 5, 6, 0 ); + if ( s0.getS( 0 ).size() != 8 ) { + return false; + } + if ( s0.getValues( 5, 0 ).size() != 1 ) { + return false; + } + if ( !s0.getValues( 5, 0 ).contains( 6 ) ) { + return false; + } + s0.addPairing( 5, 403, 0 ); + if ( s0.getValues( 5, 0 ).size() != 2 ) { + return false; + } + if ( !s0.getValues( 5, 0 ).contains( 403 ) ) { + return false; + } + s0.addPairing( 693, 100, 0 ); + s0.addPairing( 693, 101, 0 ); + if ( s0.getValues( 693, 0 ).size() != 2 ) { + return false; + } + s0.addPairing( 2, 33, 0 ); + s0.addPairing( 2, 333, 0 ); + final SortedSet[] a = s0.toArray( 0 ); + if ( !a[ 0 ].contains( 1 ) ) { + return false; + } + if ( a[ 0 ].size() != 1 ) { + return false; + } + if ( !a[ 1 ].contains( 2 ) ) { + return false; + } + if ( a[ 1 ].size() != 1 ) { + return false; + } + if ( !a[ 2 ].contains( 3 ) ) { + return false; + } + if ( !a[ 2 ].contains( 33 ) ) { + return false; + } + if ( !a[ 2 ].contains( 333 ) ) { + return false; + } + } + catch ( final Exception e ) { + e.printStackTrace( System.out ); + return false; + } + return true; + } + private static boolean testNeighborJoiningR() { try { - NeighborJoiningR nj = NeighborJoiningR.createInstance(); + final NeighborJoiningR nj0 = NeighborJoiningR.createInstance(); final BasicSymmetricalDistanceMatrix m0 = new BasicSymmetricalDistanceMatrix( 4 ); m0.setIdentifier( 0, "A" ); m0.setIdentifier( 1, "B" ); @@ -2237,7 +2391,7 @@ public class TestPhylogenyReconstruction { m0.setRow( "5 ", 1 ); m0.setRow( "3 6 ", 2 ); m0.setRow( "7.5 10.5 5.5", 3 ); - final Phylogeny p0 = nj.execute( m0 ); + final Phylogeny p0 = nj0.execute( m0 ); p0.reRoot( p0.getNode( "D" ) ); if ( isUnequal( p0.getNode( "A" ).getDistanceToParent(), 1 ) ) { return false; @@ -2257,20 +2411,20 @@ public class TestPhylogenyReconstruction { if ( isUnequal( p0.getNode( "A" ).getParent().getParent().getDistanceToParent(), 2.5 ) ) { return false; } - BasicSymmetricalDistanceMatrix m = new BasicSymmetricalDistanceMatrix( 6 ); - m.setRow( "5", 1 ); - m.setRow( "4 7", 2 ); - m.setRow( "7 10 7", 3 ); - m.setRow( "6 9 6 5", 4 ); - m.setRow( "8 11 8 9 8", 5 ); - m.setIdentifier( 0, "A" ); - m.setIdentifier( 1, "B" ); - m.setIdentifier( 2, "C" ); - m.setIdentifier( 3, "D" ); - m.setIdentifier( 4, "E" ); - m.setIdentifier( 5, "F" ); - nj = NeighborJoiningR.createInstance(); - final Phylogeny p1 = nj.execute( m ); + final BasicSymmetricalDistanceMatrix m1 = new BasicSymmetricalDistanceMatrix( 6 ); + m1.setRow( "5", 1 ); + m1.setRow( "4 7", 2 ); + m1.setRow( "7 10 7", 3 ); + m1.setRow( "6 9 6 5", 4 ); + m1.setRow( "8 11 8 9 8", 5 ); + m1.setIdentifier( 0, "A" ); + m1.setIdentifier( 1, "B" ); + m1.setIdentifier( 2, "C" ); + m1.setIdentifier( 3, "D" ); + m1.setIdentifier( 4, "E" ); + m1.setIdentifier( 5, "F" ); + final NeighborJoiningR nj1 = NeighborJoiningR.createInstance(); + final Phylogeny p1 = nj1.execute( m1 ); p1.reRoot( p1.getNode( "F" ) ); if ( isUnequal( p1.getNode( "A" ).getDistanceToParent(), 1 ) ) { return false; @@ -2308,6 +2462,140 @@ public class TestPhylogenyReconstruction { if ( isUnequal( p1.getNode( "E" ).getParent().getDistanceToParent(), 1 ) ) { return false; } + final BasicSymmetricalDistanceMatrix m2 = new BasicSymmetricalDistanceMatrix( 7 ); + m2.setIdentifier( 0, "Bovine" ); + m2.setIdentifier( 1, "Mouse" ); + m2.setIdentifier( 2, "Gibbon" ); + m2.setIdentifier( 3, "Orang" ); + m2.setIdentifier( 4, "Gorilla" ); + m2.setIdentifier( 5, "Chimp" ); + m2.setIdentifier( 6, "Human" ); + m2.setRow( "0.00000 1.68660 1.71980 1.66060 1.52430 1.60430 1.59050", 0 ); + m2.setRow( "1.68660 0.00000 1.52320 1.48410 1.44650 1.43890 1.46290", 1 ); + m2.setRow( "1.71980 1.52320 0.00000 0.71150 0.59580 0.61790 0.55830", 2 ); + m2.setRow( "1.66060 1.48410 0.71150 0.00000 0.46310 0.50610 0.47100", 3 ); + m2.setRow( "1.52430 1.44650 0.59580 0.46310 0.00000 0.34840 0.30830", 4 ); + m2.setRow( "1.60430 1.43890 0.61790 0.50610 0.34840 0.00000 0.26920", 5 ); + m2.setRow( "1.59050 1.46290 0.55830 0.47100 0.30830 0.26920 0.00000", 6 ); + final NeighborJoiningR nj2 = NeighborJoiningR.createInstance( true, 6 ); + final Phylogeny p2 = nj2.execute( m2 ); + p2.reRoot( p2.getNode( "Bovine" ) ); + if ( isUnequal( p2.getNode( "Chimp" ).getDistanceToParent(), 0.151675 ) ) { + return false; + } + if ( isUnequal( p2.getNode( "Human" ).getDistanceToParent(), 0.117525 ) ) { + return false; + } + if ( isUnequal( p2.getNode( "Gorilla" ).getDistanceToParent(), 0.153931 ) ) { + return false; + } + if ( isUnequal( p2.getNode( "Orang" ).getDistanceToParent(), 0.284694 ) ) { + return false; + } + if ( isUnequal( p2.getNode( "Gibbon" ).getDistanceToParent(), 0.357931 ) ) { + return false; + } + if ( isUnequal( p2.getNode( "Mouse" ).getDistanceToParent(), 0.76891 ) ) { + return false; + } + if ( isUnequal( p2.getNode( "Bovine" ).getDistanceToParent(), 0.458845 ) ) { + return false; + } + if ( isUnequal( p2.getNode( "Chimp" ).getParent().getDistanceToParent(), 0.039819 ) ) { + return false; + } + if ( isUnequal( p2.getNode( "Human" ).getParent().getDistanceToParent(), 0.039819 ) ) { + return false; + } + if ( isUnequal( p2.getNode( "Chimp" ).getParent().getParent().getDistanceToParent(), 0.026956 ) ) { + return false; + } + if ( isUnequal( p2.getNode( "Chimp" ).getParent().getParent().getParent().getDistanceToParent(), 0.046481 ) ) { + return false; + } + if ( isUnequal( p2.getNode( "Chimp" ).getParent().getParent().getParent().getParent().getDistanceToParent(), + 0.420269 ) ) { + return false; + } + if ( isUnequal( p2.getNode( "Chimp" ).getParent().getParent().getParent().getParent().getParent() + .getDistanceToParent(), 0.458845 ) ) { + return false; + } + // + final BasicSymmetricalDistanceMatrix m3 = new BasicSymmetricalDistanceMatrix( 20 ); + m3.setIdentifier( 0, "F_MOUSE" ); + m3.setIdentifier( 1, "11_RAT" ); + m3.setIdentifier( 2, "A_CAVPO" ); + m3.setIdentifier( 3, "D_HUMAN" ); + m3.setIdentifier( 4, "E_HUMAN" ); + m3.setIdentifier( 5, "F_HUMAN" ); + m3.setIdentifier( 6, "C_HUMAN" ); + m3.setIdentifier( 7, "6_FELCA" ); + m3.setIdentifier( 8, "D_MOUSE" ); + m3.setIdentifier( 9, "E_MOUSE" ); + m3.setIdentifier( 10, "E_RAT " ); + m3.setIdentifier( 11, "C_MOUSE" ); + m3.setIdentifier( 12, "10_RAT" ); + m3.setIdentifier( 13, "3_TAEGU" ); + m3.setIdentifier( 14, "2_SACKO" ); + m3.setIdentifier( 15, "2_PANTR" ); + m3.setIdentifier( 16, "3_CANFA" ); + m3.setIdentifier( 17, "9_HUMAN" ); + m3.setIdentifier( 18, "A_HUMAN" ); + m3.setIdentifier( 19, "B_HUMAN" ); + m3.setRow( "0.000000 0.000010 0.020875 0.010376 0.010376 0.010376 0.010376 0.010368 0.000010 0.000010 0.000010 0.000010 0.000010 0.087165 0.743570 0.010376 0.010376 0.010376 0.010376 0.010376 ", + 0 ); + m3.setRow( "0.000010 0.000000 0.020875 0.010376 0.010376 0.010376 0.010376 0.010368 0.000010 0.000010 0.000010 0.000010 0.000010 0.087165 0.743570 0.010376 0.010376 0.010376 0.010376 0.010376", + 1 ); + m3.setRow( "0.020875 0.020875 0.000000 0.031503 0.031503 0.031503 0.031503 0.031477 0.020875 0.020875 0.020875 0.020875 0.020875 0.096983 0.768150 0.031503 0.031503 0.031503 0.031503 0.031503", + 2 ); + m3.setRow( "0.010376 0.010376 0.031503 0.000000 0.000010 0.000010 0.000010 0.010375 0.010376 0.010376 0.010376 0.010376 0.010376 0.098678 0.741282 0.000010 0.000010 0.000010 0.000010 0.000010", + 3 ); + m3.setRow( "0.010376 0.010376 0.031503 0.000010 0.000000 0.000010 0.000010 0.010375 0.010376 0.010376 0.010376 0.010376 0.010376 0.098678 0.741282 0.000010 0.000010 0.000010 0.000010 0.000010", + 4 ); + m3.setRow( "0.010376 0.010376 0.031503 0.000010 0.000010 0.000000 0.000010 0.010375 0.010376 0.010376 0.010376 0.010376 0.010376 0.098678 0.741282 0.000010 0.000010 0.000010 0.000010 0.000010", + 5 ); + m3.setRow( "0.010376 0.010376 0.031503 0.000010 0.000010 0.000010 0.000000 0.010375 0.010376 0.010376 0.010376 0.010376 0.010376 0.098678 0.741282 0.000010 0.000010 0.000010 0.000010 0.000010", + 6 ); + m3.setRow( "0.010368 0.010368 0.031477 0.010375 0.010375 0.010375 0.010375 0.000000 0.010368 0.010368 0.010368 0.010368 0.010368 0.098591 0.745047 0.010375 0.010375 0.010375 0.010375 0.010375", + 7 ); + m3.setRow( "0.000010 0.000010 0.020875 0.010376 0.010376 0.010376 0.010376 0.010368 0.000000 0.000010 0.000010 0.000010 0.000010 0.087165 0.743570 0.010376 0.010376 0.010376 0.010376 0.010376", + 8 ); + m3.setRow( "0.000010 0.000010 0.020875 0.010376 0.010376 0.010376 0.010376 0.010368 0.000010 0.000000 0.000010 0.000010 0.000010 0.087165 0.743570 0.010376 0.010376 0.010376 0.010376 0.010376", + 9 ); + m3.setRow( "0.000010 0.000010 0.020875 0.010376 0.010376 0.010376 0.010376 0.010368 0.000010 0.000010 0.000000 0.000010 0.000010 0.087165 0.743570 0.010376 0.010376 0.010376 0.010376 0.010376", + 10 ); + m3.setRow( "0.000010 0.000010 0.020875 0.010376 0.010376 0.010376 0.010376 0.010368 0.000010 0.000010 0.000010 0.000000 0.000010 0.087165 0.743570 0.010376 0.010376 0.010376 0.010376 0.010376", + 11 ); + m3.setRow( "0.000010 0.000010 0.020875 0.010376 0.010376 0.010376 0.010376 0.010368 0.000010 0.000010 0.000010 0.000010 0.000000 0.087165 0.743570 0.010376 0.010376 0.010376 0.010376 0.010376", + 12 ); + m3.setRow( "0.087165 0.087165 0.096983 0.098678 0.098678 0.098678 0.098678 0.098591 0.087165 0.087165 0.087165 0.087165 0.087165 0.000000 0.720387 0.098678 0.098678 0.098678 0.098678 0.098678", + 13 ); + m3.setRow( "0.743570 0.743570 0.768150 0.741282 0.741282 0.741282 0.741282 0.745047 0.743570 0.743570 0.743570 0.743570 0.743570 0.720387 0.000000 0.741282 0.741282 0.741282 0.741282 0.741282", + 14 ); + m3.setRow( "0.010376 0.010376 0.031503 0.000010 0.000010 0.000010 0.000010 0.010375 0.010376 0.010376 0.010376 0.010376 0.010376 0.098678 0.741282 0.000000 0.000010 0.000010 0.000010 0.000010", + 15 ); + m3.setRow( "0.010376 0.010376 0.031503 0.000010 0.000010 0.000010 0.000010 0.010375 0.010376 0.010376 0.010376 0.010376 0.010376 0.098678 0.741282 0.000010 0.000000 0.000010 0.000010 0.000010", + 16 ); + m3.setRow( "0.010376 0.010376 0.031503 0.000010 0.000010 0.000010 0.000010 0.010375 0.010376 0.010376 0.010376 0.010376 0.010376 0.098678 0.741282 0.000010 0.000010 0.000000 0.000010 0.000010", + 17 ); + m3.setRow( "0.010376 0.010376 0.031503 0.000010 0.000010 0.000010 0.000010 0.010375 0.010376 0.010376 0.010376 0.010376 0.010376 0.098678 0.741282 0.000010 0.000010 0.000010 0.000000 0.000010", + 18 ); + m3.setRow( "0.010376 0.010376 0.031503 0.000010 0.000010 0.000010 0.000010 0.010375 0.010376 0.010376 0.010376 0.010376 0.010376 0.098678 0.741282 0.000010 0.000010 0.000010 0.000010 0.000000", + 19 ); + final NeighborJoiningR nj3 = NeighborJoiningR.createInstance( false, 6 ); + final Phylogeny p3 = nj3.execute( m3 ); + //Archaeopteryx.createApplication( p3 ); + //// + final int size = 100; + for( int n = 0; n <= 100; ++n ) { + final NeighborJoiningR njn = NeighborJoiningR.createInstance( false, 6 ); + final BasicSymmetricalDistanceMatrix mt = new BasicSymmetricalDistanceMatrix( size ); + mt.randomize( new Date().getTime() ); + final long start_time = new Date().getTime(); + njn.execute( mt ); + System.out.println( "Size: " + size + " -> " + ( new Date().getTime() - start_time ) + "ms" ); + } } catch ( final Exception e ) { e.printStackTrace( System.out ); @@ -2677,6 +2965,15 @@ public class TestPhylogenyReconstruction { } private static void timeNeighborJoining() { + final NeighborJoiningR njr = NeighborJoiningR.createInstance(); + for( int n = 3; n <= 9; ++n ) { + final int x = ( int ) Math.pow( 2, n ); + final BasicSymmetricalDistanceMatrix mt = new BasicSymmetricalDistanceMatrix( x ); + mt.randomize( new Date().getTime() ); + final long start_time = new Date().getTime(); + njr.execute( mt ); + System.out.println( "Size: " + x + " -> " + ( new Date().getTime() - start_time ) + "ms" ); + } final NeighborJoiningF njf = NeighborJoiningF.createInstance(); for( int n = 3; n <= 9; ++n ) { final int x = ( int ) Math.pow( 2, n );