import java.util.Arrays;
import java.util.Collections;
import java.util.Comparator;
+import java.util.HashMap;
import java.util.HashSet;
import java.util.Iterator;
import java.util.List;
public class PhylogenyMethods {
- private static PhylogenyMethods _instance = null;
-
- private PhylogenyNode _farthest_1 = null;
- private PhylogenyNode _farthest_2 = null;
+ private static PhylogenyMethods _instance = null;
+ private PhylogenyNode _farthest_1 = null;
+ private PhylogenyNode _farthest_2 = null;
private PhylogenyMethods() {
// Hidden constructor.
}
-
-
-
-
/**
* Calculates the distance between PhylogenyNodes node1 and node2.
*
* @return distance between node1 and node2
*/
public double calculateDistance( final PhylogenyNode node1, final PhylogenyNode node2 ) {
- final PhylogenyNode lca = obtainLCA( node1, node2 );
+ final PhylogenyNode lca = calculateLCA( node1, node2 );
final PhylogenyNode n1 = node1;
final PhylogenyNode n2 = node2;
return ( PhylogenyMethods.getDistance( n1, lca ) + PhylogenyMethods.getDistance( n2, lca ) );
return farthest_d;
}
- final public static Event getEventAtLCA( PhylogenyNode n1,
- PhylogenyNode n2 ) {
- return obtainLCA( n1, n2 ).getNodeData().getEvent();
+ final public static Event getEventAtLCA( final PhylogenyNode n1, final PhylogenyNode n2 ) {
+ return calculateLCA( n1, n2 ).getNodeData().getEvent();
}
-
-
-
+
@Override
public Object clone() throws CloneNotSupportedException {
throw new CloneNotSupportedException();
return _farthest_2;
}
- final public static void deleteNonOrthologousExternalNodes( final Phylogeny phy,
- final PhylogenyNode n) {
+ final public static void deleteNonOrthologousExternalNodes( final Phylogeny phy, final PhylogenyNode n ) {
if ( n.isInternal() ) {
throw new IllegalArgumentException( "node is not external" );
}
-
final ArrayList<PhylogenyNode> to_delete = new ArrayList<PhylogenyNode>();
- for ( PhylogenyNodeIterator it = phy.iteratorExternalForward(); it.hasNext(); ) {
+ for( final PhylogenyNodeIterator it = phy.iteratorExternalForward(); it.hasNext(); ) {
final PhylogenyNode i = it.next();
if ( !PhylogenyMethods.getEventAtLCA( n, i ).isSpeciation() ) {
- to_delete.add( i );
+ to_delete.add( i );
}
}
- for( PhylogenyNode d : to_delete ) {
+ for( final PhylogenyNode d : to_delete ) {
phy.deleteSubtree( d, true );
}
phy.clearHashIdToNodeMap();
phy.externalNodesHaveChanged();
-
}
-
-
-
+
/**
* Returns the LCA of PhylogenyNodes node1 and node2.
*
* @param node2
* @return LCA of node1 and node2
*/
- public final static PhylogenyNode obtainLCA( final PhylogenyNode node1, final PhylogenyNode node2 ) {
- final HashSet<Integer> ids_set = new HashSet<Integer>();
- PhylogenyNode n1 = node1;
- PhylogenyNode n2 = node2;
- ids_set.add( n1.getId() );
- while ( !n1.isRoot() ) {
- n1 = n1.getParent();
- ids_set.add( n1.getId() );
+ public final static PhylogenyNode calculateLCA( PhylogenyNode node1, PhylogenyNode node2 ) {
+ if ( node1 == node2 ) {
+ return node1;
+ }
+ if ( ( node1.getParent() == node2.getParent() ) ) {
+ return node1.getParent();
}
- while ( !ids_set.contains( n2.getId() ) && !n2.isRoot() ) {
- n2 = n2.getParent();
+ int depth1 = node1.calculateDepth();
+ int depth2 = node2.calculateDepth();
+ while ( ( depth1 > -1 ) && ( depth2 > -1 ) ) {
+ if ( depth1 > depth2 ) {
+ node1 = node1.getParent();
+ depth1--;
+ }
+ else if ( depth2 > depth1 ) {
+ node2 = node2.getParent();
+ depth2--;
+ }
+ else {
+ if ( node1 == node2 ) {
+ return node1;
+ }
+ node1 = node1.getParent();
+ node2 = node2.getParent();
+ depth1--;
+ depth2--;
+ }
+ }
+ throw new IllegalArgumentException( "illegal attempt to calculate LCA of two nodes which do not share a common root" );
+ }
+
+ public static final void preOrderReId( final Phylogeny phy ) {
+ if ( phy.isEmpty() ) {
+ return;
}
- if ( !ids_set.contains( n2.getId() ) ) {
- throw new IllegalArgumentException( "attempt to get LCA of two nodes which do not share a common root" );
+ phy.setIdToNodeMap( null );
+ int i = PhylogenyNode.getNodeCount();
+ for( final PhylogenyNodeIterator it = phy.iteratorPreorder(); it.hasNext(); ) {
+ it.next().setId( i++ );
}
- return n2;
+ PhylogenyNode.setNodeCount( i );
+ }
+
+ /**
+ * Returns the LCA of PhylogenyNodes node1 and node2.
+ * Precondition: ids are in pre-order (or level-order).
+ *
+ *
+ * @param node1
+ * @param node2
+ * @return LCA of node1 and node2
+ */
+ public final static PhylogenyNode calculateLCAonTreeWithIdsInPreOrder( PhylogenyNode node1, PhylogenyNode node2 ) {
+ while ( node1 != node2 ) {
+ if ( node1.getId() > node2.getId() ) {
+ node1 = node1.getParent();
+ }
+ else {
+ node2 = node2.getParent();
+ }
+ }
+ return node1;
}
/**
* of this Phylogeny, null if this Phylogeny is empty or if n is
* internal
*/
- public List<PhylogenyNode> getOrthologousNodes( final Phylogeny phy, final PhylogenyNode node ) {
+ public final static List<PhylogenyNode> getOrthologousNodes( final Phylogeny phy, final PhylogenyNode node ) {
final List<PhylogenyNode> nodes = new ArrayList<PhylogenyNode>();
+ PhylogenyMethods.preOrderReId( phy );
final PhylogenyNodeIterator it = phy.iteratorExternalForward();
while ( it.hasNext() ) {
final PhylogenyNode temp_node = it.next();
- if ( ( temp_node != node ) && isAreOrthologous( node, temp_node ) ) {
+ if ( ( temp_node != node ) && !calculateLCAonTreeWithIdsInPreOrder( node, temp_node ).isDuplication() ) {
nodes.add( temp_node );
}
}
return nodes;
}
- public boolean isAreOrthologous( final PhylogenyNode node1, final PhylogenyNode node2 ) {
- return !obtainLCA( node1, node2 ).isDuplication();
+ public static final HashMap<String, PhylogenyNode> createNameToExtNodeMap( final Phylogeny phy ) {
+ final HashMap<String, PhylogenyNode> nodes = new HashMap<String, PhylogenyNode>();
+ for( final PhylogenyNodeIterator iter = phy.iteratorExternalForward(); iter.hasNext(); ) {
+ final PhylogenyNode n = iter.next();
+ nodes.put( n.getName(), n );
+ }
+ return nodes;
}
public final static Phylogeny[] readPhylogenies( final PhylogenyParser parser, final File file ) throws IOException {
return PhylogenyDataUtil.BRANCH_LENGTH_DEFAULT;
}
- // Helper for getUltraParalogousNodes( PhylogenyNode ).
- public static boolean areAllChildrenDuplications( final PhylogenyNode n ) {
+ public final static boolean isAllDecendentsAreDuplications( final PhylogenyNode n ) {
if ( n.isExternal() ) {
- return false;
+ return true;
}
else {
if ( n.isDuplication() ) {
- //FIXME test me!
for( final PhylogenyNode desc : n.getDescendants() ) {
- if ( !areAllChildrenDuplications( desc ) ) {
+ if ( !isAllDecendentsAreDuplications( desc ) ) {
return false;
}
}
}
}
- public static int calculateDepth( final PhylogenyNode node ) {
- PhylogenyNode n = node;
- int steps = 0;
- while ( !n.isRoot() ) {
- steps++;
- n = n.getParent();
- }
- return steps;
- }
-
- public static double calculateDistanceToRoot( final PhylogenyNode node ) {
- PhylogenyNode n = node;
- double d = 0.0;
- while ( !n.isRoot() ) {
- if ( n.getDistanceToParent() > 0.0 ) {
- d += n.getDistanceToParent();
- }
- n = n.getParent();
- }
- return d;
- }
-
public static short calculateMaxBranchesToLeaf( final PhylogenyNode node ) {
if ( node.isExternal() ) {
return 0;
int max = 0;
for( final PhylogenyNodeIterator iter = phy.iteratorExternalForward(); iter.hasNext(); ) {
final PhylogenyNode node = iter.next();
- final int steps = calculateDepth( node );
+ final int steps = node.calculateDepth();
if ( steps > max ) {
max = steps;
}
double max = 0.0;
for( final PhylogenyNodeIterator iter = phy.iteratorExternalForward(); iter.hasNext(); ) {
final PhylogenyNode node = iter.next();
- final double d = calculateDistanceToRoot( node );
+ final double d = node.calculateDistanceToRoot();
if ( d > max ) {
max = d;
}
public static void deleteExternalNodesNegativeSelection( final String[] node_names_to_delete, final Phylogeny p )
throws IllegalArgumentException {
- for( int i = 0; i < node_names_to_delete.length; ++i ) {
- if ( ForesterUtil.isEmpty( node_names_to_delete[ i ] ) ) {
+ for( final String element : node_names_to_delete ) {
+ if ( ForesterUtil.isEmpty( element ) ) {
continue;
}
List<PhylogenyNode> nodes = null;
- nodes = p.getNodes( node_names_to_delete[ i ] );
+ nodes = p.getNodes( element );
final Iterator<PhylogenyNode> it = nodes.iterator();
while ( it.hasNext() ) {
final PhylogenyNode n = it.next();
if ( !n.isExternal() ) {
- throw new IllegalArgumentException( "attempt to delete non-external node \""
- + node_names_to_delete[ i ] + "\"" );
+ throw new IllegalArgumentException( "attempt to delete non-external node \"" + element + "\"" );
}
p.deleteSubtree( n, true );
}
* @param n
* external PhylogenyNode whose strictly speciation related Nodes
* are to be returned
- * @return Vector of references to all strictly speciation related Nodes of
+ * @return References to all strictly speciation related Nodes of
* PhylogenyNode n of this Phylogeny, null if this Phylogeny is
* empty or if n is internal
*/
public static List<PhylogenyNode> getSuperOrthologousNodes( final PhylogenyNode n ) {
// FIXME
- PhylogenyNode node = n, deepest = null;
+ PhylogenyNode node = n;
+ PhylogenyNode deepest = null;
final List<PhylogenyNode> v = new ArrayList<PhylogenyNode>();
if ( !node.isExternal() ) {
return null;
// FIXME test me
PhylogenyNode node = n;
if ( !node.isExternal() ) {
- return null;
+ throw new IllegalArgumentException( "attempt to get ultra-paralogous nodes of internal node" );
}
- while ( !node.isRoot() && node.getParent().isDuplication() && areAllChildrenDuplications( node.getParent() ) ) {
+ while ( !node.isRoot() && node.getParent().isDuplication() && isAllDecendentsAreDuplications( node.getParent() ) ) {
node = node.getParent();
}
final List<PhylogenyNode> nodes = node.getAllExternalDescendants();
public static List<PhylogenyNode> searchData( final String query,
final Phylogeny phy,
final boolean case_sensitive,
- final boolean partial ) {
+ final boolean partial,
+ final boolean search_domains ) {
final List<PhylogenyNode> nodes = new ArrayList<PhylogenyNode>();
if ( phy.isEmpty() || ( query == null ) ) {
return nodes;
partial ) ) {
match = true;
}
- if ( !match && node.getNodeData().isHasSequence()
+ if ( search_domains && !match && node.getNodeData().isHasSequence()
&& ( node.getNodeData().getSequence().getDomainArchitecture() != null ) ) {
final DomainArchitecture da = node.getNodeData().getSequence().getDomainArchitecture();
I: for( int i = 0; i < da.getNumberOfDomains(); ++i ) {
public static List<PhylogenyNode> searchDataLogicalAnd( final String[] queries,
final Phylogeny phy,
final boolean case_sensitive,
- final boolean partial ) {
+ final boolean partial,
+ final boolean search_domains ) {
final List<PhylogenyNode> nodes = new ArrayList<PhylogenyNode>();
if ( phy.isEmpty() || ( queries == null ) || ( queries.length < 1 ) ) {
return nodes;
partial ) ) {
match = true;
}
- if ( !match && node.getNodeData().isHasSequence()
+ if ( search_domains && !match && node.getNodeData().isHasSequence()
&& ( node.getNodeData().getSequence().getDomainArchitecture() != null ) ) {
final DomainArchitecture da = node.getNodeData().getSequence().getDomainArchitecture();
I: for( int i = 0; i < da.getNumberOfDomains(); ++i ) {
break I;
}
}
- // final String[] bcp_ary = node.getNodeData().getBinaryCharacters()
- // .getPresentCharactersAsStringArray();
- // I: for( final String bc : bcp_ary ) {
- // if ( match( bc, query, case_sensitive, partial ) ) {
- // match = true;
- // break I;
- // }
- // }
- // final String[] bcg_ary = node.getNodeData().getBinaryCharacters()
- // .getGainedCharactersAsStringArray();
- // I: for( final String bc : bcg_ary ) {
- // if ( match( bc, query, case_sensitive, partial ) ) {
- // match = true;
- // break I;
- // }
- // }
}
if ( !match ) {
all_matched = false;
*/
public static int taxonomyBasedDeletionOfExternalNodes( final Phylogeny reference, final Phylogeny to_be_stripped ) {
final Set<String> ref_ext_taxo = new HashSet<String>();
- final ArrayList<PhylogenyNode> nodes_to_delete = new ArrayList<PhylogenyNode>();
for( final PhylogenyNodeIterator it = reference.iteratorExternalForward(); it.hasNext(); ) {
- ref_ext_taxo.add( getSpecies( it.next() ) );
+ final PhylogenyNode n = it.next();
+ if ( !n.getNodeData().isHasTaxonomy() ) {
+ throw new IllegalArgumentException( "no taxonomic data in node: " + n );
+ }
+ // ref_ext_taxo.add( getSpecies( n ) );
+ if ( !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getScientificName() ) ) {
+ ref_ext_taxo.add( n.getNodeData().getTaxonomy().getScientificName() );
+ }
+ if ( !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getTaxonomyCode() ) ) {
+ ref_ext_taxo.add( n.getNodeData().getTaxonomy().getTaxonomyCode() );
+ }
}
+ final ArrayList<PhylogenyNode> nodes_to_delete = new ArrayList<PhylogenyNode>();
for( final PhylogenyNodeIterator it = to_be_stripped.iteratorExternalForward(); it.hasNext(); ) {
final PhylogenyNode n = it.next();
- if ( !ref_ext_taxo.contains( getSpecies( n ) ) ) {
+ if ( !n.getNodeData().isHasTaxonomy() ) {
+ nodes_to_delete.add( n );
+ }
+ else if ( !( ref_ext_taxo.contains( n.getNodeData().getTaxonomy().getScientificName() ) )
+ && !( ref_ext_taxo.contains( n.getNodeData().getTaxonomy().getTaxonomyCode() ) ) ) {
nodes_to_delete.add( n );
}
}