forester_applications/src/org/forester/applications/genome_counts_for_once_appearing_dcs.java

   1
   2 package org.forester.applications;
   3
   4 // $Id:
   5 // FORESTER -- software libraries and applications
   6 // for evolutionary biology research and applications.
   7 //
   8 // Copyright (C) 2008-2011 Christian M. Zmasek
   9 // Copyright (C) 2008-2011 Burnham Institute for Medical Research
  10 // All rights reserved
  11 //
  12 // This library is free software; you can redistribute it and/or
  13 // modify it under the terms of the GNU Lesser General Public
  14 // License as published by the Free Software Foundation; either
  15 // version 2.1 of the License, or (at your option) any later version.
  16 //
  17 // This library is distributed in the hope that it will be useful,
  18 // but WITHOUT ANY WARRANTY; without even the implied warranty of
  19 // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
  20 // Lesser General Public License for more details.
  21 //
  22 // You should have received a copy of the GNU Lesser General Public
  23 // License along with this library; if not, write to the Free Software
  24 // Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA
  25 //
  26 // Contact: phylosoft @ gmail . com
  27 // WWW: www.phylosoft.org/forester
  28 // javac -cp ~/SOFTWARE_DEV/ECLIPSE_WORKSPACE/forester/java/forester.jar
  29 // ~/SOFTWARE_DEV/ECLIPSE_WORKSPACE/forester_applications/src/org/forester/applications/genome_counts_for_once_appearing_dcs.java
  30 // java -Xmx2048m -cp
  31 // /home/czmasek/SOFTWARE_DEV/ECLIPSE_WORKSPACE/forester_applications/src/:/home/czmasek/SOFTWARE_DEV/ECLIPSE_WORKSPACE/forester/java/forester.jar
  32 // org.forester.applications.genome_counts_for_once_appearing_dcs
  33 import java.io.File;
  34 import java.util.HashMap;
  35 import java.util.List;
  36 import java.util.Map;
  37 import java.util.Set;
  38 import java.util.SortedSet;
  39 import java.util.TreeSet;
  40
  41 import org.forester.phylogeny.Phylogeny;
  42 import org.forester.phylogeny.PhylogenyNode;
  43 import org.forester.phylogeny.factories.ParserBasedPhylogenyFactory;
  44 import org.forester.phylogeny.factories.PhylogenyFactory;
  45 import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
  46 import org.forester.util.BasicDescriptiveStatistics;
  47 import org.forester.util.DescriptiveStatistics;
  48
  49 public class genome_counts_for_once_appearing_dcs {
  50
  51     public static void main( final String args[] ) {
  52         if ( args.length != 1 ) {
  53             System.err.println();
  54             System.err.println( "genome_counts_for_once_appearing_dcs: wrong number of arguments" );
  55             System.err.println( "Usage: \"genome_counts_for_once_appearing_dcs <intree>" );
  56             System.err.println();
  57             System.exit( -1 );
  58         }
  59         final File infile = new File( args[ 0 ] );
  60         Phylogeny phy = null;
  61         try {
  62             final PhylogenyFactory factory = ParserBasedPhylogenyFactory.getInstance();
  63             phy = factory.create( infile, org.forester.io.parsers.util.ParserUtils
  64                                   .createParserDependingOnFileType( infile, true ) )[ 0 ];
  65         }
  66         catch ( final Exception e ) {
  67             System.err.println( e + "\nCould not read " + infile + "\n" );
  68             System.exit( -1 );
  69         }
  70         final SortedSet<String> all_dcs = getAllExternalPresentAndGainedCharacters( phy.getRoot() );
  71         final SortedSet<String> appearing_once_dcs = new TreeSet<String>();
  72         System.out.println( "All DCs: " + all_dcs.size() );
  73         for( final String dc : all_dcs ) {
  74             int reappearing_count = 0;
  75             for( final PhylogenyNodeIterator it = phy.iteratorPreorder(); it.hasNext(); ) {
  76                 final PhylogenyNode n = it.next();
  77                 SortedSet<String> n_gained_dcs = null;
  78                 if ( n.isRoot() ) {
  79                     n_gained_dcs = n.getNodeData().getBinaryCharacters().getPresentCharacters();
  80                 }
  81                 else {
  82                     n_gained_dcs = n.getNodeData().getBinaryCharacters().getGainedCharacters();
  83                 }
  84                 if ( n_gained_dcs.contains( dc ) ) {
  85                     reappearing_count++;
  86                 }
  87             }
  88             if ( reappearing_count < 1 ) {
  89                 System.out.println( "error: " + dc );
  90                 System.exit( -1 );
  91             }
  92             if ( reappearing_count == 1 ) {
  93                 appearing_once_dcs.add( dc );
  94             }
  95         }
  96         System.out.println( "Appearing once DCs: " + appearing_once_dcs.size() );
  97         final DescriptiveStatistics stats = new BasicDescriptiveStatistics();
  98         final Map<String, Set<String>> node_to_chars = new HashMap<String, Set<String>>();
  99         final SortedSet<String> appearing_in_all_dcs = new TreeSet<String>();
 100         for( final String appearing_once_dc : appearing_once_dcs ) {
 101             int count = 0;
 102             for( final PhylogenyNodeIterator ite = phy.iteratorExternalForward(); ite.hasNext(); ) {
 103                 final PhylogenyNode ext_node = ite.next();
 104                 if ( !node_to_chars.containsKey( ext_node.getName() ) ) {
 105                     node_to_chars.put( ext_node.getName(), getAllExternalPresentAndGainedCharacters( ext_node ) );
 106                 }
 107                 if ( node_to_chars.get( ext_node.getName() ).contains( appearing_once_dc ) ) {
 108                     count++;
 109                 }
 110             }
 111             if ( count < 1 ) {
 112                 System.out.println( "error, count is <1" );
 113                 System.exit( -1 );
 114             }
 115             if ( count == phy.getNumberOfExternalNodes() ) {
 116                 appearing_in_all_dcs.add( appearing_once_dc );
 117             }
 118             stats.addValue( count );
 119         }
 120         System.out.println();
 121         System.out.println( stats.toString() );
 122         System.out.println();
 123         final int[] bins = BasicDescriptiveStatistics.performBinning( stats.getDataAsDoubleArray(), 1, 172, 172 );
 124         for( int i = 0; i < bins.length; i++ ) {
 125             System.out.println( ( i + 1 ) + "\t" + bins[ i ] );
 126         }
 127         System.out.println();
 128         System.out.println( "appearing in all:" );
 129         for( final String i : appearing_in_all_dcs ) {
 130             System.out.println( i );
 131         }
 132         System.out.println();
 133         for( final String dc : appearing_once_dcs ) {
 134             System.out.println( "1\t" + dc );
 135         }
 136     }
 137
 138     private static SortedSet<String> getAllExternalPresentAndGainedCharacters( final PhylogenyNode node ) {
 139         final SortedSet<String> chars = new TreeSet<String>();
 140         final List<PhylogenyNode> descs = node.getAllExternalDescendants();
 141         for( final PhylogenyNode desc : descs ) {
 142             chars.addAll( desc.getNodeData().getBinaryCharacters().getGainedCharacters() );
 143             chars.addAll( desc.getNodeData().getBinaryCharacters().getPresentCharacters() );
 144         }
 145         return chars;
 146     }
 147 }