2 // FORESTER -- software libraries and applications
3 // for evolutionary biology research and applications.
5 // Copyright (C) 2008-2012 Christian M. Zmasek
6 // Copyright (C) 2008-2012 Burnham Institute for Medical Research
9 // This library is free software; you can redistribute it and/or
10 // modify it under the terms of the GNU Lesser General Public
11 // License as published by the Free Software Foundation; either
12 // version 2.1 of the License, or (at your option) any later version.
14 // This library is distributed in the hope that it will be useful,
15 // but WITHOUT ANY WARRANTY; without even the implied warranty of
16 // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
17 // Lesser General Public License for more details.
19 // You should have received a copy of the GNU Lesser General Public
20 // License along with this library; if not, write to the Free Software
21 // Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA
23 // Contact: phylosoft @ gmail . com
24 // WWW: www.phylosoft.org/forester
26 package org.forester.application;
29 import java.io.IOException;
30 import java.util.SortedSet;
32 import org.forester.archaeopteryx.tools.SequenceDataRetriver;
33 import org.forester.io.parsers.util.ParserUtils;
34 import org.forester.io.writers.PhylogenyWriter;
35 import org.forester.phylogeny.Phylogeny;
36 import org.forester.phylogeny.PhylogenyMethods;
37 import org.forester.phylogeny.factories.ParserBasedPhylogenyFactory;
38 import org.forester.phylogeny.factories.PhylogenyFactory;
39 import org.forester.util.CommandLineArguments;
40 import org.forester.util.ForesterUtil;
42 public class gene_tree_preprocess {
44 final static private String HELP_OPTION_1 = "help";
45 final static private String HELP_OPTION_2 = "h";
46 final static private String FROM_OPTION = "f";
47 final static private String TO_OPTION = "t";
48 final static private String STEP_OPTION = "s";
49 final static private String WINDOW_OPTION = "w";
50 final static private String PRG_NAME = "gene_tree_preprocess";
51 final static private String PRG_DESC = "gene tree preprocessing for SDI analysis";
52 final static private String PRG_VERSION = "1.00";
53 final static private String PRG_DATE = "2012.06.07";
54 final static private String E_MAIL = "phylosoft@gmail.com";
55 final static private String WWW = "www.phylosoft.org/forester/";
57 public static void main( final String[] args ) {
59 final CommandLineArguments cla = new CommandLineArguments( args );
60 if ( cla.isOptionSet( HELP_OPTION_1 ) || cla.isOptionSet( HELP_OPTION_2 ) || ( args.length != 1 ) ) {
64 final File in = cla.getFile( 0 );
66 final PhylogenyFactory factory = ParserBasedPhylogenyFactory.getInstance();
68 phy = factory.create( in, ParserUtils.createParserDependingOnFileType( in, true ) )[ 0 ];
70 catch ( final IOException e ) {
71 ForesterUtil.fatalError( PRG_NAME,
72 "failed to read target phylogenies from [" + in + "]: "
73 + e.getLocalizedMessage() );
75 final File outtree = new File( ForesterUtil.removeSuffix( in.toString() )
76 + "_preprocessed_gene_tree.phylo.xml" );
77 final File removed_nodes = new File( ForesterUtil.removeSuffix( in.toString() ) + "_removed_nodes.txt" );
78 checkForOutputFileWriteability( outtree );
79 checkForOutputFileWriteability( removed_nodes );
80 if ( phy.getNumberOfExternalNodes() < 2 ) {
81 ForesterUtil.fatalError( PRG_NAME, "phylogeny has " + phy.getNumberOfExternalNodes()
82 + " external node(s), aborting" );
84 final SortedSet<String> not_found = SequenceDataRetriver.obtainSeqInformation( phy );
85 for( final String remove_me : not_found ) {
86 System.out.println( " not found: " + not_found );
87 PhylogenyMethods.removeNode( phy.getNode( remove_me ), phy );
89 if ( phy.getNumberOfExternalNodes() < 2 ) {
90 ForesterUtil.fatalError( PRG_NAME,
91 "after removal of unresolvable external nodes, phylogeny has "
92 + phy.getNumberOfExternalNodes() + " external node(s), aborting" );
95 final PhylogenyWriter writer = new PhylogenyWriter();
96 writer.toPhyloXML( phy, 0, outtree );
98 catch ( final IOException e ) {
99 ForesterUtil.fatalError( PRG_NAME, "failed to write to [" + outtree + "]: " + e.getLocalizedMessage() );
101 // ForesterUtil.programMessage( PRG_NAME, "wrote output to: [" + outfile + "]" );
102 ForesterUtil.programMessage( PRG_NAME, "OK" );
103 System.out.println();
105 catch ( final Exception e ) {
106 ForesterUtil.fatalError( PRG_NAME, e.getMessage() );
110 public static void checkForOutputFileWriteability( final File outfile ) {
111 final String error = ForesterUtil.isWritableFile( outfile );
112 if ( !ForesterUtil.isEmpty( error ) ) {
113 ForesterUtil.fatalError( PRG_NAME, error );
117 private static void printHelp() {
118 ForesterUtil.printProgramInformation( PRG_NAME,
124 ForesterUtil.getForesterLibraryInformation() );
125 System.out.println( "Usage:" );
126 System.out.println();
127 System.out.println( PRG_NAME + " <options> <msa input file>" );
128 System.out.println();
129 System.out.println( " options: " );
130 System.out.println();
131 System.out.println( " -" + FROM_OPTION + "=<integer>: from (msa column)" );
132 System.out.println( " -" + TO_OPTION + "=<integer>: to (msa column)" );
133 System.out.println( " or" );
134 System.out.println( " -" + WINDOW_OPTION + "=<integer>: window size (msa columns)" );
135 System.out.println( " -" + STEP_OPTION + "=<integer>: step size (msa columns)" );
136 System.out.println();
137 System.out.println();
138 System.out.println();