3 // FORESTER -- software libraries and applications
4 // for evolutionary biology research and applications.
6 // Copyright (C) 2008-2009 Christian M. Zmasek
7 // Copyright (C) 2008-2009 Burnham Institute for Medical Research
10 // This library is free software; you can redistribute it and/or
11 // modify it under the terms of the GNU Lesser General Public
12 // License as published by the Free Software Foundation; either
13 // version 2.1 of the License, or (at your option) any later version.
15 // This library is distributed in the hope that it will be useful,
16 // but WITHOUT ANY WARRANTY; without even the implied warranty of
17 // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
18 // Lesser General Public License for more details.
20 // You should have received a copy of the GNU Lesser General Public
21 // License along with this library; if not, write to the Free Software
22 // Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA
24 // Contact: phylosoft @ gmail . com
25 // WWW: https://sites.google.com/site/cmzmasek/home/software/forester
27 package org.forester.application;
30 import java.io.IOException;
31 import java.util.ArrayList;
32 import java.util.List;
34 import org.forester.io.parsers.PhylogenyParser;
35 import org.forester.io.parsers.nexus.NexusPhylogeniesParser;
36 import org.forester.io.parsers.nhx.NHXParser;
37 import org.forester.io.parsers.phyloxml.PhyloXmlDataFormatException;
38 import org.forester.io.parsers.util.ParserUtils;
39 import org.forester.io.writers.PhylogenyWriter;
40 import org.forester.phylogeny.Phylogeny;
41 import org.forester.phylogeny.PhylogenyMethods;
42 import org.forester.phylogeny.PhylogenyMethods.DESCENDANT_SORT_PRIORITY;
43 import org.forester.phylogeny.PhylogenyNode;
44 import org.forester.phylogeny.factories.ParserBasedPhylogenyFactory;
45 import org.forester.phylogeny.factories.PhylogenyFactory;
46 import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
47 import org.forester.util.CommandLineArguments;
48 import org.forester.util.ForesterUtil;
50 public class phyloxml_converter {
52 final static private String HELP_OPTION_1 = "help";
53 final static private String HELP_OPTION_2 = "h";
54 final static private String FIELD_OPTION = "f";
55 final static private String FIELD_CLADE_NAME = "nn";
56 final static private String FIELD_TAXONOMY_CODE = "tc";
57 final static private String FIELD_TAXONOMY_SCI_NAME = "sn";
58 final static private String FIELD_TAXONOMY_COMM_NAME = "cn";
59 final static private String FIELD_SEQUENCE_GENE_NAME = "gn";
60 final static private String FIELD_SEQUENCE_SYMBOL = "sy";
61 final static private String FIELD_UNIPROT_TAXONOMY_ID_SPLIT_1 = "i1";
62 final static private String FIELD_UNIPROT_TAXONOMY_ID_SPLIT_2 = "i2";
63 final static private String FIELD_DUMMY = "dummy";
64 final static private String INTERNAL_NAMES_ARE_BOOT_SUPPPORT = "i";
65 final static private String MIDPOINT_REROOT = "m";
66 final static private String EXTRACT_TAXONOMY = "xt";
67 final static private String EXTRACT_TAXONOMY_PF = "xp";
68 final static private String ORDER_SUBTREES = "o";
69 final static private String NO_TREE_LEVEL_INDENDATION = "ni";
70 final static private String REPLACE_UNDER_SCORES = "ru";
71 final static private String IGNORE_QUOTES = "iqs";
72 final static private String PRG_NAME = "phyloxml_converter";
73 final static private String PRG_VERSION = "1.301";
74 final static private String PRG_DATE = "2012.08.31";
75 final static private String E_MAIL = "phylosoft@gmail.com";
76 final static private String WWW = "www.phylosoft.org/forester/";
77 final static private boolean SPECIAL = false;
79 public static void main( final String args[] ) throws PhyloXmlDataFormatException {
80 ForesterUtil.printProgramInformation( PRG_NAME, PRG_VERSION, PRG_DATE, E_MAIL, WWW );
81 CommandLineArguments cla = null;
83 cla = new CommandLineArguments( args );
85 catch ( final Exception e ) {
86 ForesterUtil.fatalError( PRG_NAME, e.getMessage() );
88 if ( cla.isOptionSet( HELP_OPTION_1 ) || cla.isOptionSet( HELP_OPTION_2 ) || ( args.length == 0 ) ) {
92 if ( args.length < 3 ) {
94 System.out.println( "[" + PRG_NAME + "] incorrect number of arguments" );
99 final List<String> allowed_options = new ArrayList<String>();
100 allowed_options.add( NO_TREE_LEVEL_INDENDATION );
101 allowed_options.add( FIELD_OPTION );
102 allowed_options.add( MIDPOINT_REROOT );
103 allowed_options.add( ORDER_SUBTREES );
104 allowed_options.add( INTERNAL_NAMES_ARE_BOOT_SUPPPORT );
105 allowed_options.add( REPLACE_UNDER_SCORES );
106 allowed_options.add( EXTRACT_TAXONOMY );
107 allowed_options.add( EXTRACT_TAXONOMY_PF );
108 allowed_options.add( IGNORE_QUOTES );
109 if ( cla.getNumberOfNames() != 2 ) {
110 System.out.println();
111 System.out.println( "[" + PRG_NAME + "] incorrect number of arguments" );
112 System.out.println();
116 final String dissallowed_options = cla.validateAllowedOptionsAsString( allowed_options );
117 if ( dissallowed_options.length() > 0 ) {
118 ForesterUtil.fatalError( PRG_NAME, "unknown option(s): " + dissallowed_options );
120 final List<String> mandatory_options = new ArrayList<String>();
121 mandatory_options.add( FIELD_OPTION );
122 final String missing_options = cla.validateMandatoryOptionsAsString( mandatory_options );
123 if ( missing_options.length() > 0 ) {
124 ForesterUtil.fatalError( PRG_NAME, "missing option(s): " + missing_options );
126 if ( !cla.isOptionValueSet( FIELD_OPTION ) ) {
127 System.out.println();
131 final String field_option_value = cla.getOptionValue( FIELD_OPTION );
132 PhylogenyMethods.PhylogenyNodeField field = null;
133 if ( field_option_value.equals( FIELD_CLADE_NAME ) ) {
134 field = PhylogenyMethods.PhylogenyNodeField.CLADE_NAME;
136 else if ( field_option_value.equals( FIELD_TAXONOMY_CODE ) ) {
137 field = PhylogenyMethods.PhylogenyNodeField.TAXONOMY_CODE;
139 else if ( field_option_value.equals( FIELD_TAXONOMY_SCI_NAME ) ) {
140 field = PhylogenyMethods.PhylogenyNodeField.TAXONOMY_SCIENTIFIC_NAME;
142 else if ( field_option_value.equals( FIELD_TAXONOMY_COMM_NAME ) ) {
143 field = PhylogenyMethods.PhylogenyNodeField.TAXONOMY_COMMON_NAME;
145 else if ( field_option_value.equals( FIELD_SEQUENCE_GENE_NAME ) ) {
146 field = PhylogenyMethods.PhylogenyNodeField.SEQUENCE_NAME;
148 else if ( field_option_value.equals( FIELD_SEQUENCE_SYMBOL ) ) {
149 field = PhylogenyMethods.PhylogenyNodeField.SEQUENCE_SYMBOL;
151 else if ( field_option_value.equals( FIELD_UNIPROT_TAXONOMY_ID_SPLIT_1 ) ) {
152 field = PhylogenyMethods.PhylogenyNodeField.TAXONOMY_ID_UNIPROT_1;
154 else if ( field_option_value.equals( FIELD_UNIPROT_TAXONOMY_ID_SPLIT_2 ) ) {
155 field = PhylogenyMethods.PhylogenyNodeField.TAXONOMY_ID_UNIPROT_2;
157 else if ( field_option_value.equals( FIELD_DUMMY ) ) {
160 ForesterUtil.fatalError( PRG_NAME, "unknown value for -\"" + FIELD_OPTION + "\" option: \""
161 + field_option_value + "\"" );
163 boolean ignore_quotes = false;
164 if ( cla.isOptionSet( IGNORE_QUOTES ) ) {
165 ignore_quotes = true;
167 boolean int_values_are_boots = false;
168 if ( cla.isOptionSet( INTERNAL_NAMES_ARE_BOOT_SUPPPORT ) ) {
169 int_values_are_boots = true;
171 boolean midpoint_reroot = false;
172 if ( cla.isOptionSet( MIDPOINT_REROOT ) ) {
173 midpoint_reroot = true;
175 boolean order_subtrees = false;
176 if ( cla.isOptionSet( ORDER_SUBTREES ) ) {
177 order_subtrees = true;
179 boolean replace_underscores = false;
180 if ( cla.isOptionSet( REPLACE_UNDER_SCORES ) ) {
181 replace_underscores = true;
183 boolean no_indendation = false;
184 if ( cla.isOptionSet( NO_TREE_LEVEL_INDENDATION ) ) {
185 no_indendation = true;
187 boolean extr_taxonomy = false;
188 if ( cla.isOptionSet( EXTRACT_TAXONOMY ) ) {
189 extr_taxonomy = true;
191 boolean extr_taxonomy_pf_only = false;
192 if ( cla.isOptionSet( EXTRACT_TAXONOMY_PF ) ) {
193 extr_taxonomy_pf_only = true;
195 final File infile = cla.getFile( 0 );
196 final File outfile = cla.getFile( 1 );
197 if ( outfile.exists() ) {
198 ForesterUtil.fatalError( PRG_NAME, "[" + outfile + "] already exists" );
200 if ( !infile.exists() ) {
201 ForesterUtil.fatalError( PRG_NAME, "[" + infile + "] does not exist" );
203 Phylogeny[] phys = null;
205 final PhylogenyFactory factory = ParserBasedPhylogenyFactory.getInstance();
206 final PhylogenyParser parser = ParserUtils.createParserDependingOnFileType( infile, true );
207 if ( parser instanceof NHXParser ) {
208 if ( ( field != PhylogenyMethods.PhylogenyNodeField.TAXONOMY_CODE )
209 && ( field != PhylogenyMethods.PhylogenyNodeField.TAXONOMY_COMMON_NAME )
210 && ( field != PhylogenyMethods.PhylogenyNodeField.TAXONOMY_SCIENTIFIC_NAME ) ) {
211 if ( extr_taxonomy_pf_only ) {
212 ( ( NHXParser ) parser )
213 .setTaxonomyExtraction( NHXParser.TAXONOMY_EXTRACTION.PFAM_STYLE_STRICT );
214 replace_underscores = false;
216 else if ( extr_taxonomy ) {
217 ( ( NHXParser ) parser )
218 .setTaxonomyExtraction( NHXParser.TAXONOMY_EXTRACTION.PFAM_STYLE_RELAXED );
219 replace_underscores = false;
223 ( ( NHXParser ) parser ).setTaxonomyExtraction( NHXParser.TAXONOMY_EXTRACTION.NO );
225 ( ( NHXParser ) parser ).setReplaceUnderscores( replace_underscores );
226 ( ( NHXParser ) parser ).setIgnoreQuotes( ignore_quotes );
228 else if ( parser instanceof NexusPhylogeniesParser ) {
229 ( ( NexusPhylogeniesParser ) parser ).setReplaceUnderscores( replace_underscores );
230 ( ( NexusPhylogeniesParser ) parser ).setIgnoreQuotes( false );
232 phys = factory.create( infile, parser );
234 catch ( final IOException e ) {
235 ForesterUtil.fatalError( PRG_NAME, "failed to read phylogeny from [" + infile + "]: " + e.getMessage() );
238 for( final Phylogeny phy : phys ) {
239 performSpecialProcessing( phy );
242 if ( int_values_are_boots ) {
243 for( final Phylogeny phy : phys ) {
244 PhylogenyMethods.transferInternalNamesToBootstrapSupport( phy );
247 if ( field != null ) {
248 for( final Phylogeny phy : phys ) {
249 PhylogenyMethods.transferNodeNameToField( phy, field, false );
252 if ( midpoint_reroot ) {
254 for( final Phylogeny phy : phys ) {
255 PhylogenyMethods.midpointRoot( phy );
258 catch ( final Exception e ) {
259 System.out.println( "" );
260 ForesterUtil.printWarningMessage( PRG_NAME, "midpoint rerooting failed: " + e.getLocalizedMessage() );
263 if ( order_subtrees ) {
264 for( final Phylogeny phy : phys ) {
265 PhylogenyMethods.orderAppearance( phy.getRoot(), true, true, DESCENDANT_SORT_PRIORITY.TAXONOMY );
266 phy.externalNodesHaveChanged();
267 phy.clearHashIdToNodeMap();
268 phy.recalculateNumberOfExternalDescendants( true );
272 final PhylogenyWriter writer = new PhylogenyWriter();
273 if ( no_indendation ) {
274 writer.setIndentPhyloxml( false );
276 writer.toPhyloXML( phys, 0, outfile, ForesterUtil.LINE_SEPARATOR );
278 catch ( final IOException e ) {
279 ForesterUtil.fatalError( PRG_NAME, "failed to write to [" + outfile + "]: " + e.getMessage() );
281 System.out.println( "[" + PRG_NAME + "] wrote: [" + outfile + "]" );
282 System.out.println( "[" + PRG_NAME + "] OK" );
283 System.out.println();
286 private static void performSpecialProcessing( final Phylogeny phy ) {
287 // Can place some kind of custom processing here.
288 // final List<PhylogenyNode> remove_us = new ArrayList<PhylogenyNode>();
290 // for( final PhylogenyNodeIterator it = phy.iteratorPostorder(); it.hasNext(); ) {
291 // final PhylogenyNode node = it.next();
292 // final String name = node.getNodeName().toLowerCase();
293 // if ( name.startsWith( "environmental_samples" ) || name.startsWith( "unclassified" )
294 // || name.startsWith( "bacteria" ) || name.startsWith( "other" )
295 // || name.startsWith( "viroids" ) || name.startsWith( "viruses" ) ) {
296 // remove_us.add( node );
297 // System.out.println( counter++ );
301 // for( final PhylogenyNode node : remove_us ) {
302 // if ( phy.getNode( node.getNodeId() ) != null ) {
303 // phy.deleteSubtree( node );
304 // System.out.println( "deleted: " + node );
309 // for( final PhylogenyNodeIterator it = phy.iteratorPostorder(); it.hasNext(); ) {
310 // final PhylogenyNode node = it.next();
311 // node.getNodeData().setTaxonomy( null );
313 // phy.reRoot( phy.getFirstExternalNode() );
314 // PhylogenyMethods.midpointRoot( phy );
315 // phy.orderAppearance( true );
316 for( final PhylogenyNodeIterator it = phy.iteratorPostorder(); it.hasNext(); ) {
317 final PhylogenyNode node = it.next();
318 final String name = node.getName();
319 if ( !ForesterUtil.isEmpty( name ) ) {
320 // final Taxonomy taxo = new Taxonomy();
321 // if ( node.isExternal() ) {
322 // taxo.setTaxonomyCode( name );
323 // node.getNodeData().setTaxonomy( taxo );
325 // else if ( name.indexOf( '_' ) == -1 || name.length() > 6 ) {
326 // taxo.setScientificName( name );
327 // node.getNodeData().setTaxonomy( taxo );
329 // node.setName( "" );
330 // if ( name.indexOf( "BF" ) >= 0 ) {
331 // taxo.setTaxonomyCode( "BACFR" );
333 // else if ( name.indexOf( "BT" ) >= 0 ) {
334 // taxo.setTaxonomyCode( "BACTN" );
336 // else if ( name.indexOf( "MXAN" ) >= 0 ) {
337 // taxo.setTaxonomyCode( "MYXXD" );
339 // else if ( name.indexOf( "STIAU" ) >= 0 ) {
340 // taxo.setTaxonomyCode( "STIAU" );
342 // else if ( name.indexOf( "BOVA" ) >= 0 ) {
343 // taxo.setTaxonomyCode( "BACOV" );
345 // else if ( name.indexOf( "BUNI" ) >= 0 ) {
346 // taxo.setTaxonomyCode( "BACUN" );
348 // else if ( name.indexOf( "Pgin" ) >= 0 ) {
349 // taxo.setTaxonomyCode( "PORGI" );
351 // else if ( name.equals( "3CGH" ) || name.equals( "3CK7" ) ) {
352 // taxo.setTaxonomyCode( "BACTN" );
354 // node.getNodeData().setTaxonomy( taxo );
359 private static void printHelp() {
360 System.out.println( "Usage:" );
361 System.out.println();
366 + "=<field option> [options] <infile in New Hamphshire, NHX, Nexus, ToL XML, or phyloXML format> <outfile>" );
367 System.out.println();
368 System.out.println( " field options: " );
369 System.out.println();
370 System.out.println( " " + FIELD_CLADE_NAME + ": transfer name to node/clade name" );
371 System.out.println( " " + FIELD_TAXONOMY_CODE + ": transfer name to taxonomy code" );
372 System.out.println( " " + FIELD_TAXONOMY_SCI_NAME + ": transfer name to taxonomy scientific name" );
373 System.out.println( " " + FIELD_TAXONOMY_COMM_NAME + ": transfer name to taxonomy common name" );
374 System.out.println( " " + FIELD_SEQUENCE_GENE_NAME + ": transfer name to sequence name" );
375 System.out.println( " " + FIELD_SEQUENCE_SYMBOL + ": transfer name to sequence symbol" );
378 + FIELD_UNIPROT_TAXONOMY_ID_SPLIT_1
379 + ": transfer/split name to taxonomy uniprot identifier\n (split at underscore if \"id_name\" pattern, e.g. \"817_SusD\")" );
382 + FIELD_UNIPROT_TAXONOMY_ID_SPLIT_2
383 + ": transfer/split name to taxonomy uniprot identifier\n (split at underscore if \"name_id\" pattern, e.g. \"SusD_817\")" );
384 System.out.println();
385 System.out.println( " options: " );
386 System.out.println( " -" + INTERNAL_NAMES_ARE_BOOT_SUPPPORT
387 + " : internal names in NH or NHX tree are bootstrap support values" );
388 System.out.println( " -" + REPLACE_UNDER_SCORES + " : replace all underscores with spaces" );
389 System.out.println( " -" + MIDPOINT_REROOT + " : midpoint reroot" );
390 System.out.println( " -" + ORDER_SUBTREES + " : order subtrees" );
394 + " : extract taxonomy to taxonomy code from \"seqname_TAXON\"-style names (cannot be used with the following field options: "
395 + FIELD_TAXONOMY_CODE + ", " + FIELD_TAXONOMY_COMM_NAME + ", " + FIELD_TAXONOMY_SCI_NAME + ")" );
398 + EXTRACT_TAXONOMY_PF
399 + " : extract taxonomy to taxonomy code from Pfam (\"seqname_TAXON/x-y\") style names only (cannot be used with the following field options: "
400 + FIELD_TAXONOMY_CODE + ", " + FIELD_TAXONOMY_COMM_NAME + ", " + FIELD_TAXONOMY_SCI_NAME + ")" );
401 System.out.println( " -" + NO_TREE_LEVEL_INDENDATION + " : no tree level indendation in phyloXML output" );
402 System.out.println( " -" + IGNORE_QUOTES + ": ignore quotes and whitespace (e.g. \"a b\" becomes ab)" );
403 System.out.println();