2 // FORESTER -- software libraries and applications
3 // for evolutionary biology research and applications.
5 // Copyright (C) 2008-2009 Christian M. Zmasek
6 // Copyright (C) 2008-2009 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.tools;
29 import java.io.IOException;
30 import java.util.HashMap;
32 import java.util.regex.Pattern;
34 import org.forester.archaeopteryx.AptxUtil;
35 import org.forester.io.parsers.nhx.NHXFormatException;
36 import org.forester.io.parsers.phyloxml.PhyloXmlDataFormatException;
37 import org.forester.phylogeny.Phylogeny;
38 import org.forester.phylogeny.PhylogenyNode;
39 import org.forester.phylogeny.data.Accession;
40 import org.forester.phylogeny.data.Annotation;
41 import org.forester.phylogeny.data.DomainArchitecture;
42 import org.forester.phylogeny.data.Identifier;
43 import org.forester.phylogeny.data.Sequence;
44 import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
45 import org.forester.util.BasicTable;
46 import org.forester.util.BasicTableParser;
47 import org.forester.util.ForesterUtil;
49 public final class PhylogenyDecorator {
51 // From evoruby/lib/evo/apps/tseq_taxonomy_processor.rb:
52 final private static String TP_TAXONOMY_CODE = "TAXONOMY_CODE";
53 final private static String TP_TAXONOMY_ID = "TAXONOMY_ID";
54 final private static String TP_TAXONOMY_ID_PROVIDER = "TAXONOMY_ID_PROVIDER";
55 final private static String TP_TAXONOMY_SN = "TAXONOMY_SN";
56 final private static String TP_TAXONOMY_CN = "TAXONOMY_CN";
57 final private static String TP_TAXONOMY_SYN = "TAXONOMY_SYN";
58 final private static String TP_SEQ_SYMBOL = "SEQ_SYMBOL";
59 final private static String TP_SEQ_ACCESSION = "SEQ_ACCESSION";
60 final private static String TP_SEQ_ACCESSION_SOURCE = "SEQ_ACCESSION_SOURCE";
61 final private static String TP_SEQ_ANNOTATION_DESC = "SEQ_ANNOTATION_DESC";
62 final private static String TP_SEQ_ANNOTATION_REF = "SEQ_ANNOTATION_REF";
63 final private static String TP_SEQ_MOL_SEQ = "SEQ_MOL_SEQ";
64 final private static String TP_SEQ_NAME = "SEQ_NAME";
65 final private static String TP_NODE_NAME = "NODE_NAME";
66 final private static Pattern NODENAME_SEQNUMBER_TAXDOMAINNUMBER = Pattern
67 .compile( "^([a-fA-Z0-9]{1,5})_([A-Z0-9]{2,4}[A-Z])(\\d{1,4})$" );
68 public final static boolean SANITIZE = false;
69 public final static boolean VERBOSE = true;
70 private static final boolean CUT = true;
72 private PhylogenyDecorator() {
76 public static void decorate( final Phylogeny phylogeny,
77 final Map<String, Map<String, String>> map,
79 final int numbers_of_chars_allowed_to_remove_if_not_found_in_map )
80 throws IllegalArgumentException, PhyloXmlDataFormatException {
81 for( final PhylogenyNodeIterator iter = phylogeny.iteratorPostorder(); iter.hasNext(); ) {
82 final PhylogenyNode node = iter.next();
83 final String name = node.getName();
84 if ( !ForesterUtil.isEmpty( name ) ) {
85 if ( map.containsKey( name ) || ( numbers_of_chars_allowed_to_remove_if_not_found_in_map > 0 ) ) {
86 Map<String, String> new_values = map.get( name );
88 while ( ( new_values == null ) && ( numbers_of_chars_allowed_to_remove_if_not_found_in_map > 0 )
89 && ( x <= numbers_of_chars_allowed_to_remove_if_not_found_in_map ) ) {
90 new_values = map.get( name.substring( 0, name.length() - x ) );
93 if ( new_values != null ) {
94 if ( new_values.containsKey( TP_TAXONOMY_CODE ) ) {
95 AptxUtil.ensurePresenceOfTaxonomy( node );
96 node.getNodeData().getTaxonomy().setTaxonomyCode( new_values.get( TP_TAXONOMY_CODE ) );
98 if ( new_values.containsKey( TP_TAXONOMY_ID )
99 && new_values.containsKey( TP_TAXONOMY_ID_PROVIDER ) ) {
100 AptxUtil.ensurePresenceOfTaxonomy( node );
103 .setIdentifier( new Identifier( new_values.get( TP_TAXONOMY_ID ),
104 new_values.get( TP_TAXONOMY_ID_PROVIDER ) ) );
106 else if ( new_values.containsKey( TP_TAXONOMY_ID ) ) {
107 AptxUtil.ensurePresenceOfTaxonomy( node );
108 node.getNodeData().getTaxonomy()
109 .setIdentifier( new Identifier( new_values.get( TP_TAXONOMY_ID ) ) );
111 if ( new_values.containsKey( TP_TAXONOMY_SN ) ) {
112 AptxUtil.ensurePresenceOfTaxonomy( node );
113 node.getNodeData().getTaxonomy().setScientificName( new_values.get( TP_TAXONOMY_SN ) );
115 if ( new_values.containsKey( TP_TAXONOMY_CN ) ) {
116 AptxUtil.ensurePresenceOfTaxonomy( node );
117 node.getNodeData().getTaxonomy().setCommonName( new_values.get( TP_TAXONOMY_CN ) );
119 if ( new_values.containsKey( TP_TAXONOMY_SYN ) ) {
120 AptxUtil.ensurePresenceOfTaxonomy( node );
121 node.getNodeData().getTaxonomy().getSynonyms().add( new_values.get( TP_TAXONOMY_SYN ) );
123 if ( new_values.containsKey( TP_SEQ_ACCESSION )
124 && new_values.containsKey( TP_SEQ_ACCESSION_SOURCE ) ) {
125 AptxUtil.ensurePresenceOfSequence( node );
128 .setAccession( new Accession( new_values.get( TP_SEQ_ACCESSION ),
129 new_values.get( TP_SEQ_ACCESSION_SOURCE ) ) );
131 if ( new_values.containsKey( TP_SEQ_ANNOTATION_DESC ) ) {
132 AptxUtil.ensurePresenceOfSequence( node );
133 final Annotation ann = new Annotation( "?" );
134 ann.setDesc( new_values.get( TP_SEQ_ANNOTATION_DESC ) );
135 node.getNodeData().getSequence().addAnnotation( ann );
137 if ( new_values.containsKey( TP_SEQ_ANNOTATION_REF ) ) {
138 AptxUtil.ensurePresenceOfSequence( node );
139 final Annotation ann = new Annotation( new_values.get( TP_SEQ_ANNOTATION_REF ) );
140 node.getNodeData().getSequence().addAnnotation( ann );
142 if ( new_values.containsKey( TP_SEQ_SYMBOL ) ) {
143 AptxUtil.ensurePresenceOfSequence( node );
144 node.getNodeData().getSequence().setSymbol( new_values.get( TP_SEQ_SYMBOL ) );
146 if ( new_values.containsKey( TP_SEQ_NAME ) ) {
147 AptxUtil.ensurePresenceOfSequence( node );
148 node.getNodeData().getSequence().setName( new_values.get( TP_SEQ_NAME ) );
150 if ( new_values.containsKey( TP_SEQ_MOL_SEQ ) ) {
151 AptxUtil.ensurePresenceOfSequence( node );
152 node.getNodeData().getSequence().setMolecularSequence( new_values.get( TP_SEQ_MOL_SEQ ) );
154 if ( new_values.containsKey( TP_NODE_NAME ) ) {
155 node.setName( new_values.get( TP_NODE_NAME ) );
157 } // if ( new_values != null )
158 } // if ( map.containsKey( name ) || ( numbers_of_chars_allowed_to_remove_if_not_found_in_map > 0 ) )
160 throw new IllegalArgumentException( "\"" + name + "\" not found in name map" );
174 * maps names (in phylogeny) to new values
177 * @throws IllegalArgumentException
178 * @throws NHXFormatException
179 * @throws PhyloXmlDataFormatException
181 public static void decorate( final Phylogeny phylogeny,
182 final Map<String, String> map,
184 final boolean extract_bracketed_scientific_name,
185 final boolean extract_bracketed_tax_code,
187 final boolean cut_name_after_space,
188 final boolean process_name_intelligently,
189 final boolean process_similar_to,
190 final int numbers_of_chars_allowed_to_remove_if_not_found_in_map,
191 final boolean trim_after_tilde ) throws IllegalArgumentException, NHXFormatException,
192 PhyloXmlDataFormatException {
193 PhylogenyDecorator.decorate( phylogeny,
196 extract_bracketed_scientific_name,
197 extract_bracketed_tax_code,
200 cut_name_after_space,
201 process_name_intelligently,
203 numbers_of_chars_allowed_to_remove_if_not_found_in_map,
213 * maps names (in phylogeny) to new values if intermediate_map is
214 * null otherwise maps intermediate value to new value
217 * @param intermediate_map
218 * maps name (in phylogeny) to a intermediate value
219 * @throws IllegalArgumentException
220 * @throws PhyloXmlDataFormatException
222 public static void decorate( final Phylogeny phylogeny,
223 final Map<String, String> map,
225 final boolean extract_bracketed_scientific_name,
226 final boolean extract_bracketed_tax_code,
228 final Map<String, String> intermediate_map,
229 final boolean cut_name_after_space,
230 final boolean process_name_intelligently,
231 final boolean process_similar_to,
232 final int numbers_of_chars_allowed_to_remove_if_not_found_in_map,
233 final boolean trim_after_tilde ) throws IllegalArgumentException,
234 PhyloXmlDataFormatException {
235 if ( extract_bracketed_scientific_name && ( field == FIELD.TAXONOMY_SCIENTIFIC_NAME ) ) {
236 throw new IllegalArgumentException( "attempt to extract bracketed scientific name together with data field pointing to scientific name" );
238 for( final PhylogenyNodeIterator iter = phylogeny.iteratorPostorder(); iter.hasNext(); ) {
239 final PhylogenyNode node = iter.next();
240 String name = node.getName();
241 if ( trim_after_tilde && ( name.indexOf( '~' ) > 0 ) ) {
242 name = name.substring( 0, name.indexOf( '~' ) );
244 if ( !ForesterUtil.isEmpty( name ) ) {
245 if ( intermediate_map != null ) {
246 name = PhylogenyDecorator.extractIntermediate( intermediate_map, name );
248 // int space_index = name.indexOf( " " );
249 // if ( CUT && space_index > 0 ) {
250 // int y = name.lastIndexOf( "|" );
251 // name = name.substring( y + 1, space_index );
253 // String new_value = null;
254 // for( String key : map.keySet() ) {
255 // if ( key.indexOf( name ) >= 0 ) {
256 // if ( new_value == null ) {
257 // new_value = map.get( key );
260 // System.out.println( name + " is not unique" );
261 // System.exit( -1 );
265 // if ( new_value != null ) {
266 if ( map.containsKey( name ) || ( numbers_of_chars_allowed_to_remove_if_not_found_in_map > 0 ) ) {
267 String new_value = map.get( name );
269 while ( ( new_value == null ) && ( numbers_of_chars_allowed_to_remove_if_not_found_in_map > 0 )
270 && ( x <= numbers_of_chars_allowed_to_remove_if_not_found_in_map ) ) {
271 new_value = map.get( name.substring( 0, name.length() - x ) );
274 if ( new_value != null ) {
275 new_value = new_value.trim();
276 new_value.replaceAll( "/\\s+/", " " );
277 if ( extract_bracketed_scientific_name && new_value.endsWith( "]" ) ) {
278 new_value = extractBracketedScientificNames( node, new_value );
280 else if ( extract_bracketed_tax_code && new_value.endsWith( "]" ) ) {
281 new_value = extractBracketedTaxCodes( node, new_value );
284 case SEQUENCE_ANNOTATION_DESC:
285 if ( PhylogenyDecorator.VERBOSE ) {
286 System.out.println( name + ": " + new_value );
288 if ( !node.getNodeData().isHasSequence() ) {
289 node.getNodeData().setSequence( new Sequence() );
291 final Annotation annotation = new Annotation( "?" );
292 annotation.setDesc( new_value );
293 node.getNodeData().getSequence().addAnnotation( annotation );
295 case DOMAIN_STRUCTURE:
296 if ( PhylogenyDecorator.VERBOSE ) {
297 System.out.println( name + ": " + new_value );
299 if ( !node.getNodeData().isHasSequence() ) {
300 node.getNodeData().setSequence( new Sequence() );
302 node.getNodeData().getSequence()
303 .setDomainArchitecture( new DomainArchitecture( new_value ) );
306 if ( PhylogenyDecorator.VERBOSE ) {
307 System.out.println( name + ": " + new_value );
309 AptxUtil.ensurePresenceOfTaxonomy( node );
310 node.getNodeData().getTaxonomy().setTaxonomyCode( new_value );
312 case TAXONOMY_SCIENTIFIC_NAME:
313 if ( PhylogenyDecorator.VERBOSE ) {
314 System.out.println( name + ": " + new_value );
316 AptxUtil.ensurePresenceOfTaxonomy( node );
317 node.getNodeData().getTaxonomy().setScientificName( new_value );
320 if ( PhylogenyDecorator.VERBOSE ) {
321 System.out.println( name + ": " + new_value );
323 if ( !node.getNodeData().isHasSequence() ) {
324 node.getNodeData().setSequence( new Sequence() );
326 node.getNodeData().getSequence().setName( new_value );
329 if ( PhylogenyDecorator.VERBOSE ) {
330 System.out.print( name + " -> " );
332 if ( cut_name_after_space ) {
333 if ( PhylogenyDecorator.VERBOSE ) {
334 System.out.print( new_value + " -> " );
336 new_value = PhylogenyDecorator.deleteAtFirstSpace( new_value );
338 else if ( process_name_intelligently ) {
339 if ( PhylogenyDecorator.VERBOSE ) {
340 System.out.print( new_value + " -> " );
342 new_value = PhylogenyDecorator.processNameIntelligently( new_value );
344 else if ( process_similar_to ) {
345 if ( PhylogenyDecorator.VERBOSE ) {
346 System.out.print( new_value + " -> " );
348 new_value = PhylogenyDecorator.processSimilarTo( new_value );
350 if ( PhylogenyDecorator.SANITIZE ) {
351 new_value = PhylogenyDecorator.sanitize( new_value );
353 if ( PhylogenyDecorator.VERBOSE ) {
354 System.out.println( new_value );
356 node.setName( new_value );
359 throw new RuntimeException( "unknown field \"" + field + "\"" );
364 throw new IllegalArgumentException( "\"" + name + "\" not found in name map" );
370 public static void decorate( final Phylogeny[] phylogenies,
371 final Map<String, Map<String, String>> map,
373 final int numbers_of_chars_allowed_to_remove_if_not_found_in_map )
374 throws IllegalArgumentException, NHXFormatException, PhyloXmlDataFormatException {
375 for( final Phylogeny phylogenie : phylogenies ) {
377 .decorate( phylogenie, map, picky, numbers_of_chars_allowed_to_remove_if_not_found_in_map );
381 public static void decorate( final Phylogeny[] phylogenies,
382 final Map<String, String> map,
384 final boolean extract_bracketed_scientific_name,
385 final boolean extract_bracketed_tax_code,
387 final boolean cut_name_after_space,
388 final boolean process_name_intelligently,
389 final boolean process_similar_to,
390 final int numbers_of_chars_allowed_to_remove_if_not_found_in_map,
391 final boolean trim_after_tilde ) throws IllegalArgumentException, NHXFormatException,
392 PhyloXmlDataFormatException {
393 for( final Phylogeny phylogenie : phylogenies ) {
394 PhylogenyDecorator.decorate( phylogenie,
397 extract_bracketed_scientific_name,
398 extract_bracketed_tax_code,
400 cut_name_after_space,
401 process_name_intelligently,
403 numbers_of_chars_allowed_to_remove_if_not_found_in_map,
408 public static void decorate( final Phylogeny[] phylogenies,
409 final Map<String, String> map,
411 final boolean extract_bracketed_scientific_name,
412 final boolean extract_bracketed_tax_code,
414 final Map<String, String> intermediate_map,
415 final boolean cut_name_after_space,
416 final boolean process_name_intelligently,
417 final boolean process_similar_to,
418 final int numbers_of_chars_allowed_to_remove_if_not_found_in_map,
419 final boolean trim_after_tilde ) throws IllegalArgumentException, NHXFormatException,
420 PhyloXmlDataFormatException {
421 for( final Phylogeny phylogenie : phylogenies ) {
422 PhylogenyDecorator.decorate( phylogenie,
425 extract_bracketed_scientific_name,
426 extract_bracketed_tax_code,
429 cut_name_after_space,
430 process_name_intelligently,
432 numbers_of_chars_allowed_to_remove_if_not_found_in_map,
437 private static String deleteAtFirstSpace( final String name ) {
438 final int first_space = name.indexOf( " " );
439 if ( first_space > 1 ) {
440 return name.substring( 0, first_space ).trim();
445 private static String extractBracketedScientificNames( final PhylogenyNode node, final String new_value ) {
446 final int i = new_value.lastIndexOf( "[" );
447 final String scientific_name = new_value.substring( i + 1, new_value.length() - 1 );
448 AptxUtil.ensurePresenceOfTaxonomy( node );
449 node.getNodeData().getTaxonomy().setScientificName( scientific_name );
450 return new_value.substring( 0, i - 1 ).trim();
453 private static String extractBracketedTaxCodes( final PhylogenyNode node, final String new_value ) {
454 final int i = new_value.lastIndexOf( "[" );
455 final String tc = new_value.substring( i + 1, new_value.length() - 1 );
456 AptxUtil.ensurePresenceOfTaxonomy( node );
458 node.getNodeData().getTaxonomy().setTaxonomyCode( tc );
460 catch ( final PhyloXmlDataFormatException e ) {
461 throw new IllegalArgumentException( "illegal format for taxonomy code: " + tc );
463 return new_value.substring( 0, i - 1 ).trim();
466 private static String extractIntermediate( final Map<String, String> intermediate_map, final String name ) {
467 String new_name = null;
468 if ( PhylogenyDecorator.VERBOSE ) {
469 System.out.print( name + " => " );
471 if ( intermediate_map.containsKey( name ) ) {
472 new_name = intermediate_map.get( name );
473 if ( ForesterUtil.isEmpty( new_name ) ) {
474 throw new IllegalArgumentException( "\"" + name + "\" maps to null or empty string in secondary map" );
478 throw new IllegalArgumentException( "\"" + name + "\" not found in name secondary map" );
480 if ( PhylogenyDecorator.VERBOSE ) {
481 System.out.println( new_name + " " );
486 public static Map<String, Map<String, String>> parseMappingTable( final File mapping_table_file )
488 final Map<String, Map<String, String>> map = new HashMap<String, Map<String, String>>();
489 BasicTable<String> mapping_table = null;
490 mapping_table = BasicTableParser.parse( mapping_table_file, "\t", false, false );
491 for( int row = 0; row < mapping_table.getNumberOfRows(); ++row ) {
492 final Map<String, String> row_map = new HashMap<String, String>();
494 for( int col = 0; col < mapping_table.getNumberOfColumns(); ++col ) {
495 final String table_cell = mapping_table.getValue( col, row );
499 else if ( table_cell != null ) {
500 final String key = table_cell.substring( 0, table_cell.indexOf( ':' ) );
501 final String val = table_cell.substring( table_cell.indexOf( ':' ) + 1, table_cell.length() );
502 row_map.put( key, val );
505 map.put( name, row_map );
510 private static String processNameIntelligently( final String name ) {
511 final String[] s = name.split( " " );
512 if ( s.length < 2 ) {
515 else if ( ( s[ 0 ].indexOf( "_" ) > 0 ) && ( s[ 0 ].indexOf( "|" ) > 0 ) ) {
518 else if ( ( s[ 1 ].indexOf( "_" ) > 0 ) && ( s[ 1 ].indexOf( "|" ) > 0 ) ) {
521 else if ( ( s[ 0 ].indexOf( "_" ) > 0 ) && ( s[ 0 ].indexOf( "." ) > 0 ) ) {
524 else if ( ( s[ 1 ].indexOf( "_" ) > 0 ) && ( s[ 1 ].indexOf( "." ) > 0 ) ) {
527 else if ( s[ 0 ].indexOf( "_" ) > 0 ) {
530 else if ( s[ 1 ].indexOf( "_" ) > 0 ) {
538 private static String processSimilarTo( final String name ) {
539 final int i = name.toLowerCase().indexOf( "similar to" );
540 String similar_to = "";
542 similar_to = " similarity=" + name.substring( i + 10 ).trim();
544 final String pi = processNameIntelligently( name );
545 return pi + similar_to;
548 private static String sanitize( String s ) {
549 s = s.replace( ' ', '_' );
550 s = s.replace( '(', '{' );
551 s = s.replace( ')', '}' );
552 s = s.replace( '[', '{' );
553 s = s.replace( ']', '}' );
554 s = s.replace( ',', '_' );
558 public static enum FIELD {
559 NODE_NAME, SEQUENCE_ANNOTATION_DESC, DOMAIN_STRUCTURE, TAXONOMY_CODE, TAXONOMY_SCIENTIFIC_NAME, SEQUENCE_NAME;