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: https://sites.google.com/site/cmzmasek/home/software/forester
26 package org.forester.tools;
29 import java.io.IOException;
30 import java.util.HashMap;
32 import java.util.regex.Matcher;
34 import org.forester.io.parsers.nhx.NHXFormatException;
35 import org.forester.io.parsers.phyloxml.PhyloXmlDataFormatException;
36 import org.forester.io.parsers.util.ParserUtils;
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 public final static boolean SANITIZE = false;
52 final private static String TP_NODE_NAME = "NODE_NAME";
53 final private static String TP_SEQ_ACCESSION = "SEQ_ACCESSION";
54 final private static String TP_SEQ_ACCESSION_SOURCE = "SEQ_ACCESSION_SOURCE";
55 final private static String TP_SEQ_ANNOTATION_DESC = "SEQ_ANNOTATION_DESC";
56 final private static String TP_SEQ_ANNOTATION_REF = "SEQ_ANNOTATION_REF";
57 final private static String TP_SEQ_MOL_SEQ = "SEQ_MOL_SEQ";
58 final private static String TP_SEQ_NAME = "SEQ_NAME";
59 final private static String TP_SEQ_SYMBOL = "SEQ_SYMBOL";
60 final private static String TP_TAXONOMY_CN = "TAXONOMY_CN";
61 // From evoruby/lib/evo/apps/tseq_taxonomy_processor.rb:
62 final private static String TP_TAXONOMY_CODE = "TAXONOMY_CODE";
63 final private static String TP_TAXONOMY_ID = "TAXONOMY_ID";
64 final private static String TP_TAXONOMY_ID_PROVIDER = "TAXONOMY_ID_PROVIDER";
65 final private static String TP_TAXONOMY_SN = "TAXONOMY_SN";
66 final private static String TP_TAXONOMY_SYN = "TAXONOMY_SYN";
68 private PhylogenyDecorator() {
72 public static void decorate( final Phylogeny phylogeny,
73 final Map<String, Map<String, String>> map,
75 final int numbers_of_chars_allowed_to_remove_if_not_found_in_map )
76 throws IllegalArgumentException, PhyloXmlDataFormatException {
77 for( final PhylogenyNodeIterator iter = phylogeny.iteratorPostorder(); iter.hasNext(); ) {
78 final PhylogenyNode node = iter.next();
79 final String name = node.getName();
80 if ( !ForesterUtil.isEmpty( name ) ) {
81 if ( map.containsKey( name ) || ( numbers_of_chars_allowed_to_remove_if_not_found_in_map > 0 ) ) {
82 Map<String, String> new_values = map.get( name );
84 while ( ( new_values == null ) && ( numbers_of_chars_allowed_to_remove_if_not_found_in_map > 0 )
85 && ( x <= numbers_of_chars_allowed_to_remove_if_not_found_in_map ) ) {
86 new_values = map.get( name.substring( 0, name.length() - x ) );
89 if ( new_values != null ) {
90 if ( new_values.containsKey( TP_TAXONOMY_CODE ) ) {
91 ForesterUtil.ensurePresenceOfTaxonomy( node );
92 node.getNodeData().getTaxonomy().setTaxonomyCode( new_values.get( TP_TAXONOMY_CODE ) );
94 if ( new_values.containsKey( TP_TAXONOMY_ID )
95 && new_values.containsKey( TP_TAXONOMY_ID_PROVIDER ) ) {
96 ForesterUtil.ensurePresenceOfTaxonomy( node );
99 .setIdentifier( new Identifier( new_values.get( TP_TAXONOMY_ID ),
100 new_values.get( TP_TAXONOMY_ID_PROVIDER ) ) );
102 else if ( new_values.containsKey( TP_TAXONOMY_ID ) ) {
103 ForesterUtil.ensurePresenceOfTaxonomy( node );
104 node.getNodeData().getTaxonomy()
105 .setIdentifier( new Identifier( new_values.get( TP_TAXONOMY_ID ) ) );
107 if ( new_values.containsKey( TP_TAXONOMY_SN ) ) {
108 ForesterUtil.ensurePresenceOfTaxonomy( node );
109 node.getNodeData().getTaxonomy().setScientificName( new_values.get( TP_TAXONOMY_SN ) );
111 if ( new_values.containsKey( TP_TAXONOMY_CN ) ) {
112 ForesterUtil.ensurePresenceOfTaxonomy( node );
113 node.getNodeData().getTaxonomy().setCommonName( new_values.get( TP_TAXONOMY_CN ) );
115 if ( new_values.containsKey( TP_TAXONOMY_SYN ) ) {
116 ForesterUtil.ensurePresenceOfTaxonomy( node );
117 node.getNodeData().getTaxonomy().getSynonyms().add( new_values.get( TP_TAXONOMY_SYN ) );
119 if ( new_values.containsKey( TP_SEQ_ACCESSION )
120 && new_values.containsKey( TP_SEQ_ACCESSION_SOURCE ) ) {
121 ForesterUtil.ensurePresenceOfSequence( node );
124 .setAccession( new Accession( new_values.get( TP_SEQ_ACCESSION ),
125 new_values.get( TP_SEQ_ACCESSION_SOURCE ) ) );
127 if ( new_values.containsKey( TP_SEQ_ANNOTATION_DESC ) ) {
128 ForesterUtil.ensurePresenceOfSequence( node );
129 final Annotation ann = new Annotation();
130 ann.setDesc( new_values.get( TP_SEQ_ANNOTATION_DESC ) );
131 node.getNodeData().getSequence().addAnnotation( ann );
133 if ( new_values.containsKey( TP_SEQ_ANNOTATION_REF ) ) {
134 ForesterUtil.ensurePresenceOfSequence( node );
135 final Annotation ann = new Annotation( new_values.get( TP_SEQ_ANNOTATION_REF ) );
136 node.getNodeData().getSequence().addAnnotation( ann );
138 if ( new_values.containsKey( TP_SEQ_SYMBOL ) ) {
139 ForesterUtil.ensurePresenceOfSequence( node );
140 node.getNodeData().getSequence().setSymbol( new_values.get( TP_SEQ_SYMBOL ) );
142 if ( new_values.containsKey( TP_SEQ_NAME ) ) {
143 ForesterUtil.ensurePresenceOfSequence( node );
144 node.getNodeData().getSequence().setName( new_values.get( TP_SEQ_NAME ) );
146 if ( new_values.containsKey( TP_SEQ_MOL_SEQ ) ) {
147 ForesterUtil.ensurePresenceOfSequence( node );
148 node.getNodeData().getSequence().setMolecularSequence( new_values.get( TP_SEQ_MOL_SEQ ) );
150 if ( new_values.containsKey( TP_NODE_NAME ) ) {
151 node.setName( new_values.get( TP_NODE_NAME ) );
153 } // if ( new_values != null )
154 } // if ( map.containsKey( name ) || ( numbers_of_chars_allowed_to_remove_if_not_found_in_map > 0 ) )
156 throw new IllegalArgumentException( "\"" + name + "\" not found in name map" );
162 public static void decorate( final Phylogeny phylogeny,
163 final Map<String, String> map,
165 final boolean extract_bracketed_scientific_name,
166 final boolean extract_bracketed_tax_code,
168 final boolean cut_name_after_space,
169 final boolean process_name_intelligently,
170 final boolean process_similar_to,
171 final int numbers_of_chars_allowed_to_remove_if_not_found_in_map,
172 final boolean trim_after_tilde,
173 final boolean verbose ) throws IllegalArgumentException, NHXFormatException,
174 PhyloXmlDataFormatException {
175 PhylogenyDecorator.decorate( phylogeny,
178 extract_bracketed_scientific_name,
179 extract_bracketed_tax_code,
182 cut_name_after_space,
183 process_name_intelligently,
185 numbers_of_chars_allowed_to_remove_if_not_found_in_map,
196 * maps names (in phylogeny) to new values if intermediate_map is
197 * null otherwise maps intermediate value to new value
200 * @param intermediate_map
201 * maps name (in phylogeny) to a intermediate value
202 * @throws IllegalArgumentException
203 * @throws PhyloXmlDataFormatException
205 public static void decorate( final Phylogeny phylogeny,
206 final Map<String, String> map,
208 final boolean extract_bracketed_scientific_name,
209 final boolean extract_bracketed_tax_code,
211 final Map<String, String> intermediate_map,
212 final boolean cut_name_after_space,
213 final boolean process_name_intelligently,
214 final boolean process_similar_to,
215 final int numbers_of_chars_allowed_to_remove_if_not_found_in_map,
216 final boolean trim_after_tilde,
217 final boolean verbose ) throws IllegalArgumentException, PhyloXmlDataFormatException {
218 if ( extract_bracketed_scientific_name && ( field == FIELD.TAXONOMY_SCIENTIFIC_NAME ) ) {
219 throw new IllegalArgumentException( "attempt to extract bracketed scientific name together with data field pointing to scientific name" );
221 if ( map.isEmpty() ) {
222 throw new IllegalArgumentException( "map is empty" );
224 for( final PhylogenyNodeIterator iter = phylogeny.iteratorPostorder(); iter.hasNext(); ) {
225 final PhylogenyNode node = iter.next();
226 String name = node.getName();
227 String tilde_annotation = null;
228 if ( trim_after_tilde && ( name.indexOf( '~' ) > 0 ) ) {
229 final int ti = name.indexOf( '~' );
230 tilde_annotation = name.substring( ti );
231 name = name.substring( 0, ti );
233 if ( !ForesterUtil.isEmpty( name ) ) {
234 if ( intermediate_map != null ) {
235 name = PhylogenyDecorator.extractIntermediate( intermediate_map, name, verbose );
237 if ( map.containsKey( name ) || ( numbers_of_chars_allowed_to_remove_if_not_found_in_map > 0 ) ) {
238 String new_value = map.get( name );
240 while ( ( new_value == null ) && ( numbers_of_chars_allowed_to_remove_if_not_found_in_map > 0 )
241 && ( x <= numbers_of_chars_allowed_to_remove_if_not_found_in_map ) ) {
242 new_value = map.get( name.substring( 0, name.length() - x ) );
245 if ( new_value != null ) {
246 new_value = new_value.trim();
247 new_value.replaceAll( "/\\s+/", " " );
248 if ( extract_bracketed_scientific_name && new_value.endsWith( "]" ) ) {
249 new_value = extractBracketedScientificNames( node, new_value );
251 else if ( extract_bracketed_tax_code ) {
252 if ( ParserUtils.TAXOMONY_CODE_PATTERN_BRACKETED.matcher( new_value ).find() ) {
253 new_value = extractBracketedTaxCodes( node, new_value );
256 throw new IllegalArgumentException( " could not get taxonomy from \"" + new_value
263 System.out.println( name + ": " + new_value );
265 if ( !node.getNodeData().isHasSequence() ) {
266 node.getNodeData().setSequence( new Sequence() );
268 node.getNodeData().getSequence().setMolecularSequence( new_value );
270 case SEQUENCE_ANNOTATION_DESC:
272 System.out.println( name + ": " + new_value );
274 if ( !node.getNodeData().isHasSequence() ) {
275 node.getNodeData().setSequence( new Sequence() );
277 final Annotation annotation = new Annotation();
278 annotation.setDesc( new_value );
279 node.getNodeData().getSequence().addAnnotation( annotation );
281 case DOMAIN_STRUCTURE:
283 System.out.println( name + ": " + new_value );
285 if ( !node.getNodeData().isHasSequence() ) {
286 node.getNodeData().setSequence( new Sequence() );
288 node.getNodeData().getSequence()
289 .setDomainArchitecture( new DomainArchitecture( new_value ) );
293 System.out.println( name + ": " + new_value );
295 ForesterUtil.ensurePresenceOfTaxonomy( node );
296 node.getNodeData().getTaxonomy().setTaxonomyCode( new_value );
298 case TAXONOMY_SCIENTIFIC_NAME:
300 System.out.println( name + ": " + new_value );
302 ForesterUtil.ensurePresenceOfTaxonomy( node );
303 node.getNodeData().getTaxonomy().setScientificName( new_value );
306 if ( trim_after_tilde ) {
307 new_value = addTildeAnnotation( tilde_annotation, new_value );
310 System.out.println( name + ": " + new_value );
312 if ( !node.getNodeData().isHasSequence() ) {
313 node.getNodeData().setSequence( new Sequence() );
315 node.getNodeData().getSequence().setName( new_value );
319 System.out.print( name + " -> " );
321 if ( cut_name_after_space ) {
323 System.out.print( new_value + " -> " );
325 new_value = PhylogenyDecorator.deleteAtFirstSpace( new_value );
327 else if ( process_name_intelligently ) {
329 System.out.print( new_value + " -> " );
331 new_value = PhylogenyDecorator.processNameIntelligently( new_value );
333 else if ( process_similar_to ) {
335 System.out.print( new_value + " -> " );
337 new_value = PhylogenyDecorator.processSimilarTo( new_value );
339 if ( PhylogenyDecorator.SANITIZE ) {
340 new_value = PhylogenyDecorator.sanitize( new_value );
342 if ( trim_after_tilde ) {
343 new_value = addTildeAnnotation( tilde_annotation, new_value );
346 System.out.println( new_value );
348 node.setName( new_value );
351 throw new RuntimeException( "unknown field \"" + field + "\"" );
356 throw new IllegalArgumentException( "\"" + name + "\" not found in name map" );
362 public static void decorate( final Phylogeny[] phylogenies,
363 final Map<String, Map<String, String>> map,
365 final int numbers_of_chars_allowed_to_remove_if_not_found_in_map )
366 throws IllegalArgumentException, NHXFormatException, PhyloXmlDataFormatException {
367 for( final Phylogeny phylogenie : phylogenies ) {
369 .decorate( phylogenie, map, picky, numbers_of_chars_allowed_to_remove_if_not_found_in_map );
373 public static void decorate( final Phylogeny[] phylogenies,
374 final Map<String, String> map,
376 final boolean extract_bracketed_scientific_name,
377 final boolean extract_bracketed_tax_code,
379 final boolean cut_name_after_space,
380 final boolean process_name_intelligently,
381 final boolean process_similar_to,
382 final int numbers_of_chars_allowed_to_remove_if_not_found_in_map,
383 final boolean trim_after_tilde,
384 final boolean verbose ) throws IllegalArgumentException, NHXFormatException,
385 PhyloXmlDataFormatException {
386 for( final Phylogeny phylogenie : phylogenies ) {
387 PhylogenyDecorator.decorate( phylogenie,
390 extract_bracketed_scientific_name,
391 extract_bracketed_tax_code,
393 cut_name_after_space,
394 process_name_intelligently,
396 numbers_of_chars_allowed_to_remove_if_not_found_in_map,
402 public static void decorate( final Phylogeny[] phylogenies,
403 final Map<String, String> map,
405 final boolean extract_bracketed_scientific_name,
406 final boolean extract_bracketed_tax_code,
408 final Map<String, String> intermediate_map,
409 final boolean cut_name_after_space,
410 final boolean process_name_intelligently,
411 final boolean process_similar_to,
412 final int numbers_of_chars_allowed_to_remove_if_not_found_in_map,
413 final boolean trim_after_tilde,
414 final boolean verbose ) throws IllegalArgumentException, NHXFormatException,
415 PhyloXmlDataFormatException {
416 for( final Phylogeny phylogenie : phylogenies ) {
417 PhylogenyDecorator.decorate( phylogenie,
420 extract_bracketed_scientific_name,
421 extract_bracketed_tax_code,
424 cut_name_after_space,
425 process_name_intelligently,
427 numbers_of_chars_allowed_to_remove_if_not_found_in_map,
433 public static Map<String, Map<String, String>> parseMappingTable( final File mapping_table_file )
435 final Map<String, Map<String, String>> map = new HashMap<String, Map<String, String>>();
436 BasicTable<String> mapping_table = null;
437 mapping_table = BasicTableParser.parse( mapping_table_file, '\t', false, false );
438 for( int row = 0; row < mapping_table.getNumberOfRows(); ++row ) {
439 final Map<String, String> row_map = new HashMap<String, String>();
441 for( int col = 0; col < mapping_table.getNumberOfColumns(); ++col ) {
442 final String table_cell = mapping_table.getValue( col, row );
446 else if ( table_cell != null ) {
447 final String key = table_cell.substring( 0, table_cell.indexOf( ':' ) );
448 final String val = table_cell.substring( table_cell.indexOf( ':' ) + 1, table_cell.length() );
449 row_map.put( key, val );
452 map.put( name, row_map );
457 private final static String addTildeAnnotation( final String tilde_annotation, final String new_value ) {
458 if ( ForesterUtil.isEmpty( tilde_annotation ) ) {
461 return new_value + tilde_annotation;
464 private static String deleteAtFirstSpace( final String name ) {
465 final int first_space = name.indexOf( " " );
466 if ( first_space > 1 ) {
467 return name.substring( 0, first_space ).trim();
472 private static String extractBracketedScientificNames( final PhylogenyNode node, final String new_value ) {
473 final int i = new_value.lastIndexOf( "[" );
474 final String scientific_name = new_value.substring( i + 1, new_value.length() - 1 );
475 ForesterUtil.ensurePresenceOfTaxonomy( node );
476 node.getNodeData().getTaxonomy().setScientificName( scientific_name );
477 return new_value.substring( 0, i - 1 ).trim();
480 private static String extractBracketedTaxCodes( final PhylogenyNode node, final String new_value ) {
481 final StringBuilder sb = new StringBuilder();
482 sb.append( new_value );
483 final String tc = extractBracketedTaxCodes( sb );
484 if ( !ForesterUtil.isEmpty( tc ) ) {
485 ForesterUtil.ensurePresenceOfTaxonomy( node );
487 node.getNodeData().getTaxonomy().setTaxonomyCode( tc );
489 catch ( final PhyloXmlDataFormatException e ) {
490 throw new IllegalArgumentException( "illegal format for taxonomy code: " + tc );
492 return sb.toString().trim();
497 private static String extractBracketedTaxCodes( final StringBuilder sb ) {
498 final Matcher m = ParserUtils.TAXOMONY_CODE_PATTERN_BRACKETED.matcher( sb );
500 final String tc = m.group( 1 );
501 sb.delete( m.start( 1 ) - 1, m.end( 1 ) + 1 );
507 private static String extractIntermediate( final Map<String, String> intermediate_map,
509 final boolean verbose ) {
510 String new_name = null;
512 System.out.print( name + " => " );
514 if ( intermediate_map.containsKey( name ) ) {
515 new_name = intermediate_map.get( name );
516 if ( ForesterUtil.isEmpty( new_name ) ) {
517 throw new IllegalArgumentException( "\"" + name + "\" maps to null or empty string in secondary map" );
521 throw new IllegalArgumentException( "\"" + name + "\" not found in name secondary map" );
524 System.out.println( new_name + " " );
529 private static String processNameIntelligently( final String name ) {
530 final String[] s = name.split( " " );
531 if ( s.length < 2 ) {
534 else if ( ( s[ 0 ].indexOf( "_" ) > 0 ) && ( s[ 0 ].indexOf( "|" ) > 0 ) ) {
537 else if ( ( s[ 1 ].indexOf( "_" ) > 0 ) && ( s[ 1 ].indexOf( "|" ) > 0 ) ) {
540 else if ( ( s[ 0 ].indexOf( "_" ) > 0 ) && ( s[ 0 ].indexOf( "." ) > 0 ) ) {
543 else if ( ( s[ 1 ].indexOf( "_" ) > 0 ) && ( s[ 1 ].indexOf( "." ) > 0 ) ) {
546 else if ( s[ 0 ].indexOf( "_" ) > 0 ) {
549 else if ( s[ 1 ].indexOf( "_" ) > 0 ) {
557 private static String processSimilarTo( final String name ) {
558 final int i = name.toLowerCase().indexOf( "similar to" );
559 String similar_to = "";
561 similar_to = " similarity=" + name.substring( i + 10 ).trim();
563 final String pi = processNameIntelligently( name );
564 return pi + similar_to;
567 private static String sanitize( String s ) {
568 s = s.replace( ' ', '_' );
569 s = s.replace( '(', '{' );
570 s = s.replace( ')', '}' );
571 s = s.replace( '[', '{' );
572 s = s.replace( ']', '}' );
573 s = s.replace( ',', '_' );
577 public static enum FIELD {
581 SEQUENCE_ANNOTATION_DESC,
584 TAXONOMY_SCIENTIFIC_NAME;