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.Matcher;
33 import java.util.regex.Pattern;
35 import org.forester.archaeopteryx.AptxUtil;
36 import org.forester.io.parsers.nhx.NHXFormatException;
37 import org.forester.io.parsers.phyloxml.PhyloXmlDataFormatException;
38 import org.forester.phylogeny.Phylogeny;
39 import org.forester.phylogeny.PhylogenyNode;
40 import org.forester.phylogeny.data.Accession;
41 import org.forester.phylogeny.data.Annotation;
42 import org.forester.phylogeny.data.DomainArchitecture;
43 import org.forester.phylogeny.data.Identifier;
44 import org.forester.phylogeny.data.Sequence;
45 import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
46 import org.forester.util.BasicTable;
47 import org.forester.util.BasicTableParser;
48 import org.forester.util.ForesterUtil;
50 public final class PhylogenyDecorator {
52 // From evoruby/lib/evo/apps/tseq_taxonomy_processor.rb:
53 final private static String TP_TAXONOMY_CODE = "TAXONOMY_CODE";
54 final private static String TP_TAXONOMY_ID = "TAXONOMY_ID";
55 final private static String TP_TAXONOMY_ID_PROVIDER = "TAXONOMY_ID_PROVIDER";
56 final private static String TP_TAXONOMY_SN = "TAXONOMY_SN";
57 final private static String TP_TAXONOMY_CN = "TAXONOMY_CN";
58 final private static String TP_TAXONOMY_SYN = "TAXONOMY_SYN";
59 final private static String TP_SEQ_SYMBOL = "SEQ_SYMBOL";
60 final private static String TP_SEQ_ACCESSION = "SEQ_ACCESSION";
61 final private static String TP_SEQ_ACCESSION_SOURCE = "SEQ_ACCESSION_SOURCE";
62 final private static String TP_SEQ_ANNOTATION_DESC = "SEQ_ANNOTATION_DESC";
63 final private static String TP_SEQ_ANNOTATION_REF = "SEQ_ANNOTATION_REF";
64 final private static String TP_SEQ_MOL_SEQ = "SEQ_MOL_SEQ";
65 final private static String TP_SEQ_NAME = "SEQ_NAME";
66 final private static String TP_NODE_NAME = "NODE_NAME";
67 final private static Pattern NODENAME_SEQNUMBER_TAXDOMAINNUMBER = Pattern
68 .compile( "^([a-fA-Z0-9]{1,5})_([A-Z0-9]{2,4}[A-Z])(\\d{1,4})$" );
69 public final static boolean SANITIZE = false;
70 public final static boolean VERBOSE = 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 ) );
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,
186 final boolean cut_name_after_space,
187 final boolean process_name_intelligently,
188 final boolean process_similar_to,
189 final int numbers_of_chars_allowed_to_remove_if_not_found_in_map,
190 final boolean move_domain_numbers_at_end_to_middle ) throws IllegalArgumentException,
191 NHXFormatException, PhyloXmlDataFormatException {
192 PhylogenyDecorator.decorate( phylogeny,
195 extract_bracketed_scientific_name,
198 cut_name_after_space,
199 process_name_intelligently,
201 numbers_of_chars_allowed_to_remove_if_not_found_in_map,
202 move_domain_numbers_at_end_to_middle );
211 * maps names (in phylogeny) to new values if intermediate_map is
212 * null otherwise maps intermediate value to new value
215 * @param intermediate_map
216 * maps name (in phylogeny) to a intermediate value
217 * @throws IllegalArgumentException
218 * @throws PhyloXmlDataFormatException
220 public static void decorate( final Phylogeny phylogeny,
221 final Map<String, String> map,
223 final boolean extract_bracketed_scientific_name,
225 final Map<String, String> intermediate_map,
226 final boolean cut_name_after_space,
227 final boolean process_name_intelligently,
228 final boolean process_similar_to,
229 final int numbers_of_chars_allowed_to_remove_if_not_found_in_map,
230 final boolean move_domain_numbers_at_end_to_middle ) throws IllegalArgumentException,
231 PhyloXmlDataFormatException {
232 if ( extract_bracketed_scientific_name && ( field == FIELD.TAXONOMY_SCIENTIFIC_NAME ) ) {
233 throw new IllegalArgumentException( "Attempt to extract bracketed scientific name together with data field pointing to scientific name" );
235 for( final PhylogenyNodeIterator iter = phylogeny.iteratorPostorder(); iter.hasNext(); ) {
236 final PhylogenyNode node = iter.next();
237 String name = node.getName();
238 if ( !ForesterUtil.isEmpty( name ) ) {
239 if ( intermediate_map != null ) {
240 name = PhylogenyDecorator.extractIntermediate( intermediate_map, name );
242 if ( map.containsKey( name ) || ( numbers_of_chars_allowed_to_remove_if_not_found_in_map > 0 ) ) {
243 String new_value = map.get( name );
245 while ( ( new_value == null ) && ( numbers_of_chars_allowed_to_remove_if_not_found_in_map > 0 )
246 && ( x <= numbers_of_chars_allowed_to_remove_if_not_found_in_map ) ) {
247 new_value = map.get( name.substring( 0, name.length() - x ) );
250 if ( new_value != null ) {
251 new_value = new_value.trim();
252 new_value.replaceAll( "/\\s+/", " " );
253 if ( extract_bracketed_scientific_name && new_value.endsWith( "]" ) ) {
254 extractBracketedScientificNames( node, new_value );
257 case SEQUENCE_ANNOTATION_DESC:
258 if ( PhylogenyDecorator.VERBOSE ) {
259 System.out.println( name + ": " + new_value );
261 if ( !node.getNodeData().isHasSequence() ) {
262 node.getNodeData().setSequence( new Sequence() );
264 final Annotation annotation = new Annotation( "?" );
265 annotation.setDesc( new_value );
266 node.getNodeData().getSequence().addAnnotation( annotation );
268 case DOMAIN_STRUCTURE:
269 if ( PhylogenyDecorator.VERBOSE ) {
270 System.out.println( name + ": " + new_value );
272 if ( !node.getNodeData().isHasSequence() ) {
273 node.getNodeData().setSequence( new Sequence() );
275 node.getNodeData().getSequence()
276 .setDomainArchitecture( new DomainArchitecture( new_value ) );
279 if ( PhylogenyDecorator.VERBOSE ) {
280 System.out.println( name + ": " + new_value );
282 AptxUtil.ensurePresenceOfTaxonomy( node );
283 node.getNodeData().getTaxonomy().setTaxonomyCode( new_value );
285 case TAXONOMY_SCIENTIFIC_NAME:
286 if ( PhylogenyDecorator.VERBOSE ) {
287 System.out.println( name + ": " + new_value );
289 AptxUtil.ensurePresenceOfTaxonomy( node );
290 node.getNodeData().getTaxonomy().setScientificName( new_value );
293 if ( PhylogenyDecorator.VERBOSE ) {
294 System.out.println( name + ": " + new_value );
296 if ( !node.getNodeData().isHasSequence() ) {
297 node.getNodeData().setSequence( new Sequence() );
299 node.getNodeData().getSequence().setName( new_value );
302 if ( PhylogenyDecorator.VERBOSE ) {
303 System.out.print( name + " -> " );
305 if ( cut_name_after_space ) {
306 if ( PhylogenyDecorator.VERBOSE ) {
307 System.out.print( new_value + " -> " );
309 new_value = PhylogenyDecorator.deleteAtFirstSpace( new_value );
311 else if ( process_name_intelligently ) {
312 if ( PhylogenyDecorator.VERBOSE ) {
313 System.out.print( new_value + " -> " );
315 new_value = PhylogenyDecorator.processNameIntelligently( new_value );
317 else if ( process_similar_to ) {
318 if ( PhylogenyDecorator.VERBOSE ) {
319 System.out.print( new_value + " -> " );
321 new_value = PhylogenyDecorator.processSimilarTo( new_value );
323 if ( PhylogenyDecorator.SANITIZE ) {
324 new_value = PhylogenyDecorator.sanitize( new_value );
326 if ( PhylogenyDecorator.VERBOSE ) {
327 System.out.println( new_value );
329 node.setName( new_value );
332 throw new RuntimeException( "unknown field \"" + field + "\"" );
334 if ( move_domain_numbers_at_end_to_middle && ( field != FIELD.NODE_NAME ) ) {
335 node.setName( moveDomainNumbersAtEnd( node.getName() ) );
340 throw new IllegalArgumentException( "\"" + name + "\" not found in name map" );
346 public static void decorate( final Phylogeny[] phylogenies,
347 final Map<String, Map<String, String>> map,
349 final int numbers_of_chars_allowed_to_remove_if_not_found_in_map )
350 throws IllegalArgumentException, NHXFormatException, PhyloXmlDataFormatException {
351 for( int i = 0; i < phylogenies.length; ++i ) {
352 PhylogenyDecorator.decorate( phylogenies[ i ],
355 numbers_of_chars_allowed_to_remove_if_not_found_in_map );
359 public static void decorate( final Phylogeny[] phylogenies,
360 final Map<String, String> map,
362 final boolean extract_bracketed_scientific_name,
364 final boolean cut_name_after_space,
365 final boolean process_name_intelligently,
366 final boolean process_similar_to,
367 final int numbers_of_chars_allowed_to_remove_if_not_found_in_map,
368 final boolean move_domain_numbers_at_end_to_middle ) throws IllegalArgumentException,
369 NHXFormatException, PhyloXmlDataFormatException {
370 for( int i = 0; i < phylogenies.length; ++i ) {
371 PhylogenyDecorator.decorate( phylogenies[ i ],
374 extract_bracketed_scientific_name,
376 cut_name_after_space,
377 process_name_intelligently,
379 numbers_of_chars_allowed_to_remove_if_not_found_in_map,
380 move_domain_numbers_at_end_to_middle );
384 public static void decorate( final Phylogeny[] phylogenies,
385 final Map<String, String> map,
387 final boolean extract_bracketed_scientific_name,
389 final Map<String, String> intermediate_map,
390 final boolean cut_name_after_space,
391 final boolean process_name_intelligently,
392 final boolean process_similar_to,
393 final int numbers_of_chars_allowed_to_remove_if_not_found_in_map,
394 final boolean move_domain_numbers_at_end_to_middle ) throws IllegalArgumentException,
395 NHXFormatException, PhyloXmlDataFormatException {
396 for( int i = 0; i < phylogenies.length; ++i ) {
397 PhylogenyDecorator.decorate( phylogenies[ i ],
400 extract_bracketed_scientific_name,
403 cut_name_after_space,
404 process_name_intelligently,
406 numbers_of_chars_allowed_to_remove_if_not_found_in_map,
407 move_domain_numbers_at_end_to_middle );
411 private static String deleteAtFirstSpace( final String name ) {
412 final int first_space = name.indexOf( " " );
413 if ( first_space > 1 ) {
414 return name.substring( 0, first_space ).trim();
419 private static void extractBracketedScientificNames( final PhylogenyNode node, final String new_value ) {
420 final int i = new_value.lastIndexOf( "[" );
421 final String scientific_name = new_value.substring( i + 1, new_value.length() - 1 );
422 AptxUtil.ensurePresenceOfTaxonomy( node );
423 node.getNodeData().getTaxonomy().setScientificName( scientific_name );
426 private static String extractIntermediate( final Map<String, String> intermediate_map, final String name ) {
427 String new_name = null;
428 if ( PhylogenyDecorator.VERBOSE ) {
429 System.out.print( name + " => " );
431 if ( intermediate_map.containsKey( name ) ) {
432 new_name = intermediate_map.get( name );
433 if ( ForesterUtil.isEmpty( new_name ) ) {
434 throw new IllegalArgumentException( "\"" + name + "\" maps to null or empty string in secondary map" );
438 throw new IllegalArgumentException( "\"" + name + "\" not found in name secondary map" );
440 if ( PhylogenyDecorator.VERBOSE ) {
441 System.out.println( new_name + " " );
446 private static String moveDomainNumbersAtEnd( final String node_name ) {
447 final Matcher m = NODENAME_SEQNUMBER_TAXDOMAINNUMBER.matcher( node_name );
449 final String seq_number = m.group( 1 );
450 final String tax = m.group( 2 );
451 final String domain_number = m.group( 3 );
452 return seq_number + "_[" + domain_number + "]_" + tax;
459 public static Map<String, Map<String, String>> parseMappingTable( final File mapping_table_file )
461 final Map<String, Map<String, String>> map = new HashMap<String, Map<String, String>>();
462 BasicTable<String> mapping_table = null;
463 mapping_table = BasicTableParser.parse( mapping_table_file, "\t", false );
464 for( int row = 0; row < mapping_table.getNumberOfRows(); ++row ) {
465 final Map<String, String> row_map = new HashMap<String, String>();
467 for( int col = 0; col < mapping_table.getNumberOfColumns(); ++col ) {
468 final String table_cell = mapping_table.getValue( col, row );
472 else if ( table_cell != null ) {
473 final String key = table_cell.substring( 0, table_cell.indexOf( ':' ) );
474 final String val = table_cell.substring( table_cell.indexOf( ':' ) + 1, table_cell.length() );
475 row_map.put( key, val );
478 map.put( name, row_map );
483 private static String processNameIntelligently( final String name ) {
484 final String[] s = name.split( " " );
485 if ( s.length < 2 ) {
488 else if ( ( s[ 0 ].indexOf( "_" ) > 0 ) && ( s[ 0 ].indexOf( "|" ) > 0 ) ) {
491 else if ( ( s[ 1 ].indexOf( "_" ) > 0 ) && ( s[ 1 ].indexOf( "|" ) > 0 ) ) {
494 else if ( ( s[ 0 ].indexOf( "_" ) > 0 ) && ( s[ 0 ].indexOf( "." ) > 0 ) ) {
497 else if ( ( s[ 1 ].indexOf( "_" ) > 0 ) && ( s[ 1 ].indexOf( "." ) > 0 ) ) {
500 else if ( s[ 0 ].indexOf( "_" ) > 0 ) {
503 else if ( s[ 1 ].indexOf( "_" ) > 0 ) {
511 private static String processSimilarTo( final String name ) {
512 final int i = name.toLowerCase().indexOf( "similar to" );
513 String similar_to = "";
515 similar_to = " similarity=" + name.substring( i + 10 ).trim();
517 final String pi = processNameIntelligently( name );
518 return pi + similar_to;
521 private static String sanitize( String s ) {
522 s = s.replace( ' ', '_' );
523 s = s.replace( '(', '{' );
524 s = s.replace( ')', '}' );
525 s = s.replace( '[', '{' );
526 s = s.replace( ']', '}' );
527 s = s.replace( ',', '_' );
531 public static enum FIELD {
532 NODE_NAME, SEQUENCE_ANNOTATION_DESC, DOMAIN_STRUCTURE, TAXONOMY_CODE, TAXONOMY_SCIENTIFIC_NAME, SEQUENCE_NAME;