2 // FORESTER -- software libraries and applications
3 // for evolutionary biology research and applications.
5 // Copyright (C) 2013 Christian M. Zmasek
7 // This library is free software; you can redistribute it and/or
8 // modify it under the terms of the GNU Lesser General Public
9 // License as published by the Free Software Foundation; either
10 // version 2.1 of the License, or (at your option) any later version.
12 // This library is distributed in the hope that it will be useful,
13 // but WITHOUT ANY WARRANTY; without even the implied warranty of
14 // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
15 // Lesser General Public License for more details.
17 // You should have received a copy of the GNU Lesser General Public
18 // License along with this library; if not, write to the Free Software
19 // Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA
21 // Contact: phylosoft @ gmail . com
22 // WWW: https://sites.google.com/site/cmzmasek/home/software/forester
24 package org.forester.io.parsers.nhx;
26 import java.io.BufferedReader;
28 import java.io.FileNotFoundException;
29 import java.io.FileReader;
30 import java.io.IOException;
31 import java.io.InputStream;
32 import java.io.InputStreamReader;
33 import java.util.ArrayList;
34 import java.util.List;
35 import java.util.StringTokenizer;
36 import java.util.regex.Matcher;
37 import java.util.regex.Pattern;
39 import org.forester.io.parsers.IteratingPhylogenyParser;
40 import org.forester.io.parsers.PhylogenyParser;
41 import org.forester.io.parsers.phyloxml.PhyloXmlDataFormatException;
42 import org.forester.io.parsers.util.ParserUtils;
43 import org.forester.io.parsers.util.PhylogenyParserException;
44 import org.forester.phylogeny.Phylogeny;
45 import org.forester.phylogeny.PhylogenyMethods;
46 import org.forester.phylogeny.PhylogenyNode;
47 import org.forester.phylogeny.data.Accession;
48 import org.forester.phylogeny.data.Confidence;
49 import org.forester.phylogeny.data.DomainArchitecture;
50 import org.forester.phylogeny.data.Event;
51 import org.forester.phylogeny.data.Identifier;
52 import org.forester.phylogeny.data.PhylogenyDataUtil;
53 import org.forester.phylogeny.data.Sequence;
54 import org.forester.phylogeny.data.Taxonomy;
55 import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
56 import org.forester.util.ForesterUtil;
58 public final class NHXParser implements PhylogenyParser, IteratingPhylogenyParser {
60 public static final TAXONOMY_EXTRACTION TAXONOMY_EXTRACTION_DEFAULT = TAXONOMY_EXTRACTION.NO;
61 public final static Pattern NUMBERS_ONLY_PATTERN = Pattern.compile( "^[0-9\\.]+$" );
62 public final static Pattern MB_PROB_PATTERN = Pattern.compile( "prob=([^,]+)" );
63 public final static Pattern MB_PROB_SD_PATTERN = Pattern.compile( "prob_stddev=([^,]+)" );
64 public final static Pattern MB_BL_PATTERN = Pattern.compile( "length_median=([^,]+)" );
65 final static private boolean GUESS_ROOTEDNESS_DEFAULT = true;
66 final static private boolean GUESS_IF_SUPPORT_VALUES = true;
67 final static private boolean IGNORE_QUOTES_DEFAULT = false;
68 final static public boolean REPLACE_UNDERSCORES_DEFAULT = false;
69 final static private byte STRING = 0;
70 final static private byte STRING_BUFFER = 1;
71 final static private byte CHAR_ARRAY = 2;
72 final static private byte BUFFERED_READER = 3;
73 final static private byte STRING_BUILDER = 4;
74 private boolean _guess_rootedness;
75 private boolean _ignore_quotes;
76 private byte _input_type;
77 private int _source_length;
78 private PhylogenyNode _current_node;
79 private StringBuilder _current_anotation;
80 private Object _nhx_source;
81 private int _clade_level;
82 private Phylogeny _current_phylogeny;
83 private TAXONOMY_EXTRACTION _taxonomy_extraction;
84 private boolean _replace_underscores;
85 private boolean _in_comment = false;
86 private boolean _saw_colon = false;
87 private boolean _saw_closing_paren;
88 private boolean _saw_open_bracket = false;
89 private boolean _in_open_bracket = false;
90 private boolean _in_double_quote = false;
91 private boolean _in_single_quote = false;
92 private String _my_source_str = null;
93 private StringBuffer _my_source_sbuff = null;
94 private StringBuilder _my_source_sbuil = null;
95 private char[] _my_source_charary = null;
96 private BufferedReader _my_source_br = null;
98 private Phylogeny _next;
99 private Object _source;
105 public final TAXONOMY_EXTRACTION getTaxonomyExtraction() {
106 return _taxonomy_extraction;
110 public final boolean hasNext() {
111 return _next != null;
115 public final Phylogeny next() throws NHXFormatException, IOException {
116 final Phylogeny phy = _next;
122 public final Phylogeny[] parse() throws IOException {
124 final List<Phylogeny> l = new ArrayList<Phylogeny>();
125 while ( hasNext() ) {
128 final Phylogeny[] p = new Phylogeny[ l.size() ];
129 for( int i = 0; i < l.size(); ++i ) {
136 public final void reset() throws NHXFormatException, IOException {
141 _saw_open_bracket = false;
142 _in_open_bracket = false;
143 _in_double_quote = false;
144 _in_single_quote = false;
146 _current_anotation = new StringBuilder();
147 _current_phylogeny = null;
148 _current_node = null;
149 _my_source_str = null;
150 _my_source_sbuff = null;
151 _my_source_sbuil = null;
152 _my_source_charary = null;
153 _my_source_br = null;
154 determineSourceType( _source );
155 switch ( _input_type ) {
157 _my_source_str = ( String ) _nhx_source;
160 _my_source_sbuff = ( StringBuffer ) _nhx_source;
163 _my_source_sbuil = ( StringBuilder ) _nhx_source;
166 _my_source_charary = ( char[] ) _nhx_source;
168 case BUFFERED_READER:
169 if ( _my_source_br != null ) {
171 _my_source_br.close();
173 catch ( final IOException e ) {
177 _my_source_br = ( BufferedReader ) _nhx_source;
180 throw new RuntimeException( "unknown input type" );
185 public final void setGuessRootedness( final boolean guess_rootedness ) {
186 _guess_rootedness = guess_rootedness;
189 public final void setIgnoreQuotes( final boolean ignore_quotes ) {
190 _ignore_quotes = ignore_quotes;
193 public final void setReplaceUnderscores( final boolean replace_underscores ) {
194 _replace_underscores = replace_underscores;
198 public final void setSource( final Object nhx_source ) throws NHXFormatException, IOException {
199 _source = nhx_source;
203 public final void setTaxonomyExtraction( final TAXONOMY_EXTRACTION taxonomy_extraction ) {
204 _taxonomy_extraction = taxonomy_extraction;
207 private final void determineSourceType( final Object nhx_source ) throws PhylogenyParserException,
208 FileNotFoundException {
209 if ( nhx_source == null ) {
210 throw new PhylogenyParserException( getClass() + ": attempt to parse null object." );
212 else if ( nhx_source instanceof String ) {
213 _input_type = NHXParser.STRING;
214 _source_length = ( ( String ) nhx_source ).length();
215 _nhx_source = nhx_source;
217 else if ( nhx_source instanceof StringBuilder ) {
218 _input_type = NHXParser.STRING_BUILDER;
219 _source_length = ( ( StringBuilder ) nhx_source ).length();
220 _nhx_source = nhx_source;
222 else if ( nhx_source instanceof StringBuffer ) {
223 _input_type = NHXParser.STRING_BUFFER;
224 _source_length = ( ( StringBuffer ) nhx_source ).length();
225 _nhx_source = nhx_source;
227 else if ( nhx_source instanceof StringBuilder ) {
228 _input_type = NHXParser.STRING_BUILDER;
229 _source_length = ( ( StringBuilder ) nhx_source ).length();
230 _nhx_source = nhx_source;
232 else if ( nhx_source instanceof char[] ) {
233 _input_type = NHXParser.CHAR_ARRAY;
234 _source_length = ( ( char[] ) nhx_source ).length;
235 _nhx_source = nhx_source;
237 else if ( nhx_source instanceof File ) {
238 _input_type = NHXParser.BUFFERED_READER;
240 final File f = ( File ) nhx_source;
241 final String error = ForesterUtil.isReadableFile( f );
242 if ( !ForesterUtil.isEmpty( error ) ) {
243 throw new PhylogenyParserException( error );
245 _nhx_source = new BufferedReader( new FileReader( f ) );
247 else if ( nhx_source instanceof InputStream ) {
248 _input_type = NHXParser.BUFFERED_READER;
250 final InputStreamReader isr = new InputStreamReader( ( InputStream ) nhx_source );
251 _nhx_source = new BufferedReader( isr );
254 throw new IllegalArgumentException( getClass() + " can only parse objects of type String,"
255 + " StringBuffer, StringBuilder, char[], File," + " or InputStream "
256 + " [attempt to parse object of " + nhx_source.getClass() + "]." );
260 private final Phylogeny finishPhylogeny() throws PhylogenyParserException, NHXFormatException,
261 PhyloXmlDataFormatException {
262 if ( _current_phylogeny != null ) {
263 parseNHX( _current_anotation != null ? _current_anotation.toString() : "",
264 _current_phylogeny.getRoot(),
265 getTaxonomyExtraction(),
266 isReplaceUnderscores() );
267 if ( GUESS_IF_SUPPORT_VALUES ) {
268 if ( isBranchLengthsLikeBootstrapValues( _current_phylogeny ) ) {
269 moveBranchLengthsToConfidenceValues( _current_phylogeny );
272 if ( isGuessRootedness() ) {
273 final PhylogenyNode root = _current_phylogeny.getRoot();
274 if ( ( root.getDistanceToParent() >= 0.0 ) || !ForesterUtil.isEmpty( root.getName() )
275 || !ForesterUtil.isEmpty( PhylogenyMethods.getSpecies( root ) ) || root.isHasAssignedEvent() ) {
276 _current_phylogeny.setRooted( true );
279 return _current_phylogeny;
284 private final Phylogeny finishSingleNodePhylogeny() throws PhylogenyParserException, NHXFormatException,
285 PhyloXmlDataFormatException {
286 final PhylogenyNode new_node = new PhylogenyNode();
287 parseNHX( _current_anotation.toString(), new_node, getTaxonomyExtraction(), isReplaceUnderscores() );
288 _current_phylogeny = new Phylogeny();
289 _current_phylogeny.setRoot( new_node );
290 return _current_phylogeny;
293 private final void getNext() throws IOException, NHXFormatException {
294 if ( _source == null ) {
295 throw new IOException( "source is not set" );
299 if ( _input_type == BUFFERED_READER ) {
300 final int ci = _my_source_br.read();
309 if ( _i >= _source_length ) {
313 switch ( _input_type ) {
315 c = _my_source_str.charAt( _i );
318 c = _my_source_sbuff.charAt( _i );
321 c = _my_source_sbuil.charAt( _i );
324 c = _my_source_charary[ _i ];
329 if ( !_in_single_quote && !_in_double_quote ) {
333 else if ( !( ( c < 33 ) || ( c > 126 ) ) && _saw_colon
334 && ( ( c != '[' ) && ( c != '.' ) && ( ( c < 48 ) || ( c > 57 ) ) ) ) {
337 if ( _in_open_bracket && ( c == ']' ) ) {
338 _in_open_bracket = false;
341 // \n\t is always ignored,
342 // as is " (34) and ' (39) (space is 32):
343 if ( ( isIgnoreQuotes() && ( ( c < 33 ) || ( c > 126 ) || ( c == 34 ) || ( c == 39 ) || ( ( _clade_level == 0 ) && ( c == ';' ) ) ) )
344 || ( !isIgnoreQuotes() && ( ( c < 32 ) || ( c > 126 ) || ( ( _clade_level == 0 ) && ( c == ';' ) ) ) ) ) {
347 else if ( ( c == 32 ) && ( !_in_single_quote && !_in_double_quote ) ) {
350 else if ( _in_comment ) {
355 else if ( _in_double_quote ) {
357 _in_double_quote = false;
360 _current_anotation.append( c );
363 else if ( c == '"' ) {
364 _in_double_quote = true;
366 else if ( _in_single_quote ) {
368 _in_single_quote = false;
371 _current_anotation.append( c );
374 else if ( c == 39 ) {
375 _in_single_quote = true;
377 else if ( c == '[' ) {
378 _saw_open_bracket = true;
379 _in_open_bracket = true;
381 else if ( _saw_open_bracket ) {
383 // everything not starting with "[&" is considered a comment
384 // unless ":digits and/or . [bootstrap]":
386 _current_anotation.append( "[&" );
388 else if ( _saw_colon ) {
389 _current_anotation.append( "[" + c );
395 // comment consisting just of "[]":
396 _saw_open_bracket = false;
398 else if ( ( c == '(' ) && !_in_open_bracket ) {
399 final Phylogeny phy = processOpenParen();
407 else if ( ( c == ')' ) && !_in_open_bracket ) {
410 else if ( ( c == ',' ) && !_in_open_bracket ) {
414 _current_anotation.append( c );
418 if ( _clade_level != 0 ) {
419 throw new PhylogenyParserException( "error in NH (Newick) formatted data: most likely cause: number of open parens does not equal number of close parens" );
421 if ( _current_phylogeny != null ) {
422 _next = finishPhylogeny();
423 _current_phylogeny = null;
424 _current_anotation = null;
426 else if ( ( _current_anotation != null ) && ( _current_anotation.length() > 0 ) ) {
427 _next = finishSingleNodePhylogeny();
428 _current_anotation = null;
435 private final void init() {
436 setTaxonomyExtraction( TAXONOMY_EXTRACTION_DEFAULT );
437 setReplaceUnderscores( REPLACE_UNDERSCORES_DEFAULT );
438 setGuessRootedness( GUESS_ROOTEDNESS_DEFAULT );
439 setIgnoreQuotes( IGNORE_QUOTES_DEFAULT );
442 private final boolean isGuessRootedness() {
443 return _guess_rootedness;
446 private final boolean isIgnoreQuotes() {
447 return _ignore_quotes;
450 private final boolean isReplaceUnderscores() {
451 return _replace_underscores;
454 private final void processCloseParen() throws PhylogenyParserException, NHXFormatException,
455 PhyloXmlDataFormatException {
456 if ( _clade_level < 0 ) {
457 throw new PhylogenyParserException( "error in NH (Newick)/NHX formatted data: most likely cause: number of close parens is larger than number of open parens" );
460 if ( !_saw_closing_paren ) {
461 final PhylogenyNode new_node = new PhylogenyNode();
462 parseNHX( _current_anotation.toString(), new_node, getTaxonomyExtraction(), isReplaceUnderscores() );
463 _current_anotation = new StringBuilder();
464 _current_node.addAsChild( new_node );
467 parseNHX( _current_anotation.toString(),
468 _current_node.getLastChildNode(),
469 getTaxonomyExtraction(),
470 isReplaceUnderscores() );
471 _current_anotation = new StringBuilder();
473 if ( !_current_node.isRoot() ) {
474 _current_node = _current_node.getParent();
476 _saw_closing_paren = true;
479 private final void processComma() throws PhylogenyParserException, NHXFormatException, PhyloXmlDataFormatException {
480 if ( !_saw_closing_paren ) {
481 final PhylogenyNode new_node = new PhylogenyNode();
482 parseNHX( _current_anotation.toString(), new_node, getTaxonomyExtraction(), isReplaceUnderscores() );
483 if ( _current_node == null ) {
484 throw new NHXFormatException( "format might not be NH or NHX" );
486 _current_node.addAsChild( new_node );
489 parseNHX( _current_anotation.toString(),
490 _current_node.getLastChildNode(),
491 getTaxonomyExtraction(),
492 isReplaceUnderscores() );
494 _current_anotation = new StringBuilder();
495 _saw_closing_paren = false;
498 private final Phylogeny processOpenParen() throws PhylogenyParserException, NHXFormatException,
499 PhyloXmlDataFormatException {
500 Phylogeny phy = null;
501 final PhylogenyNode new_node = new PhylogenyNode();
502 if ( _clade_level == 0 ) {
503 if ( _current_phylogeny != null ) {
504 phy = finishPhylogeny();
507 _current_anotation = new StringBuilder();
508 _current_phylogeny = new Phylogeny();
509 _current_phylogeny.setRoot( new_node );
513 _current_node.addAsChild( new_node );
515 _current_node = new_node;
516 _saw_closing_paren = false;
520 public final static void parseNHX( String s,
521 final PhylogenyNode node_to_annotate,
522 final TAXONOMY_EXTRACTION taxonomy_extraction,
523 final boolean replace_underscores ) throws NHXFormatException,
524 PhyloXmlDataFormatException {
525 if ( ( taxonomy_extraction != TAXONOMY_EXTRACTION.NO ) && replace_underscores ) {
526 throw new IllegalArgumentException( "cannot extract taxonomies and replace under scores at the same time" );
528 if ( ( s != null ) && ( s.length() > 0 ) ) {
529 if ( replace_underscores ) {
530 s = s.replaceAll( "_+", " " );
532 boolean is_nhx = false;
533 final int ob = s.indexOf( "[" );
537 final int cb = s.indexOf( "]" );
539 throw new NHXFormatException( "error in NHX formatted data: no closing \"]\" in \"" + s + "\"" );
541 if ( s.indexOf( "&&NHX" ) == ( ob + 1 ) ) {
542 b = s.substring( ob + 6, cb );
545 // No &&NHX and digits only: is likely to be a support value.
546 final String bracketed = s.substring( ob + 1, cb );
547 final Matcher numbers_only = NUMBERS_ONLY_PATTERN.matcher( bracketed );
548 if ( numbers_only.matches() ) {
549 b = ":" + NHXtags.SUPPORT + bracketed;
551 else if ( s.indexOf( "prob=" ) > -1 ) {
552 processMrBayes3Data( s, node_to_annotate );
555 s = s.substring( 0, ob ) + b;
556 if ( ( s.indexOf( "[" ) > -1 ) || ( s.indexOf( "]" ) > -1 ) ) {
557 throw new NHXFormatException( "error in NHX formatted data: more than one \"]\" or \"[\"" );
560 final StringTokenizer t = new StringTokenizer( s, ":" );
561 if ( t.countTokens() > 0 ) {
562 if ( !s.startsWith( ":" ) ) {
563 node_to_annotate.setName( t.nextToken() );
564 if ( !replace_underscores && ( !is_nhx && ( taxonomy_extraction != TAXONOMY_EXTRACTION.NO ) ) ) {
565 ParserUtils.extractTaxonomyDataFromNodeName( node_to_annotate, taxonomy_extraction );
568 while ( t.hasMoreTokens() ) {
570 if ( s.startsWith( NHXtags.SPECIES_NAME ) ) {
571 if ( !node_to_annotate.getNodeData().isHasTaxonomy() ) {
572 node_to_annotate.getNodeData().setTaxonomy( new Taxonomy() );
574 node_to_annotate.getNodeData().getTaxonomy().setScientificName( s.substring( 2 ) );
576 else if ( s.startsWith( NHXtags.IS_DUPLICATION ) ) {
577 if ( ( s.charAt( 2 ) == 'Y' ) || ( s.charAt( 2 ) == 'T' ) ) {
578 node_to_annotate.getNodeData().setEvent( Event.createSingleDuplicationEvent() );
580 else if ( ( s.charAt( 2 ) == 'N' ) || ( s.charAt( 2 ) == 'F' ) ) {
581 node_to_annotate.getNodeData().setEvent( Event.createSingleSpeciationEvent() );
583 else if ( s.charAt( 2 ) == '?' ) {
584 node_to_annotate.getNodeData().setEvent( Event.createSingleSpeciationOrDuplicationEvent() );
587 throw new NHXFormatException( "error in NHX formatted data: :D=Y or :D=N or :D=?" );
590 else if ( s.startsWith( NHXtags.SUPPORT ) ) {
591 PhylogenyMethods.setConfidence( node_to_annotate, doubleValue( s.substring( 2 ) ) );
593 else if ( s.startsWith( NHXtags.TAXONOMY_ID ) ) {
594 if ( !node_to_annotate.getNodeData().isHasTaxonomy() ) {
595 node_to_annotate.getNodeData().setTaxonomy( new Taxonomy() );
597 node_to_annotate.getNodeData().getTaxonomy().setIdentifier( new Identifier( s.substring( 2 ) ) );
599 else if ( s.startsWith( NHXtags.DOMAIN_STRUCTURE ) ) {
600 if ( !node_to_annotate.getNodeData().isHasSequence() ) {
601 node_to_annotate.getNodeData().setSequence( new Sequence() );
603 node_to_annotate.getNodeData().getSequence()
604 .setDomainArchitecture( new DomainArchitecture( s.substring( 3 ) ) );
606 else if ( s.startsWith( NHXtags.SEQUENCE_ACCESSION ) ) {
607 if ( !node_to_annotate.getNodeData().isHasSequence() ) {
608 node_to_annotate.getNodeData().setSequence( new Sequence() );
610 node_to_annotate.getNodeData().getSequence()
611 .setAccession( new Accession( s.substring( 3 ), "?" ) );
613 else if ( s.startsWith( NHXtags.GENE_NAME ) ) {
614 if ( !node_to_annotate.getNodeData().isHasSequence() ) {
615 node_to_annotate.getNodeData().setSequence( new Sequence() );
617 node_to_annotate.getNodeData().getSequence().setName( s.substring( 3 ) );
619 else if ( s.indexOf( '=' ) < 0 ) {
620 if ( node_to_annotate.getDistanceToParent() != PhylogenyDataUtil.BRANCH_LENGTH_DEFAULT ) {
621 throw new NHXFormatException( "error in NHX formatted data: more than one distance to parent:"
624 node_to_annotate.setDistanceToParent( doubleValue( s ) );
626 } // while ( t.hasMoreTokens() )
631 private final static double doubleValue( final String str ) throws NHXFormatException {
633 return Double.valueOf( str ).doubleValue();
635 catch ( final NumberFormatException ex ) {
636 throw new NHXFormatException( "error in NH/NHX formatted data: failed to parse number from " + "\"" + str
641 private final static boolean isBranchLengthsLikeBootstrapValues( final Phylogeny p ) {
642 final PhylogenyNodeIterator it = p.iteratorExternalForward();
643 final double d0 = it.next().getDistanceToParent();
644 if ( ( d0 < 10 ) || !it.hasNext() ) {
647 while ( it.hasNext() ) {
648 final double d = it.next().getDistanceToParent();
649 if ( ( d != d0 ) || ( d < 10 ) ) {
656 private final static void moveBranchLengthsToConfidenceValues( final Phylogeny p ) {
657 final PhylogenyNodeIterator it = p.iteratorPostorder();
658 while ( it.hasNext() ) {
659 final PhylogenyNode n = it.next();
660 PhylogenyMethods.setBootstrapConfidence( n, n.getDistanceToParent() );
661 n.setDistanceToParent( PhylogenyDataUtil.BRANCH_LENGTH_DEFAULT );
665 private final static void processMrBayes3Data( final String s, final PhylogenyNode node_to_annotate )
666 throws NHXFormatException {
668 final Matcher mb_prob_sd_matcher = MB_PROB_SD_PATTERN.matcher( s );
669 if ( mb_prob_sd_matcher.find() ) {
671 sd = Double.parseDouble( mb_prob_sd_matcher.group( 1 ) );
673 catch ( final NumberFormatException e ) {
674 throw new NHXFormatException( "failed to parse probability standard deviation (Mr Bayes output) from \""
678 final Matcher mb_prob_matcher = MB_PROB_PATTERN.matcher( s );
679 if ( mb_prob_matcher.find() ) {
682 prob = Double.parseDouble( mb_prob_matcher.group( 1 ) );
684 catch ( final NumberFormatException e ) {
685 throw new NHXFormatException( "failed to parse probability (Mr Bayes output) from \"" + s + "\"" );
689 node_to_annotate.getBranchData()
690 .addConfidence( new Confidence( prob, "posterior probability", sd ) );
693 node_to_annotate.getBranchData().addConfidence( new Confidence( prob, "posterior probability" ) );
697 final Matcher mb_bl_matcher = MB_BL_PATTERN.matcher( s );
698 if ( mb_bl_matcher.find() ) {
701 bl = Double.parseDouble( mb_bl_matcher.group( 1 ) );
703 catch ( final NumberFormatException e ) {
704 throw new NHXFormatException( "failed to parse median branch length (Mr Bayes output) from \"" + s
708 node_to_annotate.setDistanceToParent( bl );
713 public static enum TAXONOMY_EXTRACTION {
714 NO, PFAM_STYLE_RELAXED, PFAM_STYLE_STRICT, AGGRESSIVE;