2 // forester -- software libraries and applications
3 // for genomics and evolutionary biology research.
5 // Copyright (C) 2010 Christian M Zmasek
6 // Copyright (C) 2010 Sanford-Burnham Medical Research Institute
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.ws.seqdb;
28 import java.io.BufferedReader;
29 import java.io.IOException;
30 import java.io.InputStreamReader;
31 import java.io.UnsupportedEncodingException;
33 import java.net.URLConnection;
34 import java.net.URLEncoder;
35 import java.util.ArrayList;
36 import java.util.List;
37 import java.util.SortedSet;
38 import java.util.TreeSet;
40 import org.forester.phylogeny.Phylogeny;
41 import org.forester.phylogeny.PhylogenyNode;
42 import org.forester.phylogeny.data.Accession;
43 import org.forester.phylogeny.data.Identifier;
44 import org.forester.phylogeny.data.Sequence;
45 import org.forester.phylogeny.data.Taxonomy;
46 import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
47 import org.forester.util.ForesterUtil;
48 import org.forester.util.SequenceIdParser;
50 public final class SequenceDbWsTools {
52 private static final boolean ALLOW_TAXONOMY_CODE_HACKS = true; //TODO turn off for final realease!
53 public final static String BASE_UNIPROT_URL = "http://www.uniprot.org/";
54 public final static String BASE_EMBL_DB_URL = "http://www.ebi.ac.uk/Tools/dbfetch/dbfetch/";
55 public final static String EMBL_DBS_EMBL = "embl";
56 public final static String EMBL_DBS_REFSEQ_P = "refseqp";
57 public final static String EMBL_DBS_REFSEQ_N = "refseqn";
58 private final static String URL_ENC = "UTF-8";
59 private final static boolean DEBUG = false;
61 public static List<UniProtTaxonomy> getTaxonomiesFromCommonName( final String cn, final int max_taxonomies_return )
63 final List<String> result = getTaxonomyStringFromCommonName( cn, max_taxonomies_return );
64 if ( result.size() > 0 ) {
65 return parseUniProtTaxonomy( result );
70 public static List<UniProtTaxonomy> getTaxonomiesFromCommonNameStrict( final String cn,
71 final int max_taxonomies_return )
73 final List<UniProtTaxonomy> taxonomies = getTaxonomiesFromCommonName( cn, max_taxonomies_return );
74 if ( ( taxonomies != null ) && ( taxonomies.size() > 0 ) ) {
75 final List<UniProtTaxonomy> filtered_taxonomies = new ArrayList<UniProtTaxonomy>();
76 for( final UniProtTaxonomy taxonomy : taxonomies ) {
77 if ( taxonomy.getCommonName().equalsIgnoreCase( cn ) ) {
78 filtered_taxonomies.add( taxonomy );
81 return filtered_taxonomies;
86 public static List<UniProtTaxonomy> getTaxonomiesFromId( final String id, final int max_taxonomies_return )
88 final List<String> result = getTaxonomyStringFromId( id, max_taxonomies_return );
89 if ( result.size() > 0 ) {
90 return parseUniProtTaxonomy( result );
95 public static List<UniProtTaxonomy> getTaxonomiesFromScientificName( final String sn,
96 final int max_taxonomies_return )
99 if ( sn.equals( "Drosophila" ) ) {
100 return uniProtTaxonomyToList( UniProtTaxonomy.DROSOPHILA_GENUS );
102 else if ( sn.equals( "Xenopus" ) ) {
103 return uniProtTaxonomyToList( UniProtTaxonomy.XENOPUS_GENUS );
105 // else if ( sn.equals( "Nucleariidae and Fonticula group" ) ) {
106 // return hack( UniProtTaxonomy.NUCLEARIIDAE_AND_FONTICULA );
108 final List<String> result = getTaxonomyStringFromScientificName( sn, max_taxonomies_return );
109 if ( result.size() > 0 ) {
110 return parseUniProtTaxonomy( result );
116 * Does not return "sub-types".
117 * For example, for "Mus musculus" only returns "Mus musculus"
118 * and not "Mus musculus", "Mus musculus bactrianus", ...
121 public static List<UniProtTaxonomy> getTaxonomiesFromScientificNameStrict( final String sn,
122 final int max_taxonomies_return )
124 final List<UniProtTaxonomy> taxonomies = getTaxonomiesFromScientificName( sn, max_taxonomies_return );
125 if ( ( taxonomies != null ) && ( taxonomies.size() > 0 ) ) {
126 final List<UniProtTaxonomy> filtered_taxonomies = new ArrayList<UniProtTaxonomy>();
127 for( final UniProtTaxonomy taxonomy : taxonomies ) {
128 if ( taxonomy.getScientificName().equalsIgnoreCase( sn ) ) {
129 filtered_taxonomies.add( taxonomy );
132 return filtered_taxonomies;
137 public static List<UniProtTaxonomy> getTaxonomiesFromTaxonomyCode( final String code,
138 final int max_taxonomies_return )
140 final String my_code = new String( code );
141 if ( ALLOW_TAXONOMY_CODE_HACKS ) {
142 final List<UniProtTaxonomy> l = resolveFakeTaxonomyCodes( max_taxonomies_return, my_code );
147 final List<String> result = getTaxonomyStringFromTaxonomyCode( my_code, max_taxonomies_return );
148 if ( result.size() > 0 ) {
149 return parseUniProtTaxonomy( result );
154 public static SequenceDatabaseEntry obtainEmblEntry( final Identifier id, final int max_lines_to_return )
156 final List<String> lines = queryEmblDb( id, max_lines_to_return );
157 return EbiDbEntry.createInstanceFromPlainText( lines );
160 public static SequenceDatabaseEntry obtainRefSeqEntryFromEmbl( final Identifier id, final int max_lines_to_return )
162 final List<String> lines = queryEmblDb( id, max_lines_to_return );
163 return EbiDbEntry.createInstanceFromPlainTextForRefSeq( lines );
166 public static SortedSet<String> obtainSeqInformation( final Phylogeny phy,
167 final boolean ext_nodes_only,
168 final boolean allow_to_set_taxonomic_data,
169 final int lines_to_return ) throws IOException {
170 final SortedSet<String> not_found = new TreeSet<String>();
171 for( final PhylogenyNodeIterator iter = phy.iteratorPostorder(); iter.hasNext(); ) {
172 final PhylogenyNode node = iter.next();
173 if ( ext_nodes_only && node.isInternal() ) {
177 Identifier id = null;
179 if ( node.getNodeData().isHasSequence() && ( node.getNodeData().getSequence().getAccession() != null )
180 && !ForesterUtil.isEmpty( node.getNodeData().getSequence().getAccession().getSource() )
181 && !ForesterUtil.isEmpty( node.getNodeData().getSequence().getAccession().getValue() )
182 && node.getNodeData().getSequence().getAccession().getValue().toLowerCase().startsWith( "uniprot" ) ) {
183 query = node.getNodeData().getSequence().getAccession().getValue();
186 else if ( node.getNodeData().isHasSequence()
187 && ( node.getNodeData().getSequence().getAccession() != null )
188 && !ForesterUtil.isEmpty( node.getNodeData().getSequence().getAccession().getSource() )
189 && !ForesterUtil.isEmpty( node.getNodeData().getSequence().getAccession().getValue() )
190 && ( node.getNodeData().getSequence().getAccession().getValue().toLowerCase().startsWith( "embl" ) || node
191 .getNodeData().getSequence().getAccession().getValue().toLowerCase().startsWith( "ebi" ) ) ) {
192 query = node.getNodeData().getSequence().getAccession().getValue();
195 else if ( !ForesterUtil.isEmpty( node.getName() ) ) {
196 if ( ( query = ForesterUtil.extractUniProtKbProteinSeqIdentifier( node ) ) != null ) {
199 else if ( ( id = SequenceIdParser.parse( node.getName() ) ) != null ) {
200 if ( id.getProvider().equalsIgnoreCase( Identifier.NCBI ) ) {
203 else if ( id.getProvider().equalsIgnoreCase( Identifier.REFSEQ ) ) {
208 if ( db == Db.NONE ) {
209 not_found.add( node.getName() );
211 SequenceDatabaseEntry db_entry = null;
212 if ( !ForesterUtil.isEmpty( query ) ) {
213 if ( db == Db.UNIPROT ) {
215 System.out.println( "uniprot: " + query );
217 db_entry = obtainUniProtEntry( query, lines_to_return );
219 if ( ( db == Db.EMBL ) || ( ( db == Db.UNIPROT ) && ( db_entry == null ) ) ) {
221 System.out.println( "embl: " + query );
223 db_entry = obtainEmblEntry( new Identifier( query ), lines_to_return );
224 if ( ( db == Db.UNIPROT ) && ( db_entry != null ) ) {
229 else if ( ( db == Db.REFSEQ ) && ( id != null ) ) {
230 db_entry = obtainRefSeqEntryFromEmbl( id, lines_to_return );
232 else if ( ( db == Db.NCBI ) && ( id != null ) ) {
233 db_entry = obtainEmblEntry( id, lines_to_return );
235 if ( ( db_entry != null ) && !db_entry.isEmpty() ) {
236 final Sequence seq = node.getNodeData().isHasSequence() ? node.getNodeData().getSequence()
238 if ( !ForesterUtil.isEmpty( db_entry.getAccession() ) ) {
240 if ( db == Db.EMBL ) {
243 else if ( db == Db.UNIPROT ) {
246 else if ( db == Db.NCBI ) {
249 else if ( db == Db.REFSEQ ) {
252 seq.setAccession( new Accession( db_entry.getAccession(), type ) );
254 if ( !ForesterUtil.isEmpty( db_entry.getSequenceName() ) ) {
255 seq.setName( db_entry.getSequenceName() );
257 if ( !ForesterUtil.isEmpty( db_entry.getSequenceSymbol() ) ) {
258 seq.setSymbol( db_entry.getSequenceSymbol() );
260 final Taxonomy tax = node.getNodeData().isHasTaxonomy() ? node.getNodeData().getTaxonomy()
262 if ( !ForesterUtil.isEmpty( db_entry.getTaxonomyScientificName() ) ) {
263 tax.setScientificName( db_entry.getTaxonomyScientificName() );
265 if ( allow_to_set_taxonomic_data && !ForesterUtil.isEmpty( db_entry.getTaxonomyIdentifier() ) ) {
266 tax.setIdentifier( new Identifier( db_entry.getTaxonomyIdentifier(), "uniprot" ) );
268 node.getNodeData().setTaxonomy( tax );
269 node.getNodeData().setSequence( seq );
271 else if ( db != Db.NONE ) {
272 not_found.add( node.getName() );
275 Thread.sleep( 10 );// Sleep for 10 ms
277 catch ( final InterruptedException ie ) {
283 public static SequenceDatabaseEntry obtainUniProtEntry( final String query, final int max_lines_to_return )
285 final List<String> lines = queryUniprot( "uniprot/" + query + ".txt", max_lines_to_return );
286 return UniProtEntry.createInstanceFromPlainText( lines );
289 public static List<String> queryDb( final String query, int max_lines_to_return, final String base_url )
291 if ( ForesterUtil.isEmpty( query ) ) {
292 throw new IllegalArgumentException( "illegal attempt to use empty query " );
294 if ( max_lines_to_return < 1 ) {
295 max_lines_to_return = 1;
297 final URL url = new URL( base_url + query );
299 System.out.println( "url: " + url.toString() );
301 final URLConnection urlc = url.openConnection();
302 final BufferedReader in = new BufferedReader( new InputStreamReader( urlc.getInputStream() ) );
304 final List<String> result = new ArrayList<String>();
305 while ( ( line = in.readLine() ) != null ) {
307 System.out.println( line );
310 if ( result.size() > max_lines_to_return ) {
316 // To prevent accessing online dbs in too quick succession.
319 catch ( final InterruptedException e ) {
325 public static List<String> queryEmblDb( final Identifier id, final int max_lines_to_return ) throws IOException {
326 final StringBuilder url_sb = new StringBuilder();
327 url_sb.append( BASE_EMBL_DB_URL );
328 if ( ForesterUtil.isEmpty( id.getProvider() ) || id.getProvider().equalsIgnoreCase( Identifier.NCBI ) ) {
329 url_sb.append( SequenceDbWsTools.EMBL_DBS_EMBL );
330 url_sb.append( '/' );
332 else if ( id.getProvider().equalsIgnoreCase( Identifier.REFSEQ ) ) {
333 if ( id.getValue().toUpperCase().indexOf( 'P' ) == 1 ) {
334 url_sb.append( SequenceDbWsTools.EMBL_DBS_REFSEQ_P );
335 url_sb.append( '/' );
338 url_sb.append( SequenceDbWsTools.EMBL_DBS_REFSEQ_N );
339 url_sb.append( '/' );
342 return queryDb( id.getValue(), max_lines_to_return, url_sb.toString() );
345 public static List<String> queryUniprot( final String query, final int max_lines_to_return ) throws IOException {
346 return queryDb( query, max_lines_to_return, BASE_UNIPROT_URL );
349 private static String encode( final String str ) throws UnsupportedEncodingException {
350 return URLEncoder.encode( str.trim(), URL_ENC );
353 private static List<String> getTaxonomyStringFromCommonName( final String cn, final int max_lines_to_return )
355 return queryUniprot( "taxonomy/?query=common%3a%22" + encode( cn ) + "%22&format=tab", max_lines_to_return );
358 private static List<String> getTaxonomyStringFromId( final String id, final int max_lines_to_return )
360 return queryUniprot( "taxonomy/?query=id%3a%22" + encode( id ) + "%22&format=tab", max_lines_to_return );
363 private static List<String> getTaxonomyStringFromScientificName( final String sn, final int max_lines_to_return )
365 return queryUniprot( "taxonomy/?query=scientific%3a%22" + encode( sn ) + "%22&format=tab", max_lines_to_return );
368 private static List<String> getTaxonomyStringFromTaxonomyCode( final String code, final int max_lines_to_return )
370 return queryUniprot( "taxonomy/?query=mnemonic%3a%22" + encode( code ) + "%22&format=tab", max_lines_to_return );
373 private static List<UniProtTaxonomy> parseUniProtTaxonomy( final List<String> result ) throws IOException {
374 final List<UniProtTaxonomy> taxonomies = new ArrayList<UniProtTaxonomy>();
375 for( final String line : result ) {
376 if ( ForesterUtil.isEmpty( line ) ) {
377 // Ignore empty lines.
379 else if ( line.startsWith( "Taxon" ) ) {
380 final String[] items = line.split( "\t" );
381 if ( !( items[ 1 ].equalsIgnoreCase( "Mnemonic" ) && items[ 2 ].equalsIgnoreCase( "Scientific name" )
382 && items[ 3 ].equalsIgnoreCase( "Common name" ) && items[ 4 ].equalsIgnoreCase( "Synonym" )
383 && items[ 5 ].equalsIgnoreCase( "Other Names" ) && items[ 6 ].equalsIgnoreCase( "Reviewed" )
384 && items[ 7 ].equalsIgnoreCase( "Rank" ) && items[ 8 ].equalsIgnoreCase( "Lineage" ) ) ) {
385 throw new IOException( "Unreconized UniProt Taxonomy format: " + line );
389 if ( line.split( "\t" ).length > 4 ) {
390 taxonomies.add( new UniProtTaxonomy( line ) );
397 private static List<UniProtTaxonomy> resolveFakeTaxonomyCodes( final int max_taxonomies_return, final String code )
399 if ( code.equals( "CAP" ) ) {
400 return getTaxonomiesFromId( "283909", max_taxonomies_return );
402 else if ( code.equals( "FUGRU" ) ) {
403 return getTaxonomiesFromId( "31033", max_taxonomies_return );
405 else if ( code.equals( "GIALA" ) ) {
406 return getTaxonomiesFromId( "5741", max_taxonomies_return );
408 else if ( code.equals( "TRIVE" ) ) {
409 return getTaxonomiesFromId( "413071", max_taxonomies_return );
411 else if ( code.equals( "CAPOWC" ) ) {
412 return getTaxonomiesFromId( "192875", max_taxonomies_return );
414 else if ( code.equals( "SPHARC" ) ) {
415 return getTaxonomiesFromId( "667725", max_taxonomies_return );
417 else if ( code.equals( "THETRA" ) ) {
418 return getTaxonomiesFromId( "529818", max_taxonomies_return );
420 else if ( code.equals( "CHLVUL" ) ) {
421 return getTaxonomiesFromId( "574566", max_taxonomies_return );
423 else if ( code.equals( "CITCLE" ) ) {
424 return getTaxonomiesFromId( "85681", max_taxonomies_return );
426 else if ( code.equals( "MYCPOP" ) ) {
427 return getTaxonomiesFromId( "85929", max_taxonomies_return );
429 else if ( code.equals( "AGABB" ) ) {
430 return getTaxonomiesFromId( "597362", max_taxonomies_return );
432 else if ( code.equals( "BAUCOM" ) ) {
433 return getTaxonomiesFromId( "430998", max_taxonomies_return );
435 else if ( code.equals( "DICSQU" ) ) {
436 return getTaxonomiesFromId( "114155", max_taxonomies_return );
438 else if ( code.equals( "FOMPIN" ) ) {
439 return getTaxonomiesFromId( "40483", max_taxonomies_return );
441 else if ( code.equals( "HYDMA" ) ) {
442 return getTaxonomiesFromId( "6085", max_taxonomies_return );
444 else if ( code.equals( "MYCFI" ) ) {
445 return getTaxonomiesFromId( "83344", max_taxonomies_return );
447 else if ( code.equals( "OIDMAI" ) ) {
448 return getTaxonomiesFromId( "78148", max_taxonomies_return );
450 else if ( code.equals( "OSTRC" ) ) {
451 return getTaxonomiesFromId( "385169", max_taxonomies_return );
453 else if ( code.equals( "POSPL" ) ) {
454 return getTaxonomiesFromId( "104341", max_taxonomies_return );
456 else if ( code.equals( "SAICOM" ) ) {
457 return getTaxonomiesFromId( "5606", max_taxonomies_return );
459 else if ( code.equals( "SERLA" ) ) {
460 return getTaxonomiesFromId( "85982", max_taxonomies_return );
462 else if ( code.equals( "SPORO" ) ) {
463 return getTaxonomiesFromId( "40563", max_taxonomies_return );
465 else if ( code.equals( "ACRALC" ) ) {
466 return getTaxonomiesFromId( "398408", max_taxonomies_return );
468 else if ( code.equals( "THITER" ) ) {
469 return getTaxonomiesFromId( "35720", max_taxonomies_return );
471 else if ( code.equals( "MYCTHE" ) ) {
472 return getTaxonomiesFromId( "78579", max_taxonomies_return );
474 else if ( code.equals( "CONPUT" ) ) {
475 return getTaxonomiesFromId( "80637", max_taxonomies_return );
477 else if ( code.equals( "WOLCOC" ) ) {
478 return getTaxonomiesFromId( "81056", max_taxonomies_return );
480 else if ( code.equals( "CLAGRA" ) ) {
481 return getTaxonomiesFromId( "27339", max_taxonomies_return );
483 else if ( code.equals( "XANPAR" ) ) {
484 return getTaxonomiesFromId( "107463", max_taxonomies_return );
486 else if ( code.equals( "HYDPIN" ) ) {
487 return getTaxonomiesFromId( "388859", max_taxonomies_return );
489 else if ( code.equals( "SERLAC" ) ) {
490 return getTaxonomiesFromId( "85982", max_taxonomies_return );
497 private static List<UniProtTaxonomy> uniProtTaxonomyToList( final UniProtTaxonomy tax ) {
498 final List<UniProtTaxonomy> l = new ArrayList<UniProtTaxonomy>();
504 UNIPROT, EMBL, NCBI, NONE, REFSEQ;