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.FileNotFoundException;
30 import java.io.IOException;
31 import java.io.InputStreamReader;
32 import java.io.UnsupportedEncodingException;
34 import java.net.URLConnection;
35 import java.net.URLEncoder;
36 import java.util.ArrayList;
37 import java.util.List;
38 import java.util.SortedSet;
39 import java.util.TreeSet;
41 import org.forester.go.GoTerm;
42 import org.forester.io.parsers.phyloxml.PhyloXmlDataFormatException;
43 import org.forester.phylogeny.Phylogeny;
44 import org.forester.phylogeny.PhylogenyNode;
45 import org.forester.phylogeny.data.Accession;
46 import org.forester.phylogeny.data.Accession.Source;
47 import org.forester.phylogeny.data.Annotation;
48 import org.forester.phylogeny.data.Identifier;
49 import org.forester.phylogeny.data.Sequence;
50 import org.forester.phylogeny.data.Taxonomy;
51 import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
52 import org.forester.util.ForesterUtil;
53 import org.forester.util.SequenceAccessionTools;
55 public final class SequenceDbWsTools {
57 public final static String BASE_UNIPROT_URL = "http://www.uniprot.org/";
58 public final static int DEFAULT_LINES_TO_RETURN = 4000;
59 //public final static String EMBL_DBS_EMBL = "embl";
60 public final static String EMBL_DBS_REFSEQ_N = "refseqn";
61 public final static String EMBL_DBS_REFSEQ_P = "refseqp";
62 public final static String EMBL_GENBANK = "http://www.ebi.ac.uk/Tools/dbfetch/dbfetch?db=GENBANK&style=raw&id=";
63 public final static String EMBL_REFSEQ = "http://www.ebi.ac.uk/Tools/dbfetch/dbfetch?db=REFSEQ&style=raw&id=";
64 public final static String EMBL_EMBL = "http://www.ebi.ac.uk/Tools/dbfetch/dbfetch?db=EMBL&style=raw&id=";
65 private final static boolean DEBUG = true;
66 private final static String URL_ENC = "UTF-8";
68 public static List<UniProtTaxonomy> getTaxonomiesFromCommonNameStrict( final String cn,
69 final int max_taxonomies_return )
71 final List<UniProtTaxonomy> taxonomies = getTaxonomiesFromCommonName( cn, max_taxonomies_return );
72 if ( ( taxonomies != null ) && ( taxonomies.size() > 0 ) ) {
73 final List<UniProtTaxonomy> filtered_taxonomies = new ArrayList<UniProtTaxonomy>();
74 for( final UniProtTaxonomy taxonomy : taxonomies ) {
75 if ( taxonomy.getCommonName().equalsIgnoreCase( cn ) ) {
76 filtered_taxonomies.add( taxonomy );
79 return filtered_taxonomies;
84 public static List<UniProtTaxonomy> getTaxonomiesFromId( final String id, final int max_taxonomies_return )
86 final List<String> result = getTaxonomyStringFromId( id, max_taxonomies_return );
87 if ( result.size() > 0 ) {
88 return parseUniProtTaxonomy( result );
94 * Does not return "sub-types".
95 * For example, for "Mus musculus" only returns "Mus musculus"
96 * and not "Mus musculus", "Mus musculus bactrianus", ...
99 public static List<UniProtTaxonomy> getTaxonomiesFromScientificNameStrict( final String sn,
100 final int max_taxonomies_return )
102 final List<UniProtTaxonomy> taxonomies = getTaxonomiesFromScientificName( sn, max_taxonomies_return );
103 if ( ( taxonomies != null ) && ( taxonomies.size() > 0 ) ) {
104 final List<UniProtTaxonomy> filtered_taxonomies = new ArrayList<UniProtTaxonomy>();
105 for( final UniProtTaxonomy taxonomy : taxonomies ) {
106 if ( taxonomy.getScientificName().equalsIgnoreCase( sn ) ) {
107 filtered_taxonomies.add( taxonomy );
110 return filtered_taxonomies;
115 public static List<UniProtTaxonomy> getTaxonomiesFromTaxonomyCode( final String code,
116 final int max_taxonomies_return )
118 final String my_code = new String( code );
119 final List<String> result = getTaxonomyStringFromTaxonomyCode( my_code, max_taxonomies_return );
120 if ( result.size() > 0 ) {
121 return parseUniProtTaxonomy( result );
126 public static SequenceDatabaseEntry obtainEmblEntry( final Accession acc ) throws IOException {
127 return obtainEmblEntry( acc, DEFAULT_LINES_TO_RETURN );
130 public static SequenceDatabaseEntry obtainEmblEntry( final Accession acc, final int max_lines_to_return )
132 final List<String> lines = queryEmblDb( acc, max_lines_to_return );
133 return EbiDbEntry.createInstanceFromPlainTextForRefSeq( lines );
136 public static SequenceDatabaseEntry obtainEntry( final String acc_str ) throws IOException {
137 if ( ForesterUtil.isEmpty( acc_str ) ) {
138 throw new IllegalArgumentException( "cannot not extract sequence db accessor from null or empty string" );
140 final Accession acc = SequenceAccessionTools.parseAccessorFromString( acc_str );
142 throw new IllegalArgumentException( "could not extract acceptable sequence db accessor from \"" + acc_str
145 if ( acc.getSource().equals( Source.REFSEQ.toString() ) || acc.getSource().equals( Source.EMBL.toString() )
146 || acc.getSource().equals( Source.NCBI.toString() ) ) {
147 return obtainEmblEntry( acc, DEFAULT_LINES_TO_RETURN );
149 else if ( acc.getSource().equals( Source.UNIPROT.toString() ) ) {
150 return obtainUniProtEntry( acc.getValue(), DEFAULT_LINES_TO_RETURN );
153 throw new IllegalArgumentException( "don't know how to handle request for source \"" + acc.getSource()
158 public static SequenceDatabaseEntry obtainRefSeqEntryFromEmbl( final Accession acc ) throws IOException {
159 return obtainRefSeqEntryFromEmbl( acc, DEFAULT_LINES_TO_RETURN );
162 public static SequenceDatabaseEntry obtainRefSeqEntryFromEmbl( final Accession acc, final int max_lines_to_return )
164 final List<String> lines = queryEmblDbForRefSeqEntry( acc, max_lines_to_return );
165 return EbiDbEntry.createInstanceFromPlainTextForRefSeq( lines );
168 public final static Accession obtainSeqAccession( final PhylogenyNode node ) {
169 Accession acc = SequenceAccessionTools.obtainFromSeqAccession( node );
170 if ( !isAccessionAcceptable( acc ) ) {
171 acc = SequenceAccessionTools.obtainAccessorFromDataFields( node );
176 public final static void obtainSeqInformation( final boolean allow_to_set_taxonomic_data,
177 final int lines_to_return,
178 final SortedSet<String> not_found,
179 final PhylogenyNode node ) throws IOException {
180 final Accession acc = obtainSeqAccession( node );
181 if ( !isAccessionAcceptable( acc ) ) {
182 if ( node.isExternal() || !node.isEmpty() ) {
183 not_found.add( node.toString() );
187 addDataFromDbToNode( allow_to_set_taxonomic_data, lines_to_return, not_found, node, acc );
191 public final static void obtainSeqInformation( final boolean allow_to_set_taxonomic_data,
192 final SortedSet<String> not_found,
193 final PhylogenyNode node ) throws IOException {
194 obtainSeqInformation( allow_to_set_taxonomic_data, DEFAULT_LINES_TO_RETURN, not_found, node );
197 public final static SortedSet<String> obtainSeqInformation( final Phylogeny phy,
198 final boolean ext_nodes_only,
199 final boolean allow_to_set_taxonomic_data,
200 final int lines_to_return ) throws IOException {
201 final SortedSet<String> not_found = new TreeSet<String>();
202 for( final PhylogenyNodeIterator iter = phy.iteratorPostorder(); iter.hasNext(); ) {
203 final PhylogenyNode node = iter.next();
204 if ( node.isExternal() || !ext_nodes_only ) {
205 obtainSeqInformation( allow_to_set_taxonomic_data, lines_to_return, not_found, node );
211 public final static void obtainSeqInformation( final PhylogenyNode node ) throws IOException {
212 obtainSeqInformation( true, DEFAULT_LINES_TO_RETURN, new TreeSet<String>(), node );
215 public static SequenceDatabaseEntry obtainUniProtEntry( final String query ) throws IOException {
216 return obtainUniProtEntry( query, DEFAULT_LINES_TO_RETURN );
219 public static SequenceDatabaseEntry obtainUniProtEntry( final String query, final int max_lines_to_return )
221 final List<String> lines = queryUniprot( "uniprot/" + query + ".txt", max_lines_to_return );
222 return UniProtEntry.createInstanceFromPlainText( lines );
225 public static List<String> queryDb( final String query, int max_lines_to_return, final String base_url )
227 if ( ForesterUtil.isEmpty( query ) ) {
228 throw new IllegalArgumentException( "illegal attempt to use empty query " );
230 if ( max_lines_to_return < 1 ) {
231 max_lines_to_return = 1;
233 final URL url = new URL( base_url + query );
235 System.out.println( "url: " + url.toString() );
237 final URLConnection urlc = url.openConnection();
238 final BufferedReader in = new BufferedReader( new InputStreamReader( urlc.getInputStream() ) );
240 final List<String> result = new ArrayList<String>();
241 while ( ( line = in.readLine() ) != null ) {
243 System.out.println( line );
246 if ( result.size() > max_lines_to_return ) {
252 // To prevent accessing online dbs in too quick succession.
255 catch ( final InterruptedException e ) {
261 public static List<String> queryEmblDb( final Accession acc, final int max_lines_to_return ) throws IOException {
262 final StringBuilder url_sb = new StringBuilder();
263 // url_sb.append( BASE_EMBL_DB_URL );
264 System.out.println( "source: " + acc.getSource() );
265 if ( acc.getSource().equals( Source.NCBI.toString() ) ) {
266 url_sb.append( EMBL_GENBANK );
267 //url_sb.append( '/' );
269 else if ( acc.getSource().equals( Source.REFSEQ.toString() ) ) {
270 url_sb.append( EMBL_REFSEQ );
272 else if ( acc.getSource().equals( Source.EMBL.toString() ) ) {
273 url_sb.append( EMBL_EMBL );
276 throw new IllegalArgumentException( "unable to handle source: " + acc.getSource() );
278 return queryDb( acc.getValue(), max_lines_to_return, url_sb.toString() );
281 public static List<String> queryEmblDbForRefSeqEntry( final Accession id, final int max_lines_to_return )
283 final StringBuilder url_sb = new StringBuilder();
284 url_sb.append( EMBL_REFSEQ );
285 return queryDb( id.getValue(), max_lines_to_return, url_sb.toString() );
288 public static List<String> queryUniprot( final String query, final int max_lines_to_return ) throws IOException {
289 return queryDb( query, max_lines_to_return, BASE_UNIPROT_URL );
292 final static String extractFrom( final String target, final String a ) {
293 final int i_a = target.indexOf( a );
294 return target.substring( i_a + a.length() ).trim();
297 final static String extractFromTo( final String target, final String a, final String b ) {
298 final int i_a = target.indexOf( a );
299 final int i_b = target.indexOf( b );
300 if ( ( i_a < 0 ) || ( i_b < i_a ) ) {
301 throw new IllegalArgumentException( "attempt to extract from \"" + target + "\" between \"" + a
302 + "\" and \"" + b + "\"" );
304 return target.substring( i_a + a.length(), i_b ).trim();
307 final static String extractTo( final String target, final String b ) {
308 final int i_b = target.indexOf( b );
309 return target.substring( 0, i_b ).trim();
312 private static void addDataFromDbToNode( final boolean allow_to_set_taxonomic_data,
313 final int lines_to_return,
314 final SortedSet<String> not_found,
315 final PhylogenyNode node,
316 final Accession acc ) throws IOException {
317 SequenceDatabaseEntry db_entry = null;
318 final String query = acc.getValue();
319 if ( acc.getSource().equals( Source.UNIPROT.toString() ) ) {
321 System.out.println( "uniprot: " + query );
324 db_entry = obtainUniProtEntry( query, lines_to_return );
326 catch ( final FileNotFoundException e ) {
327 // Eat this, and move to next.
330 else if ( acc.getSource().equals( Source.REFSEQ.toString() ) ) {
332 System.out.println( "refseq: " + query );
335 db_entry = obtainRefSeqEntryFromEmbl( new Accession( query ), lines_to_return );
337 catch ( final FileNotFoundException e ) {
338 // Eat this, and move to next.
341 else if ( acc.getSource().equals( Source.EMBL.toString() ) || acc.getSource().equals( Source.NCBI.toString() )
342 || acc.getSource().equals( Source.EMBL.toString() ) ) {
344 System.out.println( acc.toString() );
347 db_entry = obtainEmblEntry( acc, lines_to_return );
349 catch ( final FileNotFoundException e ) {
350 // Eat this, and move to next.
353 else if ( acc.getSource().equals( Source.GI.toString() ) ) {
355 System.out.println( "gi: " + query );
358 db_entry = obtainRefSeqEntryFromEmbl( new Accession( query ), lines_to_return );
360 catch ( final FileNotFoundException e ) {
361 // Eat this, and move to next.
364 if ( ( db_entry != null ) && !db_entry.isEmpty() ) {
365 final Sequence seq = node.getNodeData().isHasSequence() ? node.getNodeData().getSequence() : new Sequence();
366 if ( !ForesterUtil.isEmpty( db_entry.getAccession() ) ) {
367 seq.setAccession( new Accession( db_entry.getAccession(), acc.getSource() ) );
369 if ( !ForesterUtil.isEmpty( db_entry.getSequenceName() ) ) {
370 seq.setName( db_entry.getSequenceName() );
372 if ( !ForesterUtil.isEmpty( db_entry.getGeneName() ) ) {
373 seq.setGeneName( db_entry.getGeneName() );
375 if ( !ForesterUtil.isEmpty( db_entry.getSequenceSymbol() ) ) {
377 seq.setSymbol( db_entry.getSequenceSymbol() );
379 catch ( final PhyloXmlDataFormatException e ) {
380 // Eat this exception.
383 if ( ( db_entry.getGoTerms() != null ) && !db_entry.getGoTerms().isEmpty() ) {
384 for( final GoTerm go : db_entry.getGoTerms() ) {
385 final Annotation ann = new Annotation( go.getGoId().getId() );
386 ann.setDesc( go.getName() );
387 seq.addAnnotation( ann );
390 if ( ( db_entry.getCrossReferences() != null ) && !db_entry.getCrossReferences().isEmpty() ) {
391 for( final Accession x : db_entry.getCrossReferences() ) {
392 seq.addCrossReference( x );
395 if ( !ForesterUtil.isEmpty( db_entry.getChromosome() ) && !ForesterUtil.isEmpty( db_entry.getMap() ) ) {
396 seq.setLocation( "chr " + db_entry.getChromosome() + ", " + db_entry.getMap() );
398 else if ( !ForesterUtil.isEmpty( db_entry.getChromosome() ) ) {
399 seq.setLocation( "chr " + db_entry.getChromosome() );
401 else if ( !ForesterUtil.isEmpty( db_entry.getMap() ) ) {
402 seq.setLocation( db_entry.getMap() );
404 final Taxonomy tax = node.getNodeData().isHasTaxonomy() ? node.getNodeData().getTaxonomy() : new Taxonomy();
405 if ( !ForesterUtil.isEmpty( db_entry.getTaxonomyScientificName() ) ) {
406 tax.setScientificName( db_entry.getTaxonomyScientificName() );
408 if ( allow_to_set_taxonomic_data && !ForesterUtil.isEmpty( db_entry.getTaxonomyIdentifier() ) ) {
409 tax.setIdentifier( new Identifier( db_entry.getTaxonomyIdentifier(), "uniprot" ) );
411 node.getNodeData().setTaxonomy( tax );
412 node.getNodeData().setSequence( seq );
415 if ( node.isExternal() || !node.isEmpty() ) {
416 not_found.add( node.toString() );
420 Thread.sleep( 10 );// Sleep for 10 ms
422 catch ( final InterruptedException ie ) {
426 private static String encode( final String str ) throws UnsupportedEncodingException {
427 return URLEncoder.encode( str.trim(), URL_ENC );
430 private static List<UniProtTaxonomy> getTaxonomiesFromCommonName( final String cn, final int max_taxonomies_return )
432 final List<String> result = getTaxonomyStringFromCommonName( cn, max_taxonomies_return );
433 if ( result.size() > 0 ) {
434 return parseUniProtTaxonomy( result );
439 private static List<UniProtTaxonomy> getTaxonomiesFromScientificName( final String sn,
440 final int max_taxonomies_return )
442 final List<String> result = getTaxonomyStringFromScientificName( sn, max_taxonomies_return );
443 if ( result.size() > 0 ) {
444 return parseUniProtTaxonomy( result );
449 private static List<String> getTaxonomyStringFromCommonName( final String cn, final int max_lines_to_return )
451 return queryUniprot( "taxonomy/?query=common%3a%22" + encode( cn ) + "%22&format=tab", max_lines_to_return );
454 private static List<String> getTaxonomyStringFromId( final String id, final int max_lines_to_return )
456 return queryUniprot( "taxonomy/?query=id%3a%22" + encode( id ) + "%22&format=tab", max_lines_to_return );
459 private static List<String> getTaxonomyStringFromScientificName( final String sn, final int max_lines_to_return )
461 return queryUniprot( "taxonomy/?query=scientific%3a%22" + encode( sn ) + "%22&format=tab", max_lines_to_return );
464 private static List<String> getTaxonomyStringFromTaxonomyCode( final String code, final int max_lines_to_return )
466 return queryUniprot( "taxonomy/?query=mnemonic%3a%22" + encode( code ) + "%22&format=tab", max_lines_to_return );
469 private final static boolean isAccessionAcceptable( final Accession acc ) {
470 return ( !( ( acc == null ) || ForesterUtil.isEmpty( acc.getSource() ) || ForesterUtil.isEmpty( acc.getValue() ) || ( ( acc
471 .getSource().equals( Source.UNIPROT.toString() ) )
472 && ( acc.getSource().toString().equals( Source.EMBL.toString() ) ) && ( acc.getSource().toString()
473 .equals( Source.REFSEQ.toString() ) ) ) ) );
476 private static List<UniProtTaxonomy> parseUniProtTaxonomy( final List<String> result ) throws IOException {
477 final List<UniProtTaxonomy> taxonomies = new ArrayList<UniProtTaxonomy>();
478 for( final String line : result ) {
479 if ( ForesterUtil.isEmpty( line ) ) {
480 // Ignore empty lines.
482 else if ( line.startsWith( "Taxon" ) ) {
483 final String[] items = line.split( "\t" );
484 if ( !( items[ 1 ].equalsIgnoreCase( "Mnemonic" ) && items[ 2 ].equalsIgnoreCase( "Scientific name" )
485 && items[ 3 ].equalsIgnoreCase( "Common name" ) && items[ 4 ].equalsIgnoreCase( "Synonym" )
486 && items[ 5 ].equalsIgnoreCase( "Other Names" ) && items[ 6 ].equalsIgnoreCase( "Reviewed" )
487 && items[ 7 ].equalsIgnoreCase( "Rank" ) && items[ 8 ].equalsIgnoreCase( "Lineage" ) ) ) {
488 throw new IOException( "Unreconized UniProt Taxonomy format: " + line );
492 if ( line.split( "\t" ).length > 4 ) {
493 taxonomies.add( new UniProtTaxonomy( line ) );