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 private final static boolean DEBUG = true;
65 private final static String URL_ENC = "UTF-8";
67 public static List<UniProtTaxonomy> getTaxonomiesFromCommonNameStrict( final String cn,
68 final int max_taxonomies_return )
70 final List<UniProtTaxonomy> taxonomies = getTaxonomiesFromCommonName( cn, max_taxonomies_return );
71 if ( ( taxonomies != null ) && ( taxonomies.size() > 0 ) ) {
72 final List<UniProtTaxonomy> filtered_taxonomies = new ArrayList<UniProtTaxonomy>();
73 for( final UniProtTaxonomy taxonomy : taxonomies ) {
74 if ( taxonomy.getCommonName().equalsIgnoreCase( cn ) ) {
75 filtered_taxonomies.add( taxonomy );
78 return filtered_taxonomies;
83 public static List<UniProtTaxonomy> getTaxonomiesFromId( final String id, final int max_taxonomies_return )
85 final List<String> result = getTaxonomyStringFromId( id, max_taxonomies_return );
86 if ( result.size() > 0 ) {
87 return parseUniProtTaxonomy( result );
93 * Does not return "sub-types".
94 * For example, for "Mus musculus" only returns "Mus musculus"
95 * and not "Mus musculus", "Mus musculus bactrianus", ...
98 public static List<UniProtTaxonomy> getTaxonomiesFromScientificNameStrict( final String sn,
99 final int max_taxonomies_return )
101 final List<UniProtTaxonomy> taxonomies = getTaxonomiesFromScientificName( sn, max_taxonomies_return );
102 if ( ( taxonomies != null ) && ( taxonomies.size() > 0 ) ) {
103 final List<UniProtTaxonomy> filtered_taxonomies = new ArrayList<UniProtTaxonomy>();
104 for( final UniProtTaxonomy taxonomy : taxonomies ) {
105 if ( taxonomy.getScientificName().equalsIgnoreCase( sn ) ) {
106 filtered_taxonomies.add( taxonomy );
109 return filtered_taxonomies;
114 public static List<UniProtTaxonomy> getTaxonomiesFromTaxonomyCode( final String code,
115 final int max_taxonomies_return )
117 final String my_code = new String( code );
118 final List<String> result = getTaxonomyStringFromTaxonomyCode( my_code, max_taxonomies_return );
119 if ( result.size() > 0 ) {
120 return parseUniProtTaxonomy( result );
125 public static SequenceDatabaseEntry obtainEmblEntry( final Accession acc ) throws IOException {
126 return obtainEmblEntry( acc, DEFAULT_LINES_TO_RETURN );
129 public static SequenceDatabaseEntry obtainEmblEntry( final Accession acc, final int max_lines_to_return )
131 final List<String> lines = queryEmblDb( acc, max_lines_to_return );
132 return EbiDbEntry.createInstanceFromPlainTextForRefSeq( lines );
135 public static SequenceDatabaseEntry obtainEntry( final String acc_str ) throws IOException {
136 if ( ForesterUtil.isEmpty( acc_str ) ) {
137 throw new IllegalArgumentException( "cannot not extract sequence db accessor from null or empty string" );
139 final Accession acc = SequenceAccessionTools.parseAccessorFromString( acc_str );
141 throw new IllegalArgumentException( "could not extract acceptable sequence db accessor from \"" + acc_str
144 if ( acc.getSource().equals( Source.REFSEQ.toString() ) || acc.getSource().equals( Source.EMBL.toString() )
145 || acc.getSource().equals( Source.NCBI.toString() ) ) {
146 return obtainEmblEntry( acc, DEFAULT_LINES_TO_RETURN );
148 else if ( acc.getSource().equals( Source.UNIPROT.toString() ) ) {
149 return obtainUniProtEntry( acc.getValue(), DEFAULT_LINES_TO_RETURN );
152 throw new IllegalArgumentException( "don't know how to handle request for source \"" + acc.getSource()
157 public static SequenceDatabaseEntry obtainRefSeqEntryFromEmbl( final Accession acc ) throws IOException {
158 return obtainRefSeqEntryFromEmbl( acc, DEFAULT_LINES_TO_RETURN );
161 public static SequenceDatabaseEntry obtainRefSeqEntryFromEmbl( final Accession acc, final int max_lines_to_return )
163 final List<String> lines = queryEmblDbForRefSeqEntry( acc, max_lines_to_return );
164 return EbiDbEntry.createInstanceFromPlainTextForRefSeq( lines );
167 public final static Accession obtainSeqAccession( final PhylogenyNode node ) {
168 Accession acc = SequenceAccessionTools.obtainFromSeqAccession( node );
169 if ( !isAccessionAcceptable( acc ) ) {
170 acc = SequenceAccessionTools.obtainAccessorFromDataFields( node );
175 public final static void obtainSeqInformation( final boolean allow_to_set_taxonomic_data,
176 final int lines_to_return,
177 final SortedSet<String> not_found,
178 final PhylogenyNode node ) throws IOException {
179 final Accession acc = obtainSeqAccession( node );
180 if ( !isAccessionAcceptable( acc ) ) {
181 if ( node.isExternal() || !node.isEmpty() ) {
182 not_found.add( node.toString() );
186 addDataFromDbToNode( allow_to_set_taxonomic_data, lines_to_return, not_found, node, acc );
190 public final static void obtainSeqInformation( final boolean allow_to_set_taxonomic_data,
191 final SortedSet<String> not_found,
192 final PhylogenyNode node ) throws IOException {
193 obtainSeqInformation( allow_to_set_taxonomic_data, DEFAULT_LINES_TO_RETURN, not_found, node );
196 public final static SortedSet<String> obtainSeqInformation( final Phylogeny phy,
197 final boolean ext_nodes_only,
198 final boolean allow_to_set_taxonomic_data,
199 final int lines_to_return ) throws IOException {
200 final SortedSet<String> not_found = new TreeSet<String>();
201 for( final PhylogenyNodeIterator iter = phy.iteratorPostorder(); iter.hasNext(); ) {
202 final PhylogenyNode node = iter.next();
203 if ( node.isExternal() || !ext_nodes_only ) {
204 obtainSeqInformation( allow_to_set_taxonomic_data, lines_to_return, not_found, node );
210 public final static void obtainSeqInformation( final PhylogenyNode node ) throws IOException {
211 obtainSeqInformation( true, DEFAULT_LINES_TO_RETURN, new TreeSet<String>(), node );
214 public static SequenceDatabaseEntry obtainUniProtEntry( final String query ) throws IOException {
215 return obtainUniProtEntry( query, DEFAULT_LINES_TO_RETURN );
218 public static SequenceDatabaseEntry obtainUniProtEntry( final String query, final int max_lines_to_return )
220 final List<String> lines = queryUniprot( "uniprot/" + query + ".txt", max_lines_to_return );
221 return UniProtEntry.createInstanceFromPlainText( lines );
224 public static List<String> queryDb( final String query, int max_lines_to_return, final String base_url )
226 if ( ForesterUtil.isEmpty( query ) ) {
227 throw new IllegalArgumentException( "illegal attempt to use empty query " );
229 if ( max_lines_to_return < 1 ) {
230 max_lines_to_return = 1;
232 final URL url = new URL( base_url + query );
234 System.out.println( "url: " + url.toString() );
236 final URLConnection urlc = url.openConnection();
237 final BufferedReader in = new BufferedReader( new InputStreamReader( urlc.getInputStream() ) );
239 final List<String> result = new ArrayList<String>();
240 while ( ( line = in.readLine() ) != null ) {
242 System.out.println( line );
245 if ( result.size() > max_lines_to_return ) {
251 // To prevent accessing online dbs in too quick succession.
254 catch ( final InterruptedException e ) {
260 public static List<String> queryEmblDb( final Accession id, final int max_lines_to_return ) throws IOException {
261 final StringBuilder url_sb = new StringBuilder();
262 // url_sb.append( BASE_EMBL_DB_URL );
263 if ( id.getSource().equals( Source.NCBI.toString() ) ) {
264 url_sb.append( EMBL_GENBANK );
265 //url_sb.append( '/' );
267 else if ( id.getSource().equals( Source.REFSEQ.toString() ) ) {
268 url_sb.append( EMBL_REFSEQ );
269 // if ( id.getValue().toUpperCase().indexOf( 'P' ) == 1 ) {
270 // url_sb.append( SequenceDbWsTools.EMBL_DBS_REFSEQ_P );
271 // url_sb.append( '/' );
274 // url_sb.append( SequenceDbWsTools.EMBL_DBS_REFSEQ_N );
275 // url_sb.append( '/' );
279 throw new IllegalArgumentException( "unable to handle source: " + id.getSource() );
281 return queryDb( id.getValue(), max_lines_to_return, url_sb.toString() );
284 public static List<String> queryEmblDbForRefSeqEntry( final Accession id, final int max_lines_to_return )
286 final StringBuilder url_sb = new StringBuilder();
287 url_sb.append( EMBL_REFSEQ );
288 return queryDb( id.getValue(), max_lines_to_return, url_sb.toString() );
291 public static List<String> queryUniprot( final String query, final int max_lines_to_return ) throws IOException {
292 return queryDb( query, max_lines_to_return, BASE_UNIPROT_URL );
295 final static String extractFrom( final String target, final String a ) {
296 final int i_a = target.indexOf( a );
297 return target.substring( i_a + a.length() ).trim();
300 final static String extractFromTo( final String target, final String a, final String b ) {
301 final int i_a = target.indexOf( a );
302 final int i_b = target.indexOf( b );
303 if ( ( i_a < 0 ) || ( i_b < i_a ) ) {
304 throw new IllegalArgumentException( "attempt to extract from \"" + target + "\" between \"" + a
305 + "\" and \"" + b + "\"" );
307 return target.substring( i_a + a.length(), i_b ).trim();
310 final static String extractTo( final String target, final String b ) {
311 final int i_b = target.indexOf( b );
312 return target.substring( 0, i_b ).trim();
315 private static void addDataFromDbToNode( final boolean allow_to_set_taxonomic_data,
316 final int lines_to_return,
317 final SortedSet<String> not_found,
318 final PhylogenyNode node,
319 final Accession acc ) throws IOException {
320 SequenceDatabaseEntry db_entry = null;
321 final String query = acc.getValue();
322 if ( acc.getSource().equals( Source.UNIPROT.toString() ) ) {
324 System.out.println( "uniprot: " + query );
327 db_entry = obtainUniProtEntry( query, lines_to_return );
329 catch ( final FileNotFoundException e ) {
330 // Eat this, and move to next.
333 else if ( acc.getSource().equals( Source.EMBL.toString() ) ) {
335 System.out.println( "embl: " + query );
338 db_entry = obtainEmblEntry( new Accession( query ), lines_to_return );
340 catch ( final FileNotFoundException e ) {
341 // Eat this, and move to next.
344 else if ( acc.getSource().equals( Source.REFSEQ.toString() ) ) {
346 System.out.println( "refseq: " + query );
349 db_entry = obtainRefSeqEntryFromEmbl( new Accession( query ), lines_to_return );
351 catch ( final FileNotFoundException e ) {
352 // Eat this, and move to next.
355 if ( ( db_entry != null ) && !db_entry.isEmpty() ) {
356 final Sequence seq = node.getNodeData().isHasSequence() ? node.getNodeData().getSequence() : new Sequence();
357 if ( !ForesterUtil.isEmpty( db_entry.getAccession() ) ) {
358 seq.setAccession( new Accession( db_entry.getAccession(), acc.getSource() ) );
360 if ( !ForesterUtil.isEmpty( db_entry.getSequenceName() ) ) {
361 seq.setName( db_entry.getSequenceName() );
363 if ( !ForesterUtil.isEmpty( db_entry.getGeneName() ) ) {
364 seq.setGeneName( db_entry.getGeneName() );
366 if ( !ForesterUtil.isEmpty( db_entry.getSequenceSymbol() ) ) {
368 seq.setSymbol( db_entry.getSequenceSymbol() );
370 catch ( final PhyloXmlDataFormatException e ) {
371 // Eat this exception.
374 if ( ( db_entry.getGoTerms() != null ) && !db_entry.getGoTerms().isEmpty() ) {
375 for( final GoTerm go : db_entry.getGoTerms() ) {
376 final Annotation ann = new Annotation( go.getGoId().getId() );
377 ann.setDesc( go.getName() );
378 seq.addAnnotation( ann );
381 if ( ( db_entry.getCrossReferences() != null ) && !db_entry.getCrossReferences().isEmpty() ) {
382 for( final Accession x : db_entry.getCrossReferences() ) {
383 seq.addCrossReference( x );
386 final Taxonomy tax = node.getNodeData().isHasTaxonomy() ? node.getNodeData().getTaxonomy() : new Taxonomy();
387 if ( !ForesterUtil.isEmpty( db_entry.getTaxonomyScientificName() ) ) {
388 tax.setScientificName( db_entry.getTaxonomyScientificName() );
390 if ( allow_to_set_taxonomic_data && !ForesterUtil.isEmpty( db_entry.getTaxonomyIdentifier() ) ) {
391 tax.setIdentifier( new Identifier( db_entry.getTaxonomyIdentifier(), "uniprot" ) );
393 node.getNodeData().setTaxonomy( tax );
394 node.getNodeData().setSequence( seq );
397 if ( node.isExternal() || !node.isEmpty() ) {
398 not_found.add( node.toString() );
402 Thread.sleep( 10 );// Sleep for 10 ms
404 catch ( final InterruptedException ie ) {
408 private static String encode( final String str ) throws UnsupportedEncodingException {
409 return URLEncoder.encode( str.trim(), URL_ENC );
412 private static List<UniProtTaxonomy> getTaxonomiesFromCommonName( final String cn, final int max_taxonomies_return )
414 final List<String> result = getTaxonomyStringFromCommonName( cn, max_taxonomies_return );
415 if ( result.size() > 0 ) {
416 return parseUniProtTaxonomy( result );
421 private static List<UniProtTaxonomy> getTaxonomiesFromScientificName( final String sn,
422 final int max_taxonomies_return )
424 final List<String> result = getTaxonomyStringFromScientificName( sn, max_taxonomies_return );
425 if ( result.size() > 0 ) {
426 return parseUniProtTaxonomy( result );
431 private static List<String> getTaxonomyStringFromCommonName( final String cn, final int max_lines_to_return )
433 return queryUniprot( "taxonomy/?query=common%3a%22" + encode( cn ) + "%22&format=tab", max_lines_to_return );
436 private static List<String> getTaxonomyStringFromId( final String id, final int max_lines_to_return )
438 return queryUniprot( "taxonomy/?query=id%3a%22" + encode( id ) + "%22&format=tab", max_lines_to_return );
441 private static List<String> getTaxonomyStringFromScientificName( final String sn, final int max_lines_to_return )
443 return queryUniprot( "taxonomy/?query=scientific%3a%22" + encode( sn ) + "%22&format=tab", max_lines_to_return );
446 private static List<String> getTaxonomyStringFromTaxonomyCode( final String code, final int max_lines_to_return )
448 return queryUniprot( "taxonomy/?query=mnemonic%3a%22" + encode( code ) + "%22&format=tab", max_lines_to_return );
451 private final static boolean isAccessionAcceptable( final Accession acc ) {
452 return ( !( ( acc == null ) || ForesterUtil.isEmpty( acc.getSource() ) || ForesterUtil.isEmpty( acc.getValue() ) || ( ( acc
453 .getSource().equals( Source.UNIPROT.toString() ) )
454 && ( acc.getSource().toString().equals( Source.EMBL.toString() ) ) && ( acc.getSource().toString()
455 .equals( Source.REFSEQ.toString() ) ) ) ) );
458 private static List<UniProtTaxonomy> parseUniProtTaxonomy( final List<String> result ) throws IOException {
459 final List<UniProtTaxonomy> taxonomies = new ArrayList<UniProtTaxonomy>();
460 for( final String line : result ) {
461 if ( ForesterUtil.isEmpty( line ) ) {
462 // Ignore empty lines.
464 else if ( line.startsWith( "Taxon" ) ) {
465 final String[] items = line.split( "\t" );
466 if ( !( items[ 1 ].equalsIgnoreCase( "Mnemonic" ) && items[ 2 ].equalsIgnoreCase( "Scientific name" )
467 && items[ 3 ].equalsIgnoreCase( "Common name" ) && items[ 4 ].equalsIgnoreCase( "Synonym" )
468 && items[ 5 ].equalsIgnoreCase( "Other Names" ) && items[ 6 ].equalsIgnoreCase( "Reviewed" )
469 && items[ 7 ].equalsIgnoreCase( "Rank" ) && items[ 8 ].equalsIgnoreCase( "Lineage" ) ) ) {
470 throw new IOException( "Unreconized UniProt Taxonomy format: " + line );
474 if ( line.split( "\t" ).length > 4 ) {
475 taxonomies.add( new UniProtTaxonomy( line ) );