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.Annotation;
47 import org.forester.phylogeny.data.Identifier;
48 import org.forester.phylogeny.data.Sequence;
49 import org.forester.phylogeny.data.Taxonomy;
50 import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
51 import org.forester.util.ForesterUtil;
52 import org.forester.util.SequenceAccessionTools;
54 public final class SequenceDbWsTools {
56 public final static String BASE_UNIPROT_URL = "http://www.uniprot.org/";
57 public final static String BASE_EMBL_DB_URL = "http://www.ebi.ac.uk/Tools/dbfetch/dbfetch/";
58 public final static String EMBL_DBS_EMBL = "embl";
59 public final static String EMBL_DBS_REFSEQ_P = "refseqp";
60 public final static String EMBL_DBS_REFSEQ_N = "refseqn";
61 private final static String URL_ENC = "UTF-8";
62 private final static boolean DEBUG = true;
64 private static List<UniProtTaxonomy> getTaxonomiesFromCommonName( final String cn, final int max_taxonomies_return )
66 final List<String> result = getTaxonomyStringFromCommonName( cn, max_taxonomies_return );
67 if ( result.size() > 0 ) {
68 return parseUniProtTaxonomy( result );
73 public static List<UniProtTaxonomy> getTaxonomiesFromCommonNameStrict( final String cn,
74 final int max_taxonomies_return )
76 final List<UniProtTaxonomy> taxonomies = getTaxonomiesFromCommonName( cn, max_taxonomies_return );
77 if ( ( taxonomies != null ) && ( taxonomies.size() > 0 ) ) {
78 final List<UniProtTaxonomy> filtered_taxonomies = new ArrayList<UniProtTaxonomy>();
79 for( final UniProtTaxonomy taxonomy : taxonomies ) {
80 if ( taxonomy.getCommonName().equalsIgnoreCase( cn ) ) {
81 filtered_taxonomies.add( taxonomy );
84 return filtered_taxonomies;
89 public static List<UniProtTaxonomy> getTaxonomiesFromId( final String id, final int max_taxonomies_return )
91 final List<String> result = getTaxonomyStringFromId( id, max_taxonomies_return );
92 if ( result.size() > 0 ) {
93 return parseUniProtTaxonomy( result );
98 private static List<UniProtTaxonomy> getTaxonomiesFromScientificName( final String sn,
99 final int max_taxonomies_return )
101 final List<String> result = getTaxonomyStringFromScientificName( sn, max_taxonomies_return );
102 if ( result.size() > 0 ) {
103 return parseUniProtTaxonomy( result );
109 * Does not return "sub-types".
110 * For example, for "Mus musculus" only returns "Mus musculus"
111 * and not "Mus musculus", "Mus musculus bactrianus", ...
114 public static List<UniProtTaxonomy> getTaxonomiesFromScientificNameStrict( final String sn,
115 final int max_taxonomies_return )
117 final List<UniProtTaxonomy> taxonomies = getTaxonomiesFromScientificName( sn, max_taxonomies_return );
118 if ( ( taxonomies != null ) && ( taxonomies.size() > 0 ) ) {
119 final List<UniProtTaxonomy> filtered_taxonomies = new ArrayList<UniProtTaxonomy>();
120 for( final UniProtTaxonomy taxonomy : taxonomies ) {
121 if ( taxonomy.getScientificName().equalsIgnoreCase( sn ) ) {
122 filtered_taxonomies.add( taxonomy );
125 return filtered_taxonomies;
130 public static List<UniProtTaxonomy> getTaxonomiesFromTaxonomyCode( final String code,
131 final int max_taxonomies_return )
133 final String my_code = new String( code );
134 final List<String> result = getTaxonomyStringFromTaxonomyCode( my_code, max_taxonomies_return );
135 if ( result.size() > 0 ) {
136 return parseUniProtTaxonomy( result );
141 public static SequenceDatabaseEntry obtainEmblEntry( final Accession id, final int max_lines_to_return )
143 final List<String> lines = queryEmblDb( id, max_lines_to_return );
144 return EbiDbEntry.createInstanceFromPlainText( lines );
147 public static SequenceDatabaseEntry obtainRefSeqEntryFromEmbl( final Accession id, final int max_lines_to_return )
149 final List<String> lines = queryEmblDb( id, max_lines_to_return );
150 return EbiDbEntry.createInstanceFromPlainTextForRefSeq( lines );
153 public static SortedSet<String> obtainSeqInformation( final Phylogeny phy,
154 final boolean ext_nodes_only,
155 final boolean allow_to_set_taxonomic_data,
156 final int lines_to_return ) throws IOException {
157 final SortedSet<String> not_found = new TreeSet<String>();
158 for( final PhylogenyNodeIterator iter = phy.iteratorPostorder(); iter.hasNext(); ) {
159 final PhylogenyNode node = iter.next();
160 if ( ext_nodes_only && node.isInternal() ) {
163 Accession acc = SequenceAccessionTools.obtainFromSeqAccession( node );
165 || ForesterUtil.isEmpty( acc.getSource() )
166 || ForesterUtil.isEmpty( acc.getValue() )
167 || ( ( acc.getSource() != Accession.UNIPROT ) && ( acc.getSource() != Accession.EMBL ) && ( acc
168 .getSource() != Accession.REFSEQ ) ) ) {
169 acc = SequenceAccessionTools.obtainAccessorFromDataFields( node );
172 || ForesterUtil.isEmpty( acc.getSource() )
173 || ForesterUtil.isEmpty( acc.getValue() )
174 || ( ( acc.getSource() != Accession.UNIPROT ) && ( acc.getSource() != Accession.EMBL ) && ( acc
175 .getSource() != Accession.REFSEQ ) ) ) {
176 not_found.add( node.toString() );
179 SequenceDatabaseEntry db_entry = null;
180 final String query = acc.getValue();
181 if ( acc.getSource() == Accession.UNIPROT ) {
183 System.out.println( "uniprot: " + query );
186 db_entry = obtainUniProtEntry( query, lines_to_return );
188 catch ( FileNotFoundException e ) {
189 // Eat this, and move to next.
192 else if ( acc.getSource() == Accession.EMBL ) {
194 System.out.println( "embl: " + query );
197 db_entry = obtainEmblEntry( new Accession( query ), lines_to_return );
199 catch ( FileNotFoundException e ) {
200 // Eat this, and move to next.
203 else if ( acc.getSource() == Accession.REFSEQ ) {
205 System.out.println( "refseq: " + query );
208 db_entry = obtainRefSeqEntryFromEmbl( new Accession( query ), lines_to_return );
210 catch ( FileNotFoundException e ) {
211 // Eat this, and move to next.
214 if ( ( db_entry != null ) && !db_entry.isEmpty() ) {
215 final Sequence seq = node.getNodeData().isHasSequence() ? node.getNodeData().getSequence()
217 if ( !ForesterUtil.isEmpty( db_entry.getAccession() ) ) {
218 seq.setAccession( new Accession( db_entry.getAccession(), acc.getSource() ) );
220 if ( !ForesterUtil.isEmpty( db_entry.getSequenceName() ) ) {
221 seq.setName( db_entry.getSequenceName() );
223 if ( !ForesterUtil.isEmpty( db_entry.getGeneName() ) ) {
224 seq.setGeneName( db_entry.getGeneName() );
226 if ( !ForesterUtil.isEmpty( db_entry.getSequenceSymbol() ) ) {
228 seq.setSymbol( db_entry.getSequenceSymbol() );
230 catch ( final PhyloXmlDataFormatException e ) {
231 // Eat this exception.
234 if ( ( db_entry.getGoTerms() != null ) && !db_entry.getGoTerms().isEmpty() ) {
235 for( final GoTerm go : db_entry.getGoTerms() ) {
236 final Annotation ann = new Annotation( go.getGoId().getId() );
237 ann.setDesc( go.getName() );
238 seq.addAnnotation( ann );
241 if ( ( db_entry.getCrossReferences() != null ) && !db_entry.getCrossReferences().isEmpty() ) {
242 for( final Accession x : db_entry.getCrossReferences() ) {
243 seq.addCrossReference( x );
246 final Taxonomy tax = node.getNodeData().isHasTaxonomy() ? node.getNodeData().getTaxonomy()
248 if ( !ForesterUtil.isEmpty( db_entry.getTaxonomyScientificName() ) ) {
249 tax.setScientificName( db_entry.getTaxonomyScientificName() );
251 if ( allow_to_set_taxonomic_data && !ForesterUtil.isEmpty( db_entry.getTaxonomyIdentifier() ) ) {
252 tax.setIdentifier( new Identifier( db_entry.getTaxonomyIdentifier(), "uniprot" ) );
254 node.getNodeData().setTaxonomy( tax );
255 node.getNodeData().setSequence( seq );
259 not_found.add( node.getName() );
262 Thread.sleep( 10 );// Sleep for 10 ms
264 catch ( final InterruptedException ie ) {
271 public static SequenceDatabaseEntry obtainUniProtEntry( final String query, final int max_lines_to_return )
273 final List<String> lines = queryUniprot( "uniprot/" + query + ".txt", max_lines_to_return );
274 return UniProtEntry.createInstanceFromPlainText( lines );
277 public static List<String> queryDb( final String query, int max_lines_to_return, final String base_url )
279 if ( ForesterUtil.isEmpty( query ) ) {
280 throw new IllegalArgumentException( "illegal attempt to use empty query " );
282 if ( max_lines_to_return < 1 ) {
283 max_lines_to_return = 1;
285 final URL url = new URL( base_url + query );
287 System.out.println( "url: " + url.toString() );
289 final URLConnection urlc = url.openConnection();
290 final BufferedReader in = new BufferedReader( new InputStreamReader( urlc.getInputStream() ) );
292 final List<String> result = new ArrayList<String>();
293 while ( ( line = in.readLine() ) != null ) {
295 System.out.println( line );
298 if ( result.size() > max_lines_to_return ) {
304 // To prevent accessing online dbs in too quick succession.
307 catch ( final InterruptedException e ) {
313 public static List<String> queryEmblDb( final Accession id, final int max_lines_to_return ) throws IOException {
314 final StringBuilder url_sb = new StringBuilder();
315 url_sb.append( BASE_EMBL_DB_URL );
316 if ( ForesterUtil.isEmpty( id.getSource() ) || ( id.getSource() == Accession.NCBI ) ) {
317 url_sb.append( SequenceDbWsTools.EMBL_DBS_EMBL );
318 url_sb.append( '/' );
320 else if ( id.getSource() == Accession.REFSEQ ) {
321 if ( id.getValue().toUpperCase().indexOf( 'P' ) == 1 ) {
322 url_sb.append( SequenceDbWsTools.EMBL_DBS_REFSEQ_P );
323 url_sb.append( '/' );
326 url_sb.append( SequenceDbWsTools.EMBL_DBS_REFSEQ_N );
327 url_sb.append( '/' );
330 return queryDb( id.getValue(), max_lines_to_return, url_sb.toString() );
333 public static List<String> queryUniprot( final String query, final int max_lines_to_return ) throws IOException {
334 return queryDb( query, max_lines_to_return, BASE_UNIPROT_URL );
337 private static String encode( final String str ) throws UnsupportedEncodingException {
338 return URLEncoder.encode( str.trim(), URL_ENC );
341 private static List<String> getTaxonomyStringFromCommonName( final String cn, final int max_lines_to_return )
343 return queryUniprot( "taxonomy/?query=common%3a%22" + encode( cn ) + "%22&format=tab", max_lines_to_return );
346 private static List<String> getTaxonomyStringFromId( final String id, final int max_lines_to_return )
348 return queryUniprot( "taxonomy/?query=id%3a%22" + encode( id ) + "%22&format=tab", max_lines_to_return );
351 private static List<String> getTaxonomyStringFromScientificName( final String sn, final int max_lines_to_return )
353 return queryUniprot( "taxonomy/?query=scientific%3a%22" + encode( sn ) + "%22&format=tab", max_lines_to_return );
356 private static List<String> getTaxonomyStringFromTaxonomyCode( final String code, final int max_lines_to_return )
358 return queryUniprot( "taxonomy/?query=mnemonic%3a%22" + encode( code ) + "%22&format=tab", max_lines_to_return );
361 private static List<UniProtTaxonomy> parseUniProtTaxonomy( final List<String> result ) throws IOException {
362 final List<UniProtTaxonomy> taxonomies = new ArrayList<UniProtTaxonomy>();
363 for( final String line : result ) {
364 if ( ForesterUtil.isEmpty( line ) ) {
365 // Ignore empty lines.
367 else if ( line.startsWith( "Taxon" ) ) {
368 final String[] items = line.split( "\t" );
369 if ( !( items[ 1 ].equalsIgnoreCase( "Mnemonic" ) && items[ 2 ].equalsIgnoreCase( "Scientific name" )
370 && items[ 3 ].equalsIgnoreCase( "Common name" ) && items[ 4 ].equalsIgnoreCase( "Synonym" )
371 && items[ 5 ].equalsIgnoreCase( "Other Names" ) && items[ 6 ].equalsIgnoreCase( "Reviewed" )
372 && items[ 7 ].equalsIgnoreCase( "Rank" ) && items[ 8 ].equalsIgnoreCase( "Lineage" ) ) ) {
373 throw new IOException( "Unreconized UniProt Taxonomy format: " + line );
377 if ( line.split( "\t" ).length > 4 ) {
378 taxonomies.add( new UniProtTaxonomy( line ) );