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 EMBL_REFSEQ = "http://www.ebi.ac.uk/Tools/dbfetch/dbfetch?db=REFSEQ&style=raw&id=";
58 public final static String BASE_UNIPROT_URL = "http://www.uniprot.org/";
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 private final static boolean DEBUG = true;
63 private final static String URL_ENC = "UTF-8";
65 public static List<UniProtTaxonomy> getTaxonomiesFromCommonNameStrict( final String cn,
66 final int max_taxonomies_return )
68 final List<UniProtTaxonomy> taxonomies = getTaxonomiesFromCommonName( cn, max_taxonomies_return );
69 if ( ( taxonomies != null ) && ( taxonomies.size() > 0 ) ) {
70 final List<UniProtTaxonomy> filtered_taxonomies = new ArrayList<UniProtTaxonomy>();
71 for( final UniProtTaxonomy taxonomy : taxonomies ) {
72 if ( taxonomy.getCommonName().equalsIgnoreCase( cn ) ) {
73 filtered_taxonomies.add( taxonomy );
76 return filtered_taxonomies;
81 public static List<UniProtTaxonomy> getTaxonomiesFromId( final String id, final int max_taxonomies_return )
83 final List<String> result = getTaxonomyStringFromId( id, max_taxonomies_return );
84 if ( result.size() > 0 ) {
85 return parseUniProtTaxonomy( result );
91 * Does not return "sub-types".
92 * For example, for "Mus musculus" only returns "Mus musculus"
93 * and not "Mus musculus", "Mus musculus bactrianus", ...
96 public static List<UniProtTaxonomy> getTaxonomiesFromScientificNameStrict( final String sn,
97 final int max_taxonomies_return )
99 final List<UniProtTaxonomy> taxonomies = getTaxonomiesFromScientificName( sn, max_taxonomies_return );
100 if ( ( taxonomies != null ) && ( taxonomies.size() > 0 ) ) {
101 final List<UniProtTaxonomy> filtered_taxonomies = new ArrayList<UniProtTaxonomy>();
102 for( final UniProtTaxonomy taxonomy : taxonomies ) {
103 if ( taxonomy.getScientificName().equalsIgnoreCase( sn ) ) {
104 filtered_taxonomies.add( taxonomy );
107 return filtered_taxonomies;
112 public static List<UniProtTaxonomy> getTaxonomiesFromTaxonomyCode( final String code,
113 final int max_taxonomies_return )
115 final String my_code = new String( code );
116 final List<String> result = getTaxonomyStringFromTaxonomyCode( my_code, max_taxonomies_return );
117 if ( result.size() > 0 ) {
118 return parseUniProtTaxonomy( result );
123 public static SequenceDatabaseEntry obtainEmblEntry( final Accession id, final int max_lines_to_return )
125 final List<String> lines = queryEmblDb( id, max_lines_to_return );
126 return EbiDbEntry.createInstanceFromPlainText( lines );
129 public final static Accession obtainSeqAccession( final PhylogenyNode node ) {
130 Accession acc = SequenceAccessionTools.obtainFromSeqAccession( node );
131 if ( !isAccessionAcceptable( acc ) ) {
132 acc = SequenceAccessionTools.obtainAccessorFromDataFields( node );
137 public static SequenceDatabaseEntry obtainRefSeqEntryFromEmbl( final Accession id, final int max_lines_to_return )
139 final List<String> lines = queryEmblDbForRefSeqEntry( id, max_lines_to_return );
140 return EbiDbEntry.createInstanceFromPlainTextForRefSeq( lines );
143 public final static void obtainSeqInformation( final boolean allow_to_set_taxonomic_data,
144 final int lines_to_return,
145 final SortedSet<String> not_found,
146 final PhylogenyNode node ) throws IOException {
147 final Accession acc = obtainSeqAccession( node );
148 if ( !isAccessionAcceptable( acc ) ) {
149 if ( node.isExternal() || !node.isEmpty() ) {
150 not_found.add( node.toString() );
154 addDataFromDbToNode( allow_to_set_taxonomic_data, lines_to_return, not_found, node, acc );
158 public final static SortedSet<String> obtainSeqInformation( final Phylogeny phy,
159 final boolean ext_nodes_only,
160 final boolean allow_to_set_taxonomic_data,
161 final int lines_to_return ) throws IOException {
162 final SortedSet<String> not_found = new TreeSet<String>();
163 for( final PhylogenyNodeIterator iter = phy.iteratorPostorder(); iter.hasNext(); ) {
164 final PhylogenyNode node = iter.next();
165 if ( node.isExternal() || !ext_nodes_only ) {
166 obtainSeqInformation( allow_to_set_taxonomic_data, lines_to_return, not_found, node );
172 public static SequenceDatabaseEntry obtainUniProtEntry( final String query, final int max_lines_to_return )
174 final List<String> lines = queryUniprot( "uniprot/" + query + ".txt", max_lines_to_return );
175 return UniProtEntry.createInstanceFromPlainText( lines );
178 public static List<String> queryDb( final String query, int max_lines_to_return, final String base_url )
180 if ( ForesterUtil.isEmpty( query ) ) {
181 throw new IllegalArgumentException( "illegal attempt to use empty query " );
183 if ( max_lines_to_return < 1 ) {
184 max_lines_to_return = 1;
186 final URL url = new URL( base_url + query );
188 System.out.println( "url: " + url.toString() );
190 final URLConnection urlc = url.openConnection();
191 final BufferedReader in = new BufferedReader( new InputStreamReader( urlc.getInputStream() ) );
193 final List<String> result = new ArrayList<String>();
194 while ( ( line = in.readLine() ) != null ) {
196 System.out.println( line );
199 if ( result.size() > max_lines_to_return ) {
205 // To prevent accessing online dbs in too quick succession.
208 catch ( final InterruptedException e ) {
214 public static List<String> queryEmblDbForRefSeqEntry( final Accession id, final int max_lines_to_return )
216 final StringBuilder url_sb = new StringBuilder();
217 url_sb.append( EMBL_REFSEQ );
218 return queryDb( id.getValue(), max_lines_to_return, url_sb.toString() );
221 public static List<String> queryEmblDb( final Accession id, final int max_lines_to_return ) throws IOException {
222 final StringBuilder url_sb = new StringBuilder();
223 // url_sb.append( BASE_EMBL_DB_URL );
224 if ( ForesterUtil.isEmpty( id.getSource() ) || ( id.getSource().equals( Source.NCBI.toString() ) ) ) {
225 url_sb.append( EMBL_DBS_EMBL );
226 url_sb.append( '/' );
228 else if ( id.getSource().equals( Source.REFSEQ.toString() ) ) {
229 url_sb.append( EMBL_REFSEQ );
230 // if ( id.getValue().toUpperCase().indexOf( 'P' ) == 1 ) {
231 // url_sb.append( SequenceDbWsTools.EMBL_DBS_REFSEQ_P );
232 // url_sb.append( '/' );
235 // url_sb.append( SequenceDbWsTools.EMBL_DBS_REFSEQ_N );
236 // url_sb.append( '/' );
239 return queryDb( id.getValue(), max_lines_to_return, url_sb.toString() );
242 public static List<String> queryUniprot( final String query, final int max_lines_to_return ) throws IOException {
243 return queryDb( query, max_lines_to_return, BASE_UNIPROT_URL );
246 private static void addDataFromDbToNode( final boolean allow_to_set_taxonomic_data,
247 final int lines_to_return,
248 final SortedSet<String> not_found,
249 final PhylogenyNode node,
250 final Accession acc ) throws IOException {
251 SequenceDatabaseEntry db_entry = null;
252 final String query = acc.getValue();
253 if ( acc.getSource().equals( Source.UNIPROT.toString() ) ) {
255 System.out.println( "uniprot: " + query );
258 db_entry = obtainUniProtEntry( query, lines_to_return );
260 catch ( final FileNotFoundException e ) {
261 // Eat this, and move to next.
264 else if ( acc.getSource().equals( Source.EMBL.toString() ) ) {
266 System.out.println( "embl: " + query );
269 db_entry = obtainEmblEntry( new Accession( query ), lines_to_return );
271 catch ( final FileNotFoundException e ) {
272 // Eat this, and move to next.
275 else if ( acc.getSource().equals( Source.REFSEQ.toString() ) ) {
277 System.out.println( "refseq: " + query );
280 db_entry = obtainRefSeqEntryFromEmbl( new Accession( query ), lines_to_return );
282 catch ( final FileNotFoundException e ) {
283 // Eat this, and move to next.
286 if ( ( db_entry != null ) && !db_entry.isEmpty() ) {
287 final Sequence seq = node.getNodeData().isHasSequence() ? node.getNodeData().getSequence() : new Sequence();
288 if ( !ForesterUtil.isEmpty( db_entry.getAccession() ) ) {
289 seq.setAccession( new Accession( db_entry.getAccession(), acc.getSource() ) );
291 if ( !ForesterUtil.isEmpty( db_entry.getSequenceName() ) ) {
292 seq.setName( db_entry.getSequenceName() );
294 if ( !ForesterUtil.isEmpty( db_entry.getGeneName() ) ) {
295 seq.setGeneName( db_entry.getGeneName() );
297 if ( !ForesterUtil.isEmpty( db_entry.getSequenceSymbol() ) ) {
299 seq.setSymbol( db_entry.getSequenceSymbol() );
301 catch ( final PhyloXmlDataFormatException e ) {
302 // Eat this exception.
305 if ( ( db_entry.getGoTerms() != null ) && !db_entry.getGoTerms().isEmpty() ) {
306 for( final GoTerm go : db_entry.getGoTerms() ) {
307 final Annotation ann = new Annotation( go.getGoId().getId() );
308 ann.setDesc( go.getName() );
309 seq.addAnnotation( ann );
312 if ( ( db_entry.getCrossReferences() != null ) && !db_entry.getCrossReferences().isEmpty() ) {
313 for( final Accession x : db_entry.getCrossReferences() ) {
314 seq.addCrossReference( x );
317 final Taxonomy tax = node.getNodeData().isHasTaxonomy() ? node.getNodeData().getTaxonomy() : new Taxonomy();
318 if ( !ForesterUtil.isEmpty( db_entry.getTaxonomyScientificName() ) ) {
319 tax.setScientificName( db_entry.getTaxonomyScientificName() );
321 if ( allow_to_set_taxonomic_data && !ForesterUtil.isEmpty( db_entry.getTaxonomyIdentifier() ) ) {
322 tax.setIdentifier( new Identifier( db_entry.getTaxonomyIdentifier(), "uniprot" ) );
324 node.getNodeData().setTaxonomy( tax );
325 node.getNodeData().setSequence( seq );
328 if ( node.isExternal() || !node.isEmpty() ) {
329 not_found.add( node.toString() );
333 Thread.sleep( 10 );// Sleep for 10 ms
335 catch ( final InterruptedException ie ) {
339 private static String encode( final String str ) throws UnsupportedEncodingException {
340 return URLEncoder.encode( str.trim(), URL_ENC );
343 private static List<UniProtTaxonomy> getTaxonomiesFromCommonName( final String cn, final int max_taxonomies_return )
345 final List<String> result = getTaxonomyStringFromCommonName( cn, max_taxonomies_return );
346 if ( result.size() > 0 ) {
347 return parseUniProtTaxonomy( result );
352 private static List<UniProtTaxonomy> getTaxonomiesFromScientificName( final String sn,
353 final int max_taxonomies_return )
355 final List<String> result = getTaxonomyStringFromScientificName( sn, max_taxonomies_return );
356 if ( result.size() > 0 ) {
357 return parseUniProtTaxonomy( result );
362 private static List<String> getTaxonomyStringFromCommonName( final String cn, final int max_lines_to_return )
364 return queryUniprot( "taxonomy/?query=common%3a%22" + encode( cn ) + "%22&format=tab", max_lines_to_return );
367 private static List<String> getTaxonomyStringFromId( final String id, final int max_lines_to_return )
369 return queryUniprot( "taxonomy/?query=id%3a%22" + encode( id ) + "%22&format=tab", max_lines_to_return );
372 private static List<String> getTaxonomyStringFromScientificName( final String sn, final int max_lines_to_return )
374 return queryUniprot( "taxonomy/?query=scientific%3a%22" + encode( sn ) + "%22&format=tab", max_lines_to_return );
377 private static List<String> getTaxonomyStringFromTaxonomyCode( final String code, final int max_lines_to_return )
379 return queryUniprot( "taxonomy/?query=mnemonic%3a%22" + encode( code ) + "%22&format=tab", max_lines_to_return );
382 private final static boolean isAccessionAcceptable( final Accession acc ) {
383 return ( !( ( acc == null ) || ForesterUtil.isEmpty( acc.getSource() ) || ForesterUtil.isEmpty( acc.getValue() ) || ( ( acc
384 .getSource().equals( Source.UNIPROT.toString() ) )
385 && ( acc.getSource().toString().equals( Source.EMBL.toString() ) ) && ( acc.getSource().toString()
386 .equals( Source.REFSEQ.toString() ) ) ) ) );
389 private static List<UniProtTaxonomy> parseUniProtTaxonomy( final List<String> result ) throws IOException {
390 final List<UniProtTaxonomy> taxonomies = new ArrayList<UniProtTaxonomy>();
391 for( final String line : result ) {
392 if ( ForesterUtil.isEmpty( line ) ) {
393 // Ignore empty lines.
395 else if ( line.startsWith( "Taxon" ) ) {
396 final String[] items = line.split( "\t" );
397 if ( !( items[ 1 ].equalsIgnoreCase( "Mnemonic" ) && items[ 2 ].equalsIgnoreCase( "Scientific name" )
398 && items[ 3 ].equalsIgnoreCase( "Common name" ) && items[ 4 ].equalsIgnoreCase( "Synonym" )
399 && items[ 5 ].equalsIgnoreCase( "Other Names" ) && items[ 6 ].equalsIgnoreCase( "Reviewed" )
400 && items[ 7 ].equalsIgnoreCase( "Rank" ) && items[ 8 ].equalsIgnoreCase( "Lineage" ) ) ) {
401 throw new IOException( "Unreconized UniProt Taxonomy format: " + line );
405 if ( line.split( "\t" ).length > 4 ) {
406 taxonomies.add( new UniProtTaxonomy( line ) );