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 EMBL_GENBANK = "http://www.ebi.ac.uk/Tools/dbfetch/dbfetch?db=GENBANK&style=raw&id=";
59 public final static String BASE_UNIPROT_URL = "http://www.uniprot.org/";
60 //public final static String EMBL_DBS_EMBL = "embl";
61 public final static String EMBL_DBS_REFSEQ_N = "refseqn";
62 public final static String EMBL_DBS_REFSEQ_P = "refseqp";
63 private final static boolean DEBUG = true;
64 private final static String URL_ENC = "UTF-8";
65 public final static int DEFAULT_LINES_TO_RETURN = 4000;
67 final static String extractFrom( final String target, final String a ) {
68 final int i_a = target.indexOf( a );
69 return target.substring( i_a + a.length() ).trim();
72 final static String extractFromTo( final String target, final String a, final String b ) {
73 final int i_a = target.indexOf( a );
74 final int i_b = target.indexOf( b );
75 if ( ( i_a < 0 ) || ( i_b < i_a ) ) {
76 throw new IllegalArgumentException( "attempt to extract from \"" + target + "\" between \"" + a
77 + "\" and \"" + b + "\"" );
79 return target.substring( i_a + a.length(), i_b ).trim();
82 final static String extractTo( final String target, final String b ) {
83 final int i_b = target.indexOf( b );
84 return target.substring( 0, i_b ).trim();
87 public static List<UniProtTaxonomy> getTaxonomiesFromCommonNameStrict( final String cn,
88 final int max_taxonomies_return )
90 final List<UniProtTaxonomy> taxonomies = getTaxonomiesFromCommonName( cn, max_taxonomies_return );
91 if ( ( taxonomies != null ) && ( taxonomies.size() > 0 ) ) {
92 final List<UniProtTaxonomy> filtered_taxonomies = new ArrayList<UniProtTaxonomy>();
93 for( final UniProtTaxonomy taxonomy : taxonomies ) {
94 if ( taxonomy.getCommonName().equalsIgnoreCase( cn ) ) {
95 filtered_taxonomies.add( taxonomy );
98 return filtered_taxonomies;
103 public static List<UniProtTaxonomy> getTaxonomiesFromId( final String id, final int max_taxonomies_return )
105 final List<String> result = getTaxonomyStringFromId( id, max_taxonomies_return );
106 if ( result.size() > 0 ) {
107 return parseUniProtTaxonomy( result );
113 * Does not return "sub-types".
114 * For example, for "Mus musculus" only returns "Mus musculus"
115 * and not "Mus musculus", "Mus musculus bactrianus", ...
118 public static List<UniProtTaxonomy> getTaxonomiesFromScientificNameStrict( final String sn,
119 final int max_taxonomies_return )
121 final List<UniProtTaxonomy> taxonomies = getTaxonomiesFromScientificName( sn, max_taxonomies_return );
122 if ( ( taxonomies != null ) && ( taxonomies.size() > 0 ) ) {
123 final List<UniProtTaxonomy> filtered_taxonomies = new ArrayList<UniProtTaxonomy>();
124 for( final UniProtTaxonomy taxonomy : taxonomies ) {
125 if ( taxonomy.getScientificName().equalsIgnoreCase( sn ) ) {
126 filtered_taxonomies.add( taxonomy );
129 return filtered_taxonomies;
134 public static List<UniProtTaxonomy> getTaxonomiesFromTaxonomyCode( final String code,
135 final int max_taxonomies_return )
137 final String my_code = new String( code );
138 final List<String> result = getTaxonomyStringFromTaxonomyCode( my_code, max_taxonomies_return );
139 if ( result.size() > 0 ) {
140 return parseUniProtTaxonomy( result );
145 public static SequenceDatabaseEntry obtainEmblEntry( final Accession acc, final int max_lines_to_return )
147 final List<String> lines = queryEmblDb( acc, max_lines_to_return );
148 return EbiDbEntry.createInstanceFromPlainTextForRefSeq( lines );
151 public static SequenceDatabaseEntry obtainEmblEntry( final Accession acc ) throws IOException {
152 return obtainEmblEntry( acc, DEFAULT_LINES_TO_RETURN );
155 public final static Accession obtainSeqAccession( final PhylogenyNode node ) {
156 Accession acc = SequenceAccessionTools.obtainFromSeqAccession( node );
157 if ( !isAccessionAcceptable( acc ) ) {
158 acc = SequenceAccessionTools.obtainAccessorFromDataFields( node );
163 public static SequenceDatabaseEntry obtainRefSeqEntryFromEmbl( final Accession acc, final int max_lines_to_return )
165 final List<String> lines = queryEmblDbForRefSeqEntry( acc, max_lines_to_return );
166 return EbiDbEntry.createInstanceFromPlainTextForRefSeq( lines );
169 public static SequenceDatabaseEntry obtainRefSeqEntryFromEmbl( final Accession acc ) throws IOException {
170 return obtainRefSeqEntryFromEmbl( acc, DEFAULT_LINES_TO_RETURN );
173 public final static void obtainSeqInformation( final boolean allow_to_set_taxonomic_data,
174 final int lines_to_return,
175 final SortedSet<String> not_found,
176 final PhylogenyNode node ) throws IOException {
177 final Accession acc = obtainSeqAccession( node );
178 if ( !isAccessionAcceptable( acc ) ) {
179 if ( node.isExternal() || !node.isEmpty() ) {
180 not_found.add( node.toString() );
184 addDataFromDbToNode( allow_to_set_taxonomic_data, lines_to_return, not_found, node, acc );
188 public final static void obtainSeqInformation( final boolean allow_to_set_taxonomic_data,
189 final SortedSet<String> not_found,
190 final PhylogenyNode node ) throws IOException {
191 obtainSeqInformation( allow_to_set_taxonomic_data, DEFAULT_LINES_TO_RETURN, not_found, node );
194 public final static void obtainSeqInformation( final PhylogenyNode node ) throws IOException {
195 obtainSeqInformation( true, DEFAULT_LINES_TO_RETURN, new TreeSet<String>(), node );
198 public final static SortedSet<String> obtainSeqInformation( final Phylogeny phy,
199 final boolean ext_nodes_only,
200 final boolean allow_to_set_taxonomic_data,
201 final int lines_to_return ) throws IOException {
202 final SortedSet<String> not_found = new TreeSet<String>();
203 for( final PhylogenyNodeIterator iter = phy.iteratorPostorder(); iter.hasNext(); ) {
204 final PhylogenyNode node = iter.next();
205 if ( node.isExternal() || !ext_nodes_only ) {
206 obtainSeqInformation( allow_to_set_taxonomic_data, lines_to_return, not_found, node );
212 public static SequenceDatabaseEntry obtainUniProtEntry( final String query, final int max_lines_to_return )
214 final List<String> lines = queryUniprot( "uniprot/" + query + ".txt", max_lines_to_return );
215 return UniProtEntry.createInstanceFromPlainText( lines );
218 public static SequenceDatabaseEntry obtainUniProtEntry( final String query ) throws IOException {
219 return obtainUniProtEntry( query, DEFAULT_LINES_TO_RETURN );
222 public static List<String> queryDb( final String query, int max_lines_to_return, final String base_url )
224 if ( ForesterUtil.isEmpty( query ) ) {
225 throw new IllegalArgumentException( "illegal attempt to use empty query " );
227 if ( max_lines_to_return < 1 ) {
228 max_lines_to_return = 1;
230 final URL url = new URL( base_url + query );
232 System.out.println( "url: " + url.toString() );
234 final URLConnection urlc = url.openConnection();
235 final BufferedReader in = new BufferedReader( new InputStreamReader( urlc.getInputStream() ) );
237 final List<String> result = new ArrayList<String>();
238 while ( ( line = in.readLine() ) != null ) {
240 System.out.println( line );
243 if ( result.size() > max_lines_to_return ) {
249 // To prevent accessing online dbs in too quick succession.
252 catch ( final InterruptedException e ) {
258 public static List<String> queryEmblDbForRefSeqEntry( final Accession id, final int max_lines_to_return )
260 final StringBuilder url_sb = new StringBuilder();
261 url_sb.append( EMBL_REFSEQ );
262 return queryDb( id.getValue(), max_lines_to_return, url_sb.toString() );
265 public static List<String> queryEmblDb( final Accession id, final int max_lines_to_return ) throws IOException {
266 final StringBuilder url_sb = new StringBuilder();
267 // url_sb.append( BASE_EMBL_DB_URL );
268 if ( id.getSource().equals( Source.NCBI.toString() ) ) {
269 url_sb.append( EMBL_GENBANK );
270 //url_sb.append( '/' );
272 else if ( id.getSource().equals( Source.REFSEQ.toString() ) ) {
273 url_sb.append( EMBL_REFSEQ );
274 // if ( id.getValue().toUpperCase().indexOf( 'P' ) == 1 ) {
275 // url_sb.append( SequenceDbWsTools.EMBL_DBS_REFSEQ_P );
276 // url_sb.append( '/' );
279 // url_sb.append( SequenceDbWsTools.EMBL_DBS_REFSEQ_N );
280 // url_sb.append( '/' );
284 throw new IllegalArgumentException( "unable to handle source: " + id.getSource() );
286 return queryDb( id.getValue(), max_lines_to_return, url_sb.toString() );
289 public static List<String> queryUniprot( final String query, final int max_lines_to_return ) throws IOException {
290 return queryDb( query, max_lines_to_return, BASE_UNIPROT_URL );
293 private static void addDataFromDbToNode( final boolean allow_to_set_taxonomic_data,
294 final int lines_to_return,
295 final SortedSet<String> not_found,
296 final PhylogenyNode node,
297 final Accession acc ) throws IOException {
298 SequenceDatabaseEntry db_entry = null;
299 final String query = acc.getValue();
300 if ( acc.getSource().equals( Source.UNIPROT.toString() ) ) {
302 System.out.println( "uniprot: " + query );
305 db_entry = obtainUniProtEntry( query, lines_to_return );
307 catch ( final FileNotFoundException e ) {
308 // Eat this, and move to next.
311 else if ( acc.getSource().equals( Source.EMBL.toString() ) ) {
313 System.out.println( "embl: " + query );
316 db_entry = obtainEmblEntry( new Accession( query ), lines_to_return );
318 catch ( final FileNotFoundException e ) {
319 // Eat this, and move to next.
322 else if ( acc.getSource().equals( Source.REFSEQ.toString() ) ) {
324 System.out.println( "refseq: " + query );
327 db_entry = obtainRefSeqEntryFromEmbl( new Accession( query ), lines_to_return );
329 catch ( final FileNotFoundException e ) {
330 // Eat this, and move to next.
333 if ( ( db_entry != null ) && !db_entry.isEmpty() ) {
334 final Sequence seq = node.getNodeData().isHasSequence() ? node.getNodeData().getSequence() : new Sequence();
335 if ( !ForesterUtil.isEmpty( db_entry.getAccession() ) ) {
336 seq.setAccession( new Accession( db_entry.getAccession(), acc.getSource() ) );
338 if ( !ForesterUtil.isEmpty( db_entry.getSequenceName() ) ) {
339 seq.setName( db_entry.getSequenceName() );
341 if ( !ForesterUtil.isEmpty( db_entry.getGeneName() ) ) {
342 seq.setGeneName( db_entry.getGeneName() );
344 if ( !ForesterUtil.isEmpty( db_entry.getSequenceSymbol() ) ) {
346 seq.setSymbol( db_entry.getSequenceSymbol() );
348 catch ( final PhyloXmlDataFormatException e ) {
349 // Eat this exception.
352 if ( ( db_entry.getGoTerms() != null ) && !db_entry.getGoTerms().isEmpty() ) {
353 for( final GoTerm go : db_entry.getGoTerms() ) {
354 final Annotation ann = new Annotation( go.getGoId().getId() );
355 ann.setDesc( go.getName() );
356 seq.addAnnotation( ann );
359 if ( ( db_entry.getCrossReferences() != null ) && !db_entry.getCrossReferences().isEmpty() ) {
360 for( final Accession x : db_entry.getCrossReferences() ) {
361 seq.addCrossReference( x );
364 final Taxonomy tax = node.getNodeData().isHasTaxonomy() ? node.getNodeData().getTaxonomy() : new Taxonomy();
365 if ( !ForesterUtil.isEmpty( db_entry.getTaxonomyScientificName() ) ) {
366 tax.setScientificName( db_entry.getTaxonomyScientificName() );
368 if ( allow_to_set_taxonomic_data && !ForesterUtil.isEmpty( db_entry.getTaxonomyIdentifier() ) ) {
369 tax.setIdentifier( new Identifier( db_entry.getTaxonomyIdentifier(), "uniprot" ) );
371 node.getNodeData().setTaxonomy( tax );
372 node.getNodeData().setSequence( seq );
375 if ( node.isExternal() || !node.isEmpty() ) {
376 not_found.add( node.toString() );
380 Thread.sleep( 10 );// Sleep for 10 ms
382 catch ( final InterruptedException ie ) {
386 private static String encode( final String str ) throws UnsupportedEncodingException {
387 return URLEncoder.encode( str.trim(), URL_ENC );
390 private static List<UniProtTaxonomy> getTaxonomiesFromCommonName( final String cn, final int max_taxonomies_return )
392 final List<String> result = getTaxonomyStringFromCommonName( cn, max_taxonomies_return );
393 if ( result.size() > 0 ) {
394 return parseUniProtTaxonomy( result );
399 private static List<UniProtTaxonomy> getTaxonomiesFromScientificName( final String sn,
400 final int max_taxonomies_return )
402 final List<String> result = getTaxonomyStringFromScientificName( sn, max_taxonomies_return );
403 if ( result.size() > 0 ) {
404 return parseUniProtTaxonomy( result );
409 private static List<String> getTaxonomyStringFromCommonName( final String cn, final int max_lines_to_return )
411 return queryUniprot( "taxonomy/?query=common%3a%22" + encode( cn ) + "%22&format=tab", max_lines_to_return );
414 private static List<String> getTaxonomyStringFromId( final String id, final int max_lines_to_return )
416 return queryUniprot( "taxonomy/?query=id%3a%22" + encode( id ) + "%22&format=tab", max_lines_to_return );
419 private static List<String> getTaxonomyStringFromScientificName( final String sn, final int max_lines_to_return )
421 return queryUniprot( "taxonomy/?query=scientific%3a%22" + encode( sn ) + "%22&format=tab", max_lines_to_return );
424 private static List<String> getTaxonomyStringFromTaxonomyCode( final String code, final int max_lines_to_return )
426 return queryUniprot( "taxonomy/?query=mnemonic%3a%22" + encode( code ) + "%22&format=tab", max_lines_to_return );
429 private final static boolean isAccessionAcceptable( final Accession acc ) {
430 return ( !( ( acc == null ) || ForesterUtil.isEmpty( acc.getSource() ) || ForesterUtil.isEmpty( acc.getValue() ) || ( ( acc
431 .getSource().equals( Source.UNIPROT.toString() ) )
432 && ( acc.getSource().toString().equals( Source.EMBL.toString() ) ) && ( acc.getSource().toString()
433 .equals( Source.REFSEQ.toString() ) ) ) ) );
436 private static List<UniProtTaxonomy> parseUniProtTaxonomy( final List<String> result ) throws IOException {
437 final List<UniProtTaxonomy> taxonomies = new ArrayList<UniProtTaxonomy>();
438 for( final String line : result ) {
439 if ( ForesterUtil.isEmpty( line ) ) {
440 // Ignore empty lines.
442 else if ( line.startsWith( "Taxon" ) ) {
443 final String[] items = line.split( "\t" );
444 if ( !( items[ 1 ].equalsIgnoreCase( "Mnemonic" ) && items[ 2 ].equalsIgnoreCase( "Scientific name" )
445 && items[ 3 ].equalsIgnoreCase( "Common name" ) && items[ 4 ].equalsIgnoreCase( "Synonym" )
446 && items[ 5 ].equalsIgnoreCase( "Other Names" ) && items[ 6 ].equalsIgnoreCase( "Reviewed" )
447 && items[ 7 ].equalsIgnoreCase( "Rank" ) && items[ 8 ].equalsIgnoreCase( "Lineage" ) ) ) {
448 throw new IOException( "Unreconized UniProt Taxonomy format: " + line );
452 if ( line.split( "\t" ).length > 4 ) {
453 taxonomies.add( new UniProtTaxonomy( line ) );