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: www.phylosoft.org/forester
26 package org.forester.ws.uniprot;
28 import java.io.BufferedReader;
29 import java.io.IOException;
30 import java.io.InputStreamReader;
31 import java.io.UnsupportedEncodingException;
33 import java.net.URLConnection;
34 import java.net.URLEncoder;
35 import java.util.ArrayList;
36 import java.util.List;
37 import java.util.regex.Matcher;
38 import java.util.regex.Pattern;
40 import org.forester.util.ForesterUtil;
42 public final class UniProtWsTools {
47 public final static String BASE_URL = "http://www.uniprot.org/";
48 public final static String BASE_EMBL_DB_URL = "http://www.ebi.ac.uk/Tools/dbfetch/dbfetch/embl/";
49 private final static String URL_ENC = "UTF-8";
50 // uniprot/expasy accession number format (6 chars):
51 // letter digit letter-or-digit letter-or-digit letter-or-digit digit
52 // ?: => no back-reference
53 // \A => begin of String
54 // \Z => end of String
55 private final static Pattern UNIPROT_AC_PATTERN = Pattern
56 .compile( "(?:\\A|.*[^a-zA-Z0-9])([A-Z]\\d[A-Z0-9]{3}\\d)(?:[^a-zA-Z0-9]|\\Z)" );
57 private final static boolean DEBUG = true;
59 private static String encode( final String str ) throws UnsupportedEncodingException {
60 return URLEncoder.encode( str.trim(), URL_ENC );
64 * Returns null if no match.
70 static public String parseUniProtAccessor( final String query ) {
71 final Matcher m = UNIPROT_AC_PATTERN.matcher( query );
72 if ( m.lookingAt() ) {
80 public static List<UniProtTaxonomy> getTaxonomiesFromCommonName( final String cn, final int max_taxonomies_return )
82 final List<String> result = getTaxonomyStringFromCommonName( cn, max_taxonomies_return );
83 if ( result.size() > 0 ) {
84 return parseUniProtTaxonomy( result );
89 public static List<UniProtTaxonomy> getTaxonomiesFromCommonNameStrict( final String cn,
90 final int max_taxonomies_return )
92 final List<UniProtTaxonomy> taxonomies = getTaxonomiesFromCommonName( cn, max_taxonomies_return );
93 if ( ( taxonomies != null ) && ( taxonomies.size() > 0 ) ) {
94 final List<UniProtTaxonomy> filtered_taxonomies = new ArrayList<UniProtTaxonomy>();
95 for( final UniProtTaxonomy taxonomy : taxonomies ) {
96 if ( taxonomy.getCommonName().equalsIgnoreCase( cn ) ) {
97 filtered_taxonomies.add( taxonomy );
100 return filtered_taxonomies;
105 public static List<UniProtTaxonomy> getTaxonomiesFromId( final String id, final int max_taxonomies_return )
107 final List<String> result = getTaxonomyStringFromId( id, max_taxonomies_return );
108 if ( result.size() > 0 ) {
109 return parseUniProtTaxonomy( result );
114 public static List<UniProtTaxonomy> getTaxonomiesFromScientificName( final String sn,
115 final int max_taxonomies_return )
117 // Hack! Craniata? ..
118 if ( sn.equals( "Drosophila" ) ) {
119 return hack( UniProtTaxonomy.DROSOPHILA_GENUS );
121 else if ( sn.equals( "Xenopus" ) ) {
122 return hack( UniProtTaxonomy.XENOPUS_GENUS );
124 final List<String> result = getTaxonomyStringFromScientificName( sn, max_taxonomies_return );
125 if ( result.size() > 0 ) {
126 return parseUniProtTaxonomy( result );
132 * Does not return "sub-types".
133 * For example, for "Mus musculus" only returns "Mus musculus"
134 * and not "Mus musculus", "Mus musculus bactrianus", ...
137 public static List<UniProtTaxonomy> getTaxonomiesFromScientificNameStrict( final String sn,
138 final int max_taxonomies_return )
140 final List<UniProtTaxonomy> taxonomies = getTaxonomiesFromScientificName( sn, max_taxonomies_return );
141 if ( ( taxonomies != null ) && ( taxonomies.size() > 0 ) ) {
142 final List<UniProtTaxonomy> filtered_taxonomies = new ArrayList<UniProtTaxonomy>();
143 for( final UniProtTaxonomy taxonomy : taxonomies ) {
144 if ( taxonomy.getScientificName().equalsIgnoreCase( sn ) ) {
145 filtered_taxonomies.add( taxonomy );
148 return filtered_taxonomies;
153 public static List<UniProtTaxonomy> getTaxonomiesFromTaxonomyCode( final String code,
154 final int max_taxonomies_return )
156 String my_code = new String( code );
158 if ( my_code.equals( "FUGRU" ) ) {
161 else if ( my_code.equals( "CAP" ) ) {
162 return hack( UniProtTaxonomy.CAPITELLA_TELATA_SPECIES );
164 final List<String> result = getTaxonomyStringFromTaxonomyCode( my_code, max_taxonomies_return );
165 if ( result.size() > 0 ) {
166 return parseUniProtTaxonomy( result );
171 private static List<String> getTaxonomyStringFromCommonName( final String cn, final int max_lines_to_return )
173 return queryUniprot( "taxonomy/?query=common%3a%22" + encode( cn ) + "%22&format=tab", max_lines_to_return );
176 private static List<String> getTaxonomyStringFromId( final String id, final int max_lines_to_return )
178 System.out.println( "getting tax from ID" );
179 return queryUniprot( "taxonomy/?query=id%3a%22" + encode( id ) + "%22&format=tab", max_lines_to_return );
182 private static List<String> getTaxonomyStringFromScientificName( final String sn, final int max_lines_to_return )
184 return queryUniprot( "taxonomy/?query=scientific%3a%22" + encode( sn ) + "%22&format=tab", max_lines_to_return );
187 private static List<String> getTaxonomyStringFromTaxonomyCode( final String code, final int max_lines_to_return )
189 return queryUniprot( "taxonomy/?query=mnemonic%3a%22" + encode( code ) + "%22&format=tab", max_lines_to_return );
192 private static List<UniProtTaxonomy> hack( final UniProtTaxonomy tax ) {
193 final List<UniProtTaxonomy> l = new ArrayList<UniProtTaxonomy>();
198 private static List<UniProtTaxonomy> parseUniProtTaxonomy( final List<String> result ) throws IOException {
199 final List<UniProtTaxonomy> taxonomies = new ArrayList<UniProtTaxonomy>();
200 for( final String line : result ) {
201 if ( ForesterUtil.isEmpty( line ) ) {
202 // Ignore empty lines.
204 else if ( line.startsWith( "Taxon" ) ) {
205 final String[] items = line.split( "\t" );
206 if ( !( items[ 1 ].equalsIgnoreCase( "Mnemonic" ) && items[ 2 ].equalsIgnoreCase( "Scientific name" )
207 && items[ 3 ].equalsIgnoreCase( "Common name" ) && items[ 4 ].equalsIgnoreCase( "Synonym" )
208 && items[ 5 ].equalsIgnoreCase( "Other Names" ) && items[ 6 ].equalsIgnoreCase( "Reviewed" )
209 && items[ 7 ].equalsIgnoreCase( "Rank" ) && items[ 8 ].equalsIgnoreCase( "Lineage" ) ) ) {
210 throw new IOException( "Unreconized UniProt Taxonomy format: " + line );
214 if ( line.split( "\t" ).length > 4 ) {
215 taxonomies.add( new UniProtTaxonomy( line ) );
222 public static List<String> queryEmblDb( final String query, final int max_lines_to_return ) throws IOException {
223 return queryDb( query, max_lines_to_return, BASE_EMBL_DB_URL );
226 public static List<String> queryUniprot( final String query, final int max_lines_to_return ) throws IOException {
227 return queryDb( query, max_lines_to_return, BASE_URL );
230 public static List<String> queryDb( final String query, int max_lines_to_return, final String base_url )
232 if ( ForesterUtil.isEmpty( query ) ) {
233 throw new IllegalArgumentException( "illegal attempt to use empty query " );
235 if ( max_lines_to_return < 1 ) {
236 max_lines_to_return = 1;
238 final URL url = new URL( base_url + query );
240 System.out.println( "url: " + url.toString() );
242 final URLConnection urlc = url.openConnection();
243 final BufferedReader in = new BufferedReader( new InputStreamReader( urlc.getInputStream() ) );
245 final List<String> result = new ArrayList<String>();
246 while ( ( line = in.readLine() ) != null ) {
248 System.out.println( line );
251 if ( result.size() > max_lines_to_return ) {
259 public static SequenceDatabaseEntry obtainUniProtEntry( final String query, final int max_lines_to_return )
261 final List<String> lines = queryUniprot( "uniprot/" + query + ".txt", max_lines_to_return );
262 return UniProtEntry.createInstanceFromPlainText( lines );
265 public static SequenceDatabaseEntry obtainEmblEntry( final String query, final int max_lines_to_return )
267 final List<String> lines = queryEmblDb( query, max_lines_to_return );
268 return EbiDbEntry.createInstanceFromPlainText( lines );