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 private final static String URL_ENC = "UTF-8";
49 // uniprot/expasy accession number format (6 chars):
50 // letter digit letter-or-digit letter-or-digit letter-or-digit digit
51 private final static Pattern UNIPROT_AC_PATTERN = Pattern
52 .compile( "^.*[^a-zA-Z0-9]?([A-NR-ZOPQ]\\d[A-Z0-9]{3}\\d)[^a-zA-Z0-9]?" );
53 private final static boolean DEBUG = false;
55 private static String encode( final String str ) throws UnsupportedEncodingException {
56 return URLEncoder.encode( str.trim(), URL_ENC );
60 * Return null if no match.
66 static public String parseUniProtAccessor( final String query ) {
67 final Matcher m = UNIPROT_AC_PATTERN.matcher( query );
68 if ( m.lookingAt() ) {
76 public static List<UniProtTaxonomy> getTaxonomiesFromCommonName( final String cn, final int max_taxonomies_return )
78 final List<String> result = getTaxonomyStringFromCommonName( cn, max_taxonomies_return );
79 if ( result.size() > 0 ) {
80 return parseUniProtTaxonomy( result );
85 public static List<UniProtTaxonomy> getTaxonomiesFromCommonNameStrict( final String cn,
86 final int max_taxonomies_return )
88 final List<UniProtTaxonomy> taxonomies = getTaxonomiesFromCommonName( cn, max_taxonomies_return );
89 if ( ( taxonomies != null ) && ( taxonomies.size() > 0 ) ) {
90 final List<UniProtTaxonomy> filtered_taxonomies = new ArrayList<UniProtTaxonomy>();
91 for( final UniProtTaxonomy taxonomy : taxonomies ) {
92 if ( taxonomy.getCommonName().equalsIgnoreCase( cn ) ) {
93 filtered_taxonomies.add( taxonomy );
96 return filtered_taxonomies;
101 public static List<UniProtTaxonomy> getTaxonomiesFromId( final String id, final int max_taxonomies_return )
103 final List<String> result = getTaxonomyStringFromId( id, max_taxonomies_return );
104 if ( result.size() > 0 ) {
105 return parseUniProtTaxonomy( result );
110 public static List<UniProtTaxonomy> getTaxonomiesFromScientificName( final String sn,
111 final int max_taxonomies_return )
113 // Hack! Craniata? ..
114 if ( sn.equals( "Drosophila" ) ) {
115 return hack( UniProtTaxonomy.DROSOPHILA_GENUS );
117 else if ( sn.equals( "Xenopus" ) ) {
118 return hack( UniProtTaxonomy.XENOPUS_GENUS );
120 final List<String> result = getTaxonomyStringFromScientificName( sn, max_taxonomies_return );
121 if ( result.size() > 0 ) {
122 return parseUniProtTaxonomy( result );
128 * Does not return "sub-types".
129 * For example, for "Mus musculus" only returns "Mus musculus"
130 * and not "Mus musculus", "Mus musculus bactrianus", ...
133 public static List<UniProtTaxonomy> getTaxonomiesFromScientificNameStrict( final String sn,
134 final int max_taxonomies_return )
136 final List<UniProtTaxonomy> taxonomies = getTaxonomiesFromScientificName( sn, max_taxonomies_return );
137 if ( ( taxonomies != null ) && ( taxonomies.size() > 0 ) ) {
138 final List<UniProtTaxonomy> filtered_taxonomies = new ArrayList<UniProtTaxonomy>();
139 for( final UniProtTaxonomy taxonomy : taxonomies ) {
140 if ( taxonomy.getScientificName().equalsIgnoreCase( sn ) ) {
141 filtered_taxonomies.add( taxonomy );
144 return filtered_taxonomies;
149 public static List<UniProtTaxonomy> getTaxonomiesFromTaxonomyCode( final String code,
150 final int max_taxonomies_return )
152 String my_code = new String( code );
154 if ( my_code.equals( "FUGRU" ) ) {
157 else if ( my_code.equals( "CAP" ) ) {
158 return hack( UniProtTaxonomy.CAPITELLA_TELATA_SPECIES );
160 final List<String> result = getTaxonomyStringFromTaxonomyCode( my_code, max_taxonomies_return );
161 if ( result.size() > 0 ) {
162 return parseUniProtTaxonomy( result );
167 private static List<String> getTaxonomyStringFromCommonName( final String cn, final int max_lines_to_return )
169 return queryUniprot( "taxonomy/?query=common%3a%22" + encode( cn ) + "%22&format=tab", max_lines_to_return );
172 private static List<String> getTaxonomyStringFromId( final String id, final int max_lines_to_return )
174 return queryUniprot( "taxonomy/?query=id%3a%22" + encode( id ) + "%22&format=tab", max_lines_to_return );
177 private static List<String> getTaxonomyStringFromScientificName( final String sn, final int max_lines_to_return )
179 return queryUniprot( "taxonomy/?query=scientific%3a%22" + encode( sn ) + "%22&format=tab", max_lines_to_return );
182 private static List<String> getTaxonomyStringFromTaxonomyCode( final String code, final int max_lines_to_return )
184 return queryUniprot( "taxonomy/?query=mnemonic%3a%22" + encode( code ) + "%22&format=tab", max_lines_to_return );
187 private static List<UniProtTaxonomy> hack( final UniProtTaxonomy tax ) {
188 final List<UniProtTaxonomy> l = new ArrayList<UniProtTaxonomy>();
193 private static List<UniProtTaxonomy> parseUniProtTaxonomy( final List<String> result ) throws IOException {
194 final List<UniProtTaxonomy> taxonomies = new ArrayList<UniProtTaxonomy>();
195 for( final String line : result ) {
196 if ( ForesterUtil.isEmpty( line ) ) {
197 // Ignore empty lines.
199 else if ( line.startsWith( "Taxon" ) ) {
200 //TODO next the check format FIXME
203 if ( line.split( "\t" ).length > 4 ) {
204 taxonomies.add( new UniProtTaxonomy( line ) );
211 public static List<String> queryUniprot( final String query, int max_lines_to_return ) throws IOException {
212 if ( ForesterUtil.isEmpty( query ) ) {
213 throw new IllegalArgumentException( "illegal attempt to use empty query " );
215 if ( max_lines_to_return < 1 ) {
216 max_lines_to_return = 1;
218 final URL url = new URL( BASE_URL + query );
220 System.out.println( "url: " + url.toString() );
222 final URLConnection urlc = url.openConnection();
223 final BufferedReader in = new BufferedReader( new InputStreamReader( urlc.getInputStream() ) );
225 final List<String> result = new ArrayList<String>();
226 while ( ( line = in.readLine() ) != null ) {
228 if ( result.size() > max_lines_to_return ) {
236 public static SequenceDatabaseEntry obtainUniProtEntry( final String query, final int max_lines_to_return )
238 final List<String> lines = queryUniprot( "uniprot/" + query + ".txt", max_lines_to_return );
239 return UniProtEntry.createInstanceFromPlainText( lines );