2 // FORESTER -- software libraries and applications
3 // for evolutionary biology research and applications.
5 // Copyright (C) 2008-2009 Christian M. Zmasek
6 // Copyright (C) 2008-2009 Burnham Institute for Medical Research
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.archaeopteryx.tools;
28 import java.io.IOException;
30 import java.net.URISyntaxException;
31 import java.util.Arrays;
32 import java.util.Enumeration;
33 import java.util.Hashtable;
34 import java.util.Vector;
36 import javax.swing.JApplet;
38 import org.forester.archaeopteryx.AptxUtil;
39 import org.forester.archaeopteryx.TreePanel;
40 import org.forester.phylogeny.PhylogenyNode;
41 import org.forester.phylogeny.data.Identifier;
42 import org.forester.util.ForesterUtil;
43 import org.forester.util.SequenceIdParser;
44 import org.forester.ws.wabi.RestUtil;
46 public final class Blast {
48 final public static void openNcbiBlastWeb( final String query,
49 final boolean is_nucleic_acids,
52 //http://www.ncbi.nlm.nih.gov/blast/Blast.cgi?CMD=Web&PAGE=Proteins&DATABASE=swissprot&QUERY=gi|163848401
53 final StringBuilder uri_str = new StringBuilder();
54 uri_str.append( "http://www.ncbi.nlm.nih.gov/blast/Blast.cgi?CMD=Web&DATABASE=nr&PAGE=" );
55 if ( is_nucleic_acids ) {
56 uri_str.append( "Nucleotide" );
59 uri_str.append( "Proteins" );
61 uri_str.append( "&QUERY=" );
62 uri_str.append( query );
64 AptxUtil.launchWebBrowser( new URI( uri_str.toString() ), applet != null, applet, "_aptx_blast" );
66 catch ( final IOException e ) {
67 AptxUtil.showErrorMessage( p, e.toString() );
70 catch ( final URISyntaxException e ) {
71 AptxUtil.showErrorMessage( p, e.toString() );
76 final public static String obtainQueryForBlast( final PhylogenyNode node ) {
78 if ( node.getNodeData().isHasSequence() ) {
79 if ( !ForesterUtil.isEmpty( node.getNodeData().getSequence().getMolecularSequence() ) ) {
80 query = node.getNodeData().getSequence().getMolecularSequence();
82 if ( ForesterUtil.isEmpty( query ) && ( node.getNodeData().getSequence().getAccession() != null )
83 && !ForesterUtil.isEmpty( node.getNodeData().getSequence().getAccession().getValue() ) ) {
84 final Identifier id = SequenceIdParser.parse( node.getNodeData().getSequence().getAccession()
87 query = id.getValue();
90 if ( ForesterUtil.isEmpty( query ) && !ForesterUtil.isEmpty( node.getNodeData().getSequence().getName() ) ) {
91 final Identifier id = SequenceIdParser.parse( node.getNodeData().getSequence().getName() );
93 query = id.getValue();
96 if ( ForesterUtil.isEmpty( query ) && !ForesterUtil.isEmpty( node.getNodeData().getSequence().getSymbol() ) ) {
97 final Identifier id = SequenceIdParser.parse( node.getNodeData().getSequence().getSymbol() );
99 query = id.getValue();
103 if ( ForesterUtil.isEmpty( query ) && !ForesterUtil.isEmpty( node.getName() ) ) {
104 final Identifier id = SequenceIdParser.parse( node.getName() );
106 query = id.getValue();
112 final public static boolean isContainsQueryForBlast( final PhylogenyNode node ) {
113 return !ForesterUtil.isEmpty( obtainQueryForBlast( node ) );
116 final public void ddbjBlast( final String geneName ) {
117 // Retrieve accession number list which has specified gene name from searchByXMLPath of ARSA. Please click here for details of ARSA.
118 /*target: Sequence length is between 300bp and 1000bp.
120 Gene qualifire is same as specified gene name.*/
121 String queryPath = "/ENTRY/DDBJ/division=='HUM' AND (/ENTRY/DDBJ/length>=300 AND "
122 + "/ENTRY/DDBJ/length<=1000) ";
123 queryPath += "AND (/ENTRY/DDBJ/feature-table/feature{/f_key = 'CDS' AND ";
124 queryPath += "/f_quals/qualifier{/q_name = 'gene' AND /q_value=='" + geneName + "'}})";
125 String query = "service=ARSA&method=searchByXMLPath&queryPath=" + queryPath
126 + "&returnPath=/ENTRY/DDBJ/primary-accession&offset=1&count=100";
128 String arsaResult = null;
130 arsaResult = RestUtil.getResult( query );
132 catch ( final IOException e ) {
133 // TODO Auto-generated catch block
136 final String[] arsaResultLines = arsaResult.split( "\n" );
138 final int arsaResultNum = Integer.parseInt( arsaResultLines[ 0 ].replaceAll( "hitscount =", "" ).trim() );
139 //If there is no hit, print a message and exit
140 if ( arsaResultNum == 0 ) {
141 System.out.println( "There is no entry for gene:" + geneName );
144 //Retrieve DNA sequence of top hit entry by using getFASTA_DDBJEntry of GetEntry.
145 //Retrieve DNA sequence of first fit.
146 final String repAccession = arsaResultLines[ 2 ];
147 query = "service=GetEntry&method=getFASTA_DDBJEntry&accession=" + repAccession;
148 String dnaSeq = null;
150 dnaSeq = RestUtil.getResult( query );
152 catch ( final IOException e ) {
153 // TODO Auto-generated catch block
156 System.out.println( "Retrieved DNA sequence is: " + dnaSeq );
157 //Execute blastn by using searchParam of Blast with step2's sequence. Specified option is -e 0.0001 -m 8 -b 50 -v 50. It means "Extract top 50 hit which E-value is more than 0.0001.". The reference databases are specified as follows. ddbjpri(primates) ddbjrod(rodents) ddbjmam(mammals) ddbjvrt(vertebrates ) ddbjinv(invertebrates).
158 //Execute blastn with step3's sequence
159 query = "service=Blast&method=searchParam&program=blastn&database=ddbjpri ddbjrod ddbjmam ddbjvrt "
160 + "ddbjinv&query=" + dnaSeq + "¶m=-m 8 -b 50 -v 50 -e 0.0001";
161 String blastResult = null;
163 blastResult = RestUtil.getResult( query );
165 catch ( final IOException e ) {
166 // TODO Auto-generated catch block
169 // Extract both accession number and similarity score from BLAST result.
170 // This step does not use Web API and extract the part of result or edit the result. Please click here to see the details of each column in the BLAST tab delimited format which is generated by -m 8 option.
171 final String blastResultLines[] = blastResult.split( "\n" );
172 final Vector<String[]> parsedBlastResult = new Vector<String[]>();
173 for( final String blastResultLine : blastResultLines ) {
174 final String cols[] = blastResultLine.split( "\t" );
175 final String accession = cols[ 1 ].substring( 0, cols[ 1 ].indexOf( "|" ) );
176 final String[] result = { accession, cols[ 2 ] };
177 parsedBlastResult.add( result );
179 // Retrieve species name by using searchByXMLPath of ARSA. If the plural subjects whose species
180 // name are same are in the result, the highest similarity score is used.
181 //Retrieve species from accession number.
182 final Hashtable<String, String> organismAccession = new Hashtable<String, String>();
183 for( int i = 0; i < parsedBlastResult.size(); i++ ) {
184 final String[] parsed = parsedBlastResult.elementAt( i );
185 query = "service=ARSA&method=searchByXMLPath&queryPath=/ENTRY/DDBJ/primary-accession=='" + parsed[ 0 ]
186 + "'&returnPath=/ENTRY/DDBJ/organism&offset=1&count=100";
187 String organism = null;
189 organism = RestUtil.getResult( query );
191 catch ( final IOException e ) {
192 // TODO Auto-generated catch block
195 final String[] organismLines = organism.split( "\n" );
196 organism = organismLines[ 2 ];
197 //If same organism name hits, use first hit.
198 if ( !organismAccession.containsKey( organism ) ) {
199 organismAccession.put( organism, parsed[ 0 ] + "\t" + parsed[ 1 ] );
204 System.out.println( "DDBJ entries: " + arsaResultNum );
205 System.out.println( "Representative accession: " + repAccession );
206 System.out.println( "Organism name\tDDBJ accession number\tSequence similarity" );
207 final String[] keys = new String[ organismAccession.size() ];
208 final Enumeration<String> enu = organismAccession.keys();
210 while ( enu.hasMoreElements() ) {
211 keys[ count ] = enu.nextElement();
215 for( final String key : keys ) {
216 System.out.println( key + "\t" + organismAccession.get( key ) );