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.Accession;
42 import org.forester.util.ForesterUtil;
43 import org.forester.ws.wabi.RestUtil;
45 public final class Blast {
47 final public static void openNcbiBlastWeb( final String query,
48 final boolean is_nucleic_acids,
51 //http://www.ncbi.nlm.nih.gov/blast/Blast.cgi?CMD=Web&PAGE=Proteins&DATABASE=swissprot&QUERY=gi|163848401
52 final StringBuilder uri_str = new StringBuilder();
53 uri_str.append( "http://www.ncbi.nlm.nih.gov/blast/Blast.cgi?CMD=Web&DATABASE=nr&PAGE=" );
54 if ( is_nucleic_acids ) {
55 uri_str.append( "Nucleotide" );
58 uri_str.append( "Proteins" );
60 uri_str.append( "&QUERY=" );
61 uri_str.append( query );
63 AptxUtil.launchWebBrowser( new URI( uri_str.toString() ), applet != null, applet, "_aptx_blast" );
65 catch ( final IOException e ) {
66 AptxUtil.showErrorMessage( p, e.toString() );
69 catch ( final URISyntaxException e ) {
70 AptxUtil.showErrorMessage( p, e.toString() );
75 final public static String obtainQueryForBlast( final PhylogenyNode node ) {
77 if ( !ForesterUtil.isEmpty( node.getNodeData().getSequence().getMolecularSequence() ) ) {
78 query = node.getNodeData().getSequence().getMolecularSequence();
80 else if ( ( node.getNodeData().getSequence().getAccession() != null )
81 && !ForesterUtil.isEmpty( node.getNodeData().getSequence().getAccession().getValue() ) ) {
82 if ( !ForesterUtil.isEmpty( node.getNodeData().getSequence().getAccession().getSource() ) ) {
83 query = node.getNodeData().getSequence().getAccession().getSource() + "%7C";
85 query += node.getNodeData().getSequence().getAccession().getValue();
87 else if ( !ForesterUtil.isEmpty( node.getNodeData().getSequence().getName() ) ) {
88 final Accession acc = AptxUtil.obtainSequenceAccessionFromName( node.getNodeData().getSequence().getName() );
90 query = acc.getSource() + "%7C" + acc.getValue();
96 final public static boolean isContainsQueryForBlast( final PhylogenyNode node ) {
97 return !ForesterUtil.isEmpty( obtainQueryForBlast( node ) );
100 final public void ddbjBlast( final String geneName ) {
101 // Retrieve accession number list which has specified gene name from searchByXMLPath of ARSA. Please click here for details of ARSA.
102 /*target: Sequence length is between 300bp and 1000bp.
104 Gene qualifire is same as specified gene name.*/
105 String queryPath = "/ENTRY/DDBJ/division=='HUM' AND (/ENTRY/DDBJ/length>=300 AND "
106 + "/ENTRY/DDBJ/length<=1000) ";
107 queryPath += "AND (/ENTRY/DDBJ/feature-table/feature{/f_key = 'CDS' AND ";
108 queryPath += "/f_quals/qualifier{/q_name = 'gene' AND /q_value=='" + geneName + "'}})";
109 String query = "service=ARSA&method=searchByXMLPath&queryPath=" + queryPath
110 + "&returnPath=/ENTRY/DDBJ/primary-accession&offset=1&count=100";
112 String arsaResult = null;
114 arsaResult = RestUtil.getResult( query );
116 catch ( final IOException e ) {
117 // TODO Auto-generated catch block
120 final String[] arsaResultLines = arsaResult.split( "\n" );
122 final int arsaResultNum = Integer.parseInt( arsaResultLines[ 0 ].replaceAll( "hitscount =", "" ).trim() );
123 //If there is no hit, print a message and exit
124 if ( arsaResultNum == 0 ) {
125 System.out.println( "There is no entry for gene:" + geneName );
128 //Retrieve DNA sequence of top hit entry by using getFASTA_DDBJEntry of GetEntry.
129 //Retrieve DNA sequence of first fit.
130 final String repAccession = arsaResultLines[ 2 ];
131 query = "service=GetEntry&method=getFASTA_DDBJEntry&accession=" + repAccession;
132 String dnaSeq = null;
134 dnaSeq = RestUtil.getResult( query );
136 catch ( final IOException e ) {
137 // TODO Auto-generated catch block
140 System.out.println( "Retrieved DNA sequence is: " + dnaSeq );
141 //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).
142 //Execute blastn with step3's sequence
143 query = "service=Blast&method=searchParam&program=blastn&database=ddbjpri ddbjrod ddbjmam ddbjvrt "
144 + "ddbjinv&query=" + dnaSeq + "¶m=-m 8 -b 50 -v 50 -e 0.0001";
145 String blastResult = null;
147 blastResult = RestUtil.getResult( query );
149 catch ( final IOException e ) {
150 // TODO Auto-generated catch block
153 // Extract both accession number and similarity score from BLAST result.
154 // 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.
155 final String blastResultLines[] = blastResult.split( "\n" );
156 final Vector<String[]> parsedBlastResult = new Vector<String[]>();
157 for( final String blastResultLine : blastResultLines ) {
158 final String cols[] = blastResultLine.split( "\t" );
159 final String accession = cols[ 1 ].substring( 0, cols[ 1 ].indexOf( "|" ) );
160 final String[] result = { accession, cols[ 2 ] };
161 parsedBlastResult.add( result );
163 // Retrieve species name by using searchByXMLPath of ARSA. If the plural subjects whose species
164 // name are same are in the result, the highest similarity score is used.
165 //Retrieve species from accession number.
166 final Hashtable<String, String> organismAccession = new Hashtable<String, String>();
167 for( int i = 0; i < parsedBlastResult.size(); i++ ) {
168 final String[] parsed = parsedBlastResult.elementAt( i );
169 query = "service=ARSA&method=searchByXMLPath&queryPath=/ENTRY/DDBJ/primary-accession=='" + parsed[ 0 ]
170 + "'&returnPath=/ENTRY/DDBJ/organism&offset=1&count=100";
171 String organism = null;
173 organism = RestUtil.getResult( query );
175 catch ( final IOException e ) {
176 // TODO Auto-generated catch block
179 final String[] organismLines = organism.split( "\n" );
180 organism = organismLines[ 2 ];
181 //If same organism name hits, use first hit.
182 if ( !organismAccession.containsKey( organism ) ) {
183 organismAccession.put( organism, parsed[ 0 ] + "\t" + parsed[ 1 ] );
188 System.out.println( "DDBJ entries: " + arsaResultNum );
189 System.out.println( "Representative accession: " + repAccession );
190 System.out.println( "Organism name\tDDBJ accession number\tSequence similarity" );
191 final String[] keys = new String[ organismAccession.size() ];
192 final Enumeration<String> enu = organismAccession.keys();
194 while ( enu.hasMoreElements() ) {
195 keys[ count ] = enu.nextElement();
199 for( final String key : keys ) {
200 System.out.println( key + "\t" + organismAccession.get( key ) );