001/*
002 *                    BioJava development code
003 *
004 * This code may be freely distributed and modified under the
005 * terms of the GNU Lesser General Public Licence.  This should
006 * be distributed with the code.  If you do not have a copy,
007 * see:
008 *
009 *      http://www.gnu.org/copyleft/lesser.html
010 *
011 * Copyright for this code is held jointly by the individual
012 * authors.  These should be listed in @author doc comments.
013 *
014 * For more information on the BioJava project and its aims,
015 * or to join the biojava-l mailing list, visit the home page
016 * at:
017 *
018 *      http://www.biojava.org/
019 *
020 */
021package demo;
022
023import org.biojava.nbio.core.sequence.ProteinSequence;
024import org.biojava.nbio.core.sequence.compound.AminoAcidCompound;
025import org.biojava.nbio.core.sequence.compound.AminoAcidCompoundSet;
026import org.biojava.nbio.core.sequence.loader.UniprotProxySequenceReader;
027import org.biojava.nbio.ws.hmmer.HmmerDomain;
028import org.biojava.nbio.ws.hmmer.HmmerResult;
029import org.biojava.nbio.ws.hmmer.RemoteHmmerScan;
030
031import java.util.SortedSet;
032
033/**
034 * The cookbook recipe for how to request Pfam annotations for a protein sequence using the Hmmer3 service
035 *
036 * @author Andreas Prlic
037 * @since 3.0.3
038 */
039public class HmmerDemo {
040
041        public static void main(String[] args) throws Exception {
042
043
044                // first we get a UniProt sequence
045                String uniProtID = "P08487";
046                ProteinSequence seq = getUniprot(uniProtID);
047
048
049                // now we submit this sequence to the Hmmer web site
050                RemoteHmmerScan hmmer = new RemoteHmmerScan();
051
052                SortedSet<HmmerResult> results = hmmer.scan(seq);
053
054                // and now let's print out the obtained annotations
055
056                System.out.println(String.format("#\t%15s\t%10s\t%s\t%s\t%8s\t%s",
057                                "Domain","ACC", "Start","End","eValue","Description"));
058
059                int counter = 0;
060                for (HmmerResult hmmerResult : results) {
061                        //System.out.println(hmmerResult);
062
063                        for ( HmmerDomain domain : hmmerResult.getDomains()) {
064                                counter++;
065                                System.out.println(String.format("%d\t%15s\t%10s\t%5d\t%5d\t%.2e\t%s",
066                                                counter,
067                                                hmmerResult.getName(), domain.getHmmAcc(),
068                                                domain.getSqFrom(),domain.getSqTo(),
069                                                domain.getEvalue(), hmmerResult.getDesc()
070                                                ));
071
072                        }
073
074                }
075
076
077        }
078
079        /**
080         * Fetch a protein sequence from the UniProt web site
081         *
082         * @param uniProtID
083         * @return a Protein Sequence
084         * @throws Exception
085         */
086        private static ProteinSequence getUniprot(String uniProtID) throws Exception {
087
088                AminoAcidCompoundSet set = AminoAcidCompoundSet.getAminoAcidCompoundSet();
089                UniprotProxySequenceReader<AminoAcidCompound> uniprotSequence = new UniprotProxySequenceReader<AminoAcidCompound>(uniProtID,set);
090
091                ProteinSequence seq = new ProteinSequence(uniprotSequence);
092
093                return seq;
094        }
095}