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 org.biojava.nbio.structure.symmetry.core;
022
023import org.biojava.nbio.structure.Structure;
024
025import java.util.Collections;
026import java.util.List;
027
028/**
029 * Clusters the chains of one or two structures by sequence.
030 */
031public class ClusterProteinChains {
032        private Structure structure = null;
033        private Structure structure2 = null;
034        private QuatSymmetryParameters parameters = null;
035        private ClusterMerger merger = null;
036        private int proteinChainCount = 0;
037        private int nucleicAcidChainCount = 0;
038
039        public ClusterProteinChains(Structure structure, QuatSymmetryParameters parameters) {
040                this.structure = structure;
041                this.parameters = parameters;
042                run();
043        }
044
045        public ClusterProteinChains(Structure structure1, Structure structure2, QuatSymmetryParameters parameters) {
046                this.structure = structure1;
047                this.structure2 = structure2;
048                this.parameters = parameters;
049                run();
050        }
051
052        /**
053         * Get a non-redundent set of clusters for a given sequence cutoff
054         * @param sequenceIdentityThreshold
055         * @return
056         */
057        public List<SequenceAlignmentCluster> getSequenceAlignmentClusters(double sequenceIdentityThreshold) {
058                if (merger == null) {
059                        return Collections.emptyList();
060                }
061                return merger.getMergedClusters(sequenceIdentityThreshold);
062        }
063
064        /**
065         * @return the proteinChainCount
066         */
067        public int getProteinChainCount() {
068                return proteinChainCount;
069        }
070
071        /**
072         * @return the nucleicAcidChainCount
073         */
074        public int getNucleicAcidChainCount() {
075                return nucleicAcidChainCount;
076        }
077
078        private void run () {
079                // cluster protein entities
080                List<SequenceAlignmentCluster> seqClusters = null;
081
082                if (structure2 == null) {
083                        ProteinSequenceClusterer clusterer = new ProteinSequenceClusterer(structure, parameters);
084                        seqClusters = clusterer.getSequenceAlignmentClusters();
085                        proteinChainCount = clusterer.getProteinChainCount();
086                        nucleicAcidChainCount = clusterer.getNucleicAcidChainCount();
087                } else if (structure !=null && structure2 != null) {
088                        ProteinSequenceClusterer clusterer = new ProteinSequenceClusterer(structure, structure2, parameters);
089                        seqClusters = clusterer.getSequenceAlignmentClusters();
090                }
091                if (seqClusters == null  || seqClusters.size() == 0) {
092                        return;
093                }
094
095                // calculate pairwise aligment between protein clusters
096                merger = new ClusterMerger(seqClusters, parameters);
097                merger.calcPairwiseAlignments();
098        }
099}