private void MakeDendrogs(AglomerativeType linkage) { ClusterOutput outCl; hierarchicalCluster dendrog = new hierarchicalCluster(dMeasure,linkage,dirName); currentV = 0; maxV = leaves.Count+1; double remProgress = currentProgress; for(int i=0;i<leaves.Count;i++) { HClusterNode c = leaves[i]; dendrog.mustRefStructure = c.setStruct[0]; outCl = dendrog.HierarchicalClustering(c.setStruct); dendrogList.Add(c); c.levelDist = outCl.hNode.levelDist; c.realDist = dMeasure.GetRealValue(c.levelDist); c.refStructure = outCl.hNode.refStructure; if(outCl.hNode.joined!=null) { c.joined = new List<HClusterNode>(); foreach (var item in outCl.hNode.joined) c.joined.Add(item); } currentV++; currentProgress=remProgress+1.0/maxProgress* (double)currentV / maxV; } maxV = currentV; currentProgress = remProgress; }
private void RunHierarchicalCluster(string name, string dirName,string alignFile=null, DCDFile dcd=null) { DateTime cpuPart1 = DateTime.Now; DistanceMeasure distance = null; //distance.CalcDistMatrix(distance.structNames); // opt.hierarchical.atoms = PDB.PDBMODE.ALL_ATOMS; if(dcd!=null) distance = CreateMeasureForDCD(dcd, opt.hierarchical.distance, opt.hierarchical.atoms, opt.hierarchical.reference1DjuryAglom, opt.hierarchical.alignmentFileName, opt.hierarchical.hammingProfile, opt.hierarchical.jury1DProfileAglom); else distance = CreateMeasure(name,dirName,opt.hierarchical.distance, opt.hierarchical.atoms, opt.hierarchical.reference1DjuryAglom, alignFile, opt.hierarchical.hammingProfile, opt.hierarchical.jury1DProfileAglom); DebugClass.WriteMessage("Measure Created"); hierarchicalCluster hk = new hierarchicalCluster(distance, opt.hierarchical.linkageType,dirName); clType = hk.ToString(); ClusterOutput output; progressDic.Add(name, hk); distance.InitMeasure(); DateTime cpuPart2 = DateTime.Now; output = hk.HierarchicalClustering(new List<string>(distance.structNames.Keys)); UpdateOutput(name, dirName, alignFile,output, distance.ToString(), cpuPart1, cpuPart2, hk); }
public ClusterOutput DendrogUsingMeasures(List<string> structures) { jury1D juryLocal = new jury1D(); juryLocal.PrepareJury(al); ClusterOutput outC = null; Dictionary<string, List<int>> dic; //Console.WriteLine("Start after jury " + Process.GetCurrentProcess().PeakWorkingSet64); maxV = 4; currentV = 0; dic = PrepareKeys(structures,false); currentV++; //DebugClass.DebugOn(); //dic = HashEntropyCombine(dic, structures,input.reqClusters); //Console.WriteLine("Entropy ready after jury " + Process.GetCurrentProcess().PeakWorkingSet64); DebugClass.WriteMessage("Entropy ready"); //Alternative way to start of UQclust Tree must be finished //input.relClusters = 10000; input.relClusters = input.reqClusters; input.perData = 90; //dic = FastCombineKeys(dic, structures, false); dic = FastCombineKeys(dic, structures, true); DebugClass.WriteMessage("dic size" + dic.Count); currentV++; //Console.WriteLine("Combine ready after jury " + Process.GetCurrentProcess().PeakWorkingSet64); DebugClass.WriteMessage("Combine Keys ready"); Dictionary<string, string> translateToCluster = new Dictionary<string, string>(dic.Count); List<string> structuresToDendrogram = new List<string>(dic.Count); List<string> structuresFullPath = new List<string>(dic.Count); DebugClass.WriteMessage("Number of clusters: "+dic.Count); int cc = 0; foreach (var item in dic) { if (item.Value.Count > 2) { List<string> cluster = new List<string>(item.Value.Count); foreach (var str in item.Value) cluster.Add(structures[str]); ClusterOutput output = juryLocal.JuryOptWeights(cluster); structuresToDendrogram.Add(output.juryLike[0].Key); if(alignFile==null) structuresFullPath.Add(dirName + Path.DirectorySeparatorChar + output.juryLike[0].Key); else structuresFullPath.Add(output.juryLike[0].Key); translateToCluster.Add(output.juryLike[0].Key, item.Key); } else { structuresToDendrogram.Add(structures[item.Value[0]]); if(alignFile==null) structuresFullPath.Add(dirName + Path.DirectorySeparatorChar + structures[item.Value[0]]); else structuresFullPath.Add(structures[item.Value[0]]); translateToCluster.Add(structures[item.Value[0]], item.Key); } cc++; } currentV++; DebugClass.WriteMessage("Jury finished"); switch (dMeasure) { case DistanceMeasures.HAMMING: if (refJuryProfile == null || !jury1d) throw new Exception("Sorry but for jury measure you have to define 1djury profile to find reference structure"); else dist = new JuryDistance(structuresFullPath, alignFile, true, profileName, refJuryProfile); break; case DistanceMeasures.COSINE: dist = new CosineDistance(structuresFullPath, alignFile, jury1d, profileName, refJuryProfile); break; case DistanceMeasures.RMSD: dist = new Rmsd(structuresFullPath, "", jury1d, atoms, refJuryProfile); break; case DistanceMeasures.MAXSUB: dist = new MaxSub(structuresFullPath, "", jury1d, refJuryProfile); break; } // return new ClusterOutput(); DebugClass.WriteMessage("Start hierarchical"); //Console.WriteLine("Start hierarchical " + Process.GetCurrentProcess().PeakWorkingSet64); currentV = maxV; hk = new hierarchicalCluster(dist, linkageType, dirName); dist.InitMeasure(); //Now just add strctures to the leaves outC = hk.HierarchicalClustering(structuresToDendrogram); DebugClass.WriteMessage("Stop hierarchical"); List<HClusterNode> hLeaves = outC.hNode.GetLeaves(); foreach(var item in hLeaves) { if (translateToCluster.ContainsKey(item.setStruct[0])) { foreach (var str in dic[translateToCluster[item.setStruct[0]]]) if (item.setStruct[0] != structures[str]) item.setStruct.Add(structures[str]); } else throw new Exception("Cannot add structure. Something is wrong"); } outC.hNode.RedoSetStructures(); return outC; }