List<KeyValuePair<string,double>> CLusterRepresentJury(string dirName, List<string> targets,string profileName)
{
List<string> fileNames = new List<string>(targets.Count);
foreach (var item in targets)
fileNames.Add(dirName + Path.DirectorySeparatorChar + item);
jury1D jury = new jury1D();
jury.PrepareJury(fileNames, null, profileName);
ClusterOutput opt = jury.JuryOptWeights(targets);
//StreamWriter kk;
//if (File.Exists("cccc.txt"))
// kk = File.AppendText("cccc.txt");
//else
// kk = File.CreateText("cccc.txt");
//kk.WriteLine("dirNamae=" + dirName + " size=" + opt.juryLike.Count);
//for (int i = 0; i < opt.juryLike.Count; i++)
// kk.WriteLine(opt.juryLike[i].Key + " " + opt.juryLike[i].Value);
//kk.Close();
return opt.juryLike;
}
private void Run1DJury(string name, string dirName, string alignFile = null, DCDFile dcd = null)
{
DateTime cpuPart1 = DateTime.Now;
ClusterOutput output;
jury1D ju = new jury1D();
if (beginJob != null)
{
beginJob(currentProcessName, ju.ToString(), dirName, "NONE");
}
progressDic.Add(name, ju);
//DistanceMeasure distance = CreateMeasure();
if (opt.other.alignGenerate)
{
opt.other.alignFileName = "";
}
if (alignFile != null)
{
ju.PrepareJury(alignFile, opt.other.juryProfile);
}
else
if (dcd != null)
{
ju.PrepareJury(dcd, alignFile, opt.other.juryProfile);
}
else
{
ju.PrepareJury(dirName, alignFile, opt.other.juryProfile);
}
clType = ju.ToString();
DateTime cpuPart2 = DateTime.Now;
//jury1D ju = new jury1D(opt.weightHE,opt.weightC,(JuryDistance) distance);
//output = ju.JuryOpt(new List<string>(ju.stateAlign.Keys));
if (ju.alignKeys != null)
{
output = ju.JuryOptWeights(ju.alignKeys);
}
else
{
UpadateJobInfo(name, true, false);
throw new Exception("Alignment is epmty! Check errors");
}
UpdateOutput(name, dirName, alignFile, output, ju.ToString(), cpuPart1, cpuPart2, ju);
}
public ClusterOutput RunHTree()
{
HClusterNode root = null;
ClusterOutput outClust = hCluster.RunHashCluster();
Dictionary <string, List <int> > clusters = hCluster.dicFinal;
juryLocal.PrepareJury(hCluster.al);
ClusterOutput output;
List <HClusterNode> groundLevel = new List <HClusterNode>();
foreach (var item in clusters)
{
HClusterNode aux = new HClusterNode();
aux.parent = null;
aux.joined = null;
aux.setStruct = new List <string>(item.Value.Count + 1);
foreach (var index in item.Value)
{
aux.setStruct.Add(hCluster.structNames[index]);
}
output = juryLocal.JuryOptWeights(aux.setStruct);
aux.stateFreq = juryLocal.columns;
aux.refStructure = output.juryLike[0].Key;
aux.realDist = 0;
aux.levelDist = 0;
aux.dirName = item.Key;
aux.consistency = hCluster.CalcClusterConsistency(aux.setStruct);
groundLevel.Add(aux);
}
currentV = 20;
int size = groundLevel[0].dirName.Length;
double step = 80.0 / size;
for (int i = 1; i < size; i++)
{
Dictionary <string, List <HClusterNode> > join = new Dictionary <string, List <HClusterNode> >();
foreach (var item in groundLevel)
{
string key = item.dirName;
//key = key.Substring(0, key.Length -1);
key = key.Remove(key.Length - 1);
if (join.ContainsKey(key))
{
join[key].Add(item);
}
else
{
List <HClusterNode> aux = new List <HClusterNode>();
aux.Add(item);
join.Add(key, aux);
}
}
groundLevel = new List <HClusterNode>();
foreach (var item in join)
{
HClusterNode aux = JoinNodes(item.Value);
aux.levelDist = aux.levelNum = i;
aux.realDist = i;
aux.dirName = item.Key;
groundLevel.Add(aux);
}
currentV += (int)step;
}
if (groundLevel.Count == 1)
{
root = groundLevel[0];
}
else
{
root = JoinNodes(groundLevel);
root.levelDist = size;
root.realDist = size;
}
currentV = 100;
ClusterOutput outHTree = new ClusterOutput();
outHTree.hNode = root;
return(outHTree);
}
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 = refPoints * 20 * 4;
currentV = 0;
dic = PrepareKeys(structures, false);
//DebugClass.DebugOn();
// input.relClusters = input.reqClusters;
// input.perData = 90;
if (dic.Count > input.relClusters)
{
if (!input.combine)
{
dic = HashEntropyCombine(dic, structures, input.relClusters);
}
else
{
dic = Rpart(dic, structures, false);
}
//dic = FastCombineKeysNew(dic, structures, false);
}
Dictionary <string, int> xx = ReadLeafs();
dic = SelectClusters(xx, dic);
maxV = 3;
currentV = 1;
//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;
//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;
List <string> order = new List <string>(dic.Keys);
order.Sort(delegate(string a, string b)
{
if (dic[b].Count == dic[a].Count)
{
for (int i = 0; i < a.Length; i++)
{
if (a[i] != b[i])
{
if (a[i] == '0')
{
return(-1);
}
else
{
return(1);
}
}
}
}
return(dic[b].Count.CompareTo(dic[a].Count));
});
foreach (var item in order)
{
if (dic[item].Count > 2)
{
List <string> cluster = new List <string>(dic[item].Count);
foreach (var str in dic[item])
{
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);
}
else
{
structuresToDendrogram.Add(structures[dic[item][0]]);
if (alignFile == null)
{
structuresFullPath.Add(dirName + Path.DirectorySeparatorChar + structures[dic[item][0]]);
}
else
{
structuresFullPath.Add(structures[dic[item][0]]);
}
translateToCluster.Add(structures[dic[item][0]], item);
}
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, hier, 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]);
}
}
item.consistency = CalcClusterConsistency(item.setStruct);
}
else
{
throw new Exception("Cannot add structure. Something is wrong");
}
}
outC.hNode.RedoSetStructures();
outC.runParameters = hier.GetVitalParameters();
outC.runParameters += input.GetVitalParameters();
return(outC);
}
ClusterOutput DivideSpaceHamming(List <string> list)
{
ClusterOutput output = new ClusterOutput();
Dictionary <string, int> aux = new Dictionary <string, int>();
ClusterOutput outC = jury.JuryOptWeights(list);
if (outC == null)
{
return(null);
}
List <string> clust1 = new List <string>();
List <string> clust2 = new List <string>();
//consensus.ToConsensusStates(list, jury.GetStructureStates(outC.juryLike[0].Key));
consensus.ToConsensusStates(list, outC.juryLike[0].Key);
foreach (var item in list)
{
aux.Add(item, consensus.distanceOrdered[item]);
}
if (useKMeans)
{
clust1.Add(outC.juryLike[0].Key);
var item = aux.OrderByDescending(j => j.Value);
int dist = item.First().Value;
foreach (var ll in item)
{
if (dist != ll.Value)
{
break;
}
else
{
clust2.Add(ll.Key);
}
}
Dictionary <string, double> dic = new Dictionary <string, double>();
foreach (var it in outC.juryLike)
{
dic.Add(it.Key, it.Value);
}
double min = Double.MaxValue;
string rem = "";
foreach (var it in clust2)
{
if (dic[it] < min)
{
min = dic[it];
rem = it;
}
}
clust1.Add(rem);
kMeans km = new kMeans(dMeasure);
return(km.kMeansRun(kMeansIter, list, clust1));
}
else
{
int i = 0;
foreach (var item in aux.OrderBy(j => j.Value))
{
if (i < list.Count() / 2)
{
clust1.Add(item.Key);
}
else
{
clust2.Add(item.Key);
}
i++;
}
output.clusters = new List <List <string> >();
output.clusters.Add(clust1);
output.clusters.Add(clust2);
}
return(output);
}
