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 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);
}
public ClusterOutput Run(List <string> structs)
{
maxProgress = 5;
currentProgress = 0;
if (hConcensus)
{
maxProgress++;
consensus = new HammingConsensus(dMeasure.dirName, null, false, input.consensusProfile);
progressObject = consensus;
consensus.InitMeasure();
currentProgress += 1.0 / maxProgress;
}
jury = new jury1D();
progressObject = jury;
currentProgress += 1.0 / maxProgress;
progressObject = null;
jury.PrepareJury(dMeasure.dirName, dMeasure.alignFile, input.jury1DProfileFast);
currentProgress += 1.0 / maxProgress;
ClusterOutput clOut = new ClusterOutput();
root.setStruct = structs;
// if(hConcensus)
// consensus.ToConsensusStates(structs);
FastCluster(root);
maxV = initNodesNum;
while (st.Count > 0 && (leaves.Count + st.Count) < initNodesNum)
{
st.Sort(
delegate(HClusterNode p1, HClusterNode p2)
{
return(p2.setStruct.Count.CompareTo(p1.setStruct.Count));
}
);
HClusterNode node = st[0];
st.RemoveAt(0);
FastCluster(node);
currentV += leaves.Count + st.Count;
}
currentV = maxV;
currentProgress += 1.0 / maxProgress;
while (st.Count > 0)
{
HClusterNode node = st[0];
st.RemoveAt(0);
leaves.Add(node);
}
MakeDendrogs(linkage);
currentProgress += 1.0 / maxProgress;
PrepareList();
root = ConnectDendrogs(linkage);
root.levelDist = root.SearchMaxDist();
root.realDist = dMeasure.GetRealValue(root.levelDist);
//CheckRefDistances();
//dendrogList = RearangeDendrogram(root);
//root = ConnectDendrogs();
clOut.hNode = root;
currentProgress += 1.0 / maxProgress;
return(clOut);
}