static public Set <Hla> HlaSetInternal(string parameter, Set <Hla> hlaSet, Dictionary <string, Set <Hla> > supertypeMap)
{
Hla hla = HlaFactoryNoConstraints.GetGroundInstance(parameter);
//SpecialFunctions.CheckCondition(hlaSet.Contains(hla), string.Format("Hla value of {0} is unknown", parameter));
return(Set <Hla> .GetInstance(hla));
}
//!!!very similar to other code
public static Dictionary <Pair <NEC, Hla>, bool> ReadTable(HlaFactory hlaFactory, string fileName, bool dedup)
{
Dictionary <Pair <NEC, Hla>, bool> table = new Dictionary <Pair <NEC, Hla>, bool>();
foreach (Dictionary <string, string> row in SpecialFunctions.TabFileTable(fileName, "N\tepitope\tC\thla\tlabel", false))
{
string n = row["N"];
string epitope = row["epitope"];
SpecialFunctions.CheckCondition(Biology.GetInstance().LegalPeptide(epitope), string.Format("Peptide, '{0}', contains illegal char.", epitope));
string c = row["C"];
NEC nec = NEC.GetInstance(n, epitope, c);
Hla hla = hlaFactory.GetGroundInstance(row["hla"]);
string labelString = row["label"];
SpecialFunctions.CheckCondition(labelString == "0" || labelString == "1", "Expect label to be '0' or '1'");
Pair <NEC, Hla> pair = new Pair <NEC, Hla>(nec, hla);
bool labelAsBool = (labelString == "1");
if (dedup && table.ContainsKey(pair))
{
SpecialFunctions.CheckCondition(table[pair] == labelAsBool, "The example " + pair.ToString() + " appears with contradictory labels.");
continue;
}
table.Add(pair, labelAsBool);
}
return(table);
}
public double Predict(List <Dictionary <string, string> > patientTable, NEC nec, bool modelOnly)
{
double predictedPTotal = 0.0;
foreach (Dictionary <string, string> patientRow in patientTable)
{
double product = 1.0;
foreach (KeyValuePair <string, string> columnAndValue in patientRow)
{
Hla hla = HlaFactory.GetGroundInstance(columnAndValue.Key.Substring(0, 1) + columnAndValue.Value);
Debug.Assert(nec.N.Length == SampleNEC.N.Length && nec.E.Length == SampleNEC.E.Length && nec.C.Length == SampleNEC.C.Length); // real assert
string sourceIgnore;
double probability = Predict(nec, hla, modelOnly, out sourceIgnore);
product *= 1.0 - probability;
}
double noiseyOrForThisPatient = 1.0 - product;
predictedPTotal += noiseyOrForThisPatient;
}
double predictedP = predictedPTotal / (double)patientTable.Count;
return(predictedP);
}
//internal EpitopeLearningData[] Split(int cCrossValPart, Random aRandom)
//{
// List<KeyValuePair<MerAndHlaToLength, bool>> shuffleList = new List<KeyValuePair<MerAndHlaToLength, bool>>();
// foreach (KeyValuePair<Pair<string, Hla>, bool> merAndHlaToLengthWithLabel in this)
// {
// shuffleList.Add(merAndHlaToLengthWithLabel);
// int iRandomPos = aRandom.Next(shuffleList.Count);
// shuffleList[shuffleList.Count - 1] = shuffleList[iRandomPos];
// shuffleList[iRandomPos] = merAndHlaToLengthWithLabel;
// }
// EpitopeLearningData[] rgrg = new EpitopeLearningData[cCrossValPart];
// for (int irgrg = 0; irgrg < rgrg.Length; ++irgrg)
// {
// rgrg[irgrg] = new EpitopeLearningData(string.Format("{0}{1}", Name, irgrg));
// }
// for (int iShuffleList = 0; iShuffleList < shuffleList.Count; ++iShuffleList)
// {
// KeyValuePair<MerAndHlaToLength, bool> merAndHlaToLengthWithLabel = shuffleList[iShuffleList];
// int iSet = iShuffleList * cCrossValPart / shuffleList.Count;
// rgrg[iSet].Add(merAndHlaToLengthWithLabel.Key, merAndHlaToLengthWithLabel.Value);
// }
// return rgrg;
//}
public static EpitopeLearningData GetDbWhole(HlaFactory hlaFactory, int eLength, string datasetName, string fileOrResourceName)
{
Set <string> wantedSet = CreateSourceSet(datasetName);
EpitopeLearningData rg = new EpitopeLearningData(datasetName);
//SpecialFunctions.CheckCondition(hlaResolution.Equals(HlaResolution.ABMixed));
foreach (Dictionary <string, string> row in Predictor.TabFileTable(fileOrResourceName, "peptide hla source label", false))
{
string peptide = row["peptide"];
SpecialFunctions.CheckCondition(Biology.GetInstance().LegalPeptide(peptide), string.Format("Peptide, '{0}', contains illegal char.", peptide));
if (peptide.Length != eLength) //!!!const
{
continue;
}
string source = row["source"];
Set <string> providedSet = CreateSourceSet(source);
//Debug.Assert(providedSet.IsSubsetOf(Set<string>.GetInstance(new string[] { "Aplus", "LANL", "IEDB" }))); // real assert
if (providedSet.IntersectionIsEmpty(wantedSet))
{
continue;
}
Hla hla = hlaFactory.GetGroundInstance(row["hla"]);
//HlaToLength hlaToLength = HlaToLength.GetInstance(hla, hlaResolution);
Pair <string, Hla> peptideAndHla = new Pair <string, Hla>(peptide, hla);
//MerAndHlaToLength aMerAndHlaToLength = MerAndHlaToLength.GetInstance(peptide, hlaToLength, kmerDefinition);
string label = row["label"];
SpecialFunctions.CheckCondition(label == "0" || label == "1", string.Format("Warning: Epitope example {0} has unknown label {1} and will be ignored.", peptideAndHla, label));
rg[peptideAndHla] = (label == "1");
}
return(rg);
}