public static void FilterBySequence(string[] rawFiles, string decoyPrefix, double totalPeptideFPR,
double specificPeptideFPR, MascotQueryType type, bool perFileThreshold, bool debug,
HashSet <string> sequences, bool onlyCollectSequences, IIdentificationProvider ip)
{
for (int i = 0; i < rawFiles.Length; i++)
{
FilterBySequence(ip.GetIdentifications(rawFiles[i], type), sequences);
ip.Dispose();
}
}
public static void FdrThresholding(string[] rawFiles, string decoyPrefix, double peptideFdr, double peptidePep,
MascotQueryType type, bool perFileThreshold, bool debug, HashSet <string> sequences,
bool onlyCollectSequences, IProteinSet proteinSet,
HashSet <string> labelModificationSet, IIdentificationProvider ip)
{
CalcFdr(rawFiles, decoyPrefix, type, proteinSet, debug, labelModificationSet, ip);
double pepThreshVal;
double[] pepThreshVals = new double[rawFiles.Length];
if (peptideFdr < 1)
{
for (int i = 0; i < rawFiles.Length; i++)
{
pepThreshVals[i] = FindReverseHitThresholdValue(ip.GetIdentifications(rawFiles[i], type), peptideFdr,
decoyPrefix, proteinSet);
ip.Dispose();
if (peptidePep < 1)
{
pepThreshVals[i] = Math.Min(pepThreshVals[i], peptidePep);
}
}
pepThreshVal = ArrayUtil.Median(pepThreshVals);
if (peptidePep < 1)
{
pepThreshVal = Math.Min(pepThreshVal, peptidePep);
}
}
else
{
for (int i = 0; i < rawFiles.Length; i++)
{
pepThreshVals[i] = peptidePep;
}
pepThreshVal = peptidePep;
}
if (onlyCollectSequences)
{
for (int i = 0; i < rawFiles.Length; i++)
{
CollectSequences(ip.GetIdentifications(rawFiles[i], type),
perFileThreshold ? pepThreshVals[i] : pepThreshVal, sequences);
ip.Dispose();
}
}
else
{
for (int i = 0; i < rawFiles.Length; i++)
{
ApplyReverseHitThreshold(ip.GetIdentifications(rawFiles[i], type),
perFileThreshold ? pepThreshVals[i] : pepThreshVal);
ip.Dispose();
}
}
}
public MascotQuery(int scanNum, string rawFile, MascotQueryType queryType, string[] fixedMods)
{
this.scanNum = scanNum;
this.rawFile = rawFile;
this.queryType = queryType;
this.fixedMods = new ushort[fixedMods.Length];
for (int i = 0; i < fixedMods.Length; i++)
{
this.fixedMods[i] = Tables.modifications[fixedMods[i]].Index;
}
}
private static void LimitPep(string[] rawFiles, MascotQueryType type, IIdentificationProvider ip)
{
for (int i = 0; i < rawFiles.Length; i++)
{
Identifications ident = ip.GetIdentifications(rawFiles[i], type);
int n = ident.Count;
for (int j = 0; j < n; j++)
{
MascotPeptide p = ident.GetPeptidesAt(j)[0];
p.Pep = Math.Min(p.Pep, 1);
}
ident.Write();
ip.Dispose();
}
}
private static void CalcFdr(string[] rawFiles, string decoyPrefix, MascotQueryType type, IProteinSet proteinSet, bool debug,
IIdentificationProvider ip)
{
List <bool> correct = new List <bool>();
List <double> scores = new List <double>();
List <double> seqLen = new List <double>();
for (int i = 0; i < rawFiles.Length; i++)
{
Identifications ident = ip.GetIdentifications(rawFiles[i], type);
int n = ident.Count;
for (int j = 0; j < n; j++)
{
bool c = ident.IsHighestScoringCorrect(j, decoyPrefix, proteinSet);
double s = ident.GetHighestAltScore(j);
double l = Math.Log(ident.GetBestSequence(j).Length);
if (!double.IsNaN(s) && !double.IsInfinity(s))
{
correct.Add(c);
scores.Add(s);
seqLen.Add(l);
}
}
ip.Dispose();
if (correct.Count > 10000000)
{
break;
}
}
if (correct.Count == 0)
{
return;
}
bool write = debug && (type == MascotQueryType.Silac);
BayesianInversion2D bi = new BayesianInversion2D(scores.ToArray(), seqLen.ToArray(), correct.ToArray(), write);
if (write)
{
Write(rawFiles, bi);
}
for (int i = 0; i < rawFiles.Length; i++)
{
SetPep(ip.GetIdentifications(rawFiles[i], type), bi);
ip.Dispose();
}
}
public void Read()
{
if (!File.Exists(filePath))
{
return;
}
using (BinaryReader reader = FileUtil.GetBinaryReader(filePath)) {
int len = reader.ReadInt32();
scanNumbers = new int[len];
peptides = new MascotPeptide[len][];
fixedModifications = new ushort[len][];
for (int i = 0; i < scanNumbers.Length; i++)
{
scanNumbers[i] = reader.ReadInt32();
int l = reader.ReadInt32();
peptides[i] = new MascotPeptide[l];
for (int j = 0; j < peptides[i].Length; j++)
{
peptides[i][j] = new MascotPeptide(reader);
}
l = reader.ReadInt32();
fixedModifications[i] = new ushort[l];
for (int j = 0; j < fixedModifications[i].Length; j++)
{
fixedModifications[i][j] = reader.ReadUInt16();
}
}
byte x = reader.ReadByte();
switch (x)
{
case 0:
type = MascotQueryType.Silac;
break;
case 1:
type = MascotQueryType.Isotope;
break;
case 2:
type = MascotQueryType.Peak;
break;
}
reader.Close();
}
}
public Identifications(MascotQuery[] queries, string filePath, MascotQueryType type)
{
this.filePath = filePath;
this.type = type;
scanNumbers = new int[queries.Length];
peptides = new MascotPeptide[queries.Length][];
fixedModifications = new ushort[queries.Length][];
for (int i = 0; i < scanNumbers.Length; i++)
{
scanNumbers[i] = queries[i].ScanNum;
}
int[] o = ArrayUtil.Order(scanNumbers);
scanNumbers = ArrayUtil.SubArray(scanNumbers, o);
queries = ArrayUtil.SubArray(queries, o);
for (int i = 0; i < queries.Length; i++)
{
peptides[i] = queries[i].GetPeptides();
fixedModifications[i] = queries[i].FixedMods;
double[] scores = new double[peptides[i].Length];
for (int j = 0; j < scores.Length; j++)
{
scores[j] = -peptides[i][j].MascotScore;
}
int[] o1 = ArrayUtil.Order(scores);
peptides[i] = ArrayUtil.SubArray(peptides[i], o1);
}
List <int> valids = new List <int>();
for (int i = 0; i < scanNumbers.Length; i++)
{
if (peptides[i].Length > 0)
{
valids.Add(i);
}
}
int[] oo = valids.ToArray();
scanNumbers = ArrayUtil.SubArray(scanNumbers, oo);
peptides = ArrayUtil.SubArray(peptides, oo);
fixedModifications = ArrayUtil.SubArray(fixedModifications, oo);
}
public MsmsHit(MascotPeptide[] peptides, int scanNumber, int fileIndex, MascotQueryType type,
int silacIndex, double elutionTime, double mz, double monoisotopicMz, ushort[] fixedMods,
HashSet <string> labelModificationSet, SilacType silacType, SilacLabel[] labels1, SilacLabel[] labels2)
{
rawFileIndex = fileIndex;
this.scanNumber = scanNumber;
this.silacIndex = silacIndex;
this.type = type;
pep = peptides[0].Pep;
score = peptides[0].MascotScore;
altScore = peptides[0].AltScore;
charge = (int)Math.Round(peptides[0].Mass / mz);
massErrorPpm = peptides[0].MassErrorPpm;
if (peptides.Length > 1)
{
deltaScoreAll = peptides[0].MascotScore - peptides[1].MascotScore;
}
else
{
deltaScoreAll = peptides[0].MascotScore;
}
int ind = -1;
for (int i = 1; i < peptides.Length; i++)
{
if (!peptides[i].Sequence.Equals(peptides[0].Sequence))
{
ind = i;
break;
}
}
if (ind != -1)
{
deltaScoreDifferentPep = peptides[0].MascotScore - peptides[ind].MascotScore;
}
else
{
deltaScoreDifferentPep = peptides[0].MascotScore;
}
labelModifications =
peptides[0].Modifications.GetLabelModifications(fixedMods, peptides[0].Sequence, labelModificationSet);
trueModifications = peptides[0].Modifications.GetTrueModifications(labelModificationSet);
this.elutionTime = elutionTime;
this.mz = mz;
this.monoisotopicMz = monoisotopicMz;
if (silacType == SilacType.Singlets)
{
this.silacIndex = 0;
}
else if (type != MascotQueryType.Silac)
{
AminoAcid[] allAas = T07SearchEngineEnhancement.CalcAllAas(silacType, labels1, labels2);
char[] allAaLetts = AminoAcid.GetSingleLetters(allAas);
for (int i = 0; i < allAaLetts.Length; i++)
{
this.silacIndex =
CalcSilacIndex(allAaLetts[i], labelModifications, peptides[0].Sequence, silacType, labels1,
labels2);
if (this.silacIndex != -1)
{
break;
}
}
}
}
public MsmsHit(BinaryReader reader)
{
rawFileIndex = reader.ReadInt32();
scanNumber = reader.ReadInt32();
silacIndex = reader.ReadInt32();
byte x = reader.ReadByte();
switch (x)
{
case 0:
type = MascotQueryType.Silac;
break;
case 1:
type = MascotQueryType.Isotope;
break;
case 2:
type = MascotQueryType.Peak;
break;
}
pep = reader.ReadDouble();
score = reader.ReadDouble();
altScore = reader.ReadDouble();
deltaScoreAll = reader.ReadDouble();
deltaScoreDifferentPep = reader.ReadDouble();
labelModifications = PeptideModificationState.Read(reader);
trueModifications = PeptideModificationState.Read(reader);
elutionTime = reader.ReadDouble();
id = reader.ReadInt32();
mz = reader.ReadDouble();
monoisotopicMz = reader.ReadDouble();
evidenceId = reader.ReadInt32();
ptmScore = reader.ReadDouble();
deltaPtmScore = reader.ReadDouble();
ptmScoreCounts = reader.ReadInt32();
ptmScoreFinished = reader.ReadBoolean();
massErrorPpm = reader.ReadDouble();
changed = reader.ReadBoolean();
int len = reader.ReadInt32();
description = new MsmsPeakAnnotation[len];
intensities = new float[len];
massDiffs = new float[len];
for (int i = 0; i < len; i++)
{
description[i] = new MsmsPeakAnnotation(reader);
intensities[i] = reader.ReadSingle();
massDiffs[i] = reader.ReadSingle();
}
charge = reader.ReadInt32();
modProbabilities = new Dictionary <ushort, double[]>();
len = reader.ReadInt32();
ushort[] keys = new ushort[len];
for (int i = 0; i < keys.Length; i++)
{
keys[i] = reader.ReadUInt16();
}
foreach (ushort key in keys)
{
len = reader.ReadInt32();
double[] value = new double[len];
for (int i = 0; i < value.Length; i++)
{
value[i] = reader.ReadDouble();
}
modProbabilities.Add(key, value);
}
modScoreDiffs = new Dictionary <ushort, double[]>();
len = reader.ReadInt32();
keys = new ushort[len];
for (int i = 0; i < keys.Length; i++)
{
keys[i] = reader.ReadUInt16();
}
foreach (ushort key in keys)
{
len = reader.ReadInt32();
double[] value = new double[len];
for (int i = 0; i < value.Length; i++)
{
value[i] = reader.ReadDouble();
}
modScoreDiffs.Add(key, value);
}
}
public static void CalcFdr(string[] rawFiles, string decoyPrefix, MascotQueryType type, IProteinSet proteinSet, bool debug,
HashSet <string> labelModificationSet, IIdentificationProvider ip)
{
CalcFdr(rawFiles, decoyPrefix, type, proteinSet, debug, ip);
}