public RawFileInfo(string fullFilePathWithExtension, IMsDataFile <IMsDataScan <IMzSpectrum <IMzPeak> > > dataFile)
{
this.fullFilePathWithExtension = fullFilePathWithExtension;
this.filenameWithoutExtension = System.IO.Path.GetFileNameWithoutExtension(this.fullFilePathWithExtension);
this.dataFile = dataFile;
clearAfterDone = false;
}
public RawFileInfo(string fullFilePathWithExtension)
{
this.fullFilePathWithExtension = fullFilePathWithExtension;
this.filenameWithoutExtension = System.IO.Path.GetFileNameWithoutExtension(this.fullFilePathWithExtension);
this.dataFile = null;
clearAfterDone = true;
}
public LocalizationEngine(IEnumerable <PeptideSpectralMatch> allResultingIdentifications, List <ProductType> lp, IMsDataFile <IMsDataScan <IMzSpectrum <IMzPeak> > > myMsDataFile, Tolerance fragmentTolerance, List <string> nestedIds, bool addCompIons) : base(nestedIds)
{
this.allResultingIdentifications = allResultingIdentifications;
this.lp = lp;
this.myMsDataFile = myMsDataFile;
this.fragmentTolerance = fragmentTolerance;
this.addCompIons = addCompIons;
this.dissociationTypes = DetermineDissociationType(lp);
}
public static IEnumerable <Ms2ScanWithSpecificMass> GetMs2Scans(
IMsDataFile <IMsDataScan <IMzSpectrum <IMzPeak> > > myMSDataFile,
string fullFilePath,
bool doPrecursorDeconvolution,
bool useProvidedPrecursorInfo,
double deconvolutionIntensityRatio,
int deconvolutionMaxAssumedChargeState,
Tolerance deconvolutionMassTolerance)
{
foreach (var ms2scan in myMSDataFile.OfType <IMsDataScanWithPrecursor <IMzSpectrum <IMzPeak> > >())
{
List <(double, int)> isolatedStuff = new List <(double, int)>();
if (ms2scan.OneBasedPrecursorScanNumber.HasValue)
{
var precursorSpectrum = myMSDataFile.GetOneBasedScan(ms2scan.OneBasedPrecursorScanNumber.Value);
ms2scan.RefineSelectedMzAndIntensity(precursorSpectrum.MassSpectrum);
if (ms2scan.SelectedIonMonoisotopicGuessMz.HasValue)
{
ms2scan.ComputeMonoisotopicPeakIntensity(precursorSpectrum.MassSpectrum);
}
if (doPrecursorDeconvolution)
{
foreach (var envelope in ms2scan.GetIsolatedMassesAndCharges(precursorSpectrum.MassSpectrum, 1, deconvolutionMaxAssumedChargeState, deconvolutionMassTolerance.Value, deconvolutionIntensityRatio))
{
var monoPeakMz = envelope.monoisotopicMass.ToMz(envelope.charge);
isolatedStuff.Add((monoPeakMz, envelope.charge));
}
}
}
if (useProvidedPrecursorInfo && ms2scan.SelectedIonChargeStateGuess.HasValue)
{
var precursorCharge = ms2scan.SelectedIonChargeStateGuess.Value;
if (ms2scan.SelectedIonMonoisotopicGuessMz.HasValue)
{
var precursorMZ = ms2scan.SelectedIonMonoisotopicGuessMz.Value;
if (!isolatedStuff.Any(b => deconvolutionMassTolerance.Within(precursorMZ.ToMass(precursorCharge), b.Item1.ToMass(b.Item2))))
{
isolatedStuff.Add((precursorMZ, precursorCharge));
}
}
else
{
var precursorMZ = ms2scan.SelectedIonMZ;
if (!isolatedStuff.Any(b => deconvolutionMassTolerance.Within(precursorMZ.ToMass(precursorCharge), b.Item1.ToMass(b.Item2))))
{
isolatedStuff.Add((precursorMZ, precursorCharge));
}
}
}
foreach (var heh in isolatedStuff)
{
yield return(new Ms2ScanWithSpecificMass(ms2scan, heh.Item1, heh.Item2, fullFilePath));
}
}
}
public SummedMsDataFile(IMsDataFile <IMsDataScan <IMzSpectrum <IMzPeak> > > raw, int numScansToAverage, double ppmToleranceForPeakCombination) :
base(raw.NumSpectra - numScansToAverage + 1,
new SourceFile(
@"scan number only nativeID format",
raw.SourceFile.MassSpectrometerFileFormat,
raw.SourceFile.CheckSum,
raw.SourceFile.FileChecksumType,
raw.SourceFile.Uri,
raw.SourceFile.Id,
raw.SourceFile.FileName))
{
this.raw = raw;
this.numScansToAverage = numScansToAverage;
this.ppmToleranceForPeakCombination = ppmToleranceForPeakCombination;
}
public DataPointAcquisitionEngine(
List <PeptideSpectralMatch> goodIdentifications,
IMsDataFile <IMsDataScan <IMzSpectrum <IMzPeak> > > myMsDataFile,
Tolerance mzToleranceForMs1Search,
Tolerance mzToleranceForMs2Search,
int numFragmentsNeededForEveryIdentification,
int minMS1isotopicPeaksNeededForConfirmedIdentification,
int minMS2isotopicPeaksNeededForConfirmedIdentification,
FragmentTypes fragmentTypesForCalibration,
List <string> nestedIds) : base(nestedIds)
{
this.goodIdentifications = goodIdentifications;
this.myMsDataFile = myMsDataFile;
this.mzToleranceForMs1Search = mzToleranceForMs1Search;
this.mzToleranceForMs2Search = mzToleranceForMs2Search;
this.numFragmentsNeededForEveryIdentification = numFragmentsNeededForEveryIdentification;
this.minMS1isotopicPeaksNeededForConfirmedIdentification = minMS1isotopicPeaksNeededForConfirmedIdentification;
this.minMS2isotopicPeaksNeededForConfirmedIdentification = minMS2isotopicPeaksNeededForConfirmedIdentification;
this.fragmentTypesForCalibration = fragmentTypesForCalibration;
}
public void LoadMzmlTest()
{
Mzml a = Mzml.LoadAllStaticData(@"tiny.pwiz.1.1.mzML");
var ya = a.GetOneBasedScan(1).MassSpectrum;
Assert.AreEqual(15, ya.Size);
var ya2 = a.GetOneBasedScan(2).MassSpectrum;
Assert.AreEqual(10, ya2.Size);
var ya3 = a.GetOneBasedScan(3).MassSpectrum;
Assert.AreEqual(0, ya3.Size);
var ya4 = a.GetOneBasedScan(4).MassSpectrum;
Assert.AreEqual(15, ya4.Size);
IMsDataFile <IMsDataScan <IMzSpectrum <IMzPeak> > > ok = a;
Assert.AreEqual(1, ok.GetClosestOneBasedSpectrumNumber(5));
}
public static void CreateAndWriteMyMzmlWithCalibratedSpectra(IMsDataFile <IMsDataScan <IMzSpectrum <IMzPeak> > > myMsDataFile, string outputFile, bool writeIndexed)
{
var mzML = new Generated.mzMLType()
{
version = "1",
cvList = new Generated.CVListType()
};
mzML.cvList.count = "1";
mzML.cvList.cv = new Generated.CVType[1];
mzML.cvList.cv[0] = new Generated.CVType()
{
URI = @"https://raw.githubusercontent.com/HUPO-PSI/psi-ms-CV/master/psi-ms.obo",
fullName = "Proteomics Standards Initiative Mass Spectrometry Ontology",
id = "MS"
};
mzML.fileDescription = new Generated.FileDescriptionType()
{
fileContent = new Generated.ParamGroupType()
};
mzML.fileDescription.fileContent.cvParam = new Generated.CVParamType[2];
mzML.fileDescription.fileContent.cvParam[0] = new Generated.CVParamType()
{
accession = "MS:1000579" // MS1 Data
};
mzML.fileDescription.fileContent.cvParam[1] = new Generated.CVParamType()
{
accession = "MS:1000580" // MSn Data
};
mzML.softwareList = new Generated.SoftwareListType()
{
count = "1",
software = new Generated.SoftwareType[1]
};
// TODO: add the raw file fields
mzML.softwareList.software[0] = new Generated.SoftwareType()
{
id = "mzLib",
version = "1",
cvParam = new Generated.CVParamType[1]
};
mzML.softwareList.software[0].cvParam[0] = new Generated.CVParamType()
{
accession = "MS:1000799",
value = "mzLib"
};
// Leaving empty. Can't figure out the configurations.
// ToDo: read instrumentConfigurationList from mzML file
mzML.instrumentConfigurationList = new Generated.InstrumentConfigurationListType();
mzML.dataProcessingList = new Generated.DataProcessingListType()
{
count = "1",
dataProcessing = new Generated.DataProcessingType[1]
};
// Only writing mine! Might have had some other data processing (but not if it is a raw file)
// ToDo: read dataProcessingList from mzML file
mzML.dataProcessingList.dataProcessing[0] = new Generated.DataProcessingType()
{
id = "mzLibProcessing"
};
mzML.run = new Generated.RunType()
{
chromatogramList = new Generated.ChromatogramListType()
{
count = "1",
chromatogram = new Generated.ChromatogramType[1]
}
};
// ToDo: Finish the chromatogram writing!
mzML.run.chromatogramList.chromatogram[0] = new Generated.ChromatogramType();
mzML.run.spectrumList = new Generated.SpectrumListType()
{
count = (myMsDataFile.NumSpectra).ToString(CultureInfo.InvariantCulture),
defaultDataProcessingRef = "mzLibProcessing",
spectrum = new Generated.SpectrumType[myMsDataFile.NumSpectra]
};
// Loop over all spectra
for (int i = 1; i <= myMsDataFile.NumSpectra; i++)
{
mzML.run.spectrumList.spectrum[i - 1] = new Generated.SpectrumType()
{
defaultArrayLength = myMsDataFile.GetOneBasedScan(i).MassSpectrum.Size,
index = i.ToString(CultureInfo.InvariantCulture),
id = myMsDataFile.GetOneBasedScan(i).OneBasedScanNumber.ToString(),
cvParam = new Generated.CVParamType[8]
};
mzML.run.spectrumList.spectrum[i - 1].cvParam[0] = new Generated.CVParamType();
if (myMsDataFile.GetOneBasedScan(i).MsnOrder == 1)
{
mzML.run.spectrumList.spectrum[i - 1].cvParam[0].accession = "MS:1000579";
}
else if (myMsDataFile.GetOneBasedScan(i) is IMsDataScanWithPrecursor <IMzSpectrum <IMzPeak> > )
{
var scanWithPrecursor = myMsDataFile.GetOneBasedScan(i) as IMsDataScanWithPrecursor <IMzSpectrum <IMzPeak> >;
mzML.run.spectrumList.spectrum[i - 1].cvParam[0].accession = "MS:1000580";
// So needs a precursor!
mzML.run.spectrumList.spectrum[i - 1].precursorList = new Generated.PrecursorListType()
{
count = 1.ToString(),
precursor = new Generated.PrecursorType[1]
};
mzML.run.spectrumList.spectrum[i - 1].precursorList.precursor[0] = new Generated.PrecursorType();
string precursorID = scanWithPrecursor.OneBasedPrecursorScanNumber.ToString();
mzML.run.spectrumList.spectrum[i - 1].precursorList.precursor[0].spectrumRef = precursorID;
mzML.run.spectrumList.spectrum[i - 1].precursorList.precursor[0].selectedIonList = new Generated.SelectedIonListType()
{
count = 1.ToString(),
selectedIon = new Generated.ParamGroupType[1]
};
mzML.run.spectrumList.spectrum[i - 1].precursorList.precursor[0].selectedIonList.selectedIon[0] = new Generated.ParamGroupType()
{
cvParam = new Generated.CVParamType[3]
};
// Selected ion MZ
mzML.run.spectrumList.spectrum[i - 1].precursorList.precursor[0].selectedIonList.selectedIon[0].cvParam[0] = new Generated.CVParamType()
{
name = "selected ion m/z",
value = scanWithPrecursor.SelectedIonMZ.ToString(CultureInfo.InvariantCulture),
accession = "MS:1000744"
};
// Charge State
if (scanWithPrecursor.SelectedIonChargeStateGuess.HasValue)
{
mzML.run.spectrumList.spectrum[i - 1].precursorList.precursor[0].selectedIonList.selectedIon[0].cvParam[1] = new Generated.CVParamType()
{
name = "charge state",
value = scanWithPrecursor.SelectedIonChargeStateGuess.Value.ToString(CultureInfo.InvariantCulture),
accession = "MS:1000041"
};
}
// Selected ion intensity
if (scanWithPrecursor.SelectedIonIntensity.HasValue)
{
mzML.run.spectrumList.spectrum[i - 1].precursorList.precursor[0].selectedIonList.selectedIon[0].cvParam[2] = new Generated.CVParamType()
{
name = "peak intensity",
value = scanWithPrecursor.SelectedIonIntensity.Value.ToString(CultureInfo.InvariantCulture),
accession = "MS:1000042"
};
}
MzRange isolationRange = scanWithPrecursor.IsolationRange;
mzML.run.spectrumList.spectrum[i - 1].precursorList.precursor[0].isolationWindow = new Generated.ParamGroupType()
{
cvParam = new Generated.CVParamType[3]
};
mzML.run.spectrumList.spectrum[i - 1].precursorList.precursor[0].isolationWindow.cvParam[0] = new Generated.CVParamType()
{
accession = "MS:1000827",
name = "isolation window target m/z",
value = isolationRange.Mean.ToString(CultureInfo.InvariantCulture)
};
mzML.run.spectrumList.spectrum[i - 1].precursorList.precursor[0].isolationWindow.cvParam[1] = new Generated.CVParamType()
{
accession = "MS:1000828",
name = "isolation window lower offset",
value = (isolationRange.Width / 2).ToString(CultureInfo.InvariantCulture)
};
mzML.run.spectrumList.spectrum[i - 1].precursorList.precursor[0].isolationWindow.cvParam[2] = new Generated.CVParamType()
{
accession = "MS:1000829",
name = "isolation window upper offset",
value = (isolationRange.Width / 2).ToString(CultureInfo.InvariantCulture)
};
mzML.run.spectrumList.spectrum[i - 1].precursorList.precursor[0].activation = new Generated.ParamGroupType()
{
cvParam = new Generated.CVParamType[1]
};
mzML.run.spectrumList.spectrum[i - 1].precursorList.precursor[0].activation.cvParam[0] = new Generated.CVParamType();
DissociationType dissociationType = scanWithPrecursor.DissociationType;
mzML.run.spectrumList.spectrum[i - 1].precursorList.precursor[0].activation.cvParam[0].accession = DissociationTypeAccessions[dissociationType];
mzML.run.spectrumList.spectrum[i - 1].precursorList.precursor[0].activation.cvParam[0].name = DissociationTypeNames[dissociationType];
}
mzML.run.spectrumList.spectrum[i - 1].cvParam[1] = new Generated.CVParamType()
{
name = "ms level",
accession = "MS:1000511",
value = myMsDataFile.GetOneBasedScan(i).MsnOrder.ToString(CultureInfo.InvariantCulture)
};
mzML.run.spectrumList.spectrum[i - 1].cvParam[2] = new Generated.CVParamType()
{
name = CentroidNames[myMsDataFile.GetOneBasedScan(i).IsCentroid],
accession = CentroidAccessions[myMsDataFile.GetOneBasedScan(i).IsCentroid]
};
if (PolarityNames.TryGetValue(myMsDataFile.GetOneBasedScan(i).Polarity, out string polarityName) && PolarityAccessions.TryGetValue(myMsDataFile.GetOneBasedScan(i).Polarity, out string polarityAccession))
{
mzML.run.spectrumList.spectrum[i - 1].cvParam[3] = new Generated.CVParamType()
{
name = polarityName,
accession = polarityAccession
};
}
// Spectrum title
mzML.run.spectrumList.spectrum[i - 1].cvParam[4] = new Generated.CVParamType()
{
name = "spectrum title",
accession = "MS:1000796",
value = myMsDataFile.GetOneBasedScan(i).OneBasedScanNumber.ToString()
};
if ((myMsDataFile.GetOneBasedScan(i).MassSpectrum.Size) > 0)
{
// Lowest observed mz
mzML.run.spectrumList.spectrum[i - 1].cvParam[5] = new Generated.CVParamType()
{
name = "lowest observed m/z",
accession = "MS:1000528",
value = myMsDataFile.GetOneBasedScan(i).MassSpectrum.FirstX.ToString(CultureInfo.InvariantCulture)
};
// Highest observed mz
mzML.run.spectrumList.spectrum[i - 1].cvParam[6] = new Generated.CVParamType()
{
name = "highest observed m/z",
accession = "MS:1000527",
value = myMsDataFile.GetOneBasedScan(i).MassSpectrum.LastX.ToString(CultureInfo.InvariantCulture)
};
}
// Total ion current
mzML.run.spectrumList.spectrum[i - 1].cvParam[7] = new Generated.CVParamType()
{
name = "total ion current",
accession = "MS:1000285",
value = myMsDataFile.GetOneBasedScan(i).TotalIonCurrent.ToString(CultureInfo.InvariantCulture)
};
// Retention time
mzML.run.spectrumList.spectrum[i - 1].scanList = new Generated.ScanListType()
{
count = "1",
scan = new Generated.ScanType[1]
};
mzML.run.spectrumList.spectrum[i - 1].scanList.scan[0] = new Generated.ScanType()
{
cvParam = new Generated.CVParamType[3]
};
mzML.run.spectrumList.spectrum[i - 1].scanList.scan[0].cvParam[0] = new Generated.CVParamType()
{
name = "scan start time",
accession = "MS:1000016",
value = myMsDataFile.GetOneBasedScan(i).RetentionTime.ToString(CultureInfo.InvariantCulture),
unitCvRef = "UO",
unitAccession = "UO:0000031",
unitName = "minute"
};
mzML.run.spectrumList.spectrum[i - 1].scanList.scan[0].cvParam[1] = new Generated.CVParamType()
{
name = "filter string",
accession = "MS:1000512",
value = myMsDataFile.GetOneBasedScan(i).ScanFilter
};
if (myMsDataFile.GetOneBasedScan(i).InjectionTime.HasValue)
{
mzML.run.spectrumList.spectrum[i - 1].scanList.scan[0].cvParam[2] = new Generated.CVParamType()
{
name = "ion injection time",
accession = "MS:1000927",
value = myMsDataFile.GetOneBasedScan(i).InjectionTime.Value.ToString(CultureInfo.InvariantCulture)
};
}
if (myMsDataFile.GetOneBasedScan(i) is IMsDataScanWithPrecursor <IMzSpectrum <IMzPeak> > )
{
var scanWithPrecursor = myMsDataFile.GetOneBasedScan(i) as IMsDataScanWithPrecursor <IMzSpectrum <IMzPeak> >;
if (scanWithPrecursor.SelectedIonMonoisotopicGuessMz.HasValue)
{
mzML.run.spectrumList.spectrum[i - 1].scanList.scan[0].userParam = new Generated.UserParamType[1];
mzML.run.spectrumList.spectrum[i - 1].scanList.scan[0].userParam[0] = new Generated.UserParamType()
{
name = "[mzLib]Monoisotopic M/Z:",
value = scanWithPrecursor.SelectedIonMonoisotopicGuessMz.Value.ToString(CultureInfo.InvariantCulture)
};
}
}
mzML.run.spectrumList.spectrum[i - 1].scanList.scan[0].scanWindowList = new Generated.ScanWindowListType()
{
count = 1,
scanWindow = new Generated.ParamGroupType[1]
};
mzML.run.spectrumList.spectrum[i - 1].scanList.scan[0].scanWindowList.scanWindow[0] = new Generated.ParamGroupType()
{
cvParam = new Generated.CVParamType[2]
};
mzML.run.spectrumList.spectrum[i - 1].scanList.scan[0].scanWindowList.scanWindow[0].cvParam[0] = new Generated.CVParamType()
{
name = "scan window lower limit",
accession = "MS:1000501",
value = myMsDataFile.GetOneBasedScan(i).ScanWindowRange.Minimum.ToString(CultureInfo.InvariantCulture)
};
mzML.run.spectrumList.spectrum[i - 1].scanList.scan[0].scanWindowList.scanWindow[0].cvParam[1] = new Generated.CVParamType()
{
name = "scan window upper limit",
accession = "MS:1000500",
value = myMsDataFile.GetOneBasedScan(i).ScanWindowRange.Maximum.ToString(CultureInfo.InvariantCulture)
};
mzML.run.spectrumList.spectrum[i - 1].binaryDataArrayList = new Generated.BinaryDataArrayListType()
{
// ONLY WRITING M/Z AND INTENSITY DATA, NOT THE CHARGE! (but can add charge info later)
// CHARGE (and other stuff) CAN BE IMPORTANT IN ML APPLICATIONS!!!!!
count = 2.ToString(),
binaryDataArray = new Generated.BinaryDataArrayType[5]
};
// M/Z Data
mzML.run.spectrumList.spectrum[i - 1].binaryDataArrayList.binaryDataArray[0] = new Generated.BinaryDataArrayType()
{
binary = myMsDataFile.GetOneBasedScan(i).MassSpectrum.Get64BitXarray()
};
mzML.run.spectrumList.spectrum[i - 1].binaryDataArrayList.binaryDataArray[0].encodedLength = (4 * Math.Ceiling(((double)mzML.run.spectrumList.spectrum[i - 1].binaryDataArrayList.binaryDataArray[0].binary.Length / 3))).ToString(CultureInfo.InvariantCulture);
mzML.run.spectrumList.spectrum[i - 1].binaryDataArrayList.binaryDataArray[0].cvParam = new Generated.CVParamType[3];
mzML.run.spectrumList.spectrum[i - 1].binaryDataArrayList.binaryDataArray[0].cvParam[0] = new Generated.CVParamType()
{
accession = "MS:1000514",
name = "m/z array"
};
mzML.run.spectrumList.spectrum[i - 1].binaryDataArrayList.binaryDataArray[0].cvParam[1] = new Generated.CVParamType()
{
accession = "MS:1000523",
name = "64-bit float"
};
mzML.run.spectrumList.spectrum[i - 1].binaryDataArrayList.binaryDataArray[0].cvParam[2] = new Generated.CVParamType()
{
accession = "MS:1000576",
name = "no compression"
};
// Intensity Data
mzML.run.spectrumList.spectrum[i - 1].binaryDataArrayList.binaryDataArray[1] = new Generated.BinaryDataArrayType()
{
binary = myMsDataFile.GetOneBasedScan(i).MassSpectrum.Get64BitYarray()
};
mzML.run.spectrumList.spectrum[i - 1].binaryDataArrayList.binaryDataArray[1].encodedLength = (4 * Math.Ceiling(((double)mzML.run.spectrumList.spectrum[i - 1].binaryDataArrayList.binaryDataArray[1].binary.Length / 3))).ToString(CultureInfo.InvariantCulture);
mzML.run.spectrumList.spectrum[i - 1].binaryDataArrayList.binaryDataArray[1].cvParam = new Generated.CVParamType[3];
mzML.run.spectrumList.spectrum[i - 1].binaryDataArrayList.binaryDataArray[1].cvParam[0] = new Generated.CVParamType()
{
accession = "MS:1000515",
name = "intensity array"
};
mzML.run.spectrumList.spectrum[i - 1].binaryDataArrayList.binaryDataArray[1].cvParam[1] = new Generated.CVParamType()
{
accession = "MS:1000523",
name = "64-bit float"
};
mzML.run.spectrumList.spectrum[i - 1].binaryDataArrayList.binaryDataArray[1].cvParam[2] = new Generated.CVParamType()
{
accession = "MS:1000576",
name = "no compression"
};
if (myMsDataFile.GetOneBasedScan(i).NoiseData != null)
{
// mass
mzML.run.spectrumList.spectrum[i - 1].binaryDataArrayList.binaryDataArray[2] = new Generated.BinaryDataArrayType()
{
binary = myMsDataFile.GetOneBasedScan(i).Get64BitNoiseDataMass()
};
mzML.run.spectrumList.spectrum[i - 1].binaryDataArrayList.binaryDataArray[2].encodedLength = (4 * Math.Ceiling(((double)mzML.run.spectrumList.spectrum[i - 1].binaryDataArrayList.binaryDataArray[2].binary.Length / 3))).ToString(CultureInfo.InvariantCulture);
mzML.run.spectrumList.spectrum[i - 1].binaryDataArrayList.binaryDataArray[2].cvParam = new Generated.CVParamType[3];
mzML.run.spectrumList.spectrum[i - 1].binaryDataArrayList.binaryDataArray[2].cvParam[0] = new Generated.CVParamType()
{
accession = "MS:1000786",
name = "non-standard data array"
};
mzML.run.spectrumList.spectrum[i - 1].binaryDataArrayList.binaryDataArray[2].cvParam[1] = new Generated.CVParamType()
{
accession = "MS:1000523",
name = "64-bit float"
};
mzML.run.spectrumList.spectrum[i - 1].binaryDataArrayList.binaryDataArray[2].cvParam[2] = new Generated.CVParamType()
{
accession = "MS:1000576",
name = "no compression"
};
mzML.run.spectrumList.spectrum[i - 1].binaryDataArrayList.binaryDataArray[2].userParam = new Generated.UserParamType[1];
mzML.run.spectrumList.spectrum[i - 1].binaryDataArrayList.binaryDataArray[2].userParam[0] = new Generated.UserParamType()
{
name = "kelleherCustomType",
value = "noise m/z"
};
// noise
mzML.run.spectrumList.spectrum[i - 1].binaryDataArrayList.binaryDataArray[3] = new Generated.BinaryDataArrayType()
{
binary = myMsDataFile.GetOneBasedScan(i).Get64BitNoiseDataNoise()
};
mzML.run.spectrumList.spectrum[i - 1].binaryDataArrayList.binaryDataArray[3].encodedLength = (4 * Math.Ceiling(((double)mzML.run.spectrumList.spectrum[i - 1].binaryDataArrayList.binaryDataArray[3].binary.Length / 3))).ToString(CultureInfo.InvariantCulture);
mzML.run.spectrumList.spectrum[i - 1].binaryDataArrayList.binaryDataArray[3].cvParam = new Generated.CVParamType[3];
mzML.run.spectrumList.spectrum[i - 1].binaryDataArrayList.binaryDataArray[3].cvParam[0] = new Generated.CVParamType()
{
accession = "MS:1000786",
name = "non-standard data array"
};
mzML.run.spectrumList.spectrum[i - 1].binaryDataArrayList.binaryDataArray[3].cvParam[1] = new Generated.CVParamType()
{
accession = "MS:1000523",
name = "64-bit float"
};
mzML.run.spectrumList.spectrum[i - 1].binaryDataArrayList.binaryDataArray[3].cvParam[2] = new Generated.CVParamType()
{
accession = "MS:1000576",
name = "no compression"
};
mzML.run.spectrumList.spectrum[i - 1].binaryDataArrayList.binaryDataArray[3].userParam = new Generated.UserParamType[1];
mzML.run.spectrumList.spectrum[i - 1].binaryDataArrayList.binaryDataArray[3].userParam[0] = new Generated.UserParamType()
{
name = "kelleherCustomType",
value = "noise baseline"
};
// baseline
mzML.run.spectrumList.spectrum[i - 1].binaryDataArrayList.binaryDataArray[4] = new Generated.BinaryDataArrayType()
{
binary = myMsDataFile.GetOneBasedScan(i).Get64BitNoiseDataBaseline()
};
mzML.run.spectrumList.spectrum[i - 1].binaryDataArrayList.binaryDataArray[4].encodedLength = (4 * Math.Ceiling(((double)mzML.run.spectrumList.spectrum[i - 1].binaryDataArrayList.binaryDataArray[4].binary.Length / 3))).ToString(CultureInfo.InvariantCulture);
mzML.run.spectrumList.spectrum[i - 1].binaryDataArrayList.binaryDataArray[4].cvParam = new Generated.CVParamType[3];
mzML.run.spectrumList.spectrum[i - 1].binaryDataArrayList.binaryDataArray[4].cvParam[0] = new Generated.CVParamType()
{
accession = "MS:1000786",
name = "non-standard data array"
};
mzML.run.spectrumList.spectrum[i - 1].binaryDataArrayList.binaryDataArray[4].cvParam[1] = new Generated.CVParamType()
{
accession = "MS:1000523",
name = "64-bit float"
};
mzML.run.spectrumList.spectrum[i - 1].binaryDataArrayList.binaryDataArray[4].cvParam[2] = new Generated.CVParamType()
{
accession = "MS:1000576",
name = "no compression"
};
mzML.run.spectrumList.spectrum[i - 1].binaryDataArrayList.binaryDataArray[4].userParam = new Generated.UserParamType[1];
mzML.run.spectrumList.spectrum[i - 1].binaryDataArrayList.binaryDataArray[4].userParam[0] = new Generated.UserParamType()
{
name = "kelleherCustomType",
value = "noise intensity"
};
}
}
if (writeIndexed)
{
throw new NotImplementedException("Writing indexed mzMLs not yet supported");
}
else
{
using (TextWriter writer = new StreamWriter(outputFile))
{
mzmlSerializer.Serialize(writer, mzML);
}
}
}
protected override MyTaskResults RunSpecific(string OutputFolder, List <DbForTask> dbFilenameList, List <string> currentRawFileList, string taskId, FileSpecificSettings[] fileSettingsList)
{
myTaskResults = new MyTaskResults(this);
List <PsmCross> allPsms = new List <PsmCross>();
var compactPeptideToProteinPeptideMatch = new Dictionary <CompactPeptideBase, HashSet <PeptideWithSetModifications> >();
Status("Loading modifications...", taskId);
#region Load modifications
List <ModificationWithMass> variableModifications = GlobalVariables.AllModsKnown.OfType <ModificationWithMass>().Where(b => CommonParameters.ListOfModsVariable.Contains((b.modificationType, b.id))).ToList();
List <ModificationWithMass> fixedModifications = GlobalVariables.AllModsKnown.OfType <ModificationWithMass>().Where(b => CommonParameters.ListOfModsFixed.Contains((b.modificationType, b.id))).ToList();
List <string> localizeableModificationTypes = CommonParameters.LocalizeAll ? GlobalVariables.AllModTypesKnown.ToList() : CommonParameters.ListOfModTypesLocalize.ToList();
#endregion Load modifications
Status("Loading proteins...", new List <string> {
taskId
});
var proteinList = dbFilenameList.SelectMany(b => LoadProteinDb(b.FilePath, true, XlSearchParameters.DecoyType, localizeableModificationTypes, b.IsContaminant, out Dictionary <string, Modification> unknownModifications)).ToList();
List <ProductType> ionTypes = new List <ProductType>();
if (CommonParameters.BIons)
{
ionTypes.Add(ProductType.BnoB1ions);
}
if (CommonParameters.YIons)
{
ionTypes.Add(ProductType.Y);
}
if (CommonParameters.ZdotIons)
{
ionTypes.Add(ProductType.Zdot);
}
if (CommonParameters.CIons)
{
ionTypes.Add(ProductType.C);
}
TerminusType terminusType = ProductTypeMethod.IdentifyTerminusType(ionTypes);
var crosslinker = new CrosslinkerTypeClass();
crosslinker.SelectCrosslinker(XlSearchParameters.CrosslinkerType);
if (XlSearchParameters.CrosslinkerType == CrosslinkerType.UserDefined)
{
crosslinker.CrosslinkerName = XlSearchParameters.UdXLkerName;
crosslinker.Cleavable = XlSearchParameters.UdXLkerCleavable;
crosslinker.TotalMass = XlSearchParameters.UdXLkerTotalMass.HasValue ? (double)XlSearchParameters.UdXLkerTotalMass : 9999;
crosslinker.CleaveMassShort = XlSearchParameters.UdXLkerShortMass.HasValue ? (double)XlSearchParameters.UdXLkerShortMass : 9999;
crosslinker.CleaveMassLong = XlSearchParameters.UdXLkerShortMass.HasValue ? (double)XlSearchParameters.UdXLkerLongMass : 9999;
crosslinker.CrosslinkerModSite = XlSearchParameters.UdXLkerResidue;
crosslinker.LoopMass = XlSearchParameters.UdXLkerLoopMass.HasValue ? (double)XlSearchParameters.UdXLkerLoopMass : 9999;
crosslinker.DeadendMassH2O = XlSearchParameters.UdXLkerDeadendMassH2O.HasValue ? (double)XlSearchParameters.UdXLkerDeadendMassH2O : 9999;
crosslinker.DeadendMassNH2 = XlSearchParameters.UdXLkerDeadendMassNH2.HasValue ? (double)XlSearchParameters.UdXLkerDeadendMassNH2 : 9999;
crosslinker.DeadendMassTris = XlSearchParameters.UdXLkerDeadendMassTris.HasValue ? (double)XlSearchParameters.UdXLkerDeadendMassTris : 9999;
}
ParallelOptions parallelOptions = new ParallelOptions();
if (CommonParameters.MaxParallelFilesToAnalyze.HasValue)
{
parallelOptions.MaxDegreeOfParallelism = CommonParameters.MaxParallelFilesToAnalyze.Value;
}
MyFileManager myFileManager = new MyFileManager(XlSearchParameters.DisposeOfFileWhenDone);
HashSet <IDigestionParams> ListOfDigestionParams = GetListOfDistinctDigestionParams(CommonParameters, fileSettingsList.Select(b => SetAllFileSpecificCommonParams(CommonParameters, b)));
int completedFiles = 0;
object indexLock = new object();
object psmLock = new object();
Status("Searching files...", taskId);
#region proseCreatedWhileRunning
proseCreatedWhileRunning.Append("The following crosslink discovery were used: ");
proseCreatedWhileRunning.Append("crosslinker name = " + crosslinker.CrosslinkerName + "; ");
proseCreatedWhileRunning.Append("crosslinker type = " + crosslinker.Cleavable + "; ");
proseCreatedWhileRunning.Append("crosslinker mass = " + crosslinker.TotalMass + "; ");
proseCreatedWhileRunning.Append("crosslinker modification site(s) = " + crosslinker.CrosslinkerModSite + "; ");
proseCreatedWhileRunning.Append("protease = " + CommonParameters.DigestionParams.Protease + "; ");
proseCreatedWhileRunning.Append("maximum missed cleavages = " + CommonParameters.DigestionParams.MaxMissedCleavages + "; ");
proseCreatedWhileRunning.Append("minimum peptide length = " + CommonParameters.DigestionParams.MinPeptideLength + "; ");
if (CommonParameters.DigestionParams.MaxPeptideLength == null)
{
proseCreatedWhileRunning.Append("maximum peptide length = unspecified; ");
}
else
{
proseCreatedWhileRunning.Append("maximum peptide length = " + CommonParameters.DigestionParams.MaxPeptideLength + "; ");
}
proseCreatedWhileRunning.Append("initiator methionine behavior = " + CommonParameters.DigestionParams.InitiatorMethionineBehavior + "; ");
proseCreatedWhileRunning.Append("max modification isoforms = " + CommonParameters.DigestionParams.MaxModificationIsoforms + "; ");
proseCreatedWhileRunning.Append("fixed modifications = " + string.Join(", ", fixedModifications.Select(m => m.id)) + "; ");
proseCreatedWhileRunning.Append("variable modifications = " + string.Join(", ", variableModifications.Select(m => m.id)) + "; ");
proseCreatedWhileRunning.Append("parent mass tolerance(s) = " + XlSearchParameters.XlPrecusorMsTl + "; ");
proseCreatedWhileRunning.Append("product mass tolerance = " + CommonParameters.ProductMassTolerance + "; ");
proseCreatedWhileRunning.Append("The combined search database contained " + proteinList.Count + " total entries including " + proteinList.Where(p => p.IsContaminant).Count() + " contaminant sequences. ");
#endregion proseCreatedWhileRunning
Parallel.For(0, currentRawFileList.Count, parallelOptions, spectraFileIndex =>
{
var origDataFile = currentRawFileList[spectraFileIndex];
ICommonParameters combinedParams = SetAllFileSpecificCommonParams(CommonParameters, fileSettingsList[spectraFileIndex]);
List <PsmCross> newPsms = new List <PsmCross>();
var thisId = new List <string> {
taskId, "Individual Spectra Files", origDataFile
};
NewCollection(Path.GetFileName(origDataFile), thisId);
Status("Loading spectra file...", thisId);
IMsDataFile <IMsDataScan <IMzSpectrum <IMzPeak> > > myMsDataFile = myFileManager.LoadFile(origDataFile, combinedParams.TopNpeaks, combinedParams.MinRatio, combinedParams.TrimMs1Peaks, combinedParams.TrimMsMsPeaks);
Status("Getting ms2 scans...", thisId);
Ms2ScanWithSpecificMass[] arrayOfMs2ScansSortedByMass = GetMs2Scans(myMsDataFile, origDataFile, combinedParams.DoPrecursorDeconvolution, combinedParams.UseProvidedPrecursorInfo, combinedParams.DeconvolutionIntensityRatio, combinedParams.DeconvolutionMaxAssumedChargeState, combinedParams.DeconvolutionMassTolerance).OrderBy(b => b.PrecursorMass).ToArray();
//List<Ms2ScanWithSpecificMass> arrayOfMs2ScansSortedByMass = new List<Ms2ScanWithSpecificMass>();
//arrayOfMs2ScansSortedByMass = GetMs2Scans(myMsDataFile, origDataFile, combinedParams.DoPrecursorDeconvolution, combinedParams.UseProvidedPrecursorInfo, combinedParams.DeconvolutionIntensityRatio, combinedParams.DeconvolutionMaxAssumedChargeState, combinedParams.DeconvolutionMassTolerance).OrderBy(b => b.PrecursorMass).ToList();
//Code to resolve MS3 data
//if (XlSearchParameters.FragmentationType == FragmentaionType.MS2_HCD || XlSearchParameters.FragmentationType == FragmentaionType.MS2_EthCD)
//{
// arrayOfMs2ScansSortedByMass = GetMs2Scans(myMsDataFile, origDataFile, combinedParams.DoPrecursorDeconvolution, combinedParams.UseProvidedPrecursorInfo, combinedParams.DeconvolutionIntensityRatio, combinedParams.DeconvolutionMaxAssumedChargeState, combinedParams.DeconvolutionMassTolerance).OrderBy(b => b.PrecursorMass).ToList();
//}
//else
//{
// arrayOfMs2ScansSortedByMass = GetCombinedMs2Scans(myMsDataFile, origDataFile, combinedParams.DoPrecursorDeconvolution, combinedParams.UseProvidedPrecursorInfo, combinedParams.DeconvolutionIntensityRatio, combinedParams.DeconvolutionMaxAssumedChargeState, combinedParams.DeconvolutionMassTolerance).OrderBy(b => b.PrecursorMass).ToList();
//}
for (int currentPartition = 0; currentPartition < CommonParameters.TotalPartitions; currentPartition++)
{
List <CompactPeptide> peptideIndex = null;
List <Protein> proteinListSubset = proteinList.GetRange(currentPartition * proteinList.Count() / combinedParams.TotalPartitions, ((currentPartition + 1) * proteinList.Count() / combinedParams.TotalPartitions) - (currentPartition * proteinList.Count() / combinedParams.TotalPartitions));
#region Generate indices for modern search
Status("Getting fragment dictionary...", new List <string> {
taskId
});
var indexEngine = new IndexingEngine(proteinListSubset, variableModifications, fixedModifications, ionTypes, currentPartition, UsefulProteomicsDatabases.DecoyType.Reverse, ListOfDigestionParams, combinedParams, 30000.0, new List <string> {
taskId
});
List <int>[] fragmentIndex = null;
lock (indexLock)
GenerateIndexes(indexEngine, dbFilenameList, ref peptideIndex, ref fragmentIndex, taskId);
#endregion Generate indices for modern search
Status("Searching files...", taskId);
new TwoPassCrosslinkSearchEngine(newPsms, arrayOfMs2ScansSortedByMass, peptideIndex, fragmentIndex, ionTypes, currentPartition, combinedParams, false, XlSearchParameters.XlPrecusorMsTl, crosslinker, XlSearchParameters.CrosslinkSearchTop, XlSearchParameters.CrosslinkSearchTopNum, XlSearchParameters.XlQuench_H2O, XlSearchParameters.XlQuench_NH2, XlSearchParameters.XlQuench_Tris, XlSearchParameters.XlCharge_2_3, XlSearchParameters.XlCharge_2_3_PrimeFragment, thisId).Run();
ReportProgress(new ProgressEventArgs(100, "Done with search " + (currentPartition + 1) + "/" + CommonParameters.TotalPartitions + "!", thisId));
}
lock (psmLock)
{
allPsms.AddRange(newPsms);
}
completedFiles++;
ReportProgress(new ProgressEventArgs(completedFiles / currentRawFileList.Count, "Searching...", new List <string> {
taskId, "Individual Spectra Files"
}));
});
ReportProgress(new ProgressEventArgs(100, "Done with all searches!", new List <string> {
taskId, "Individual Spectra Files"
}));
Status("Crosslink analysis engine", taskId);
MetaMorpheusEngineResults allcrosslinkanalysisResults;
allcrosslinkanalysisResults = new CrosslinkAnalysisEngine(allPsms, compactPeptideToProteinPeptideMatch, proteinList, variableModifications, fixedModifications, ionTypes, OutputFolder, crosslinker, terminusType, CommonParameters, new List <string> {
taskId
}).Run();
allPsms = allPsms.Where(p => p != null).ToList();
if (XlSearchParameters.XlOutAll)
{
try
{
WriteAllToTsv(allPsms, OutputFolder, "allPsms", new List <string> {
taskId
});
}
catch (Exception)
{
throw;
}
}
var allPsmsXL = allPsms.Where(p => p.CrossType == PsmCrossType.Cross).Where(p => p.XLBestScore >= CommonParameters.ScoreCutoff && p.BetaPsmCross.XLBestScore >= CommonParameters.ScoreCutoff).ToList();
foreach (var item in allPsmsXL)
{
if (item.OneBasedStartResidueInProtein.HasValue)
{
item.XlProteinPos = item.OneBasedStartResidueInProtein.Value + item.XlPos - 1;
}
if (item.BetaPsmCross.OneBasedStartResidueInProtein.HasValue)
{
item.BetaPsmCross.XlProteinPos = item.BetaPsmCross.OneBasedStartResidueInProtein.Value + item.BetaPsmCross.XlPos - 1;
}
}
#region Inter Crosslink
//Write Inter Psms FDR
var interPsmsXL = allPsmsXL.Where(p => !p.CompactPeptides.First().Value.Item2.Select(b => b.Protein.Accession).First().Contains(p.BetaPsmCross.CompactPeptides.First().Value.Item2.Select(b => b.Protein.Accession).First()) &&
!p.BetaPsmCross.CompactPeptides.First().Value.Item2.Select(b => b.Protein.Accession).First().Contains(p.CompactPeptides.First().Value.Item2.Select(b => b.Protein.Accession).First())).OrderByDescending(p => p.XLQvalueTotalScore).ToList();
foreach (var item in interPsmsXL)
{
item.CrossType = PsmCrossType.Inter;
}
var interPsmsXLFDR = CrosslinkDoFalseDiscoveryRateAnalysis(interPsmsXL).ToList();
//var interPsmsXLFDR = CrosslinkFDRAnalysis(interPsmsXL).ToList();
if (XlSearchParameters.XlOutCrosslink)
{
WriteCrosslinkToTsv(interPsmsXLFDR, OutputFolder, "xl_inter_fdr", new List <string> {
taskId
});
}
if (XlSearchParameters.XlOutPercolator)
{
try
{
var interPsmsXLPercolator = interPsmsXL.Where(p => p.XLBestScore >= 2 && p.BetaPsmCross.XLBestScore >= 2).OrderBy(p => p.ScanNumber).ToList();
WriteCrosslinkToTxtForPercolator(interPsmsXLPercolator, OutputFolder, "xl_inter_perc", crosslinker, new List <string> {
taskId
});
}
catch (Exception)
{
throw;
}
}
#endregion Inter Crosslink
#region Intra Cross-link
//Write Intra Psms FDR
var intraPsmsXL = allPsmsXL.Where(p => p.CompactPeptides.First().Value.Item2.Select(b => b.Protein.Accession).First() == p.BetaPsmCross.CompactPeptides.First().Value.Item2.Select(b => b.Protein.Accession).First() ||
p.CompactPeptides.First().Value.Item2.Select(b => b.Protein.Accession).First().Contains(p.BetaPsmCross.CompactPeptides.First().Value.Item2.Select(b => b.Protein.Accession).First()) ||
p.BetaPsmCross.CompactPeptides.First().Value.Item2.Select(b => b.Protein.Accession).First().Contains(p.CompactPeptides.First().Value.Item2.Select(b => b.Protein.Accession).First())).OrderByDescending(p => p.XLQvalueTotalScore).ToList();
foreach (var item in intraPsmsXL)
{
item.CrossType = PsmCrossType.Intra;
}
var intraPsmsXLFDR = CrosslinkDoFalseDiscoveryRateAnalysis(intraPsmsXL).ToList();
//var intraPsmsXLFDR = CrosslinkFDRAnalysis(intraPsmsXL).ToList();
if (XlSearchParameters.XlOutCrosslink)
{
WriteCrosslinkToTsv(intraPsmsXLFDR, OutputFolder, "xl_intra_fdr", new List <string> {
taskId
});
}
if (XlSearchParameters.XlOutPercolator)
{
try
{
var intraPsmsXLPercolator = intraPsmsXL.Where(p => p.XLBestScore >= 2 && p.BetaPsmCross.XLBestScore >= 2).OrderBy(p => p.ScanNumber).ToList();
WriteCrosslinkToTxtForPercolator(intraPsmsXLPercolator, OutputFolder, "xl_intra_perc", crosslinker, new List <string> {
taskId
});
}
catch (Exception)
{
throw;
}
}
#endregion Intra Cross-link
#region Single peptide
var singlePsms = allPsms.Where(p => p.CrossType == PsmCrossType.Singe && !p.FullSequence.Contains("Crosslink")).OrderByDescending(p => p.Score).ToList();
var singlePsmsFDR = SingleFDRAnalysis(singlePsms).ToList();
if (XlSearchParameters.XlOutAll)
{
WriteSingleToTsv(singlePsmsFDR, OutputFolder, "single_fdr", new List <string> {
taskId
});
}
#endregion Single peptide
#region Loop peptide
var loopPsms = allPsms.Where(p => p.CrossType == PsmCrossType.Loop).OrderByDescending(p => p.XLTotalScore).ToList();
var loopPsmsFDR = SingleFDRAnalysis(loopPsms).ToList();
if (XlSearchParameters.XlOutAll)
{
WriteSingleToTsv(loopPsmsFDR, OutputFolder, "loop_fdr", new List <string> {
taskId
});
}
#endregion Loop peptide
#region deadend peptide
var deadendPsms = allPsms.Where(p => p.CrossType == PsmCrossType.DeadEnd || p.CrossType == PsmCrossType.DeadEndH2O || p.CrossType == PsmCrossType.DeadEndNH2 || p.CrossType == PsmCrossType.DeadEndTris).OrderByDescending(p => p.XLTotalScore).ToList();
deadendPsms.AddRange(allPsms.Where(p => p.CrossType == PsmCrossType.Singe && p.FullSequence.Contains("Crosslink")).ToList());
var deadendPsmsFDR = SingleFDRAnalysis(deadendPsms).ToList();
if (XlSearchParameters.XlOutAll)
{
WriteSingleToTsv(deadendPsmsFDR, OutputFolder, "deadend_fdr", new List <string> {
taskId
});
}
#endregion deadend peptide
if (XlSearchParameters.XlOutPepXML)
{
List <PsmCross> allPsmsFDR = new List <PsmCross>();
allPsmsFDR.AddRange(intraPsmsXLFDR.Where(p => p.IsDecoy != true && p.BetaPsmCross.IsDecoy != true && p.FdrInfo.QValue <= 0.05).ToList());
allPsmsFDR.AddRange(interPsmsXLFDR.Where(p => p.IsDecoy != true && p.BetaPsmCross.IsDecoy != true && p.FdrInfo.QValue <= 0.05).ToList());
allPsmsFDR.AddRange(singlePsmsFDR.Where(p => p.IsDecoy != true && p.FdrInfo.QValue <= 0.05).ToList());
allPsmsFDR.AddRange(loopPsmsFDR.Where(p => p.IsDecoy != true && p.FdrInfo.QValue <= 0.05).ToList());
allPsmsFDR.AddRange(deadendPsmsFDR.Where(p => p.IsDecoy != true && p.FdrInfo.QValue <= 0.05).ToList());
allPsmsFDR = allPsmsFDR.OrderBy(p => p.ScanNumber).ToList();
foreach (var fullFilePath in currentRawFileList)
{
string fileNameNoExtension = Path.GetFileNameWithoutExtension(fullFilePath);
WritePepXML_xl(allPsmsFDR.Where(p => p.FullFilePath == fullFilePath).ToList(), dbFilenameList, variableModifications, fixedModifications, localizeableModificationTypes, OutputFolder, fileNameNoExtension, new List <string> {
taskId
});
}
}
if (XlSearchParameters.XlOutAll)
{
List <PsmCross> allPsmsXLFDR = new List <PsmCross>();
allPsmsXLFDR.AddRange(intraPsmsXLFDR.Where(p => p.IsDecoy != true && p.BetaPsmCross.IsDecoy != true && p.FdrInfo.QValue <= 0.05).ToList());
allPsmsXLFDR.AddRange(interPsmsXLFDR.Where(p => p.IsDecoy != true && p.BetaPsmCross.IsDecoy != true && p.FdrInfo.QValue <= 0.05).ToList());
try
{
allPsmsXLFDR = allPsmsXLFDR.OrderByDescending(p => p.XLQvalueTotalScore).ToList();
var allPsmsXLFDRGroup = FindCrosslinks(allPsmsXLFDR);
WriteCrosslinkToTsv(allPsmsXLFDRGroup, OutputFolder, "allPsmsXLFDRGroup", new List <string> {
taskId
});
}
catch (Exception)
{
throw;
}
}
return(myTaskResults);
}
private void LoadData(string path, FileType fileType)
{
if (fileType == FileType.DeconvolutionTSV)
{
System.IO.StreamReader reader = new System.IO.StreamReader(path);
string line;
int lineNum = 1;
while (reader.Peek() > 0)
{
line = reader.ReadLine();
List <IsotopicEnvelope> envs = new List <IsotopicEnvelope>();
if (lineNum != 1)
{
var parsedLine = line.Split('\t');
var mass = double.Parse(parsedLine[0]);
var apexRt = double.Parse(parsedLine[10]);
var envelopes = parsedLine[17].Split(new string[] { "[", "]" }, StringSplitOptions.RemoveEmptyEntries);
foreach (var envelope in envelopes)
{
var split = envelope.Split(new string[] { "|", "(", ")" }, StringSplitOptions.RemoveEmptyEntries);
int charge = int.Parse(split[0]);
double rt = double.Parse(split[1]);
int scan = int.Parse(split[2]);
List <MassSpectralPeak> peaks = new List <MassSpectralPeak>();
for (int i = 3; i < split.Length; i++)
{
string[] sp = split[i].Split(new string[] { "," }, StringSplitOptions.RemoveEmptyEntries);
MassSpectralPeak peak = new MassSpectralPeak(double.Parse(sp[0]), double.Parse(sp[1]));
peaks.Add(peak);
}
IsotopicEnvelope env = new IsotopicEnvelope(rt, charge, peaks);
envs.Add(env);
}
var gsdf = envs.GroupBy(p => p.charge).Where(v => v.Count() > 1);
if (gsdf.Any())
{
var deconvolutedFeature = new ChromatographicPeak(envs, mass, apexRt);
if (deconvolutedFeature.GetSignalToBaseline() > 2.0)
{
DeconvolutedFeatures.Add(deconvolutedFeature);
}
}
}
lineNum++;
}
reader.Close();
}
else if (fileType == FileType.MetaMorpheusPsmTsv)
{
System.IO.StreamReader reader = new System.IO.StreamReader(path);
string line;
int lineNum = 1;
while (reader.Peek() > 0)
{
line = reader.ReadLine();
List <IsotopicEnvelope> envs = new List <IsotopicEnvelope>();
if (lineNum != 1)
{
var parsedLine = line.Split('\t');
}
}
}
else if (fileType == FileType.RawFile)
{
string ext = System.IO.Path.GetExtension(path).ToUpperInvariant();
if (ext.Equals(".RAW"))
{
rawFile = ThermoStaticData.LoadAllStaticData(path);
}
if (ext.Equals(".MZML"))
{
rawFile = Mzml.LoadAllStaticData(path);
}
else
{
throw new Exception("Cannot read file format: " + ext);
}
}
else
{
throw new Exception("Cannot read file " + path);
}
}
private (List <PeptideSpectralMatch>, DataPointAquisitionResults) GetDataAcquisitionResults(IMsDataFile <IMsDataScan <IMzSpectrum <IMzPeak> > > myMsDataFile, string currentDataFile, List <ModificationWithMass> variableModifications, List <ModificationWithMass> fixedModifications, List <Protein> proteinList, string taskId, ICommonParameters combinedParameters, Tolerance initPrecTol, Tolerance initProdTol)
{
var fileNameWithoutExtension = Path.GetFileNameWithoutExtension(currentDataFile);
MassDiffAcceptor searchMode;
if (initPrecTol is PpmTolerance)
{
searchMode = new SinglePpmAroundZeroSearchMode(initPrecTol.Value);
}
else
{
searchMode = new SingleAbsoluteAroundZeroSearchMode(initPrecTol.Value);
}
FragmentTypes fragmentTypesForCalibration = FragmentTypes.None;
if (combinedParameters.BIons)
{
fragmentTypesForCalibration = fragmentTypesForCalibration | FragmentTypes.b;
}
if (combinedParameters.YIons)
{
fragmentTypesForCalibration = fragmentTypesForCalibration | FragmentTypes.y;
}
if (combinedParameters.CIons)
{
fragmentTypesForCalibration = fragmentTypesForCalibration | FragmentTypes.c;
}
if (combinedParameters.ZdotIons)
{
fragmentTypesForCalibration = fragmentTypesForCalibration | FragmentTypes.zdot;
}
var listOfSortedms2Scans = GetMs2Scans(myMsDataFile, currentDataFile, combinedParameters.DoPrecursorDeconvolution, combinedParameters.UseProvidedPrecursorInfo, combinedParameters.DeconvolutionIntensityRatio, combinedParameters.DeconvolutionMaxAssumedChargeState, combinedParameters.DeconvolutionMassTolerance).OrderBy(b => b.PrecursorMass).ToArray();
PeptideSpectralMatch[] allPsmsArray = new PeptideSpectralMatch[listOfSortedms2Scans.Length];
List <ProductType> lp = new List <ProductType>();
if (combinedParameters.BIons)
{
lp.Add(ProductType.B);
}
if (combinedParameters.YIons)
{
lp.Add(ProductType.Y);
}
if (combinedParameters.CIons)
{
lp.Add(ProductType.C);
}
if (combinedParameters.ZdotIons)
{
lp.Add(ProductType.Zdot);
}
Log("Searching with searchMode: " + searchMode, new List <string> {
taskId, "Individual Spectra Files", fileNameWithoutExtension
});
Log("Searching with productMassTolerance: " + initProdTol, new List <string> {
taskId, "Individual Spectra Files", fileNameWithoutExtension
});
new ClassicSearchEngine(allPsmsArray, listOfSortedms2Scans, variableModifications, fixedModifications, proteinList, lp, searchMode, false, combinedParameters, initProdTol, new List <string> {
taskId, "Individual Spectra Files", fileNameWithoutExtension
}).Run();
List <PeptideSpectralMatch> allPsms = allPsmsArray.ToList();
Dictionary <CompactPeptideBase, HashSet <PeptideWithSetModifications> > compactPeptideToProteinPeptideMatching = ((SequencesToActualProteinPeptidesEngineResults) new SequencesToActualProteinPeptidesEngine(allPsms, proteinList, fixedModifications, variableModifications, lp, new List <IDigestionParams> {
combinedParameters.DigestionParams
}, combinedParameters.ReportAllAmbiguity, new List <string> {
taskId, "Individual Spectra Files", fileNameWithoutExtension
}).Run()).CompactPeptideToProteinPeptideMatching;
foreach (var huh in allPsms)
{
if (huh != null)
{
huh.MatchToProteinLinkedPeptides(compactPeptideToProteinPeptideMatching);
}
}
allPsms = allPsms.Where(b => b != null).OrderByDescending(b => b.Score).ThenBy(b => b.PeptideMonisotopicMass.HasValue ? Math.Abs(b.ScanPrecursorMass - b.PeptideMonisotopicMass.Value) : double.MaxValue).GroupBy(b => (b.FullFilePath, b.ScanNumber, b.PeptideMonisotopicMass)).Select(b => b.First()).ToList();
new FdrAnalysisEngine(allPsms, searchMode.NumNotches, false, new List <string> {
taskId, "Individual Spectra Files", fileNameWithoutExtension
}).Run();
List <PeptideSpectralMatch> goodIdentifications = allPsms.Where(b => b.FdrInfo.QValueNotch < 0.01 && !b.IsDecoy && b.FullSequence != null).ToList();
if (!goodIdentifications.Any())
{
Warn("No PSMs below 1% FDR observed!");
return(new List <PeptideSpectralMatch>(), null);
}
var dissociationTypes = MetaMorpheusEngine.DetermineDissociationType(lp);
foreach (var psm in allPsms)
{
var theScan = myMsDataFile.GetOneBasedScan(psm.ScanNumber);
double thePrecursorMass = psm.ScanPrecursorMass;
foreach (var huh in lp)
{
var ionMasses = psm.CompactPeptides.First().Key.ProductMassesMightHaveDuplicatesAndNaNs(new List <ProductType> {
huh
});
Array.Sort(ionMasses);
List <double> matchedIonMassesList = new List <double>();
List <double> productMassErrorDaList = new List <double>();
List <double> productMassErrorPpmList = new List <double>();
LocalizationEngine.MatchIons(theScan, initProdTol, ionMasses, matchedIonMassesList, productMassErrorDaList, productMassErrorPpmList, thePrecursorMass, dissociationTypes, false);
double[] matchedIonMassesOnlyMatches = matchedIonMassesList.ToArray();
psm.MatchedIonDictOnlyMatches.Add(huh, matchedIonMassesOnlyMatches);
psm.ProductMassErrorDa.Add(huh, productMassErrorDaList.ToArray());
psm.ProductMassErrorPpm.Add(huh, productMassErrorPpmList.ToArray());
}
}
DataPointAquisitionResults currentResult = (DataPointAquisitionResults) new DataPointAcquisitionEngine(
goodIdentifications,
myMsDataFile,
initPrecTol,
initProdTol,
CalibrationParameters.NumFragmentsNeededForEveryIdentification,
CalibrationParameters.MinMS1IsotopicPeaksNeededForConfirmedIdentification,
CalibrationParameters.MinMS2IsotopicPeaksNeededForConfirmedIdentification,
fragmentTypesForCalibration,
new List <string> {
taskId, "Individual Spectra Files", fileNameWithoutExtension
}).Run();
return(goodIdentifications, currentResult);
}
protected override MyTaskResults RunSpecific(string OutputFolder, List <DbForTask> dbFilenameList, List <string> currentRawFileList, string taskId, FileSpecificSettings[] fileSettingsList)
{
myTaskResults = new MyTaskResults(this);
if (NeoType.Equals(NeoTaskType.AggregateTargetDecoyFiles))
{
//getfolders
if (NeoParameters.DecoyFilePath == null)
{
NeoParameters.DecoyFilePath = new DirectoryInfo(OutputFolder).Name;
string taskString = NeoParameters.DecoyFilePath.Split('-')[0];
int taskNum = Convert.ToInt32(taskString.Substring(4, taskString.Length - 4));
taskNum--;
NeoParameters.DecoyFilePath = OutputFolder.Substring(0, OutputFolder.Length - NeoParameters.DecoyFilePath.Length) + "Task" + taskNum + "-SearchTask\\" + Path.GetFileNameWithoutExtension(currentRawFileList[0]) + "_PSMs.psmtsv";
if (NeoParameters.TargetFilePath == null)
{
NeoParameters.TargetFilePath = new DirectoryInfo(OutputFolder).Name;
taskNum--;
NeoParameters.TargetFilePath = OutputFolder.Substring(0, OutputFolder.Length - NeoParameters.TargetFilePath.Length) + "Task" + taskNum + "-SearchTask\\" + Path.GetFileNameWithoutExtension(currentRawFileList[0]) + "_PSMs.psmtsv";
}
}
if (NeoParameters.TargetFilePath == null)
{
NeoParameters.TargetFilePath = new DirectoryInfo(OutputFolder).Name;
string taskString = NeoParameters.TargetFilePath.Split('-')[0];
int taskNum = Convert.ToInt32(taskString.Substring(4, taskString.Length - 4));
taskNum--;
NeoParameters.TargetFilePath = OutputFolder.Substring(0, OutputFolder.Length - NeoParameters.TargetFilePath.Length) + "Task" + taskNum + "-SearchTask\\" + Path.GetFileNameWithoutExtension(currentRawFileList[0]) + "_PSMs.psmtsv";
}
AggregateSearchFiles.Combine(NeoParameters.TargetFilePath, NeoParameters.DecoyFilePath, OutputFolder + "\\" + Path.GetFileNameWithoutExtension(currentRawFileList[0]));
}
else if (NeoType.Equals(NeoTaskType.AggregateNormalSplicedFiles))
{
//reset database
dbFilenameList = StoredDatabases;
string normalPath = "";
string cisPath = new DirectoryInfo(OutputFolder).Name;
string taskString = cisPath.Split('-')[0];
int taskNum = Convert.ToInt32(taskString.Substring(4, taskString.Length - 4));
taskNum -= 2;
string transPath = OutputFolder.Substring(0, OutputFolder.Length - cisPath.Length) + "Task" + (taskNum + 1) + "-SearchTask\\" + Path.GetFileNameWithoutExtension(currentRawFileList[0]) + "_PSMs.psmtsv";
cisPath = OutputFolder.Substring(0, OutputFolder.Length - cisPath.Length) + "Task" + taskNum + "-SearchTask\\" + Path.GetFileNameWithoutExtension(currentRawFileList[0]) + "_PSMs.psmtsv";
AggregateSearchFiles.RecursiveNeoAggregation(normalPath, cisPath, OutputFolder, "CisResults.psmtsv");
AggregateSearchFiles.RecursiveNeoAggregation(normalPath, transPath, OutputFolder, "TransResults.psmtsv");
}
else if (NeoType.Equals(NeoTaskType.GenerateSplicedPeptides))
{
NeoMassCalculator.ImportMasses();
ParallelOptions parallelOptions = new ParallelOptions();
if (CommonParameters.MaxParallelFilesToAnalyze.HasValue)
{
parallelOptions.MaxDegreeOfParallelism = CommonParameters.MaxParallelFilesToAnalyze.Value;
}
MyFileManager myFileManager = new MyFileManager(true);
//Import Spectra
Parallel.For(0, currentRawFileList.Count, parallelOptions, spectraFileIndex =>
{
var origDataFile = currentRawFileList[spectraFileIndex];
ICommonParameters combinedParams = SetAllFileSpecificCommonParams(CommonParameters, fileSettingsList[spectraFileIndex]);
var thisId = new List <string> {
taskId, "Individual Spectra Files", origDataFile
};
NewCollection(Path.GetFileName(origDataFile), thisId);
Status("Loading spectra file...", thisId);
IMsDataFile <IMsDataScan <IMzSpectrum <IMzPeak> > > myMsDataFile = myFileManager.LoadFile(origDataFile, combinedParams.TopNpeaks, combinedParams.MinRatio, combinedParams.TrimMs1Peaks, combinedParams.TrimMsMsPeaks);
Status("Getting ms2 scans...", thisId);
Ms2ScanWithSpecificMass[] arrayOfMs2ScansSortedByMass = GetMs2Scans(myMsDataFile, origDataFile, combinedParams.DoPrecursorDeconvolution, combinedParams.UseProvidedPrecursorInfo, combinedParams.DeconvolutionIntensityRatio, combinedParams.DeconvolutionMaxAssumedChargeState, combinedParams.DeconvolutionMassTolerance).OrderBy(b => b.PrecursorMass).ToArray();
//Import Database
Status("Loading modifications...", taskId);
#region Load modifications
List <ModificationWithMass> variableModifications = GlobalVariables.AllModsKnown.OfType <ModificationWithMass>().Where(b => CommonParameters.ListOfModsVariable.Contains((b.modificationType, b.id))).ToList();
List <ModificationWithMass> fixedModifications = GlobalVariables.AllModsKnown.OfType <ModificationWithMass>().Where(b => CommonParameters.ListOfModsFixed.Contains((b.modificationType, b.id))).ToList();
List <string> localizeableModificationTypes = CommonParameters.ListOfModTypesLocalize == null ? new List <string>() : CommonParameters.ListOfModTypesLocalize.ToList();
if (CommonParameters.LocalizeAll)
{
localizeableModificationTypes = GlobalVariables.AllModTypesKnown.ToList();
}
else
{
localizeableModificationTypes = GlobalVariables.AllModTypesKnown.Where(b => localizeableModificationTypes.Contains(b)).ToList();
}
#endregion Load modifications
var proteinList = dbFilenameList.SelectMany(b => LoadProteinDb(b.FilePath, true, DecoyType.None, localizeableModificationTypes, b.IsContaminant, out Dictionary <string, Modification> unknownModifications)).ToList();
//Read N and C files
string nPath = NeoParameters.NFilePath;
string cPath = NeoParameters.CFilePath;
//if termini input
if (nPath == null || cPath == null)
{
//if no termini input
string taskHeader = "Task";
string[] pathArray = OutputFolder.Split('\\');
string basePath = "";
for (int i = 0; i < pathArray.Length - 1; i++)
{
basePath += pathArray[i] + '\\';
}
string currentTaskNumber = pathArray[pathArray.Length - 1].Split('-')[0];
currentTaskNumber = currentTaskNumber.Substring(taskHeader.Length, currentTaskNumber.Length - taskHeader.Length);
string NHeader = "";
string CHeader = "";
if (cPath == null)
{
CHeader = taskHeader + (Convert.ToInt16(currentTaskNumber) - 1);
if (nPath == null)
{
NHeader = taskHeader + (Convert.ToInt16(currentTaskNumber) - 2);
}
}
else
{
NHeader = taskHeader + (Convert.ToInt16(currentTaskNumber) - 1);
}
foreach (string s in Directory.GetDirectories(basePath))
{
if (s.Contains(NHeader))
{
nPath = s;
}
else if (s.Contains(CHeader))
{
cPath = s;
}
}
string fileName = Path.GetFileNameWithoutExtension(currentRawFileList[0]) + "_PSMs.psmtsv";
nPath += "\\" + fileName;
cPath += "\\" + fileName;
}
Status("Importing Search Results...", taskId);
List <NeoPsm> psms = ImportPsmtsv.ImportNeoPsms(nPath, cPath);
//Splice
Status("Splicing Fragments...", taskId);
List <NeoPsm> candidates = NeoSplicePeptides.SplicePeptides(psms);
//Find Ambiguity
Status("Identifying Ambiguity...", taskId);
NeoFindAmbiguity.FindAmbiguity(candidates, proteinList, arrayOfMs2ScansSortedByMass, dbFilenameList[0].FilePath);
//Export Results
Status("Exporting Results...", taskId);
NeoExport.ExportAll(candidates, arrayOfMs2ScansSortedByMass, OutputFolder);
//Switch databases
string outputFolder = NeoExport.path + NeoExport.folder + @"\" + NeoExport.folder + "FusionDatabaseAppendixNC.fasta";
dbFilenameList = new List <DbForTask>()
{
new DbForTask(outputFolder, false)
};
});
public CalibrationEngine(IMsDataFile <IMsDataScan <IMzSpectrum <IMzPeak> > > myMSDataFile, DataPointAquisitionResults datapoints, List <string> nestedIds) : base(nestedIds)
{
this.myMsDataFile = myMSDataFile;
this.datapoints = datapoints;
}
protected override MyTaskResults RunSpecific(string OutputFolder, List <DbForTask> dbFilenameList, List <string> currentRawFileList, string taskId, FileSpecificSettings[] fileSettingsList)
{
myTaskResults = new MyTaskResults(this)
{
newDatabases = new List <DbForTask>()
};
Status("Loading modifications...", new List <string> {
taskId
});
List <ModificationWithMass> variableModifications = GlobalVariables.AllModsKnown.OfType <ModificationWithMass>().Where(b => CommonParameters.ListOfModsVariable.Contains((b.modificationType, b.id))).ToList();
List <ModificationWithMass> fixedModifications = GlobalVariables.AllModsKnown.OfType <ModificationWithMass>().Where(b => CommonParameters.ListOfModsFixed.Contains((b.modificationType, b.id))).ToList();
List <string> localizeableModificationTypes = CommonParameters.LocalizeAll ? GlobalVariables.AllModTypesKnown.ToList() : CommonParameters.ListOfModTypesLocalize.ToList();
List <ModificationWithMass> gptmdModifications = GlobalVariables.AllModsKnown.OfType <ModificationWithMass>().Where(b => GptmdParameters.ListOfModsGptmd.Contains((b.modificationType, b.id))).ToList();
IEnumerable <Tuple <double, double> > combos = LoadCombos(gptmdModifications).ToList();
List <PeptideSpectralMatch> allPsms = new List <PeptideSpectralMatch>();
List <ProductType> ionTypes = new List <ProductType>();
if (CommonParameters.BIons)
{
ionTypes.Add(ProductType.B);
}
if (CommonParameters.YIons)
{
ionTypes.Add(ProductType.Y);
}
if (CommonParameters.CIons)
{
ionTypes.Add(ProductType.C);
}
if (CommonParameters.ZdotIons)
{
ionTypes.Add(ProductType.Zdot);
}
Status("Loading proteins...", new List <string> {
taskId
});
Dictionary <string, Modification> um = null;
//Decoys are currently not being searched with DecoyType.None
var proteinList = dbFilenameList.SelectMany(b => LoadProteinDb(b.FilePath, true, DecoyType.Reverse, localizeableModificationTypes, b.IsContaminant, out um)).ToList();
var numRawFiles = currentRawFileList.Count;
proseCreatedWhileRunning.Append("The following G-PTM-D settings were used: "); proseCreatedWhileRunning.Append("protease = " + CommonParameters.DigestionParams.Protease + "; ");
proseCreatedWhileRunning.Append("maximum missed cleavages = " + CommonParameters.DigestionParams.MaxMissedCleavages + "; ");
proseCreatedWhileRunning.Append("minimum peptide length = " + CommonParameters.DigestionParams.MinPeptideLength + "; ");
if (CommonParameters.DigestionParams.MaxPeptideLength == null)
{
proseCreatedWhileRunning.Append("maximum peptide length = unspecified; ");
}
else
{
proseCreatedWhileRunning.Append("maximum peptide length = " + CommonParameters.DigestionParams.MaxPeptideLength + "; ");
}
proseCreatedWhileRunning.Append("initiator methionine behavior = " + CommonParameters.DigestionParams.InitiatorMethionineBehavior + "; ");
proseCreatedWhileRunning.Append("max modification isoforms = " + CommonParameters.DigestionParams.MaxModificationIsoforms + "; ");
proseCreatedWhileRunning.Append("fixed modifications = " + string.Join(", ", fixedModifications.Select(m => m.id)) + "; ");
proseCreatedWhileRunning.Append("variable modifications = " + string.Join(", ", variableModifications.Select(m => m.id)) + "; ");
proseCreatedWhileRunning.Append("G-PTM-D modifications count = " + gptmdModifications.Count + "; ");
//puppet searchmode for writing files. Actual searchmode is filespecific
MassDiffAcceptor tempSearchMode = new DotMassDiffAcceptor("", GetAcceptableMassShifts(fixedModifications, variableModifications, gptmdModifications, combos), CommonParameters.PrecursorMassTolerance);
proseCreatedWhileRunning.Append("parent mass tolerance(s) = {" + tempSearchMode.ToProseString() + "}; ");
proseCreatedWhileRunning.Append("product mass tolerance = " + CommonParameters.ProductMassTolerance + " Da. ");
proseCreatedWhileRunning.Append("The combined search database contained " + proteinList.Count + " total entries including " + proteinList.Where(p => p.IsContaminant).Count() + " contaminant sequences. ");
Status("Running G-PTM-D...", new List <string> {
taskId
});
HashSet <IDigestionParams> ListOfDigestionParams = GetListOfDistinctDigestionParams(CommonParameters, fileSettingsList.Select(b => SetAllFileSpecificCommonParams(CommonParameters, b)));
MyFileManager myFileManager = new MyFileManager(true);
object lock1 = new object();
object lock2 = new object();
ParallelOptions parallelOptions = new ParallelOptions();
if (CommonParameters.MaxParallelFilesToAnalyze.HasValue)
{
parallelOptions.MaxDegreeOfParallelism = CommonParameters.MaxParallelFilesToAnalyze.Value;
}
Parallel.For(0, currentRawFileList.Count, parallelOptions, spectraFileIndex =>
{
var origDataFile = currentRawFileList[spectraFileIndex];
ICommonParameters combinedParams = SetAllFileSpecificCommonParams(CommonParameters, fileSettingsList[spectraFileIndex]);
MassDiffAcceptor searchMode = new DotMassDiffAcceptor("", GetAcceptableMassShifts(fixedModifications, variableModifications, gptmdModifications, combos), combinedParams.PrecursorMassTolerance);
NewCollection(Path.GetFileName(origDataFile), new List <string> {
taskId, "Individual Spectra Files", origDataFile
});
StartingDataFile(origDataFile, new List <string> {
taskId, "Individual Spectra Files", origDataFile
});
Status("Loading spectra file...", new List <string> {
taskId, "Individual Spectra Files", origDataFile
});
IMsDataFile <IMsDataScan <IMzSpectrum <IMzPeak> > > myMsDataFile = myFileManager.LoadFile(origDataFile, combinedParams.TopNpeaks, combinedParams.MinRatio, combinedParams.TrimMs1Peaks, combinedParams.TrimMsMsPeaks);
Status("Getting ms2 scans...", new List <string> {
taskId, "Individual Spectra Files", origDataFile
});
Ms2ScanWithSpecificMass[] arrayOfMs2ScansSortedByMass = GetMs2Scans(myMsDataFile, origDataFile, combinedParams.DoPrecursorDeconvolution, combinedParams.UseProvidedPrecursorInfo, combinedParams.DeconvolutionIntensityRatio, combinedParams.DeconvolutionMaxAssumedChargeState, combinedParams.DeconvolutionMassTolerance).OrderBy(b => b.PrecursorMass).ToArray();
myFileManager.DoneWithFile(origDataFile);
PeptideSpectralMatch[] allPsmsArray = new PeptideSpectralMatch[arrayOfMs2ScansSortedByMass.Length];
new ClassicSearchEngine(allPsmsArray, arrayOfMs2ScansSortedByMass, variableModifications, fixedModifications, proteinList, ionTypes, searchMode, false, combinedParams, combinedParams.ProductMassTolerance, new List <string> {
taskId, "Individual Spectra Files", origDataFile
}).Run();
lock (lock2)
{
allPsms.AddRange(allPsmsArray);
}
FinishedDataFile(origDataFile, new List <string> {
taskId, "Individual Spectra Files", origDataFile
});
ReportProgress(new ProgressEventArgs(100, "Done!", new List <string> {
taskId, "Individual Spectra Files", origDataFile
}));
});
ReportProgress(new ProgressEventArgs(100, "Done!", new List <string> {
taskId, "Individual Spectra Files"
}));
// Group and order psms
SequencesToActualProteinPeptidesEngine sequencesToActualProteinPeptidesEngineTest = new SequencesToActualProteinPeptidesEngine(allPsms, proteinList, fixedModifications, variableModifications, ionTypes, ListOfDigestionParams, CommonParameters.ReportAllAmbiguity, new List <string> {
taskId
});
var resTest = (SequencesToActualProteinPeptidesEngineResults)sequencesToActualProteinPeptidesEngineTest.Run();
Dictionary <CompactPeptideBase, HashSet <PeptideWithSetModifications> > compactPeptideToProteinPeptideMatchingTest = resTest.CompactPeptideToProteinPeptideMatching;
foreach (var huh in allPsms)
{
if (huh != null)
{
huh.MatchToProteinLinkedPeptides(compactPeptideToProteinPeptideMatchingTest);
}
}
allPsms = allPsms.Where(b => b != null).OrderByDescending(b => b.Score).ThenBy(b => b.PeptideMonisotopicMass.HasValue ? Math.Abs(b.ScanPrecursorMass - b.PeptideMonisotopicMass.Value) : double.MaxValue).GroupBy(b => new Tuple <string, int, double?>(b.FullFilePath, b.ScanNumber, b.PeptideMonisotopicMass)).Select(b => b.First()).ToList();
new FdrAnalysisEngine(allPsms, tempSearchMode.NumNotches, false, new List <string> {
taskId
}).Run();
var writtenFile = Path.Combine(OutputFolder, "GPTMD_Candidates.psmtsv");
WritePsmsToTsv(allPsms, writtenFile, new Dictionary <string, int>());
SucessfullyFinishedWritingFile(writtenFile, new List <string> {
taskId
});
var gptmdResults = (GptmdResults) new GptmdEngine(allPsms, gptmdModifications, combos, CommonParameters.PrecursorMassTolerance, new List <string> {
taskId
}).Run();
if (dbFilenameList.Any(b => !b.IsContaminant))
{
// do NOT use this code (Path.GetFilenameWithoutExtension) because GPTMD on .xml.gz will result in .xml.xml file type being written
//string outputXMLdbFullName = Path.Combine(OutputFolder, string.Join("-", dbFilenameList.Where(b => !b.IsContaminant).Select(b => Path.GetFileNameWithoutExtension(b.FilePath))) + "GPTMD.xml");
List <string> databaseNames = new List <string>();
foreach (var nonContaminantDb in dbFilenameList.Where(p => !p.IsContaminant))
{
var dbName = Path.GetFileName(nonContaminantDb.FilePath);
int indexOfFirstDot = dbName.IndexOf(".");
databaseNames.Add(dbName.Substring(0, indexOfFirstDot));
}
string outputXMLdbFullName = Path.Combine(OutputFolder, string.Join("-", databaseNames) + "GPTMD.xml");
var newModsActuallyWritten = ProteinDbWriter.WriteXmlDatabase(gptmdResults.Mods, proteinList.Where(b => !b.IsDecoy && !b.IsContaminant).ToList(), outputXMLdbFullName);
SucessfullyFinishedWritingFile(outputXMLdbFullName, new List <string> {
taskId
});
myTaskResults.newDatabases.Add(new DbForTask(outputXMLdbFullName, false));
myTaskResults.AddNiceText("Modifications added: " + newModsActuallyWritten.Select(b => b.Value).Sum());
myTaskResults.AddNiceText("Mods types and counts:");
myTaskResults.AddNiceText(string.Join(Environment.NewLine, newModsActuallyWritten.OrderByDescending(b => b.Value).Select(b => "\t" + b.Key + "\t" + b.Value)));
}
if (dbFilenameList.Any(b => b.IsContaminant))
{
// do NOT use this code (Path.GetFilenameWithoutExtension) because GPTMD on .xml.gz will result in .xml.xml file type being written
//string outputXMLdbFullNameContaminants = Path.Combine(OutputFolder, string.Join("-", dbFilenameList.Where(b => b.IsContaminant).Select(b => Path.GetFileNameWithoutExtension(b.FilePath))) + "GPTMD.xml");
List <string> databaseNames = new List <string>();
foreach (var contaminantDb in dbFilenameList.Where(p => p.IsContaminant))
{
var dbName = Path.GetFileName(contaminantDb.FilePath);
int indexOfFirstDot = dbName.IndexOf(".");
databaseNames.Add(dbName.Substring(0, indexOfFirstDot));
}
string outputXMLdbFullNameContaminants = Path.Combine(OutputFolder, string.Join("-", databaseNames) + "GPTMD.xml");
var newModsActuallyWritten = ProteinDbWriter.WriteXmlDatabase(gptmdResults.Mods, proteinList.Where(b => !b.IsDecoy && b.IsContaminant).ToList(), outputXMLdbFullNameContaminants);
SucessfullyFinishedWritingFile(outputXMLdbFullNameContaminants, new List <string> {
taskId
});
myTaskResults.newDatabases.Add(new DbForTask(outputXMLdbFullNameContaminants, true));
myTaskResults.AddNiceText("Contaminant modifications added: " + newModsActuallyWritten.Select(b => b.Value).Sum());
myTaskResults.AddNiceText("Mods types and counts:");
myTaskResults.AddNiceText(string.Join(Environment.NewLine, newModsActuallyWritten.OrderByDescending(b => b.Value).Select(b => "\t" + b.Key + "\t" + b.Value)));
}
return(myTaskResults);
}