public static void XlTestXlPosCal()
{
var prot = new Protein("MNNNKQQQQ", null);
Protease protease = new Protease("New Custom Protease", new List <Tuple <string, TerminusType> > {
new Tuple <string, TerminusType>("K", TerminusType.C)
}, new List <Tuple <string, TerminusType> >(), CleavageSpecificity.Full, null, null, null);
ProteaseDictionary.Dictionary.Add(protease.Name, protease);
DigestionParams digestionParams = new DigestionParams(protease: protease.Name, minPeptideLength: 1, initiatorMethionineBehavior: InitiatorMethionineBehavior.Retain);
List <ModificationWithMass> variableModifications = new List <ModificationWithMass>();
var ye = prot.Digest(digestionParams, new List <ModificationWithMass>(), variableModifications).ToList();
var pep = ye[0];
Assert.AreEqual(pep.BaseSequence, "MNNNK");
CrosslinkerTypeClass crosslinker = new CrosslinkerTypeClass();
crosslinker.SelectCrosslinker(CrosslinkerType.DSS);
Assert.AreEqual(crosslinker.CrosslinkerModSites, "K");
Assert.AreEqual(Residue.GetResidue(crosslinker.CrosslinkerModSites).MonoisotopicMass, 128.09496301518999, 1e-9);
var n = pep.CompactPeptide(TerminusType.None).NTerminalMasses;
var c = pep.CompactPeptide(TerminusType.None).CTerminalMasses;
Assert.AreEqual(n.Count(), 4);
Assert.AreEqual(c.Count(), 4);
Assert.AreEqual(c[0], 128.09496301518999, 1e-6);
var x = PsmCross.XlPosCal(pep.CompactPeptide(TerminusType.None), crosslinker.CrosslinkerModSites).ToArray();
Assert.AreEqual(x[0], 4);
var pep2 = ye[2];
Assert.AreEqual("MNNNKQQQQ", pep2.BaseSequence);
var n2 = pep2.CompactPeptide(TerminusType.None).NTerminalMasses;
var c2 = pep2.CompactPeptide(TerminusType.None).CTerminalMasses;
Assert.AreEqual(n2.Count(), 8);
Assert.AreEqual(c2.Count(), 8);
Assert.AreEqual(n2[4] - n2[3], 128.09496301518999, 1e-6);
var x2 = PsmCross.XlPosCal(pep2.CompactPeptide(TerminusType.None), crosslinker.CrosslinkerModSites).ToArray();
Assert.AreEqual(x2[0], 4);
//Test crosslinker with multiple types of mod
var protSTC = new Protein("GASTACK", null);
var peps = protSTC.Digest(digestionParams, new List <ModificationWithMass>(), variableModifications).ToList();
var pepSTC = peps[0];
Assert.AreEqual(pepSTC.BaseSequence, "GASTACK");
CrosslinkerTypeClass crosslinker2 = new CrosslinkerTypeClass("ST", "C", "crosslinkerSTC", false, -18.01056, 0, 0, 0, 0, 0, 0);
string crosslinkerModSitesAll = new string((crosslinker2.CrosslinkerModSites + crosslinker2.CrosslinkerModSites2).ToCharArray().Distinct().ToArray());
Assert.AreEqual(crosslinkerModSitesAll, "STC");
}
public CrosslinkAnalysisEngine(List <PsmCross> newPsms, Dictionary <CompactPeptideBase, HashSet <PeptideWithSetModifications> > compactPeptideToProteinPeptideMatching, List <Protein> proteinList, List <ModificationWithMass> variableModifications, List <ModificationWithMass> fixedModifications, List <ProductType> lp, string outputFolder, CrosslinkerTypeClass crosslinker, TerminusType terminusType, CommonParameters commonParameters, List <string> nestedIds) : base(commonParameters, nestedIds)
{
NewPsms = newPsms;
CompactPeptideToProteinPeptideMatching = compactPeptideToProteinPeptideMatching;
ProteinList = proteinList;
VariableModifications = variableModifications;
FixedModifications = fixedModifications;
ProductTypes = lp;
OutputFolder = outputFolder;
Crosslinker = crosslinker;
TerminusType = terminusType;
}
public CrosslinkAnalysisEngine(List <PsmCross> newPsms, Dictionary <CompactPeptideBase, HashSet <PeptideWithSetModifications> > compactPeptideToProteinPeptideMatching, List <Protein> proteinList, List <ModificationWithMass> variableModifications, List <ModificationWithMass> fixedModifications, List <ProductType> lp, string OutputFolder, CrosslinkerTypeClass crosslinker, TerminusType terminusType, ICommonParameters CommonParameters, List <string> nestedIds) : base(nestedIds)
{
this.newPsms = newPsms;
this.compactPeptideToProteinPeptideMatching = compactPeptideToProteinPeptideMatching;
this.proteinList = proteinList;
this.variableModifications = variableModifications;
this.fixedModifications = fixedModifications;
this.lp = lp;
this.OutputFolder = OutputFolder;
this.crosslinker = crosslinker;
this.terminusType = terminusType;
this.CommonParameters = CommonParameters;
}
public static void XlTestXlPosCal()
{
var prot = new Protein("MNNNKQQQQ", null);
var protease = new Protease("Custom Protease", new List <string> {
"K"
}, new List <string>(), TerminusType.C, CleavageSpecificity.Full, null, null, null);
DigestionParams digestionParams = new DigestionParams
{
InitiatorMethionineBehavior = InitiatorMethionineBehavior.Retain,
MaxMissedCleavages = 2,
Protease = protease,
MinPeptideLength = 1
};
List <ModificationWithMass> variableModifications = new List <ModificationWithMass>();
var ye = prot.Digest(digestionParams, new List <ModificationWithMass>(), variableModifications).ToList();
var pep = ye[0];
Assert.AreEqual(pep.BaseSequence, "MNNNK");
CrosslinkerTypeClass crosslinker = new CrosslinkerTypeClass();
crosslinker.SelectCrosslinker(CrosslinkerType.DSS);
Assert.AreEqual(crosslinker.CrosslinkerModSite, 'K');
Assert.AreEqual(Residue.GetResidue(crosslinker.CrosslinkerModSite).MonoisotopicMass, 128.09496301518999, 1e-9);
var n = pep.CompactPeptide(TerminusType.None).NTerminalMasses;
var c = pep.CompactPeptide(TerminusType.None).CTerminalMasses;
Assert.AreEqual(n.Count(), 4);
Assert.AreEqual(c.Count(), 4);
Assert.AreEqual(c[0], 128.09496301518999, 1e-6);
var x = PsmCross.XlPosCal(pep.CompactPeptide(TerminusType.None), crosslinker).ToArray();
Assert.AreEqual(x[0], 4);
var pep2 = ye[2];
Assert.AreEqual("MNNNKQQQQ", pep2.BaseSequence);
var n2 = pep2.CompactPeptide(TerminusType.None).NTerminalMasses;
var c2 = pep2.CompactPeptide(TerminusType.None).CTerminalMasses;
Assert.AreEqual(n2.Count(), 8);
Assert.AreEqual(c2.Count(), 8);
Assert.AreEqual(n2[4] - n2[3], 128.09496301518999, 1e-6);
var x2 = PsmCross.XlPosCal(pep2.CompactPeptide(TerminusType.None), crosslinker).ToArray();
Assert.AreEqual(x2[0], 4);
}
//Generate user defined crosslinker
public static CrosslinkerTypeClass GenerateUserDefinedCrosslinker(XlSearchParameters xlSearchParameters)
{
var crosslinker = new CrosslinkerTypeClass(
xlSearchParameters.UdXLkerResidues,
xlSearchParameters.UdXLkerResidues2,
xlSearchParameters.UdXLkerName,
xlSearchParameters.UdXLkerCleavable,
(xlSearchParameters.UdXLkerTotalMass.HasValue ? (double)xlSearchParameters.UdXLkerTotalMass : 9999),
(xlSearchParameters.UdXLkerShortMass.HasValue ? (double)xlSearchParameters.UdXLkerShortMass : 9999),
(xlSearchParameters.UdXLkerLongMass.HasValue ? (double)xlSearchParameters.UdXLkerLongMass : 9999),
(xlSearchParameters.UdXLkerLoopMass.HasValue ? (double)xlSearchParameters.UdXLkerLoopMass : 9999),
(xlSearchParameters.UdXLkerDeadendMassH2O.HasValue ? (double)xlSearchParameters.UdXLkerDeadendMassH2O : 9999),
(xlSearchParameters.UdXLkerDeadendMassNH2.HasValue ? (double)xlSearchParameters.UdXLkerDeadendMassNH2 : 9999),
(xlSearchParameters.UdXLkerDeadendMassTris.HasValue ? (double)xlSearchParameters.UdXLkerDeadendMassTris : 9999)
);
return(crosslinker);
}
public static void XlTest_BSA_DSSO()
{
//Generate parameters
var commonParameters = new CommonParameters(doPrecursorDeconvolution: false, cIons: true, zDotIons: true, scoreCutoff: 2, digestionParams: new DigestionParams(minPeptideLength: 5));
var xlSearchParameters = new XlSearchParameters {
XlCharge_2_3_PrimeFragment = true
};
//Create databases contain two protein.
var proteinList = new List <Protein> {
new Protein("EKVLTSSAR", "Fake01"), new Protein("LSQKFPK", "Fake02")
};
ModificationMotif.TryGetMotif("M", out ModificationMotif motif1);
ModificationWithMass mod1 = new ModificationWithMass("Oxidation of M", "Common Variable", motif1, TerminusLocalization.Any, 15.99491461957);
ModificationMotif.TryGetMotif("C", out ModificationMotif motif2);
ModificationWithMass mod2 = new ModificationWithMass("Carbamidomethyl of C", "Common Fixed", motif2, TerminusLocalization.Any, 57.02146372068994);
var variableModifications = new List <ModificationWithMass>()
{
mod1
};
var fixedModifications = new List <ModificationWithMass>()
{
mod2
};
var localizeableModifications = new List <ModificationWithMass>();
var lp = new List <ProductType> {
ProductType.BnoB1ions, ProductType.Y, ProductType.C, ProductType.Zdot
};
Dictionary <ModificationWithMass, ushort> modsDictionary = new Dictionary <ModificationWithMass, ushort>();
foreach (var mod in fixedModifications)
{
modsDictionary.Add(mod, 0);
}
int i = 1;
foreach (var mod in variableModifications)
{
modsDictionary.Add(mod, (ushort)i);
i++;
}
foreach (var mod in localizeableModifications)
{
modsDictionary.Add(mod, (ushort)i);
i++;
}
//Generate digested peptide lists.
List <PeptideWithSetModifications> digestedList = new List <PeptideWithSetModifications>();
foreach (var item in proteinList)
{
var digested = item.Digest(commonParameters.DigestionParams, fixedModifications, variableModifications).ToList();
digestedList.AddRange(digested);
}
foreach (var fdfd in digestedList)
{
fdfd.CompactPeptide(TerminusType.None);
}
//Run index engine
var indexEngine = new IndexingEngine(proteinList, variableModifications, fixedModifications, lp, 1, DecoyType.Reverse, new List <DigestionParams>
{
commonParameters.DigestionParams
}, commonParameters, 30000, new List <string>());
var indexResults = (IndexingResults)indexEngine.Run();
var fragmentIndexCount = indexResults.FragmentIndex.Count(p => p != null);
var fragmentIndexAll = indexResults.FragmentIndex.Select((s, j) => new { j, s }).Where(p => p.s != null).Select(t => t.j).ToList();
Assert.IsTrue(fragmentIndexAll.Count() > 0);
//Get MS2 scans.
var myMsDataFile = new XLTestDataFile();
var listOfSortedms2Scans = MetaMorpheusTask.GetMs2Scans(myMsDataFile, null, commonParameters.DoPrecursorDeconvolution, commonParameters.UseProvidedPrecursorInfo, commonParameters.DeconvolutionIntensityRatio, commonParameters.DeconvolutionMaxAssumedChargeState, commonParameters.DeconvolutionMassTolerance).OrderBy(b => b.PrecursorMass).ToArray();
//Generate crosslinker, which is DSSO here.
CrosslinkerTypeClass crosslinker = new CrosslinkerTypeClass();
crosslinker.SelectCrosslinker(xlSearchParameters.CrosslinkerType);
//TwoPassCrosslinkSearchEngine.Run().
List <PsmCross> newPsms = new List <PsmCross>();
new TwoPassCrosslinkSearchEngine(newPsms, listOfSortedms2Scans, indexResults.PeptideIndex, indexResults.FragmentIndex, lp, 0, commonParameters, 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, new List <string> {
}).Run();
var compactPeptideToProteinPeptideMatch = new Dictionary <CompactPeptideBase, HashSet <PeptideWithSetModifications> >();
new CrosslinkAnalysisEngine(newPsms, compactPeptideToProteinPeptideMatch, proteinList, variableModifications, fixedModifications, lp, null, crosslinker, TerminusType.None, commonParameters, new List <string> {
}).Run();
foreach (var item in newPsms)
{
item.SetFdrValues(0, 0, 0, 0, 0, 0, 0, 0, 0, false);
}
//Test newPsms
Assert.AreEqual(newPsms.Count(), 3);
//Test Output
var task = new XLSearchTask();
task.WriteAllToTsv(newPsms, TestContext.CurrentContext.TestDirectory, "allPsms", new List <string> {
});
task.WritePepXML_xl(newPsms, proteinList, null, variableModifications, fixedModifications, null, TestContext.CurrentContext.TestDirectory, "pep.XML", new List <string> {
});
task.WriteSingleToTsv(newPsms.Where(p => p.CrossType == PsmCrossType.Singe).ToList(), TestContext.CurrentContext.TestDirectory, "singlePsms", new List <string> {
});
//Test PsmCross.XlCalculateTotalProductMasses.
var psmCrossAlpha = new PsmCross(digestedList[1].CompactPeptide(TerminusType.None), 0, 0, i, listOfSortedms2Scans[0], commonParameters.DigestionParams);
var psmCrossBeta = new PsmCross(digestedList[2].CompactPeptide(TerminusType.None), 0, 0, i, listOfSortedms2Scans[0], commonParameters.DigestionParams);
var linkPos = PsmCross.XlPosCal(psmCrossAlpha.compactPeptide, crosslinker.CrosslinkerModSites);
var productMassesAlphaList = PsmCross.XlCalculateTotalProductMasses(psmCrossAlpha, psmCrossBeta.compactPeptide.MonoisotopicMassIncludingFixedMods + crosslinker.TotalMass, crosslinker, lp, true, false, linkPos);
Assert.AreEqual(productMassesAlphaList[0].ProductMz.Length, 99);
}
protected override MyTaskResults RunSpecific(string OutputFolder, List <DbForTask> dbFilenameList, List <string> currentRawFileList, string taskId, FileSpecificParameters[] fileSettingsList)
{
MyTaskResults = new MyTaskResults(this);
List <PsmCross> allPsms = new List <PsmCross>();
var compactPeptideToProteinPeptideMatch = new Dictionary <CompactPeptideBase, HashSet <PeptideWithSetModifications> >();
Status("Loading modifications...", 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 = GlobalVariables.AllModTypesKnown.ToList();
// load proteins
List <Protein> proteinList = LoadProteins(taskId, dbFilenameList, true, XlSearchParameters.DecoyType, localizeableModificationTypes, CommonParameters);
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 = ProductTypeMethods.IdentifyTerminusType(ionTypes);
var crosslinker = new CrosslinkerTypeClass();
crosslinker.SelectCrosslinker(XlSearchParameters.CrosslinkerType);
if (XlSearchParameters.CrosslinkerType == CrosslinkerType.UserDefined)
{
crosslinker = GenerateUserDefinedCrosslinker(XlSearchParameters);
}
MyFileManager myFileManager = new MyFileManager(XlSearchParameters.DisposeOfFileWhenDone);
var fileSpecificCommonParams = fileSettingsList.Select(b => SetAllFileSpecificCommonParams(CommonParameters, b));
HashSet <DigestionParams> ListOfDigestionParams = new HashSet <DigestionParams>(fileSpecificCommonParams.Select(p => p.DigestionParams));
int completedFiles = 0;
object indexLock = new object();
object psmLock = new object();
Status("Searching files...", taskId);
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.CrosslinkerModSites + "; ");
ProseCreatedWhileRunning.Append("protease = " + CommonParameters.DigestionParams.Protease + "; ");
ProseCreatedWhileRunning.Append("maximum missed cleavages = " + CommonParameters.DigestionParams.MaxMissedCleavages + "; ");
ProseCreatedWhileRunning.Append("minimum peptide length = " + CommonParameters.DigestionParams.MinPeptideLength + "; ");
ProseCreatedWhileRunning.Append(CommonParameters.DigestionParams.MaxPeptideLength == int.MaxValue ?
"maximum peptide length = unspecified; " :
"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. ");
for (int spectraFileIndex = 0; spectraFileIndex < currentRawFileList.Count; spectraFileIndex++)
{
if (GlobalVariables.StopLoops)
{
break;
}
var origDataFile = currentRawFileList[spectraFileIndex];
CommonParameters 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);
MsDataFile myMsDataFile = myFileManager.LoadFile(origDataFile, combinedParams.TopNpeaks, combinedParams.MinRatio, combinedParams.TrimMs1Peaks, combinedParams.TrimMsMsPeaks, combinedParams);
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();
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));
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);
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.Where(p => p != null));
}
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.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;
}
}
//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;
}
}
//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;
}
}
var singlePsms = allPsms.Where(p => p.CrossType == PsmCrossType.Singe && p.FullSequence != null && !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
});
}
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
});
}
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 != null && p.FullSequence.Contains("Crosslink")).ToList());
var deadendPsmsFDR = SingleFDRAnalysis(deadendPsms).ToList();
if (XlSearchParameters.XlOutAll)
{
WriteSingleToTsv(deadendPsmsFDR, OutputFolder, "deadend_fdr", new List <string> {
taskId
});
}
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(), proteinList, dbFilenameList[0].FilePath, 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 WritePepXML_xl(List <PsmCross> items, List <DbForTask> dbFilenameList, List <ModificationWithMass> variableModifications, List <ModificationWithMass> fixedModifications, List <string> localizeableModificationTypes, string outputFolder, string fileName, List <string> nestedIds)
{
XmlSerializer _indexedSerializer = new XmlSerializer(typeof(pepXML.Generated.msms_pipeline_analysis));
var _pepxml = new pepXML.Generated.msms_pipeline_analysis();
#region Add element to pepXML
_pepxml.date = DateTime.Now;
_pepxml.summary_xml = items[0].FullFilePath + ".pep.xml";
string proteaseC = ""; string proteaseNC = "";
foreach (var x in CommonParameters.DigestionParams.Protease.SequencesInducingCleavage)
{
proteaseC += x;
}
foreach (var x in CommonParameters.DigestionParams.Protease.SequencesPreventingCleavage)
{
proteaseNC += x;
}
CrosslinkerTypeClass crosslinker = new CrosslinkerTypeClass().SelectCrosslinker(XlSearchParameters.CrosslinkerType);
var proteinList = dbFilenameList.SelectMany(b => LoadProteinDb(b.FilePath, true, XlSearchParameters.DecoyType, localizeableModificationTypes, b.IsContaminant, out Dictionary <string, Modification> unknownModifications)).ToList();
uint proteinTot = Convert.ToUInt32(proteinList.Count);
string fileNameNoExtension = Path.GetFileNameWithoutExtension(items[0].FullFilePath);
string filePathNoExtension = Path.ChangeExtension(items[0].FullFilePath, null);
var para = new List <pepXML.Generated.nameValueType>();
{
para.Add(new pepXML.Generated.nameValueType {
name = "threads", value = ""
});
para.Add(new pepXML.Generated.nameValueType {
name = "database", value = dbFilenameList[0].FilePath
});
para.Add(new pepXML.Generated.nameValueType {
name = "MS_data_file", value = items[0].FullFilePath
});
para.Add(new pepXML.Generated.nameValueType {
name = "Search with All Possible Beta Peptides", value = XlSearchParameters.CrosslinkSearchWithAllBeta.ToString()
});
para.Add(new pepXML.Generated.nameValueType {
name = "Cross-link Precusor Mass Tolence", value = XlSearchParameters.XlPrecusorMsTl.ToString()
});
para.Add(new pepXML.Generated.nameValueType {
name = "Cross-linker Type", value = crosslinker.CrosslinkerName
});
para.Add(new pepXML.Generated.nameValueType {
name = "Cross-linker mass", value = crosslinker.TotalMass.ToString()
});
para.Add(new pepXML.Generated.nameValueType {
name = "Cross-linker cleavable", value = crosslinker.Cleavable.ToString()
});
para.Add(new pepXML.Generated.nameValueType {
name = "Cross-linker cleavable long mass", value = crosslinker.CleaveMassLong.ToString()
});
para.Add(new pepXML.Generated.nameValueType {
name = "Cross-linker cleavable short mass", value = crosslinker.CleaveMassShort.ToString()
});
para.Add(new pepXML.Generated.nameValueType {
name = "Cross-linker xl site", value = crosslinker.CrosslinkerModSite.ToString()
});
para.Add(new pepXML.Generated.nameValueType {
name = "Generate decoy proteins", value = XlSearchParameters.DecoyType.ToString()
});
para.Add(new pepXML.Generated.nameValueType {
name = "MaxMissed Cleavages", value = CommonParameters.DigestionParams.MaxMissedCleavages.ToString()
});
para.Add(new pepXML.Generated.nameValueType {
name = "Protease", value = CommonParameters.DigestionParams.Protease.Name
});
para.Add(new pepXML.Generated.nameValueType {
name = "Initiator Methionine", value = CommonParameters.DigestionParams.InitiatorMethionineBehavior.ToString()
});
para.Add(new pepXML.Generated.nameValueType {
name = "Max Modification Isoforms", value = CommonParameters.DigestionParams.MaxModificationIsoforms.ToString()
});
para.Add(new pepXML.Generated.nameValueType {
name = "Min Peptide Len", value = CommonParameters.DigestionParams.MinPeptideLength.ToString()
});
para.Add(new pepXML.Generated.nameValueType {
name = "Max Peptide Len", value = CommonParameters.DigestionParams.MaxPeptideLength.ToString()
});
para.Add(new pepXML.Generated.nameValueType {
name = "Product Mass Tolerance", value = CommonParameters.ProductMassTolerance.ToString()
});
para.Add(new pepXML.Generated.nameValueType {
name = "Ions to search", value = "B " + CommonParameters.BIons.ToString() + " Y " + CommonParameters.YIons.ToString() + " C " + CommonParameters.CIons.ToString() + " Z " + CommonParameters.ZdotIons.ToString()
});
para.Add(new pepXML.Generated.nameValueType {
name = "Allowed Beta Precusor Mass Difference", value = XlSearchParameters.XlBetaPrecusorMsTl.ToString()
});
foreach (var item in fixedModifications)
{
para.Add(new pepXML.Generated.nameValueType {
name = "Fixed Modifications: " + item.id, value = item.monoisotopicMass.ToString()
});
}
foreach (var item in variableModifications)
{
para.Add(new pepXML.Generated.nameValueType {
name = "Variable Modifications: " + item.id, value = item.monoisotopicMass.ToString()
});
}
para.Add(new pepXML.Generated.nameValueType {
name = "Localize All Modifications", value = CommonParameters.LocalizeAll.ToString()
});
}
_pepxml.msms_run_summary = new pepXML.Generated.msms_pipeline_analysisMsms_run_summary[1]
{
new pepXML.Generated.msms_pipeline_analysisMsms_run_summary
{
base_name = filePathNoExtension,
raw_data_type = "raw",
raw_data = ".mzML",
sample_enzyme = new pepXML.Generated.msms_pipeline_analysisMsms_run_summarySample_enzyme()
{
name = CommonParameters.DigestionParams.Protease.Name,
specificity = new pepXML.Generated.msms_pipeline_analysisMsms_run_summarySample_enzymeSpecificity[1]
{
new pepXML.Generated.msms_pipeline_analysisMsms_run_summarySample_enzymeSpecificity
{
cut = proteaseC,
no_cut = proteaseNC,
}
}
},
search_summary = new pepXML.Generated.msms_pipeline_analysisMsms_run_summarySearch_summary[1]
{
new pepXML.Generated.msms_pipeline_analysisMsms_run_summarySearch_summary
{
base_name = filePathNoExtension,
//search_engine = pepXML.Generated.engineType.Kojak,
search_engine_version = GlobalVariables.MetaMorpheusVersion,
precursor_mass_type = pepXML.Generated.massType.monoisotopic,
fragment_mass_type = pepXML.Generated.massType.monoisotopic,
search_id = 1,
search_database = new pepXML.Generated.msms_pipeline_analysisMsms_run_summarySearch_summarySearch_database
{
local_path = dbFilenameList[0].FilePath,
type = pepXML.Generated.msms_pipeline_analysisMsms_run_summarySearch_summarySearch_databaseType.AA,
},
enzymatic_search_constraint = new pepXML.Generated.msms_pipeline_analysisMsms_run_summarySearch_summaryEnzymatic_search_constraint
{
enzyme = CommonParameters.DigestionParams.Protease.Name,
max_num_internal_cleavages = CommonParameters.DigestionParams.MaxMissedCleavages.ToString(),
//min_number_termini = "2"
},
parameter = para.ToArray()
}
},
}
};
_pepxml.msms_run_summary[0].spectrum_query = new pepXML.Generated.msms_pipeline_analysisMsms_run_summarySpectrum_query[items.Count];
var searchHits = new List <pepXML.Generated.msms_pipeline_analysisMsms_run_summarySpectrum_querySearch_resultSearch_hit>();
for (int i = 0; i < items.Count; i++)
{
int modsFixedNum = items[i].CompactPeptides.First().Value.Item2.First().allModsOneIsNterminus.Count;
var mods = new List <pepXML.Generated.modInfoDataTypeMod_aminoacid_mass> ();
for (int j = 0; j < modsFixedNum; j++)
{
var mod = new pepXML.Generated.modInfoDataTypeMod_aminoacid_mass
{
mass = items[i].CompactPeptides.First().Value.Item2.First().allModsOneIsNterminus.Values.Select(p => p.monoisotopicMass).ToList()[j],
position = items[i].CompactPeptides.First().Value.Item2.First().allModsOneIsNterminus.Keys.ToList()[j].ToString()
};
mods.Add(mod);
}
if (items[i].CrossType == PsmCrossType.Singe)
{
var searchHit = new pepXML.Generated.msms_pipeline_analysisMsms_run_summarySpectrum_querySearch_resultSearch_hit
{
hit_rank = 1,
peptide = items[i].BaseSequence,
peptide_prev_aa = items[i].CompactPeptides.First().Value.Item2.First().PreviousAminoAcid.ToString(),
peptide_next_aa = items[i].CompactPeptides.First().Value.Item2.First().NextAminoAcid.ToString(),
protein = items[i].CompactPeptides.First().Value.Item2.First().Protein.Accession,
num_tot_proteins = 1,
calc_neutral_pep_mass = (float)items[i].ScanPrecursorMonoisotopicPeakMz * items[i].ScanPrecursorCharge,
massdiff = (items[i].ScanPrecursorMass - items[i].PeptideMonisotopicMass.Value).ToString(),
xlink_typeSpecified = true,
xlink_type = pepXML.Generated.msms_pipeline_analysisMsms_run_summarySpectrum_querySearch_resultSearch_hitXlink_type.na,
modification_info = new pepXML.Generated.modInfoDataType {
mod_aminoacid_mass = mods.ToArray()
},
search_score = new pepXML.Generated.nameValueType[]
{
new pepXML.Generated.nameValueType {
name = "xlTotalScore", value = items[i].XLTotalScore.ToString()
},
new pepXML.Generated.nameValueType {
name = "Qvalue", value = items[i].FdrInfo.QValue.ToString()
}
},
};
searchHits.Add(searchHit);
}
if (items[i].CrossType == PsmCrossType.DeadEnd || items[i].CrossType == PsmCrossType.DeadEndH2O || items[i].CrossType == PsmCrossType.DeadEndNH2 || items[i].CrossType == PsmCrossType.DeadEndTris)
{
double crosslinkerDeadEndMass = 0;
switch (items[i].CrossType)
{
case PsmCrossType.DeadEndNH2:
crosslinkerDeadEndMass = crosslinker.DeadendMassNH2;
break;
case PsmCrossType.DeadEndTris:
crosslinkerDeadEndMass = crosslinker.DeadendMassTris;
break;
default:
crosslinkerDeadEndMass = crosslinker.DeadendMassH2O;
break;
}
var mod = new pepXML.Generated.modInfoDataTypeMod_aminoacid_mass {
mass = crosslinkerDeadEndMass, position = items[i].XlPos.ToString()
};
mods.Add(mod);
var searchHit = new pepXML.Generated.msms_pipeline_analysisMsms_run_summarySpectrum_querySearch_resultSearch_hit
{
hit_rank = 1,
peptide = items[i].BaseSequence,
peptide_prev_aa = items[i].CompactPeptides.First().Value.Item2.First().PreviousAminoAcid.ToString(),
peptide_next_aa = items[i].CompactPeptides.First().Value.Item2.First().NextAminoAcid.ToString(),
protein = items[i].CompactPeptides.First().Value.Item2.First().Protein.Accession,
num_tot_proteins = 1,
calc_neutral_pep_mass = (float)items[i].ScanPrecursorMonoisotopicPeakMz * items[i].ScanPrecursorCharge,
massdiff = (items[i].ScanPrecursorMass - items[i].PeptideMonisotopicMass.Value - crosslinkerDeadEndMass).ToString(),
xlink_typeSpecified = true,
xlink_type = pepXML.Generated.msms_pipeline_analysisMsms_run_summarySpectrum_querySearch_resultSearch_hitXlink_type.na,
modification_info = new pepXML.Generated.modInfoDataType {
mod_aminoacid_mass = mods.ToArray()
},
search_score = new pepXML.Generated.nameValueType[]
{
new pepXML.Generated.nameValueType {
name = "xlTotalScore", value = items[i].XLTotalScore.ToString()
},
new pepXML.Generated.nameValueType {
name = "Qvalue", value = items[i].FdrInfo.QValue.ToString()
}
},
};
searchHits.Add(searchHit);
}
if (items[i].CrossType == PsmCrossType.Inter || items[i].CrossType == PsmCrossType.Intra || items[i].CrossType == PsmCrossType.Cross)
{
int modsFixedNumBeta = items[i].BetaPsmCross.CompactPeptides.First().Value.Item2.First().allModsOneIsNterminus.Count;
var modsBeta = new List <pepXML.Generated.modInfoDataTypeMod_aminoacid_mass>();
for (int j = 0; j < modsFixedNumBeta; j++)
{
var modBeta = new pepXML.Generated.modInfoDataTypeMod_aminoacid_mass
{
mass = items[i].BetaPsmCross.CompactPeptides.First().Value.Item2.First().allModsOneIsNterminus.Values.Select(p => p.monoisotopicMass).ToList()[j],
position = items[i].BetaPsmCross.CompactPeptides.First().Value.Item2.First().allModsOneIsNterminus.Keys.ToList()[j].ToString()
};
modsBeta.Add(modBeta);
}
var alpha = new pepXML.Generated.msms_pipeline_analysisMsms_run_summarySpectrum_querySearch_resultSearch_hitXlinkLinked_peptide
{
peptide = items[i].BaseSequence,
peptide_prev_aa = items[i].CompactPeptides.First().Value.Item2.First().PreviousAminoAcid.ToString(),
peptide_next_aa = items[i].CompactPeptides.First().Value.Item2.First().NextAminoAcid.ToString(),
protein = items[i].CompactPeptides.First().Value.Item2.First().Protein.Accession,
num_tot_proteins = 1,
calc_neutral_pep_mass = (float)items[i].PeptideMonisotopicMass.Value,
complement_mass = (float)(items[i].ScanPrecursorMass - items[i].PeptideMonisotopicMass.Value),
designation = "alpha",
modification_info = new pepXML.Generated.modInfoDataType {
mod_aminoacid_mass = mods.ToArray()
},
xlink_score = new pepXML.Generated.nameValueType[]
{
new pepXML.Generated.nameValueType {
name = "xlscore", value = items[i].XLBestScore.ToString()
},
new pepXML.Generated.nameValueType {
name = "link", value = items[i].XlPos.ToString()
},
}
};
var beta = new pepXML.Generated.msms_pipeline_analysisMsms_run_summarySpectrum_querySearch_resultSearch_hitXlinkLinked_peptide
{
peptide = items[i].BetaPsmCross.BaseSequence,
peptide_prev_aa = items[i].BetaPsmCross.CompactPeptides.First().Value.Item2.First().PreviousAminoAcid.ToString(),
peptide_next_aa = items[i].BetaPsmCross.CompactPeptides.First().Value.Item2.First().NextAminoAcid.ToString(),
protein = items[i].BetaPsmCross.CompactPeptides.First().Value.Item2.First().Protein.Accession,
num_tot_proteins = 1,
calc_neutral_pep_mass = (float)items[i].BetaPsmCross.PeptideMonisotopicMass.Value,
complement_mass = (float)(items[i].ScanPrecursorMass - items[i].PeptideMonisotopicMass.Value),
designation = "beta",
modification_info = new pepXML.Generated.modInfoDataType {
mod_aminoacid_mass = modsBeta.ToArray()
},
xlink_score = new pepXML.Generated.nameValueType[]
{
new pepXML.Generated.nameValueType {
name = "xlscore", value = items[i].BetaPsmCross.XLBestScore.ToString()
},
new pepXML.Generated.nameValueType {
name = "link", value = items[i].BetaPsmCross.XlPos.ToString()
},
}
};
var cross = new pepXML.Generated.msms_pipeline_analysisMsms_run_summarySpectrum_querySearch_resultSearch_hitXlinkLinked_peptide[2] {
alpha, beta
};
var searchHit = new pepXML.Generated.msms_pipeline_analysisMsms_run_summarySpectrum_querySearch_resultSearch_hit
{
hit_rank = 1,
peptide = "-",
peptide_prev_aa = "-",
peptide_next_aa = "-",
protein = "-",
num_tot_proteins = 1,
calc_neutral_pep_mass = (float)items[i].ScanPrecursorMonoisotopicPeakMz * items[i].ScanPrecursorCharge,
massdiff = (items[i].ScanPrecursorMass - items[i].BetaPsmCross.PeptideMonisotopicMass.Value - items[i].PeptideMonisotopicMass.Value - crosslinker.TotalMass).ToString(),
xlink_typeSpecified = true,
xlink_type = pepXML.Generated.msms_pipeline_analysisMsms_run_summarySpectrum_querySearch_resultSearch_hitXlink_type.xl,
xlink = new pepXML.Generated.msms_pipeline_analysisMsms_run_summarySpectrum_querySearch_resultSearch_hitXlink
{
identifier = crosslinker.CrosslinkerName,
mass = (float)crosslinker.TotalMass,
linked_peptide = cross
},
search_score = new pepXML.Generated.nameValueType[]
{
new pepXML.Generated.nameValueType {
name = "xlTotalScore", value = items[i].XLTotalScore.ToString()
},
new pepXML.Generated.nameValueType {
name = "Qvalue", value = items[i].FdrInfo.QValue.ToString()
}
}
};
searchHits.Add(searchHit);
}
if (items[i].CrossType == PsmCrossType.Loop)
{
var thePeptide = new pepXML.Generated.msms_pipeline_analysisMsms_run_summarySpectrum_querySearch_resultSearch_hitXlinkLinked_peptide
{
xlink_score = new pepXML.Generated.nameValueType[]
{
new pepXML.Generated.nameValueType {
name = "link", value = items[i].XlPos.ToString()
},
new pepXML.Generated.nameValueType {
name = "link", value = items[i].XlPos2.ToString()
}
}
};
var cross = new pepXML.Generated.msms_pipeline_analysisMsms_run_summarySpectrum_querySearch_resultSearch_hitXlinkLinked_peptide[1] {
thePeptide
};
var searchHit = new pepXML.Generated.msms_pipeline_analysisMsms_run_summarySpectrum_querySearch_resultSearch_hit
{
hit_rank = 1,
peptide = items[i].BaseSequence,
peptide_prev_aa = items[i].CompactPeptides.First().Value.Item2.First().PreviousAminoAcid.ToString(),
peptide_next_aa = items[i].CompactPeptides.First().Value.Item2.First().NextAminoAcid.ToString(),
protein = items[i].CompactPeptides.First().Value.Item2.First().Protein.Accession,
num_tot_proteins = 1,
calc_neutral_pep_mass = (float)items[i].ScanPrecursorMonoisotopicPeakMz * items[i].ScanPrecursorCharge,
massdiff = (items[i].ScanPrecursorMass - items[i].PeptideMonisotopicMass.Value - crosslinker.LoopMass).ToString(),
xlink_typeSpecified = true,
xlink_type = pepXML.Generated.msms_pipeline_analysisMsms_run_summarySpectrum_querySearch_resultSearch_hitXlink_type.loop,
modification_info = new pepXML.Generated.modInfoDataType {
mod_aminoacid_mass = mods.ToArray()
},
xlink = new pepXML.Generated.msms_pipeline_analysisMsms_run_summarySpectrum_querySearch_resultSearch_hitXlink
{
identifier = crosslinker.CrosslinkerName,
mass = (float)crosslinker.TotalMass,
linked_peptide = cross
},
search_score = new pepXML.Generated.nameValueType[]
{
new pepXML.Generated.nameValueType {
name = "xlTotalScore", value = items[i].XLTotalScore.ToString()
},
new pepXML.Generated.nameValueType {
name = "Qvalue", value = items[i].FdrInfo.QValue.ToString()
}
}
};
searchHits.Add(searchHit);
}
}
for (int i = 0; i < items.Count; i++)
{
_pepxml.msms_run_summary[0].spectrum_query[i] = new pepXML.Generated.msms_pipeline_analysisMsms_run_summarySpectrum_query()
{
spectrum = fileNameNoExtension + "." + items[i].ScanNumber.ToString(),
start_scan = Convert.ToUInt32(items[i].ScanNumber),
end_scan = Convert.ToUInt32(items[i].ScanNumber),
precursor_neutral_mass = (float)items[i].ScanPrecursorMonoisotopicPeakMz * items[i].ScanPrecursorCharge,
assumed_charge = items[i].ScanPrecursorCharge.ToString(),
index = Convert.ToUInt32(i + 1),
retention_time_sec = (float)items[i].ScanRetentionTime,
search_result = new pepXML.Generated.msms_pipeline_analysisMsms_run_summarySpectrum_querySearch_result[1]
{
new pepXML.Generated.msms_pipeline_analysisMsms_run_summarySpectrum_querySearch_result
{
search_hit = new pepXML.Generated.msms_pipeline_analysisMsms_run_summarySpectrum_querySearch_resultSearch_hit[1]
{
searchHits[i]
}
}
}
};
}
#endregion Add element to pepXML
TextWriter writer = new StreamWriter(Path.Combine(outputFolder, fileName + ".pep.xml"));
_indexedSerializer.Serialize(writer, _pepxml);
writer.Close();
SucessfullyFinishedWritingFile(Path.Combine(outputFolder, fileName + ".pep.xml"), nestedIds);
}
private void WriteCrosslinkToTxtForPercolator(List <PsmCross> items, string outputFolder, string fileName, CrosslinkerTypeClass crosslinker, List <string> nestedIds)
{
var writtenFile = Path.Combine(outputFolder, fileName + ".txt");
using (StreamWriter output = new StreamWriter(writtenFile))
{
output.WriteLine("SpecId\tLabel\tScannr\tScore\tdScore\tNormRank\tCharge\tMass\tPPM\tLenShort\tLenLong\tLenSum" +
"\tPeptide\tProtein");
foreach (var item in items)
{
if (item.BaseSequence != null && item.BetaPsmCross.BaseSequence != null && item.ProteinAccesion != null && item.BetaPsmCross.ProteinAccesion != null)
{
string x = "T"; int label = 1;
if (item.IsDecoy || item.BetaPsmCross.IsDecoy)
{
x = "D"; label = -1;
}
output.WriteLine(
x + "-" + item.ScanNumber.ToString(CultureInfo.InvariantCulture) + "-" + item.ScanRetentionTime.ToString(CultureInfo.InvariantCulture)
+ "\t" + label.ToString(CultureInfo.InvariantCulture)
+ "\t" + item.ScanNumber.ToString(CultureInfo.InvariantCulture)
+ "\t" + item.XLTotalScore.ToString(CultureInfo.InvariantCulture)
+ "\t" + item.DScore.ToString(CultureInfo.InvariantCulture)
+ "\t" + (item.XlRank[0] + item.XlRank[1]).ToString(CultureInfo.InvariantCulture)
+ "\t" + item.ScanPrecursorCharge.ToString(CultureInfo.InvariantCulture)
+ "\t" + item.ScanPrecursorMass.ToString(CultureInfo.InvariantCulture)
+ "\t" + ((item.PeptideMonisotopicMass.HasValue && item.BetaPsmCross.PeptideMonisotopicMass.HasValue) ? ((item.ScanPrecursorMass - item.BetaPsmCross.PeptideMonisotopicMass.Value - item.PeptideMonisotopicMass.Value - crosslinker.TotalMass) / item.ScanPrecursorMass * 1E6).ToString(CultureInfo.InvariantCulture) : "---")
+ "\t" + item.BetaPsmCross.BaseSequence.Length.ToString(CultureInfo.InvariantCulture)
+ "\t" + item.BaseSequence.Length.ToString(CultureInfo.InvariantCulture)
+ "\t" + (item.BetaPsmCross.BaseSequence.Length + item.BaseSequence.Length).ToString(CultureInfo.InvariantCulture)
+ "\t" + "-." + item.BaseSequence + item.XlPos.ToString(CultureInfo.InvariantCulture) + "--" + item.BetaPsmCross.BaseSequence + item.BetaPsmCross.XlPos.ToString(CultureInfo.InvariantCulture) + ".-"
+ "\t" + item.CompactPeptides.First().Value.Item2.Select(p => p.Protein.Accession).First().ToString(CultureInfo.InvariantCulture)
+ "(" + item.XlProteinPos.ToString(CultureInfo.InvariantCulture) + ")"
+ "\t" + item.BetaPsmCross.CompactPeptides.First().Value.Item2.Select(p => p.Protein.Accession).First().ToString(CultureInfo.InvariantCulture)
+ "(" + item.BetaPsmCross.XlProteinPos.ToString(CultureInfo.InvariantCulture) + ")"
);
}
}
}
SucessfullyFinishedWritingFile(writtenFile, nestedIds);
}
public static void XlTestLocalization()
{
var CommonParameters = new CommonParameters();
var proteinList = new List <Protein> {
new Protein("CASIQKFGERLCVLHEKTPVSEK", null)
};
ModificationMotif.TryGetMotif("M", out ModificationMotif motif1);
ModificationWithMass mod1 = new ModificationWithMass("Oxidation of M", "Common Variable", motif1, TerminusLocalization.Any, 15.99491461957);
ModificationMotif.TryGetMotif("C", out ModificationMotif motif2);
ModificationWithMass mod2 = new ModificationWithMass("Carbamidomethyl of C", "Common Fixed", motif2, TerminusLocalization.Any, 57.02146372068994);
var variableModifications = new List <ModificationWithMass>()
{
mod1
};
var fixedModifications = new List <ModificationWithMass>()
{
mod2
};
var localizeableModifications = new List <ModificationWithMass>();
var lp = new List <ProductType> {
ProductType.BnoB1ions, ProductType.Y
};
Dictionary <ModificationWithMass, ushort> modsDictionary = new Dictionary <ModificationWithMass, ushort>();
foreach (var mod in fixedModifications)
{
modsDictionary.Add(mod, 0);
}
int i = 1;
foreach (var mod in variableModifications)
{
modsDictionary.Add(mod, (ushort)i);
i++;
}
foreach (var mod in localizeableModifications)
{
modsDictionary.Add(mod, (ushort)i);
i++;
}
var engine = new IndexingEngine(proteinList, variableModifications, fixedModifications, lp, 1, DecoyType.Reverse, new List <IDigestionParams> {
CommonParameters.DigestionParams
}, CommonParameters, 30000, new List <string>());
var results = (IndexingResults)engine.Run();
var digestedList = proteinList[0].Digest(CommonParameters.DigestionParams, fixedModifications, variableModifications).ToList();
foreach (var fdfd in digestedList)
{
fdfd.CompactPeptide(TerminusType.None);
//Assert.Contains(fdfd.CompactPeptide(TerminusType.None), results.PeptideIndex);
}
var productMasses = digestedList[3].CompactPeptide(TerminusType.None).ProductMassesMightHaveDuplicatesAndNaNs(new List <ProductType> {
ProductType.B, ProductType.Y
});
CrosslinkerTypeClass crosslinker = new CrosslinkerTypeClass();
crosslinker.SelectCrosslinker(CrosslinkerType.DSS);
var x = PsmCross.XlPosCal(digestedList[3].CompactPeptide(TerminusType.None), crosslinker).ToArray();
Assert.AreEqual(x[0], 5);
var myMsDataFile = new XLTestDataFile();
var listOfSortedms2Scans = MetaMorpheusTask.GetMs2Scans(myMsDataFile, null, CommonParameters.DoPrecursorDeconvolution, CommonParameters.UseProvidedPrecursorInfo, CommonParameters.DeconvolutionIntensityRatio, CommonParameters.DeconvolutionMaxAssumedChargeState, CommonParameters.DeconvolutionMassTolerance).OrderBy(b => b.PrecursorMass).ToArray();
var psmCrossAlpha = new PsmCross(digestedList[3].CompactPeptide(TerminusType.None), 0, 0, i, listOfSortedms2Scans[0]);
var psmCrossBeta = new PsmCross(digestedList[5].CompactPeptide(TerminusType.None), 0, 0, i, listOfSortedms2Scans[0]);
var modMassAlpha1 = psmCrossBeta.compactPeptide.MonoisotopicMassIncludingFixedMods + crosslinker.TotalMass;
//Another method to calculate modification mass of cross-linked peptides
//var modMassAlpha2 = listOfSortedms2Scans[0].PrecursorMass - psmCrossAlpha.compactPeptide.MonoisotopicMassIncludingFixedMods;
var linkPos = PsmCross.XlPosCal(psmCrossAlpha.compactPeptide, crosslinker);
var productMassesAlphaList = PsmCross.XlCalculateTotalProductMasses(psmCrossAlpha, modMassAlpha1, crosslinker, lp, true, false, linkPos);
Assert.AreEqual(productMassesAlphaList[0].ProductMz.Length, 35);
Assert.AreEqual(productMassesAlphaList[0].ProductMz[26], 2312.21985342336);
}
