public static void RemoveAmbiguousPeptides()
{
var variableModifications = new List <Modification>();
var fixedModifications = new List <Modification>();
var origDataFile = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestData\TaGe_SA_HeLa_04_subset_longestSeq.mzML");
MyFileManager myFileManager = new MyFileManager(true);
CommonParameters CommonParameters = new CommonParameters(digestionParams: new DigestionParams());
var myMsDataFile = myFileManager.LoadFile(origDataFile, CommonParameters);
var searchModes = new SinglePpmAroundZeroSearchMode(5);
List <Protein> proteinList = ProteinDbLoader.LoadProteinFasta(Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestData\hela_snip_for_unitTest.fasta"), true, DecoyType.Reverse, false, ProteinDbLoader.UniprotAccessionRegex, ProteinDbLoader.UniprotFullNameRegex, ProteinDbLoader.UniprotFullNameRegex, ProteinDbLoader.UniprotGeneNameRegex,
ProteinDbLoader.UniprotOrganismRegex, out var dbErrors, -1);
var listOfSortedms2Scans = MetaMorpheusTask.GetMs2Scans(myMsDataFile, @"TestData\TaGe_SA_HeLa_04_subset_longestSeq.mzML", CommonParameters).OrderBy(b => b.PrecursorMass).ToArray();
PeptideSpectralMatch[] allPsmsArray = new PeptideSpectralMatch[listOfSortedms2Scans.Length];
new ClassicSearchEngine(allPsmsArray, listOfSortedms2Scans, variableModifications, fixedModifications, null, null, null, proteinList, searchModes, CommonParameters, new List <string>()).Run();
var nonNullPsms = allPsmsArray.Where(p => p != null).ToList();
nonNullPsms.OrderByDescending(p => p.Score);
var maxScore = nonNullPsms.Select(n => n.Score).Max();
PeptideSpectralMatch maxScorePsm = nonNullPsms.Where(n => n.Score == maxScore).First();
Protein newProteinToRemove = new Protein("RREMVE", "BUBBA", isDecoy: false);
PeptideWithSetModifications pwsmToRemove = new PeptideWithSetModifications(newProteinToRemove, new DigestionParams(), 1, 6, CleavageSpecificity.Full, "peptideDescription", 2, new Dictionary <int, Modification>(), 1, "RREMVE");
maxScorePsm.AddOrReplace(pwsmToRemove, maxScore, 1, true, maxScorePsm.MatchedFragmentIons, maxScore);
maxScorePsm.ResolveAllAmbiguities();
List <PeptideSpectralMatch> psmBloated = new List <PeptideSpectralMatch>();
psmBloated.AddRange(nonNullPsms);
psmBloated.AddRange(nonNullPsms.GetRange(0, nonNullPsms.Count - 2));
foreach (PeptideSpectralMatch psm in nonNullPsms.GetRange(0, nonNullPsms.Count - 2))
{
Protein newDecoyProtein = new Protein(psm.BestMatchingPeptides.First().Peptide.BaseSequence + "K", "DECOY_" + psm.BestMatchingPeptides.First().Peptide.Protein.Accession, isDecoy: true);
PeptideWithSetModifications pwsmDecoy = new PeptideWithSetModifications(newDecoyProtein, new DigestionParams(), 1, psm.BestMatchingPeptides.First().Peptide.BaseSequence.Length + 1, CleavageSpecificity.Full, "peptideDescription", 2, new Dictionary <int, Modification>(), 1, psm.BestMatchingPeptides.First().Peptide.BaseSequence + "K");
PeptideSpectralMatch decoyPsm = new PeptideSpectralMatch(pwsmDecoy, 1, psm.Score, psm.ScanIndex, listOfSortedms2Scans[psm.ScanIndex], new DigestionParams(), psm.MatchedFragmentIons);
decoyPsm.ResolveAllAmbiguities();
psmBloated.Add(decoyPsm);
}
PeptideSpectralMatch oldBloatedMaxScorePsm = psmBloated.Where(n => n.Score == maxScore).First();
int countOfBestPeptidesBloatedMax = oldBloatedMaxScorePsm.BestMatchingPeptides.Count();
FdrAnalysisResults fdrResultsClassicDelta = (FdrAnalysisResults)(new FdrAnalysisEngine(psmBloated.Where(p => p != null).ToList(), 1, CommonParameters, new List <string>()).Run());
PeptideSpectralMatch newMaxScorePsm = psmBloated.Where(n => n.Score == maxScore).First();
Assert.AreEqual(countOfBestPeptidesBloatedMax - 1, newMaxScorePsm.BestMatchingPeptides.Count());
}
public static void TestRemoveThisAmbiguousePeptide()
{
Ms2ScanWithSpecificMass scanB = new Ms2ScanWithSpecificMass(
new MsDataScan(
new MzSpectrum(new double[] { }, new double[] { }, false),
2, 1, true, Polarity.Positive, double.NaN, null, null, MZAnalyzerType.Orbitrap, double.NaN, null, null, "scan=1", double.NaN, null, null, double.NaN, null, DissociationType.AnyActivationType, 1, null),
100, 1, null, new CommonParameters(), null);
PeptideSpectralMatch psm1 = new PeptideSpectralMatch(new PeptideWithSetModifications(new Protein("PEPTIDE", "ACCESSION", "ORGANISM"), new DigestionParams(), 1, 2, CleavageSpecificity.Full, "", 0, new Dictionary <int, Modification>(), 0), 0, 10, 1, scanB, new DigestionParams(), new List <MatchedFragmentIon>(), 0);
PeptideWithSetModifications pwsm = new PeptideWithSetModifications(new Protein("PEPTIDE", "ACCESSION", "ORGANISM"), new DigestionParams(), 1, 2, CleavageSpecificity.Full, "", 0, new Dictionary <int, Modification>(), 0);
psm1.AddOrReplace(pwsm, 10, 1, true, new List <MatchedFragmentIon>(), 0);
Assert.AreEqual(2, psm1.BestMatchingPeptides.Count());
psm1.RemoveThisAmbiguousPeptide(1, pwsm);
Assert.AreEqual(1, psm1.BestMatchingPeptides.Count());
}
public static void FdrTestMethod()
{
MassDiffAcceptor searchModes = new DotMassDiffAcceptor(null, new List <double> {
0, 1.0029
}, new PpmTolerance(5));
List <string> nestedIds = new List <string>();
Protein p = new Protein("MNKNNKNNNKNNNNK", null);
DigestionParams digestionParams = new DigestionParams();
var digested = p.Digest(digestionParams, new List <Modification>(), new List <Modification>()).ToList();
PeptideWithSetModifications pep1 = digested[0];
PeptideWithSetModifications pep2 = digested[1];
PeptideWithSetModifications pep3 = digested[2];
PeptideWithSetModifications pep4 = digested[3];
TestDataFile t = new TestDataFile(new List <PeptideWithSetModifications> {
pep1, pep2, pep3
});
MsDataScan mzLibScan1 = t.GetOneBasedScan(2);
Ms2ScanWithSpecificMass scan1 = new Ms2ScanWithSpecificMass(mzLibScan1, pep1.MonoisotopicMass.ToMz(1), 1, null, new CommonParameters());
PeptideSpectralMatch psm1 = new PeptideSpectralMatch(pep1, 0, 3, 0, scan1, digestionParams, new List <MatchedFragmentIon>());
MsDataScan mzLibScan2 = t.GetOneBasedScan(4);
Ms2ScanWithSpecificMass scan2 = new Ms2ScanWithSpecificMass(mzLibScan2, pep2.MonoisotopicMass.ToMz(1), 1, null, new CommonParameters());
PeptideSpectralMatch psm2 = new PeptideSpectralMatch(pep2, 1, 2, 1, scan2, digestionParams, new List <MatchedFragmentIon>());
MsDataScan mzLibScan3 = t.GetOneBasedScan(6);
Ms2ScanWithSpecificMass scan3 = new Ms2ScanWithSpecificMass(mzLibScan3, pep3.MonoisotopicMass.ToMz(1), 1, null, new CommonParameters());
PeptideSpectralMatch psm3 = new PeptideSpectralMatch(pep3, 0, 1, 2, scan3, digestionParams, new List <MatchedFragmentIon>());
psm3.AddOrReplace(pep4, 1, 1, true, new List <MatchedFragmentIon>(), 0);
var newPsms = new List <PeptideSpectralMatch> {
psm1, psm2, psm3
};
foreach (PeptideSpectralMatch psm in newPsms)
{
psm.ResolveAllAmbiguities();
}
FdrAnalysisEngine fdr = new FdrAnalysisEngine(newPsms, searchModes.NumNotches, new CommonParameters(), nestedIds);
fdr.Run();
Assert.AreEqual(2, searchModes.NumNotches);
Assert.AreEqual(0, newPsms[0].FdrInfo.CumulativeDecoyNotch);
Assert.AreEqual(1, newPsms[0].FdrInfo.CumulativeTargetNotch);
Assert.AreEqual(0, newPsms[1].FdrInfo.CumulativeDecoyNotch);
Assert.AreEqual(1, newPsms[1].FdrInfo.CumulativeTargetNotch);
Assert.AreEqual(0, newPsms[2].FdrInfo.CumulativeDecoyNotch);
Assert.AreEqual(1, newPsms[2].FdrInfo.CumulativeTargetNotch);
Assert.AreEqual(0, newPsms[0].FdrInfo.CumulativeDecoy);
Assert.AreEqual(1, newPsms[0].FdrInfo.CumulativeTarget);
Assert.AreEqual(0, newPsms[1].FdrInfo.CumulativeDecoy);
Assert.AreEqual(2, newPsms[1].FdrInfo.CumulativeTarget);
Assert.AreEqual(0, newPsms[2].FdrInfo.CumulativeDecoy);
Assert.AreEqual(3, newPsms[2].FdrInfo.CumulativeTarget);
}
public static void TestModificationAnalysisWithNonLocalizedPtms()
{
IScan scan = new ThisTestScan();
ModificationMotif.TryGetMotif("N", out ModificationMotif motif1);
Modification mod1 = new Modification(_originalId: "mod1", _modificationType: "mt", _target: motif1, _locationRestriction: "Anywhere.", _monoisotopicMass: 10, _neutralLosses: new Dictionary <DissociationType, List <double> > {
{ MassSpectrometry.DissociationType.AnyActivationType, new List <double> {
10
} }
});
IDictionary <int, List <Modification> > oneBasedModifications = new Dictionary <int, List <Modification> >
{
{ 2, new List <Modification> {
mod1
} },
{ 7, new List <Modification> {
mod1
} },
};
Protein protein1 = new Protein("MNLDLDNDL", "prot1", oneBasedModifications: oneBasedModifications);
Dictionary <int, Modification> allModsOneIsNterminus1 = new Dictionary <int, Modification>
{
{ 2, mod1 },
};
PeptideWithSetModifications pwsm1 = new PeptideWithSetModifications(protein1, new DigestionParams(), 2, 9, CleavageSpecificity.Unknown, null, 0, allModsOneIsNterminus1, 0);
Dictionary <int, Modification> allModsOneIsNterminus3 = new Dictionary <int, Modification>
{
{ 7, mod1 },
};
PeptideWithSetModifications pwsm2 = new PeptideWithSetModifications(protein1, new DigestionParams(), 2, 9, CleavageSpecificity.Unknown, null, 0, allModsOneIsNterminus3, 0);
CommonParameters CommonParameters = new CommonParameters(digestionParams: new DigestionParams(maxMissedCleavages: 0, minPeptideLength: 1), scoreCutoff: 1);
PeptideSpectralMatch myPsm = new PeptideSpectralMatch(pwsm1, 0, 10, 0, scan, new DigestionParams(), new List <MatchedFragmentIon>());
myPsm.AddOrReplace(pwsm2, 10, 0, true, new List <MatchedFragmentIon>(), 0);
myPsm.ResolveAllAmbiguities();
MassDiffAcceptor searchMode = new SinglePpmAroundZeroSearchMode(5);
List <Protein> proteinList = new List <Protein> {
protein1
};
FdrAnalysisEngine fdrAnalysisEngine = new FdrAnalysisEngine(new List <PeptideSpectralMatch> {
myPsm
}, searchMode.NumNotches, CommonParameters, new List <string>());
fdrAnalysisEngine.Run();
ModificationAnalysisEngine modificationAnalysisEngine = new ModificationAnalysisEngine(new List <PeptideSpectralMatch> {
myPsm
}, new CommonParameters(), new List <string>());
var res = (ModificationAnalysisResults)modificationAnalysisEngine.Run();
Assert.AreEqual(1, res.CountOfEachModSeenOnProteins.Count());
Assert.AreEqual(2, res.CountOfEachModSeenOnProteins[mod1.IdWithMotif]);
Assert.AreEqual(0, res.CountOfModsSeenAndLocalized.Count());
Assert.AreEqual(0, res.CountOfAmbiguousButLocalizedModsSeen.Count);
Assert.AreEqual(1, res.CountOfUnlocalizedMods[mod1.IdWithMotif]); // Saw it, but not sure where!
Assert.AreEqual(0, res.CountOfUnlocalizedFormulas.Count());
}
public static void FdrTestMethod()
{
MassDiffAcceptor searchModes = new DotMassDiffAcceptor(null, new List <double> {
0, 1.0029
}, new PpmTolerance(5));
List <string> nestedIds = new List <string>();
Protein p = new Protein("MNKNNKNNNKNNNNK", null);
DigestionParams digestionParams = new DigestionParams();
var digested = p.Digest(digestionParams, new List <ModificationWithMass>(), new List <ModificationWithMass>()).ToList();
PeptideWithSetModifications pep1 = digested[0];
PeptideWithSetModifications pep2 = digested[1];
PeptideWithSetModifications pep3 = digested[2];
PeptideWithSetModifications pep4 = digested[3];
TestDataFile t = new TestDataFile(new List <PeptideWithSetModifications> {
pep1, pep2, pep3
});
CompactPeptide peptide1 = new CompactPeptide(pep1, TerminusType.None);
IMsDataScanWithPrecursor <IMzSpectrum <IMzPeak> > mzLibScan1 = t.GetOneBasedScan(2) as IMsDataScanWithPrecursor <IMzSpectrum <IMzPeak> >;
Ms2ScanWithSpecificMass scan1 = new Ms2ScanWithSpecificMass(mzLibScan1, peptide1.MonoisotopicMassIncludingFixedMods.ToMz(1), 1, null);
PeptideSpectralMatch psm1 = new PeptideSpectralMatch(peptide1, 0, 3, 0, scan1);
CompactPeptide peptide2 = new CompactPeptide(pep2, TerminusType.None);
IMsDataScanWithPrecursor <IMzSpectrum <IMzPeak> > mzLibScan2 = t.GetOneBasedScan(4) as IMsDataScanWithPrecursor <IMzSpectrum <IMzPeak> >;
Ms2ScanWithSpecificMass scan2 = new Ms2ScanWithSpecificMass(mzLibScan2, peptide2.MonoisotopicMassIncludingFixedMods.ToMz(1), 1, null);
PeptideSpectralMatch psm2 = new PeptideSpectralMatch(peptide2, 1, 2, 1, scan2);
CompactPeptide peptide3 = new CompactPeptide(pep3, TerminusType.None);
IMsDataScanWithPrecursor <IMzSpectrum <IMzPeak> > mzLibScan3 = t.GetOneBasedScan(6) as IMsDataScanWithPrecursor <IMzSpectrum <IMzPeak> >;
Ms2ScanWithSpecificMass scan3 = new Ms2ScanWithSpecificMass(mzLibScan3, peptide3.MonoisotopicMassIncludingFixedMods.ToMz(1), 1, null);
PeptideSpectralMatch psm3 = new PeptideSpectralMatch(peptide3, 0, 1, 2, scan3);
CompactPeptide peptide4 = new CompactPeptide(pep4, TerminusType.None);
psm3.AddOrReplace(peptide4, 1, 1, true);
Dictionary <CompactPeptideBase, HashSet <PeptideWithSetModifications> > matching = new Dictionary <CompactPeptideBase, HashSet <PeptideWithSetModifications> >
{
{
peptide1, new HashSet <PeptideWithSetModifications> {
pep1
}
},
{
peptide2, new HashSet <PeptideWithSetModifications> {
pep2
}
},
{
peptide3, new HashSet <PeptideWithSetModifications> {
pep3
}
},
{
peptide4, new HashSet <PeptideWithSetModifications> {
pep4
}
},
};
psm1.MatchToProteinLinkedPeptides(matching);
psm2.MatchToProteinLinkedPeptides(matching);
psm3.MatchToProteinLinkedPeptides(matching);
var newPsms = new List <PeptideSpectralMatch> {
psm1, psm2, psm3
};
FdrAnalysisEngine fdr = new FdrAnalysisEngine(newPsms, searchModes.NumNotches, true, nestedIds);
fdr.Run();
Assert.AreEqual(2, searchModes.NumNotches);
Assert.AreEqual(0, newPsms[0].FdrInfo.CumulativeDecoyNotch);
Assert.AreEqual(1, newPsms[0].FdrInfo.CumulativeTargetNotch);
Assert.AreEqual(0, newPsms[1].FdrInfo.CumulativeDecoyNotch);
Assert.AreEqual(1, newPsms[1].FdrInfo.CumulativeTargetNotch);
Assert.AreEqual(0, newPsms[2].FdrInfo.CumulativeDecoyNotch);
Assert.AreEqual(1, newPsms[2].FdrInfo.CumulativeTargetNotch);
Assert.AreEqual(0, newPsms[0].FdrInfo.CumulativeDecoy);
Assert.AreEqual(1, newPsms[0].FdrInfo.CumulativeTarget);
Assert.AreEqual(0, newPsms[1].FdrInfo.CumulativeDecoy);
Assert.AreEqual(2, newPsms[1].FdrInfo.CumulativeTarget);
Assert.AreEqual(0, newPsms[2].FdrInfo.CumulativeDecoy);
Assert.AreEqual(3, newPsms[2].FdrInfo.CumulativeTarget);
}
public static void ResolveModificationsTest()
{
double mass = 12.0 + new PeptideWithSetModifications(new Protein("LNLDLDND", "prot1"), new DigestionParams(), 1, 8, CleavageSpecificity.Full, "", 0, new Dictionary <int, Modification>(), 0, null).MonoisotopicMass.ToMz(1);
Ms2ScanWithSpecificMass scan = new Ms2ScanWithSpecificMass(new MsDataScan(new MzSpectrum(new double[, ] {
}), 0, 0, true, Polarity.Positive,
0, new MzLibUtil.MzRange(0, 0), "", MZAnalyzerType.FTICR, 0, null, null, ""), mass, 1, "", new CommonParameters());
ModificationMotif.TryGetMotif("N", out ModificationMotif motif1);
Dictionary <DissociationType, List <double> > NeutralLosses = new Dictionary <DissociationType, List <double> >();
NeutralLosses.Add(DissociationType.HCD, new List <double> {
0
});
Modification modFormula_C1 = new Modification(_originalId: "modC", _accession: "", _modificationType: "mt", _featureType: "", _target: motif1, _locationRestriction: "Anywhere.", _chemicalFormula: new ChemicalFormula(ChemicalFormula.ParseFormula("C1")), null, null, null, null, _neutralLosses: NeutralLosses, null, null);
Modification modFormula_H1 = new Modification(_originalId: "modH", _accession: "", _modificationType: "mt", _featureType: "", _target: motif1, _locationRestriction: "Anywhere.", _chemicalFormula: new ChemicalFormula(ChemicalFormula.ParseFormula("H1")), null, null, null, null, _neutralLosses: NeutralLosses, null, null);
IDictionary <int, List <Modification> > oneBasedModifications = new Dictionary <int, List <Modification> >
{
{ 2, new List <Modification> {
modFormula_C1, modFormula_H1
} },
};
Protein protein1 = new Protein("MNLDLDNDL", "prot1", oneBasedModifications: oneBasedModifications);
Dictionary <int, Modification> allModsOneIsNterminus1 = new Dictionary <int, Modification>
{
{ 2, modFormula_C1 },
};
PeptideWithSetModifications pwsm1 = new PeptideWithSetModifications(protein1, new DigestionParams(), 2, 9, CleavageSpecificity.Unknown, null, 0, allModsOneIsNterminus1, 0);
Dictionary <int, Modification> allModsOneIsNterminus2 = new Dictionary <int, Modification>
{
{ 2, modFormula_H1 },
};
PeptideWithSetModifications pwsm2 = new PeptideWithSetModifications(protein1, new DigestionParams(), 2, 9, CleavageSpecificity.Unknown, null, 0, allModsOneIsNterminus2, 0);
CommonParameters CommonParameters = new CommonParameters(digestionParams: new DigestionParams(maxMissedCleavages: 0, minPeptideLength: 1), scoreCutoff: 1);
var fsp = new List <(string fileName, CommonParameters fileSpecificParameters)>();
fsp.Add(("", CommonParameters));
List <MatchedFragmentIon> mfi = new List <MatchedFragmentIon>();
//we're adding a neutral loss of 5 to the product to make sure we hit the right spot in the unit test to add that loss to the product ion string
Product p = new Product(ProductType.b, FragmentationTerminus.N, 1, 1, 1, 5);
mfi.Add(new MatchedFragmentIon(ref p, 1, 1, 1));
PeptideSpectralMatch myPsm = new PeptideSpectralMatch(pwsm1, 0, 10, 0, scan, new CommonParameters(), mfi);
myPsm.AddOrReplace(pwsm2, 10, 0, true, mfi, 10);
myPsm.ResolveAllAmbiguities();
//Here we have a situation where there are two mods at the same position with different chemical formuala. They cannot be resolved and so the return value is null.
Assert.IsNull(myPsm.ModsChemicalFormula);
string myPsmString = myPsm.ToString();
string[] myPsmStringSplit = myPsmString.Split('\t');
string ppmErrorString = myPsmStringSplit[23];
//The two different mods produce two separate mass errors, which are both then reported
Assert.AreEqual("0.00|11801.30", ppmErrorString);
//Make sure we see produt ion neutral losses in the output.
string matchedIonSeries = myPsmStringSplit[38];
Assert.AreEqual("[(b1-5.00)+1]", matchedIonSeries);
//removing one of the peptides to reset for the next test
myPsm.RemoveThisAmbiguousPeptide(0, pwsm2);
PeptideWithSetModifications pwsm3 = new PeptideWithSetModifications(protein1, new DigestionParams(), 2, 9, CleavageSpecificity.Unknown, null, 0, allModsOneIsNterminus1, 0);
myPsm.AddOrReplace(pwsm3, 10, 0, true, mfi, 10);
myPsm.ResolveAllAmbiguities();
//Now we have removed one of the peptides with a different chemical formual and replaced it with a mod that has the same chemical formula as the remaining original best peptide
//Here we have a situation where there are two mods at the same position have the same chemical formuala and they can be resolved and so the return value the chemical formual of the mod.
Assert.AreEqual("C", myPsm.ModsChemicalFormula.Formula.ToString());
myPsmString = myPsm.ToString();
myPsmStringSplit = myPsmString.Split('\t');
ppmErrorString = myPsmStringSplit[23];
Assert.AreEqual("0.00", ppmErrorString);
}
