public static void TestCombos()
{
List <PeptideSpectralMatch> allIdentifications = null;
ModificationMotif.TryGetMotif("N", out ModificationMotif motifN);
ModificationMotif.TryGetMotif("P", out ModificationMotif motifP);
var gptmdModifications = new List <ModificationWithMass> {
new ModificationWithMass("21", "mt", motifN, TerminusLocalization.Any, 21.981943, null),
new ModificationWithMass("16", "mt", motifP, TerminusLocalization.Any, 15.994915, null)
};
IEnumerable <Tuple <double, double> > combos = new List <Tuple <double, double> > {
new Tuple <double, double>(21.981943, 15.994915)
};
Tolerance precursorMassTolerance = new PpmTolerance(10);
MsDataScan dfd = new MsDataScan(new MzSpectrum(new double[] { 1 }, new double[] { 1 }, false), 0, 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, 0, null);
Ms2ScanWithSpecificMass scan = new Ms2ScanWithSpecificMass(dfd, (651.297638557 + 21.981943 + 15.994915).ToMz(1), 1, "filepath");
var parentProtein = new Protein("NNNPPP", "accession");
DigestionParams digestionParams = new DigestionParams(minPeptideLength: 5);
List <ModificationWithMass> variableModifications = new List <ModificationWithMass>();
var modPep = parentProtein.Digest(digestionParams, new List <ModificationWithMass>(), variableModifications).First();
var peptidesWithSetModifications = new List <PeptideWithSetModifications> {
modPep
};
PeptideSpectralMatch match = new PeptideSpectralMatch(peptidesWithSetModifications.First().CompactPeptide(TerminusType.None), 0, 0, 0, scan, digestionParams);
PeptideSpectralMatch newPsm = new PeptideSpectralMatch(peptidesWithSetModifications.First().CompactPeptide(TerminusType.None), 0, 0, 0, scan, digestionParams);
Dictionary <ModificationWithMass, ushort> modsDictionary = new Dictionary <ModificationWithMass, ushort>();
Dictionary <CompactPeptideBase, HashSet <PeptideWithSetModifications> > matching = new Dictionary <CompactPeptideBase, HashSet <PeptideWithSetModifications> >
{
{ peptidesWithSetModifications.First().CompactPeptide(TerminusType.None), new HashSet <PeptideWithSetModifications> {
peptidesWithSetModifications.First()
} }
};
List <ProductType> lp = new List <ProductType> {
ProductType.B, ProductType.Y
};
Tolerance fragmentTolerance = new AbsoluteTolerance(0.01);
match.MatchToProteinLinkedPeptides(matching);
match.SetFdrValues(1, 0, 0, 1, 0, 0, 0, 0, 0, false);
allIdentifications = new List <PeptideSpectralMatch> {
match
};
var engine = new GptmdEngine(allIdentifications, gptmdModifications, combos, new Dictionary <string, Tolerance> {
{ "filepath", precursorMassTolerance }
}, new CommonParameters(), new List <string>());
var res = (GptmdResults)engine.Run();
Assert.AreEqual(1, res.Mods.Count);
Assert.AreEqual(6, res.Mods["accession"].Count);
Assert.AreEqual(3, res.Mods["accession"].Where(b => b.Item2.id.Equals("21")).Count());
Assert.AreEqual(3, res.Mods["accession"].Where(b => b.Item2.id.Equals("16")).Count());
}
public static void TestPsmHeader()
{
DigestionParams digestionParams = new DigestionParams();
PeptideWithSetModifications pepWithSetMods = new Protein(
"MQQQQQQQ",
"accession1",
"org",
new List <Tuple <string, string> > {
new Tuple <string, string>("geneNameType", "geneName")
},
new Dictionary <int, List <Modification> > {
{ 2, new List <Modification> {
new Modification("mod", "mod")
} }
},
name: "name",
full_name: "fullName",
sequenceVariations: new List <SequenceVariation> {
new SequenceVariation(2, "P", "Q", "changed this sequence")
})
.Digest(digestionParams, new List <ModificationWithMass>(), new List <ModificationWithMass>()).First();
MsDataFile myMsDataFile = new TestDataFile(pepWithSetMods, "quadratic");
MsDataScan scann = myMsDataFile.GetOneBasedScan(2);
Ms2ScanWithSpecificMass scan = new Ms2ScanWithSpecificMass(scann, 4, 1, null);
PeptideSpectralMatch psm = new PeptideSpectralMatch(pepWithSetMods.CompactPeptide(TerminusType.None), 1, 2, 3, scan, digestionParams);
var t = psm.ToString();
var tabsepheader = PeptideSpectralMatch.GetTabSeparatedHeader();
Assert.AreEqual(psm.ToString().Count(f => f == '\t'), PeptideSpectralMatch.GetTabSeparatedHeader().Count(f => f == '\t'));
Dictionary <CompactPeptideBase, HashSet <PeptideWithSetModifications> > matching = new Dictionary <CompactPeptideBase, HashSet <PeptideWithSetModifications> >
{
{ pepWithSetMods.CompactPeptide(TerminusType.None), new HashSet <PeptideWithSetModifications> {
pepWithSetMods
} }
};
psm.MatchToProteinLinkedPeptides(matching);
Assert.AreEqual(psm.ToString().Count(f => f == '\t'), PeptideSpectralMatch.GetTabSeparatedHeader().Count(f => f == '\t'));
Tolerance fragmentTolerance = new PpmTolerance(10);
List <ProductType> lp = new List <ProductType> {
ProductType.B
};
new LocalizationEngine(new List <PeptideSpectralMatch> {
psm
}, lp, myMsDataFile, new CommonParameters(productMassTolerance: fragmentTolerance), new List <string>()).Run();
Assert.AreEqual(psm.ToString().Count(f => f == '\t'), PeptideSpectralMatch.GetTabSeparatedHeader().Count(f => f == '\t'));
psm.SetFdrValues(6, 6, 6, 6, 6, 6, 0, 0, 0, true);
Assert.AreEqual(psm.ToString().Count(f => f == '\t'), PeptideSpectralMatch.GetTabSeparatedHeader().Count(f => f == '\t'));
}
public static void TestGptmdEngine()
{
List <PeptideSpectralMatch> allResultingIdentifications = null;
ModificationMotif.TryGetMotif("N", out ModificationMotif motifN);
var gptmdModifications = new List <ModificationWithMass> {
new ModificationWithMass("21", "mt", motifN, TerminusLocalization.Any, 21.981943)
};
IEnumerable <Tuple <double, double> > combos = new List <Tuple <double, double> >();
Tolerance precursorMassTolerance = new PpmTolerance(10);
allResultingIdentifications = new List <PeptideSpectralMatch>();
var engine = new GptmdEngine(allResultingIdentifications, gptmdModifications, combos, precursorMassTolerance, new List <string>());
var res = (GptmdResults)engine.Run();
Assert.AreEqual(0, res.Mods.Count);
//PsmParent newPsm = new TestParentSpectrumMatch(588.22520189093 + 21.981943);
Ms2ScanWithSpecificMass scan = new Ms2ScanWithSpecificMass(new MzmlScanWithPrecursor(0, new MzmlMzSpectrum(new double[] { 1 }, new double[] { 1 }, false), 1, true, Polarity.Positive, double.NaN, null, null, MZAnalyzerType.Orbitrap, double.NaN, double.NaN, null, null, double.NaN, null, DissociationType.AnyActivationType, 0, null, null, "scan=1"), (588.22520189093 + 21.981943).ToMz(1), 1, null);
var parentProtein = new Protein("NNNNN", "accession");
var protease = new Protease("Custom Protease", new List <string> {
"K"
}, new List <string>(), TerminusType.C, CleavageSpecificity.Full, null, null, null);
DigestionParams digestionParams = new DigestionParams();
List <ModificationWithMass> variableModifications = new List <ModificationWithMass>();
var modPep = parentProtein.Digest(digestionParams, new List <ModificationWithMass>(), variableModifications).First();
var peptidesWithSetModifications = new List <PeptideWithSetModifications> {
modPep
};
PeptideSpectralMatch newPsm = new PeptideSpectralMatch(peptidesWithSetModifications.First().CompactPeptide(TerminusType.None), 0, 0, 0, scan);
Dictionary <ModificationWithMass, ushort> modsDictionary = new Dictionary <ModificationWithMass, ushort>();
Dictionary <CompactPeptideBase, HashSet <PeptideWithSetModifications> > matching = new Dictionary <CompactPeptideBase, HashSet <PeptideWithSetModifications> >
{
{ peptidesWithSetModifications.First().CompactPeptide(TerminusType.None), new HashSet <PeptideWithSetModifications> {
peptidesWithSetModifications.First()
} }
};
List <ProductType> lp = new List <ProductType> {
ProductType.B, ProductType.Y
};
Tolerance fragmentTolerance = new AbsoluteTolerance(0.01);
newPsm.MatchToProteinLinkedPeptides(matching);
newPsm.SetFdrValues(1, 0, 0, 1, 0, 0, 0, 0, 0, false);
allResultingIdentifications.Add(newPsm);
engine = new GptmdEngine(allResultingIdentifications, gptmdModifications, combos, precursorMassTolerance, new List <string>());
res = (GptmdResults)engine.Run();
Assert.AreEqual(1, res.Mods.Count);
Assert.AreEqual(5, res.Mods["accession"].Count);
}
public static void TestGptmdEngine(string proteinSequence, string accession, string sequenceVariantDescription, int numModifiedResidues)
{
List <PeptideSpectralMatch> allResultingIdentifications = null;
ModificationMotif.TryGetMotif("N", out ModificationMotif motifN);
var gptmdModifications = new List <Modification> {
new Modification(_originalId: "21", _modificationType: "mt", _target: motifN, _locationRestriction: "Anywhere.", _monoisotopicMass: 21.981943)
};
IEnumerable <Tuple <double, double> > combos = new List <Tuple <double, double> >();
Tolerance precursorMassTolerance = new PpmTolerance(10);
allResultingIdentifications = new List <PeptideSpectralMatch>();
var fsp = new List <(string fileName, CommonParameters fileSpecificParameters)>();
fsp.Add(("", new CommonParameters()));
var engine = new GptmdEngine(allResultingIdentifications, gptmdModifications, combos, new Dictionary <string, Tolerance> {
{ "filepath", precursorMassTolerance }
}, new CommonParameters(), fsp, new List <string>());
var res = (GptmdResults)engine.Run();
Assert.AreEqual(0, res.Mods.Count);
var parentProtein = new Protein(proteinSequence, accession, sequenceVariations: new List <SequenceVariation> {
new SequenceVariation(1, "N", "A", sequenceVariantDescription)
});
var variantProteins = parentProtein.GetVariantProteins();
CommonParameters commonParameters = new CommonParameters(digestionParams: new DigestionParams(minPeptideLength: 5));
List <Modification> variableModifications = new List <Modification>();
var modPep = variantProteins.SelectMany(p => p.Digest(commonParameters.DigestionParams, new List <Modification>(), variableModifications)).First();
//PsmParent newPsm = new TestParentSpectrumMatch(588.22520189093 + 21.981943);
Ms2ScanWithSpecificMass scan = new Ms2ScanWithSpecificMass(new MsDataScan(new MzSpectrum(new double[] { 1 }, new double[] { 1 }, false), 0, 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, 0, null), (new Proteomics.AminoAcidPolymer.Peptide(modPep.BaseSequence).MonoisotopicMass + 21.981943).ToMz(1), 1, "filepath", new CommonParameters());
var peptidesWithSetModifications = new List <PeptideWithSetModifications> {
modPep
};
PeptideSpectralMatch newPsm = new PeptideSpectralMatch(peptidesWithSetModifications.First(), 0, 0, 0, scan, commonParameters, new List <MatchedFragmentIon>());
Tolerance fragmentTolerance = new AbsoluteTolerance(0.01);
newPsm.SetFdrValues(1, 0, 0, 1, 0, 0, 0, 0);
allResultingIdentifications.Add(newPsm);
engine = new GptmdEngine(allResultingIdentifications, gptmdModifications, combos, new Dictionary <string, Tolerance> {
{ "filepath", precursorMassTolerance }
}, new CommonParameters(), null, new List <string>());
res = (GptmdResults)engine.Run();
Assert.AreEqual(1, res.Mods.Count);
Assert.AreEqual(numModifiedResidues, res.Mods["accession"].Count);
}
public static void TestPsmHeader()
{
CommonParameters commonParameters = new CommonParameters();
PeptideWithSetModifications pepWithSetMods = new Protein(
"MQQQQQQQ",
"accession1",
"org",
new List <Tuple <string, string> > {
new Tuple <string, string>("geneNameType", "geneName")
},
new Dictionary <int, List <Modification> > {
{ 2, new List <Modification> {
new Modification("mod", "mod")
} }
},
name: "name",
fullName: "fullName",
sequenceVariations: new List <SequenceVariation> {
new SequenceVariation(2, "P", "Q", "changed this sequence")
})
.Digest(commonParameters.DigestionParams, new List <Modification>(), new List <Modification>()).First();
MsDataFile myMsDataFile = new TestDataFile(pepWithSetMods, "quadratic");
MsDataScan scann = myMsDataFile.GetOneBasedScan(2);
Ms2ScanWithSpecificMass scan = new Ms2ScanWithSpecificMass(scann, 4, 1, null, new CommonParameters());
var theoreticalIons = new List <Product>();
pepWithSetMods.Fragment(DissociationType.HCD, FragmentationTerminus.Both, theoreticalIons);
var matchedIons = MetaMorpheusEngine.MatchFragmentIons(scan, theoreticalIons, new CommonParameters());
PeptideSpectralMatch psm = new PeptideSpectralMatch(pepWithSetMods, 1, 2, 3, scan, commonParameters, matchedIons);
psm.ResolveAllAmbiguities();
var t = psm.ToString();
var tabsepheader = PeptideSpectralMatch.GetTabSeparatedHeader();
Assert.AreEqual(psm.ToString().Count(f => f == '\t'), PeptideSpectralMatch.GetTabSeparatedHeader().Count(f => f == '\t'));
Assert.AreEqual(psm.ToString().Count(f => f == '\t'), PeptideSpectralMatch.GetTabSeparatedHeader().Count(f => f == '\t'));
Tolerance fragmentTolerance = new PpmTolerance(10);
new LocalizationEngine(new List <PeptideSpectralMatch> {
psm
}, myMsDataFile, new CommonParameters(productMassTolerance: fragmentTolerance), null, new List <string>()).Run();
Assert.AreEqual(psm.ToString().Count(f => f == '\t'), PeptideSpectralMatch.GetTabSeparatedHeader().Count(f => f == '\t'));
psm.SetFdrValues(6, 6, 6, 6, 6, 0, 0, 0);
Assert.AreEqual(psm.ToString().Count(f => f == '\t'), PeptideSpectralMatch.GetTabSeparatedHeader().Count(f => f == '\t'));
}
public static void TestCombos(string proteinSequence, string accession, string variantAA, string sequenceVariantDescription, int numModHashes, int numModifiedResidues, int numModifiedResiduesN, int numModifiedResiduesP, int numModifiedResiduesNP)
{
List <PeptideSpectralMatch> allIdentifications = null;
ModificationMotif.TryGetMotif("N", out ModificationMotif motifN);
ModificationMotif.TryGetMotif("P", out ModificationMotif motifP);
var gptmdModifications = new List <Modification> {
new Modification(_originalId: "21", _modificationType: "mt", _target: motifN, _locationRestriction: "Anywhere.", _monoisotopicMass: 21.981943),
new Modification(_originalId: "16", _modificationType: "mt", _target: motifP, _locationRestriction: "Anywhere.", _monoisotopicMass: 15.994915)
};
IEnumerable <Tuple <double, double> > combos = new List <Tuple <double, double> > {
new Tuple <double, double>(21.981943, 15.994915)
};
Tolerance precursorMassTolerance = new PpmTolerance(10);
var parentProtein = new Protein(proteinSequence, accession, sequenceVariations: new List <SequenceVariation> {
new SequenceVariation(1, "N", variantAA, sequenceVariantDescription)
});
var variantProteins = parentProtein.GetVariantProteins();
DigestionParams digestionParams = new DigestionParams(minPeptideLength: 5);
List <Modification> variableModifications = new List <Modification>();
var modPep = variantProteins.SelectMany(p => p.Digest(digestionParams, new List <Modification>(), variableModifications)).First();
MsDataScan dfd = new MsDataScan(new MzSpectrum(new double[] { 1 }, new double[] { 1 }, false), 0, 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, 0, null);
Ms2ScanWithSpecificMass scan = new Ms2ScanWithSpecificMass(dfd, (new Proteomics.AminoAcidPolymer.Peptide(modPep.BaseSequence).MonoisotopicMass + 21.981943 + 15.994915).ToMz(1), 1, "filepath", new CommonParameters());
var peptidesWithSetModifications = new List <PeptideWithSetModifications> {
modPep
};
PeptideSpectralMatch match = new PeptideSpectralMatch(peptidesWithSetModifications.First(), 0, 0, 0, scan, digestionParams, new List <MatchedFragmentIon>());
PeptideSpectralMatch newPsm = new PeptideSpectralMatch(peptidesWithSetModifications.First(), 0, 0, 0, scan, digestionParams, new List <MatchedFragmentIon>());
Tolerance fragmentTolerance = new AbsoluteTolerance(0.01);
match.SetFdrValues(1, 0, 0, 1, 0, 0, 0, 0);
allIdentifications = new List <PeptideSpectralMatch> {
match
};
var engine = new GptmdEngine(allIdentifications, gptmdModifications, combos, new Dictionary <string, Tolerance> {
{ "filepath", precursorMassTolerance }
}, new CommonParameters(), new List <string>());
var res = (GptmdResults)engine.Run();
Assert.AreEqual(numModHashes, res.Mods.Count);
Assert.AreEqual(numModifiedResidues, res.Mods["accession"].Count);
Assert.AreEqual(numModifiedResiduesN, res.Mods["accession"].Where(b => b.Item2.OriginalId.Equals("21")).Count());
Assert.AreEqual(numModifiedResiduesP, res.Mods["accession"].Where(b => b.Item2.OriginalId.Equals("16")).Count());
res.Mods.TryGetValue("accession_N1P", out var hash);
Assert.AreEqual(numModifiedResiduesNP, (hash ?? new HashSet <Tuple <int, Modification> >()).Count);
}
public static void TestMzIdentMlWriterWithUniprotPsiMod()
{
Protein protein = new Protein("PEPTIDE", "", databaseFilePath: "temp");
ModificationMotif.TryGetMotif("T", out var motif);
Modification fakeMod = new Modification(_originalId: "FAKE", _accession: "FAKE_MOD_ACCESSION", _modificationType: "fake",
_target: motif, _locationRestriction: "Anywhere.", _monoisotopicMass: 0,
_databaseReference: new Dictionary <string, IList <string> > {
{ "PSI-MOD", new List <string> {
"FAKE_MOD_ACCESSION"
} }
});
string resIdAccession = fakeMod.DatabaseReference["PSI-MOD"].First();
var peptide = protein.Digest(new DigestionParams(), new List <Modification> {
fakeMod
}, new List <Modification>()).First();
MsDataScan dfb = new MsDataScan(new MzSpectrum(new double[] { 1 }, new double[] { 1 }, false), 0, 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, 0, null);
Ms2ScanWithSpecificMass scan = new Ms2ScanWithSpecificMass(dfb, 2, 0, "File", new CommonParameters());
var psm = new PeptideSpectralMatch(peptide, 0, 1, 0, scan, new DigestionParams(), new List <MatchedFragmentIon>());
psm.ResolveAllAmbiguities();
psm.SetFdrValues(0, 0, 0, 0, 0, 0, 0, 0);
string path = Path.Combine(TestContext.CurrentContext.TestDirectory, "ResIdOutput.mzID");
MzIdentMLWriter.WriteMzIdentMl(new List <PeptideSpectralMatch> {
psm
}, new List <ProteinGroup>(), new List <Modification>(),
new List <Modification>(), new List <SilacLabel>(), new List <Protease>(), 0, new PpmTolerance(20), new PpmTolerance(20),
0, path);
var file = File.ReadAllLines(path);
bool found = false;
foreach (var line in file)
{
if (line.Contains("FAKE on T") && line.Contains("PSI-MOD:" + resIdAccession))
{
found = true;
}
}
Assert.That(found);
File.Delete(path);
}
public static void TestMzIdentMlWriterWithUniprotResId()
{
Protein protein = new Protein("PEPTIDE", "", databaseFilePath: "temp");
Modification uniProtMod = GlobalVariables.AllModsKnown.First(p =>
p.IdWithMotif == "FMN phosphoryl threonine on T" &&
p.ModificationType == "UniProt" &&
p.Target.ToString() == "T" &&
p.DatabaseReference.ContainsKey("RESID") &&
p.LocationRestriction == "Anywhere.");
string resIdAccession = uniProtMod.DatabaseReference["RESID"].First();
var peptide = protein.Digest(new DigestionParams(), new List <Modification> {
uniProtMod
}, new List <Modification>()).First();
MsDataScan dfb = new MsDataScan(new MzSpectrum(new double[] { 1 }, new double[] { 1 }, false), 0, 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, 0, null);
Ms2ScanWithSpecificMass scan = new Ms2ScanWithSpecificMass(dfb, 2, 0, "File", new CommonParameters());
var psm = new PeptideSpectralMatch(peptide, 0, 1, 0, scan, new DigestionParams(), new List <MatchedFragmentIon>());
psm.ResolveAllAmbiguities();
psm.SetFdrValues(0, 0, 0, 0, 0, 0, 0, 0);
string path = Path.Combine(TestContext.CurrentContext.TestDirectory, "ResIdOutput.mzID");
MzIdentMLWriter.WriteMzIdentMl(new List <PeptideSpectralMatch> {
psm
}, new List <ProteinGroup>(), new List <Modification>(),
new List <Modification>(), new List <SilacLabel>(), new List <Protease>(), 0, new PpmTolerance(20), new PpmTolerance(20),
0, path);
var file = File.ReadAllLines(path);
bool found = false;
foreach (var line in file)
{
if (line.Contains("FMN phosphoryl threonine on T") && line.Contains("RESID:" + resIdAccession))
{
found = true;
}
}
Assert.That(found);
File.Delete(path);
}
public static void TestPsmHeader()
{
DigestionParams digestionParams = new DigestionParams();
PeptideWithSetModifications pepWithSetMods = new Protein("MQQQQQQQ", "accession1").Digest(digestionParams, new List <ModificationWithMass>(), new List <ModificationWithMass>()).First();
IMsDataFile <IMsDataScan <IMzSpectrum <IMzPeak> > > myMsDataFile = new TestDataFile(pepWithSetMods, "quadratic");
IMsDataScanWithPrecursor <IMzSpectrum <IMzPeak> > scann = myMsDataFile.GetOneBasedScan(2) as IMsDataScanWithPrecursor <IMzSpectrum <IMzPeak> >;
Ms2ScanWithSpecificMass scan = new Ms2ScanWithSpecificMass(scann, 4, 1, null);
PeptideSpectralMatch psm = new PeptideSpectralMatch(pepWithSetMods.CompactPeptide(TerminusType.None), 1, 2, 3, scan);
var t = psm.ToString();
var tabsepheader = PeptideSpectralMatch.GetTabSeparatedHeader();
Assert.AreEqual(psm.ToString().Count(f => f == '\t'), PeptideSpectralMatch.GetTabSeparatedHeader().Count(f => f == '\t'));
Dictionary <CompactPeptideBase, HashSet <PeptideWithSetModifications> > matching = new Dictionary <CompactPeptideBase, HashSet <PeptideWithSetModifications> >
{
{ pepWithSetMods.CompactPeptide(TerminusType.None), new HashSet <PeptideWithSetModifications> {
pepWithSetMods
} }
};
psm.MatchToProteinLinkedPeptides(matching);
Assert.AreEqual(psm.ToString().Count(f => f == '\t'), PeptideSpectralMatch.GetTabSeparatedHeader().Count(f => f == '\t'));
Tolerance fragmentTolerance = new PpmTolerance(10);
List <ProductType> lp = new List <ProductType> {
ProductType.B
};
new LocalizationEngine(new List <PeptideSpectralMatch> {
psm
}, lp, myMsDataFile, fragmentTolerance, new List <string>(), false).Run();
Assert.AreEqual(psm.ToString().Count(f => f == '\t'), PeptideSpectralMatch.GetTabSeparatedHeader().Count(f => f == '\t'));
psm.SetFdrValues(6, 6, 6, 6, 6, 6, 0, 0, 0, false);
Assert.AreEqual(psm.ToString().Count(f => f == '\t'), PeptideSpectralMatch.GetTabSeparatedHeader().Count(f => f == '\t'));
}
public static void TryFailSequenceCoverage()
{
var prot1 = new Protein("MMKMMK", "prot1");
ModificationMotif.TryGetMotif("M", out ModificationMotif motifM);
Modification mod1 = new Modification(_originalId: "mod1", _modificationType: "mt", _target: motifM, _locationRestriction: "N-terminal.", _monoisotopicMass: 10);
Modification mod2 = new Modification(_originalId: "mod2", _modificationType: "mt", _target: motifM, _locationRestriction: "Peptide N-terminal.", _monoisotopicMass: 10);
Modification mod3 = new Modification(_originalId: "mod3", _modificationType: "mt", _target: motifM, _locationRestriction: "Anywhere.", _monoisotopicMass: 10);
ModificationMotif.TryGetMotif("K", out ModificationMotif motifK);
Modification mod4 = new Modification(_originalId: "mod4", _modificationType: "mt", _target: motifK, _locationRestriction: "Peptide C-terminal.", _monoisotopicMass: 10);
Modification mod5 = new Modification(_originalId: "mod5", _modificationType: "mt", _target: motifK, _locationRestriction: "C-terminal.", _monoisotopicMass: 10);
Dictionary <int, Modification> modsFor1 = new Dictionary <int, Modification>
{
{ 1, mod1 },
{ 3, mod3 },
{ 5, mod4 },
};
Dictionary <int, Modification> modsFor2 = new Dictionary <int, Modification>
{
{ 1, mod2 },
{ 5, mod5 },
};
Dictionary <int, Modification> modsFor3 = new Dictionary <int, Modification>
{
{ 1, mod1 },
{ 5, mod3 },
{ 8, mod5 }
};
DigestionParams digestionParams = new DigestionParams();
var pwsm1 = new PeptideWithSetModifications(prot1, digestionParams, 1, 3, CleavageSpecificity.Unknown, "", 0, modsFor1, 0);
var pwsm2 = new PeptideWithSetModifications(prot1, digestionParams, 4, 6, CleavageSpecificity.Unknown, "", 0, modsFor2, 0);
var pwsm3 = new PeptideWithSetModifications(prot1, digestionParams, 1, 6, CleavageSpecificity.Unknown, "", 0, modsFor3, 0);
HashSet <PeptideWithSetModifications> peptides = new HashSet <PeptideWithSetModifications>
{
pwsm1,
pwsm2,
pwsm3,
};
IScan scan = new ThisTestScan();
var psm1 = new PeptideSpectralMatch(pwsm1, 0, 1, 0, scan, digestionParams, new List <MatchedFragmentIon>());
psm1.SetFdrValues(0, 0, 0, 0, 0, 0, 0, 0, 0, false);
var psm2 = new PeptideSpectralMatch(pwsm2, 0, 1, 0, scan, digestionParams, new List <MatchedFragmentIon>());
psm2.SetFdrValues(0, 0, 0, 0, 0, 0, 0, 0, 0, false);
var psm3 = new PeptideSpectralMatch(pwsm3, 0, 1, 0, scan, digestionParams, new List <MatchedFragmentIon>());
psm3.SetFdrValues(0, 0, 0, 0, 0, 0, 0, 0, 0, false);
List <PeptideSpectralMatch> newPsms = new List <PeptideSpectralMatch>
{
psm1,
psm2,
psm3,
};
newPsms.ForEach(p => p.ResolveAllAmbiguities());
ProteinParsimonyEngine ppe = new ProteinParsimonyEngine(newPsms, true, new CommonParameters(), new List <string>());
ProteinParsimonyResults fjkd = (ProteinParsimonyResults)ppe.Run();
ProteinScoringAndFdrEngine psafe = new ProteinScoringAndFdrEngine(fjkd.ProteinGroups, newPsms, true, true, true, new CommonParameters(), new List <string>());
psafe.Run();
fjkd.ProteinGroups.First().CalculateSequenceCoverage();
var firstSequenceCoverageDisplayList = fjkd.ProteinGroups.First().SequenceCoverageDisplayList.First();
Assert.AreEqual("MMKMMK", firstSequenceCoverageDisplayList);
var firstSequenceCoverageDisplayListWithMods = fjkd.ProteinGroups.First().SequenceCoverageDisplayListWithMods.First();
Assert.AreEqual("[mod1 on M]-MM[mod3 on M]KM[mod3 on M]MK-[mod5 on K]", firstSequenceCoverageDisplayListWithMods);
var firstModInfo = fjkd.ProteinGroups.First().ModsInfo.First();
Assert.IsTrue(firstModInfo.Contains(@"#aa1[mod1 on M,info:occupancy=1.00(2/2)]"));
Assert.IsTrue(firstModInfo.Contains(@"#aa2[mod3 on M,info:occupancy=0.50(1/2)]"));
Assert.IsFalse(firstModInfo.Contains(@"#aa3"));
Assert.IsTrue(firstModInfo.Contains(@"#aa4[mod3 on M,info:occupancy=0.50(1/2)]"));
Assert.IsFalse(firstModInfo.Contains(@"#aa5"));
Assert.IsTrue(firstModInfo.Contains(@"#aa6[mod5 on K,info:occupancy=1.00(2/2)]"));
}
public static void TryFailSequenceCoverage()
{
var prot1 = new Protein("MMKMMK", "prot1");
ModificationMotif.TryGetMotif("M", out ModificationMotif motifM);
ModificationWithMass mod1 = new ModificationWithMass("mod1", "mt", motifM, TerminusLocalization.NProt, 10);
ModificationWithMass mod2 = new ModificationWithMass("mod2", "mt", motifM, TerminusLocalization.NPep, 10);
ModificationWithMass mod3 = new ModificationWithMass("mod3", "mt", motifM, TerminusLocalization.Any, 10);
ModificationMotif.TryGetMotif("K", out ModificationMotif motifK);
ModificationWithMass mod4 = new ModificationWithMass("mod4", "mt", motifK, TerminusLocalization.PepC, 10);
ModificationWithMass mod5 = new ModificationWithMass("mod5", "mt", motifK, TerminusLocalization.ProtC, 10);
Dictionary <int, ModificationWithMass> modsFor1 = new Dictionary <int, ModificationWithMass>
{
{ 1, mod1 },
{ 3, mod3 },
{ 5, mod4 },
};
Dictionary <int, ModificationWithMass> modsFor2 = new Dictionary <int, ModificationWithMass>
{
{ 1, mod2 },
{ 5, mod5 },
};
Dictionary <int, ModificationWithMass> modsFor3 = new Dictionary <int, ModificationWithMass>
{
{ 1, mod1 },
{ 5, mod3 },
{ 8, mod5 }
};
DigestionParams digestionParams = new DigestionParams();
var pwsm1 = new PeptideWithSetModifications(protein: prot1, digestionParams: digestionParams, oneBasedStartResidueInProtein: 1, oneBasedEndResidueInProtein: 3, peptideDescription: "", missedCleavages: 0, allModsOneIsNterminus: modsFor1, numFixedMods: 0);
var pwsm2 = new PeptideWithSetModifications(protein: prot1, digestionParams: digestionParams, oneBasedStartResidueInProtein: 4, oneBasedEndResidueInProtein: 6, peptideDescription: "", missedCleavages: 0, allModsOneIsNterminus: modsFor2, numFixedMods: 0);
var pwsm3 = new PeptideWithSetModifications(protein: prot1, digestionParams: digestionParams, oneBasedStartResidueInProtein: 1, oneBasedEndResidueInProtein: 6, peptideDescription: "", missedCleavages: 0, allModsOneIsNterminus: modsFor3, numFixedMods: 0);
HashSet <PeptideWithSetModifications> peptides = new HashSet <PeptideWithSetModifications>
{
pwsm1,
pwsm2,
pwsm3,
};
Dictionary <CompactPeptideBase, HashSet <PeptideWithSetModifications> > matching = new Dictionary <CompactPeptideBase, HashSet <PeptideWithSetModifications> >
{
{ pwsm1.CompactPeptide(TerminusType.None), new HashSet <PeptideWithSetModifications> {
pwsm1
} },
{ pwsm2.CompactPeptide(TerminusType.None), new HashSet <PeptideWithSetModifications> {
pwsm2
} },
{ pwsm3.CompactPeptide(TerminusType.None), new HashSet <PeptideWithSetModifications> {
pwsm3
} },
};
IScan scan = new ThisTestScan();
var psm1 = new PeptideSpectralMatch(pwsm1.CompactPeptide(TerminusType.None), 0, 1, 0, scan, digestionParams);
psm1.SetFdrValues(0, 0, 0, 0, 0, 0, 0, 0, 0, false);
psm1.MatchToProteinLinkedPeptides(matching);
var psm2 = new PeptideSpectralMatch(pwsm2.CompactPeptide(TerminusType.None), 0, 1, 0, scan, digestionParams);
psm2.SetFdrValues(0, 0, 0, 0, 0, 0, 0, 0, 0, false);
psm2.MatchToProteinLinkedPeptides(matching);
var psm3 = new PeptideSpectralMatch(pwsm3.CompactPeptide(TerminusType.None), 0, 1, 0, scan, digestionParams);
psm3.SetFdrValues(0, 0, 0, 0, 0, 0, 0, 0, 0, false);
psm3.MatchToProteinLinkedPeptides(matching);
List <PeptideSpectralMatch> newPsms = new List <PeptideSpectralMatch>
{
psm1,
psm2,
psm3,
};
ProteinParsimonyEngine ppe = new ProteinParsimonyEngine(matching, true, new CommonParameters(), new List <string>());
ProteinParsimonyResults fjkd = (ProteinParsimonyResults)ppe.Run();
ProteinScoringAndFdrEngine psafe = new ProteinScoringAndFdrEngine(fjkd.ProteinGroups, newPsms, true, true, true, new CommonParameters(), new List <string>());
psafe.Run();
fjkd.ProteinGroups.First().CalculateSequenceCoverage();
var firstSequenceCoverageDisplayList = fjkd.ProteinGroups.First().SequenceCoverageDisplayList.First();
Assert.AreEqual("MMKMMK", firstSequenceCoverageDisplayList);
var firstSequenceCoverageDisplayListWithMods = fjkd.ProteinGroups.First().SequenceCoverageDisplayListWithMods.First();
Assert.AreEqual("[mod1]-MM[mod3]KM[mod3]MK-[mod5]", firstSequenceCoverageDisplayListWithMods);
var firstModInfo = fjkd.ProteinGroups.First().ModsInfo.First();
Assert.IsTrue(firstModInfo.Contains(@"#aa1[mod1,info:occupancy=1.00(2/2)]"));
Assert.IsTrue(firstModInfo.Contains(@"#aa2[mod3,info:occupancy=0.50(1/2)]"));
Assert.IsFalse(firstModInfo.Contains(@"#aa3"));
Assert.IsTrue(firstModInfo.Contains(@"#aa4[mod3,info:occupancy=0.50(1/2)]"));
Assert.IsFalse(firstModInfo.Contains(@"#aa5"));
Assert.IsTrue(firstModInfo.Contains(@"#aa6[mod5,info:occupancy=1.00(2/2)]"));
}
private void DoFalseDiscoveryRateAnalysis(FdrAnalysisResults myAnalysisResults)
{
// Stop if canceled
if (GlobalVariables.StopLoops)
{
return;
}
// calculate FDR on a per-protease basis (targets and decoys for a specific protease)
var psmsGroupedByProtease = AllPsms.GroupBy(p => p.DigestionParams.Protease);
foreach (var proteasePsms in psmsGroupedByProtease)
{
var psms = proteasePsms.ToList();
// generate the null distribution for e-value calculations
double globalMeanScore = 0;
int globalMeanCount = 0;
if (CalculateEValue && psms.Any())
{
List <double> combinedScores = new List <double>();
foreach (PeptideSpectralMatch psm in psms)
{
psm.AllScores.Sort();
combinedScores.AddRange(psm.AllScores);
//remove top scoring peptide
if (combinedScores.Any())
{
combinedScores.RemoveAt(combinedScores.Count - 1);
}
}
if (combinedScores.Any())
{
globalMeanScore = combinedScores.Average();
globalMeanCount = (int)((double)combinedScores.Count / psms.Count);
}
else
{
// should be a very rare case... if there are PSMs but each PSM only has one hit
globalMeanScore = 0;
globalMeanCount = 0;
}
}
//Calculate delta scores for the psms (regardless of if we are using them)
foreach (PeptideSpectralMatch psm in psms)
{
if (psm != null)
{
psm.CalculateDeltaScore(ScoreCutoff);
}
}
//determine if Score or DeltaScore performs better
if (UseDeltaScore)
{
const double qValueCutoff = 0.01; //optimize to get the most PSMs at a 1% FDR
List <PeptideSpectralMatch> scoreSorted = psms.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();
int ScorePSMs = GetNumPSMsAtqValueCutoff(scoreSorted, qValueCutoff);
scoreSorted = psms.OrderByDescending(b => b.DeltaScore).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();
int DeltaScorePSMs = GetNumPSMsAtqValueCutoff(scoreSorted, qValueCutoff);
//sort by best method
myAnalysisResults.DeltaScoreImprovement = DeltaScorePSMs > ScorePSMs;
psms = myAnalysisResults.DeltaScoreImprovement ?
psms.OrderByDescending(b => b.DeltaScore).ThenBy(b => b.PeptideMonisotopicMass.HasValue ? Math.Abs(b.ScanPrecursorMass - b.PeptideMonisotopicMass.Value) : double.MaxValue).ToList() :
psms.OrderByDescending(b => b.Score).ThenBy(b => b.PeptideMonisotopicMass.HasValue ? Math.Abs(b.ScanPrecursorMass - b.PeptideMonisotopicMass.Value) : double.MaxValue).ToList();
}
else //sort by score
{
psms = psms.OrderByDescending(b => b.Score).ThenBy(b => b.PeptideMonisotopicMass.HasValue ? Math.Abs(b.ScanPrecursorMass - b.PeptideMonisotopicMass.Value) : double.MaxValue).ToList();
}
double cumulativeTarget = 0;
double cumulativeDecoy = 0;
//set up arrays for local FDRs
double[] cumulativeTargetPerNotch = new double[MassDiffAcceptorNumNotches + 1];
double[] cumulativeDecoyPerNotch = new double[MassDiffAcceptorNumNotches + 1];
//Assign FDR values to PSMs
for (int i = 0; i < psms.Count; i++)
{
// Stop if canceled
if (GlobalVariables.StopLoops)
{
break;
}
PeptideSpectralMatch psm = psms[i];
int notch = psm.Notch ?? MassDiffAcceptorNumNotches;
if (psm.IsDecoy)
{
// the PSM can be ambiguous between a target and a decoy sequence
// in that case, count it as the fraction of decoy hits
// e.g. if the PSM matched to 1 target and 2 decoys, it counts as 2/3 decoy
double decoyHits = 0;
double totalHits = 0;
var hits = psm.BestMatchingPeptides.GroupBy(p => p.Peptide.FullSequence);
foreach (var hit in hits)
{
if (hit.First().Peptide.Protein.IsDecoy)
{
decoyHits++;
}
totalHits++;
}
cumulativeDecoy += decoyHits / totalHits;
cumulativeDecoyPerNotch[notch] += decoyHits / totalHits;
}
else
{
cumulativeTarget++;
cumulativeTargetPerNotch[notch]++;
}
double qValue = Math.Min(1, cumulativeDecoy / cumulativeTarget);
double qValueNotch = Math.Min(1, cumulativeDecoyPerNotch[notch] / cumulativeTargetPerNotch[notch]);
double maximumLikelihood = 0;
double eValue = 0;
double eScore = 0;
if (CalculateEValue)
{
eValue = GetEValue(psm, globalMeanCount, globalMeanScore, out maximumLikelihood);
eScore = -Math.Log(eValue, 10);
}
psm.SetFdrValues(cumulativeTarget, cumulativeDecoy, qValue, cumulativeTargetPerNotch[notch], cumulativeDecoyPerNotch[notch], qValueNotch, maximumLikelihood, eValue, eScore, CalculateEValue);
}
// set q-value thresholds such that a lower scoring PSM can't have
// a higher confidence than a higher scoring PSM
//Populate min qValues
double qValueThreshold = 1.0;
double[] qValueNotchThreshold = new double[MassDiffAcceptorNumNotches + 1];
for (int i = 0; i < qValueNotchThreshold.Length; i++)
{
qValueNotchThreshold[i] = 1.0;
}
for (int i = psms.Count - 1; i >= 0; i--)
{
PeptideSpectralMatch psm = psms[i];
// threshold q-values
if (psm.FdrInfo.QValue > qValueThreshold)
{
psm.FdrInfo.QValue = qValueThreshold;
}
else if (psm.FdrInfo.QValue < qValueThreshold)
{
qValueThreshold = psm.FdrInfo.QValue;
}
// threshold notch q-values
int notch = psm.Notch ?? MassDiffAcceptorNumNotches;
if (psm.FdrInfo.QValueNotch > qValueNotchThreshold[notch])
{
psm.FdrInfo.QValueNotch = qValueNotchThreshold[notch];
}
else if (psm.FdrInfo.QValueNotch < qValueNotchThreshold[notch])
{
qValueNotchThreshold[notch] = psm.FdrInfo.QValueNotch;
}
}
}
if (AnalysisType == "PSM")
{
CountPsm();
}
}
public static void TestPTMOutput()
{
List <ModificationWithMass> variableModifications = new List <ModificationWithMass>();
List <ModificationWithMass> fixedModifications = new List <ModificationWithMass>();
ModificationMotif.TryGetMotif("S", out ModificationMotif motif);
variableModifications.Add(new ModificationWithMassAndCf("resMod", "HaHa", motif, TerminusLocalization.Any, ChemicalFormula.ParseFormula("H")));
var proteinList = new List <Protein> {
new Protein("MNNNSKQQQ", "accession")
};
var protease = new Protease("CustomProtease", 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);
Dictionary <CompactPeptideBase, HashSet <PeptideWithSetModifications> > compactPeptideToProteinPeptideMatching = new Dictionary <CompactPeptideBase, HashSet <PeptideWithSetModifications> >();
Dictionary <ModificationWithMass, ushort> modsDictionary = new Dictionary <ModificationWithMass, ushort>
{
{ variableModifications.Last(), 1 }
};
DigestionParams digestionParams = new DigestionParams(protease: protease.Name, maxMissedCleavages: 0, minPeptideLength: 1);
var modPep = proteinList.First().Digest(digestionParams, fixedModifications, variableModifications).Last();
HashSet <PeptideWithSetModifications> value = new HashSet <PeptideWithSetModifications> {
modPep
};
CompactPeptide compactPeptide1 = new CompactPeptide(value.First(), TerminusType.None);
Assert.AreEqual("QQQ", value.First().Sequence);
var firstProtDigest = proteinList.First().Digest(digestionParams, fixedModifications, variableModifications).ToList();
HashSet <PeptideWithSetModifications> value2 = new HashSet <PeptideWithSetModifications> {
firstProtDigest[0]
};
CompactPeptide compactPeptide2 = new CompactPeptide(value2.First(), TerminusType.None);
Assert.AreEqual("MNNNSK", value2.First().Sequence);
HashSet <PeptideWithSetModifications> value2mod = new HashSet <PeptideWithSetModifications> {
firstProtDigest[1]
};
CompactPeptide compactPeptide2mod = new CompactPeptide(value2mod.Last(), TerminusType.None);
Assert.AreEqual("MNNNS[HaHa:resMod]K", value2mod.Last().Sequence);
HashSet <PeptideWithSetModifications> value3 = new HashSet <PeptideWithSetModifications> {
firstProtDigest[2]
};
CompactPeptide compactPeptide3 = new CompactPeptide(value3.First(), TerminusType.None);
Assert.AreEqual("NNNSK", value3.First().Sequence);
HashSet <PeptideWithSetModifications> value3mod = new HashSet <PeptideWithSetModifications> {
firstProtDigest[3]
};
CompactPeptide compactPeptide3mod = new CompactPeptide(value3mod.Last(), TerminusType.None);
Assert.AreEqual("NNNS[HaHa:resMod]K", value3mod.Last().Sequence);
var peptideList = new HashSet <PeptideWithSetModifications>();
foreach (var protein in proteinList)
{
foreach (var peptide in protein.Digest(digestionParams, new List <ModificationWithMass>(), variableModifications))
{
peptideList.Add(peptide);
}
}
compactPeptideToProteinPeptideMatching.Add(compactPeptide1, value);
compactPeptideToProteinPeptideMatching.Add(compactPeptide2, value2);
compactPeptideToProteinPeptideMatching.Add(compactPeptide3, value3);
compactPeptideToProteinPeptideMatching.Add(compactPeptide2mod, value2mod);
compactPeptideToProteinPeptideMatching.Add(compactPeptide3mod, value3mod);
ProteinParsimonyEngine engine = new ProteinParsimonyEngine(compactPeptideToProteinPeptideMatching, true, new CommonParameters(), new List <string> {
"ff"
});
var cool = (ProteinParsimonyResults)engine.Run();
var proteinGroups = cool.ProteinGroups;
MsDataScan jdfk = new MsDataScan(new MzSpectrum(new double[] { 1 }, new double[] { 1 }, false), 0, 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, 0, null);
Ms2ScanWithSpecificMass ms2scan = new Ms2ScanWithSpecificMass(jdfk, 2, 0, "File");
List <ProductType> lp = new List <ProductType> {
ProductType.B, ProductType.Y
};
Tolerance fragmentTolerance = new AbsoluteTolerance(0.01);
var match1 = new PeptideSpectralMatch(peptideList.ElementAt(0).CompactPeptide(TerminusType.None), 0, 10, 0, ms2scan, digestionParams)
{
};
match1.SetFdrValues(0, 0, 0, 0, 0, 0, 0, 0, 0, false);
var match2 = new PeptideSpectralMatch(peptideList.ElementAt(1).CompactPeptide(TerminusType.None), 0, 10, 0, ms2scan, digestionParams)
{
};
match2.SetFdrValues(0, 0, 0, 0, 0, 0, 0, 0, 0, false);
var match3 = new PeptideSpectralMatch(peptideList.ElementAt(1).CompactPeptide(TerminusType.None), 0, 10, 0, ms2scan, digestionParams)
{
};
match3.SetFdrValues(0, 0, 0, 0, 0, 0, 0, 0, 0, false);
match1.MatchToProteinLinkedPeptides(compactPeptideToProteinPeptideMatching);
match2.MatchToProteinLinkedPeptides(compactPeptideToProteinPeptideMatching);
match3.MatchToProteinLinkedPeptides(compactPeptideToProteinPeptideMatching);
List <PeptideSpectralMatch> psms = new List <PeptideSpectralMatch>
{
match1,
match2,
match3
};
ProteinScoringAndFdrEngine f = new ProteinScoringAndFdrEngine(proteinGroups, psms, false, false, true, new CommonParameters(), new List <string>());
f.Run();
Assert.AreEqual("#aa5[resMod,info:occupancy=0.67(2/3)];", proteinGroups.First().ModsInfo[0]);
}
public static void TestPTMOutput()
{
List <Modification> variableModifications = new List <Modification>();
List <Modification> fixedModifications = new List <Modification>();
ModificationMotif.TryGetMotif("S", out ModificationMotif motifS);
ModificationMotif.TryGetMotif("I", out ModificationMotif motifI);
variableModifications.Add(new Modification(_originalId: "resMod", _modificationType: "HaHa", _target: motifS, _locationRestriction: "Anywhere.", _chemicalFormula: ChemicalFormula.ParseFormula("H")));
variableModifications.Add(new Modification(_originalId: "iModOne", _modificationType: "HaHa", _target: motifI, _locationRestriction: "Anywhere.", _chemicalFormula: ChemicalFormula.ParseFormula("H")));
variableModifications.Add(new Modification(_originalId: "iModTwo", _modificationType: "HaHa", _target: motifI, _locationRestriction: "Anywhere.", _chemicalFormula: ChemicalFormula.ParseFormula("H")));
var proteinList = new List <Protein> {
new Protein("MNNNSKQQQI", "accession")
};
var protease = new Protease("CustomProtease", CleavageSpecificity.Full, null, null, new List <DigestionMotif> {
new DigestionMotif("K", null, 1, null)
});
ProteaseDictionary.Dictionary.Add(protease.Name, protease);
Dictionary <Modification, ushort> modsDictionary = new Dictionary <Modification, ushort>
{
{ variableModifications.Last(), 1 }
};
CommonParameters commonParameters = new CommonParameters(digestionParams: new DigestionParams(protease: protease.Name, maxMissedCleavages: 0, minPeptideLength: 1));
var protDigest = proteinList.First().Digest(commonParameters.DigestionParams, fixedModifications, variableModifications).ToList();
int idx = 0;
var pep1 = new HashSet <PeptideWithSetModifications> {
protDigest[idx++]
};
Assert.AreEqual("MNNNSK", pep1.Single().FullSequence);//this might be base
var pep1mod = new HashSet <PeptideWithSetModifications> {
protDigest[idx++]
};
Assert.AreEqual("MNNNS[HaHa:resMod on S]K", pep1mod.Single().FullSequence);//this might be base
var pep3 = new HashSet <PeptideWithSetModifications> {
protDigest[idx++]
};
Assert.AreEqual("NNNSK", pep3.Single().FullSequence);//this might be base
var pep3mod = new HashSet <PeptideWithSetModifications> {
protDigest[idx++]
};
Assert.AreEqual("NNNS[HaHa:resMod on S]K", pep3mod.Single().FullSequence);//this might be base
var pep4 = new HashSet <PeptideWithSetModifications> {
protDigest[idx++]
};
Assert.AreEqual("QQQI", pep4.Single().FullSequence);//this might be base
var pep4mod1 = new HashSet <PeptideWithSetModifications> {
protDigest[idx++]
};
Assert.AreEqual("QQQI[HaHa:iModOne on I]", pep4mod1.Single().FullSequence);//this might be base
var pep4mod2 = new HashSet <PeptideWithSetModifications> {
protDigest[idx++]
};
Assert.AreEqual("QQQI[HaHa:iModTwo on I]", pep4mod2.Single().FullSequence);//this might be base
var peptideList = new HashSet <PeptideWithSetModifications>();
foreach (var peptide in proteinList.SelectMany(protein => protein.Digest(commonParameters.DigestionParams, new List <Modification>(), variableModifications)))
{
peptideList.Add(peptide);
}
MsDataScan jdfk = new MsDataScan(new MzSpectrum(new double[] { 1 }, new double[] { 1 }, false), 0, 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, 0, null);
Ms2ScanWithSpecificMass ms2scan = new Ms2ScanWithSpecificMass(jdfk, 2, 0, "File", new CommonParameters());
Tolerance fragmentTolerance = new AbsoluteTolerance(0.01);
var match1 = new PeptideSpectralMatch(peptideList.ElementAt(0), 0, 10, 0, ms2scan, commonParameters, new List <MatchedFragmentIon>())
{
};
match1.SetFdrValues(0, 0, 0, 0, 0, 0, 0, 0);
var match2 = new PeptideSpectralMatch(peptideList.ElementAt(1), 0, 10, 0, ms2scan, commonParameters, new List <MatchedFragmentIon>())
{
};
match2.SetFdrValues(0, 0, 0, 0, 0, 0, 0, 0);
var match3 = new PeptideSpectralMatch(peptideList.ElementAt(1), 0, 10, 0, ms2scan, commonParameters, new List <MatchedFragmentIon>())
{
};
match3.SetFdrValues(0, 0, 0, 0, 0, 0, 0, 0);
var match4 = new PeptideSpectralMatch(peptideList.ElementAt(4), 0, 10, 0, ms2scan, commonParameters, new List <MatchedFragmentIon>())
{
};
match4.SetFdrValues(0, 0, 0, 0, 0, 0, 0, 0);
var match5 = new PeptideSpectralMatch(peptideList.ElementAt(5), 0, 10, 0, ms2scan, commonParameters, new List <MatchedFragmentIon>())
{
};
match5.SetFdrValues(0, 0, 0, 0, 0, 0, 0, 0);
var match6 = new PeptideSpectralMatch(peptideList.ElementAt(6), 0, 10, 0, ms2scan, commonParameters, new List <MatchedFragmentIon>())
{
};
match6.SetFdrValues(0, 0, 0, 0, 0, 0, 0, 0);
var match44 = new PeptideSpectralMatch(peptideList.ElementAt(4), 0, 10, 0, ms2scan, commonParameters, new List <MatchedFragmentIon>())
{
};
match44.SetFdrValues(0, 0, 0, 0, 0, 0, 0, 0);
var match55 = new PeptideSpectralMatch(peptideList.ElementAt(5), 0, 10, 0, ms2scan, commonParameters, new List <MatchedFragmentIon>())
{
};
match55.SetFdrValues(0, 0, 0, 0, 0, 0, 0, 0);
var match66 = new PeptideSpectralMatch(peptideList.ElementAt(6), 0, 10, 0, ms2scan, commonParameters, new List <MatchedFragmentIon>())
{
};
match66.SetFdrValues(0, 0, 0, 0, 0, 0, 0, 0);
List <PeptideSpectralMatch> psms = new List <PeptideSpectralMatch>
{
match1,
match2,
match3,
match4,
match44,
match5,
match55,
match6,
match66
};
psms.ForEach(p => p.ResolveAllAmbiguities());
ProteinParsimonyEngine engine = new ProteinParsimonyEngine(psms, true, new CommonParameters(), null, new List <string> {
"ff"
});
var cool = (ProteinParsimonyResults)engine.Run();
var proteinGroups = cool.ProteinGroups;
ProteinScoringAndFdrEngine f = new ProteinScoringAndFdrEngine(proteinGroups, psms, false, false, true, new CommonParameters(), null, new List <string>());
f.Run();
Assert.AreEqual("#aa5[resMod on S,info:occupancy=0.67(2/3)];#aa10[iModOne on I,info:occupancy=0.33(2/6)];#aa10[iModTwo on I,info:occupancy=0.33(2/6)]", proteinGroups.First().ModsInfo[0]);
}
private void DoFalseDiscoveryRateAnalysis(FdrAnalysisResults myAnalysisResults)
{
// Stop if canceled
if (GlobalVariables.StopLoops)
{
return;
}
// calculate FDR on a per-protease basis (targets and decoys for a specific protease)
var psmsGroupedByProtease = AllPsms.GroupBy(p => p.DigestionParams.Protease);
foreach (var proteasePsms in psmsGroupedByProtease)
{
var psms = proteasePsms.ToList();
//determine if Score or DeltaScore performs better
if (UseDeltaScore)
{
const double qValueCutoff = 0.01; //optimize to get the most PSMs at a 1% FDR
List <PeptideSpectralMatch> scoreSorted = psms.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();
int ScorePSMs = GetNumPSMsAtqValueCutoff(scoreSorted, qValueCutoff);
scoreSorted = psms.OrderByDescending(b => b.DeltaScore).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();
int DeltaScorePSMs = GetNumPSMsAtqValueCutoff(scoreSorted, qValueCutoff);
//sort by best method
myAnalysisResults.DeltaScoreImprovement = DeltaScorePSMs > ScorePSMs;
psms = myAnalysisResults.DeltaScoreImprovement ?
psms.OrderByDescending(b => b.DeltaScore).ThenBy(b => b.PeptideMonisotopicMass.HasValue ? Math.Abs(b.ScanPrecursorMass - b.PeptideMonisotopicMass.Value) : double.MaxValue).ToList() :
psms.OrderByDescending(b => b.Score).ThenBy(b => b.PeptideMonisotopicMass.HasValue ? Math.Abs(b.ScanPrecursorMass - b.PeptideMonisotopicMass.Value) : double.MaxValue).ToList();
}
else //sort by score
{
psms = psms.OrderByDescending(b => b.Score).ThenBy(b => b.PeptideMonisotopicMass.HasValue ? Math.Abs(b.ScanPrecursorMass - b.PeptideMonisotopicMass.Value) : double.MaxValue).ToList();
}
double cumulativeTarget = 0;
double cumulativeDecoy = 0;
//set up arrays for local FDRs
double[] cumulativeTargetPerNotch = new double[MassDiffAcceptorNumNotches + 1];
double[] cumulativeDecoyPerNotch = new double[MassDiffAcceptorNumNotches + 1];
//Assign FDR values to PSMs
for (int i = 0; i < psms.Count; i++)
{
// Stop if canceled
if (GlobalVariables.StopLoops)
{
break;
}
PeptideSpectralMatch psm = psms[i];
int notch = psm.Notch ?? MassDiffAcceptorNumNotches;
if (psm.IsDecoy)
{
// the PSM can be ambiguous between a target and a decoy sequence
// in that case, count it as the fraction of decoy hits
// e.g. if the PSM matched to 1 target and 2 decoys, it counts as 2/3 decoy
double decoyHits = 0;
double totalHits = 0;
var hits = psm.BestMatchingPeptides.GroupBy(p => p.Peptide.FullSequence);
foreach (var hit in hits)
{
if (hit.First().Peptide.Protein.IsDecoy)
{
decoyHits++;
}
totalHits++;
}
cumulativeDecoy += decoyHits / totalHits;
cumulativeDecoyPerNotch[notch] += decoyHits / totalHits;
}
else
{
cumulativeTarget++;
cumulativeTargetPerNotch[notch]++;
}
double qValue = Math.Min(1, cumulativeDecoy / cumulativeTarget);
double qValueNotch = Math.Min(1, cumulativeDecoyPerNotch[notch] / cumulativeTargetPerNotch[notch]);
double pep = psm.FdrInfo == null ? double.NaN : psm.FdrInfo.PEP;
double pepQValue = psm.FdrInfo == null ? double.NaN : psm.FdrInfo.PEP_QValue;
psm.SetFdrValues(cumulativeTarget, cumulativeDecoy, qValue, cumulativeTargetPerNotch[notch], cumulativeDecoyPerNotch[notch], qValueNotch, pep, pepQValue);
}
// set q-value thresholds such that a lower scoring PSM can't have
// a higher confidence than a higher scoring PSM
//Populate min qValues
double qValueThreshold = 1.0;
double[] qValueNotchThreshold = new double[MassDiffAcceptorNumNotches + 1];
for (int i = 0; i < qValueNotchThreshold.Length; i++)
{
qValueNotchThreshold[i] = 1.0;
}
for (int i = psms.Count - 1; i >= 0; i--)
{
PeptideSpectralMatch psm = psms[i];
// threshold q-values
if (psm.FdrInfo.QValue > qValueThreshold)
{
psm.FdrInfo.QValue = qValueThreshold;
}
else if (psm.FdrInfo.QValue < qValueThreshold)
{
qValueThreshold = psm.FdrInfo.QValue;
}
// threshold notch q-values
int notch = psm.Notch ?? MassDiffAcceptorNumNotches;
if (psm.FdrInfo.QValueNotch > qValueNotchThreshold[notch])
{
psm.FdrInfo.QValueNotch = qValueNotchThreshold[notch];
}
else if (psm.FdrInfo.QValueNotch < qValueNotchThreshold[notch])
{
qValueNotchThreshold[notch] = psm.FdrInfo.QValueNotch;
}
}
}
if (AnalysisType == "PSM")
{
CountPsm();
if (AllPsms.Count > 0)
{
myAnalysisResults.BinarySearchTreeMetrics = PEP_Analysis.ComputePEPValuesForAllPSMsGeneric(AllPsms);
Compute_PEPValue_Based_QValue(AllPsms);
}
}
if (AnalysisType == "Peptide")
{
Compute_PEPValue_Based_QValue(AllPsms);
}
}
public static void TestPTMOutput()
{
List <Modification> variableModifications = new List <Modification>();
List <Modification> fixedModifications = new List <Modification>();
ModificationMotif.TryGetMotif("S", out ModificationMotif motif);
variableModifications.Add(new Modification(_originalId: "resMod", _modificationType: "HaHa", _target: motif, _locationRestriction: "Anywhere.", _chemicalFormula: ChemicalFormula.ParseFormula("H")));
var proteinList = new List <Protein> {
new Protein("MNNNSKQQQ", "accession")
};
var protease = new Protease("CustomProtease", CleavageSpecificity.Full, null, null, new List <DigestionMotif> {
new DigestionMotif("K", null, 1, null)
});
ProteaseDictionary.Dictionary.Add(protease.Name, protease);
Dictionary <Modification, ushort> modsDictionary = new Dictionary <Modification, ushort>
{
{ variableModifications.Last(), 1 }
};
DigestionParams digestionParams = new DigestionParams(protease: protease.Name, maxMissedCleavages: 0, minPeptideLength: 1);
var modPep = proteinList.First().Digest(digestionParams, fixedModifications, variableModifications).Last();
HashSet <PeptideWithSetModifications> value = new HashSet <PeptideWithSetModifications> {
modPep
};
PeptideWithSetModifications compactPeptide1 = value.First();
Assert.AreEqual("QQQ", value.First().FullSequence);//this might be base
var firstProtDigest = proteinList.First().Digest(digestionParams, fixedModifications, variableModifications).ToList();
HashSet <PeptideWithSetModifications> value2 = new HashSet <PeptideWithSetModifications> {
firstProtDigest[0]
};
PeptideWithSetModifications compactPeptide2 = value2.First();
Assert.AreEqual("MNNNSK", value2.First().FullSequence);//this might be base
HashSet <PeptideWithSetModifications> value2mod = new HashSet <PeptideWithSetModifications> {
firstProtDigest[1]
};
PeptideWithSetModifications compactPeptide2mod = value2mod.Last();
Assert.AreEqual("MNNNS[HaHa:resMod on S]K", value2mod.Last().FullSequence);//this might be base
HashSet <PeptideWithSetModifications> value3 = new HashSet <PeptideWithSetModifications> {
firstProtDigest[2]
};
PeptideWithSetModifications compactPeptide3 = value3.First();
Assert.AreEqual("NNNSK", value3.First().FullSequence);//this might be base
HashSet <PeptideWithSetModifications> value3mod = new HashSet <PeptideWithSetModifications> {
firstProtDigest[3]
};
PeptideWithSetModifications compactPeptide3mod = value3mod.Last();
Assert.AreEqual("NNNS[HaHa:resMod on S]K", value3mod.Last().FullSequence);//this might be base
var peptideList = new HashSet <PeptideWithSetModifications>();
foreach (var protein in proteinList)
{
foreach (var peptide in protein.Digest(digestionParams, new List <Modification>(), variableModifications))
{
peptideList.Add(peptide);
}
}
MsDataScan jdfk = new MsDataScan(new MzSpectrum(new double[] { 1 }, new double[] { 1 }, false), 0, 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, 0, null);
Ms2ScanWithSpecificMass ms2scan = new Ms2ScanWithSpecificMass(jdfk, 2, 0, "File", new CommonParameters());
Tolerance fragmentTolerance = new AbsoluteTolerance(0.01);
var match1 = new PeptideSpectralMatch(peptideList.ElementAt(0), 0, 10, 0, ms2scan, digestionParams, new List <MatchedFragmentIon>())
{
};
match1.SetFdrValues(0, 0, 0, 0, 0, 0, 0, 0, 0, false);
var match2 = new PeptideSpectralMatch(peptideList.ElementAt(1), 0, 10, 0, ms2scan, digestionParams, new List <MatchedFragmentIon>())
{
};
match2.SetFdrValues(0, 0, 0, 0, 0, 0, 0, 0, 0, false);
var match3 = new PeptideSpectralMatch(peptideList.ElementAt(1), 0, 10, 0, ms2scan, digestionParams, new List <MatchedFragmentIon>())
{
};
match3.SetFdrValues(0, 0, 0, 0, 0, 0, 0, 0, 0, false);
List <PeptideSpectralMatch> psms = new List <PeptideSpectralMatch>
{
match1,
match2,
match3
};
psms.ForEach(p => p.ResolveAllAmbiguities());
ProteinParsimonyEngine engine = new ProteinParsimonyEngine(psms, true, new CommonParameters(), new List <string> {
"ff"
});
var cool = (ProteinParsimonyResults)engine.Run();
var proteinGroups = cool.ProteinGroups;
ProteinScoringAndFdrEngine f = new ProteinScoringAndFdrEngine(proteinGroups, psms, false, false, true, new CommonParameters(), new List <string>());
f.Run();
Assert.AreEqual("#aa5[resMod on S,info:occupancy=0.67(2/3)];", proteinGroups.First().ModsInfo[0]);
}
private static Tuple <List <PeptideSpectralMatch>, Dictionary <CompactPeptideBase, HashSet <PeptideWithSetModifications> >, MassDiffAcceptor, bool, CompactPeptideBase, CompactPeptideBase> GetInfo(bool localizeable)
{
CommonParameters CommonParameters = new CommonParameters(digestionParams: new DigestionParams(maxMissedCleavages: 0, minPeptideLength: 1, maxModificationIsoforms: 2, initiatorMethionineBehavior: InitiatorMethionineBehavior.Retain, maxModsForPeptides: 1), scoreCutoff: 1);
// Alanine = Glycine + CH2
Protein protein1 = new Protein("MA", "protein1");
Protein protein2 = new Protein("MG", "protein2");
Protein protein3;
double monoisotopicMass = Chemistry.ChemicalFormula.ParseFormula("CH2").MonoisotopicMass;
ModificationMotif.TryGetMotif("G", out ModificationMotif motif1);
ModificationMotif.TryGetMotif("A", out ModificationMotif motif2);
TerminusLocalization modificationSites = TerminusLocalization.Any;
List <ModificationWithMass> allKnownFixedModifications = new List <ModificationWithMass>
{
new ModificationWithMass("CH2 on Glycine", null, motif1, modificationSites, monoisotopicMass)
};
List <ModificationWithMass> variableModifications;
ModificationWithMass alanineMod = new ModificationWithMass("CH2 on Alanine", null, motif2, modificationSites, monoisotopicMass);
if (localizeable)
{
variableModifications = new List <ModificationWithMass>();
IDictionary <int, List <Modification> > oneBasedModifications = new Dictionary <int, List <Modification> >
{
{ 2, new List <Modification> {
alanineMod
} }
};
protein3 = new Protein("MA", "protein3", oneBasedModifications: oneBasedModifications);
}
else
{
variableModifications = new List <ModificationWithMass>();
variableModifications = new List <ModificationWithMass> {
alanineMod
};
protein3 = new Protein("MA", "protein3");
}
var pepWithSetModifications1 = protein1.Digest(CommonParameters.DigestionParams, allKnownFixedModifications, variableModifications).First();
var pepWithSetModifications2 = protein2.Digest(CommonParameters.DigestionParams, allKnownFixedModifications, variableModifications).First();
var pepWithSetModifications3 = protein3.Digest(CommonParameters.DigestionParams, allKnownFixedModifications, variableModifications).Last();
CompactPeptide compactPeptide1 = new CompactPeptide(pepWithSetModifications1, TerminusType.None);
CompactPeptide compactPeptideDuplicate = new CompactPeptide(pepWithSetModifications2, TerminusType.None);
Assert.AreEqual(compactPeptide1, compactPeptideDuplicate);
CompactPeptide compactPeptide2 = new CompactPeptide(pepWithSetModifications3, TerminusType.None);
string fullFilePath = null;
int precursorCharge = 0;
TestDataFile testDataFile = new TestDataFile();
MsDataScan mzLibScan = testDataFile.GetOneBasedScan(2);
Ms2ScanWithSpecificMass scan = new Ms2ScanWithSpecificMass(mzLibScan, 0, precursorCharge, fullFilePath);
int scanIndex = 0;
double score = 0;
int notch = 0;
PeptideSpectralMatch psm1 = new PeptideSpectralMatch(compactPeptide1, notch, score, scanIndex, scan, CommonParameters.DigestionParams);
psm1.SetFdrValues(0, 0, 0, 0, 0, 0, 0, 0, 0, false);
PeptideSpectralMatch psm2 = new PeptideSpectralMatch(compactPeptide1, notch, score, scanIndex, scan, CommonParameters.DigestionParams);
psm2.SetFdrValues(0, 0, 0, 0, 0, 0, 0, 0, 0, false);
PeptideSpectralMatch psm3 = new PeptideSpectralMatch(compactPeptide2, notch, score, scanIndex, scan, CommonParameters.DigestionParams);
psm3.SetFdrValues(0, 0, 0, 0, 0, 0, 0, 0, 0, false);
var newPsms = new List <PeptideSpectralMatch>
{
psm1,
psm2,
psm3
};
MassDiffAcceptor massDiffAcceptors = new SinglePpmAroundZeroSearchMode(5);
SequencesToActualProteinPeptidesEngine stappe = new SequencesToActualProteinPeptidesEngine(newPsms, new List <Protein> {
protein1, protein2, protein3
},
allKnownFixedModifications, variableModifications, new List <ProductType> {
ProductType.B, ProductType.Y
}, new List <DigestionParams> {
CommonParameters.DigestionParams
}, CommonParameters.ReportAllAmbiguity, CommonParameters, new List <string>());
var haha = (SequencesToActualProteinPeptidesEngineResults)stappe.Run();
var compactPeptideToProteinPeptideMatching = haha.CompactPeptideToProteinPeptideMatching;
Assert.AreEqual(2, compactPeptideToProteinPeptideMatching.Count);
psm1.MatchToProteinLinkedPeptides(compactPeptideToProteinPeptideMatching);
bool noOneHitWonders = false;
return(new Tuple <List <PeptideSpectralMatch>, Dictionary <CompactPeptideBase, HashSet <PeptideWithSetModifications> >, MassDiffAcceptor, bool, CompactPeptideBase, CompactPeptideBase>
(
newPsms, compactPeptideToProteinPeptideMatching, massDiffAcceptors, noOneHitWonders, compactPeptide1, compactPeptide2
));
}
public static void ParsimonyDontTreatModifiedFormsAsUnique()
{
bool modPeptidesAreUnique = false;
// set up mods
var modDictionary = new Dictionary <int, List <Modification> >();
ModificationMotif.TryGetMotif("M", out ModificationMotif motif1);
var mod = new Modification(_originalId: "Oxidation of M", _modificationType: "Common Variable", _target: motif1, _locationRestriction: "Anywhere.", _monoisotopicMass: 15.99491461957);
// modified version of protein
var protein1 = new Protein("PEPTIDEM", "accession1");
// unmodified version of protein
var protein2 = new Protein("YYYKPEPTIDEM", "accession2");
List <PeptideWithSetModifications> pwsmsFromProtein1 = protein1.Digest(new DigestionParams(protease: "trypsin", minPeptideLength: 1), new List <Modification> {
mod
}, new List <Modification>()).ToList(); //this is a fixed mod
List <PeptideWithSetModifications> pwsmsFromProtein2 = protein2.Digest(new DigestionParams(protease: "trypsin", minPeptideLength: 1), new List <Modification>(), new List <Modification>()).ToList();
// check to make sure mod is present
PeptideWithSetModifications modifiedPeptide = pwsmsFromProtein1[0];
PeptideWithSetModifications unmodifiedPeptide = pwsmsFromProtein2[1];
Assert.That(!modifiedPeptide.FullSequence.Equals(unmodifiedPeptide.FullSequence)); // sequences should not be equal (one has a mod)
Assert.That(modifiedPeptide.BaseSequence.Equals(unmodifiedPeptide.BaseSequence)); // base sequences should be equal
Assert.That(modifiedPeptide.NumMods == 1); // methionine was oxidized on this protein
Assert.That(unmodifiedPeptide.NumMods == 0); // there was no modification on this protein
// build PSMs for parsimony
List <PeptideSpectralMatch> psmsForParsimony = new List <PeptideSpectralMatch>();
MsDataScan fakeScan = new MsDataScan(new MzSpectrum(new double[] { 1 }, new double[] { 1 }, false),
0, 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, 0, null);
Ms2ScanWithSpecificMass scan = new Ms2ScanWithSpecificMass(fakeScan, 2, 0, "File", new CommonParameters());
PeptideSpectralMatch psm1 = new PeptideSpectralMatch(modifiedPeptide, 0, 10, 1, scan, new DigestionParams(), new List <MatchedFragmentIon>());
psm1.SetFdrValues(0, 0, 0, 0, 0, 0, 0, 0);
psm1.ResolveAllAmbiguities();
PeptideSpectralMatch psm2 = new PeptideSpectralMatch(unmodifiedPeptide, 0, 10, 2, scan, new DigestionParams(), new List <MatchedFragmentIon>());
psm2.SetFdrValues(0, 0, 0, 0, 0, 0, 0, 0);
psm2.ResolveAllAmbiguities();
psmsForParsimony.Add(psm1);
psmsForParsimony.Add(psm2);
// apply parsimony
ProteinParsimonyEngine pae = new ProteinParsimonyEngine(psmsForParsimony, modPeptidesAreUnique, new CommonParameters(), new List <string>());
// because the two chosen peptides are the same, we should end up with both protein accessions still in the list
var proteinParsimonyResult = (ProteinParsimonyResults)pae.Run();
// score protein groups and merge indistinguishable ones
ProteinScoringAndFdrEngine proteinScoringEngine = new ProteinScoringAndFdrEngine(proteinParsimonyResult.ProteinGroups, psmsForParsimony, false, true, true, new CommonParameters(), new List <string>());
var results = (ProteinScoringAndFdrResults)proteinScoringEngine.Run();
int countOfProteinGroups = results.SortedAndScoredProteinGroups.Count;
// because modified peptides were NOT considered as unique,
// then there should be one ambiguous protein group after parsimony,
// and two protein accessions for each peptide
Assert.AreEqual(1, countOfProteinGroups);
Assert.AreEqual(2, results.SortedAndScoredProteinGroups.First().Proteins.Count);
Assert.IsNull(psm1.ProteinAccession);
Assert.IsNull(psm2.ProteinAccession);
}
