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 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 TestModFits()
{
ModificationMotif.TryGetMotif("X", out ModificationMotif motif);
ModificationWithMass attemptToLocalize = new ModificationWithMass(null, null, motif, TerminusLocalization.Any, double.NaN);
Protein protein = new Protein("M", null);
int peptideOneBasedIndex = 1;
int peptideLength = 1;
int proteinOneBasedIndex = 1;
Assert.IsTrue(GptmdEngine.ModFits(attemptToLocalize, protein, peptideOneBasedIndex, peptideLength, proteinOneBasedIndex));
ModificationMotif.TryGetMotif("M", out motif);
attemptToLocalize = new ModificationWithMass(null, null, motif, TerminusLocalization.Any, double.NaN);
Assert.IsTrue(GptmdEngine.ModFits(attemptToLocalize, protein, peptideOneBasedIndex, peptideLength, proteinOneBasedIndex));
ModificationMotif.TryGetMotif("N", out motif);
attemptToLocalize = new ModificationWithMass(null, null, motif, TerminusLocalization.Any, double.NaN);
Assert.IsFalse(GptmdEngine.ModFits(attemptToLocalize, protein, peptideOneBasedIndex, peptideLength, proteinOneBasedIndex));
ModificationMotif.TryGetMotif("Mx", out motif);
attemptToLocalize = new ModificationWithMass(null, null, motif, TerminusLocalization.Any, double.NaN);
Assert.IsFalse(GptmdEngine.ModFits(attemptToLocalize, protein, peptideOneBasedIndex, peptideLength, proteinOneBasedIndex));
ModificationMotif.TryGetMotif("Mr", out motif);
attemptToLocalize = new ModificationWithMass(null, null, motif, TerminusLocalization.Any, double.NaN);
Assert.IsFalse(GptmdEngine.ModFits(attemptToLocalize, protein, peptideOneBasedIndex, peptideLength, proteinOneBasedIndex));
ModificationMotif.TryGetMotif("xM", out motif);
attemptToLocalize = new ModificationWithMass(null, null, motif, TerminusLocalization.Any, double.NaN);
Assert.IsFalse(GptmdEngine.ModFits(attemptToLocalize, protein, peptideOneBasedIndex, peptideLength, proteinOneBasedIndex));
ModificationMotif.TryGetMotif("Nxs", out motif);
attemptToLocalize = new ModificationWithMass(null, null, motif, TerminusLocalization.Any, double.NaN);
protein = new Protein("MNRS", null);
peptideOneBasedIndex = 1;
peptideLength = 1;
proteinOneBasedIndex = 1;
Assert.IsFalse(GptmdEngine.ModFits(attemptToLocalize, protein, peptideOneBasedIndex, peptideLength, proteinOneBasedIndex));
ModificationMotif.TryGetMotif("Nxs", out motif);
attemptToLocalize = new ModificationWithMass(null, null, motif, TerminusLocalization.Any, double.NaN);
protein = new Protein("MNRS", null);
peptideOneBasedIndex = 1;
peptideLength = 1;
proteinOneBasedIndex = 1;
Assert.IsFalse(GptmdEngine.ModFits(attemptToLocalize, protein, peptideOneBasedIndex, peptideLength, proteinOneBasedIndex));
peptideOneBasedIndex = 2;
peptideLength = 1;
proteinOneBasedIndex = 2;
Assert.IsTrue(GptmdEngine.ModFits(attemptToLocalize, protein, peptideOneBasedIndex, peptideLength, proteinOneBasedIndex));
protein = new Protein("MNRN", null);
Assert.IsFalse(GptmdEngine.ModFits(attemptToLocalize, protein, peptideOneBasedIndex, peptideLength, proteinOneBasedIndex));
}
public static void TestUniProtGptmdConflict()
{
// this unit test checks to make sure GPTMD does not annotate mods at residues on
// proteins where the equivalent uniprot mod already exists
Modification uniProtPhospho = GlobalVariables.AllModsKnown.First(p => p.ModificationType == "UniProt" && p.IdWithMotif.Contains("Phosphoserine"));
Modification mmPhospho = GlobalVariables.AllModsKnown.First(p => p.ModificationType == "Common Biological" && p.IdWithMotif.Contains("Phosphorylation on S"));
Protein protein = new Protein("PEPTIDESK", "test",
oneBasedModifications: new Dictionary <int, List <Modification> >()
{
{ 8, new List <Modification> {
uniProtPhospho
} }
});
PeptideWithSetModifications pep = protein.Digest(new DigestionParams(), new List <Modification>(), new List <Modification>()).First(p => p.AllModsOneIsNterminus.Count == 0);
// mod should not fit anywhere on the protein
for (int i = 0; i < pep.Length; i++)
{
bool modFits = GptmdEngine.ModFits(mmPhospho, protein, i + 1, pep.Length, pep.OneBasedStartResidueInProtein + i);
Assert.That(!modFits);
}
// the following code is just a control to make sure the phosphorylation actually does fit
// at the given residue if the UniProt phosphorylation is not already present
var someOtherSMod = GlobalVariables.AllModsKnown.Where(p => p.ModificationType == "Common Biological" && p.IdWithMotif.Contains("HexNAc on S")).First();
protein = new Protein("PEPTIDESK", "test",
oneBasedModifications: new Dictionary <int, List <Modification> >()
{
{ 8, new List <Modification> {
someOtherSMod
} }
});
pep = protein.Digest(new DigestionParams(), new List <Modification>(), new List <Modification>()).First(p => p.AllModsOneIsNterminus.Count == 0);
// mod should fit at position 8
for (int i = 0; i < pep.Length; i++)
{
bool modFits = GptmdEngine.ModFits(mmPhospho, protein, i + 1, pep.Length, pep.OneBasedStartResidueInProtein + i);
if (i + 1 == 8)
{
Assert.That(modFits);
}
else
{
Assert.That(!modFits);
}
}
}
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 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 Test_GptmdEngineModFits(string targetAminoAcid, string proteinSequence, string locationRestriction, int peptideOneBasedIndex, int peptideLength, int proteinOneBasedIndex, bool result)
{
ModificationMotif.TryGetMotif(targetAminoAcid, out ModificationMotif motif);
Modification attemptToLocalize = new Modification(null, null, null, null, _target: motif, _locationRestriction: locationRestriction, _chemicalFormula: null, _monoisotopicMass: 1, _databaseReference: null, _taxonomicRange: null, _keywords: null, _neutralLosses: null, _diagnosticIons: null, _fileOrigin: null);
Dictionary <int, List <Modification> > oneBasedModifications = new Dictionary <int, List <Modification> >();
oneBasedModifications.Add(proteinOneBasedIndex, new List <Modification>()
{
attemptToLocalize
});
Protein protein = new Protein(proteinSequence, null, null, null, oneBasedModifications, null, null, null, false, false, null, null, null, null, null, null, "");
Assert.AreEqual(result, GptmdEngine.ModFits(attemptToLocalize, protein, peptideOneBasedIndex, peptideLength, proteinOneBasedIndex));
}
