public static void PostSearchNormalizeTest()
{
SearchTask searchTask = new SearchTask()
{
SearchParameters = new SearchParameters
{
Normalize = true
},
};
string myFile = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestData\PrunedDbSpectra.mzml");
string myDatabase = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestData\DbForPrunedDb.fasta");
string folderPath = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestNormalizationExperDesign");
string experimentalDesignFile = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestData\ExperimentalDesign.tsv");
using (StreamWriter output = new StreamWriter(experimentalDesignFile))
{
output.WriteLine("FileName\tCondition\tBiorep\tFraction\tTechrep");
output.WriteLine("PrunedDbSpectra.mzml" + "\t" + "condition" + "\t" + "1" + "\t" + "1" + "\t" + "1");
}
DbForTask db = new DbForTask(myDatabase, false);
// run the task
Directory.CreateDirectory(folderPath);
searchTask.RunTask(folderPath, new List <DbForTask> {
db
}, new List <string> {
myFile
}, "normal");
Directory.Delete(folderPath, true);
// delete the exper design and try again. this should skip quantification
File.Delete(experimentalDesignFile);
// run the task
Directory.CreateDirectory(folderPath);
searchTask.RunTask(folderPath, new List <DbForTask> {
db
}, new List <string> {
myFile
}, "normal");
// PSMs should be present but no quant output
Assert.That(!File.Exists(Path.Combine(folderPath, "AllQuantifiedPeptides.tsv")));
Assert.That(File.Exists(Path.Combine(folderPath, "AllPSMs.psmtsv")));
Directory.Delete(folderPath, true);
}
public static void ProteinGroupsNoParsimonyTest()
{
SearchTask searchTask = new SearchTask()
{
SearchParameters = new SearchParameters
{
DoParsimony = false
},
};
string myFile = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestData\PrunedDbSpectra.mzml");
string myDatabase = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestData\DbForPrunedDb.fasta");
string folderPath = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestProteinGroupsNoParsimony");
DbForTask db = new DbForTask(myDatabase, false);
Directory.CreateDirectory(folderPath);
searchTask.RunTask(folderPath, new List <DbForTask> {
db
}, new List <string> {
myFile
}, "normal");
Directory.Delete(folderPath, true);
}
public static void PrunedDbWithContaminantsTest()
{
SearchTask searchTask = new SearchTask()
{
SearchParameters = new SearchParameters
{
WritePrunedDatabase = true
},
};
string myFile = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestData\PrunedDbSpectra.mzml");
string myDatabase = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestData\DbForPrunedDb.fasta");
string folderPath = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestNormalization");
string filePath = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestData\ExperimentalDesign.tsv");
// contaminant DB
DbForTask db = new DbForTask(myDatabase, true);
Directory.CreateDirectory(folderPath);
searchTask.RunTask(folderPath, new List <DbForTask> {
db
}, new List <string> {
myFile
}, "normal");
Assert.That(File.ReadAllLines(Path.Combine(folderPath, @"DbForPrunedDbproteinPruned.xml")).Length > 0);
Assert.That(File.ReadAllLines(Path.Combine(folderPath, @"DbForPrunedDbPruned.xml")).Length > 0);
Directory.Delete(folderPath, true);
}
public static void TestMetaDrawReadPsmFile()
{
SearchTask searchTask = new SearchTask();
string myFile = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestData\PrunedDbSpectra.mzml");
string myDatabase = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestData\DbForPrunedDb.fasta");
string folderPath = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestMetaDrawReadPsmFile");
DbForTask db = new DbForTask(myDatabase, false);
Directory.CreateDirectory(folderPath);
searchTask.RunTask(folderPath, new List <DbForTask> {
db
}, new List <string> {
myFile
}, "metadraw");
string psmFile = Directory.GetFiles(folderPath).First(f => f.Contains("AllPSMs.psmtsv"));
List <PsmFromTsv> parsedPsms = PsmTsvReader.ReadTsv(psmFile, out var warnings);
Assert.AreEqual(11, parsedPsms.Count);
Assert.AreEqual(0, warnings.Count);
Directory.Delete(folderPath, true);
}
public static void TestPsmFromTsvIonParsing()
{
string outputFolder = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestPsmFromTsvIonParsing");
string proteinDatabase = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestData\SpectralLibrarySearch\P16858.fasta");
string spectraFile = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestData\SpectralLibrarySearch\slicedMouse.raw");
Directory.CreateDirectory(outputFolder);
// run search task
var searchtask = new SearchTask();
searchtask.RunTask(outputFolder,
new List <DbForTask>
{
new DbForTask(proteinDatabase, false),
},
new List <string> {
spectraFile
}, "");
var psmFile = Path.Combine(outputFolder, @"AllPSMs.psmtsv");
// load results into metadraw
var metadrawLogic = new MetaDrawLogic();
metadrawLogic.SpectraFilePaths.Add(spectraFile);
metadrawLogic.PsmResultFilePaths.Add(psmFile);
var errors = metadrawLogic.LoadFiles(true, true);
Assert.That(!errors.Any());
// assert PsmFromTsv matched ion properties
var lines = File.ReadAllLines(psmFile);
int ind = Array.IndexOf(lines[0].Split('\t'), "Matched Ion Mass-To-Charge Ratios");
var ionStrings = lines[1].Split('\t')[ind].Split(new char[] { ',', ';' })
.Select(p => p.Trim().Replace("[", string.Empty).Replace("]", string.Empty)).ToList();
var parsedIons = metadrawLogic.FilteredListOfPsms[0].MatchedIons;
for (int i = 0; i < ionStrings.Count; i++)
{
var ionString = ionStrings[i];
var parsedIon = parsedIons[i];
var split = ionString.Split(new char[] { '+', ':' });
string ion = split[0];
int charge = int.Parse(split[1]);
double mz = double.Parse(split[2]);
Assert.That(mz == parsedIon.Mz);
Assert.That(mz.ToMass(charge) == parsedIon.NeutralTheoreticalProduct.NeutralMass);
Assert.That(charge == parsedIon.Charge);
Assert.That(ion == parsedIon.NeutralTheoreticalProduct.ProductType.ToString() + parsedIon.NeutralTheoreticalProduct.FragmentNumber);
}
// delete output
Directory.Delete(outputFolder, true);
}
public static void TestMetaDrawLoadingWithWeirdFileNames()
{
// test loading when the file has a periods, commas, spaces in the name
string outputFolder = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestMetaDrawLoadingWithWeirdFileNames");
string proteinDatabase = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestData\smalldb.fasta");
string spectraFile = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestData\SmallCalibratible_Yeast.mzML");
string pathWithPeriodInIt = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestData\S.m,al. lC,al.ib r.at,i ble_Ye.ast.mzML");
File.Copy(spectraFile, pathWithPeriodInIt, true);
spectraFile = pathWithPeriodInIt;
Directory.CreateDirectory(outputFolder);
// run search task
var searchtask = new SearchTask();
searchtask.RunTask(outputFolder, new List <DbForTask> {
new DbForTask(proteinDatabase, false)
}, new List <string> {
spectraFile
}, "");
var psmFile = Path.Combine(outputFolder, @"AllPSMs.psmtsv");
// load results into metadraw
var metadrawLogic = new MetaDrawLogic();
metadrawLogic.PsmResultFilePaths.Add(psmFile);
metadrawLogic.SpectraFilePaths.Add(pathWithPeriodInIt);
var errors = metadrawLogic.LoadFiles(true, true);
Assert.That(!errors.Any());
Assert.That(metadrawLogic.FilteredListOfPsms.First().FileNameWithoutExtension == "S.m,al. lC,al.ib r.at,i ble_Ye.ast");
var plotView = new OxyPlot.Wpf.PlotView();
var canvas = new Canvas();
var parentChildScanPlotsView = new ParentChildScanPlotsView();
// plot PSM
metadrawLogic.DisplaySpectrumMatch(plotView, canvas, metadrawLogic.FilteredListOfPsms.First(), parentChildScanPlotsView, out errors);
Assert.That(errors == null || !errors.Any());
// export to PDF
metadrawLogic.ExportToPdf(plotView, canvas, new List <PsmFromTsv> {
metadrawLogic.FilteredListOfPsms.First()
}, parentChildScanPlotsView, outputFolder, out errors);
Assert.That(!errors.Any());
// clean up resources
metadrawLogic.CleanUpResources();
// delete output
File.Delete(pathWithPeriodInIt);
Directory.Delete(outputFolder, true);
}
public static void TestMetaDrawErrors()
{
string outputFolder = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestMetaDrawErrors");
string proteinDatabase = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestData\smalldb.fasta");
string spectraFile = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestData\SmallCalibratible_Yeast.mzML");
Directory.CreateDirectory(outputFolder);
// run search task
var searchtask = new SearchTask();
searchtask.RunTask(outputFolder, new List <DbForTask> {
new DbForTask(proteinDatabase, false)
}, new List <string> {
spectraFile
}, "");
var psmFile = Path.Combine(outputFolder, @"AllPSMs.psmtsv");
// load results into metadraw (skipping spectra file, to produce an error msg)
var metadrawLogic = new MetaDrawLogic();
metadrawLogic.PsmResultFilePaths.Add(psmFile);
// this should produce an error because an expected spectra file is not present
var errors = metadrawLogic.LoadFiles(loadSpectra: true, loadPsms: true);
Assert.That(errors.Any());
Assert.That(!metadrawLogic.FilteredListOfPsms.Any());
// this should not produce an error because we said not to load spectra
errors = metadrawLogic.LoadFiles(loadSpectra: false, loadPsms: true);
Assert.That(!errors.Any());
var psmsFromTsv = PsmTsvReader.ReadTsv(psmFile, out var warnings);
var plotView = new OxyPlot.Wpf.PlotView();
var canvas = new Canvas();
var parentChildScanPlotsView = new ParentChildScanPlotsView();
// plotting PSM should produce an error because spectra are not loaded
metadrawLogic.DisplaySpectrumMatch(plotView, canvas, psmsFromTsv.First(), parentChildScanPlotsView, out errors);
Assert.That(errors.Any());
// export to PDF should produce an error because spectra are not loaded
metadrawLogic.ExportToPdf(plotView, canvas, new List <PsmFromTsv> {
psmsFromTsv.First()
}, parentChildScanPlotsView, outputFolder, out errors);
Assert.That(errors.Any());
// clean up resources
metadrawLogic.CleanUpResources();
// delete output
Directory.Delete(outputFolder, true);
}
public static void PostSearchNormalizeTest()
{
SearchTask searchTask = new SearchTask()
{
SearchParameters = new SearchParameters
{
Normalize = true
},
};
string myFile = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestData\PrunedDbSpectra.mzml");
string myDatabase = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestData\DbForPrunedDb.fasta");
string folderPath = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestNormalization");
string filePath = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestData\ExperimentalDesign.tsv");
using (StreamWriter output = new StreamWriter(filePath))
{
output.WriteLine("FileName\tCondition\tBiorep\tFraction\tTechrep");
output.WriteLine("PrunedDbSpectra" + "\t" + "condition" + "\t" + "1" + "\t" + "1" + "\t" + "1");
}
DbForTask db = new DbForTask(myDatabase, false);
Directory.CreateDirectory(folderPath);
searchTask.RunTask(folderPath, new List <DbForTask> {
db
}, new List <string> {
myFile
}, "normal");
File.Delete(filePath);
Assert.That(() => searchTask.RunTask(folderPath, new List <DbForTask> {
db
}, new List <string> {
myFile
}, "normal"),
Throws.TypeOf <MetaMorpheusException>());
Directory.Delete(folderPath, true);
}
public static void TestSilacWhenProteinIsMissing()
{
//make heavy residue and add to search task
Residue heavyLysine = new Residue("a", 'a', "a", Chemistry.ChemicalFormula.ParseFormula("C{13}6H12N{15}2O"), ModificationSites.All); //+8 lysine
Residue lightLysine = Residue.GetResidue('K');
SearchTask task = new SearchTask
{
SearchParameters = new SearchParameters
{
SilacLabels = new List <SilacLabel> {
new SilacLabel(lightLysine.Letter, heavyLysine.Letter, heavyLysine.ThisChemicalFormula.Formula, heavyLysine.MonoisotopicMass - lightLysine.MonoisotopicMass)
},
NoOneHitWonders = true
//The NoOneHitWonders=true doesn't really seem like a SILAC test, but we're testing that there's no crash if a quantified peptide's proteinGroup isn't quantified
//This happens if somebody messed with parsimony (picked TDS) or from requiring two peptides per protein (and we're only finding one). We're testing the second case here.
}
};
PeptideWithSetModifications lightPeptide = new PeptideWithSetModifications("PEPTIDEK", new Dictionary <string, Modification>());
List <double> massDifferences = new List <double> {
heavyLysine.MonoisotopicMass - lightLysine.MonoisotopicMass
};
MsDataFile myMsDataFile1 = new TestDataFile(lightPeptide, massDifferences);
string mzmlName = @"silac.mzML";
IO.MzML.MzmlMethods.CreateAndWriteMyMzmlWithCalibratedSpectra(myMsDataFile1, mzmlName, false);
string xmlName = "SilacDb.xml";
Protein theProtein = new Protein("PEPTIDEK", "accession1");
ProteinDbWriter.WriteXmlDatabase(new Dictionary <string, HashSet <Tuple <int, Modification> > >(), new List <Protein> {
theProtein
}, xmlName);
string outputFolder = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestSilac");
Directory.CreateDirectory(outputFolder);
var theStringResult = task.RunTask(outputFolder, new List <DbForTask> {
new DbForTask(xmlName, false)
}, new List <string> {
mzmlName
}, "taskId1").ToString();
}
public void MoreTests(string filename, DecoyType decoyType = DecoyType.None)
{
string xmlName = Path.Combine(TestContext.CurrentContext.TestDirectory, "TestData", filename);
var proteins = ProteinDbLoader.LoadProteinXML(xmlName, decoyType == DecoyType.None, decoyType, null, false, null, out var un);
var peps = proteins[1].Digest(CommonParameters.DigestionParams, null, null).ToList();
PeptideWithSetModifications pep = peps[peps.Count - 2];
string mzmlName = $"ajgdiv{filename}{decoyType.ToString()}.mzML";
MsDataFile myMsDataFile = new TestDataFile(new List <PeptideWithSetModifications> {
pep
});
IO.MzML.MzmlMethods.CreateAndWriteMyMzmlWithCalibratedSpectra(myMsDataFile, mzmlName, false);
string outputFolder = Path.Combine(TestContext.CurrentContext.TestDirectory, $"TestSearchWithVariants{filename}{decoyType.ToString()}");
Directory.CreateDirectory(outputFolder);
SearchTask st = new SearchTask
{
SearchParameters = new SearchParameters
{
DoParsimony = true,
DecoyType = decoyType,
SearchTarget = decoyType == DecoyType.None,
ModPeptidesAreDifferent = false
},
CommonParameters = new CommonParameters(scoreCutoff: 1, digestionParams: new DigestionParams(minPeptideLength: 2), precursorMassTolerance: new PpmTolerance(20)),
};
st.RunTask(outputFolder, new List <DbForTask> {
new DbForTask(xmlName, false)
}, new List <string> {
mzmlName
}, "");
var psms = File.ReadAllLines(Path.Combine(outputFolder, "AllPSMs.psmtsv"));
//Assert.IsTrue(psms.Any(line => line.Contains($"\t{variantPsmShort}\t" + (containsVariant ? variantPsmShort : "\t"))));
Directory.Delete(outputFolder, true);
File.Delete(mzmlName);
//Directory.Delete(Path.Combine(TestContext.CurrentContext.TestDirectory, @"Task Settings"), true);
}
public static void SpectralLibrarySearchTest()
{
var testDir = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestData\SpectralLibrarySearch");
var outputDir = Path.Combine(testDir, @"SpectralLibrarySearchTest");
string library1 = Path.Combine(testDir, @"P16858_target.msp");
string library2 = Path.Combine(testDir, @"P16858_decoy.msp");
string fastaDb = Path.Combine(testDir, @"P16858.fasta");
string spectraFile = Path.Combine(testDir, @"slicedMouse.raw");
Directory.CreateDirectory(outputDir);
var searchTask = new SearchTask();
searchTask.RunTask(outputDir,
new List <DbForTask>
{
new DbForTask(library1, false),
new DbForTask(library2, false),
new DbForTask(fastaDb, false)
},
new List <string> {
spectraFile
},
"");
var results = File.ReadAllLines(Path.Combine(outputDir, @"AllPSMs.psmtsv"));
var split = results[0].Split('\t');
int ind = Array.IndexOf(split, "Normalized Spectral Angle");
Assert.That(ind >= 0);
var spectralAngle = double.Parse(results[1].Split('\t')[ind]);
Assert.That(Math.Round(spectralAngle, 2) == 0.82);
Directory.Delete(outputDir, true);
}
public static void FdrFilteredParsimonyTest()
{
SearchTask Task1 = new SearchTask
{
CommonParameters = new CommonParameters
(
qValueOutputFilter: 1
),
SearchParameters = new SearchParameters
{
DoParsimony = true,
SearchTarget = true,
WritePrunedDatabase = true,
SearchType = SearchType.Classic
}
};
string mzmlName = @"TestData\PrunedDbSpectra.mzml";
string fastaName = @"TestData\DbForPrunedDb.fasta";
var results = Task1.RunTask(Environment.CurrentDirectory, new List <DbForTask>()
{
new DbForTask(fastaName, false)
}, new List <string>()
{
mzmlName
}, "test");
var thisTaskOutputFolder = MySetUpClass.outputFolder;
var psms = Path.Combine(thisTaskOutputFolder, "AllPSMs.psmtsv");
Assert.AreEqual(12, File.ReadLines(psms).Count());
var protGroups = Path.Combine(thisTaskOutputFolder, "AllProteinGroups.tsv");
Assert.AreEqual(7, File.ReadLines(protGroups).Count());
}
public static void TestProteinSplitAcrossFiles()
{
SearchTask st = new SearchTask()
{
CommonParameters = new CommonParameters(
scoreCutoff: 1,
digestionParams: new DigestionParams(
maxMissedCleavages: 0,
minPeptideLength: 5,
initiatorMethionineBehavior: InitiatorMethionineBehavior.Retain)),
SearchParameters = new SearchParameters
{
DoHistogramAnalysis = true,
MassDiffAcceptorType = MassDiffAcceptorType.Open,
MatchBetweenRuns = true,
DoQuantification = true
},
};
string proteinDbFilePath = Path.Combine(TestContext.CurrentContext.TestDirectory, "TestProteinSplitAcrossFiles.xml");
string mzmlFilePath1 = Path.Combine(TestContext.CurrentContext.TestDirectory, "TestProteinSplitAcrossFiles1.mzML");
string mzmlFilePath2 = Path.Combine(TestContext.CurrentContext.TestDirectory, "TestProteinSplitAcrossFiles2.mzML");
ModificationMotif.TryGetMotif("D", out ModificationMotif motif);
Modification mod = new Modification(_originalId: "mod1 on D", _modificationType: "mt", _target: motif, _locationRestriction: "Anywhere.", _monoisotopicMass: 10);
IDictionary <int, List <Modification> > oneBasedModification = new Dictionary <int, List <Modification> >
{
{ 3, new List <Modification> {
mod
} }
};
Protein prot1 = new Protein("MEDEEK", "prot1", oneBasedModifications: oneBasedModification);
var pep1 = prot1.Digest(st.CommonParameters.DigestionParams, new List <Modification>(), new List <Modification>()).First();
var pep2 = prot1.Digest(st.CommonParameters.DigestionParams, new List <Modification>(), new List <Modification>()).Last();
List <PeptideWithSetModifications> listForFile1 = new List <PeptideWithSetModifications> {
pep1, pep2
};
List <PeptideWithSetModifications> listForFile2 = new List <PeptideWithSetModifications> {
pep2
};
MsDataFile myMsDataFile1 = new TestDataFile(listForFile1);
MsDataFile myMsDataFile2 = new TestDataFile(listForFile2);
List <Protein> proteinList = new List <Protein> {
prot1
};
IO.MzML.MzmlMethods.CreateAndWriteMyMzmlWithCalibratedSpectra(myMsDataFile1, mzmlFilePath1, false);
IO.MzML.MzmlMethods.CreateAndWriteMyMzmlWithCalibratedSpectra(myMsDataFile2, mzmlFilePath2, false);
ProteinDbWriter.WriteXmlDatabase(new Dictionary <string, HashSet <Tuple <int, Modification> > >(), proteinList, proteinDbFilePath);
string output_folder = Path.Combine(TestContext.CurrentContext.TestDirectory, "TestProteinSplitAcrossFiles");
Directory.CreateDirectory(output_folder);
st.RunTask(
output_folder,
new List <DbForTask> {
new DbForTask(proteinDbFilePath, false)
},
new List <string> {
mzmlFilePath1, mzmlFilePath2,
},
null);
Directory.Delete(output_folder, true);
File.Delete(proteinDbFilePath);
File.Delete(mzmlFilePath1);
File.Delete(mzmlFilePath2);
Directory.Delete(Path.Combine(TestContext.CurrentContext.TestDirectory, @"Task Settings"), true);
}
public static void TestBinGeneration()
{
SearchTask st = new SearchTask
{
CommonParameters = new CommonParameters(scoreCutoff: 1, digestionParams: new DigestionParams(minPeptideLength: 5, initiatorMethionineBehavior: InitiatorMethionineBehavior.Retain)),
SearchParameters = new SearchParameters
{
DoHistogramAnalysis = true,
MassDiffAcceptorType = MassDiffAcceptorType.Open,
DecoyType = DecoyType.None,
DoParsimony = true,
DoQuantification = true
},
};
string proteinDbFilePath = Path.Combine(TestContext.CurrentContext.TestDirectory, "BinGenerationTest.xml");
string mzmlFilePath = Path.Combine(TestContext.CurrentContext.TestDirectory, "BinGenerationTest.mzML");
Protein prot1 = new Protein("MEDEEK", "prot1");
Protein prot2 = new Protein("MENEEK", "prot2");
ModificationMotif.TryGetMotif("D", out ModificationMotif motif);
Modification mod = new Modification(_target: motif, _locationRestriction: "Anywhere.", _monoisotopicMass: 10);
var pep1_0 = prot1.Digest(st.CommonParameters.DigestionParams, new List <Modification>(), new List <Modification>()).First();
var pep1_10 = prot1.Digest(st.CommonParameters.DigestionParams, new List <Modification>(), new List <Modification>()).Last();
Protein prot3 = new Protein("MAAADAAAAAAAAAAAAAAA", "prot3");
var pep2_0 = prot3.Digest(st.CommonParameters.DigestionParams, new List <Modification>(), new List <Modification>()).First();
var pep2_10 = prot3.Digest(st.CommonParameters.DigestionParams, new List <Modification>(), new List <Modification> {
mod
}).Last();
Protein prot4 = new Protein("MNNDNNNN", "prot4");
var pep3_10 = prot4.Digest(st.CommonParameters.DigestionParams, new List <Modification>(), new List <Modification> {
mod
}).Last();
List <PeptideWithSetModifications> pepsWithSetMods = new List <PeptideWithSetModifications> {
pep1_0, pep1_10, pep2_0, pep2_10, pep3_10
};
MsDataFile myMsDataFile = new TestDataFile(pepsWithSetMods);
List <Protein> proteinList = new List <Protein> {
prot1, prot2, prot3, prot4
};
IO.MzML.MzmlMethods.CreateAndWriteMyMzmlWithCalibratedSpectra(myMsDataFile, mzmlFilePath, false);
ProteinDbWriter.WriteXmlDatabase(new Dictionary <string, HashSet <Tuple <int, Modification> > >(), proteinList, proteinDbFilePath);
string output_folder = Path.Combine(TestContext.CurrentContext.TestDirectory, "TestBinGeneration");
Directory.CreateDirectory(output_folder);
st.RunTask(
output_folder,
new List <DbForTask> {
new DbForTask(proteinDbFilePath, false)
},
new List <string> {
mzmlFilePath
},
null);
Assert.AreEqual(3, File.ReadLines(Path.Combine(output_folder, @"MassDifferenceHistogram.tsv")).Count());
Directory.Delete(output_folder, true);
File.Delete(proteinDbFilePath);
File.Delete(mzmlFilePath);
Directory.Delete(Path.Combine(TestContext.CurrentContext.TestDirectory, @"Task Settings"), true);
}
public static void TestProteinPrunedWithModSelectionAndVariants()
{
var modToWrite = GlobalVariables.AllModsKnown.Where(p => p.ModificationType == "UniProt" && p.Target.ToString() == "T").First();
var modToNotWrite = GlobalVariables.AllModsKnown.Where(p => p.ModificationType == "Common Artifact" && p.Target.ToString() == "X").First();
Dictionary <int, List <Modification> > variantMods = new Dictionary <int, List <Modification> >();
variantMods.Add(1, new List <Modification>()
{
modToNotWrite
});
List <SequenceVariation> variants = new List <SequenceVariation> {
new SequenceVariation(4, 4, "V", "T", @"20\t41168825\t.\tT\tC\t14290.77\t.\tANN=C|missense_variant|MODERATE|PLCG1|ENSG00000124181|transcript|ENST00000244007.7|protein_coding|22/33|c.2438T>C|p.Ile813Thr|2635/5285|2438/3876|813/1291||\tGT:AD:DP:GQ:PL\t1/1:1,392:393:99:14319,1142,0", variantMods)
};
var protein1 = new Protein("PEPVIDEKPEPT", "1", oneBasedModifications: new Dictionary <int, List <Modification> > {
{ 1, new List <Modification> {
modToNotWrite
} }, { 12, new List <Modification> {
modToWrite
} }
}, sequenceVariations: variants);
var protein2 = new Protein("PEPIDPEPT", "2", oneBasedModifications: new Dictionary <int, List <Modification> > {
{ 1, new List <Modification> {
modToNotWrite
} }, { 9, new List <Modification> {
modToWrite
} }
});
var protein1Variants = protein1.GetVariantProteins(1, 0);
string path = @"temp";
var proteinList = new List <Protein> {
protein1, protein2
};
proteinList.AddRange(protein1Variants);
ProteinDbWriter.WriteXmlDatabase(new Dictionary <string, HashSet <Tuple <int, Modification> > >(), proteinList, path);
Directory.CreateDirectory(Path.Combine(TestContext.CurrentContext.TestDirectory, @"PrunedDbTestVariant"));
Dictionary <string, HashSet <Tuple <int, Modification> > > modList = new Dictionary <string, HashSet <Tuple <int, Modification> > >();
var Hash = new HashSet <Tuple <int, Modification> >
{
new Tuple <int, Modification>(1, modToWrite),
new Tuple <int, Modification>(2, modToNotWrite),
};
var db = ProteinDbWriter.WriteXmlDatabase(modList, proteinList, Path.Combine(TestContext.CurrentContext.TestDirectory, @"PrunedDbTestVariant/fakeDb.xml"));
var peptideObserved = protein1Variants.First().Digest(new DigestionParams(minPeptideLength: 1), new List <Modification>(), new List <Modification>())
.Where(p => p.BaseSequence == "PEPT").First();
PostSearchAnalysisParameters testPostTaskParameters = new PostSearchAnalysisParameters();
CommonParameters commonParam = new CommonParameters(useDeltaScore: false);
double[,] noiseData = new double[10000, 10000];
noiseData[0, 0] = 1.0;
List <Proteomics.Fragmentation.MatchedFragmentIon> matchedFragmentIons = new List <Proteomics.Fragmentation.MatchedFragmentIon>()
{
};
MzSpectrum spectrum = new MzSpectrum(noiseData);
MsDataScan scan = new MsDataScan(spectrum, 1, 1, true, Polarity.Unknown, 2, new MzLibUtil.MzRange(10, 1000), "", MZAnalyzerType.Orbitrap, 10000, null, noiseData, "");
testPostTaskParameters.ProteinList = proteinList;
testPostTaskParameters.AllPsms = new List <PeptideSpectralMatch> {
new PeptideSpectralMatch(peptideObserved, 0, 20, 1, new Ms2ScanWithSpecificMass(scan, 100, 1, @"", commonParam), commonParam, matchedFragmentIons)
};
testPostTaskParameters.SearchParameters = new SearchParameters();
testPostTaskParameters.SearchParameters.WritePrunedDatabase = true;
testPostTaskParameters.SearchParameters.DoQuantification = false;
testPostTaskParameters.SearchParameters.WriteMzId = false;
testPostTaskParameters.DatabaseFilenameList = new List <DbForTask>()
{
new DbForTask(Path.Combine(TestContext.CurrentContext.TestDirectory, @"PrunedDbTest/fakeDb.xml"), false)
};
testPostTaskParameters.OutputFolder = Path.Combine(TestContext.CurrentContext.TestDirectory, @"PrunedDbTest");
Directory.CreateDirectory(Path.Combine(TestContext.CurrentContext.TestDirectory, @"PrunedDbTest/individual"));
testPostTaskParameters.IndividualResultsOutputFolder = Path.Combine(TestContext.CurrentContext.TestDirectory, @"PrunedDbTest/individual");
int[] stuffForSpectraFile = new int[2];
stuffForSpectraFile[0] = 10;
stuffForSpectraFile[1] = 10;
Dictionary <string, int[]> numSpectraPerFile = new Dictionary <string, int[]>();
numSpectraPerFile.Add("", stuffForSpectraFile);
testPostTaskParameters.NumMs2SpectraPerFile = numSpectraPerFile;
MsDataFile myMsDataFile = new TestDataFile(new List <PeptideWithSetModifications>
{
peptideObserved
});
string mzmlName = @"newMzml.mzML";
IO.MzML.MzmlMethods.CreateAndWriteMyMzmlWithCalibratedSpectra(myMsDataFile, mzmlName, false);
modList.Add("test", Hash);
testPostTaskParameters.CurrentRawFileList = new List <string>()
{
mzmlName
};
SearchTask task5 = new SearchTask
{
SearchParameters = new SearchParameters
{
WritePrunedDatabase = true,
SearchTarget = true,
MassDiffAcceptorType = MassDiffAcceptorType.Exact,
},
CommonParameters = new CommonParameters()
};
var test = task5.RunTask(Path.Combine(TestContext.CurrentContext.TestDirectory, @"PrunedDbTest"), new List <DbForTask>()
{
new DbForTask(Path.Combine(TestContext.CurrentContext.TestDirectory, @"PrunedDbTest/fakeDb.xml"), false)
}, new List <string>()
{
mzmlName
}, "name");
testPostTaskParameters.SearchTaskResults = test;
PostSearchAnalysisTask testPostTask = new PostSearchAnalysisTask();
testPostTask.Parameters = testPostTaskParameters;
testPostTask.CommonParameters = commonParam;
testPostTask.FileSpecificParameters = new List <(string FileName, CommonParameters Parameters)> {
("newMzMl.mzml", commonParam)
};
testPostTask.Run();
var proteinsLoaded = ProteinDbLoader.LoadProteinXML(path, true, DecoyType.None, GlobalVariables.AllModsKnown, false, new List <string>(), out var unknownMods);
// assert that mods on proteins are the same before/after task is run
Assert.AreEqual(protein1Variants.First().Accession, proteinsLoaded.First().Accession);
Assert.AreEqual(protein1Variants.First().OneBasedPossibleLocalizedModifications.Count(), proteinsLoaded.First().OneBasedPossibleLocalizedModifications.Count());
Assert.AreEqual(protein2.OneBasedPossibleLocalizedModifications.Count(), proteinsLoaded.ElementAt(1).OneBasedPossibleLocalizedModifications.Count());
// assert that protein pruned DB has correct proteins mods
var proteinPruned = ProteinDbLoader.LoadProteinXML(Path.Combine(TestContext.CurrentContext.TestDirectory, @"PrunedDbTest/fakeDbproteinPruned.xml"), true, DecoyType.None, GlobalVariables.AllModsKnown, false, new List <string>(), out var unknownMods1);
Assert.That(proteinPruned.Count().Equals(1));
Assert.That(proteinPruned.FirstOrDefault().OneBasedPossibleLocalizedModifications.Count().Equals(1));
// assert that mod-pruned DB has correct proteins and mods
var modPruned = ProteinDbLoader.LoadProteinXML(Path.Combine(TestContext.CurrentContext.TestDirectory, @"PrunedDbTest/fakeDbpruned.xml"), true, DecoyType.None, GlobalVariables.AllModsKnown, false, new List <string>(), out var unknownMods2);
Assert.That(modPruned.Count().Equals(2));
Assert.That(modPruned.ElementAt(0).OneBasedPossibleLocalizedModifications.Count().Equals(1));
Assert.That(modPruned.ElementAt(1).OneBasedPossibleLocalizedModifications.Count().Equals(1));
}
public static void SearchWithPeptidesAddedInParsimonyTest()
{
// Make sure can run the complete search task when multiple compact peptides may correspond to a single PWSM
SearchTask st = new SearchTask
{
SearchParameters = new SearchParameters
{
DoParsimony = true,
DecoyType = DecoyType.None,
ModPeptidesAreDifferent = false
},
CommonParameters = new CommonParameters(scoreCutoff: 1, digestionParams: new DigestionParams(minPeptideLength: 2)),
};
string xmlName = "andguiaheow.xml";
CommonParameters CommonParameters = new CommonParameters(
scoreCutoff: 1,
digestionParams: new DigestionParams(
maxMissedCleavages: 0,
minPeptideLength: 1,
maxModificationIsoforms: 2,
initiatorMethionineBehavior: InitiatorMethionineBehavior.Retain,
maxModsForPeptides: 1));
ModificationMotif.TryGetMotif("A", out ModificationMotif motifA);
Modification alanineMod = new Modification(_originalId: "111", _modificationType: "mt", _target: motifA, _locationRestriction: "Anywhere.", _monoisotopicMass: 111);
var variableModifications = new List <Modification>();
IDictionary <int, List <Modification> > oneBasedModifications1 = new Dictionary <int, List <Modification> >
{
{ 2, new List <Modification> {
alanineMod
} }
};
Protein protein1 = new Protein("MA", "protein1", oneBasedModifications: oneBasedModifications1);
// Alanine = Glycine + CH2
ModificationMotif.TryGetMotif("G", out ModificationMotif motif1);
Modification glycineMod = new Modification(_originalId: "CH2 on Glycine", _modificationType: "mt", _target: motif1, _locationRestriction: "Anywhere.", _monoisotopicMass: Chemistry.ChemicalFormula.ParseFormula("CH2").MonoisotopicMass);
IDictionary <int, List <Modification> > oneBasedModifications2 = new Dictionary <int, List <Modification> >
{
{ 2, new List <Modification> {
glycineMod
} }
};
Protein protein2 = new Protein("MG", "protein3", oneBasedModifications: oneBasedModifications2);
PeptideWithSetModifications pepMA = protein1.Digest(CommonParameters.DigestionParams, new List <Modification>(), variableModifications).First();
PeptideWithSetModifications pepMA111 = protein1.Digest(CommonParameters.DigestionParams, new List <Modification>(), variableModifications).Last();
var pepMG = protein2.Digest(CommonParameters.DigestionParams, new List <Modification>(), variableModifications).First();
ProteinDbWriter.WriteXmlDatabase(new Dictionary <string, HashSet <Tuple <int, Modification> > >(), new List <Protein> {
protein1, protein2
}, xmlName);
string mzmlName = @"ajgdiu.mzML";
MsDataFile myMsDataFile = new TestDataFile(new List <PeptideWithSetModifications> {
pepMA, pepMG, pepMA111
});
IO.MzML.MzmlMethods.CreateAndWriteMyMzmlWithCalibratedSpectra(myMsDataFile, mzmlName, false);
string outputFolder = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestSearchWithPeptidesAddedInParsimony");
Directory.CreateDirectory(outputFolder);
st.RunTask(outputFolder,
new List <DbForTask> {
new DbForTask(xmlName, false)
},
new List <string> {
mzmlName
}, "");
Directory.Delete(outputFolder, true);
File.Delete(mzmlName);
File.Delete(xmlName);
Directory.Delete(Path.Combine(TestContext.CurrentContext.TestDirectory, @"Task Settings"), true);
}
public static void TestBinGeneration()
{
SearchTask st = new SearchTask
{
CommonParameters = new CommonParameters
{
ScoreCutoff = 1,
DigestionParams = new DigestionParams
{
InitiatorMethionineBehavior = InitiatorMethionineBehavior.Retain,
},
ConserveMemory = false,
},
SearchParameters = new SearchParameters
{
DoHistogramAnalysis = true,
MassDiffAcceptorType = MassDiffAcceptorType.Open,
DecoyType = DecoyType.None,
DoParsimony = true,
DoQuantification = true
},
};
string proteinDbFilePath = Path.Combine(TestContext.CurrentContext.TestDirectory, "BinGenerationTest.xml");
string mzmlFilePath = Path.Combine(TestContext.CurrentContext.TestDirectory, "BinGenerationTest.mzml");
Protein prot1 = new Protein("MEDEEK", "prot1");
Protein prot2 = new Protein("MENEEK", "prot2");
ModificationMotif.TryGetMotif("D", out ModificationMotif motif);
ModificationWithMass mod = new ModificationWithMass(null, null, motif, TerminusLocalization.Any, 10);
var pep1_0 = prot1.Digest(st.CommonParameters.DigestionParams, new List <ModificationWithMass>(), new List <ModificationWithMass>()).First();
var pep1_10 = prot1.Digest(st.CommonParameters.DigestionParams, new List <ModificationWithMass>(), new List <ModificationWithMass>()).Last();
Protein prot3 = new Protein("MAAADAAAAAAAAAAAAAAA", "prot3");
var pep2_0 = prot3.Digest(st.CommonParameters.DigestionParams, new List <ModificationWithMass>(), new List <ModificationWithMass>()).First();
var pep2_10 = prot3.Digest(st.CommonParameters.DigestionParams, new List <ModificationWithMass>(), new List <ModificationWithMass> {
mod
}).Last();
Protein prot4 = new Protein("MNNDNNNN", "prot4");
var pep3_10 = prot4.Digest(st.CommonParameters.DigestionParams, new List <ModificationWithMass>(), new List <ModificationWithMass> {
mod
}).Last();
List <PeptideWithSetModifications> pepsWithSetMods = new List <PeptideWithSetModifications> {
pep1_0, pep1_10, pep2_0, pep2_10, pep3_10
};
IMsDataFile <IMsDataScan <IMzSpectrum <IMzPeak> > > myMsDataFile = new TestDataFile(pepsWithSetMods);
List <Protein> proteinList = new List <Protein> {
prot1, prot2, prot3, prot4
};
IO.MzML.MzmlMethods.CreateAndWriteMyMzmlWithCalibratedSpectra(myMsDataFile, mzmlFilePath, false);
ProteinDbWriter.WriteXmlDatabase(new Dictionary <string, HashSet <Tuple <int, Modification> > >(), proteinList, proteinDbFilePath);
string output_folder = Path.Combine(TestContext.CurrentContext.TestDirectory, "TestBinGeneration");
Directory.CreateDirectory(output_folder);
st.RunTask(
output_folder,
new List <DbForTask> {
new DbForTask(proteinDbFilePath, false)
},
new List <string> {
mzmlFilePath
},
null);
Assert.AreEqual(3, File.ReadLines(Path.Combine(output_folder, @"aggregate.mytsv")).Count());
}
[TestCase(9, 0, true, "EDITPEPEDITP2PPP", DecoyType.Reverse)] // MPEPPP becomes MPPPEP with the variant beginning at position 2
public static void SearchTests(int proteinIdx, int peptideIdx, bool containsVariant, string variantPsmShort, DecoyType decoyType = DecoyType.None)
{
Stopwatch stopwatch = new Stopwatch();
stopwatch.Start();
// Make sure can run the complete search task when multiple compact peptides may correspond to a single PWSM
SearchTask st = new SearchTask
{
SearchParameters = new SearchParameters
{
DoParsimony = true,
DecoyType = decoyType,
SearchTarget = decoyType == DecoyType.None,
ModPeptidesAreDifferent = false
},
CommonParameters = new CommonParameters(scoreCutoff: 1, digestionParams: new DigestionParams(minPeptideLength: 2), precursorMassTolerance: new PpmTolerance(20)),
};
ModificationMotif.TryGetMotif("V", out ModificationMotif motifV);
Modification mv = new Modification("mod", null, "type", null, motifV, "Anywhere.", null, 42.01, new Dictionary <string, IList <string> >(), null, null, null, null, null);
ModificationMotif.TryGetMotif("P", out ModificationMotif motifP);
Modification mp = new Modification("mod", null, "type", null, motifP, "Anywhere.", null, 42.01, new Dictionary <string, IList <string> >(), null, null, null, null, null);
List <Protein> proteins = new List <Protein>
{
new Protein("MPEPTIDE", "protein1", sequenceVariations: new List <SequenceVariation> {
new SequenceVariation(4, 4, "P", "V", @"1\t50000000\t.\tA\tG\t.\tPASS\tANN=G||||||||||||||||\tGT:AD:DP\t1/1:30,30:30", null)
}),
new Protein("MPEPTIDE", "protein2", sequenceVariations: new List <SequenceVariation> {
new SequenceVariation(4, 5, "PT", "KT", @"1\t50000000\t.\tA\tG\t.\tPASS\tANN=G||||||||||||||||\tGT:AD:DP\t1/1:30,30:30", null)
}),
new Protein("MPEPTIDE", "protein3", sequenceVariations: new List <SequenceVariation> {
new SequenceVariation(4, 4, "P", "PPP", @"1\t50000000\t.\tA\tG\t.\tPASS\tANN=G||||||||||||||||\tGT:AD:DP\t1/1:30,30:30", null)
}),
new Protein("MPEPPPTIDE", "protein3", sequenceVariations: new List <SequenceVariation> {
new SequenceVariation(4, 6, "PPP", "P", @"1\t50000000\t.\tA\tG\t.\tPASS\tANN=G||||||||||||||||\tGT:AD:DP\t1/1:30,30:30", null)
}),
new Protein("MPEPKPKTIDE", "protein3", sequenceVariations: new List <SequenceVariation> {
new SequenceVariation(4, 7, "PKPK", "PK", @"1\t50000000\t.\tA\tG\t.\tPASS\tANN=G||||||||||||||||\tGT:AD:DP\t1/1:30,30:30", null)
}),
new Protein("MPEPTAIDE", "protein2", sequenceVariations: new List <SequenceVariation> {
new SequenceVariation(4, 5, "PTA", "KT", @"1\t50000000\t.\tA\tG\t.\tPASS\tANN=G||||||||||||||||\tGT:AD:DP\t1/1:30,30:30", null)
}),
new Protein("MPEKKAIDE", "protein2", sequenceVariations: new List <SequenceVariation> {
new SequenceVariation(4, 4, "KKA", "K", @"1\t50000000\t.\tA\tG\t.\tPASS\tANN=G||||||||||||||||\tGT:AD:DP\t1/1:30,30:30", null)
}),
new Protein("MPEPTIDE", "protein1", sequenceVariations: new List <SequenceVariation> {
new SequenceVariation(4, 4, "P", "V", @"1\t50000000\t.\tA\tG\t.\tPASS\tANN=G||||||||||||||||\tGT:AD:DP\t1/1:30,30:30", new Dictionary <int, List <Modification> > {
{ 4, new[] { mv }.ToList() }
})
}),
new Protein("MPEPTIDE", "protein3", sequenceVariations: new List <SequenceVariation> {
new SequenceVariation(4, 4, "P", "PPP", @"1\t50000000\t.\tA\tG\t.\tPASS\tANN=G||||||||||||||||\tGT:AD:DP\t1/1:30,30:30", new Dictionary <int, List <Modification> > {
{ 5, new[] { mp }.ToList() }
})
}),
new Protein("MPEPTIDEPEPTIDE", "protein3", sequenceVariations: new List <SequenceVariation> {
new SequenceVariation(4, 4, "PTIDEPEPTIDE", "PPP", @"1\t50000000\t.\tA\tG\t.\tPASS\tANN=G||||||||||||||||\tGT:AD:DP\t1/1:30,30:30", null)
}),
};
PeptideWithSetModifications pep = proteins[proteinIdx].GetVariantProteins().SelectMany(p => p.Digest(CommonParameters.DigestionParams, null, null)).ToList()[peptideIdx];
string xmlName = $"andguiaheov{proteinIdx.ToString()}.xml";
ProteinDbWriter.WriteXmlDatabase(null, new List <Protein> {
proteins[proteinIdx]
}, xmlName);
string mzmlName = $"ajgdiv{proteinIdx.ToString()}.mzML";
MsDataFile myMsDataFile = new TestDataFile(new List <PeptideWithSetModifications> {
pep
});
IO.MzML.MzmlMethods.CreateAndWriteMyMzmlWithCalibratedSpectra(myMsDataFile, mzmlName, false);
string outputFolder = Path.Combine(TestContext.CurrentContext.TestDirectory, $"TestSearchWithVariants{proteinIdx.ToString()}");
Directory.CreateDirectory(outputFolder);
st.RunTask(outputFolder, new List <DbForTask> {
new DbForTask(xmlName, false)
}, new List <string> {
mzmlName
}, "");
var psms = File.ReadAllLines(Path.Combine(outputFolder, "AllPSMs.psmtsv"));
Assert.IsTrue(psms.Any(line => line.Contains(containsVariant ? variantPsmShort : "\t")));
Directory.Delete(outputFolder, true);
File.Delete(mzmlName);
File.Delete(xmlName);
Directory.Delete(Path.Combine(TestContext.CurrentContext.TestDirectory, @"Task Settings"), true);
Console.WriteLine($"Analysis time for VariantSearchTests.SearchTests({proteinIdx.ToString()},{peptideIdx.ToString()},{containsVariant.ToString()},{variantPsmShort}): {stopwatch.Elapsed.Hours}h {stopwatch.Elapsed.Minutes}m {stopwatch.Elapsed.Seconds}s");
}
public static void TestSilacMultipleModsPerCondition()
{
//The concern with multiple mods per label is the conversions back and forth between "light" and "heavy" labels
Residue heavyLysine = new Residue("a", 'a', "a", Chemistry.ChemicalFormula.ParseFormula("C{13}6H12N{15}2O"), ModificationSites.All); //+8 lysine
Residue heavyArginine = new Residue("b", 'b', "b", Chemistry.ChemicalFormula.ParseFormula("C{13}6H12N4O"), ModificationSites.All); //+6 arginine
Residue lightLysine = Residue.GetResidue('K');
Residue lightArginine = Residue.GetResidue('R');
SilacLabel krLabel = new SilacLabel(lightLysine.Letter, heavyLysine.Letter, heavyLysine.ThisChemicalFormula.Formula, heavyLysine.MonoisotopicMass - lightLysine.MonoisotopicMass);
krLabel.AddAdditionalSilacLabel(new SilacLabel(lightArginine.Letter, heavyArginine.Letter, heavyArginine.ThisChemicalFormula.Formula, heavyArginine.MonoisotopicMass - lightArginine.MonoisotopicMass));
SearchTask task = new SearchTask
{
SearchParameters = new SearchParameters
{
SilacLabels = new List <SilacLabel> {
krLabel
}
},
CommonParameters = new CommonParameters(digestionParams: new DigestionParams(minPeptideLength: 2))
};
PeptideWithSetModifications lightPeptide = new PeptideWithSetModifications("SEQENEWITHAKANDANR", new Dictionary <string, Modification>());
List <double> massDifferences = new List <double> {
(heavyLysine.MonoisotopicMass + heavyArginine.MonoisotopicMass) - (lightLysine.MonoisotopicMass + lightArginine.MonoisotopicMass)
};
MsDataFile myMsDataFile1 = new TestDataFile(lightPeptide, massDifferences);
string mzmlName = @"silac.mzML";
IO.MzML.MzmlMethods.CreateAndWriteMyMzmlWithCalibratedSpectra(myMsDataFile1, mzmlName, false);
string xmlName = "SilacDb.xml";
Protein theProtein = new Protein("MPRTEINRSEQENEWITHAKANDANRANDSMSTFF", "accession1");
ProteinDbWriter.WriteXmlDatabase(new Dictionary <string, HashSet <Tuple <int, Modification> > >(), new List <Protein> {
theProtein
}, xmlName);
string outputFolder = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestSilac");
Directory.CreateDirectory(outputFolder);
task.RunTask(outputFolder, new List <DbForTask> {
new DbForTask(xmlName, false)
}, new List <string> {
mzmlName
}, "taskId1");
//test proteins
string[] output = File.ReadAllLines(TestContext.CurrentContext.TestDirectory + @"/TestSilac/AllProteinGroups.tsv");
Assert.AreEqual(output.Length, 2);
Assert.IsTrue(output[0].Contains("Intensity_silac\tIntensity_silac(K+8.014 & R+6.020)")); //test that two files were made
Assert.IsTrue(output[1].Contains("875000\t437500")); //test the heavy intensity is half that of the light (per the raw file)
//test peptides
output = File.ReadAllLines(TestContext.CurrentContext.TestDirectory + @"/TestSilac/AllQuantifiedPeptides.tsv");
Assert.AreEqual(output.Length, 2);
Assert.IsTrue(output[1].Contains("SEQENEWITHAKANDANR\taccession1\t")); //test the sequence and accession were not modified
Assert.IsTrue(output[1].Contains("875000")); //test intensity
Assert.IsFalse(output[1].Contains("SEQENEWITHAK(+8.014)ANDANR(+6.020)")); //test the sequence was not doubled modified
Assert.IsTrue(output[1].Contains("437500")); //test intensity
//test peaks
output = File.ReadAllLines(TestContext.CurrentContext.TestDirectory + @"/TestSilac/AllQuantifiedPeaks.tsv");
Assert.AreEqual(output.Length, 3);
Assert.IsTrue(output[1].Contains("silac\t")); //test the filename was NOT modified (it was for proteins, but we don't want it for peptides)
Assert.IsTrue(output[2].Contains("silac\t")); //test the filename was NOT modified (it was for proteins, but we don't want it for peptides)
Assert.IsTrue(output[1].Contains("SEQENEWITHAKANDANR\t")); //test light sequence was not modified
Assert.IsTrue(output[2].Contains("SEQENEWITHAK(+8.014)ANDANR(+6.020)\t")); //test heavy sequence was output correctly (do NOT want "PEPTIDEa")
Assert.IsTrue(output[1].Contains("2111.96")); //test light mass
Assert.IsTrue(output[2].Contains("2125.99")); //test heavy mass
Assert.IsTrue(output[2].Contains("accession1")); //test heavy accesssion is light in output
///Test for when an additional label is the only label on a peptide
///Usually crashes in mzId
//Delete old files
File.Delete(mzmlName);
Directory.Delete(outputFolder, true);
lightPeptide = new PeptideWithSetModifications("ANDANR", new Dictionary <string, Modification>()); //has the additional, but not the original
massDifferences = new List <double> {
(heavyArginine.MonoisotopicMass) - (lightArginine.MonoisotopicMass)
};
myMsDataFile1 = new TestDataFile(lightPeptide, massDifferences, true);
mzmlName = @"silac.mzML";
IO.MzML.MzmlMethods.CreateAndWriteMyMzmlWithCalibratedSpectra(myMsDataFile1, mzmlName, false);
Directory.CreateDirectory(outputFolder);
task.RunTask(outputFolder, new List <DbForTask> {
new DbForTask(xmlName, false)
}, new List <string> {
mzmlName
}, "taskId1");
//Clear the old files
Directory.Delete(outputFolder, true);
File.Delete(xmlName);
File.Delete(mzmlName);
}
public static void TestProteinSplitAcrossFiles()
{
SearchTask st = new SearchTask()
{
CommonParameters = new CommonParameters
{
ScoreCutoff = 1,
DigestionParams = new DigestionParams
{
InitiatorMethionineBehavior = InitiatorMethionineBehavior.Retain,
MaxMissedCleavages = 0
},
ConserveMemory = false,
},
SearchParameters = new SearchParameters
{
DoHistogramAnalysis = true,
MassDiffAcceptorType = MassDiffAcceptorType.Open,
MatchBetweenRuns = true,
DoQuantification = true
},
};
string proteinDbFilePath = Path.Combine(TestContext.CurrentContext.TestDirectory, "TestProteinSplitAcrossFiles.xml");
string mzmlFilePath1 = Path.Combine(TestContext.CurrentContext.TestDirectory, "TestProteinSplitAcrossFiles1.mzml");
string mzmlFilePath2 = Path.Combine(TestContext.CurrentContext.TestDirectory, "TestProteinSplitAcrossFiles2.mzml");
ModificationMotif.TryGetMotif("D", out ModificationMotif motif);
ModificationWithMass mod = new ModificationWithMass("mod1", "mt", motif, TerminusLocalization.Any, 10);
IDictionary <int, List <Modification> > oneBasedModification = new Dictionary <int, List <Modification> >
{
{ 3, new List <Modification> {
mod
} }
};
Protein prot1 = new Protein("MEDEEK", "prot1", oneBasedModifications: oneBasedModification);
var pep1 = prot1.Digest(st.CommonParameters.DigestionParams, new List <ModificationWithMass>(), new List <ModificationWithMass>()).First();
var pep2 = prot1.Digest(st.CommonParameters.DigestionParams, new List <ModificationWithMass>(), new List <ModificationWithMass>()).Last();
List <PeptideWithSetModifications> listForFile1 = new List <PeptideWithSetModifications> {
pep1, pep2
};
List <PeptideWithSetModifications> listForFile2 = new List <PeptideWithSetModifications> {
pep2
};
IMsDataFile <IMsDataScan <IMzSpectrum <IMzPeak> > > myMsDataFile1 = new TestDataFile(listForFile1);
IMsDataFile <IMsDataScan <IMzSpectrum <IMzPeak> > > myMsDataFile2 = new TestDataFile(listForFile2);
List <Protein> proteinList = new List <Protein> {
prot1
};
IO.MzML.MzmlMethods.CreateAndWriteMyMzmlWithCalibratedSpectra(myMsDataFile1, mzmlFilePath1, false);
IO.MzML.MzmlMethods.CreateAndWriteMyMzmlWithCalibratedSpectra(myMsDataFile2, mzmlFilePath2, false);
ProteinDbWriter.WriteXmlDatabase(new Dictionary <string, HashSet <Tuple <int, Modification> > >(), proteinList, proteinDbFilePath);
string output_folder = Path.Combine(TestContext.CurrentContext.TestDirectory, "TestProteinSplitAcrossFiles");
Directory.CreateDirectory(output_folder);
st.RunTask(
output_folder,
new List <DbForTask> {
new DbForTask(proteinDbFilePath, false)
},
new List <string> {
mzmlFilePath1, mzmlFilePath2,
},
null);
}
public static void SearchWithPeptidesAddedInParsimonyTest()
{
// Make sure can run the complete search task when multiple compact peptides may correspond to a single PWSM
SearchTask st = new SearchTask
{
SearchParameters = new SearchParameters
{
DoParsimony = true,
DecoyType = DecoyType.None,
ModPeptidesAreDifferent = false
},
CommonParameters = new CommonParameters
{
ScoreCutoff = 1,
DigestionParams = new DigestionParams
{
MinPeptideLength = 2
}
}
};
string xmlName = "andguiaheow.xml";
#region Generate protein and write to file
CommonParameters CommonParameters = new CommonParameters
{
DigestionParams = new DigestionParams
{
MaxMissedCleavages = 0,
MinPeptideLength = null,
InitiatorMethionineBehavior = InitiatorMethionineBehavior.Retain,
MaxModsForPeptide = 1,
MaxModificationIsoforms = 2
},
ScoreCutoff = 1
};
ModificationMotif.TryGetMotif("A", out ModificationMotif motifA);
ModificationWithMass alanineMod = new ModificationWithMass("111", "mt", motifA, TerminusLocalization.Any, 111);
var variableModifications = new List <ModificationWithMass>();
IDictionary <int, List <Modification> > oneBasedModifications1 = new Dictionary <int, List <Modification> >
{
{ 2, new List <Modification> {
alanineMod
} }
};
Protein protein1 = new Protein("MA", "protein1", oneBasedModifications: oneBasedModifications1);
// Alanine = Glycine + CH2
ModificationMotif.TryGetMotif("G", out ModificationMotif motif1);
ModificationWithMass glycineMod = new ModificationWithMass("CH2 on Glycine", "mt", motif1, TerminusLocalization.Any, Chemistry.ChemicalFormula.ParseFormula("CH2").MonoisotopicMass);
IDictionary <int, List <Modification> > oneBasedModifications2 = new Dictionary <int, List <Modification> >
{
{ 2, new List <Modification> {
glycineMod
} }
};
Protein protein2 = new Protein("MG", "protein3", oneBasedModifications: oneBasedModifications2);
PeptideWithSetModifications pepMA = protein1.Digest(CommonParameters.DigestionParams, new List <ModificationWithMass>(), variableModifications).First();
PeptideWithSetModifications pepMA111 = protein1.Digest(CommonParameters.DigestionParams, new List <ModificationWithMass>(), variableModifications).Last();
var pepMG = protein2.Digest(CommonParameters.DigestionParams, new List <ModificationWithMass>(), variableModifications).First();
ProteinDbWriter.WriteXmlDatabase(new Dictionary <string, HashSet <Tuple <int, Modification> > >(), new List <Protein> {
protein1, protein2
}, xmlName);
#endregion Generate protein and write to file
string mzmlName = @"ajgdiu.mzML";
#region Generate and write the mzml
{
IMsDataFile <IMsDataScan <IMzSpectrum <IMzPeak> > > myMsDataFile = new TestDataFile(new List <PeptideWithSetModifications> {
pepMA, pepMG, pepMA111
}, true);
IO.MzML.MzmlMethods.CreateAndWriteMyMzmlWithCalibratedSpectra(myMsDataFile, mzmlName, false);
}
#endregion Generate and write the mzml
st.RunTask("",
new List <DbForTask> {
new DbForTask(xmlName, false)
},
new List <string> {
mzmlName
}, "");
}
public static void TestProteinQuantFileHeaders(bool hasDefinedExperimentalDesign, int bioreps, int fractions, int techreps)
{
// create the unit test directory
string unitTestFolder = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestProteinQuantFileHeaders");
Directory.CreateDirectory(unitTestFolder);
List <SpectraFileInfo> fileInfos = new List <SpectraFileInfo>();
string peptide = "PEPTIDE";
double ionIntensity = 1e6;
string condition = hasDefinedExperimentalDesign ? "TestCondition" : "";
// create the protein database
Protein prot = new Protein(peptide, @"");
string dbName = Path.Combine(unitTestFolder, "testDB.fasta");
UsefulProteomicsDatabases.ProteinDbWriter.WriteFastaDatabase(new List <Protein> {
prot
}, dbName, ">");
// create the .mzML files to search/quantify
for (int b = 0; b < bioreps; b++)
{
for (int f = 0; f < fractions; f++)
{
for (int r = 0; r < techreps; r++)
{
string fileToWrite = "file_" + "b" + b + "f" + f + "r" + r + ".mzML";
// generate mzml file
MsDataScan[] scans = new MsDataScan[2];
// create the MS1 scan
ChemicalFormula cf = new Proteomics.AminoAcidPolymer.Peptide(peptide).GetChemicalFormula();
IsotopicDistribution dist = IsotopicDistribution.GetDistribution(cf, 0.125, 1e-8);
double[] mz = dist.Masses.Select(v => v.ToMz(1)).ToArray();
double[] intensities = dist.Intensities.Select(v => v * ionIntensity).ToArray();
scans[0] = new MsDataScan(massSpectrum: new MzSpectrum(mz, intensities, false), oneBasedScanNumber: 1, msnOrder: 1, isCentroid: true,
polarity: Polarity.Positive, retentionTime: 1.0, scanWindowRange: new MzRange(400, 1600), scanFilter: "f",
mzAnalyzer: MZAnalyzerType.Orbitrap, totalIonCurrent: intensities.Sum(), injectionTime: 1.0, noiseData: null, nativeId: "scan=1");
// create the MS2 scan
var pep = new PeptideWithSetModifications(peptide, new Dictionary <string, Proteomics.Modification>());
List <Product> frags = new List <Product>();
pep.Fragment(DissociationType.HCD, FragmentationTerminus.Both, frags);
double[] mz2 = frags.Select(v => v.NeutralMass.ToMz(1)).ToArray();
double[] intensities2 = frags.Select(v => 1e6).ToArray();
scans[1] = new MsDataScan(massSpectrum: new MzSpectrum(mz2, intensities2, false), oneBasedScanNumber: 2, msnOrder: 2, isCentroid: true,
polarity: Polarity.Positive, retentionTime: 1.01, scanWindowRange: new MzRange(100, 1600), scanFilter: "f",
mzAnalyzer: MZAnalyzerType.Orbitrap, totalIonCurrent: intensities.Sum(), injectionTime: 1.0, noiseData: null, nativeId: "scan=2", selectedIonMz: pep.MonoisotopicMass.ToMz(1),
selectedIonChargeStateGuess: 1, selectedIonIntensity: 1e6, isolationMZ: pep.MonoisotopicMass.ToMz(1), isolationWidth: 1.5, dissociationType: DissociationType.HCD,
oneBasedPrecursorScanNumber: 1, selectedIonMonoisotopicGuessMz: pep.MonoisotopicMass.ToMz(1), hcdEnergy: "35");
// write the .mzML
string fullPath = Path.Combine(unitTestFolder, fileToWrite);
IO.MzML.MzmlMethods.CreateAndWriteMyMzmlWithCalibratedSpectra(
new MsDataFile(scans, new SourceFile(@"scan number only nativeID format", "mzML format", null, "SHA-1", @"C:\fake.mzML", null)),
fullPath, false);
var spectraFileInfo = new SpectraFileInfo(fullPath, condition, b, r, f);
fileInfos.Add(spectraFileInfo);
}
}
}
// write the experimental design for this quantification test
if (hasDefinedExperimentalDesign)
{
ExperimentalDesign.WriteExperimentalDesignToFile(fileInfos);
}
// run the search/quantification
SearchTask task = new SearchTask();
task.RunTask(unitTestFolder, new List <DbForTask> {
new DbForTask(dbName, false)
}, fileInfos.Select(p => p.FullFilePathWithExtension).ToList(), "");
// read in the protein quant results
Assert.That(File.Exists(Path.Combine(unitTestFolder, "AllQuantifiedProteinGroups.tsv")));
var lines = File.ReadAllLines(Path.Combine(unitTestFolder, "AllQuantifiedProteinGroups.tsv"));
// check the intensity column headers
var splitHeader = lines[0].Split(new char[] { '\t' }).ToList();
var intensityColumnHeaders = splitHeader.Where(p => p.Contains("Intensity", StringComparison.OrdinalIgnoreCase)).ToList();
Assert.That(intensityColumnHeaders.Count == 2);
if (!hasDefinedExperimentalDesign)
{
Assert.That(intensityColumnHeaders[0] == "Intensity_file_b0f0r0");
Assert.That(intensityColumnHeaders[1] == "Intensity_file_b1f0r0");
}
else
{
Assert.That(intensityColumnHeaders[0] == "Intensity_TestCondition_1");
Assert.That(intensityColumnHeaders[1] == "Intensity_TestCondition_2");
}
// check the protein intensity values
int ind1 = splitHeader.IndexOf(intensityColumnHeaders[0]);
int ind2 = splitHeader.IndexOf(intensityColumnHeaders[1]);
double intensity1 = double.Parse(lines[1].Split(new char[] { '\t' })[ind1]);
double intensity2 = double.Parse(lines[1].Split(new char[] { '\t' })[ind2]);
Assert.That(intensity1 > 0);
Assert.That(intensity2 > 0);
Assert.That(intensity1 == intensity2);
Directory.Delete(unitTestFolder, true);
}
public static void MetaDraw_SearchTaskTest()
{
string outputFolder = Path.Combine(TestContext.CurrentContext.TestDirectory, @"MetaDraw_SearchTaskTest");
string proteinDatabase = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestData\smalldb.fasta");
string spectraFile = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestData\SmallCalibratible_Yeast.mzML");
Directory.CreateDirectory(outputFolder);
// run search task
var searchtask = new SearchTask();
searchtask.RunTask(outputFolder, new List <DbForTask> {
new DbForTask(proteinDatabase, false)
}, new List <string> {
spectraFile
}, "");
var psmFile = Path.Combine(outputFolder, @"AllPSMs.psmtsv");
// load results into metadraw
var metadrawLogic = new MetaDrawLogic();
metadrawLogic.SpectraFilePaths.Add(spectraFile);
metadrawLogic.PsmResultFilePaths.Add(psmFile);
var errors = metadrawLogic.LoadFiles(true, true);
Assert.That(!errors.Any());
Assert.That(metadrawLogic.FilteredListOfPsms.Any());
// test results filter
MetaDrawSettings.QValueFilter = 0.01;
MetaDrawSettings.ShowDecoys = false;
metadrawLogic.FilterPsms();
Assert.That(metadrawLogic.FilteredListOfPsms.All(p => p.DecoyContamTarget == "T"));
Assert.That(metadrawLogic.FilteredListOfPsms.All(p => p.QValue <= 0.01));
MetaDrawSettings.QValueFilter = 1.0;
MetaDrawSettings.ShowDecoys = true;
metadrawLogic.FilterPsms();
Assert.That(metadrawLogic.FilteredListOfPsms.Any(p => p.DecoyContamTarget == "D"));
Assert.That(metadrawLogic.FilteredListOfPsms.Any(p => p.QValue > 0.01));
// test text search filter (filter by full sequence)
string filterString = @"QIVHDSGR";
metadrawLogic.FilterPsmsByString(filterString);
int c = 0;
foreach (var filteredPsm in metadrawLogic.PeptideSpectralMatchesView)
{
var psmObj = (PsmFromTsv)filteredPsm;
Assert.That(psmObj.FullSequence.Contains(filterString));
c++;
}
Assert.That(c > 0);
// test text search filter (filter by MS2 scan number)
filterString = @"120";
metadrawLogic.FilterPsmsByString(filterString);
c = 0;
foreach (var filteredPsm in metadrawLogic.PeptideSpectralMatchesView)
{
var psmObj = (PsmFromTsv)filteredPsm;
Assert.That(psmObj.Ms2ScanNumber.ToString().Contains(filterString));
c++;
}
Assert.That(c > 0);
// draw PSM
var plotView = new OxyPlot.Wpf.PlotView();
var canvas = new Canvas();
var parentChildView = new ParentChildScanPlotsView();
var psm = metadrawLogic.FilteredListOfPsms.First();
metadrawLogic.DisplaySpectrumMatch(plotView, canvas, psm, parentChildView, out errors);
Assert.That(errors == null || !errors.Any());
// test that plot was drawn
var plotSeries = plotView.Model.Series;
var series = plotSeries[0]; // the first m/z peak
var peakPoints = ((LineSeries)series).Points;
Assert.That(Math.Round(peakPoints[0].X, 2) == 101.07); // m/z
Assert.That(Math.Round(peakPoints[1].X, 2) == 101.07);
Assert.That((int)peakPoints[0].Y == 0); // intensity
Assert.That((int)peakPoints[1].Y == 35045);
var plotAxes = plotView.Model.Axes;
Assert.That(plotAxes.Count == 2);
// test that base sequence annotation was drawn
int numAnnotatedResidues = psm.BaseSeq.Length;
int numAnnotatedIons = psm.MatchedIons.Count;
int numAnnotatedMods = psm.FullSequence.Count(p => p == '[');
Assert.That(canvas.Children.Count == numAnnotatedResidues + numAnnotatedIons + numAnnotatedMods);
// write pdf
var psmsToExport = metadrawLogic.FilteredListOfPsms.Where(p => p.FullSequence == "QIVHDSGR").Take(3).ToList();
metadrawLogic.ExportToPdf(plotView, canvas, psmsToExport, parentChildView, outputFolder, out errors);
// test that pdf exists
Assert.That(File.Exists(Path.Combine(outputFolder, @"116_QIVHDSGR.pdf")));
Assert.That(File.Exists(Path.Combine(outputFolder, @"120_QIVHDSGR.pdf")));
Assert.That(File.Exists(Path.Combine(outputFolder, @"127_QIVHDSGR.pdf")));
// test displaying a PSM with a mod
var modPsm = metadrawLogic.FilteredListOfPsms.First(p => p.FullSequence.Contains("["));
metadrawLogic.DisplaySpectrumMatch(plotView, canvas, modPsm, parentChildView, out errors);
Assert.That(errors == null || !errors.Any());
Assert.That(canvas.Children.Count == modPsm.BaseSeq.Length + modPsm.MatchedIons.Count + modPsm.FullSequence.Count(p => p == '['));
// clean up resources
metadrawLogic.CleanUpResources();
Assert.That(!metadrawLogic.FilteredListOfPsms.Any());
Assert.That(!metadrawLogic.PsmResultFilePaths.Any());
Assert.That(!metadrawLogic.SpectraFilePaths.Any());
// delete output
Directory.Delete(outputFolder, true);
}
public static void TestSilacQuantification()
{
//make heavy residue and add to search task
Residue heavyLysine = new Residue("a", 'a', "a", Chemistry.ChemicalFormula.ParseFormula("C{13}6H12N{15}2O"), ModificationSites.All); //+8 lysine
Residue lightLysine = Residue.GetResidue('K');
SearchTask task = new SearchTask
{
SearchParameters = new SearchParameters
{
SilacLabels = new List <SilacLabel> {
new SilacLabel(lightLysine.Letter, heavyLysine.Letter, heavyLysine.ThisChemicalFormula.Formula, heavyLysine.MonoisotopicMass - lightLysine.MonoisotopicMass)
}
}
};
PeptideWithSetModifications lightPeptide = new PeptideWithSetModifications("PEPTIDEK", new Dictionary <string, Modification>());
List <double> massDifferences = new List <double> {
heavyLysine.MonoisotopicMass - lightLysine.MonoisotopicMass
};
MsDataFile myMsDataFile1 = new TestDataFile(lightPeptide, massDifferences);
string mzmlName = @"silac.mzML";
IO.MzML.MzmlMethods.CreateAndWriteMyMzmlWithCalibratedSpectra(myMsDataFile1, mzmlName, false);
string xmlName = "SilacDb.xml";
Protein theProtein = new Protein("PEPTIDEK", "accession1");
ProteinDbWriter.WriteXmlDatabase(new Dictionary <string, HashSet <Tuple <int, Modification> > >(), new List <Protein> {
theProtein
}, xmlName);
string outputFolder = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestSilac");
Directory.CreateDirectory(outputFolder);
var theStringResult = task.RunTask(outputFolder, new List <DbForTask> {
new DbForTask(xmlName, false)
}, new List <string> {
mzmlName
}, "taskId1").ToString();
Assert.IsTrue(theStringResult.Contains("All target PSMS within 1% FDR: 1")); //it's not a psm, it's a MBR feature
///Normal Peptide
//test proteins
string[] output = File.ReadAllLines(TestContext.CurrentContext.TestDirectory + @"/TestSilac/AllProteinGroups.tsv");
Assert.AreEqual(output.Length, 2);
Assert.IsTrue(output[0].Contains("Intensity_silac\tIntensity_silac(K+8.014)")); //test that two files were made
Assert.IsTrue(output[1].Contains("875000\t437500")); //test the heavy intensity is half that of the light (per the raw file)
//test peptides
output = File.ReadAllLines(TestContext.CurrentContext.TestDirectory + @"/TestSilac/AllQuantifiedPeptides.tsv");
Assert.AreEqual(output.Length, 2);
Assert.IsTrue(output[1].Contains("PEPTIDEK\taccession1\t")); //test the sequence and accession were not modified
Assert.IsTrue(output[1].Contains("875000")); //test intensity
Assert.IsFalse(output[1].Contains("PEPTIDEK(+8.014)")); //test the sequence was not doubled modified
Assert.IsTrue(output[1].Contains("437500")); //test intensity
//test peaks
output = File.ReadAllLines(TestContext.CurrentContext.TestDirectory + @"/TestSilac/AllQuantifiedPeaks.tsv");
Assert.AreEqual(output.Length, 3);
Assert.IsTrue(output[1].Contains("silac\t")); //test the filename was NOT modified (it was for proteins, but we don't want it for peptides)
Assert.IsTrue(output[2].Contains("silac\t")); //test the filename was NOT modified (it was for proteins, but we don't want it for peptides)
Assert.IsTrue(output[1].Contains("PEPTIDEK\t")); //test light sequence was not modified
Assert.IsTrue(output[2].Contains("PEPTIDEK(+8.014)\t")); //test heavy sequence was output correctly (do NOT want "PEPTIDEa")
Assert.IsTrue(output[1].Contains("927.45")); //test light mass
Assert.IsTrue(output[2].Contains("935.46")); //test heavy mass
///Ambiguous base sequence peptide
//Clear the old files
Directory.Delete(outputFolder, true);
File.Delete(xmlName);
File.Delete(mzmlName);
//make a heavy peptide
massDifferences = new List <double> {
heavyLysine.MonoisotopicMass - lightLysine.MonoisotopicMass
};
myMsDataFile1 = new TestDataFile(lightPeptide, massDifferences, true);
IO.MzML.MzmlMethods.CreateAndWriteMyMzmlWithCalibratedSpectra(myMsDataFile1, mzmlName, false);
//make an ambiguous database
Protein theProtein2 = new Protein("PEPTLDEKPEPTIDEK", "accession2");
ProteinDbWriter.WriteXmlDatabase(new Dictionary <string, HashSet <Tuple <int, Modification> > >(), new List <Protein> {
theProtein, theProtein2
}, xmlName);
Directory.CreateDirectory(outputFolder);
theStringResult = task.RunTask(outputFolder, new List <DbForTask> {
new DbForTask(xmlName, false)
}, new List <string> {
mzmlName
}, "taskId1").ToString();
output = File.ReadAllLines(TestContext.CurrentContext.TestDirectory + @"/TestSilac/AllPSMs.psmtsv");
Assert.IsTrue(output[1].Contains("silac\t")); //test the filename was NOT modified (it was for proteins, but we don't want it for peptides)
Assert.IsTrue(output[1].Contains("PEPTIDEK(+8.014)|PEPTLDEK(+8.014)|PEPTIDEK(+8.014)") ||
output[1].Contains("PEPTIDEK(+8.014)|PEPTIDEK(+8.014)|PEPTLDEK(+8.014)") ||
output[1].Contains("PEPTLDEK(+8.014)|PEPTIDEK(+8.014)|PEPTIDEK(+8.014)")); //test the heavy ambiguous peptides were all found
//Need the options, because output isn't consistent as of 3/26/19
///Ambiguous proteinGroup
//Clear the old files
Directory.Delete(outputFolder, true);
File.Delete(xmlName);
//make an ambiguous database
theProtein2 = new Protein("PEPTIDEK", "accession2");
ProteinDbWriter.WriteXmlDatabase(new Dictionary <string, HashSet <Tuple <int, Modification> > >(), new List <Protein> {
theProtein, theProtein2
}, xmlName);
Directory.CreateDirectory(outputFolder);
theStringResult = task.RunTask(outputFolder, new List <DbForTask> {
new DbForTask(xmlName, false)
}, new List <string> {
mzmlName
}, "taskId1").ToString();
output = File.ReadAllLines(TestContext.CurrentContext.TestDirectory + @"/TestSilac/AllPSMs.psmtsv");
Assert.IsTrue(output[1].Contains("accession1|accession2") ||
output[1].Contains("accession2|accession1")); //test the heavy ambiguous peptides were all found
//Need the options, because output isn't consistent as of 3/26/19
Assert.IsTrue(output[1].Contains("\tPEPTIDEK(+8.014)\t")); //test the heavy ambiguous peptides were all found
//delete files
Directory.Delete(outputFolder, true);
File.Delete(xmlName);
File.Delete(mzmlName);
}
public static void TestSilacNoLightProtein()
{
//The concern with multiple mods per label is the conversions back and forth between "light" and "heavy" labels
Residue heavyArginine = new Residue("c", 'c', "c", Chemistry.ChemicalFormula.ParseFormula("C6H12N{15}4O"), ModificationSites.All); //+4 arginine
Residue heavierArginine = new Residue("d", 'd', "d", Chemistry.ChemicalFormula.ParseFormula("C{13}6H12N{15}4O"), ModificationSites.All); //+10 arginine
Residue.AddNewResiduesToDictionary(new List <Residue> {
heavyArginine
}); //These should be added in the search task, but we need to add this one earlier so that we can create a heavy pwsm
Residue lightArginine = Residue.GetResidue('R');
SilacLabel heavyLabel = new SilacLabel(lightArginine.Letter, heavyArginine.Letter, heavyArginine.ThisChemicalFormula.Formula, heavyArginine.MonoisotopicMass - lightArginine.MonoisotopicMass);
SilacLabel heavierLabel = new SilacLabel(lightArginine.Letter, heavierArginine.Letter, heavierArginine.ThisChemicalFormula.Formula, heavierArginine.MonoisotopicMass - lightArginine.MonoisotopicMass);
SearchTask task = new SearchTask
{
SearchParameters = new SearchParameters
{
SilacLabels = new List <SilacLabel> {
heavyLabel, heavierLabel
}
},
CommonParameters = new CommonParameters(digestionParams: new DigestionParams(generateUnlabeledProteinsForSilac: false)) //this is the important part of the unit test
};
PeptideWithSetModifications heavyPeptide = new PeptideWithSetModifications("PEPTIDEc", new Dictionary <string, Modification>());
List <double> massDifferences = new List <double> {
heavierArginine.MonoisotopicMass - heavyArginine.MonoisotopicMass
};
MsDataFile myMsDataFile1 = new TestDataFile(heavyPeptide, massDifferences);
string mzmlName = @"silac.mzML";
IO.MzML.MzmlMethods.CreateAndWriteMyMzmlWithCalibratedSpectra(myMsDataFile1, mzmlName, false);
string xmlName = "SilacDb.xml";
Protein theProtein = new Protein("PEPTIDER", "accession1");
ProteinDbWriter.WriteXmlDatabase(new Dictionary <string, HashSet <Tuple <int, Modification> > >(), new List <Protein> {
theProtein
}, xmlName);
string outputFolder = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestSilac");
Directory.CreateDirectory(outputFolder);
var theStringResult = task.RunTask(outputFolder, new List <DbForTask> {
new DbForTask(xmlName, false)
}, new List <string> {
mzmlName
}, "taskId1").ToString();
//test proteins
string[] output = File.ReadAllLines(TestContext.CurrentContext.TestDirectory + @"/TestSilac/AllProteinGroups.tsv");
Assert.AreEqual(output.Length, 2);
Assert.IsTrue(output[0].Contains("Modification Info List\tIntensity_silac(R+3.988)\tIntensity_silac(R+10.008)")); //test that two files were made and no light file
Assert.IsTrue(output[1].Contains("875000\t437500")); //test the heavier intensity is half that of the heavy (per the raw file)
//test peptides
output = File.ReadAllLines(TestContext.CurrentContext.TestDirectory + @"/TestSilac/AllQuantifiedPeptides.tsv");
Assert.AreEqual(output.Length, 2);
Assert.IsTrue(output[0].Contains("Organism\tIntensity_silac(R+3.988)\tIntensity_silac(R+10.008)")); //test the two files were made and no light file
Assert.IsTrue(output[1].Contains("875000\t437500")); //test intensity
//test peaks
output = File.ReadAllLines(TestContext.CurrentContext.TestDirectory + @"/TestSilac/AllQuantifiedPeaks.tsv");
Assert.AreEqual(output.Length, 3);
Assert.IsTrue(output[1].Contains("silac\t")); //test the filename was NOT modified (it was for proteins, but we don't want it for peptides)
Assert.IsTrue(output[2].Contains("silac\t")); //test the filename was NOT modified (it was for proteins, but we don't want it for peptides)
Assert.IsTrue(output[1].Contains("PEPTIDER(+3.988)\t")); //test light sequence was not modified
Assert.IsTrue(output[2].Contains("PEPTIDER(+10.008)\t")); //test heavy sequence was output correctly (do NOT want "PEPTIDEa")
Assert.IsTrue(output[1].Contains("959.44")); //test light mass
Assert.IsTrue(output[2].Contains("965.46")); //test heavy mass
//test PSMs
output = File.ReadAllLines(TestContext.CurrentContext.TestDirectory + @"/TestSilac/AllPSMs.psmtsv");
Assert.IsTrue(output[1].Contains("959.44")); //test the correct monoisotopic mass
Assert.IsTrue(output[1].Contains("PEPTIDER(+3.988)")); //test the correct psm
Assert.IsTrue(output[1].Contains("silac\t")); //test the filename was NOT modified (it was for proteins, but we don't want it for peptides)
//Clear the old files
Directory.Delete(outputFolder, true);
File.Delete(xmlName);
File.Delete(mzmlName);
}
public static void TestMetaDrawWithSpectralLibrary()
{
string outputFolder = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestMetaDrawWithSpectraLibrary");
string proteinDatabase = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestData\SpectralLibrarySearch\P16858.fasta");
string library1 = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestData\SpectralLibrarySearch\P16858_target.msp");
string library2 = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestData\SpectralLibrarySearch\P16858_decoy.msp");
string spectraFile = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestData\SpectralLibrarySearch\slicedMouse.raw");
Directory.CreateDirectory(outputFolder);
// run search task
var searchtask = new SearchTask();
searchtask.RunTask(outputFolder,
new List <DbForTask>
{
new DbForTask(proteinDatabase, false),
new DbForTask(library1, false),
new DbForTask(library2, false),
},
new List <string> {
spectraFile
}, "");
var psmFile = Path.Combine(outputFolder, @"AllPSMs.psmtsv");
// load results into metadraw
var metadrawLogic = new MetaDrawLogic();
metadrawLogic.SpectraFilePaths.Add(spectraFile);
metadrawLogic.PsmResultFilePaths.Add(psmFile);
metadrawLogic.SpectralLibraryPaths.Add(library1);
metadrawLogic.SpectralLibraryPaths.Add(library2);
var errors = metadrawLogic.LoadFiles(true, true);
Assert.That(!errors.Any());
// draw PSM
var plotView = new OxyPlot.Wpf.PlotView();
var canvas = new Canvas();
var parentChildView = new ParentChildScanPlotsView();
var psm = metadrawLogic.FilteredListOfPsms.First();
metadrawLogic.DisplaySpectrumMatch(plotView, canvas, psm, parentChildView, out errors);
Assert.That(errors == null || !errors.Any());
// test that plot was drawn
var plotSeries = plotView.Model.Series;
// test that library peaks were drawn in the mirror plot (these peaks have negative intensities)
var mirrorPlotPeaks = plotSeries.Where(p => ((LineSeries)p).Points[1].Y < 0).ToList();
Assert.That(mirrorPlotPeaks.Count == 52);
var plotAxes = plotView.Model.Axes;
Assert.That(plotAxes.Count == 2);
// write pdf
var psmsToExport = metadrawLogic.FilteredListOfPsms.Where(p => p.FullSequence == "VIHDNFGIVEGLMTTVHAITATQK").Take(1).ToList();
metadrawLogic.ExportToPdf(plotView, canvas, psmsToExport, parentChildView, outputFolder, out errors);
// test that pdf exists
Assert.That(File.Exists(Path.Combine(outputFolder, @"6_VIHDNFGIVEGLMTTVHAITATQK.pdf")));
// clean up resources
metadrawLogic.CleanUpResources();
Assert.That(!metadrawLogic.FilteredListOfPsms.Any());
Assert.That(!metadrawLogic.PsmResultFilePaths.Any());
Assert.That(!metadrawLogic.SpectraFilePaths.Any());
Assert.That(!metadrawLogic.SpectralLibraryPaths.Any());
// delete output
Directory.Delete(outputFolder, true);
}
public static void TestAutodetectDissocationTypeFromScanHeader()
{
SearchTask searchTask = new SearchTask()
{
SearchParameters = new SearchParameters
{
DoQuantification = false // quant disabled just to save some time
},
// use DissociationType.Autodetect as the dissociation type. this signals to the search that the dissociation type
// should be taken from the scan header on a scan-specific basis
CommonParameters = new CommonParameters(dissociationType: DissociationType.Autodetect)
};
string myFile = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestData\SmallCalibratible_Yeast.mzML");
string myDatabase = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestData\smalldb.fasta");
string folderPath = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestAutodetectDissocationTypeFromScanHeader");
DbForTask db = new DbForTask(myDatabase, false);
// run the task
var autoTaskFolder = Path.Combine(folderPath, @"Autodetect");
Directory.CreateDirectory(autoTaskFolder);
searchTask.RunTask(autoTaskFolder, new List <DbForTask> {
db
}, new List <string> {
myFile
}, "");
// run identical task but select the HCD dissociation type instead of autodetect
var hcdTaskFolder = Path.Combine(folderPath, @"HCD");
Directory.CreateDirectory(hcdTaskFolder);
searchTask = new SearchTask()
{
SearchParameters = new SearchParameters
{
DoQuantification = false
},
CommonParameters = new CommonParameters(dissociationType: DissociationType.HCD)
};
searchTask.RunTask(hcdTaskFolder, new List <DbForTask> {
db
}, new List <string> {
myFile
}, "");
// check search results
var psmFileAutodetect = File.ReadAllLines(Path.Combine(autoTaskFolder, "AllPSMs.psmtsv"));
var psmFileHcd = File.ReadAllLines(Path.Combine(hcdTaskFolder, "AllPSMs.psmtsv"));
Assert.That(psmFileAutodetect.Length == psmFileHcd.Length);
for (int i = 0; i < psmFileAutodetect.Length; i++)
{
Assert.That(psmFileAutodetect[i].Equals(psmFileHcd[i]));
}
// clean up
Directory.Delete(folderPath, true);
}
