public MyTaskResults Run(string OutputFolder, List <DbForTask> dbFilenameList, List <string> currentRawFileList, string taskId, FileSpecificParameters[] fileSettingsList, List <CrosslinkSpectralMatch> allPsms, CommonParameters commonParameters, XlSearchParameters xlSearchParameters, List <Protein> proteinList, List <Modification> variableModifications, List <Modification> fixedModifications, List <string> localizeableModificationTypes, MyTaskResults MyTaskResults)
{
foreach (var csm in allPsms)
{
csm.ResolveProteinPosAmbiguitiesForXl();
}
var allPsmsXL = allPsms.Where(p => p.CrossType == PsmCrossType.Cross).ToList();
// inter-crosslinks; different proteins are linked
var interCsms = allPsmsXL.Where(p => !p.IsIntraCsm()).ToList();
foreach (var item in interCsms)
{
item.CrossType = PsmCrossType.Inter;
}
// intra-crosslinks; crosslinks within a protein
var intraCsms = allPsmsXL.Where(p => p.IsIntraCsm()).ToList();
foreach (var item in intraCsms)
{
item.CrossType = PsmCrossType.Intra;
}
// calculate FDR
DoCrosslinkFdrAnalysis(interCsms);
DoCrosslinkFdrAnalysis(intraCsms);
SingleFDRAnalysis(allPsms, commonParameters, new List <string> {
taskId
});
// write interlink CSMs
if (interCsms.Any())
{
string file = Path.Combine(OutputFolder, "XL_Interlinks.tsv");
WriteFile.WritePsmCrossToTsv(interCsms, file, 2);
FinishedWritingFile(file, new List <string> {
taskId
});
}
MyTaskResults.AddNiceText("Target inter-crosslinks within 1% FDR: " + interCsms.Count(p => p.FdrInfo.QValue <= 0.01 && !p.IsDecoy && !p.BetaPeptide.IsDecoy));
if (xlSearchParameters.WriteOutputForPercolator)
{
var interPsmsXLPercolator = interCsms.Where(p => p.Score >= 2 && p.BetaPeptide.Score >= 2).OrderBy(p => p.ScanNumber).ToList();
WriteFile.WriteCrosslinkToTxtForPercolator(interPsmsXLPercolator, OutputFolder, "XL_Interlinks_Percolator", xlSearchParameters.Crosslinker);
FinishedWritingFile(Path.Combine(OutputFolder, "XL_Interlinks_Percolator.txt"), new List <string> {
taskId
});
}
// write intralink CSMs
if (intraCsms.Any())
{
string file = Path.Combine(OutputFolder, "XL_Intralinks.tsv");
WriteFile.WritePsmCrossToTsv(intraCsms, file, 2);
FinishedWritingFile(file, new List <string> {
taskId
});
}
MyTaskResults.AddNiceText("Target intra-crosslinks within 1% FDR: " + intraCsms.Count(p => p.FdrInfo.QValue <= 0.01 && !p.IsDecoy && !p.BetaPeptide.IsDecoy));
if (xlSearchParameters.WriteOutputForPercolator)
{
var intraPsmsXLPercolator = intraCsms.Where(p => p.Score >= 2 && p.BetaPeptide.Score >= 2).OrderBy(p => p.ScanNumber).ToList();
WriteFile.WriteCrosslinkToTxtForPercolator(intraPsmsXLPercolator, OutputFolder, "XL_Intralinks_Percolator", xlSearchParameters.Crosslinker);
FinishedWritingFile(Path.Combine(OutputFolder, "XL_Intralinks_Percolator.txt"), new List <string> {
taskId
});
}
// write single peptides
var singlePsms = allPsms.Where(p => p.CrossType == PsmCrossType.Single).ToList();
if (singlePsms.Any())
{
string writtenFileSingle = Path.Combine(OutputFolder, "SinglePeptides" + ".tsv");
WriteFile.WritePsmCrossToTsv(singlePsms, writtenFileSingle, 1);
FinishedWritingFile(writtenFileSingle, new List <string> {
taskId
});
}
MyTaskResults.AddNiceText("Target single peptides within 1% FDR: " + singlePsms.Count(p => p.FdrInfo.QValue <= 0.01 && !p.IsDecoy));
// write loops
var loopPsms = allPsms.Where(p => p.CrossType == PsmCrossType.Loop).ToList();
if (loopPsms.Any())
{
string writtenFileLoop = Path.Combine(OutputFolder, "Looplinks" + ".tsv");
WriteFile.WritePsmCrossToTsv(loopPsms, writtenFileLoop, 1);
FinishedWritingFile(writtenFileLoop, new List <string> {
taskId
});
}
MyTaskResults.AddNiceText("Target loop-linked peptides within 1% FDR: " + loopPsms.Count(p => p.FdrInfo.QValue <= 0.01 && !p.IsDecoy));
// write deadends
var deadendPsms = allPsms.Where(p => p.CrossType == PsmCrossType.DeadEnd ||
p.CrossType == PsmCrossType.DeadEndH2O ||
p.CrossType == PsmCrossType.DeadEndNH2 ||
p.CrossType == PsmCrossType.DeadEndTris).ToList();
if (deadendPsms.Any())
{
string writtenFileDeadend = Path.Combine(OutputFolder, "Deadends" + ".tsv");
WriteFile.WritePsmCrossToTsv(deadendPsms, writtenFileDeadend, 1);
FinishedWritingFile(writtenFileDeadend, new List <string> {
taskId
});
}
MyTaskResults.AddNiceText("Target deadend peptides within 1% FDR: " + deadendPsms.Count(p => p.FdrInfo.QValue <= 0.01 && !p.IsDecoy));
// write pepXML
if (xlSearchParameters.WritePepXml)
{
List <CrosslinkSpectralMatch> writeToXml = new List <CrosslinkSpectralMatch>();
writeToXml.AddRange(intraCsms.Where(p => !p.IsDecoy && !p.BetaPeptide.IsDecoy && p.FdrInfo.QValue <= 0.05));
writeToXml.AddRange(interCsms.Where(p => !p.IsDecoy && !p.BetaPeptide.IsDecoy && p.FdrInfo.QValue <= 0.05));
writeToXml.AddRange(singlePsms.Where(p => !p.IsDecoy && p.FdrInfo.QValue <= 0.05));
writeToXml.AddRange(loopPsms.Where(p => !p.IsDecoy && p.FdrInfo.QValue <= 0.05));
writeToXml.AddRange(deadendPsms.Where(p => !p.IsDecoy && p.FdrInfo.QValue <= 0.05));
writeToXml = writeToXml.OrderBy(p => p.ScanNumber).ToList();
foreach (var fullFilePath in currentRawFileList)
{
string fileNameNoExtension = Path.GetFileNameWithoutExtension(fullFilePath);
WriteFile.WritePepXML_xl(writeToXml.Where(p => p.FullFilePath == fullFilePath).ToList(), proteinList, dbFilenameList[0].FilePath, variableModifications, fixedModifications, localizeableModificationTypes, OutputFolder, fileNameNoExtension, commonParameters, xlSearchParameters);
FinishedWritingFile(Path.Combine(OutputFolder, fileNameNoExtension + ".pep.XML"), new List <string> {
taskId
});
}
}
return(MyTaskResults);
}
protected override MyTaskResults RunSpecific(string OutputFolder, List <DbForTask> dbFilenameList, List <string> currentRawFileList, string taskId, FileSpecificParameters[] fileSettingsList)
{
MyTaskResults = new MyTaskResults(this);
List <CrosslinkSpectralMatch> allPsms = new List <CrosslinkSpectralMatch>();
LoadModifications(taskId, out var variableModifications, out var fixedModifications, out var localizeableModificationTypes);
// load proteins
List <Protein> proteinList = LoadProteins(taskId, dbFilenameList, true, XlSearchParameters.DecoyType, localizeableModificationTypes, CommonParameters);
var crosslinker = XlSearchParameters.Crosslinker;
MyFileManager myFileManager = new MyFileManager(true);
var fileSpecificCommonParams = fileSettingsList.Select(b => SetAllFileSpecificCommonParams(CommonParameters, b));
HashSet <DigestionParams> ListOfDigestionParams = new HashSet <DigestionParams>(fileSpecificCommonParams.Select(p => p.DigestionParams));
int completedFiles = 0;
object indexLock = new object();
object psmLock = new object();
Status("Searching files...", taskId);
ProseCreatedWhileRunning.Append("The following crosslink discovery were used: ");
ProseCreatedWhileRunning.Append("crosslinker name = " + crosslinker.CrosslinkerName + "; ");
ProseCreatedWhileRunning.Append("crosslinker type = " + crosslinker.Cleavable + "; ");
ProseCreatedWhileRunning.Append("crosslinker mass = " + crosslinker.TotalMass + "; ");
ProseCreatedWhileRunning.Append("crosslinker modification site(s) = " + crosslinker.CrosslinkerModSites + "; ");
ProseCreatedWhileRunning.Append("protease = " + CommonParameters.DigestionParams.Protease + "; ");
ProseCreatedWhileRunning.Append("maximum missed cleavages = " + CommonParameters.DigestionParams.MaxMissedCleavages + "; ");
ProseCreatedWhileRunning.Append("minimum peptide length = " + CommonParameters.DigestionParams.MinPeptideLength + "; ");
ProseCreatedWhileRunning.Append(CommonParameters.DigestionParams.MaxPeptideLength == int.MaxValue ?
"maximum peptide length = unspecified; " :
"maximum peptide length = " + CommonParameters.DigestionParams.MaxPeptideLength + "; ");
ProseCreatedWhileRunning.Append("initiator methionine behavior = " + CommonParameters.DigestionParams.InitiatorMethionineBehavior + "; ");
ProseCreatedWhileRunning.Append("max modification isoforms = " + CommonParameters.DigestionParams.MaxModificationIsoforms + "; ");
ProseCreatedWhileRunning.Append("fixed modifications = " + string.Join(", ", fixedModifications.Select(m => m.IdWithMotif) + "; "));
ProseCreatedWhileRunning.Append("variable modifications = " + string.Join(", ", variableModifications.Select(m => m.IdWithMotif)) + "; ");
ProseCreatedWhileRunning.Append("parent mass tolerance(s) = " + CommonParameters.PrecursorMassTolerance + "; ");
ProseCreatedWhileRunning.Append("product mass tolerance = " + CommonParameters.ProductMassTolerance + "; ");
ProseCreatedWhileRunning.Append("The combined search database contained " + proteinList.Count + " total entries including " + proteinList.Where(p => p.IsContaminant).Count() + " contaminant sequences. ");
for (int spectraFileIndex = 0; spectraFileIndex < currentRawFileList.Count; spectraFileIndex++)
{
var origDataFile = currentRawFileList[spectraFileIndex];
CommonParameters combinedParams = SetAllFileSpecificCommonParams(CommonParameters, fileSettingsList[spectraFileIndex]);
var thisId = new List <string> {
taskId, "Individual Spectra Files", origDataFile
};
NewCollection(Path.GetFileName(origDataFile), thisId);
Status("Loading spectra file...", thisId);
MsDataFile myMsDataFile = myFileManager.LoadFile(origDataFile, combinedParams);
Status("Getting ms2 scans...", thisId);
Ms2ScanWithSpecificMass[] arrayOfMs2ScansSortedByMass = GetMs2Scans(myMsDataFile, origDataFile, combinedParams).OrderBy(b => b.PrecursorMass).ToArray();
CrosslinkSpectralMatch[] newPsms = new CrosslinkSpectralMatch[arrayOfMs2ScansSortedByMass.Length];
for (int currentPartition = 0; currentPartition < CommonParameters.TotalPartitions; currentPartition++)
{
List <PeptideWithSetModifications> peptideIndex = null;
List <Protein> proteinListSubset = proteinList.GetRange(currentPartition * proteinList.Count() / combinedParams.TotalPartitions, ((currentPartition + 1) * proteinList.Count() / combinedParams.TotalPartitions) - (currentPartition * proteinList.Count() / combinedParams.TotalPartitions));
Status("Getting fragment dictionary...", new List <string> {
taskId
});
var indexEngine = new IndexingEngine(proteinListSubset, variableModifications, fixedModifications, null, currentPartition, UsefulProteomicsDatabases.DecoyType.Reverse, combinedParams, 30000.0, false, dbFilenameList.Select(p => new FileInfo(p.FilePath)).ToList(), new List <string> {
taskId
});
List <int>[] fragmentIndex = null;
List <int>[] precursorIndex = null;
GenerateIndexes(indexEngine, dbFilenameList, ref peptideIndex, ref fragmentIndex, ref precursorIndex, proteinList, taskId);
Status("Searching files...", taskId);
new CrosslinkSearchEngine(newPsms, arrayOfMs2ScansSortedByMass, peptideIndex, fragmentIndex, currentPartition, combinedParams, crosslinker,
XlSearchParameters.RestrictToTopNHits, XlSearchParameters.CrosslinkSearchTopNum, XlSearchParameters.XlQuench_H2O,
XlSearchParameters.XlQuench_NH2, XlSearchParameters.XlQuench_Tris, thisId).Run();
ReportProgress(new ProgressEventArgs(100, "Done with search " + (currentPartition + 1) + "/" + CommonParameters.TotalPartitions + "!", thisId));
if (GlobalVariables.StopLoops)
{
break;
}
}
allPsms.AddRange(newPsms.Where(p => p != null));
completedFiles++;
ReportProgress(new ProgressEventArgs(completedFiles / currentRawFileList.Count, "Searching...", new List <string> {
taskId, "Individual Spectra Files"
}));
}
ReportProgress(new ProgressEventArgs(100, "Done with all searches!", new List <string> {
taskId, "Individual Spectra Files"
}));
allPsms = allPsms.OrderByDescending(p => p.XLTotalScore).ToList();
var allPsmsXL = allPsms.Where(p => p.CrossType == PsmCrossType.Cross).ToList();
// inter-crosslinks; different proteins are linked
var interCsms = allPsmsXL.Where(p => !p.ProteinAccession.Equals(p.BetaPeptide.ProteinAccession)).ToList();
foreach (var item in interCsms)
{
item.CrossType = PsmCrossType.Inter;
}
// intra-crosslinks; crosslinks within a protein
var intraCsms = allPsmsXL.Where(p => p.ProteinAccession.Equals(p.BetaPeptide.ProteinAccession)).ToList();
foreach (var item in intraCsms)
{
item.CrossType = PsmCrossType.Intra;
}
// calculate FDR
DoCrosslinkFdrAnalysis(interCsms);
DoCrosslinkFdrAnalysis(intraCsms);
SingleFDRAnalysis(allPsms, new List <string> {
taskId
});
// calculate protein crosslink residue numbers
foreach (var csm in allPsmsXL)
{
// alpha peptide crosslink residue in the protein
csm.XlProteinPos = csm.OneBasedStartResidueInProtein.Value + csm.LinkPositions[0] - 1;
// beta crosslink residue in protein
csm.BetaPeptide.XlProteinPos = csm.BetaPeptide.OneBasedStartResidueInProtein.Value + csm.BetaPeptide.LinkPositions[0] - 1;
}
// write interlink CSMs
if (interCsms.Any())
{
string file = Path.Combine(OutputFolder, "XL_Interlinks.tsv");
WritePsmCrossToTsv(interCsms, file, 2);
FinishedWritingFile(file, new List <string> {
taskId
});
}
MyTaskResults.AddNiceText("Target inter-crosslinks within 1% FDR: " + interCsms.Count(p => p.FdrInfo.QValue <= 0.01 && !p.IsDecoy && !p.BetaPeptide.IsDecoy));
if (XlSearchParameters.WriteOutputForPercolator)
{
var interPsmsXLPercolator = interCsms.Where(p => p.Score >= 2 && p.BetaPeptide.Score >= 2).OrderBy(p => p.ScanNumber).ToList();
WriteCrosslinkToTxtForPercolator(interPsmsXLPercolator, OutputFolder, "XL_Interlinks_Percolator", crosslinker, new List <string> {
taskId
});
}
// write intralink CSMs
if (intraCsms.Any())
{
string file = Path.Combine(OutputFolder, "XL_Intralinks.tsv");
WritePsmCrossToTsv(intraCsms, file, 2);
FinishedWritingFile(file, new List <string> {
taskId
});
}
MyTaskResults.AddNiceText("Target intra-crosslinks within 1% FDR: " + intraCsms.Count(p => p.FdrInfo.QValue <= 0.01 && !p.IsDecoy && !p.BetaPeptide.IsDecoy));
if (XlSearchParameters.WriteOutputForPercolator)
{
var intraPsmsXLPercolator = intraCsms.Where(p => p.Score >= 2 && p.BetaPeptide.Score >= 2).OrderBy(p => p.ScanNumber).ToList();
WriteCrosslinkToTxtForPercolator(intraPsmsXLPercolator, OutputFolder, "XL_Intralinks_Percolator", crosslinker, new List <string> {
taskId
});
}
// write single peptides
var singlePsms = allPsms.Where(p => p.CrossType == PsmCrossType.Single).ToList();
if (singlePsms.Any())
{
string writtenFileSingle = Path.Combine(OutputFolder, "SinglePeptides" + ".tsv");
WritePsmCrossToTsv(singlePsms, writtenFileSingle, 1);
FinishedWritingFile(writtenFileSingle, new List <string> {
taskId
});
}
MyTaskResults.AddNiceText("Target single peptides within 1% FDR: " + singlePsms.Count(p => p.FdrInfo.QValue <= 0.01 && !p.IsDecoy));
// write loops
var loopPsms = allPsms.Where(p => p.CrossType == PsmCrossType.Loop).ToList();
if (loopPsms.Any())
{
string writtenFileLoop = Path.Combine(OutputFolder, "Looplinks" + ".tsv");
WritePsmCrossToTsv(loopPsms, writtenFileLoop, 1);
FinishedWritingFile(writtenFileLoop, new List <string> {
taskId
});
}
MyTaskResults.AddNiceText("Target loop-linked peptides within 1% FDR: " + loopPsms.Count(p => p.FdrInfo.QValue <= 0.01 && !p.IsDecoy));
// write deadends
var deadendPsms = allPsms.Where(p => p.CrossType == PsmCrossType.DeadEnd ||
p.CrossType == PsmCrossType.DeadEndH2O ||
p.CrossType == PsmCrossType.DeadEndNH2 ||
p.CrossType == PsmCrossType.DeadEndTris).ToList();
if (deadendPsms.Any())
{
string writtenFileDeadend = Path.Combine(OutputFolder, "Deadends" + ".tsv");
WritePsmCrossToTsv(deadendPsms, writtenFileDeadend, 1);
FinishedWritingFile(writtenFileDeadend, new List <string> {
taskId
});
}
MyTaskResults.AddNiceText("Target deadend peptides within 1% FDR: " + deadendPsms.Count(p => p.FdrInfo.QValue <= 0.01 && !p.IsDecoy));
// write pepXML
if (XlSearchParameters.WritePepXml)
{
List <CrosslinkSpectralMatch> writeToXml = new List <CrosslinkSpectralMatch>();
writeToXml.AddRange(intraCsms.Where(p => !p.IsDecoy && !p.BetaPeptide.IsDecoy && p.FdrInfo.QValue <= 0.05));
writeToXml.AddRange(interCsms.Where(p => !p.IsDecoy && !p.BetaPeptide.IsDecoy && p.FdrInfo.QValue <= 0.05));
writeToXml.AddRange(singlePsms.Where(p => !p.IsDecoy && p.FdrInfo.QValue <= 0.05));
writeToXml.AddRange(loopPsms.Where(p => !p.IsDecoy && p.FdrInfo.QValue <= 0.05));
writeToXml.AddRange(deadendPsms.Where(p => !p.IsDecoy && p.FdrInfo.QValue <= 0.05));
writeToXml = writeToXml.OrderBy(p => p.ScanNumber).ToList();
foreach (var fullFilePath in currentRawFileList)
{
string fileNameNoExtension = Path.GetFileNameWithoutExtension(fullFilePath);
WritePepXML_xl(writeToXml.Where(p => p.FullFilePath == fullFilePath).ToList(), proteinList, dbFilenameList[0].FilePath, variableModifications, fixedModifications, localizeableModificationTypes, OutputFolder, fileNameNoExtension, new List <string> {
taskId
});
}
}
return(MyTaskResults);
}
protected override MyTaskResults RunSpecific(string OutputFolder, List <DbForTask> dbFilenameList, List <string> currentRawFileList, string taskId, FileSpecificParameters[] fileSettingsList)
{
LoadModifications(taskId, out var variableModifications, out var fixedModifications, out var localizeableModificationTypes);
// TODO: print error messages loading GPTMD mods
List <Modification> gptmdModifications = GlobalVariables.AllModsKnown.OfType <Modification>().Where(b => GptmdParameters.ListOfModsGptmd.Contains((b.ModificationType, b.IdWithMotif))).ToList();
IEnumerable <Tuple <double, double> > combos = LoadCombos(gptmdModifications).ToList();
// load proteins
List <Protein> proteinList = LoadProteins(taskId, dbFilenameList, true, DecoyType.Reverse, localizeableModificationTypes, CommonParameters);
List <PeptideSpectralMatch> allPsms = new List <PeptideSpectralMatch>();
var numRawFiles = currentRawFileList.Count;
// write prose settings
ProseCreatedWhileRunning.Append("The following G-PTM-D settings were used: "); ProseCreatedWhileRunning.Append("protease = " + CommonParameters.DigestionParams.Protease + "; ");
ProseCreatedWhileRunning.Append("maximum missed cleavages = " + CommonParameters.DigestionParams.MaxMissedCleavages + "; ");
ProseCreatedWhileRunning.Append("minimum peptide length = " + CommonParameters.DigestionParams.MinPeptideLength + "; ");
ProseCreatedWhileRunning.Append(CommonParameters.DigestionParams.MaxPeptideLength == int.MaxValue ?
"maximum peptide length = unspecified; " :
"maximum peptide length = " + CommonParameters.DigestionParams.MaxPeptideLength + "; ");
ProseCreatedWhileRunning.Append("initiator methionine behavior = " + CommonParameters.DigestionParams.InitiatorMethionineBehavior + "; ");
ProseCreatedWhileRunning.Append("max modification isoforms = " + CommonParameters.DigestionParams.MaxModificationIsoforms + "; ");
ProseCreatedWhileRunning.Append("fixed modifications = " + string.Join(", ", fixedModifications.Select(m => m.IdWithMotif)) + "; ");
ProseCreatedWhileRunning.Append("variable modifications = " + string.Join(", ", variableModifications.Select(m => m.IdWithMotif)) + "; ");
ProseCreatedWhileRunning.Append("G-PTM-D modifications count = " + gptmdModifications.Count + "; ");
// temporary search type for writing prose
// the actual search type is technically file-specific but we don't allow file-specific notches, so it's safe to do this
MassDiffAcceptor tempSearchMode = new DotMassDiffAcceptor("", GetAcceptableMassShifts(fixedModifications, variableModifications, gptmdModifications, combos), CommonParameters.PrecursorMassTolerance);
ProseCreatedWhileRunning.Append("precursor mass tolerance(s) = {" + tempSearchMode.ToProseString() + "}; ");
ProseCreatedWhileRunning.Append("product mass tolerance = " + CommonParameters.ProductMassTolerance + ". ");
ProseCreatedWhileRunning.Append("The combined search database contained " + proteinList.Count(p => !p.IsDecoy) + " non-decoy protein entries including " + proteinList.Where(p => p.IsContaminant).Count() + " contaminant sequences. ");
// start the G-PTM-D task
Status("Running G-PTM-D...", new List <string> {
taskId
});
MyTaskResults = new MyTaskResults(this)
{
NewDatabases = new List <DbForTask>()
};
var fileSpecificCommonParams = fileSettingsList.Select(b => SetAllFileSpecificCommonParams(CommonParameters, b));
HashSet <DigestionParams> ListOfDigestionParams = new HashSet <DigestionParams>(fileSpecificCommonParams.Select(p => p.DigestionParams));
MyFileManager myFileManager = new MyFileManager(true);
object lock1 = new object();
object lock2 = new object();
for (int spectraFileIndex = 0; spectraFileIndex < currentRawFileList.Count; spectraFileIndex++)
{
// Stop if canceled
if (GlobalVariables.StopLoops)
{
break;
}
var origDataFile = currentRawFileList[spectraFileIndex];
// mark the file as in-progress
StartingDataFile(origDataFile, new List <string> {
taskId, "Individual Spectra Files", origDataFile
});
CommonParameters combinedParams = SetAllFileSpecificCommonParams(CommonParameters, fileSettingsList[spectraFileIndex]);
MassDiffAcceptor searchMode = new DotMassDiffAcceptor("", GetAcceptableMassShifts(fixedModifications, variableModifications, gptmdModifications, combos), combinedParams.PrecursorMassTolerance);
NewCollection(Path.GetFileName(origDataFile), new List <string> {
taskId, "Individual Spectra Files", origDataFile
});
Status("Loading spectra file...", new List <string> {
taskId, "Individual Spectra Files", origDataFile
});
MsDataFile myMsDataFile = myFileManager.LoadFile(origDataFile, combinedParams);
Status("Getting ms2 scans...", new List <string> {
taskId, "Individual Spectra Files", origDataFile
});
Ms2ScanWithSpecificMass[] arrayOfMs2ScansSortedByMass = GetMs2Scans(myMsDataFile, origDataFile, combinedParams).OrderBy(b => b.PrecursorMass).ToArray();
myFileManager.DoneWithFile(origDataFile);
PeptideSpectralMatch[] allPsmsArray = new PeptideSpectralMatch[arrayOfMs2ScansSortedByMass.Length];
new ClassicSearchEngine(allPsmsArray, arrayOfMs2ScansSortedByMass, variableModifications, fixedModifications, null, proteinList, searchMode, combinedParams, new List <string> {
taskId, "Individual Spectra Files", origDataFile
}).Run();
allPsms.AddRange(allPsmsArray.Where(p => p != null));
FinishedDataFile(origDataFile, new List <string> {
taskId, "Individual Spectra Files", origDataFile
});
ReportProgress(new ProgressEventArgs(100, "Done!", new List <string> {
taskId, "Individual Spectra Files", origDataFile
}));
}
ReportProgress(new ProgressEventArgs(100, "Done!", new List <string> {
taskId, "Individual Spectra Files"
}));
allPsms = allPsms.OrderByDescending(b => b.Score)
.ThenBy(b => b.PeptideMonisotopicMass.HasValue ? Math.Abs(b.ScanPrecursorMass - b.PeptideMonisotopicMass.Value) : double.MaxValue)
.GroupBy(b => new Tuple <string, int, double?>(b.FullFilePath, b.ScanNumber, b.PeptideMonisotopicMass))
.Select(b => b.First()).ToList();
new FdrAnalysisEngine(allPsms, tempSearchMode.NumNotches, CommonParameters, new List <string> {
taskId
}).Run();
var writtenFile = Path.Combine(OutputFolder, "GPTMD_Candidates.psmtsv");
WritePsmsToTsv(allPsms, writtenFile, new Dictionary <string, int>());
FinishedWritingFile(writtenFile, new List <string> {
taskId
});
// get file-specific precursor mass tolerances for the GPTMD engine
var filePathToPrecursorMassTolerance = new Dictionary <string, Tolerance>();
for (int i = 0; i < currentRawFileList.Count; i++)
{
string filePath = currentRawFileList[i];
Tolerance fileTolerance = CommonParameters.PrecursorMassTolerance;
if (fileSettingsList[i] != null && fileSettingsList[i].PrecursorMassTolerance != null)
{
fileTolerance = fileSettingsList[i].PrecursorMassTolerance;
}
filePathToPrecursorMassTolerance.Add(filePath, fileTolerance);
}
// run GPTMD engine
var gptmdResults = (GptmdResults) new GptmdEngine(allPsms, gptmdModifications, combos, filePathToPrecursorMassTolerance, CommonParameters, new List <string> {
taskId
}).Run();
// Stop if canceled
if (GlobalVariables.StopLoops)
{
return(MyTaskResults);
}
// write GPTMD databases
if (dbFilenameList.Any(b => !b.IsContaminant))
{
List <string> databaseNames = new List <string>();
foreach (var nonContaminantDb in dbFilenameList.Where(p => !p.IsContaminant))
{
var dbName = Path.GetFileNameWithoutExtension(nonContaminantDb.FilePath);
var theExtension = Path.GetExtension(nonContaminantDb.FilePath).ToLowerInvariant();
bool compressed = theExtension.EndsWith("gz");
databaseNames.Add(compressed ? Path.GetFileNameWithoutExtension(dbName) : dbName);
}
string outputXMLdbFullName = Path.Combine(OutputFolder, string.Join("-", databaseNames) + "GPTMD.xml");
var newModsActuallyWritten = ProteinDbWriter.WriteXmlDatabase(gptmdResults.Mods, proteinList.Where(b => !b.IsDecoy && !b.IsContaminant).ToList(), outputXMLdbFullName);
FinishedWritingFile(outputXMLdbFullName, new List <string> {
taskId
});
MyTaskResults.NewDatabases.Add(new DbForTask(outputXMLdbFullName, false));
MyTaskResults.AddNiceText("Modifications added: " + newModsActuallyWritten.Select(b => b.Value).Sum());
MyTaskResults.AddNiceText("Mods types and counts:");
MyTaskResults.AddNiceText(string.Join(Environment.NewLine, newModsActuallyWritten.OrderByDescending(b => b.Value).Select(b => "\t" + b.Key + "\t" + b.Value)));
}
if (dbFilenameList.Any(b => b.IsContaminant))
{
// do NOT use this code (Path.GetFilenameWithoutExtension) because GPTMD on .xml.gz will result in .xml.xml file type being written
//string outputXMLdbFullNameContaminants = Path.Combine(OutputFolder, string.Join("-", dbFilenameList.Where(b => b.IsContaminant).Select(b => Path.GetFileNameWithoutExtension(b.FilePath))) + "GPTMD.xml");
List <string> databaseNames = new List <string>();
foreach (var contaminantDb in dbFilenameList.Where(p => p.IsContaminant))
{
var dbName = Path.GetFileName(contaminantDb.FilePath);
int indexOfFirstDot = dbName.IndexOf(".");
databaseNames.Add(dbName.Substring(0, indexOfFirstDot));
}
string outputXMLdbFullNameContaminants = Path.Combine(OutputFolder, string.Join("-", databaseNames) + "GPTMD.xml");
var newModsActuallyWritten = ProteinDbWriter.WriteXmlDatabase(gptmdResults.Mods, proteinList.Where(b => !b.IsDecoy && b.IsContaminant).ToList(), outputXMLdbFullNameContaminants);
FinishedWritingFile(outputXMLdbFullNameContaminants, new List <string> {
taskId
});
MyTaskResults.NewDatabases.Add(new DbForTask(outputXMLdbFullNameContaminants, true));
MyTaskResults.AddNiceText("Contaminant modifications added: " + newModsActuallyWritten.Select(b => b.Value).Sum());
MyTaskResults.AddNiceText("Mods types and counts:");
MyTaskResults.AddNiceText(string.Join(Environment.NewLine, newModsActuallyWritten.OrderByDescending(b => b.Value).Select(b => "\t" + b.Key + "\t" + b.Value)));
}
return(MyTaskResults);
}
protected override MyTaskResults RunSpecific(string OutputFolder, List <DbForTask> dbFilenameList, List <string> currentRawFileList, string taskId, FileSpecificSettings[] fileSettingsList)
{
myTaskResults = new MyTaskResults(this)
{
newDatabases = new List <DbForTask>()
};
Status("Loading modifications...", new List <string> {
taskId
});
List <ModificationWithMass> variableModifications = GlobalVariables.AllModsKnown.OfType <ModificationWithMass>().Where(b => CommonParameters.ListOfModsVariable.Contains((b.modificationType, b.id))).ToList();
List <ModificationWithMass> fixedModifications = GlobalVariables.AllModsKnown.OfType <ModificationWithMass>().Where(b => CommonParameters.ListOfModsFixed.Contains((b.modificationType, b.id))).ToList();
List <string> localizeableModificationTypes = CommonParameters.LocalizeAll ? GlobalVariables.AllModTypesKnown.ToList() : CommonParameters.ListOfModTypesLocalize.ToList();
List <ModificationWithMass> gptmdModifications = GlobalVariables.AllModsKnown.OfType <ModificationWithMass>().Where(b => GptmdParameters.ListOfModsGptmd.Contains((b.modificationType, b.id))).ToList();
IEnumerable <Tuple <double, double> > combos = LoadCombos(gptmdModifications).ToList();
List <PeptideSpectralMatch> allPsms = new List <PeptideSpectralMatch>();
List <ProductType> ionTypes = new List <ProductType>();
if (CommonParameters.BIons)
{
ionTypes.Add(ProductType.B);
}
if (CommonParameters.YIons)
{
ionTypes.Add(ProductType.Y);
}
if (CommonParameters.CIons)
{
ionTypes.Add(ProductType.C);
}
if (CommonParameters.ZdotIons)
{
ionTypes.Add(ProductType.Zdot);
}
Status("Loading proteins...", new List <string> {
taskId
});
Dictionary <string, Modification> um = null;
//Decoys are currently not being searched with DecoyType.None
var proteinList = dbFilenameList.SelectMany(b => LoadProteinDb(b.FilePath, true, DecoyType.Reverse, localizeableModificationTypes, b.IsContaminant, out um)).ToList();
var numRawFiles = currentRawFileList.Count;
proseCreatedWhileRunning.Append("The following G-PTM-D settings were used: "); proseCreatedWhileRunning.Append("protease = " + CommonParameters.DigestionParams.Protease + "; ");
proseCreatedWhileRunning.Append("maximum missed cleavages = " + CommonParameters.DigestionParams.MaxMissedCleavages + "; ");
proseCreatedWhileRunning.Append("minimum peptide length = " + CommonParameters.DigestionParams.MinPeptideLength + "; ");
if (CommonParameters.DigestionParams.MaxPeptideLength == null)
{
proseCreatedWhileRunning.Append("maximum peptide length = unspecified; ");
}
else
{
proseCreatedWhileRunning.Append("maximum peptide length = " + CommonParameters.DigestionParams.MaxPeptideLength + "; ");
}
proseCreatedWhileRunning.Append("initiator methionine behavior = " + CommonParameters.DigestionParams.InitiatorMethionineBehavior + "; ");
proseCreatedWhileRunning.Append("max modification isoforms = " + CommonParameters.DigestionParams.MaxModificationIsoforms + "; ");
proseCreatedWhileRunning.Append("fixed modifications = " + string.Join(", ", fixedModifications.Select(m => m.id)) + "; ");
proseCreatedWhileRunning.Append("variable modifications = " + string.Join(", ", variableModifications.Select(m => m.id)) + "; ");
proseCreatedWhileRunning.Append("G-PTM-D modifications count = " + gptmdModifications.Count + "; ");
//puppet searchmode for writing files. Actual searchmode is filespecific
MassDiffAcceptor tempSearchMode = new DotMassDiffAcceptor("", GetAcceptableMassShifts(fixedModifications, variableModifications, gptmdModifications, combos), CommonParameters.PrecursorMassTolerance);
proseCreatedWhileRunning.Append("parent mass tolerance(s) = {" + tempSearchMode.ToProseString() + "}; ");
proseCreatedWhileRunning.Append("product mass tolerance = " + CommonParameters.ProductMassTolerance + " Da. ");
proseCreatedWhileRunning.Append("The combined search database contained " + proteinList.Count + " total entries including " + proteinList.Where(p => p.IsContaminant).Count() + " contaminant sequences. ");
Status("Running G-PTM-D...", new List <string> {
taskId
});
HashSet <IDigestionParams> ListOfDigestionParams = GetListOfDistinctDigestionParams(CommonParameters, fileSettingsList.Select(b => SetAllFileSpecificCommonParams(CommonParameters, b)));
MyFileManager myFileManager = new MyFileManager(true);
object lock1 = new object();
object lock2 = new object();
ParallelOptions parallelOptions = new ParallelOptions();
if (CommonParameters.MaxParallelFilesToAnalyze.HasValue)
{
parallelOptions.MaxDegreeOfParallelism = CommonParameters.MaxParallelFilesToAnalyze.Value;
}
Parallel.For(0, currentRawFileList.Count, parallelOptions, spectraFileIndex =>
{
var origDataFile = currentRawFileList[spectraFileIndex];
ICommonParameters combinedParams = SetAllFileSpecificCommonParams(CommonParameters, fileSettingsList[spectraFileIndex]);
MassDiffAcceptor searchMode = new DotMassDiffAcceptor("", GetAcceptableMassShifts(fixedModifications, variableModifications, gptmdModifications, combos), combinedParams.PrecursorMassTolerance);
NewCollection(Path.GetFileName(origDataFile), new List <string> {
taskId, "Individual Spectra Files", origDataFile
});
StartingDataFile(origDataFile, new List <string> {
taskId, "Individual Spectra Files", origDataFile
});
Status("Loading spectra file...", new List <string> {
taskId, "Individual Spectra Files", origDataFile
});
IMsDataFile <IMsDataScan <IMzSpectrum <IMzPeak> > > myMsDataFile = myFileManager.LoadFile(origDataFile, combinedParams.TopNpeaks, combinedParams.MinRatio, combinedParams.TrimMs1Peaks, combinedParams.TrimMsMsPeaks);
Status("Getting ms2 scans...", new List <string> {
taskId, "Individual Spectra Files", origDataFile
});
Ms2ScanWithSpecificMass[] arrayOfMs2ScansSortedByMass = GetMs2Scans(myMsDataFile, origDataFile, combinedParams.DoPrecursorDeconvolution, combinedParams.UseProvidedPrecursorInfo, combinedParams.DeconvolutionIntensityRatio, combinedParams.DeconvolutionMaxAssumedChargeState, combinedParams.DeconvolutionMassTolerance).OrderBy(b => b.PrecursorMass).ToArray();
myFileManager.DoneWithFile(origDataFile);
PeptideSpectralMatch[] allPsmsArray = new PeptideSpectralMatch[arrayOfMs2ScansSortedByMass.Length];
new ClassicSearchEngine(allPsmsArray, arrayOfMs2ScansSortedByMass, variableModifications, fixedModifications, proteinList, ionTypes, searchMode, false, combinedParams, combinedParams.ProductMassTolerance, new List <string> {
taskId, "Individual Spectra Files", origDataFile
}).Run();
lock (lock2)
{
allPsms.AddRange(allPsmsArray);
}
FinishedDataFile(origDataFile, new List <string> {
taskId, "Individual Spectra Files", origDataFile
});
ReportProgress(new ProgressEventArgs(100, "Done!", new List <string> {
taskId, "Individual Spectra Files", origDataFile
}));
});
ReportProgress(new ProgressEventArgs(100, "Done!", new List <string> {
taskId, "Individual Spectra Files"
}));
// Group and order psms
SequencesToActualProteinPeptidesEngine sequencesToActualProteinPeptidesEngineTest = new SequencesToActualProteinPeptidesEngine(allPsms, proteinList, fixedModifications, variableModifications, ionTypes, ListOfDigestionParams, CommonParameters.ReportAllAmbiguity, new List <string> {
taskId
});
var resTest = (SequencesToActualProteinPeptidesEngineResults)sequencesToActualProteinPeptidesEngineTest.Run();
Dictionary <CompactPeptideBase, HashSet <PeptideWithSetModifications> > compactPeptideToProteinPeptideMatchingTest = resTest.CompactPeptideToProteinPeptideMatching;
foreach (var huh in allPsms)
{
if (huh != null)
{
huh.MatchToProteinLinkedPeptides(compactPeptideToProteinPeptideMatchingTest);
}
}
allPsms = allPsms.Where(b => b != null).OrderByDescending(b => b.Score).ThenBy(b => b.PeptideMonisotopicMass.HasValue ? Math.Abs(b.ScanPrecursorMass - b.PeptideMonisotopicMass.Value) : double.MaxValue).GroupBy(b => new Tuple <string, int, double?>(b.FullFilePath, b.ScanNumber, b.PeptideMonisotopicMass)).Select(b => b.First()).ToList();
new FdrAnalysisEngine(allPsms, tempSearchMode.NumNotches, false, new List <string> {
taskId
}).Run();
var writtenFile = Path.Combine(OutputFolder, "GPTMD_Candidates.psmtsv");
WritePsmsToTsv(allPsms, writtenFile, new Dictionary <string, int>());
SucessfullyFinishedWritingFile(writtenFile, new List <string> {
taskId
});
var gptmdResults = (GptmdResults) new GptmdEngine(allPsms, gptmdModifications, combos, CommonParameters.PrecursorMassTolerance, new List <string> {
taskId
}).Run();
if (dbFilenameList.Any(b => !b.IsContaminant))
{
// do NOT use this code (Path.GetFilenameWithoutExtension) because GPTMD on .xml.gz will result in .xml.xml file type being written
//string outputXMLdbFullName = Path.Combine(OutputFolder, string.Join("-", dbFilenameList.Where(b => !b.IsContaminant).Select(b => Path.GetFileNameWithoutExtension(b.FilePath))) + "GPTMD.xml");
List <string> databaseNames = new List <string>();
foreach (var nonContaminantDb in dbFilenameList.Where(p => !p.IsContaminant))
{
var dbName = Path.GetFileName(nonContaminantDb.FilePath);
int indexOfFirstDot = dbName.IndexOf(".");
databaseNames.Add(dbName.Substring(0, indexOfFirstDot));
}
string outputXMLdbFullName = Path.Combine(OutputFolder, string.Join("-", databaseNames) + "GPTMD.xml");
var newModsActuallyWritten = ProteinDbWriter.WriteXmlDatabase(gptmdResults.Mods, proteinList.Where(b => !b.IsDecoy && !b.IsContaminant).ToList(), outputXMLdbFullName);
SucessfullyFinishedWritingFile(outputXMLdbFullName, new List <string> {
taskId
});
myTaskResults.newDatabases.Add(new DbForTask(outputXMLdbFullName, false));
myTaskResults.AddNiceText("Modifications added: " + newModsActuallyWritten.Select(b => b.Value).Sum());
myTaskResults.AddNiceText("Mods types and counts:");
myTaskResults.AddNiceText(string.Join(Environment.NewLine, newModsActuallyWritten.OrderByDescending(b => b.Value).Select(b => "\t" + b.Key + "\t" + b.Value)));
}
if (dbFilenameList.Any(b => b.IsContaminant))
{
// do NOT use this code (Path.GetFilenameWithoutExtension) because GPTMD on .xml.gz will result in .xml.xml file type being written
//string outputXMLdbFullNameContaminants = Path.Combine(OutputFolder, string.Join("-", dbFilenameList.Where(b => b.IsContaminant).Select(b => Path.GetFileNameWithoutExtension(b.FilePath))) + "GPTMD.xml");
List <string> databaseNames = new List <string>();
foreach (var contaminantDb in dbFilenameList.Where(p => p.IsContaminant))
{
var dbName = Path.GetFileName(contaminantDb.FilePath);
int indexOfFirstDot = dbName.IndexOf(".");
databaseNames.Add(dbName.Substring(0, indexOfFirstDot));
}
string outputXMLdbFullNameContaminants = Path.Combine(OutputFolder, string.Join("-", databaseNames) + "GPTMD.xml");
var newModsActuallyWritten = ProteinDbWriter.WriteXmlDatabase(gptmdResults.Mods, proteinList.Where(b => !b.IsDecoy && b.IsContaminant).ToList(), outputXMLdbFullNameContaminants);
SucessfullyFinishedWritingFile(outputXMLdbFullNameContaminants, new List <string> {
taskId
});
myTaskResults.newDatabases.Add(new DbForTask(outputXMLdbFullNameContaminants, true));
myTaskResults.AddNiceText("Contaminant modifications added: " + newModsActuallyWritten.Select(b => b.Value).Sum());
myTaskResults.AddNiceText("Mods types and counts:");
myTaskResults.AddNiceText(string.Join(Environment.NewLine, newModsActuallyWritten.OrderByDescending(b => b.Value).Select(b => "\t" + b.Key + "\t" + b.Value)));
}
return(myTaskResults);
}