/*
* Writes the result database to a file, to make it faster to re-initialize the
* software
*/
//public static void writeResultDatabaseToFile(String file_path, ResultDatabase rd)
//{
// log.Debug("Writing Result Database to a file...");
// try
// {
// StreamWriter writer = new StreamWriter(file_path);
// log.Debug("File name: " + file_path);
// // Get all IDs
// List<IDs> ids = new List<IDs>(rd.getIDs());
// // Sort by scan number
// ids.Sort((IDs x, IDs y) => (x.getScanNum()).CompareTo(y.getScanNum()));
// // Write header
// String[] header = new String[] { "scan", "scan_t", "peptide_mass", "peptide_sequence", "parent_proteins",
// "peptide_evidence", "peptide_reference", "database_sequence_id", "xCorr", "deltaCN", "deltaCNStar",
// "spscore", "sprank", "evalue" };
// writer.Write(String.Join("\t", header));
// foreach (IDs id in ids)
// {
// writer.Write("\n" + outputIDToTSVFormat(id));
// writer.Flush();
// }
// writer.Flush();
// writer.Close();
// }
// catch (Exception e)
// {
// Console.WriteLine(e.ToString());
// log.Error("Writing file unsuccessful!!!");
// Environment.Exit(0);
// }
// log.Debug("Writing file successful.");
//}
/*
* Write the identification features used for training the logistic regression
* classifier
*/
//public static void writeIdentificationFeaturesFile(String file_path,
// List<IdentificationFeatures> positiveTrainingSet,
// List<IdentificationFeatures> negativeTrainingSet)
//{
// log.Debug("Writing Identification Features to a file...");
// try
// {
// StreamWriter writer = new StreamWriter(file_path);
// log.Debug("File name: " + file_path);
// // Write header TODO remove
// String header = "label," + IdentificationFeatures.getHeader();
// writer.Write(header);
// // in the first column, 1 indicates positive training set
// foreach (IdentificationFeatures i in positiveTrainingSet)
// {
// writer.Write("\n" + "1," + i.WriteToFile());
// writer.Flush();
// }
// // in the first column, 0 indicates negative training set
// foreach (IdentificationFeatures i in negativeTrainingSet)
// {
// writer.Write("\n" + "0," + i.WriteToFile());
// writer.Flush();
// }
// writer.Flush();
// writer.Close();
// }
// catch (Exception e)
// {
// e.printStackTrace();
// log.Error("Writing file unsuccessful!!!");
// System.exit(0);
// }
// log.Debug("Writing file successful.");
//}
/*
* Useful for outputting the IDs object in the correct order for
* writeResultDatabaseToFile
*/
private static String outputIDToTSVFormat(IDs id)
{
return(id.getScanNum() + "\t" + id.getScanTime() + "\t" + id.getPeptideMass() + "\t" + id.getPeptideSequence()
+ "\t" + id.getParentProteinAccessions() + "\t" + id.getPepEvid() + "\t" + id.getPepRef() + "\t"
+ id.getDBSeqID() + "\t" + id.getXCorr() + "\t" + id.getDeltaCN() + "\t" + id.getDeltaCNStar() + "\t"
+ id.getSPScore() + "\t" + id.getSPRank() + "\t" + id.getEValue());
}
protected void evaluateIdentification(IDs id)
{
// check if the peptide is identified or not
if (id == null)
{
performanceEvaluator.countMS2UnidentifiedAnalyzed();
return;
}
Peptide pep = getPeptideFromIdentification(id); // if it was going to be null, it already returned
// is fragmented
// add decoy or non-existent protein connections
// database.addProteinFromIdentification(pep, id.getParentProteinAccessions());
Double xCorr = id.getXCorr();
Double dCN = id.getDeltaCN();
pep.addScore(xCorr, xCorrThreshold, dCN);
performanceEvaluator.evaluateAnalysis(exclusionList, pep);
// add the peptide to the exclusion list if it is over the xCorr threshold
if ((xCorr > xCorrThreshold))
{
performanceEvaluator.countPeptidesExcluded();
log.Debug("xCorrThreshold passed. Peptide added to the exclusion list.");
exclusionList.addPeptide(pep);
// calibrates our retention time alignment if the observed time is different
// from the predicted only if it passes this threshold
calibrateRetentionTime(pep);
}
// add all of the other peptides belonging to the parent protein(s) if numDB
// threshold is passed
foreach (Protein parentProtein in pep.getProteins())
{
if ((parentProtein.getNumDB() >= numDBThreshold) && (!parentProtein.IsExcluded()))
{
parentProtein.setExcluded(true);
log.Debug("Parent protein " + parentProtein.getAccession() + " is identified confidently "
+ parentProtein.getNumDB() + " times!");
performanceEvaluator.countProteinsExcluded();
exclusionList.addProtein(parentProtein);
}
log.Debug(parentProtein);
}
log.Debug(pep);
}
protected void evaluateIdentification(IDs id)
{
log.Debug("NoExclusion. Scores added, but nothing added to the exclusion list");
// check if the peptide is identified or not
if (id == null)
{
performanceEvaluator.countMS2UnidentifiedAnalyzed();
return;
}
Peptide pep = getPeptideFromIdentification(id); // if it was going to be null, it already returned
// is fragmented
// add decoy or non-existent protein connections
// database.addProteinFromIdentification(pep, id.getParentProteinAccessions());
Double xCorr = id.getXCorr();
Double dCN = id.getDeltaCN();
pep.addScore(xCorr, 0.0, dCN);
performanceEvaluator.evaluateAnalysis(exclusionList, pep);
RetentionTime rt = pep.getRetentionTime();
if (!rtCalcPredictedRT.Keys.Contains(pep.getSequence()))
{
rtCalcPredictedRT.Add(pep.getSequence(), rt.getRetentionTimePeak());
}
ObservedPeptideRtTrackerObject observedPep = new ObservedPeptideRtTrackerObject(pep.getSequence(), id.getScanTime(), id.getXCorr(),
rt.getRetentionTimePeak(), rt.getRetentionTimeStart() + GlobalVar.retentionTimeWindowSize,
RetentionTime.getRetentionTimeOffset(), rtCalcPredictedRT[pep.getSequence()], (rt.IsPredicted() ? 1 : 0));
if ((xCorr > 2.5))
{
// calibrates our retention time alignment if the observed time is different
// from the predicted only if it passes this threshold
calibrateRetentionTime(pep);
}
observedPep.offset = RetentionTime.getRetentionTimeOffset();
peptideIDRT.Add(observedPep);
}
protected void evaluateIdentification(IDs id)
{
log.Debug("RandomExclusion. Scores added, but nothing added to the exclusion list");
// check if the peptide is identified or not
if (id == null)
{
performanceEvaluator.countMS2UnidentifiedAnalyzed();
return;
}
Peptide pep = getPeptideFromIdentification(id); // if it was going to be null, it already returned
// is fragmented
Double xCorr = id.getXCorr();
Double dCN = id.getDeltaCN();
pep.addScore(xCorr, 0.0, dCN);
performanceEvaluator.evaluateAnalysis(exclusionList, pep);
}
public static void WritePSM(IDs id)
{
IDWriter.WriteLine(String.Join("\t", id.getScanNum().ToString(), id.getScanTime().ToString(), id.getPeptideSequence().ToString(),
id.getPeptideMass().ToString(), id.getXCorr().ToString(), id.getDeltaCN().ToString(), String.Join(",", id.getParentProteinAccessions())));
}
protected void evaluateIdentification(IDs id)
{
// check if the peptide is identified or not
if (id == null)
{
performanceEvaluator.countMS2UnidentifiedAnalyzed();
return;
}
Peptide pep = getPeptideFromIdentification(id); // id is null, it already returned
// add decoy or non-existent protein connections
// database.AddProteinFromIdentification(pep, id.getParentProteinAccessions());
Double xCorr = id.getXCorr();
Double dCN = id.getDeltaCN();
pep.addScore(xCorr, dCN);
#if (!DONTEVALUATE)
performanceEvaluator.evaluateAnalysis(exclusionList, pep);
#endif
// exclude this peptide for analysis if the xCorr score is above a threshold
const double XCORR_THRESHOLD = 2.5;
// add the peptide to the exclusion list if it is over the xCorr threshold
if ((xCorr > XCORR_THRESHOLD))
{
performanceEvaluator.countPeptidesExcluded();
log.Debug("xCorrThreshold passed. Peptide added to the exclusion list.");
exclusionList.addPeptide(pep);
// calibrates our retention time alignment if the observed time is different
// from the predicted only if it passes this threshold
calibrateRetentionTime(pep);
}
// Add all the peptides corresponding to the parent protein, if the parent
// protein is deemed confidently identified by the logisitc regression
// classifier
Dictionary <String, Boolean> identificationPredictions = IdentificationFeatureExtractionUtil
.assessProteinIdentificationConfidence(pep.getProteins(), lrAccord);
List <Protein> proteinsToExclude = new List <Protein>();
foreach (Protein parentProtein in pep.getProteins())
{
// prevents repeated exclusion of a protein already excluded
if ((!parentProtein.IsExcluded()))
{
// determine if parent protein is confidently identified
bool isConfidentlyIdentified = identificationPredictions[parentProtein.getAccession()];
if (isConfidentlyIdentified)
{
// exclude all peptides of that protein
parentProtein.setExcluded(true);
log.Debug("Parent protein " + parentProtein.getAccession() + " is identified confidently "
+ parentProtein.getNumDB() + " times!");
performanceEvaluator.countProteinsExcluded();
proteinsToExclude.Add(parentProtein);
}
}
}
exclusionList.addProteins(proteinsToExclude);
}
protected void evaluateIdentification(IDs id)
{
// check if the peptide is identified or not
if (id == null)
{
performanceEvaluator.countMS2UnidentifiedAnalyzed();
return;
}
Peptide pep = getPeptideFromIdentification(id); // id is null, it already returned
//log.Info("Peptide Observed Time: {0}\tPredicted Time: {1} -----------------", id.getScanTime(),pep.getRetentionTime().getRetentionTimeStart());
// add decoy or non-existent protein connections
// database.AddProteinFromIdentification(pep, id.getParentProteinAccessions());
Double xCorr = id.getXCorr();
double dCN = id.getDeltaCN();
pep.addScore(xCorr, dCN);
#if (!DONTEVALUATE)
performanceEvaluator.evaluateAnalysis(exclusionList, pep);
#endif
//RetentionTime rt = pep.getRetentionTime();
//if (!rtCalcPredictedRT.Keys.Contains(pep.getSequence()))
//{
// rtCalcPredictedRT.Add(pep.getSequence(), rt.getRetentionTimePeak());
//}
//double[] values = new double[] { id.getScanTime(), id.getXCorr(), rt.getRetentionTimePeak(), rt.getRetentionTimeStart() + GlobalVar.retentionTimeWindowSize, RetentionTime.getRetentionTimeOffset(), rtCalcPredictedRT[pep.getSequence()], rt.IsPredicted() ? 1 : 0 };
// exclude this peptide for analysis if the xCorr score is above a threshold
const double XCORR_THRESHOLD = 2.5;
// add the peptide to the exclusion list if it is over the xCorr threshold
if ((xCorr > XCORR_THRESHOLD))
{
performanceEvaluator.countPeptidesExcluded();
log.Debug("xCorrThreshold passed. Peptide added to the exclusion list.");
exclusionList.addPeptide(pep);
// calibrates our retention time alignment if the observed time is different
// from the predicted only if it passes this threshold
calibrateRetentionTime(pep);
}
// Add all the peptides corresponding to the parent protein, if the parent
// protein is deemed confidently identified by the logisitc regression
// classifier
Dictionary <String, Boolean> identificationPredictions = IdentificationFeatureExtractionUtil
.assessProteinIdentificationConfidence(pep.getProteins(), lrAccord);
List <Protein> proteinsToExclude = new List <Protein>();
foreach (Protein parentProtein in pep.getProteins())
{
// prevents repeated exclusion of a protein already excluded
if ((!parentProtein.IsExcluded()))
{
// determine if parent protein is confidently identified
bool isConfidentlyIdentified = identificationPredictions[parentProtein.getAccession()];
if (isConfidentlyIdentified)
{
// exclude all peptides of that protein
#if TRACKEXCLUDEDPROTEINFEATURE
excludedProteinFeatureList.Add(parentProtein.vectorize().ItemArray);
#endif
parentProtein.setExcluded(true);
log.Debug("Parent protein " + parentProtein.getAccession() + " is identified confidently "
+ parentProtein.getNumDB() + " times!");
performanceEvaluator.countProteinsExcluded();
proteinsToExclude.Add(parentProtein);
}
}
}
exclusionList.addProteins(proteinsToExclude);
}
public static void CometSingleSearchTest()
{
String idx = "C:\\Coding\\2019LavalleeLab\\GitProjectRealTimeMS\\TestData\\PreComputedFiles\\uniprot_SwissProt_Human_1_11_2017_decoyConcacenated.fasta.idx";
//String idx = "C:\\temp\\comet_2019015\\comet_source_2019015\\IDXMake\\uniprot_SwissProt_Human_1_11_2017_decoyConcacenated.fasta.idx";
String param = "C:\\Coding\\2019LavalleeLab\\temp2\\ExampleDataSet\\2019.comet.params";
CometSingleSearch.InitializeComet(idx, param);
CometSingleSearch.QualityCheck();
Program.ExitProgram(1);
String dataRoot = "C:\\Users\\LavalleeLab\\Documents\\JoshTemp\\MealTimeMS_APITestRun\\Data\\";
String outputRoot = "C:\\Users\\LavalleeLab\\Documents\\JoshTemp\\MealTimeMS_APITestRun\\Output\\";
//String mzmlPath = dataRoot+"60minMZMLShrink.csv";
String mzmlPath = dataRoot + "8001.ms2.txt";
String dbPath = dataRoot + "tinyDB.fasta.idx"; //
String outputPath = outputRoot + "output.txt";
String paramsPath = dataRoot + "comet.params";
MZMLFile mzml = Loader.parseMS2File(mzmlPath);
//MZMLFile mzml = null;
CometSingleSearch.InitializeComet(dbPath, paramsPath);
var watch = System.Diagnostics.Stopwatch.StartNew();
int counter = 0;
Console.WriteLine("Starting comet search");
WriterClass.initiateWriter(outputPath);
for (int i = 0; i < 1; i++)
{
if (i % 1 == 0)
{
Spectra spec = mzml.getSpectraArray()[i];
if (spec.getMSLevel() != 2)
{
continue;
}
Console.WriteLine("scanNum {0} RT {2} Mass {2} MSLevel {3}", spec.getScanNum(), spec.getStartTime(),
spec.getCalculatedPrecursorMass(), spec.getMSLevel());
IDs id = null;
if (CometSingleSearch.Search(spec, out id))
{
String outLine = String.Format("{0}\t{1}\txcorr\t{2}\tdcn\t{3}", id.getScanNum(), id.getPeptideSequence(), id.getXCorr(), id.getDeltaCN());
Console.WriteLine(outLine);
WriterClass.writeln(outLine);
}
else
{
Console.WriteLine("Spectrum cannot be matched\n");
}
counter++;
}
}
watch.Stop();
Console.WriteLine("Comet search of " + counter + " spectra took " + watch.ElapsedMilliseconds + " milliseconds");
WriterClass.CloseWriter();
}