/*
* These are from the experiment and will be removed if you call reset on the
* graph
*/
public Peptide addPeptideFromIdentification(IDs id, double currentTime)
{
String peptideSequence = id.getPeptideSequence();
double peptideMass = id.getPeptideMass();
HashSet <String> parentProteinAccessions = id.getParentProteinAccessions();
Peptide pep;
if (containsPeptide(peptideSequence))
{
return(getPeptide(peptideSequence));
}
else
{
// Adds the peptide from the identification into the database
pep = new Peptide(peptideSequence, peptideMass, false);
// these peptides will be removed if reset() is called
SequenceToPeptide.Add(peptideSequence, pep);
peptides.Add(pep);
if (includeRetentionTime)
{
// TODO right now this takes the current time as the peak retention time...
// should we run it through RTCalc so we can better estimate our RT alignment?
// 2019-04-29 No, do not. Observed times are better than predicted
// pep.setRetentionTime(RetentionTimeUtil.convertDoubleToRetentionTime(rt,
// retentionTimeWindow,
// retentionTimeWindow));
RetentionTime rt = new RetentionTime(currentTime + retentionTimeWindow, retentionTimeWindow,
retentionTimeWindow, false);
pep.setRetentionTime(rt);
}
}
// update its parent proteins
foreach (String acc in parentProteinAccessions)
{
Protein parentProtein = AccesstionToProtein[acc];
if (parentProtein != null)
{
pep.addProtein(parentProtein);
}
else if (acc.Contains(GlobalVar.DecoyPrefix))
{
log.Info("WARNINGin Decoy parent protein for this peptide was not found!!");
log.Info(acc);
}
else
{
log.Warn("WARNINGin Non-decoy parent protein for this peptide was not found!!");
log.Warn(acc);
}
}
return(pep);
}
protected Peptide getPeptideFromIdentification(IDs id)
{
String peptideSequence = id.getPeptideSequence();
Peptide pep = database.getPeptide(peptideSequence);
if (pep == null)
{
log.Debug("Adding peptide...");
pep = database.addPeptideFromIdentification(id, currentTime);
log.Debug("Added peptide " + peptideSequence + ".");
performanceEvaluator.countPeptidesAdded();
}
else
{
log.Debug("Peptide found.");
performanceEvaluator.countPeptidesIdentified();
}
return(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())));
}
/*
* 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());
}
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();
}