static void PreExperimentSetUp()
{
ConstructDecoyFasta();
ConstructIDX();
if (GlobalVar.IsSimulation)
//if(false)
{
ms2SpectraList = Loader.parseMS2File(InputFileOrganizer.MS2SimulationTestFile).getSpectraArray();
GlobalVar.ExperimentTotalScans = ms2SpectraList.Count;
FullPepXMLAndProteinProphetSetup();
baseLinePpr = ProteinProphetEvaluator.getProteinProphetResult(InputFileOrganizer.OriginalProtXMLFile);
//so in alex's original code, "original experiment" refers to original experiment without any exclusion or manipulation with this program
//"baseline comparison" refers to the results after "NoExclusion" run, which is a top 6 or top 12 DDA run, which is not implemented in this program
//So the two are the same in thie program
int numMS2Analyzed = (int)GlobalVar.ExperimentTotalScans;
PerformanceEvaluator.setBaselineComparison(baseLinePpr, numMS2Analyzed, 12);
PerformanceEvaluator.setOriginalExperiment(baseLinePpr.getNum_proteins_identified());
}
log.Debug("Setting up Database");
database = databaseSetUp(InputFileOrganizer.ExclusionDBFasta);
log.Debug("Done setting up database.");
CometSingleSearch.InitializeComet(InputFileOrganizer.IDXDataBase, InputFileOrganizer.CometParamsFile);
//CometSingleSearch.InitializeComet_NonRealTime("C:\\Coding\\2019LavalleeLab\\temp2\\ModifiedDBSearchFiles\\NoExclusionRealTimeCometSearch.tsv");
//CometSingleSearch.QualityCheck();
Console.WriteLine("pre-experimental setup finished");
}
public static ProteinProphetResult postProcessing(ExclusionProfile exclusionProfile, String experimentName,
Boolean keepResults)
{
String partialCometFileOutputFolder = Path.Combine(InputFileOrganizer.OutputFolderOfTheRun, "PartialCometFile");
if (!Directory.Exists(partialCometFileOutputFolder))
{
Directory.CreateDirectory(partialCometFileOutputFolder);
}
String outputCometFile = Path.Combine(partialCometFileOutputFolder,
experimentName + "_partial" + InputFileOrganizer.PepXMLSuffix);
PartialPepXMLWriter.writePartialPepXMLFile(InputFileOrganizer.OriginalCometOutput, exclusionProfile.getSpectraUsed(),
outputCometFile, InputFileOrganizer.MS2SimulationTestFile, InputFileOrganizer.FASTA_FILE, outputCometFile); //TODO was using MZML instead of MS2
ProteinProphetResult ppr = RunProteinProphet(outputCometFile, InputFileOrganizer.OutputFolderOfTheRun, keepResults);
//PostProcessingScripts.deleteFile(outputCometFile);
// delete these files if this flag is false
//if (!keepResults)
//{
//}
return(ppr);
}
public BaselineComparison(ProteinProphetResult ppr, int numMS2, int ddaNum)
{
proteinsIdentifiedByNoExclusion = ppr.getProteinsIdentified();
numProteinsIdentifiedNaiveExperiment = proteinsIdentifiedByNoExclusion.Count;
totalResourcesNaiveExperiment = numMS2;
this.ddaNum = ddaNum;
}
public String getPerformanceVector(String experimentName, String experimentType, double analysisTime,
double totalRunTime, ProteinProphetResult ppr, int ddaNum, ExclusionProfile exclusionProfile)
{
performanceEvaluator.finalizePerformanceEvaluator(experimentName, experimentType, analysisTime, totalRunTime,
exclusionList, ppr, ddaNum, exclusionProfile);
return(performanceEvaluator.outputPerformance());
}
public static void setBaselineComparison(ProteinProphetResult ppr, int numMS2, int ddaNum)
{
if (!baselineComparisonSet.ContainsKey(ddaNum))
{
BaselineComparison bc = new BaselineComparison(ppr, numMS2, ddaNum);
baselineComparisonSet.Add(ddaNum, bc);
}
}
public static void DoJob()
{
String comet = "C:\\Users\\LavalleeLab\\Documents\\JoshTemp\\RealTimeMS\\TestData\\MS_QC_120min.pep.xml";
String output = "C:\\Users\\LavalleeLab\\Documents\\JoshTemp\\RealTimeMS\\TestData\\";
ProteinProphetResult ppr = PostProcessingScripts.RunProteinProphet(comet, output, true);
Console.WriteLine(ppr.ToString());
}
private void setProteinsIdentified(ProteinProphetResult ppr, List <String> proteinsIdentifiedByNoExclusion)
{
if (ppr != null)
{
List <String> proteinsIdentified = ppr.getProteinsIdentified();
int intersect = compareProteins(proteinsIdentifiedByNoExclusion, proteinsIdentified);
ChangeValue(Header.NumProteinsIdentified, proteinsIdentified.Count);
ChangeValue(Header.ProteinsIdentifiedInLimitedDDA, intersect);
}
}
public ProteinProphetFile(String protXMLFileName, Dictionary <String, List <String> > proteinsToPeptides,
double fdr_threshold, double protein_probablity_threshold)
{
this.protXMLFileName = protXMLFileName;
this.proteinsToPeptides = proteinsToPeptides;
int numProteinsIdentified = proteinsToPeptides.Keys.Count;
proteinProphetResult = new ProteinProphetResult(fdr_threshold, protein_probablity_threshold,
getProteinNames());
}
public static ProteinProphetResult RunProteinProphet(String cometFilePath, String outputFolder, Boolean keepResults)
{
Logger.debug("Post processing comet file: ");
Console.WriteLine("Runnign protein prophet, if program doesn't respond for a long time, try pressing a typing a few keys into the command line");
String proteinProphetOutput = ProteinProphetSearch(cometFilePath, outputFolder, keepResults);
ProteinProphetResult ppr = ProteinProphetEvaluator.getProteinProphetResult(proteinProphetOutput);
ppr.SetProteinGroup(ProteinProphetEvaluator.ExtractPositiveProteinGroups(proteinProphetOutput));
return(ppr);
}
public static void DoJob()
{
InputFileOrganizer.FASTA_FILE = "C:\\Coding\\2019LavalleeLab\\temp2\\ExampleDataSet\\uniprot_SwissProt_Human_1_11_2017.fasta";
//String outputCometFile = "C:\\Coding\\2019LavalleeLab\\temp2\\ModifiedDBSearchFiles\\Result\\ModdedSearch_MLGEGolden_nonCheat_peptideSearchResultIncluded\\PartialCometFile\\1ModdedSearch_MLGE_nonCheat_peptideSearchResultIncluded_partial.pep.xml";
String outputCometFile = "C:\\Coding\\2019LavalleeLab\\temp2\\ModifiedDBSearchFiles\\Result\\Modded_MLGEGolden_rtCheatpeptideSearchResultIncluded\\PartialCometFile\\1Modded_MLGEGolden_rtCheat_partial.pep.xml";
ProteinProphetResult ppr = PostProcessingScripts.RunProteinProphet(outputCometFile, InputFileOrganizer.OutputFolderOfTheRun, true);
//String proteinProphetFile = "C:\\Coding\\2019LavalleeLab\\temp2\\Output\\ProteinGroup_Combined_rtCheat\\protein_prophet_output\\ProteinGroup_Combined_rtCheat_partial_interact.prot.xml";
//ProteinProphetResult ppr = ProteinProphetEvaluator.getProteinProphetResult(proteinProphetFile);
Console.WriteLine(ppr.ToString());
Console.WriteLine("Protein groups " + ppr.getFilteredProteinGroups().Count);
}
private void postProcessingCalculations(int ddaNum, ProteinProphetResult ppr, ExclusionProfile exclusionProfile)
{
BaselineComparison bc = baselineComparisonSet[ddaNum];
List <String> proteinsIdentifiedByNoExclusion = bc.getProteinsIdentifiedByNoExclusion();
int totalResourcesNaiveExperiment = bc.getTotalResourcesNaiveExperiment();
int numProteinsIdentifiedNaiveExperiment = bc.getNumProteinsIdentifiedNaiveExperiment();
// set proteins identified first
setProteinsIdentified(ppr, proteinsIdentifiedByNoExclusion);
int correctlyExcluded = (int)data[Header.EvaluateExclusion_FoundOnCurrentExclusionList]
+ (int)data[Header.EvaluateExclusion_FoundOnCurrentObservedExclusionList];
int incorrectlyExcluded = (int)data[Header.EvaluateExclusion_NotFoundOnExclusionList];
/*
* found on past observed, found on past exclusion list, and found on future
* exclusion list are not incorrect exclusions, they are retention time being
* predicted incorrectly...
*/
double ratioIncorrectlyExcludedOverCorrectlyExcluded = takeRatio(incorrectlyExcluded, correctlyExcluded);
ChangeValue(Header.CorrectlyExcluded, correctlyExcluded);
ChangeValue(Header.IncorrectlyExcluded, incorrectlyExcluded);
ChangeValue(Header.RatioIncorrectlyExcludedOverCorrectlyExcluded, ratioIncorrectlyExcludedOverCorrectlyExcluded);
// Resources saved in total # available MS2 - # ms2 used foreach analysis
int resourcesSaved = totalResourcesNaiveExperiment - (int)data[Header.NumMS2Analyzed];
double percentResourcesSaved = takeRatio(resourcesSaved, totalResourcesNaiveExperiment);
double percentResourcesUsed = 1 - percentResourcesSaved;
ChangeValue(Header.PercentResourcesSaved, percentResourcesSaved);
ChangeValue(Header.PercentResourcesUsed, percentResourcesUsed);
/*-
* Protein Identification Sensitivity = # proteins identified / # proteins identified in whole experiment
* Protein Identification Fold Change = # proteins identified / # proteins identified by naive approach
* Protein Identification Sensitivity Limited DDA = # proteins identified also identified in naive approach / proteins identified by naive approach
*/
ChangeValue(Header.ProteinIdentificationSensitivity,
takeRatio((int)data[Header.NumProteinsIdentified], numProteinsIdentifiedOriginalExperiment));
ChangeValue(Header.ProteinIdentificationFoldChange,
takeRatio((int)data[Header.NumProteinsIdentified], numProteinsIdentifiedNaiveExperiment));
ChangeValue(Header.ProteinIdentificationSensitivityLimitedDDA,
takeRatio((int)data[Header.ProteinsIdentifiedInLimitedDDA], numProteinsIdentifiedNaiveExperiment));
List <String> inProgramExcludedProteins = exclusionProfile.getDatabase().getExcludedProteins();
int proteinOverlap_inProgramExcluded_vs_NoExclusion = compareProteins(inProgramExcludedProteins, proteinsIdentifiedByNoExclusion);
ChangeValue(Header.NumProteinOverlap_ExcludedProteinsAgainstNoExclusionProteins, proteinOverlap_inProgramExcluded_vs_NoExclusion);
ChangeValue(Header.ProteinGroupsIdentified, ppr.getFilteredProteinGroups().Count);
}
public static String DoJob(ProteinProphetResult ppr, ExclusionProfile exclusionProfile, int experimentNum)
{
String outputFile = Path.Combine(InputFileOrganizer.OutputFolderOfTheRun, "NumberOfPeptidesPerIdentifiedProtein_" + experimentNum + ".txt");
StreamWriter sw = new StreamWriter(outputFile);
sw.WriteLine("Accession\tNumberOfPeptides\tSpectralCount");
List <String> confidentlyIdentifiedProts = ppr.getProteinsIdentified();
foreach (String accession in confidentlyIdentifiedProts)
{
Protein prot = exclusionProfile.getDatabase().getProtein(accession);
HashSet <String> peptidesObserved = new HashSet <String>();
foreach (PeptideScore pepEvidence in prot.getPeptideScore())
{
peptidesObserved.Add(pepEvidence.getPeptideSequence());
}
sw.WriteLine("{0}\t{1}\t{2}", accession, peptidesObserved.Count, prot.getPeptideScore().Count);
}
sw.Close();
return(outputFile);
}
public static void DoJob()
{
StreamWriter sw = new StreamWriter(Path.Combine(InputFileOrganizer.OutputFolderOfTheRun, "ExcludedProteinComparison.txt"));
String ExcludedProteinFile = "C:\\Coding\\2019LavalleeLab\\temp2\\Output\\Gold_MLGE_nonCheat.txt_output\\ExcludedProteinList.txt";
StreamReader sr = new StreamReader(ExcludedProteinFile);
List <String> inProgramConfidentlyIdentified = new List <String>();
String line = sr.ReadLine();
while (line != null)
{
inProgramConfidentlyIdentified.Add(line);
line = sr.ReadLine();
}
String proteinProphetFile = "C:\\Coding\\2019LavalleeLab\\GitProjectRealTimeMS\\TestData\\PreComputedFiles\\MS_QC_120min_interact.prot.xml";
ProteinProphetResult ppr = ProteinProphetEvaluator.getProteinProphetResult(proteinProphetFile);
List <String> realConfidentIdentified = ppr.getProteinsIdentified();
List <String> intersection = ListUtil.FindIntersection(inProgramConfidentlyIdentified, realConfidentIdentified);
sw.WriteLine("In-Program excluded: {0}", inProgramConfidentlyIdentified.Count);
sw.WriteLine("Real confidently identified: {0}", realConfidentIdentified.Count);
sw.WriteLine("Intersection: {0}", intersection.Count);
sw.Close();
}
public void finalizePerformanceEvaluator(String experimentName, String experimentType, double analysisTime,
double totalRunTime, ExclusionList exclusionList, ProteinProphetResult ppr, int ddaNum, ExclusionProfile exclusionProfile)
{
setExperimentName(experimentName, experimentType);
setExperimentDuration(analysisTime, totalRunTime);
setExperimentParams();
setExclusionList(exclusionList);
postProcessingCalculations(ddaNum, ppr, exclusionProfile);
}
static String mzml = "C:\\Coding\\2019LavalleeLab\\RealTest_Results_20200219\\MSQC_QE_200ng_HEK_2hr_to_run_200219172225.mzML"; //"C:\\Coding\\2019LavalleeLab\\GoldStandardData\\MZML_Files\\MS_QC_120min.mzml";
public static void DoJob()
{
//comet
Console.WriteLine("Performing Comet search on full ms2 data");
String fullCometFile = PostProcessingScripts.CometStandardSearch(ms2File, InputFileOrganizer.OutputFolderOfTheRun, true);
InputFileOrganizer.OriginalCometOutput = fullCometFile;
//protein prophet
Console.WriteLine("Perform a protein prophet search on full pepxml");
String fullProteinProphetFile = PostProcessingScripts.ProteinProphetSearch(fullCometFile, InputFileOrganizer.OutputFolderOfTheRun, true);
InputFileOrganizer.OriginalProtXMLFile = fullProteinProphetFile;
ProteinProphetResult baseLinePpr = ProteinProphetEvaluator.getProteinProphetResult(InputFileOrganizer.OriginalProtXMLFile);
//load spectra
Console.WriteLine("loading spectra array");
List <Spectra> ls = Loader.parseMS2File(ms2File).getSpectraArray();
List <int> includedSpectra = new List <int>();
List <int> excludedSpectra = new List <int>();
StreamReader sr = new StreamReader(excludedSpectraFile);
String line = sr.ReadLine();
while (line != null)
{
int excluded = int.Parse(line);
excludedSpectra.Add(excluded);
line = sr.ReadLine();
}
foreach (Spectra sp in ls)
{
if (!excludedSpectra.Contains(sp.getScanNum()))
{
includedSpectra.Add(sp.getScanNum());
}
}
String outputCometFile = Path.Combine(InputFileOrganizer.OutputFolderOfTheRun, "realTestpartialOut.pep.xml"); //"C:\\Coding\\2019LavalleeLab\\GoldStandardData\\pepxml\\MS_QC_120min_partial.pep.xml";
String fastaFile = InputFileOrganizer.FASTA_FILE; //"C:\\Coding\\2019LavalleeLab\\GoldStandardData\\Database\\uniprot_SwissProt_Human_1_11_2017.fasta";
PartialPepXMLWriter.writePartialPepXMLFile(fullCometFile, includedSpectra,
outputCometFile, mzml, fastaFile, outputCometFile);
String partialProt = PostProcessingScripts.ProteinProphetSearch(outputCometFile, InputFileOrganizer.OutputFolderOfTheRun, true);
ProteinProphetResult partialPpr = ProteinProphetEvaluator.getProteinProphetResult(partialProt);
double partialNum = partialPpr.getNum_proteins_identified();
double totalNum = baseLinePpr.getNum_proteins_identified();
double idSens = partialNum / totalNum * 100.0;
double includedScanNum = includedSpectra.Count;
double totalScanNum = ls.Count;
double usedResource = includedScanNum / totalScanNum * 100;
String line1 = String.Format("includedScans {0} \t totalScanNum {1} \tUsedResources {2}", includedScanNum, totalScanNum, usedResource);
String line2 = String.Format("partialNum {0} \t totalNum {1} \tidsens {2}", partialNum, totalNum, idSens);
Console.WriteLine(line1);
Console.WriteLine(line2);
WriterClass.writeln(line1);
WriterClass.writeln(line2);
WriterClass.CloseWriter();
}
