public static void FilterForConfidentlyIdentifiedProteinOnly()
{
List <String> ppr = ProteinProphetEvaluator.extractIdentifiedProteinNames(InputFileOrganizer.OriginalProtXMLFile);
String excludedSpectraPerProteinAll = Path.Combine("ProteinTotalSpectraAgainstExcludedSpectra.txt");
String outputFile = Path.Combine(InputFileOrganizer.OutputFolderOfTheRun, "FilteredProteinWithExcludedSpectraCount.txt");
StreamReader sr = new StreamReader(excludedSpectraPerProteinAll);
StreamWriter sw = new StreamWriter(outputFile);
String line = sr.ReadLine();
sw.WriteLine(line);
line = sr.ReadLine();
int count = 0;
while (line != null)
{
String protName = line.Split("\t".ToCharArray())[0];
if (ppr.Contains(protName))
{
sw.WriteLine(line);
count++;
}
line = sr.ReadLine();
}
sw.Close();
Console.WriteLine(count);
}
public static void DoJob()
{
String originalProt = "C:\\Coding\\2019LavalleeLab\\GitProjectRealTimeMS\\TestData\\PreComputedFiles\\MS_QC_120min_interact.prot.xml";
var protGroups = ProteinProphetEvaluator.ExtractPositiveProteinGroups(originalProt);
Console.WriteLine(protGroups.Count);
}
private static void PostExperimentProcessing(Experiment e)
{
//WriterClass.writeln(exclusionProfile.ReportFailedCometSearchStatistics());
WriterClass.Flush();
if (GlobalVar.IsSimulation)
{
ProteinProphetResult ppr;
if (GlobalVar.isSimulationForFeatureExtraction)
{
ppr = ProteinProphetEvaluator.getProteinProphetResult(InputFileOrganizer.OriginalProtXMLFile);
}
else
{
String proteinProphetResultFileName = e.experimentNumber + GlobalVar.experimentName;
ppr = PostProcessingScripts.postProcessing(e.exclusionProfile, proteinProphetResultFileName, true);
}
e.totalRunTime = getCurrentTime() - e.experimentStartTime;
String result = e.exclusionProfile.getPerformanceVector(e.experimentName, e.exclusionProfile.getAnalysisType().getDescription()
, e.analysisTime, e.totalRunTime, ppr, 12, e.exclusionProfile);
Console.WriteLine(result);
Console.WriteLine("Protein groups: " + ppr.getFilteredProteinGroups().Count);
WriterClass.writeln(result);
//WriterClass.writeln("Protein groups: "+ ppr.getFilteredProteinGroups().Count) ;
e.ppr = ppr;
}
else
{
WriterClass.writeln(e.exclusionProfile.GetPerformanceEvaluator().outputPerformance());
}
}
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 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();
}
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();
}
private static void writeFeatures(List <IdentificationFeatures> idf)
{
log.Info("Classifying positive and negative sets");
// Extract which proteins were confidently identified at 0.01 FDR with protein prophet
List <String> identifiedProteins = ProteinProphetEvaluator.extractIdentifiedProteinNames(InputFileOrganizer.OriginalProtXMLFile);
// Extract which proteins were not confidently identified, with a specified FDR
// threshold
List <String> negativeTrainingSetProteins = ProteinProphetEvaluator.extractNegativeTrainingSetProteinNames(InputFileOrganizer.OriginalProtXMLFile, 0.25);
// 2019-05-23 FOUND IT! Here is where we filter the negative training set with
// above 20% FDR
// Proteins identified with a 0.01 FDR with protein prophet
List <IdentificationFeatures> positiveTrainingSet = new List <IdentificationFeatures>();
// Proteins not identified with a 0.01 FDR protein prophet
List <IdentificationFeatures> negativeTrainingSet = new List <IdentificationFeatures>();
List <IdentificationFeatures> nonPositiveTrainingSet = new List <IdentificationFeatures>();
// Determine which features are in positive or negative training set
foreach (IdentificationFeatures i in idf)
{
String accession = i.getAccession();
if (i.getCardinality() > 0)
{
if (!accession.StartsWith(GlobalVar.DecoyPrefix))
{
//if this is a real protein
if (identifiedProteins.Contains(accession))
{
positiveTrainingSet.Add(i);
}
else
{
nonPositiveTrainingSet.Add(i);
}
if (negativeTrainingSetProteins.Contains(accession))
{
negativeTrainingSet.Add(i);
}
}
else
{
//if it's a decoy protein
negativeTrainingSet.Add(i);
nonPositiveTrainingSet.Add(i);
}
}
}
WriteIdentificationFeaturesFile(OutputFile_PositiveAndNegative, positiveTrainingSet, negativeTrainingSet);
WriteIdentificationFeaturesFile(OutputFile_PositiveAndNonPositive, positiveTrainingSet, nonPositiveTrainingSet);
List <IdentificationFeatures> positiveSetNoDecoy = new List <IdentificationFeatures>();
List <IdentificationFeatures> nonPositiveSetNoDecoy = new List <IdentificationFeatures>();
foreach (IdentificationFeatures i in positiveTrainingSet)
{
if (!i.getAccession().Contains(GlobalVar.DecoyPrefix))
{
positiveSetNoDecoy.Add(i);
}
}
foreach (IdentificationFeatures i in nonPositiveTrainingSet)
{
if (!i.getAccession().Contains(GlobalVar.DecoyPrefix))
{
nonPositiveSetNoDecoy.Add(i);
}
}
WriteIdentificationFeaturesFile(OutputFile_PositiveAndNonPositive_NoDecoy, positiveSetNoDecoy, nonPositiveSetNoDecoy);
}
