Revert "PrSM output for top-down (#2062)" (#2079)

This reverts commit 97335a4.

EngineLayer/GlobalVariables.cs

@@ -32,13 +32,7 @@ public static class GlobalVariables
         private static char[] _InvalidAminoAcids;
 
         // this affects output labels, etc. and can be changed to "Proteoform" for top-down searches
-        public static Analyte AnalyteType;
-
-        public enum Analyte
-        {
-            Peptide,
-            Proteoform
-        }
+        public static string AnalyteType;
 
         public static List<string> ErrorsReadingMods;
 
@@ -69,7 +63,7 @@ public static void SetUpGlobalVariables()
             Loaders.LoadElements();
             AcceptedDatabaseFormats = new List<string> { ".fasta", ".fa", ".xml", ".msp" };
             AcceptedSpectraFormats = new List<string> { ".raw", ".mzml", ".mgf" };
-            AnalyteType = Analyte.Peptide;
+            AnalyteType = "Peptide";
             _InvalidAminoAcids = new char[] { 'X', 'B', 'J', 'Z', ':', '|', ';', '[', ']', '{', '}', '(', ')', '+', '-' };
             ExperimentalDesignFileName = "ExperimentalDesign.tsv";
             SeparationTypes = new List<string> { { "HPLC" }, { "CZE" } };

EngineLayer/MetaMorpheusEngine.cs

@@ -216,4 +216,4 @@ private void FinishedSingleEngine(MetaMorpheusEngineResults myResults)
             FinishedSingleEngineHandler?.Invoke(this, new SingleEngineFinishedEventArgs(myResults));
         }
     }
-}
+}

GUI/TaskWindows/GPTMDTaskWindow.xaml.cs

@@ -240,7 +240,7 @@ private void CancelButton_Click(object sender, RoutedEventArgs e)
             DialogResult = false;
             CustomFragmentationWindow.Close();
         }
-
+        
         private void ProteaseSpecificUpdate(object sender, SelectionChangedEventArgs e)
         {
             string proteaseName = ((Protease)ProteaseComboBox.SelectedItem).Name;
@@ -456,7 +456,7 @@ private void SaveButton_Click(object sender, RoutedEventArgs e)
                     dissociationType: dissociationType,
                     scoreCutoff: double.Parse(MinScoreAllowed.Text, CultureInfo.InvariantCulture),
                     precursorMassTolerance: precursorMassTolerance,
-                    productMassTolerance: productMassTolerance,
+                    productMassTolerance: productMassTolerance,                    
                     trimMs1Peaks: TrimMs1Peaks,
                     trimMsMsPeaks: TrimMsMsPeaks,
                     numberOfPeaksToKeepPerWindow: numPeaksToKeep,

TaskLayer/MetaMorpheusTask.cs

@@ -946,11 +946,11 @@ public static void DetermineAnalyteType(CommonParameters commonParameters)
                 && commonParameters.DigestionParams.Protease != null
                 && commonParameters.DigestionParams.Protease.Name == "top-down")
             {
-                GlobalVariables.AnalyteType = GlobalVariables.Analyte.Proteoform;
+                GlobalVariables.AnalyteType = "Proteoform";
             }
             else
             {
-                GlobalVariables.AnalyteType = GlobalVariables.Analyte.Peptide;
+                GlobalVariables.AnalyteType = "Peptide";
             }
         }
 

TaskLayer/SearchTask/PostSearchAnalysisTask.cs

@@ -128,11 +128,11 @@ private void ProteinAnalysis()
             List<PeptideSpectralMatch> psmsForProteinParsimony = Parameters.AllPsms;
 
             // run parsimony
-            ProteinParsimonyResults proteinAnalysisResults = (ProteinParsimonyResults)(new ProteinParsimonyEngine(psmsForProteinParsimony, Parameters.SearchParameters.ModPeptidesAreDifferent, CommonParameters, FileSpecificParameters, new List<string> { Parameters.SearchTaskId }).Run());
+            ProteinParsimonyResults proteinAnalysisResults = (ProteinParsimonyResults)(new ProteinParsimonyEngine(psmsForProteinParsimony, Parameters.SearchParameters.ModPeptidesAreDifferent, CommonParameters, this.FileSpecificParameters, new List<string> { Parameters.SearchTaskId }).Run());
 
             // score protein groups and calculate FDR
             ProteinScoringAndFdrResults proteinScoringAndFdrResults = (ProteinScoringAndFdrResults)new ProteinScoringAndFdrEngine(proteinAnalysisResults.ProteinGroups, psmsForProteinParsimony,
-                Parameters.SearchParameters.NoOneHitWonders, Parameters.SearchParameters.ModPeptidesAreDifferent, true, CommonParameters, FileSpecificParameters, new List<string> { Parameters.SearchTaskId }).Run();
+                Parameters.SearchParameters.NoOneHitWonders, Parameters.SearchParameters.ModPeptidesAreDifferent, true, CommonParameters, this.FileSpecificParameters, new List<string> { Parameters.SearchTaskId }).Run();
 
             ProteinGroups = proteinScoringAndFdrResults.SortedAndScoredProteinGroups;
 
@@ -516,10 +516,7 @@ private void HistogramAnalysis()
 
         private void WritePsmResults()
         {
-            //if doing proteoform analysis, then output is proteoform-spectrum match (PrSM) instead of peptide-spectrum match (PSM)
-            string analyteString = GlobalVariables.AnalyteType == GlobalVariables.Analyte.Proteoform ? "PrSM" : "PSM";
-
-            Status("Writing " + analyteString + " results...", Parameters.SearchTaskId);
+            Status("Writing PSM results...", Parameters.SearchTaskId);
             var FilteredPsmListForOutput = Parameters.AllPsms
                 .Where(p => p.FdrInfo.QValue <= CommonParameters.QValueOutputFilter
                 && p.FdrInfo.QValueNotch <= CommonParameters.QValueOutputFilter).ToList();
@@ -534,18 +531,18 @@ private void WritePsmResults()
             }
 
             // write PSMs
-            string writtenFile = Path.Combine(Parameters.OutputFolder, "All" + analyteString + "s.psmtsv");
+            string writtenFile = Path.Combine(Parameters.OutputFolder, "AllPSMs.psmtsv");
             WritePsmsToTsv(FilteredPsmListForOutput, writtenFile, Parameters.SearchParameters.ModsToWriteSelection);
             FinishedWritingFile(writtenFile, new List<string> { Parameters.SearchTaskId });
 
             // write PSMs for percolator
             // percolator native read format is .tab
-            writtenFile = Path.Combine(Parameters.OutputFolder, "All" + analyteString + "s_FormattedForPercolator.tab");
+            writtenFile = Path.Combine(Parameters.OutputFolder, "AllPSMs_FormattedForPercolator.tab");
             WritePsmsForPercolator(FilteredPsmListForOutput, writtenFile);
             FinishedWritingFile(writtenFile, new List<string> { Parameters.SearchTaskId });
 
             // write summary text
-            Parameters.SearchTaskResults.AddPsmPeptideProteinSummaryText("All target " + analyteString + "s within 1% FDR: " + Parameters.AllPsms.Count(a => a.FdrInfo.QValue <= 0.01 && !a.IsDecoy) + Environment.NewLine);
+            Parameters.SearchTaskResults.AddPsmPeptideProteinSummaryText("All target PSMS within 1% FDR: " + Parameters.AllPsms.Count(a => a.FdrInfo.QValue <= 0.01 && !a.IsDecoy) + Environment.NewLine);
             if (Parameters.SearchParameters.DoParsimony)
             {
                 Parameters.SearchTaskResults.AddTaskSummaryText("All target protein groups within 1% FDR: " + ProteinGroups.Count(b => b.QValue <= 0.01 && !b.IsDecoy)
@@ -562,7 +559,7 @@ private void WritePsmResults()
 
                 Parameters.SearchTaskResults.AddTaskSummaryText("MS2 spectra in " + strippedFileName + ": " + Parameters.NumMs2SpectraPerFile[strippedFileName][0]);
                 Parameters.SearchTaskResults.AddTaskSummaryText("Precursors fragmented in " + strippedFileName + ": " + Parameters.NumMs2SpectraPerFile[strippedFileName][1]);
-                Parameters.SearchTaskResults.AddTaskSummaryText("Target " + analyteString + "s within 1% FDR in " + strippedFileName + ": " + psmsForThisFile.Count(a => a.FdrInfo.QValue <= 0.01 && !a.IsDecoy));
+                Parameters.SearchTaskResults.AddTaskSummaryText("Target PSMs within 1% FDR in " + strippedFileName + ": " + psmsForThisFile.Count(a => a.FdrInfo.QValue <= 0.01 && !a.IsDecoy));
 
                 // writes all individual spectra file search results to subdirectory
                 if (Parameters.CurrentRawFileList.Count > 1 && Parameters.SearchParameters.WriteIndividualFiles)
@@ -571,12 +568,12 @@ private void WritePsmResults()
                     Directory.CreateDirectory(Parameters.IndividualResultsOutputFolder);
 
                     // write PSMs
-                    writtenFile = Path.Combine(Parameters.IndividualResultsOutputFolder, strippedFileName + "_" + analyteString + "s.psmtsv");
+                    writtenFile = Path.Combine(Parameters.IndividualResultsOutputFolder, strippedFileName + "_PSMs.psmtsv");
                     WritePsmsToTsv(psmsForThisFile, writtenFile, Parameters.SearchParameters.ModsToWriteSelection);
                     FinishedWritingFile(writtenFile, new List<string> { Parameters.SearchTaskId, "Individual Spectra Files", file.First().FullFilePath });
 
                     // write PSMs for percolator
-                    writtenFile = Path.Combine(Parameters.IndividualResultsOutputFolder, strippedFileName + "_" + analyteString + "sFormattedForPercolator.tab");
+                    writtenFile = Path.Combine(Parameters.IndividualResultsOutputFolder, strippedFileName + "_PSMsFormattedForPercolator.tab");
                     WritePsmsForPercolator(psmsForThisFile, writtenFile);
                     FinishedWritingFile(writtenFile, new List<string> { Parameters.SearchTaskId, "Individual Spectra Files", file.First().FullFilePath });
                 }
@@ -656,10 +653,10 @@ private void WriteProteinResults()
                         {
                             mzidFilePath = Path.Combine(Parameters.IndividualResultsOutputFolder, strippedFileName + ".mzID");
                         }
-                        MzIdentMLWriter.WriteMzIdentMl(psmsForThisFile.Where(p => p.FdrInfo.QValue <= CommonParameters.QValueOutputFilter),
+                        MzIdentMLWriter.WriteMzIdentMl(psmsForThisFile.Where(p => p.FdrInfo.QValue <= CommonParameters.QValueOutputFilter), 
                             subsetProteinGroupsForThisFile, Parameters.VariableModifications, Parameters.FixedModifications, Parameters.SearchParameters.SilacLabels,
                             new List<Protease> { CommonParameters.DigestionParams.Protease }, CommonParameters.QValueOutputFilter, CommonParameters.ProductMassTolerance,
-                            CommonParameters.PrecursorMassTolerance, CommonParameters.DigestionParams.MaxMissedCleavages, mzidFilePath,
+                            CommonParameters.PrecursorMassTolerance, CommonParameters.DigestionParams.MaxMissedCleavages, mzidFilePath, 
                             Parameters.SearchParameters.IncludeModMotifInMzid);
 
                         FinishedWritingFile(mzidFilePath, new List<string> { Parameters.SearchTaskId, "Individual Spectra Files", fullFilePath });
@@ -1005,16 +1002,16 @@ private void WritePeptideResults()
             WritePsmsToTsv(peptides, writtenFile, Parameters.SearchParameters.ModsToWriteSelection);
             FinishedWritingFile(writtenFile, new List<string> { Parameters.SearchTaskId });
 
-            Parameters.SearchTaskResults.AddPsmPeptideProteinSummaryText("All target " + GlobalVariables.AnalyteType.ToString().ToLower() + "s within 1% FDR: " + peptides.Count(a => a.FdrInfo.QValue <= 0.01 && !a.IsDecoy));
+            Parameters.SearchTaskResults.AddPsmPeptideProteinSummaryText("All target " + GlobalVariables.AnalyteType.ToLower() + "s within 1% FDR: " + peptides.Count(a => a.FdrInfo.QValue <= 0.01 && !a.IsDecoy));
 
             foreach (var file in PsmsGroupedByFile)
             {
                 // write summary text
                 var psmsForThisFile = file.ToList();
                 string strippedFileName = Path.GetFileNameWithoutExtension(file.First().FullFilePath);
                 var peptidesForFile = psmsForThisFile.GroupBy(b => b.FullSequence).Select(b => b.FirstOrDefault()).OrderByDescending(b => b.Score).ToList();
-                new FdrAnalysisEngine(peptidesForFile, Parameters.NumNotches, CommonParameters, FileSpecificParameters, new List<string> { Parameters.SearchTaskId }, "Peptide").Run();
-                Parameters.SearchTaskResults.AddTaskSummaryText("Target " + GlobalVariables.AnalyteType.ToString().ToLower() + "s within 1% FDR in " + strippedFileName + ": " + peptidesForFile.Count(a => a.FdrInfo.QValue <= 0.01 && !a.IsDecoy) + Environment.NewLine);
+                new FdrAnalysisEngine(peptidesForFile, Parameters.NumNotches, CommonParameters, this.FileSpecificParameters, new List<string> { Parameters.SearchTaskId }, "Peptide").Run();
+                Parameters.SearchTaskResults.AddTaskSummaryText("Target " + GlobalVariables.AnalyteType.ToLower() + "s within 1% FDR in " + strippedFileName + ": " + peptidesForFile.Count(a => a.FdrInfo.QValue <= 0.01 && !a.IsDecoy) + Environment.NewLine);
 
                 // writes all individual spectra file search results to subdirectory
                 if (Parameters.CurrentRawFileList.Count > 1 && Parameters.SearchParameters.WriteIndividualFiles)

Test/MyTaskTest.cs

@@ -274,7 +274,7 @@ public static void MakeSureFdrDoesntSkip()
 
             // RUN!
             var theStringResult = task.RunTask(outputFolder, new List<DbForTask> { new DbForTask(xmlName, false) }, new List<string> { mzmlName }, "taskId1").ToString();
-            Assert.IsTrue(theStringResult.Contains("All target PSMs within 1% FDR: 1"));
+            Assert.IsTrue(theStringResult.Contains("All target PSMS within 1% FDR: 1"));
             Directory.Delete(outputFolder, true);
             File.Delete(xmlName);
             File.Delete(mzmlName);

Test/SilacTest.cs

@@ -207,7 +207,7 @@ public static void TestSilacQuantification()
             Directory.CreateDirectory(outputFolder);
             var theStringResult = task.RunTask(outputFolder, new List<DbForTask> { new DbForTask(xmlName, false) }, new List<string> { mzmlName, mzmlName2 }, "taskId1").ToString();
 
-            Assert.IsTrue(theStringResult.Contains("All target PSMs within 1% FDR: 2")); //it's not a psm, it's a MBR feature. 2 because there are two files, but not 4 because MBR != psm
+            Assert.IsTrue(theStringResult.Contains("All target PSMS within 1% FDR: 2")); //it's not a psm, it's a MBR feature. 2 because there are two files, but not 4 because MBR != psm
 
             ///Normal Peptide
             //test proteins

Test/Test.csproj

@@ -277,12 +277,6 @@
     <None Update="TestVariantPep.mzML">
       <CopyToOutputDirectory>Always</CopyToOutputDirectory>
     </None>
-    <None Update="TopDownTestData\ProteoformAmbiguity.fasta">
-      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
-    </None>
-    <None Update="TopDownTestData\ProteoformAmbiguity.mzML">
-      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
-    </None>
     <None Update="TopDownTestData\slicedTDYeast.mzML">
       <CopyToOutputDirectory>Always</CopyToOutputDirectory>
     </None>

Test/TopDownTest.cs → Test/TestTopDown.cs

@@ -16,7 +16,7 @@
 namespace Test
 {
     [TestFixture]
-    public class TopDownTest
+    public class TestTopDown
     {
         [Test]
         public static void TestClassicSearchEngineTopDown()
@@ -29,7 +29,7 @@ public static void TestClassicSearchEngineTopDown()
             MetaMorpheusTask.DetermineAnalyteType(CommonParameters);
 
             // test output file name (should be proteoform and not peptide)
-            Assert.That(GlobalVariables.AnalyteType == GlobalVariables.Analyte.Proteoform);
+            Assert.That(GlobalVariables.AnalyteType == "Proteoform");
 
             var variableModifications = new List<Modification>();
             var fixedModifications = new List<Modification>();
@@ -47,63 +47,13 @@ public static void TestClassicSearchEngineTopDown()
             var listOfSortedms2Scans = MetaMorpheusTask.GetMs2Scans(myMsDataFile, null, new CommonParameters()).OrderBy(b => b.PrecursorMass).ToArray();
 
             PeptideSpectralMatch[] allPsmsArray = new PeptideSpectralMatch[listOfSortedms2Scans.Length];
-            new ClassicSearchEngine(allPsmsArray, listOfSortedms2Scans, variableModifications, fixedModifications, null, null, null,
+            new ClassicSearchEngine(allPsmsArray, listOfSortedms2Scans, variableModifications, fixedModifications, null, null, null, 
                 proteinList, searchMode, CommonParameters, null, null, new List<string>()).Run();
 
             var psm = allPsmsArray.Where(p => p != null).FirstOrDefault();
             Assert.That(psm.MatchedFragmentIons.Count == 47);
         }
 
-        /// <summary>
-        /// TODO: MetaMorpheus currently reports ambiguity at the PrSM level, but starts tossing things when we get to the proteoform/protein level. See issue #2061
-        /// Example 1: a base seqeunce is needed for parsimony, but an ambiguous sequence means the base sequence is null.
-        /// Example 2: a full sequence is needed for determining which peptides/proteoforms are unique, but ambiguous localization means the full sequence is null.
-        /// </summary>
-        [Test]
-        public static void TestAmbiguousProteoformOutput()
-        {
-            CommonParameters commonParameters = new CommonParameters(
-               digestionParams: new DigestionParams(protease: "top-down"),
-               scoreCutoff: 1,
-               useProvidedPrecursorInfo: false,
-               deconvolutionMaxAssumedChargeState: 60,
-               trimMsMsPeaks: false,
-               listOfModsVariable: new List<(string, string)> { ("Common Variable", "Oxidation on M"), ("Common Biological", "Acetylation on K"), ("Common Biological", "Trimethylation on K") },
-               listOfModsFixed: new List<(string, string)> { ("Common Fixed", "Carbamidomethyl on C") }
-                    );
-
-            SearchParameters searchParameters = new SearchParameters
-            {
-                DoQuantification = false
-            };
-
-
-            SearchTask searchTask = new SearchTask
-            {
-                CommonParameters = commonParameters,
-                SearchParameters = searchParameters
-            };
-
-            List<(string, MetaMorpheusTask)> taskList = new List<(string, MetaMorpheusTask)> { ("task1", searchTask) };
-            string outputFolder = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestProteoformAmbiguity");
-            string mzmlName = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TopDownTestData/ProteoformAmbiguity.mzML");
-            string fastaName = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TopDownTestData/ProteoformAmbiguity.fasta");
-            // RUN!
-            var engine = new EverythingRunnerEngine(taskList, new List<string> { mzmlName }, new List<DbForTask> { new DbForTask(fastaName, false) }, outputFolder);
-            engine.Run();
-
-            //There are 8 PrSMs, each with a unique proteoform and protein
-            //check that all 8 PrSMs are reported, all 8 unique proteoforms, and all 8 proteins
-            string[] prsmLines = File.ReadAllLines(Path.Combine(outputFolder, "task1/AllPrSMs.psmtsv"));
-            Assert.AreEqual(prsmLines.Length, 9); //8 + header
-            string[] proteoformLines = File.ReadAllLines(Path.Combine(outputFolder, "task1/AllProteoforms.psmtsv"));
-            Assert.AreEqual(proteoformLines.Length, 4); //3 + header, five of the PrSMs have ambiguous full sequences, which are needed to determine individuality
-            string[] proteinLines = File.ReadAllLines(Path.Combine(outputFolder, "task1/AllProteinGroups.tsv"));
-            Assert.AreEqual(proteinLines.Length, 7); //6 + header, two of the PrSMs have ambiguous base sequences, which prevents their use in parsimony
-
-            Directory.Delete(outputFolder, true);
-        }
-
         [Test]
         public static void TestModernSearchEngineTopDown()
         {
@@ -139,4 +89,4 @@ public static void TestModernSearchEngineTopDown()
             Assert.That(psm.MatchedFragmentIons.Count == 47);
         }
     }
-}
+}