[WIP] Unit Tests for LFQ in MetaMorpheus

TaskLayer/SearchTask/PostSearchAnalysisTask.cs

@@ -254,22 +254,12 @@ private void QuantificationAnalysis()
             }
 
             // get PSMs to pass to FlashLFQ
-            List<PeptideSpectralMatch> unambiguousPsmsBelowOnePercentFdr = new();
-            if (Parameters.AllPsms.Count > 100)//PEP is not computed when there are fewer than 100 psms
-            {
-                unambiguousPsmsBelowOnePercentFdr = Parameters.AllPsms.Where(p =>
-                    p.FdrInfo.PEP_QValue <= 0.01
-                    && !p.IsDecoy
-                    && p.FullSequence != null).ToList(); //if ambiguous, there's no full sequence
-            }
-            else
-            {
-                unambiguousPsmsBelowOnePercentFdr = Parameters.AllPsms.Where(p =>
+            List<PeptideSpectralMatch> unambiguousPsmsBelowOnePercentFdr =  Parameters.AllPsms.Where(p =>
                     p.FdrInfo.QValue <= 0.01
+                    && p.FdrInfo.QValueNotch <= 0.01
                     && !p.IsDecoy
                     && p.FullSequence != null).ToList(); //if ambiguous, there's no full sequence
-            }
-
+
             // pass protein group info for each PSM
             var psmToProteinGroups = new Dictionary<PeptideSpectralMatch, List<FlashLFQ.ProteinGroup>>();
             if (ProteinGroups != null && ProteinGroups.Count != 0) //ProteinGroups can be null if parsimony wasn't done, and it can be empty if you're doing the two peptide rule
@@ -282,7 +272,10 @@ private void QuantificationAnalysis()
                         string.Join("|", proteinsOrderedByAccession.Select(p => p.GeneNames.Select(x => x.Item2).FirstOrDefault())),
                         string.Join("|", proteinsOrderedByAccession.Select(p => p.Organism).Distinct()));
 
-                    foreach (var psm in proteinGroup.AllPsmsBelowOnePercentFDR.Where(v => v.FullSequence != null))
+                    foreach (var psm in proteinGroup.AllPsmsBelowOnePercentFDR.Where(p=>p.FdrInfo.QValue <= 0.01
+                    && p.FdrInfo.QValueNotch <= 0.01
+                    && !p.IsDecoy
+                    && p.FullSequence != null))
                     {
                         if (psmToProteinGroups.TryGetValue(psm, out var flashLfqProteinGroups))
                         {

Test/LFQTestData/ExperimentalDesign.tsv

@@ -0,0 +1,3 @@
+FileName	Condition	Biorep	Fraction	Techrep
+20100614_Velos1_TaGe_SA_K562_3.mzML	one	1	1	1
+20100614_Velos1_TaGe_SA_K562_4.mzML	two	1	1	1

Test/LFQTestData/Task1-SearchTaskconfig.toml

@@ -0,0 +1,95 @@
+TaskType = "Search"
+
+[SearchParameters]
+DisposeOfFileWhenDone = true
+DoParsimony = true
+ModPeptidesAreDifferent = false
+NoOneHitWonders = false
+MatchBetweenRuns = true
+Normalize = false
+QuantifyPpmTol = 5.0
+DoHistogramAnalysis = false
+SearchTarget = true
+DecoyType = "Reverse"
+MassDiffAcceptorType = "OneMM"
+WritePrunedDatabase = false
+KeepAllUniprotMods = true
+DoLocalizationAnalysis = true
+DoQuantification = true
+DoMbrAnalysis = true
+SearchType = "Classic"
+LocalFdrCategories = ["FullySpecific"]
+MaxFragmentSize = 30000.0
+MinAllowedInternalFragmentLength = 0
+HistogramBinTolInDaltons = 0.003
+MaximumMassThatFragmentIonScoreIsDoubled = 0.0
+WriteMzId = false
+WritePepXml = false
+WriteDecoys = false
+WriteContaminants = true
+WriteIndividualFiles = true
+WriteSpectralLibrary = false
+UpdateSpectralLibrary = false
+CompressIndividualFiles = false
+TCAmbiguity = "RemoveContaminant"
+IncludeModMotifInMzid = false
+
+[SearchParameters.ModsToWriteSelection]
+'N-linked glycosylation' = 3
+'O-linked glycosylation' = 3
+'Other glycosylation' = 3
+'Common Biological' = 3
+'Less Common' = 3
+Metal = 3
+'2+ nucleotide substitution' = 3
+'1 nucleotide substitution' = 3
+UniProt = 2
+
+[CommonParameters]
+TaskDescriptor = "SearchTask"
+MaxThreadsToUsePerFile = 7
+ListOfModsFixed = "Common Fixed\tCarbamidomethyl on C\t\tCommon Fixed\tCarbamidomethyl on U"
+ListOfModsVariable = "Common Variable\tOxidation on M"
+DoPrecursorDeconvolution = true
+UseProvidedPrecursorInfo = true
+DeconvolutionIntensityRatio = 3.0
+DeconvolutionMaxAssumedChargeState = 12
+DeconvolutionMassTolerance = "±4.0000 PPM"
+TotalPartitions = 1
+ProductMassTolerance = "±20.0000 PPM"
+PrecursorMassTolerance = "±5.0000 PPM"
+AddCompIons = false
+ScoreCutoff = 5.0
+ReportAllAmbiguity = true
+NumberOfPeaksToKeepPerWindow = 200
+MinimumAllowedIntensityRatioToBasePeak = 0.01
+NormalizePeaksAccrossAllWindows = false
+TrimMs1Peaks = false
+TrimMsMsPeaks = true
+UseDeltaScore = false
+QValueOutputFilter = 1.0
+PepQValueOutputFilter = 1.0
+CustomIons = []
+AssumeOrphanPeaksAreZ1Fragments = true
+MaxHeterozygousVariants = 4
+MinVariantDepth = 1
+AddTruncations = false
+DissociationType = "HCD"
+SeparationType = "HPLC"
+MS2ChildScanDissociationType = "Unknown"
+MS3ChildScanDissociationType = "Unknown"
+
+[CommonParameters.DigestionParams]
+MaxMissedCleavages = 2
+InitiatorMethionineBehavior = "Variable"
+MinPeptideLength = 7
+MaxPeptideLength = 2147483647
+MaxModificationIsoforms = 1024
+MaxModsForPeptide = 2
+Protease = "trypsin"
+SearchModeType = "Full"
+FragmentationTerminus = "Both"
+SpecificProtease = "trypsin"
+GeneratehUnlabeledProteinsForSilac = true
+KeepNGlycopeptide = false
+KeepOGlycopeptide = false