Пример #1
0
        public static void TestSeparateIonsByTerminus()
        {
            List <ProductType> allIonTypes = new List <ProductType> {
                ProductType.B, ProductType.C, ProductType.Zdot, ProductType.Y
            };
            List <List <ProductType> > separated = ProductTypeMethods.SeparateIonsByTerminus(allIonTypes);

            Assert.IsTrue(separated.Count == 2);
            Assert.IsTrue(separated[0].Count == 2);
            Assert.IsTrue(separated[1].Count == 2);
            Assert.IsTrue(separated[0].Contains(ProductType.B));
            Assert.IsTrue(separated[0].Contains(ProductType.C));
            Assert.IsTrue(separated[1].Contains(ProductType.Y));
            Assert.IsTrue(separated[1].Contains(ProductType.Zdot));
            List <List <ProductType> > nOnly = ProductTypeMethods.SeparateIonsByTerminus(separated[0]);

            Assert.IsTrue(nOnly.Count == 1);
            Assert.IsTrue(nOnly[0].Count == 2);
            Assert.IsTrue(nOnly[0].Contains(ProductType.B));
            Assert.IsTrue(nOnly[0].Contains(ProductType.C));
            List <List <ProductType> > cOnly = ProductTypeMethods.SeparateIonsByTerminus(separated[1]);

            Assert.IsTrue(cOnly.Count == 1);
            Assert.IsTrue(cOnly[0].Count == 2);
            Assert.IsTrue(cOnly[0].Contains(ProductType.Y));
            Assert.IsTrue(cOnly[0].Contains(ProductType.Zdot));
        }
Пример #2
0
        public static void TestSeparateIonsByTerminus()
        {
            List <ProductType> allIonTypes = new List <ProductType> {
                ProductType.b, ProductType.c, ProductType.zPlusOne, ProductType.y
            };
            List <List <ProductType> > separated = ProductTypeMethods.SeparateIonsByTerminus(allIonTypes);

            Assert.IsTrue(separated.Count == 2);
            Assert.IsTrue(separated[0].Count == 2);
            Assert.IsTrue(separated[1].Count == 2);
            Assert.IsTrue(separated[0].Contains(ProductType.b));
            Assert.IsTrue(separated[0].Contains(ProductType.c));
            Assert.IsTrue(separated[1].Contains(ProductType.y));
            Assert.IsTrue(separated[1].Contains(ProductType.zPlusOne));
            List <List <ProductType> > nOnly = ProductTypeMethods.SeparateIonsByTerminus(separated[0]);

            Assert.IsTrue(nOnly.Count == 1);
            Assert.IsTrue(nOnly[0].Count == 2);
            Assert.IsTrue(nOnly[0].Contains(ProductType.b));
            Assert.IsTrue(nOnly[0].Contains(ProductType.c));
            List <List <ProductType> > cOnly = ProductTypeMethods.SeparateIonsByTerminus(separated[1]);

            Assert.IsTrue(cOnly.Count == 1);
            Assert.IsTrue(cOnly[0].Count == 2);
            Assert.IsTrue(cOnly[0].Contains(ProductType.y));
            Assert.IsTrue(cOnly[0].Contains(ProductType.zPlusOne));
        }
Пример #3
0
        protected override MyTaskResults RunSpecific(string OutputFolder, List <DbForTask> dbFilenameList, List <string> currentRawFileList, string taskId, FileSpecificParameters[] fileSettingsList)
        {
            // disable quantification if a .mgf is being used
            if (SearchParameters.DoQuantification && currentRawFileList.Any(x => Path.GetExtension(x).Equals(".mgf", StringComparison.OrdinalIgnoreCase)))
            {
                SearchParameters.DoQuantification = false;
            }

            // load modifications
            Status("Loading modifications...", taskId);
            List <ModificationWithMass> variableModifications = GlobalVariables.AllModsKnown.OfType <ModificationWithMass>().Where(b => CommonParameters.ListOfModsVariable.Contains((b.modificationType, b.id))).ToList();
            List <ModificationWithMass> fixedModifications    = GlobalVariables.AllModsKnown.OfType <ModificationWithMass>().Where(b => CommonParameters.ListOfModsFixed.Contains((b.modificationType, b.id))).ToList();
            List <string> localizeableModificationTypes       = GlobalVariables.AllModTypesKnown.ToList();

            // what types of fragment ions to search for
            List <ProductType> ionTypes = new List <ProductType>();

            if (CommonParameters.BIons && CommonParameters.AddCompIons)
            {
                ionTypes.Add(ProductType.B);
            }
            else if (CommonParameters.BIons)
            {
                ionTypes.Add(ProductType.BnoB1ions);
            }
            if (CommonParameters.YIons)
            {
                ionTypes.Add(ProductType.Y);
            }
            if (CommonParameters.ZdotIons)
            {
                ionTypes.Add(ProductType.Zdot);
            }
            if (CommonParameters.CIons)
            {
                ionTypes.Add(ProductType.C);
            }

            // load proteins
            List <Protein> proteinList = LoadProteins(taskId, dbFilenameList, SearchParameters.SearchTarget, SearchParameters.DecoyType, localizeableModificationTypes, CommonParameters);

            // write prose settings
            ProseCreatedWhileRunning.Append("The following search settings were used: ");
            ProseCreatedWhileRunning.Append("protease = " + CommonParameters.DigestionParams.Protease + "; ");
            ProseCreatedWhileRunning.Append("maximum missed cleavages = " + CommonParameters.DigestionParams.MaxMissedCleavages + "; ");
            ProseCreatedWhileRunning.Append("minimum peptide length = " + CommonParameters.DigestionParams.MinPeptideLength + "; ");
            ProseCreatedWhileRunning.Append(CommonParameters.DigestionParams.MaxPeptideLength == int.MaxValue ?
                                            "maximum peptide length = unspecified; " :
                                            "maximum peptide length = " + CommonParameters.DigestionParams.MaxPeptideLength + "; ");
            ProseCreatedWhileRunning.Append("initiator methionine behavior = " + CommonParameters.DigestionParams.InitiatorMethionineBehavior + "; ");
            ProseCreatedWhileRunning.Append("fixed modifications = " + string.Join(", ", fixedModifications.Select(m => m.id)) + "; ");
            ProseCreatedWhileRunning.Append("variable modifications = " + string.Join(", ", variableModifications.Select(m => m.id)) + "; ");
            ProseCreatedWhileRunning.Append("max mods per peptide = " + CommonParameters.DigestionParams.MaxModsForPeptide + "; ");
            ProseCreatedWhileRunning.Append("max modification isoforms = " + CommonParameters.DigestionParams.MaxModificationIsoforms + "; ");
            ProseCreatedWhileRunning.Append("precursor mass tolerance = " + CommonParameters.PrecursorMassTolerance + "; ");
            ProseCreatedWhileRunning.Append("product mass tolerance = " + CommonParameters.ProductMassTolerance + "; ");
            ProseCreatedWhileRunning.Append("report PSM ambiguity = " + CommonParameters.ReportAllAmbiguity + ". ");
            ProseCreatedWhileRunning.Append("The combined search database contained " + proteinList.Count(p => !p.IsDecoy) + " non-decoy protein entries including " + proteinList.Count(p => p.IsContaminant) + " contaminant sequences. ");

            // start the search task
            MyTaskResults = new MyTaskResults(this);
            List <PeptideSpectralMatch> allPsms         = new List <PeptideSpectralMatch>();
            FlashLFQResults             flashLfqResults = null;

            MyFileManager myFileManager = new MyFileManager(SearchParameters.DisposeOfFileWhenDone);

            var fileSpecificCommonParams = fileSettingsList.Select(b => SetAllFileSpecificCommonParams(CommonParameters, b));
            HashSet <DigestionParams> ListOfDigestionParams = new HashSet <DigestionParams>(fileSpecificCommonParams.Select(p => p.DigestionParams));

            int    completedFiles = 0;
            object indexLock      = new object();
            object psmLock        = new object();

            Status("Searching files...", taskId);
            Status("Searching files...", new List <string> {
                taskId, "Individual Spectra Files"
            });

            Dictionary <string, int[]> numMs2SpectraPerFile = new Dictionary <string, int[]>();

            for (int spectraFileIndex = 0; spectraFileIndex < currentRawFileList.Count; spectraFileIndex++)
            {
                if (GlobalVariables.StopLoops)
                {
                    break;
                }

                var origDataFile = currentRawFileList[spectraFileIndex];

                // mark the file as in-progress
                StartingDataFile(origDataFile, new List <string> {
                    taskId, "Individual Spectra Files", origDataFile
                });

                CommonParameters combinedParams = SetAllFileSpecificCommonParams(CommonParameters, fileSettingsList[spectraFileIndex]);

                MassDiffAcceptor massDiffAcceptor = GetMassDiffAcceptor(combinedParams.PrecursorMassTolerance, SearchParameters.MassDiffAcceptorType, SearchParameters.CustomMdac);

                var thisId = new List <string> {
                    taskId, "Individual Spectra Files", origDataFile
                };
                NewCollection(Path.GetFileName(origDataFile), thisId);
                Status("Loading spectra file...", thisId);
                MsDataFile myMsDataFile = myFileManager.LoadFile(origDataFile, combinedParams.TopNpeaks, combinedParams.MinRatio, combinedParams.TrimMs1Peaks, combinedParams.TrimMsMsPeaks, combinedParams);
                Status("Getting ms2 scans...", thisId);
                Ms2ScanWithSpecificMass[] arrayOfMs2ScansSortedByMass = GetMs2Scans(myMsDataFile, origDataFile, combinedParams.DoPrecursorDeconvolution, combinedParams.UseProvidedPrecursorInfo, combinedParams.DeconvolutionIntensityRatio, combinedParams.DeconvolutionMaxAssumedChargeState, combinedParams.DeconvolutionMassTolerance).OrderBy(b => b.PrecursorMass).ToArray();
                numMs2SpectraPerFile.Add(Path.GetFileNameWithoutExtension(origDataFile), new int[] { myMsDataFile.GetAllScansList().Count(p => p.MsnOrder == 2), arrayOfMs2ScansSortedByMass.Length });
                myFileManager.DoneWithFile(origDataFile);

                var fileSpecificPsms = new PeptideSpectralMatch[arrayOfMs2ScansSortedByMass.Length];
                // modern search
                if (SearchParameters.SearchType == SearchType.Modern)
                {
                    for (int currentPartition = 0; currentPartition < combinedParams.TotalPartitions; currentPartition++)
                    {
                        List <CompactPeptide> peptideIndex      = null;
                        List <Protein>        proteinListSubset = proteinList.GetRange(currentPartition * proteinList.Count() / combinedParams.TotalPartitions, ((currentPartition + 1) * proteinList.Count() / combinedParams.TotalPartitions) - (currentPartition * proteinList.Count() / combinedParams.TotalPartitions));

                        Status("Getting fragment dictionary...", new List <string> {
                            taskId
                        });
                        var indexEngine = new IndexingEngine(proteinListSubset, variableModifications, fixedModifications, ionTypes, currentPartition, SearchParameters.DecoyType, ListOfDigestionParams, combinedParams, SearchParameters.MaxFragmentSize, new List <string> {
                            taskId
                        });
                        List <int>[] fragmentIndex = null;
                        lock (indexLock)
                        {
                            GenerateIndexes(indexEngine, dbFilenameList, ref peptideIndex, ref fragmentIndex, taskId);
                        }

                        Status("Searching files...", taskId);

                        new ModernSearchEngine(fileSpecificPsms, arrayOfMs2ScansSortedByMass, peptideIndex, fragmentIndex, ionTypes, currentPartition, combinedParams, massDiffAcceptor, SearchParameters.MaximumMassThatFragmentIonScoreIsDoubled, thisId).Run();

                        ReportProgress(new ProgressEventArgs(100, "Done with search " + (currentPartition + 1) + "/" + combinedParams.TotalPartitions + "!", thisId));
                    }
                }
                // nonspecific search
                else if (SearchParameters.SearchType == SearchType.NonSpecific)
                {
                    List <List <ProductType> > terminusSeparatedIons = ProductTypeMethods.SeparateIonsByTerminus(ionTypes);
                    foreach (List <ProductType> terminusSpecificIons in terminusSeparatedIons)
                    {
                        for (int currentPartition = 0; currentPartition < combinedParams.TotalPartitions; currentPartition++)
                        {
                            List <CompactPeptide> peptideIndex      = null;
                            List <Protein>        proteinListSubset = proteinList.GetRange(currentPartition * proteinList.Count() / combinedParams.TotalPartitions, ((currentPartition + 1) * proteinList.Count() / combinedParams.TotalPartitions) - (currentPartition * proteinList.Count() / combinedParams.TotalPartitions));

                            List <int>[] fragmentIndex = new List <int> [1];

                            Status("Getting fragment dictionary...", new List <string> {
                                taskId
                            });
                            var indexEngine = new IndexingEngine(proteinListSubset, variableModifications, fixedModifications, terminusSpecificIons, currentPartition, SearchParameters.DecoyType, ListOfDigestionParams, combinedParams, SearchParameters.MaxFragmentSize, new List <string> {
                                taskId
                            });
                            lock (indexLock)
                                GenerateIndexes(indexEngine, dbFilenameList, ref peptideIndex, ref fragmentIndex, taskId);

                            Status("Getting precursor dictionary...", new List <string> {
                                taskId
                            });
                            List <CompactPeptide> peptideIndexPrecursor      = null;
                            List <Protein>        proteinListSubsetPrecursor = proteinList.GetRange(currentPartition * proteinList.Count() / combinedParams.TotalPartitions, ((currentPartition + 1) * proteinList.Count() / combinedParams.TotalPartitions) - (currentPartition * proteinList.Count() / combinedParams.TotalPartitions));
                            List <int>[]          fragmentIndexPrecursor     = new List <int> [1];
                            var indexEnginePrecursor = new PrecursorIndexingEngine(proteinListSubsetPrecursor, variableModifications, fixedModifications, terminusSpecificIons, currentPartition, SearchParameters.DecoyType, ListOfDigestionParams, combinedParams, 0, new List <string> {
                                taskId
                            });
                            lock (indexLock)
                                GenerateIndexes(indexEnginePrecursor, dbFilenameList, ref peptideIndexPrecursor, ref fragmentIndexPrecursor, taskId);

                            if (peptideIndex.Count != peptideIndexPrecursor.Count)
                            {
                                throw new MetaMorpheusException("peptideIndex not identical between indexing engines");
                            }

                            Status("Searching files...", taskId);

                            new NonSpecificEnzymeSearchEngine(fileSpecificPsms, arrayOfMs2ScansSortedByMass, peptideIndex, fragmentIndex, fragmentIndexPrecursor, terminusSpecificIons, currentPartition, combinedParams, massDiffAcceptor, SearchParameters.MaximumMassThatFragmentIonScoreIsDoubled, thisId).Run();

                            ReportProgress(new ProgressEventArgs(100, "Done with search " + (currentPartition + 1) + "/" + combinedParams.TotalPartitions + "!", thisId));
                        }
                    }
                }
                // classic search
                else
                {
                    Status("Starting search...", thisId);
                    new ClassicSearchEngine(fileSpecificPsms, arrayOfMs2ScansSortedByMass, variableModifications, fixedModifications, proteinList, ionTypes, massDiffAcceptor, combinedParams, thisId).Run();

                    ReportProgress(new ProgressEventArgs(100, "Done with search!", thisId));
                }
                lock (psmLock)
                {
                    allPsms.AddRange(fileSpecificPsms.Where(p => p != null));
                }

                completedFiles++;
                FinishedDataFile(origDataFile, new List <string> {
                    taskId, "Individual Spectra Files", origDataFile
                });
                ReportProgress(new ProgressEventArgs(completedFiles / currentRawFileList.Count, "Searching...", new List <string> {
                    taskId, "Individual Spectra Files"
                }));
            }

            ReportProgress(new ProgressEventArgs(100, "Done with all searches!", new List <string> {
                taskId, "Individual Spectra Files"
            }));

            PostSearchAnalysisParameters parameters = new PostSearchAnalysisParameters();

            parameters.SearchTaskResults             = MyTaskResults;
            parameters.SearchTaskId                  = taskId;
            parameters.SearchParameters              = SearchParameters;
            parameters.ProteinList                   = proteinList;
            parameters.IonTypes                      = ionTypes;
            parameters.AllPsms                       = allPsms;
            parameters.FixedModifications            = fixedModifications;
            parameters.VariableModifications         = variableModifications;
            parameters.ListOfDigestionParams         = ListOfDigestionParams;
            parameters.CurrentRawFileList            = currentRawFileList;
            parameters.MyFileManager                 = myFileManager;
            parameters.NumNotches                    = GetNumNotches(SearchParameters.MassDiffAcceptorType, SearchParameters.CustomMdac);
            parameters.OutputFolder                  = OutputFolder;
            parameters.IndividualResultsOutputFolder = Path.Combine(OutputFolder, "Individual File Results");
            parameters.FlashLfqResults               = flashLfqResults;
            parameters.FileSettingsList              = fileSettingsList;
            parameters.NumMs2SpectraPerFile          = numMs2SpectraPerFile;
            parameters.DatabaseFilenameList          = dbFilenameList;
            PostSearchAnalysisTask postProcessing = new PostSearchAnalysisTask();

            postProcessing.Parameters       = parameters;
            postProcessing.CommonParameters = CommonParameters;
            return(postProcessing.Run());
        }