public IcRescorer(string specFilePath, string icResultFilePath, string outputFilePath, AminoAcidSet aaSet, Tolerance tolerance, double ms2CorrThreshold = 0.7
, int minProductIonCharge = 1, int maxProductIonCharge = 10)
{
var run = InMemoryLcMsRun.GetLcMsRun(specFilePath, 1.4826, 1.4826);
_topDownScorer = new InformedTopDownScorer(run, aaSet, minProductIonCharge, maxProductIonCharge, tolerance, ms2CorrThreshold);
Rescore(icResultFilePath, outputFilePath);
}
public FeatureBasedTagSearchEngine(
LcMsRun run,
Ms1FtParser featureParser,
ProductScorerBasedOnDeconvolutedSpectra ms2Scorer,
SequenceTagParser tagParser,
FastaDatabase fastaDb,
Tolerance tolerance,
AminoAcidSet aaSet,
double maxSequenceMass = 50000.0,
int minProductIonCharge = 1,
int maxProductIonCharge = 20)
{
_run = run;
_ms2Scorer = ms2Scorer;
_featureParser = featureParser;
_ms1FtFilter = new Ms1FtFilter(run, tolerance, featureParser.Ms1FtFileName);
_tagParser = tagParser;
_fastaDb = fastaDb;
_searchableDb = new SearchableDatabase(fastaDb);
_tolerance = tolerance;
_aaSet = aaSet;
_maxSequenceMass = maxSequenceMass;
_minProductIonCharge = minProductIonCharge;
_maxProductIonCharge = maxProductIonCharge;
}
public SequenceTagIndexFinder(Tolerance tolerance, int minCharge, int maxCharge)
{
_tolerance = tolerance;
_minCharge = minCharge;
_maxCharge = maxCharge;
}
public new Xic GetFullProductExtractedIonChromatogram(double mz, Tolerance tolerance, double precursorIonMz)
{
var tolTh = tolerance.GetToleranceAsTh(mz);
var minMz = mz - tolTh;
var maxMz = mz + tolTh;
return GetFullProductExtractedIonChromatogram(minMz, maxMz, precursorIonMz);
}
public static Spectrum GetDeconvolutedSpectrum(Spectrum spec, int minCharge, int maxCharge, Tolerance tolerance, double corrThreshold,
int isotopeOffsetTolerance, double filteringWindowSize = 1.1)
{
var deconvolutedPeaks = Deconvoluter.GetDeconvolutedPeaks(spec, minCharge, maxCharge, isotopeOffsetTolerance, filteringWindowSize, tolerance, corrThreshold);
var peakList = new List<Peak>();
var binHash = new HashSet<int>();
foreach (var deconvolutedPeak in deconvolutedPeaks)
{
var mass = deconvolutedPeak.Mass;
var binNum = GetBinNumber(mass);
if (!binHash.Add(binNum)) continue;
peakList.Add(new Peak(mass, deconvolutedPeak.Intensity));
}
var productSpec = spec as ProductSpectrum;
if (productSpec != null)
{
return new ProductSpectrum(peakList, spec.ScanNum)
{
MsLevel = spec.MsLevel,
ActivationMethod = productSpec.ActivationMethod,
IsolationWindow = productSpec.IsolationWindow
};
}
return new Spectrum(peakList, spec.ScanNum);
}
/// <summary>
/// Gets the extracted ion chromatogram of the specified m/z (using only MS1 spectra)
/// </summary>
/// <param name="mz">target m/z</param>
/// <param name="tolerance">tolerance</param>
/// <returns>XIC as a list of XICPeaks</returns>
public IList<XicPeak> GetExtractedIonChromatogram(double mz, Tolerance tolerance)
{
var tolTh = tolerance.GetToleranceAsTh(mz);
var minMz = mz - tolTh;
var maxMz = mz + tolTh;
return GetExtractedIonChromatogram(minMz, maxMz);
}
public ScanBasedTagSearchEngine(
LcMsRun run,
ISequenceTagFinder seqTagFinder,
LcMsPeakMatrix featureFinder,
FastaDatabase fastaDb,
Tolerance tolerance,
AminoAcidSet aaSet,
CompositeScorerFactory ms2ScorerFactory = null,
int minMatchedTagLength = DefaultMinMatchedTagLength,
double maxSequenceMass = 50000.0,
int minProductIonCharge = 1,
int maxProductIonCharge = 20)
{
_run = run;
_featureFinder = featureFinder;
_searchableDb = new SearchableDatabase(fastaDb);
_tolerance = tolerance;
_aaSet = aaSet;
_minMatchedTagLength = minMatchedTagLength;
_maxSequenceMass = maxSequenceMass;
_minProductIonCharge = minProductIonCharge;
_maxProductIonCharge = maxProductIonCharge;
MinScan = int.MinValue;
MaxScan = int.MaxValue;
_ms2ScorerFactory = ms2ScorerFactory;
_seqTagFinder = seqTagFinder;
}
public Ms1FtFilter(LcMsRun run, Tolerance massTolerance, string ms1FtFileName, double minLikelihoodRatio = 0)
{
_lcMsChargeMap = new LcMsChargeMap(run, massTolerance);
_minLikelihoodRatio = minLikelihoodRatio;
Read(ms1FtFileName);
}
public IEnumerable<int> GetMatchingMs2ScanNums(double sequenceMass, Tolerance tolerance, LcMsRun run)
{
var massBinNum = GetBinNumber(sequenceMass);
IEnumerable<int> ms2ScanNums;
if (_sequenceMassBinToScanNumsMap.TryGetValue(massBinNum, out ms2ScanNums)) return ms2ScanNums;
return new int[0];
}
public static IList<Peak> FindAllPeaks(List<Peak> peakList, double mz, Tolerance tolerance)
{
var tolTh = tolerance.GetToleranceAsTh(mz);
var minMz = mz - tolTh;
var maxMz = mz + tolTh;
return FindAllPeaks(peakList, minMz, maxMz);
}
public IcTopDownLauncher(
string specFilePath,
string dbFilePath,
string outputDir,
AminoAcidSet aaSet,
string featureFilePath = null)
{
ErrorMessage = string.Empty;
SpecFilePath = specFilePath;
DatabaseFilePath = dbFilePath;
AminoAcidSet = aaSet;
OutputDir = outputDir;
FeatureFilePath = featureFilePath;
MinSequenceLength = 21;
MaxSequenceLength = 300;
MaxNumNTermCleavages = 1;
MaxNumCTermCleavages = 0;
MinPrecursorIonCharge = 2;
MaxPrecursorIonCharge = 60;
MinProductIonCharge = 1;
MaxProductIonCharge = 20;
MinSequenceMass = 2000.0;
MaxSequenceMass = 50000.0;
PrecursorIonTolerance = new Tolerance(10);
ProductIonTolerance = new Tolerance(10);
RunTargetDecoyAnalysis = DatabaseSearchMode.Both;
SearchMode = InternalCleavageType.SingleInternalCleavage;
MaxNumThreads = 4;
ScanNumbers = null;
NumMatchesPerSpectrum = 3;
TagBasedSearch = true;
}
public void TestFeatureAlignment()
{
const string outFilePath = @"\\protoapps\UserData\Jungkap\Lewy\aligned\promex_crosstab_temp.tsv";
//CPTAC_Intact_CR32A_24Aug15_Bane_15-02-06-RZ
var prsmReader = new ProteinSpectrumMatchReader();
var tolerance = new Tolerance(10);
var alignment = new LcMsFeatureAlignment(new AnalysisCompRef.CompRefFeatureComparer(tolerance));
for (var i = 0; i < NdataSet; i++)
{
var rawFile = string.Format(@"{0}\{1}.pbf", PbfPath, GetDataSetNames(i));
var mspFile = string.Format(@"{0}\{1}_IcTda.tsv", MsPfFolder, GetDataSetNames(i));
var mspFile2 = string.Format(@"{0}\{1}_IcTda.tsv", MsPfFolder2, GetDataSetNames(i));
var ms1FtFile = string.Format(@"{0}\{1}.ms1ft", Ms1FtFolder, GetDataSetNames(i));
Console.WriteLine(rawFile);
var run = PbfLcMsRun.GetLcMsRun(rawFile);
var prsmList1 = prsmReader.LoadIdentificationResult(mspFile, ProteinSpectrumMatch.SearchTool.MsPathFinder);
var prsmList2 = prsmReader.LoadIdentificationResult(mspFile2, ProteinSpectrumMatch.SearchTool.MsPathFinder);
prsmList1.AddRange(prsmList2);
var prsmList = MergePrsm(prsmList1);
var features = LcMsFeatureAlignment.LoadProMexResult(i, ms1FtFile, run);
for (var j = 0; j < prsmList.Count; j++)
{
var match = prsmList[j];
match.ProteinId = match.ProteinName;
}
// tag features by PrSMs
for (var j = 0; j < features.Count; j++)
{
//features[j].ProteinSpectrumMatches = new ProteinSpectrumMatchSet(i);
var massTol = tolerance.GetToleranceAsTh(features[j].Mass);
foreach (var match in prsmList)
{
if (features[j].MinScanNum < match.ScanNum && match.ScanNum < features[j].MaxScanNum && Math.Abs(features[j].Mass - match.Mass) < massTol)
{
features[j].ProteinSpectrumMatches.Add(match);
}
}
}
alignment.AddDataSet(i, features, run);
}
alignment.AlignFeatures();
Console.WriteLine("{0} alignments ", alignment.CountAlignedFeatures);
for (var i = 0; i < NdataSet; i++)
{
alignment.FillMissingFeatures(i);
Console.WriteLine("{0} has been processed", GetDataSetNames(i));
}
OutputCrossTabWithId(outFilePath, alignment);
}
public PrecursorOffsetFrequency(int reducedCharge, float offset, float frequency, Tolerance tolerance)
{
ReducedCharge = reducedCharge;
Offset = offset;
Frequency = frequency;
Tolerance = tolerance;
}
public List<List<MSDeconvNode>> GetClustersList(Tolerance tol, double elutionInterval,List<MSDeconvNode> nodeList)
{
var edgeDict = GetEdges(nodeList,tol,elutionInterval);
var connectedComponents = new List<List<MSDeconvNode>>();
var nodesInComponenets = new Dictionary<MSDeconvNode,int>();
for (int i = 0; i < nodeList.Count; i++)
{
if (!nodesInComponenets.ContainsKey(nodeList[i]))
{
connectedComponents.Add(GetConnectedComponenet(nodeList[i],edgeDict,nodesInComponenets));
}
}
/**foreach (var c in connectedComponents)
{
Console.WriteLine("Connected Componenet Elements:");
foreach (var n in c)
{
Console.WriteLine("{0} {1}", n.ScanNumber,n.RealMonoMass);
}
Console.WriteLine();
}*/
return connectedComponents;
}
public MatchedPeakPostScorer(Tolerance tolerance, int minCharge, int maxCharge)
{
_tolerance = tolerance;
_minCharge = minCharge;
_maxCharge = maxCharge;
_rankingInfo = new Dictionary<int, int[]>();
}
public ScoredSpectrum(Spectrum spec, RankScore scorer, int charge, double massWithH2O, Tolerance tolerance)
{
_rankedSpec = new RankedSpectrum(spec);
_scorer = scorer;
_charge = charge;
_sequenceMass = massWithH2O;
_tolerance = tolerance;
}
public MsDeconvFilter(LcMsRun run, Tolerance massTolerance, string msDeconvFileName)
{
_run = run;
_massTolerance = massTolerance;
_lcMsMatchMap = new LcMsMatchMap();
Read(msDeconvFileName);
}
public FitBasedLogLikelihoodRatioScorer(ProductSpectrum ms2Spec, Tolerance tolerance, int minCharge, int maxCharge)
{
_ms2Spec = ms2Spec;
_tolerance = tolerance;
_minCharge = minCharge;
_maxCharge = maxCharge;
_baseIonTypes = ms2Spec.ActivationMethod != ActivationMethod.ETD ? BaseIonTypesCID : BaseIonTypesETD;
}
/// <summary>
/// Finds the maximum intensity peak within the specified range
/// </summary>
/// <param name="mz">m/z</param>
/// <param name="tolerance">tolerance</param>
/// <returns>maximum intensity peak</returns>
public Peak FindPeak(double mz, Tolerance tolerance)
{
var tolTh = tolerance.GetToleranceAsTh(mz);
var minMz = mz - tolTh;
var maxMz = mz + tolTh;
return FindPeak(minMz, maxMz);
}
public static List<DeconvolutedPeak> GetDeconvolutedPeaks(
Spectrum spec, int minCharge, int maxCharge,
int isotopeOffsetTolerance, double filteringWindowSize,
Tolerance tolerance, double corrScoreThreshold)
{
return GetDeconvolutedPeaks(spec.Peaks, minCharge, maxCharge, isotopeOffsetTolerance, filteringWindowSize,
tolerance, corrScoreThreshold);
}
public FeatureSet GetFeatures(double mz, Tolerance tolerance, DataReader.FrameType frameType)
{
var intensityBlock = _uimfUtil.GetXic(mz, tolerance.GetValue(), frameType,
tolerance.GetUnit() == ToleranceUnit.Ppm ? DataReader.ToleranceType.PPM : DataReader.ToleranceType.Thomson);
var features = new FeatureSet(intensityBlock);
return features;
}
public IsotopeIntensityCorrelationScoreTrainerUsingMgfFile(List<MSMSSpectrum> spectra, Dictionary<GroupParameter, List<IonType>> ionTypes, Tolerance tolerance, int maxCharge)
{
_spectra = spectra;
_ionTypes = ionTypes;
_tolerance = tolerance;
_maxCharge = maxCharge;
IsotopeIntensityCorrProbDictionary = new Dictionary<GroupParameter, Dictionary<IonType, Dictionary<int, double>>>();
}
public IonTypeTrainerUsingMgfFile(List<MSMSSpectrum> spectra, Tolerance tolerance, int maxCharge)
{
_spectra = spectra;
_tolerance = tolerance;
_maxCharge = maxCharge;
_ionFrequencyFunction = new Dictionary<GroupParameter, Dictionary<IonType, double>>();
IonTypes = new Dictionary<GroupParameter, List<IonType>>();
}
public InformedTopDownScorer(LcMsRun run, AminoAcidSet aaSet, int minProductCharge, int maxProductCharge, Tolerance tolerance, double ms2CorrThreshold = 0.7)
{
Run = run;
AminoAcidSet = aaSet;
MinProductCharge = minProductCharge;
MaxProductCharge = maxProductCharge;
Tolerance = tolerance;
Ms2CorrThreshold = ms2CorrThreshold;
}
public MatchedTagSet(string sequence,
AminoAcidSet aminoAcidSet, Tolerance tolerance, Tolerance relaxedTolerance)
{
_sequence = sequence;
_aminoAcidSet = aminoAcidSet;
_tolerance = tolerance;
_relaxedTolerance = relaxedTolerance;
_tags = new List<MatchedTag>();
}
public IsosFilter(LcMsRun run, Tolerance massTolerance, string isosFileName, double fitScoreThreshold = 1.0)
{
_run = run;
_massTolerance = massTolerance;
_fitScoreThreshold = fitScoreThreshold;
_lcMsMatchMap = new LcMsMatchMap();
Read(isosFileName);
}
public void AddMostAbundantIsotopePeakIntensity()
{
var methodName = MethodBase.GetCurrentMethod().Name;
TestUtils.ShowStarting(methodName);
const string rawFilePath = @"\\proto-2\UnitTest_Files\InformedProteomics_TestFiles\TestYufengData\QC_ShewIntact_40K_LongSeparation_1_141016155143.raw";
if (!File.Exists(rawFilePath))
{
Assert.Ignore(@"Skipping test " + methodName + @" since file not found: " + rawFilePath);
}
var run = PbfLcMsRun.GetLcMsRun(rawFilePath);
const string resultFilePath = @"\\proto-2\UnitTest_Files\InformedProteomics_TestFiles\TestYufengData\QC_ShewIntact_40K_LongSeparation_1_141016155143_IcTda.tsv";
var parser = new TsvFileParser(resultFilePath);
var compositions = parser.GetData("Composition").Select(Composition.Parse).ToArray();
var scanNums = parser.GetData("Scan").Select(s => Convert.ToInt32(s)).ToArray();
var charges = parser.GetData("Charge").Select(s => Convert.ToInt32(s)).ToArray();
var precursorIntensities = new double[parser.NumData];
var tolerance = new Tolerance(10);
for (var i = 0; i < parser.NumData; i++)
{
var scanNum = scanNums[i];
var composition = compositions[i];
var charge = charges[i];
var precursorIon = new Ion(composition, charge);
var precursorScanNum = run.GetPrecursorScanNum(scanNum);
var precursorSpec = run.GetSpectrum(precursorScanNum);
var isotopePeaks = precursorSpec.GetAllIsotopePeaks(precursorIon, tolerance, 0.1);
if (isotopePeaks != null)
{
var maxIntensity = 0.0;
for (var j = 0; j < isotopePeaks.Length; j++)
{
if (isotopePeaks[j] != null && isotopePeaks[j].Intensity > maxIntensity)
maxIntensity = isotopePeaks[j].Intensity;
}
precursorIntensities[i] = maxIntensity;
}
}
// Writing
const string newResultFilePath = @"\\proto-2\UnitTest_Files\InformedProteomics_TestFiles\TestYufengData\QC_ShewIntact_40K_LongSeparation_1_141016155143_IcTdaWithIntensities.tsv";
using (var writer = new StreamWriter(newResultFilePath))
{
writer.WriteLine(string.Join("\t", parser.GetHeaders())+"\t"+"PrecursorIntensity");
for (var i = 0; i < parser.NumData; i++)
{
writer.WriteLine(parser.GetRows()[i]+"\t"+precursorIntensities[i]);
}
}
Console.WriteLine("Done");
}
public RatioScoreTrainerUsingMgfFile(List<MSMSSpectrum> spectra, Dictionary<GroupParameter, List<IonType>> ionTypes, Tolerance tolerance, int maxCharge)
{
_spectra = spectra;
_ionTypes = ionTypes;
_tolerance = tolerance;
_maxCharge = maxCharge;
RatioProbDictionary = new Dictionary<GroupParameter, Dictionary<Tuple<IonType, IonType>, Dictionary<int, double>>>();
NoIonProbDictionary = new Dictionary<GroupParameter, double>();
_allNumberDictionary = new Dictionary<GroupParameter, double>();
}
public InformedBottomUpScorer(LcMsRun run, AminoAcidSet aaSet, int minProductCharge, int maxProductCharge, Tolerance tolerance)
{
Run = run;
AminoAcidSet = aaSet;
MinProductCharge = minProductCharge;
MaxProductCharge = maxProductCharge;
Tolerance = tolerance;
_rankScorer = new RankScore(ActivationMethod.HCD, Ms2DetectorType.Orbitrap, Enzyme.Trypsin, Protocol.Standard);
_scoredSpectra = new Dictionary<int, ScoredSpectrum>();
}
public static DeconvolutedSpectrum GetDeconvolutedSpectrum(
Spectrum spec, int minCharge, int maxCharge,
int isotopeOffsetTolerance, double filteringWindowSize,
Tolerance tolerance, double corrScoreThreshold = 0.7)
{
var peaks = GetDeconvolutedPeaks(spec.Peaks, minCharge, maxCharge, isotopeOffsetTolerance, filteringWindowSize,
tolerance, corrScoreThreshold);
return new DeconvolutedSpectrum(spec, peaks.ToArray());
}
