public void CalibrateHitsAndComponents(RegressionForestModel bestCf)
{
foreach (SpectrumMatch hit in all_topdown_hits)
{
hit.mz = hit.mz - bestCf.Predict(new double[] { hit.mz, hit.ms1_scan.RetentionTime, Math.Log(hit.ms1_scan.TotalIonCurrent), hit.ms1_scan.InjectionTime.HasValue ? Math.Log(hit.ms1_scan.InjectionTime.Value) : double.NaN });
}
foreach (Component c in Sweet.lollipop.calibration_components.Where(h => h.input_file.lt_condition == raw_file.lt_condition && h.input_file.biological_replicate == raw_file.biological_replicate && h.input_file.fraction == raw_file.fraction && h.input_file.technical_replicate == raw_file.technical_replicate))
{
foreach (ChargeState cs in c.charge_states)
{
int scanNumber = myMsDataFile.GetClosestOneBasedSpectrumNumber(c.rt_apex);
var scan = myMsDataFile.GetOneBasedScan(scanNumber);
bool ms1Scan = scan.MsnOrder == 1;
while (!ms1Scan)
{
scanNumber--;
scan = myMsDataFile.GetOneBasedScan(scanNumber);
ms1Scan = scan.MsnOrder == 1;
}
cs.mz_centroid = cs.mz_centroid - bestCf.Predict(new double[] { cs.mz_centroid, scan.RetentionTime, Math.Log(scan.TotalIonCurrent), scan.InjectionTime.HasValue ? Math.Log(scan.InjectionTime.Value) : double.NaN });
}
}
foreach (var a in myMsDataFile.GetAllScansList().Where(s => s.MsnOrder == 1))
{
Func <MzPeak, double> theFunc = x => x.Mz - bestCf.Predict(new double[] { x.Mz, a.RetentionTime, Math.Log(a.TotalIonCurrent), a.InjectionTime.HasValue ? Math.Log(a.InjectionTime.Value) : double.NaN });
a.MassSpectrum.ReplaceXbyApplyingFunction(theFunc);
}
}
private void CalibrateSpectra(IPredictorModel <double> ms1predictor, IPredictorModel <double> ms2predictor)
{
Parallel.ForEach(Partitioner.Create(1, MyMsDataFile.NumSpectra + 1), new ParallelOptions {
MaxDegreeOfParallelism = commonParameters.MaxThreadsToUsePerFile
}, (fff, loopState) =>
{
for (int i = fff.Item1; i < fff.Item2; i++)
{
// Stop loop if canceled
if (GlobalVariables.StopLoops)
{
loopState.Stop();
return;
}
var scan = MyMsDataFile.GetOneBasedScan(i);
if (scan.MsnOrder == 2)
{
var precursorScan = MyMsDataFile.GetOneBasedScan(scan.OneBasedPrecursorScanNumber.Value);
if (!scan.SelectedIonMonoisotopicGuessIntensity.HasValue && scan.SelectedIonMonoisotopicGuessMz.HasValue)
{
scan.ComputeMonoisotopicPeakIntensity(precursorScan.MassSpectrum);
}
double theFunc(MzPeak x) => x.Mz - ms2predictor.Predict(new double[] { x.Mz, scan.RetentionTime, Math.Log(scan.TotalIonCurrent), scan.InjectionTime.HasValue ? Math.Log(scan.InjectionTime.Value) : double.NaN, Math.Log(x.Intensity) });
double theFuncForPrecursor(MzPeak x) => x.Mz - ms1predictor.Predict(new double[] { x.Mz, precursorScan.RetentionTime, Math.Log(precursorScan.TotalIonCurrent), precursorScan.InjectionTime.HasValue ? Math.Log(precursorScan.InjectionTime.Value) : double.NaN, Math.Log(x.Intensity) });
scan.TransformMzs(theFunc, theFuncForPrecursor);
}
else
{
Func <MzPeak, double> theFunc = x => x.Mz - ms1predictor.Predict(new double[] { x.Mz, scan.RetentionTime, Math.Log(scan.TotalIonCurrent), scan.InjectionTime.HasValue ? Math.Log(scan.InjectionTime.Value) : double.NaN, Math.Log(x.Intensity) });
scan.MassSpectrum.ReplaceXbyApplyingFunction(theFunc);
}
}
}
);
}
private void DrawPsm(int oneBasedScanNumber, string fullSequence = null)
{
MsDataScan msDataScanToDraw = MsDataFile.GetOneBasedScan(oneBasedScanNumber);
IEnumerable <MetaDrawPsm> scanPsms = peptideSpectralMatches.Where(p => p.ScanNum == oneBasedScanNumber);
if (fullSequence != null)
{
scanPsms = scanPsms.Where(p => p.FullSequence == fullSequence);
}
MetaDrawPsm psmToDraw = scanPsms.FirstOrDefault();
// draw annotated spectrum
mainViewModel.DrawPeptideSpectralMatch(msDataScanToDraw, psmToDraw);
// draw annotated base sequence
DrawAnnotatedBaseSequence(psmToDraw);
}
protected override MetaMorpheusEngineResults RunSpecific()
{
// don't try to localize mass differences for ambiguous peptides
foreach (PeptideSpectralMatch psm in AllResultingIdentifications.Where(b => b.FullSequence != null))
{
// Stop loop if canceled
if (GlobalVariables.StopLoops)
{
break;
}
MsDataScan scan = MyMsDataFile.GetOneBasedScan(psm.ScanNumber);
Ms2ScanWithSpecificMass scanWithSpecificMass = new Ms2ScanWithSpecificMass(scan, psm.ScanPrecursorMonoisotopicPeakMz, psm.ScanPrecursorCharge, psm.FullFilePath, CommonParameters);
PeptideWithSetModifications peptide = psm.BestMatchingPeptides.First().Peptide;
double massDifference = psm.ScanPrecursorMass - peptide.MonoisotopicMass;
// this section will iterate through all residues of the peptide and try to localize the mass-diff at each residue and report a score for each residue
var localizedScores = new List <double>();
for (int r = 0; r < peptide.Length; r++)
{
// create new PeptideWithSetMods with unidentified mass difference at the given residue
PeptideWithSetModifications peptideWithLocalizedMassDiff = peptide.Localize(r, massDifference);
// this is the list of theoretical products for this peptide with mass-difference on this residue
List <Product> productsWithLocalizedMassDiff = peptideWithLocalizedMassDiff.Fragment(CommonParameters.DissociationType, CommonParameters.DigestionParams.FragmentationTerminus).ToList();
var matchedIons = MatchFragmentIons(scanWithSpecificMass, productsWithLocalizedMassDiff, CommonParameters);
// score when the mass-diff is on this residue
double localizedScore = CalculatePeptideScore(scan, matchedIons);
localizedScores.Add(localizedScore);
}
psm.LocalizedScores = localizedScores;
}
return(new LocalizationEngineResults(this));
}
protected override MetaMorpheusEngineResults RunSpecific()
{
TerminusType terminusType = ProductTypeMethods.IdentifyTerminusType(ProductTypes);
foreach (PeptideSpectralMatch psm in AllResultingIdentifications)
{
// Stop loop if canceled
if (GlobalVariables.StopLoops)
{
break;
}
psm.MatchedIonSeriesDict = new Dictionary <ProductType, int[]>();
psm.MatchedIonMassToChargeRatioDict = new Dictionary <ProductType, double[]>();
psm.ProductMassErrorDa = new Dictionary <ProductType, double[]>();
psm.ProductMassErrorPpm = new Dictionary <ProductType, double[]>();
psm.MatchedIonIntensitiesDict = new Dictionary <ProductType, double[]>();
var theScan = MyMsDataFile.GetOneBasedScan(psm.ScanNumber);
double thePrecursorMass = psm.ScanPrecursorMass;
foreach (ProductType productType in ProductTypes)
{
var sortedTheoreticalProductMasses = psm.CompactPeptides.First().Key.ProductMassesMightHaveDuplicatesAndNaNs(new List <ProductType> {
productType
});
Array.Sort(sortedTheoreticalProductMasses);
List <int> matchedIonSeriesList = new List <int>();
List <double> matchedIonMassToChargeRatioList = new List <double>();
List <double> productMassErrorDaList = new List <double>();
List <double> productMassErrorPpmList = new List <double>();
List <double> matchedIonIntensityList = new List <double>();
//populate the above lists
MatchIonsOld(theScan, commonParameters.ProductMassTolerance, sortedTheoreticalProductMasses, matchedIonSeriesList, matchedIonMassToChargeRatioList, productMassErrorDaList, productMassErrorPpmList, matchedIonIntensityList, thePrecursorMass, productType, commonParameters.AddCompIons);
psm.MatchedIonSeriesDict.Add(productType, matchedIonSeriesList.ToArray());
psm.MatchedIonMassToChargeRatioDict.Add(productType, matchedIonMassToChargeRatioList.ToArray());
psm.ProductMassErrorDa.Add(productType, productMassErrorDaList.ToArray());
psm.ProductMassErrorPpm.Add(productType, productMassErrorPpmList.ToArray());
psm.MatchedIonIntensitiesDict.Add(productType, matchedIonIntensityList.ToArray());
}
}
foreach (PeptideSpectralMatch psm in AllResultingIdentifications.Where(b => b.NumDifferentCompactPeptides == 1))
{
// Stop loop if canceled
if (GlobalVariables.StopLoops)
{
break;
}
var theScan = MyMsDataFile.GetOneBasedScan(psm.ScanNumber);
double thePrecursorMass = psm.ScanPrecursorMass;
if (psm.FullSequence == null)
{
continue;
}
PeptideWithSetModifications representative = psm.CompactPeptides.First().Value.Item2.First();
var localizedScores = new List <double>();
for (int indexToLocalize = 0; indexToLocalize < representative.Length; indexToLocalize++)
{
PeptideWithSetModifications localizedPeptide = representative.Localize(indexToLocalize, psm.ScanPrecursorMass - representative.MonoisotopicMass);
var gg = localizedPeptide.CompactPeptide(terminusType).ProductMassesMightHaveDuplicatesAndNaNs(ProductTypes);
Array.Sort(gg);
var score = CalculatePeptideScoreOld(theScan, commonParameters.ProductMassTolerance, gg, thePrecursorMass, DissociationTypes, commonParameters.AddCompIons, 0);
localizedScores.Add(score);
}
psm.LocalizedScores = localizedScores;
}
return(new LocalizationEngineResults(this));
}
private void DrawPsm(int oneBasedScanNumber, string fullSequence = null, string fileName = null)
{
MsDataScan msDataScanToDraw = MsDataFile.GetOneBasedScan(oneBasedScanNumber);
IEnumerable <PsmFromTsv> scanPsms = filteredListOfPsms.Where(p => p.Ms2ScanNumber == oneBasedScanNumber);
if (fullSequence != null)
{
scanPsms = scanPsms.Where(p => p.FullSequence == fullSequence);
}
PsmFromTsv psmToDraw = scanPsms.FirstOrDefault();
// if this spectrum has child scans, draw them in the "advanced" tab
if ((psmToDraw.ChildScanMatchedIons != null && psmToDraw.ChildScanMatchedIons.Count > 0) ||
(psmToDraw.BetaPeptideChildScanMatchedIons != null && psmToDraw.BetaPeptideChildScanMatchedIons.Count > 0))
{
ParentChildScanView.Visibility = Visibility.Visible;
ParentScanView.Visibility = Visibility.Visible;
// draw parent scans
var parentPsmModel = new PsmAnnotationViewModel();
MsDataScan parentScan = MsDataFile.GetOneBasedScan(psmToDraw.Ms2ScanNumber);
parentPsmModel.DrawPeptideSpectralMatch(parentScan, psmToDraw, metaDrawGraphicalSettings.ShowMzValues,
metaDrawGraphicalSettings.ShowAnnotationCharges, metaDrawGraphicalSettings.AnnotatedFontSize, metaDrawGraphicalSettings.BoldText);
string parentAnnotation = "Scan: " + parentScan.OneBasedScanNumber.ToString()
+ " Dissociation Type: " + parentScan.DissociationType.ToString()
+ " MsOrder: " + parentScan.MsnOrder.ToString()
+ " Selected Mz: " + parentScan.SelectedIonMZ.Value.ToString("0.##")
+ " Retention Time: " + parentScan.RetentionTime.ToString("0.##");
itemsControlSampleViewModel.AddNewRow(parentPsmModel, parentAnnotation, null);
// draw child scans
HashSet <int> scansDrawn = new HashSet <int>();
var allChildScanMatchedIons = psmToDraw.ChildScanMatchedIons;
if (psmToDraw.BetaPeptideChildScanMatchedIons != null)
{
allChildScanMatchedIons = allChildScanMatchedIons.Concat(psmToDraw.BetaPeptideChildScanMatchedIons).ToDictionary(p => p.Key, q => q.Value);
}
foreach (var childScanMatchedIons in allChildScanMatchedIons)
{
int scanNumber = childScanMatchedIons.Key;
if (scansDrawn.Contains(scanNumber))
{
continue;
}
scansDrawn.Add(scanNumber);
List <MatchedFragmentIon> matchedIons = childScanMatchedIons.Value;
var childPsmModel = new PsmAnnotationViewModel();
MsDataScan childScan = MsDataFile.GetOneBasedScan(scanNumber);
childPsmModel.DrawPeptideSpectralMatch(childScan, psmToDraw, metaDrawGraphicalSettings.ShowMzValues,
metaDrawGraphicalSettings.ShowAnnotationCharges, metaDrawGraphicalSettings.AnnotatedFontSize, metaDrawGraphicalSettings.BoldText);
string childAnnotation = "Scan: " + scanNumber.ToString()
+ " Dissociation Type: " + childScan.DissociationType.ToString()
+ " MsOrder: " + childScan.MsnOrder.ToString()
+ " Selected Mz: " + childScan.SelectedIonMZ.Value.ToString("0.##")
+ " RetentionTime: " + childScan.RetentionTime.ToString("0.##");
Canvas aCanvas = new Canvas {
Height = 60
};
DrawAnnotatedBaseSequence(aCanvas, psmToDraw, true);
itemsControlSampleViewModel.AddNewRow(childPsmModel, childAnnotation, aCanvas);
}
}
else
{
ParentChildScanView.Visibility = Visibility.Collapsed;
ParentScanView.Visibility = Visibility.Collapsed;
}
// if this is a crosslink spectrum match, there are two base sequence annotations to draw
// this makes the canvas taller to fit both of these peptide sequences
if (psmToDraw.BetaPeptideBaseSequence != null)
{
int height = 150;
canvas.Height = height;
PsmAnnotationGrid.RowDefinitions[1].Height = new GridLength(height);
}
else
{
int height = 60;
canvas.Height = height;
PsmAnnotationGrid.RowDefinitions[1].Height = new GridLength(height);
}
// draw annotated spectrum
mainViewModel.DrawPeptideSpectralMatch(msDataScanToDraw, psmToDraw, metaDrawGraphicalSettings.ShowMzValues,
metaDrawGraphicalSettings.ShowAnnotationCharges, metaDrawGraphicalSettings.AnnotatedFontSize, metaDrawGraphicalSettings.BoldText);
// draw annotated base sequence
DrawAnnotatedBaseSequence(canvas, psmToDraw);
}
protected override MetaMorpheusEngineResults RunSpecific()
{
Status("Extracting data points:");
// The final training point list
int numMs1MassChargeCombinationsConsidered = 0;
int numMs1MassChargeCombinationsThatAreIgnoredBecauseOfTooManyPeaks = 0;
int numMs2MassChargeCombinationsConsidered = 0;
int numMs2MassChargeCombinationsThatAreIgnoredBecauseOfTooManyPeaks = 0;
List <LabeledDataPoint> Ms1List = new List <LabeledDataPoint>();
List <LabeledDataPoint> Ms2List = new List <LabeledDataPoint>();
object lockObj = new object();
object lockObj2 = new object();
int maxThreadsPerFile = CommonParameters.MaxThreadsToUsePerFile;
int[] threads = Enumerable.Range(0, maxThreadsPerFile).ToArray();
Parallel.ForEach(threads, (matchIndex) =>
{
for (; matchIndex < GoodIdentifications.Count; matchIndex += maxThreadsPerFile)
{
// Stop loop if canceled
if (GlobalVariables.StopLoops)
{
return;
}
PeptideSpectralMatch identification = GoodIdentifications[matchIndex];
// Each identification has an MS2 spectrum attached to it.
int ms2scanNumber = identification.ScanNumber;
int peptideCharge = identification.ScanPrecursorCharge;
if (identification.FullSequence == null || identification.BestMatchingPeptides.Any(p => p.Peptide.AllModsOneIsNterminus.Any(m => m.Value.ChemicalFormula == null)))
{
continue;
}
var representativeSinglePeptide = identification.BestMatchingPeptides.First().Peptide;
// Get the peptide, don't forget to add the modifications!!!!
var SequenceWithChemicalFormulas = representativeSinglePeptide.SequenceWithChemicalFormulas;
if (SequenceWithChemicalFormulas == null || representativeSinglePeptide.AllModsOneIsNterminus.Any(b => b.Value.NeutralLosses != null))
{
continue;
}
Peptide coolPeptide = new Peptide(SequenceWithChemicalFormulas);
var ms2tuple = SearchMS2Spectrum(MyMsDataFile.GetOneBasedScan(ms2scanNumber), identification);
lock (lockObj2)
{
Ms2List.AddRange(ms2tuple);
}
// Calculate isotopic distribution of the full peptide
var dist = IsotopicDistribution.GetDistribution(coolPeptide.GetChemicalFormula(), FineResolutionForIsotopeDistCalculation, 0.001);
double[] theoreticalMasses = dist.Masses.ToArray();
double[] theoreticalIntensities = dist.Intensities.ToArray();
Array.Sort(theoreticalIntensities, theoreticalMasses, Comparer <double> .Create((x, y) => y.CompareTo(x)));
var ms1tupleBack = SearchMS1Spectra(theoreticalMasses, theoreticalIntensities, ms2scanNumber, -1, peptideCharge, identification);
var ms1tupleForward = SearchMS1Spectra(theoreticalMasses, theoreticalIntensities, ms2scanNumber, 1, peptideCharge, identification);
lock (lockObj)
{
Ms1List.AddRange(ms1tupleBack.Item1);
numMs1MassChargeCombinationsConsidered += ms1tupleBack.Item2;
numMs1MassChargeCombinationsThatAreIgnoredBecauseOfTooManyPeaks += ms1tupleBack.Item3;
Ms1List.AddRange(ms1tupleForward.Item1);
numMs1MassChargeCombinationsConsidered += ms1tupleForward.Item2;
numMs1MassChargeCombinationsThatAreIgnoredBecauseOfTooManyPeaks += ms1tupleForward.Item3;
}
}
});
// datapoints are ordered because they were acquired in a parallized search and we want repeatable results
return(new DataPointAquisitionResults(this,
GoodIdentifications,
Ms1List.OrderBy(p => p.ScanNumber).ThenBy(p => p.ExperimentalMz).ToList(),
Ms2List.OrderBy(p => p.ScanNumber).ThenBy(p => p.ExperimentalMz).ToList(),
numMs1MassChargeCombinationsConsidered,
numMs1MassChargeCombinationsThatAreIgnoredBecauseOfTooManyPeaks,
numMs2MassChargeCombinationsConsidered,
numMs2MassChargeCombinationsThatAreIgnoredBecauseOfTooManyPeaks
));
}
protected override MetaMorpheusEngineResults RunSpecific()
{
// don't try to localize mass differences for ambiguous peptides
PeptideSpectralMatch[] unambiguousPsms = AllResultingIdentifications.Where(b => b.FullSequence != null).ToArray();
double psmsSearched = 0;
int oldPercentProgress = 0;
ReportProgress(new ProgressEventArgs(oldPercentProgress, "Localizing mass-differences... ", NestedIds));
Parallel.ForEach(Partitioner.Create(0, unambiguousPsms.Length),
new ParallelOptions {
MaxDegreeOfParallelism = CommonParameters.MaxThreadsToUsePerFile
},
(range, loopState) =>
{
for (int i = range.Item1; i < range.Item2; i++)
{
PeptideSpectralMatch psm = unambiguousPsms[i];
// Stop loop if canceled
if (GlobalVariables.StopLoops)
{
break;
}
MsDataScan scan = MyMsDataFile.GetOneBasedScan(psm.ScanNumber);
Ms2ScanWithSpecificMass scanWithSpecificMass = new Ms2ScanWithSpecificMass(scan, psm.ScanPrecursorMonoisotopicPeakMz, psm.ScanPrecursorCharge, psm.FullFilePath, CommonParameters);
PeptideWithSetModifications peptide = psm.BestMatchingPeptides.First().Peptide;
double massDifference = psm.ScanPrecursorMass - peptide.MonoisotopicMass;
// this section will iterate through all residues of the peptide and try to localize the mass-diff at each residue and report a score for each residue
var localizedScores = new List <double>();
for (int r = 0; r < peptide.Length; r++)
{
// create new PeptideWithSetMods with unidentified mass difference at the given residue
PeptideWithSetModifications peptideWithLocalizedMassDiff = peptide.Localize(r, massDifference);
// this is the list of theoretical products for this peptide with mass-difference on this residue
List <Product> productsWithLocalizedMassDiff = peptideWithLocalizedMassDiff.Fragment(CommonParameters.DissociationType, CommonParameters.DigestionParams.FragmentationTerminus).ToList();
var matchedIons = MatchFragmentIons(scanWithSpecificMass, productsWithLocalizedMassDiff, CommonParameters);
// score when the mass-diff is on this residue
double localizedScore = CalculatePeptideScore(scan, matchedIons);
localizedScores.Add(localizedScore);
}
psm.LocalizedScores = localizedScores;
// report search progress (PSM mass differences localized so far out of total)
psmsSearched++;
var percentProgress = (int)((psmsSearched / unambiguousPsms.Length) * 100);
if (percentProgress > oldPercentProgress)
{
oldPercentProgress = percentProgress;
ReportProgress(new ProgressEventArgs(percentProgress, "Localizing mass-differences... ", NestedIds));
}
}
});
return(new LocalizationEngineResults(this));
}