public static void LoadThermoTest3()
{
ThermoStaticData a = ThermoStaticData.LoadAllStaticData(@"small.RAW");
Assert.IsTrue(a.GetAllScansList().Where(eb => eb.MsnOrder > 1).Count() > 0);
Assert.IsTrue(a.GetAllScansList().Where(eb => eb.MsnOrder == 1).Count() > 0);
Assert.IsFalse(a.ThermoGlobalParams.MonoisotopicselectionEnabled);
var hehe = a.GetAllScansList().First(b => b.MsnOrder > 1);
var prec = a.GetOneBasedScan(hehe.OneBasedPrecursorScanNumber.Value);
Assert.IsNull(hehe.SelectedIonChargeStateGuess);
Assert.IsNull(hehe.SelectedIonIntensity);
hehe.ComputeSelectedPeakIntensity(prec.MassSpectrum);
Assert.AreEqual(1017759, hehe.SelectedIonIntensity, 1);
Assert.IsNull(hehe.SelectedIonMonoisotopicGuessIntensity);
hehe.ComputeMonoisotopicPeakIntensity(prec.MassSpectrum);
Assert.AreEqual(1017759, hehe.SelectedIonMonoisotopicGuessIntensity, 1);
}
public static void WindowFilteringStaticTest()
{
//test window number of 1
ThermoStaticData a_w = ThermoStaticData.LoadAllStaticData(@"05-13-16_cali_MS_60K-res_MS.raw");
ThermoStaticData b_w = ThermoStaticData.LoadAllStaticData(@"05-13-16_cali_MS_60K-res_MS.raw", filterParams: new FilteringParams(numberOfPeaksToKeepPerWindow: 400, numberOfWindows: 1, applyTrimmingToMs1: true));
ThermoStaticData c_w = ThermoStaticData.LoadAllStaticData(@"05-13-16_cali_MS_60K-res_MS.raw", filterParams: new FilteringParams(minimumAllowedIntensityRatioToBasePeak: 0.001, numberOfWindows: 1, applyTrimmingToMs1: true));
ThermoStaticData d_w = ThermoStaticData.LoadAllStaticData(@"05-13-16_cali_MS_60K-res_MS.raw", filterParams: new FilteringParams(minimumAllowedIntensityRatioToBasePeak: 0.001, numberOfPeaksToKeepPerWindow: 400, numberOfWindows: 1, applyTrimmingToMs1: true));
var aLen = a_w.GetOneBasedScan(1).MassSpectrum.Size;
var bLen = b_w.GetOneBasedScan(1).MassSpectrum.Size;
var cLen = c_w.GetOneBasedScan(1).MassSpectrum.Size;
var dLen = d_w.GetOneBasedScan(1).MassSpectrum.Size;
Assert.AreEqual(Math.Min(bLen, cLen), dLen);
var aLen2 = a_w.GetOneBasedScan(2).MassSpectrum.Size;
var bLen2 = b_w.GetOneBasedScan(2).MassSpectrum.Size;
var cLen2 = c_w.GetOneBasedScan(2).MassSpectrum.Size;
var dLen2 = d_w.GetOneBasedScan(2).MassSpectrum.Size;
Assert.AreEqual(Math.Min(bLen2, cLen2), dLen2);
var aLen3 = a_w.GetOneBasedScan(3).MassSpectrum.Size;
var bLen3 = b_w.GetOneBasedScan(3).MassSpectrum.Size;
var cLen3 = c_w.GetOneBasedScan(3).MassSpectrum.Size;
var dLen3 = d_w.GetOneBasedScan(3).MassSpectrum.Size;
Assert.AreEqual(Math.Min(bLen3, cLen3), dLen3);
}
public static void LoadThermoFiltered2()
{
ThermoStaticData a = ThermoStaticData.LoadAllStaticData(@"small.raw");
ThermoStaticData b = ThermoStaticData.LoadAllStaticData(@"small.raw", filterParams: new FilteringParams(numberOfPeaksToKeepPerWindow: 40, applyTrimmingToMs1: true, applyTrimmingToMsMs: true));
ThermoStaticData c = ThermoStaticData.LoadAllStaticData(@"small.raw", filterParams: new FilteringParams(minimumAllowedIntensityRatioToBasePeak: 0.1, applyTrimmingToMs1: true, applyTrimmingToMsMs: true));
ThermoStaticData d = ThermoStaticData.LoadAllStaticData(@"small.raw", filterParams: new FilteringParams(minimumAllowedIntensityRatioToBasePeak: 0.1, numberOfPeaksToKeepPerWindow: 40, applyTrimmingToMs1: true, applyTrimmingToMsMs: true));
var aLen = a.GetOneBasedScan(1).MassSpectrum.Size;
var bLen = b.GetOneBasedScan(1).MassSpectrum.Size;
var cLen = c.GetOneBasedScan(1).MassSpectrum.Size;
var dLen = d.GetOneBasedScan(1).MassSpectrum.Size;
Assert.AreEqual(Math.Min(bLen, cLen), dLen);
var aLen2 = a.GetOneBasedScan(2).MassSpectrum.Size;
var bLen2 = b.GetOneBasedScan(2).MassSpectrum.Size;
var cLen2 = c.GetOneBasedScan(2).MassSpectrum.Size;
var dLen2 = d.GetOneBasedScan(2).MassSpectrum.Size;
Assert.AreEqual(Math.Min(bLen2, cLen2), dLen2);
var aLen3 = a.GetOneBasedScan(3).MassSpectrum.Size;
var bLen3 = b.GetOneBasedScan(3).MassSpectrum.Size;
var cLen3 = c.GetOneBasedScan(3).MassSpectrum.Size;
var dLen3 = d.GetOneBasedScan(3).MassSpectrum.Size;
Assert.AreEqual(Math.Min(bLen3, cLen3), dLen3);
}
internal IMsDataFile <IMsDataScan <IMzSpectrum <IMzPeak> > > LoadFile(string origDataFile, int?topNpeaks, double?minRatio, bool trimMs1Peaks, bool trimMsMsPeaks)
{
FilteringParams filter = new FilteringParams(topNpeaks, minRatio, null, trimMs1Peaks, trimMsMsPeaks);
if (myMsDataFiles.TryGetValue(origDataFile, out IMsDataFile <IMsDataScan <IMzSpectrum <IMzPeak> > > value) && value != null)
{
return(value);
}
// By now know that need to load this file!!!
lock (fileLoadingLock) // Lock because reading is sequential
if (Path.GetExtension(origDataFile).Equals(".mzML", StringComparison.OrdinalIgnoreCase))
{
myMsDataFiles[origDataFile] = Mzml.LoadAllStaticData(origDataFile, filter);
}
else
{
#if NETFRAMEWORK
myMsDataFiles[origDataFile] = ThermoStaticData.LoadAllStaticData(origDataFile, filter);
#else
Warn("No capability for reading " + origDataFile);
#endif
}
return(myMsDataFiles[origDataFile]);
}
public MsDataFile LoadFile(string origDataFile, int?topNpeaks, double?minRatio, bool trimMs1Peaks, bool trimMsMsPeaks, CommonParameters commonParameters)
{
FilteringParams filter = new FilteringParams(topNpeaks, minRatio, 1, trimMs1Peaks, trimMsMsPeaks);
if (MyMsDataFiles.TryGetValue(origDataFile, out MsDataFile value) && value != null)
{
return(value);
}
// By now know that need to load this file!!!
lock (FileLoadingLock) // Lock because reading is sequential
{
if (Path.GetExtension(origDataFile).Equals(".mzML", StringComparison.OrdinalIgnoreCase))
{
MyMsDataFiles[origDataFile] = Mzml.LoadAllStaticData(origDataFile, filter, commonParameters.MaxThreadsToUsePerFile);
}
else if (Path.GetExtension(origDataFile).Equals(".mgf", StringComparison.OrdinalIgnoreCase))
{
MyMsDataFiles[origDataFile] = Mgf.LoadAllStaticData(origDataFile, filter);
}
else
{
#if NETFRAMEWORK
MyMsDataFiles[origDataFile] = ThermoStaticData.LoadAllStaticData(origDataFile, filter);
#else
Warn("No capability for reading " + origDataFile);
#endif
}
return(MyMsDataFiles[origDataFile]);
}
}
public bool Run_TdMzCal(InputFile raw_file, List <TopDownHit> topdown_hits)
{
all_topdown_hits = topdown_hits.Where(h => h.score > 0).ToList();
//need to reset m/z in case same td hits used for multiple calibration raw files...
Parallel.ForEach(all_topdown_hits, h => h.mz = h.reported_mass.ToMz(h.charge));
high_scoring_topdown_hits = all_topdown_hits.Where(h => h.score >= 40).ToList();
this.raw_file = raw_file;
if (high_scoring_topdown_hits.Count < 5)
{
return(false);
}
myMsDataFile = Path.GetExtension(raw_file.complete_path) == ".raw" ?
ThermoStaticData.LoadAllStaticData(raw_file.complete_path) :
null;
if (myMsDataFile == null)
{
myMsDataFile = Mzml.LoadAllStaticData(raw_file.complete_path);
}
if (myMsDataFile == null)
{
return(false);
}
DataPointAquisitionResults dataPointAcquisitionResult = GetDataPoints();
if (dataPointAcquisitionResult.Ms1List.Count < 10)
{
return(false);
}
var myMs1DataPoints = new List <(double[] xValues, double yValue)>();
for (int i = 0; i < dataPointAcquisitionResult.Ms1List.Count; i++)
{
//x values
var explanatoryVariables = new double[4];
explanatoryVariables[0] = dataPointAcquisitionResult.Ms1List[i].mz;
explanatoryVariables[1] = dataPointAcquisitionResult.Ms1List[i].retentionTime;
explanatoryVariables[2] = dataPointAcquisitionResult.Ms1List[i].logTotalIonCurrent;
explanatoryVariables[3] = dataPointAcquisitionResult.Ms1List[i].logInjectionTime;
//yvalue
double mzError = dataPointAcquisitionResult.Ms1List[i].massError;
myMs1DataPoints.Add((explanatoryVariables, mzError));
}
var ms1Model = GetRandomForestModel(myMs1DataPoints);
CalibrateHitsAndComponents(ms1Model);
if (Sweet.lollipop.calibrate_raw_files)
{
MzmlMethods.CreateAndWriteMyMzmlWithCalibratedSpectra(myMsDataFile, raw_file.directory + "\\" + raw_file.filename + "_calibrated.mzML", false);
}
return(true);
}
public static void TestSummedMsDataFile()
{
ThermoStaticData rawFile = ThermoStaticData.LoadAllStaticData(@"05-13-16_cali_MS_60K-res_MS.raw");
// 3 scans
SummedMsDataFile summed3 = new SummedMsDataFile(rawFile, 3, 10);
Assert.AreEqual(rawFile.NumSpectra - 2, summed3.NumSpectra);
var resultingTic = summed3.GetOneBasedScan(1).TotalIonCurrent;
var mySummedTic = rawFile.GetOneBasedScan(1).MassSpectrum.SumOfAllY + rawFile.GetOneBasedScan(2).MassSpectrum.SumOfAllY + rawFile.GetOneBasedScan(3).MassSpectrum.SumOfAllY;
var instrumentSummedTic = rawFile.GetOneBasedScan(1).TotalIonCurrent + rawFile.GetOneBasedScan(2).TotalIonCurrent + rawFile.GetOneBasedScan(3).TotalIonCurrent;
// Tics are approximately what they should be
Assert.IsTrue(Math.Abs(resultingTic - mySummedTic) / mySummedTic < 1e-4);
Assert.IsTrue(Math.Abs(resultingTic - instrumentSummedTic) / instrumentSummedTic < 1e-1);
// Equal to representative
Assert.AreEqual(summed3.GetOneBasedScan(1).RetentionTime, rawFile.GetOneBasedScan(2).RetentionTime);
Assert.IsTrue(summed3.GetOneBasedScan(1).MassSpectrum.Size <= rawFile.GetOneBasedScan(1).MassSpectrum.Size + rawFile.GetOneBasedScan(2).MassSpectrum.Size + rawFile.GetOneBasedScan(3).MassSpectrum.Size);
Assert.IsTrue(summed3.GetOneBasedScan(1).MassSpectrum.Size >= rawFile.GetOneBasedScan(1).MassSpectrum.Size);
Assert.IsTrue(summed3.GetOneBasedScan(1).MassSpectrum.Size >= rawFile.GetOneBasedScan(2).MassSpectrum.Size);
Assert.IsTrue(summed3.GetOneBasedScan(1).MassSpectrum.Size >= rawFile.GetOneBasedScan(3).MassSpectrum.Size);
Assert.IsTrue(summed3.GetOneBasedScan(1).MassSpectrum.YofPeakWithHighestY == rawFile.GetOneBasedScan(1).MassSpectrum.YofPeakWithHighestY + rawFile.GetOneBasedScan(2).MassSpectrum.YofPeakWithHighestY + rawFile.GetOneBasedScan(3).MassSpectrum.YofPeakWithHighestY);
// Interval of 893-899 mz
Assert.AreEqual(2, rawFile.GetOneBasedScan(1).MassSpectrum.NumPeaksWithinRange(893, 899));
Assert.AreEqual(2, rawFile.GetOneBasedScan(2).MassSpectrum.NumPeaksWithinRange(893, 899));
Assert.AreEqual(1, rawFile.GetOneBasedScan(3).MassSpectrum.NumPeaksWithinRange(893, 899));
// One peak persists across the three scans! So instead of 5 see three peaks in summed
Assert.AreEqual(3, summed3.GetOneBasedScan(1).MassSpectrum.NumPeaksWithinRange(893, 899));
Assert.AreEqual(summed3.GetOneBasedScan(1).MassSpectrum.FirstX, Math.Min(Math.Min(rawFile.GetOneBasedScan(1).MassSpectrum.FirstX.Value, rawFile.GetOneBasedScan(2).MassSpectrum.FirstX.Value), rawFile.GetOneBasedScan(3).MassSpectrum.FirstX.Value));
Assert.AreEqual(summed3.GetOneBasedScan(1).MassSpectrum.LastX, Math.Max(Math.Max(rawFile.GetOneBasedScan(1).MassSpectrum.LastX.Value, rawFile.GetOneBasedScan(2).MassSpectrum.LastX.Value), rawFile.GetOneBasedScan(3).MassSpectrum.LastX.Value));
// 5 scans
SummedMsDataFile summed5 = new SummedMsDataFile(rawFile, 5, 10);
Assert.AreEqual(rawFile.NumSpectra - 4, summed5.NumSpectra);
MzmlMethods.CreateAndWriteMyMzmlWithCalibratedSpectra(summed5, "testSummed.mzML", false);
var ok = Mzml.LoadAllStaticData("testSummed.mzML");
MzmlMethods.CreateAndWriteMyMzmlWithCalibratedSpectra(ok, "testSummed2.mzML", false);
Mzml.LoadAllStaticData("testSummed2.mzML");
}
public static void WriteIndexedMzmlFromThermoTest()
{
var smallThermo = ThermoStaticData.LoadAllStaticData(@"small.raw");
MzmlMethods.CreateAndWriteMyMzmlWithCalibratedSpectra(smallThermo, Path.Combine(TestContext.CurrentContext.TestDirectory, "Hi.mzML"), true);
var smallMzml = Mzml.LoadAllStaticData(@"Hi.mzML");
Assert.AreEqual(smallMzml.NumSpectra, 48);
Assert.AreEqual(smallMzml.GetOneBasedScan(8).OneBasedScanNumber, 8);
Assert.AreEqual(smallThermo.GetOneBasedScan(5).RetentionTime, smallMzml.GetOneBasedScan(5).RetentionTime);
}
public static void LoadThermoFiltered()
{
ThermoStaticData a = ThermoStaticData.LoadAllStaticData(@"05-13-16_cali_MS_60K-res_MS.raw");
ThermoStaticData b = ThermoStaticData.LoadAllStaticData(@"05-13-16_cali_MS_60K-res_MS.raw", filterParams: new FilteringParams(numberOfPeaksToKeepPerWindow: 400, applyTrimmingToMs1: true));
ThermoStaticData c = ThermoStaticData.LoadAllStaticData(@"05-13-16_cali_MS_60K-res_MS.raw", filterParams: new FilteringParams(minimumAllowedIntensityRatioToBasePeak: 0.001, applyTrimmingToMs1: true));
ThermoStaticData d = ThermoStaticData.LoadAllStaticData(@"05-13-16_cali_MS_60K-res_MS.raw", filterParams: new FilteringParams(minimumAllowedIntensityRatioToBasePeak: 0.001, numberOfPeaksToKeepPerWindow: 400, applyTrimmingToMs1: true));
var aLen = a.GetOneBasedScan(1).MassSpectrum.Size;
var bLen = b.GetOneBasedScan(1).MassSpectrum.Size;
var cLen = c.GetOneBasedScan(1).MassSpectrum.Size;
var dLen = d.GetOneBasedScan(1).MassSpectrum.Size;
Assert.AreEqual(Math.Min(bLen, cLen), dLen);
}
public static void LoadCompressedMzml()
{
ThermoStaticData a = ThermoStaticData.LoadAllStaticData(@"small.RAW");
Mzml b = Mzml.LoadAllStaticData(@"smallCentroid.mzML");
Assert.AreEqual(a.NumSpectra, b.NumSpectra);
Assert.AreEqual(a.GetOneBasedScan(1).MassSpectrum.XofPeakWithHighestY.Value, b.GetOneBasedScan(1).MassSpectrum.XofPeakWithHighestY.Value, 1e-8);
Assert.IsTrue(Math.Abs((a.GetOneBasedScan(1).MassSpectrum.YofPeakWithHighestY.Value - b.GetOneBasedScan(1).MassSpectrum.YofPeakWithHighestY.Value) / b.GetOneBasedScan(1).MassSpectrum.YofPeakWithHighestY.Value) < 1e-8);
Assert.AreEqual(a.GetOneBasedScan(2).MassSpectrum.XofPeakWithHighestY.Value, b.GetOneBasedScan(2).MassSpectrum.XofPeakWithHighestY, 1e-8);
Assert.IsTrue(Math.Abs((a.GetOneBasedScan(2).MassSpectrum.YofPeakWithHighestY.Value - b.GetOneBasedScan(2).MassSpectrum.YofPeakWithHighestY.Value) / b.GetOneBasedScan(1).MassSpectrum.YofPeakWithHighestY.Value) < 1e-8);
Assert.AreEqual(a.GetOneBasedScan(3).MassSpectrum.XofPeakWithHighestY.Value, b.GetOneBasedScan(3).MassSpectrum.XofPeakWithHighestY.Value, 1e-8);
Assert.IsTrue(Math.Abs((a.GetOneBasedScan(3).MassSpectrum.YofPeakWithHighestY.Value - b.GetOneBasedScan(3).MassSpectrum.YofPeakWithHighestY.Value) / b.GetOneBasedScan(1).MassSpectrum.YofPeakWithHighestY.Value) < 1e-8);
}
private void AddAFile(string filePath)
{
string filename = Path.GetFileName(filePath);
string theExtension = Path.GetExtension(filename).ToLowerInvariant();
switch (theExtension)
{
case ".raw":
if (!ThermoStaticData.CheckForMsFileReader())
{
AddNotification("Warning! Cannot find Thermo MSFileReader (v3.0 SP2 is preferred); a crash may result from searching this .raw file");
}
goto case ".mzml";
case ".mzml":
SpectraFileForDataGrid spectraFile = new SpectraFileForDataGrid(filePath);
if (!spectraFilesForDataGrid.Select(f => f.FilePath).Contains(spectraFile.FilePath))
{
spectraFilesForDataGrid.Add(spectraFile);
}
if (string.IsNullOrEmpty(OutputFolderTextBox.Text))
{
var pathOfFirstSpectraFile = Path.GetDirectoryName(spectraFilesForDataGrid.First().FilePath);
OutputFolderTextBox.Text = Path.Combine(pathOfFirstSpectraFile, @"FlashLFQ_$DATETIME");
}
break;
case ".txt":
case ".tsv":
case ".psmtsv":
case ".tabular":
IdentificationFileForDataGrid identFile = new IdentificationFileForDataGrid(filePath);
if (!identFilesForDataGrid.Select(f => f.FilePath).Contains(identFile.FilePath) && !identFile.FileName.Equals("ExperimentalDesign.tsv"))
{
identFilesForDataGrid.Add(identFile);
}
break;
default:
AddNotification("Unrecognized file type: " + theExtension);
break;
}
}
public static void MultiWindowFiltering()
{
//tests for filtering with window
ThermoStaticData a_w = ThermoStaticData.LoadAllStaticData(@"05-13-16_cali_MS_60K-res_MS.raw", filterParams: new FilteringParams(numberOfWindows: 1, applyTrimmingToMs1: true));
Assert.AreEqual(1120, a_w.GetOneBasedScan(1).MassSpectrum.Size);
//number of 2
ThermoStaticData b_w = ThermoStaticData.LoadAllStaticData(@"05-13-16_cali_MS_60K-res_MS.raw", filterParams: new FilteringParams(numberOfPeaksToKeepPerWindow: 200, numberOfWindows: 3, applyTrimmingToMs1: true));
Assert.AreEqual(600, b_w.GetOneBasedScan(1).MassSpectrum.Size);
//number of 4
ThermoStaticData c_w = ThermoStaticData.LoadAllStaticData(@"05-13-16_cali_MS_60K-res_MS.raw", filterParams: new FilteringParams(numberOfPeaksToKeepPerWindow: 200, numberOfWindows: 4, applyTrimmingToMs1: true));
Assert.AreEqual(800, c_w.GetOneBasedScan(1).MassSpectrum.Size);
//number of 6, which doesn't divide 1120
ThermoStaticData d_w = ThermoStaticData.LoadAllStaticData(@"05-13-16_cali_MS_60K-res_MS.raw", filterParams: new FilteringParams(numberOfPeaksToKeepPerWindow: 150, numberOfWindows: 6, applyTrimmingToMs1: true));
Assert.AreEqual(900, d_w.GetOneBasedScan(1).MassSpectrum.Size);
}
public MsDataFile LoadFile(string origDataFile, CommonParameters commonParameters)
{
FilteringParams filter = new FilteringParams(commonParameters.NumberOfPeaksToKeepPerWindow, commonParameters.MinimumAllowedIntensityRatioToBasePeak, commonParameters.WindowWidthThomsons, commonParameters.NumberOfWindows, commonParameters.NormalizePeaksAccrossAllWindows, commonParameters.TrimMs1Peaks, commonParameters.TrimMsMsPeaks);
if (commonParameters.DissociationType == DissociationType.LowCID || commonParameters.ChildScanDissociationType == DissociationType.LowCID)
{
filter = null;
}
if (MyMsDataFiles.TryGetValue(origDataFile, out MsDataFile value) && value != null)
{
return(value);
}
// By now know that need to load this file!!!
lock (FileLoadingLock) // Lock because reading is sequential
{
if (Path.GetExtension(origDataFile).Equals(".mzML", StringComparison.OrdinalIgnoreCase))
{
MyMsDataFiles[origDataFile] = Mzml.LoadAllStaticData(origDataFile, filter, commonParameters.MaxThreadsToUsePerFile);
}
else if (Path.GetExtension(origDataFile).Equals(".mgf", StringComparison.OrdinalIgnoreCase))
{
MyMsDataFiles[origDataFile] = Mgf.LoadAllStaticData(origDataFile, filter);
}
else
{
#if NETFRAMEWORK
MyMsDataFiles[origDataFile] = ThermoStaticData.LoadAllStaticData(origDataFile, filter);
#else
Warn("No capability for reading " + origDataFile);
#endif
}
return(MyMsDataFiles[origDataFile]);
}
}
public static void LoadThermoTest2()
{
ThermoStaticData a = ThermoStaticData.LoadAllStaticData(@"05-13-16_cali_MS_60K-res_MS.raw");
Assert.AreEqual(360, a.NumSpectra);
Assert.GreaterOrEqual(1000, a.GetOneBasedScan(1).MassSpectrum.Extract(0, 500).Last().Mz);
Assert.AreEqual(2, a.GetOneBasedScan(1).MassSpectrum.FilterByY(5e6, double.MaxValue).Count());
var ye = a.GetOneBasedScan(1).MassSpectrum.CopyTo2DArray();
Assert.AreEqual(77561752, a.GetOneBasedScan(1).TotalIonCurrent);
Assert.AreEqual(144, a.GetClosestOneBasedSpectrumNumber(2));
MzSpectrum newSpectrum = new MzSpectrum(a.GetOneBasedScan(51).MassSpectrum.XArray, a.GetOneBasedScan(51).MassSpectrum.YArray, true);
Assert.AreEqual(1120, a.GetOneBasedScan(1).MassSpectrum.Size);
var newDeconvolution = a.GetOneBasedScan(1).MassSpectrum.Deconvolute(new MzRange(double.MinValue, double.MaxValue), 1, 10, 1, 4).ToList();
Assert.IsTrue(newDeconvolution.Any(b => Math.Abs(b.peaks.First().mz.ToMass(b.charge) - 523.257) < 0.001));
MzmlMethods.CreateAndWriteMyMzmlWithCalibratedSpectra(a, Path.Combine(TestContext.CurrentContext.TestDirectory, "convertedThermo.mzML"), false);
var sdafaf = a.Deconvolute(null, null, 1, 30, 10, 3, 10, b => true).OrderByDescending(b => b.NumPeaks).First();
Assert.IsTrue(Math.Abs(262.64 - sdafaf.Mass.ToMz(2)) <= 0.01);
using (ThermoDynamicData dynamicThermo = ThermoDynamicData.InitiateDynamicConnection(@"05-13-16_cali_MS_60K-res_MS.raw"))
{
Assert.AreEqual(136, dynamicThermo.GetClosestOneBasedSpectrumNumber(1.89));
dynamicThermo.ClearCachedScans();
}
Mzml readCovertedMzmlFile = Mzml.LoadAllStaticData(Path.Combine(TestContext.CurrentContext.TestDirectory, "convertedThermo.mzML"));
Assert.AreEqual(a.GetAllScansList().First().Polarity, readCovertedMzmlFile.GetAllScansList().First().Polarity);
}
public static void ReadWriteReadEtc()
{
{
ThermoStaticData a = ThermoStaticData.LoadAllStaticData(@"testFileWMS2.raw");
MzmlMethods.CreateAndWriteMyMzmlWithCalibratedSpectra(a, "a.mzML", false);
var aa = Mzml.LoadAllStaticData("a.mzML");
MzmlMethods.CreateAndWriteMyMzmlWithCalibratedSpectra(aa, "aa.mzML", true);
Mzml.LoadAllStaticData("aa.mzML");
}
{
ThermoStaticData a = ThermoStaticData.LoadAllStaticData(@"small.raw");
MzmlMethods.CreateAndWriteMyMzmlWithCalibratedSpectra(a, "a.mzML", false);
var aa = Mzml.LoadAllStaticData("a.mzML");
MzmlMethods.CreateAndWriteMyMzmlWithCalibratedSpectra(aa, "aa.mzML", true);
Mzml.LoadAllStaticData("aa.mzML");
}
{
ThermoStaticData a = ThermoStaticData.LoadAllStaticData(@"05-13-16_cali_MS_60K-res_MS.raw");
MzmlMethods.CreateAndWriteMyMzmlWithCalibratedSpectra(a, "a.mzML", false);
var aa = Mzml.LoadAllStaticData("a.mzML");
MzmlMethods.CreateAndWriteMyMzmlWithCalibratedSpectra(aa, "aa.mzML", true);
Mzml.LoadAllStaticData("aa.mzML");
}
}
private void LoadData(string path, FileType fileType)
{
if (fileType == FileType.DeconvolutionTSV)
{
System.IO.StreamReader reader = new System.IO.StreamReader(path);
string line;
int lineNum = 1;
while (reader.Peek() > 0)
{
line = reader.ReadLine();
List <IsotopicEnvelope> envs = new List <IsotopicEnvelope>();
if (lineNum != 1)
{
var parsedLine = line.Split('\t');
var mass = double.Parse(parsedLine[0]);
var apexRt = double.Parse(parsedLine[10]);
var envelopes = parsedLine[17].Split(new string[] { "[", "]" }, StringSplitOptions.RemoveEmptyEntries);
foreach (var envelope in envelopes)
{
var split = envelope.Split(new string[] { "|", "(", ")" }, StringSplitOptions.RemoveEmptyEntries);
int charge = int.Parse(split[0]);
double rt = double.Parse(split[1]);
int scan = int.Parse(split[2]);
List <MassSpectralPeak> peaks = new List <MassSpectralPeak>();
for (int i = 3; i < split.Length; i++)
{
string[] sp = split[i].Split(new string[] { "," }, StringSplitOptions.RemoveEmptyEntries);
MassSpectralPeak peak = new MassSpectralPeak(double.Parse(sp[0]), double.Parse(sp[1]));
peaks.Add(peak);
}
IsotopicEnvelope env = new IsotopicEnvelope(rt, charge, peaks);
envs.Add(env);
}
var gsdf = envs.GroupBy(p => p.charge).Where(v => v.Count() > 1);
if (gsdf.Any())
{
var deconvolutedFeature = new ChromatographicPeak(envs, mass, apexRt);
if (deconvolutedFeature.GetSignalToBaseline() > 2.0)
{
DeconvolutedFeatures.Add(deconvolutedFeature);
}
}
}
lineNum++;
}
reader.Close();
}
else if (fileType == FileType.MetaMorpheusPsmTsv)
{
System.IO.StreamReader reader = new System.IO.StreamReader(path);
string line;
int lineNum = 1;
while (reader.Peek() > 0)
{
line = reader.ReadLine();
List <IsotopicEnvelope> envs = new List <IsotopicEnvelope>();
if (lineNum != 1)
{
var parsedLine = line.Split('\t');
}
}
}
else if (fileType == FileType.RawFile)
{
string ext = System.IO.Path.GetExtension(path).ToUpperInvariant();
if (ext.Equals(".RAW"))
{
rawFile = ThermoStaticData.LoadAllStaticData(path);
}
if (ext.Equals(".MZML"))
{
rawFile = Mzml.LoadAllStaticData(path);
}
else
{
throw new Exception("Cannot read file format: " + ext);
}
}
else
{
throw new Exception("Cannot read file " + path);
}
}
public static void ThermoReaderNotInstalled()
{
bool check = ThermoStaticData.CheckForMsFileReader();
Assert.IsTrue(check);
}
public static void ThermoLoadError()
{
Assert.Throws <FileNotFoundException>(() => ThermoStaticData.LoadAllStaticData(@"aaa.RAW"));
}
private static void DoFileDecon(string[] args)
{
var p = new FluentCommandLineParser <ApplicationArguments>();
p.Setup(arg => arg.AggregationTolerancePpm)
.As("AggregationTolerancePpm");
p.Setup(arg => arg.DeconvolutionTolerancePpm)
.As("DeconvolutionTolerancePpm");
p.Setup(arg => arg.MinScan)
.As("MinScan");
p.Setup(arg => arg.MaxScan)
.As("MaxScan");
p.Setup(arg => arg.MinAssumedChargeState)
.As("MinAssumedChargeState");
p.Setup(arg => arg.MaxAssumedChargeState)
.As("MaxAssumedChargeState");
p.Setup(arg => arg.IntensityRatioLimit)
.As("IntensityRatioLimit");
p.Setup(arg => arg.AverageScans)
.As("AverageScans");
p.Setup(arg => arg.NumScansRequired)
.As("NumScansRequired");
p.Setup(arg => arg.FilePath)
.As("FilePath").
Required();
var result = p.Parse(args);
Console.WriteLine("Running deconvolution using the following parameters:");
Console.WriteLine(p.Object);
if (result.HasErrors == false)
{
MsDataFile myMsDataFile;
if (Path.GetExtension(p.Object.FilePath).Equals(".mzML", StringComparison.OrdinalIgnoreCase))
{
myMsDataFile = Mzml.LoadAllStaticData(p.Object.FilePath);
}
else
{
myMsDataFile = ThermoStaticData.LoadAllStaticData(p.Object.FilePath);
}
if (p.Object.AverageScans > 1)
{
myMsDataFile = new SummedMsDataFile(myMsDataFile, p.Object.AverageScans, p.Object.DeconvolutionTolerancePpm);
}
using (StreamWriter output = new StreamWriter(@"DeconvolutionOutput-" + DateTime.Now.ToString("yyyy-MM-dd-HH-mm-ss", CultureInfo.InvariantCulture) + ".tsv"))
{
output.WriteLine("Mass\tScore\tNumPeaks\tNumScans\tMinScan\tMaxScan\tElutionStart\tElutionEnd\tTotalNormalizedIntensity\tObservedCharges\tMostIntenseElutionTime\tMostIntenseCharge\tMostIntenseMz\tNumPeaksInMostIntenseEnvelope\tMostIntenseEnvelopeIntensity\tElutionOfMostIntenseCharge");
foreach (var nice in myMsDataFile.Deconvolute(p.Object.MinScan, p.Object.MaxScan, p.Object.MinAssumedChargeState, p.Object.MaxAssumedChargeState, p.Object.DeconvolutionTolerancePpm, p.Object.IntensityRatioLimit, p.Object.AggregationTolerancePpm, b => b.MsnOrder == 1).OrderByDescending(b => b.Score))
{
if ((nice.MaxScanIndex - nice.MinScanIndex + 1) >= p.Object.NumScansRequired)
{
output.WriteLine(nice.OneLineString());
}
}
}
}
else
{
Console.WriteLine("BAD PARAMETERS");
Console.WriteLine(result.ErrorText);
}
}
private static void Main(string[] args)
{
DoubleRange r = new DoubleRange(-187, double.PositiveInfinity);
Console.WriteLine(r);
Console.WriteLine(r.ToString());
//Loaders.LoadElements("elements2.dat");
//Dictionary<string, Modification> um;
//ProteinDbLoader.LoadProteinXML(@"C:\Users\stepa\Desktop\01012017_MM_ONLYGPTMD.xml", true, new List<Modification>(), false, new List<string> { "GO", "EnsemblFungi" }, null, out um);
//ThermoStaticData.LoadAllStaticData(@"C:\Users\stepa\Desktop\PrecursorProblems\2016_080902_SMC_EC_Glyco_EThcD.raw");
//Mzml.LoadAllStaticData(@"C:\Users\stepa\Source\Repos\MetaMorpheus\Test\bin\Debug\ok.mzML");
//var oddk = ThermoDynamicData.InitiateDynamicConnection(@"C:\Users\stepa\Data\CalibrationPaperData\Jurkat\120426_Jurkat_highLC_Frac1.raw");
//ThermoStaticData.LoadAllStaticData(@"C:\Users\stepa\Desktop\yeast_tmt\m04667.raw");
//ThermoStaticData.LoadAllStaticData(@"C:\Users\stepa\Desktop\human_spike\C14-11130.raw");
//ThermoStaticData.LoadAllStaticData(@"C:\Users\stepa\Data\CalibrationPaperData\Jurkat\120426_Jurkat_highLC_Frac18.raw");
ThermoStaticData.LoadAllStaticData(@"C:\Users\stepa\Desktop\CoIsolation\05-11-17_YL_25iso.raw");
//var hheh = oddk.GetMsScansInTimeRange(47.2469, 47.25693).ToList();
//Mzml.LoadAllStaticData(@"C:\Users\stepa\Data\CalibrationPaperData\Jurkat\120426_Jurkat_highLC_Frac28.mzML");
//var okff = ThermoStaticData.LoadAllStaticData(@"C:\Users\stepa\Data\CalibrationPaperData\Jurkat\120426_Jurkat_highLC_Frac28.raw");
//var okff = ThermoStaticData.LoadAllStaticData(@"C:\Users\stepa\Data\ForRyan\golden.raw");
//MzmlMethods.CreateAndWriteMyMzmlWithCalibratedSpectra(okff, @"C:\Users\stepa\Data\ForRyan\adsfjk.mzML");
//Mzml.LoadAllStaticData(@"C:\Users\stepa\Desktop\02-15-17_Cys-tag_light\02-14-17_Cl-1_rep1.mzML");
//using (var nice = ThermoDynamicData.InitiateDynamicConnection(@"C:\Users\stepa\Desktop\02-15-17_Cys-tag_light\02-14-17_Cl-1_rep1.raw"))
//{
// Console.WriteLine(nice.GetOneBasedScan(1000).RetentionTime);
//}
//// OLD MASS SPEC
//var theFiles = new List<string>{
// //@"C:\Users\stepa\Data\CalibrationPaperData\Jurkat\120426_Jurkat_highLC_Frac17.raw",
// //@"C:\Users\stepa\Data\CalibrationPaperData\Mouse\04-30-13_CAST_Frac5_4uL.raw",
// //@"C:\Users\stepa\Data\CalibrationPaperData\Yeast\12-10-16_A17A_yeast_BU_fract9_rep1_8uL.raw",
// //@"C:\Users\stepa\Desktop\MvsMM\04-21-17_Lys_1-200_rep1.raw",
// //@"C:\Users\stepa\Desktop\MvsMM\04-21-17_Lys_1-200_rep1.mzML",
// @"C:\Users\stepa\Data\CalibrationPaperData\Mouse\04-29-13_B6_Frac7_5uL.raw"
//};
//// Params
//var tols = new List<Tolerance> { new Tolerance("5 PPM") };
//var isotopeRatios = new List<int> { 4 };
//var maxAssumedChargeState = 10;
//foreach (var theFile in theFiles)
//{
// var okff = ThermoStaticData.LoadAllStaticData(theFile);
// //var okff = Mzml.LoadAllStaticData(theFile);
// int countScans = 0;
// int totalHaveMMandCharge = 0;
// var totalHaveMyMass = new int[1, 1];
// var totalMatch = new int[1, 1];
// //foreach (var scanWithPrec in okff.OfType<IMsDataScanWithPrecursor<IMzSpectrum<IMzPeak>>>())
// var scanWithPrec = okff.GetOneBasedScan(11042) as IMsDataScanWithPrecursor<IMzSpectrum<IMzPeak>>;
// {
// countScans++;
// Console.WriteLine("Scan " + scanWithPrec.OneBasedScanNumber + " ; isolation=" + scanWithPrec.IsolationMz + " ; mm=" + scanWithPrec.SelectedIonMonoisotopicGuessMz + " ; charge=" + scanWithPrec.SelectedIonChargeStateGuess);
// if (scanWithPrec.SelectedIonMonoisotopicGuessMz.HasValue && scanWithPrec.SelectedIonChargeStateGuess.HasValue)
// {
// totalHaveMMandCharge++;
// }
// for (int i = 0; i < tols.Count; i++)
// {
// var tol = tols[i];
// for (int j = 0; j < isotopeRatios.Count; j++)
// {
// var isotopeRatio = isotopeRatios[j];
// var mzEnvelopesWithCharges = scanWithPrec.GetIsolatedMassesAndCharges(okff.GetOneBasedScan(scanWithPrec.OneBasedPrecursorScanNumber).MassSpectrum, maxAssumedChargeState, tol, isotopeRatio).ToList();
// if (mzEnvelopesWithCharges.Count() > 0)
// totalHaveMyMass[i, j]++;
// if (scanWithPrec.SelectedIonMonoisotopicGuessMz.HasValue && scanWithPrec.SelectedIonChargeStateGuess.HasValue)
// {
// if (mzEnvelopesWithCharges.Any(bd => tol.Within(bd.Item1.First().Mz.ToMass(bd.Item2), scanWithPrec.SelectedIonMonoisotopicGuessMz.Value.ToMass(scanWithPrec.SelectedIonChargeStateGuess.Value))))
// {
// totalMatch[i, j]++;
// Console.WriteLine("Match!");
// }
// else
// {
// Console.WriteLine(string.Join(Environment.NewLine, mzEnvelopesWithCharges.Select(b => "\t" + b.Item2 + " : " + string.Join(",", b.Item1))));
// }
// }
// else
// {
// Console.WriteLine(string.Join(Environment.NewLine, mzEnvelopesWithCharges.Select(b => "\t" + b.Item2 + " : " + string.Join(",", b.Item1))));
// }
// }
// }
// }
// Console.WriteLine("countScans: " + countScans);
// Console.WriteLine("totalHaveMMandCharge: " + totalHaveMMandCharge);
// for (int i = 0; i < tols.Count; i++)
// {
// var tol = tols[i];
// for (int j = 0; j < isotopeRatios.Count; j++)
// {
// Console.WriteLine("i = " + i + " j = " + j);
// Console.WriteLine("totalHaveMyMass: " + totalHaveMyMass[i, j]);
// Console.WriteLine("totalMatch: " + totalMatch[i, j]);
// }
// }
//}
//using (var nice = ThermoDynamicData.InitiateDynamicConnection(@"C:\Users\stepa\Data\CalibrationPaperData\Mouse\04-30-13_CAST_Frac5_4uL.raw"))
////{
//using (var nice = ThermoDynamicData.InitiateDynamicConnection(@"C:\Users\stepa\Data\CalibrationPaperData\Jurkat\120426_Jurkat_highLC_Frac17.raw"))
//{
//var hehdfe = nice.GetOneBasedScan(168) as IMsDataScanWithPrecursor<ThermoSpectrum>;
//Console.WriteLine("Scan " + hehdfe.OneBasedScanNumber + " ; isolation=" + hehdfe.IsolationMz + " ; mm=" + hehdfe.SelectedIonMonoisotopicGuessMz);
//var fdf = hehdfe.GetIsolatedMassesAndCharges(nice.GetOneBasedScan(hehdfe.OneBasedPrecursorScanNumber).MassSpectrum, 10, new Tolerance("20 PPM"), 10, 1);
//Console.WriteLine(fdf.Count() + ";" + hehdfe.SelectedIonMonoisotopicGuessMz.HasValue);
//Console.WriteLine(string.Join(Environment.NewLine, fdf.Select(b => "\t" + b.Item1 + "; " + b.Item2 + "; " + b.Item1.First())));
// Console.WriteLine();
// int totalHaveMM = 0;
// int totalHaveMMandMatch = 0;
// int totalHaveMyMass = 0;
// int totalHaveMMandMatchAll = 0;
// int totalHaveMyMassAll = 0;
// foreach (var hehdfe in nice.OfType<IMsDataScanWithPrecursor<ThermoSpectrum>>())
// {
// Console.WriteLine("Scan " + hehdfe.OneBasedScanNumber + " ; isolation=" + hehdfe.IsolationMz + " ; mm=" + hehdfe.SelectedIonMonoisotopicGuessMz + " ; charge=" + hehdfe.SelectedIonChargeStateGuess);
// //var fdf = hehdfe.GetIsolatedMassesAndCharges(nice.GetOneBasedScan(hehdfe.OneBasedPrecursorScanNumber).MassSpectrum, 10, tol, 10, 1).ToList();
// //if (fdf.Count() > 0)
// // totalHaveMyMass++;
// //if (hehdfe.SelectedIonMonoisotopicGuessMz.HasValue)
// //{
// // totalHaveMM++;
// // if (fdf.Any(bd => tol.Within(bd.Item1.First().ToMass(bd.Item2), hehdfe.SelectedIonMonoisotopicGuessMz.Value.ToMass(hehdfe.SelectedIonChargeStateGuess.Value))))
// // totalHaveMMandMatch++;
// //}
// if (fdfAll.Count() > 0)
// totalHaveMyMassAll++;
// Console.WriteLine(fdfAll.Count() + ";" + hehdfe.SelectedIonMonoisotopicGuessMz.HasValue);
// if (hehdfe.SelectedIonMonoisotopicGuessMz.HasValue)
// {
// totalHaveMM++;
// var massFromScan = hehdfe.SelectedIonMonoisotopicGuessMz.Value.ToMass(hehdfe.SelectedIonChargeStateGuess.Value);
// if (fdfAll.Any(bd => tol.Within(bd.Item1.First().ToMass(bd.Item2), massFromScan)))
// totalHaveMMandMatchAll++;
// if (totalHaveMMandMatchAll - totalHaveMyMassAll < -6)
// Console.WriteLine(totalHaveMMandMatchAll + " not equal " + totalHaveMyMassAll);
// }
// Console.WriteLine();
// }
//}
//using (var nice = ThermoDynamicData.InitiateDynamicConnection(@"C:\Users\stepa\Data\CalibrationPaperData\Jurkat\120426_Jurkat_highLC_Frac17.raw"))
//{
// var ok = nice.GetOneBasedScan(24676);
// var hm = ok as IMsDataScanWithPrecursor<IMzSpectrum<IMzPeak>>;
// hm.RecomputeSelectedPeak(nice.GetOneBasedScan(hm.OneBasedPrecursorScanNumber).MassSpectrum);
//}
//using (var nice = ThermoDynamicData.InitiateDynamicConnection(@"C:\Users\stepa\Desktop\02-15-17_Cys-tag_light\02-14-17_Cl-1_rep1.raw"))
//{
// var ok = nice.GetOneBasedScan(71291);
// var hm = ok as IMsDataScanWithPrecursor<IMzSpectrum<IMzPeak>>;
// var prevSpectrum = nice.GetOneBasedScan(hm.OneBasedPrecursorScanNumber).MassSpectrum;
// Console.WriteLine(hm.SelectedIonGuessChargeStateGuess + Environment.NewLine
// + hm.SelectedIonGuessMZ + Environment.NewLine
// + hm.SelectedIonGuessIntensity + Environment.NewLine
// + hm.SelectedIonGuessMonoisotopicMZ + Environment.NewLine
// + hm.SelectedIonGuessMonoisotopicIntensity + Environment.NewLine);
// hm.RecomputeChargeState(prevSpectrum, 0.01, 4);
// Console.WriteLine(hm.SelectedIonGuessChargeStateGuess + Environment.NewLine
// + hm.SelectedIonGuessMZ + Environment.NewLine
// + hm.SelectedIonGuessIntensity + Environment.NewLine
// + hm.SelectedIonGuessMonoisotopicMZ + Environment.NewLine
// + hm.SelectedIonGuessMonoisotopicIntensity + Environment.NewLine);
// hm.ComputeSelectedPeakIntensity(prevSpectrum);
// Console.WriteLine(hm.SelectedIonGuessChargeStateGuess + Environment.NewLine
// + hm.SelectedIonGuessMZ + Environment.NewLine
// + hm.SelectedIonGuessIntensity + Environment.NewLine
// + hm.SelectedIonGuessMonoisotopicMZ + Environment.NewLine
// + hm.SelectedIonGuessMonoisotopicIntensity + Environment.NewLine);
// hm.ComputeMonoisotopicPeakIntensity(prevSpectrum);
// Console.WriteLine(hm.SelectedIonGuessChargeStateGuess + Environment.NewLine
// + hm.SelectedIonGuessMZ + Environment.NewLine
// + hm.SelectedIonGuessIntensity + Environment.NewLine
// + hm.SelectedIonGuessMonoisotopicMZ + Environment.NewLine
// + hm.SelectedIonGuessMonoisotopicIntensity + Environment.NewLine);
// hm.RecomputeSelectedPeak(prevSpectrum);
// Console.WriteLine(hm.SelectedIonGuessChargeStateGuess + Environment.NewLine
// + hm.SelectedIonGuessMZ + Environment.NewLine
// + hm.SelectedIonGuessIntensity + Environment.NewLine
// + hm.SelectedIonGuessMonoisotopicMZ + Environment.NewLine
// + hm.SelectedIonGuessMonoisotopicIntensity + Environment.NewLine);
// hm.RecomputeMonoisotopicPeak(prevSpectrum, 0.01, 0.3);
// Console.WriteLine(hm.SelectedIonGuessChargeStateGuess + Environment.NewLine
// + hm.SelectedIonGuessMZ + Environment.NewLine
// + hm.SelectedIonGuessIntensity + Environment.NewLine
// + hm.SelectedIonGuessMonoisotopicMZ + Environment.NewLine
// + hm.SelectedIonGuessMonoisotopicIntensity + Environment.NewLine);
// hm.RecomputeSelectedPeak(nice.GetOneBasedScan(hm.OneBasedPrecursorScanNumber).MassSpectrum);
//}
PopulatePeriodicTable();
BenchmarkFormula();
Console.WriteLine("");
BenchmarkFormula2();
Console.WriteLine("");
BenchmarkTimeGettingElementFromPeriodicTable();
Console.WriteLine("");
BenchmarkGettingIsotopes();
Console.WriteLine("");
BenchmarkIsotopicDistribution();
Loaders.LoadElements(@"elements.tmp");
Console.WriteLine("");
BenchmarkDatabaseLoadWrite();
}
public static void TestExternalPassedFile()
{
Console.WriteLine("UNIT TEST - Entering unit test");
string[] filePaths = Directory.GetFiles(TestContext.CurrentContext.TestDirectory).Where(f => f.Substring(f.IndexOf('.')).ToUpper().Equals(".RAW")).ToArray();
var thermoFile = ThermoStaticData.LoadAllStaticData(filePaths[0]);
string elements = Path.Combine(TestContext.CurrentContext.TestDirectory, "elements.dat");
string ident = Path.Combine(TestContext.CurrentContext.TestDirectory, "aggregatePSMs_5ppmAroundZero.psmtsv");
FlashLFQEngine engine = new FlashLFQEngine();
Console.WriteLine("UNIT TEST - About to load elements");
Loaders.LoadElements(elements);
Console.WriteLine("UNIT TEST - Finished loading elements");
engine.PassFilePaths(filePaths);
Assert.That(engine.ParseArgs(new string[] {
"--ppm 5",
"--sil false",
"--pau false",
"--mbr true"
}
));
Console.WriteLine("UNIT TEST - Done making engine");
engine.globalStopwatch.Start();
engine.SetParallelization(1);
Console.WriteLine("UNIT TEST - Adding identifications");
var ids = File.ReadAllLines(ident);
int lineCount = 1;
foreach (var line in ids)
{
if (lineCount != 1)
{
var splitLine = line.Split('\t');
engine.AddIdentification(Path.GetFileNameWithoutExtension(splitLine[0]), splitLine[20], splitLine[21], double.Parse(splitLine[27]), double.Parse(splitLine[2]), (int)double.Parse(splitLine[6]), new List <string> {
splitLine[14]
});
}
lineCount++;
}
Console.WriteLine("UNIT TEST - Finished adding IDs");
engine.ConstructIndexTemplateFromIdentifications();
Console.WriteLine("UNIT TEST - Finished constructing bins");
Assert.That(engine.observedMzsToUseForIndex.Count > 0);
Assert.That(engine.baseSequenceToIsotopicDistribution.Count > 0);
Console.WriteLine("UNIT TEST - Bins are OK");
for (int i = 0; i < engine.filePaths.Length; i++)
{
Console.WriteLine("UNIT TEST - Quantifying file " + (i + 1));
try
{
Assert.That(engine.Quantify(thermoFile, engine.filePaths[i]));
}
catch (AssertionException)
{
Console.WriteLine("UNIT TEST - Could not quantify file \"" + engine.filePaths[i] + "\"");
}
}
//if (engine.mbr)
// engine.RetentionTimeCalibrationAndErrorCheckMatchedFeatures();
Console.WriteLine("UNIT TEST - Quantifying proteins ");
engine.QuantifyProteins();
Console.WriteLine("UNIT TEST - Asserting results");
Assert.That(engine.SumFeatures(engine.allFeaturesByFile.SelectMany(p => p), true).Any());
Assert.That(engine.SumFeatures(engine.allFeaturesByFile.SelectMany(p => p), false).Any());
Assert.That(engine.allFeaturesByFile[0].First().intensity > 0);
Assert.That(!engine.allFeaturesByFile[0].First().isMbrFeature);
Console.WriteLine("UNIT TEST - All passed");
}
private static void Main(string[] args)
{
Loaders.LoadElements("elements.dat");
var p = new FluentCommandLineParser <ApplicationArguments>();
p.Setup(arg => arg.DeconvolutionTolerancePpm)
.As("DeconvolutionTolerancePpm");
p.Setup(arg => arg.MinScan)
.As("MinScan");
p.Setup(arg => arg.MaxScan)
.As("MaxScan");
p.Setup(arg => arg.MinAssumedChargeState)
.As("MinAssumedChargeState");
p.Setup(arg => arg.MaxAssumedChargeState)
.As("MaxAssumedChargeState");
p.Setup(arg => arg.IntensityRatioLimit)
.As("IntensityRatioLimit");
p.Setup(arg => arg.FilePath)
.As("FilePath").
Required();
var result = p.Parse(args);
Console.WriteLine("Running deconvolution using the following parameters:");
Console.WriteLine(p.Object);
if (result.HasErrors == false)
{
IMsDataFile <IMsDataScan <IMzSpectrum <IMzPeak> > > myMsDataFile;
if (Path.GetExtension(p.Object.FilePath).Equals(".mzML", StringComparison.OrdinalIgnoreCase))
{
myMsDataFile = Mzml.LoadAllStaticData(p.Object.FilePath);
}
else
{
myMsDataFile = ThermoStaticData.LoadAllStaticData(p.Object.FilePath);
}
using (StreamWriter output = new StreamWriter(@"MS2DeconvolutionOutput-" + DateTime.Now.ToString("yyyy-MM-dd-HH-mm-ss", CultureInfo.InvariantCulture) + ".tsv"))
{
output.WriteLine("Mass\tNumPeaks\tNumScans\tMinScan\tMaxScan\tAverageElutionTime\tIntensity\tObservedCharges\tMostIntenseCharge\tMostIntenseMz\tNumPeaksInMostIntenseEnvelope");
foreach (var ok in myMsDataFile.OfType <IMsDataScanWithPrecursor <IMzSpectrum <IMzPeak> > >())
{
if ((!p.Object.MinScan.HasValue || ok.OneBasedScanNumber >= p.Object.MinScan) && (!p.Object.MaxScan.HasValue || ok.OneBasedScanNumber <= p.Object.MaxScan))
{
var hmm = ok.MassSpectrum.Deconvolute(new MzRange(0, double.PositiveInfinity), p.Object.MinAssumedChargeState, p.Object.MaxAssumedChargeState, p.Object.DeconvolutionTolerancePpm, p.Object.IntensityRatioLimit).ToList();
List <DeconvolutionFeatureWithMassesAndScans> currentListOfGroups = new List <DeconvolutionFeatureWithMassesAndScans>();
foreach (var isotopicEnvelope in hmm)
{
DeconvolutionFeatureWithMassesAndScans matchingGroup = null;
var mass = isotopicEnvelope.monoisotopicMass;
foreach (var possibleGroup in currentListOfGroups)
{
var possibleGroupMass = possibleGroup.Mass;
if (Math.Abs(mass - possibleGroupMass) / possibleGroupMass * 1e6 <= p.Object.AggregationTolerancePpm ||
Math.Abs(mass + 1.002868314 - possibleGroupMass) / possibleGroupMass * 1e6 <= p.Object.AggregationTolerancePpm ||
Math.Abs(mass + 2.005408917 - possibleGroupMass) / possibleGroupMass * 1e6 <= p.Object.AggregationTolerancePpm ||
Math.Abs(mass + 3.007841294 - possibleGroupMass) / possibleGroupMass * 1e6 <= p.Object.AggregationTolerancePpm ||
Math.Abs(mass - 1.002868314 - possibleGroupMass) / possibleGroupMass * 1e6 <= p.Object.AggregationTolerancePpm ||
Math.Abs(mass - 2.005408917 - possibleGroupMass) / possibleGroupMass * 1e6 <= p.Object.AggregationTolerancePpm ||
Math.Abs(mass - 3.007841294 - possibleGroupMass) / possibleGroupMass * 1e6 <= p.Object.AggregationTolerancePpm)
{
matchingGroup = possibleGroup;
matchingGroup.AddEnvelope(isotopicEnvelope, ok.OneBasedScanNumber, ok.RetentionTime);
break;
}
}
if (matchingGroup == null)
{
var newGroupScans = new DeconvolutionFeatureWithMassesAndScans();
newGroupScans.AddEnvelope(isotopicEnvelope, ok.OneBasedScanNumber, ok.RetentionTime);
currentListOfGroups.Add(newGroupScans);
}
}
foreach (var ook in currentListOfGroups)
{
output.WriteLine(ook.OneLineString());
}
}
}
}
}
else
{
Console.WriteLine("BAD PARAMETERS");
Console.WriteLine(result.ErrorText);
}
}
public bool Run_TdMzCal(InputFile raw_file, List <SpectrumMatch> topdown_hits)
{
all_topdown_hits = topdown_hits.Where(h => h.score > 0).ToList();
//need to reset m/z in case same td hits used for multiple calibration raw files...
Parallel.ForEach(all_topdown_hits, h => h.mz = h.reported_mass.ToMz(h.charge));
high_scoring_topdown_hits = all_topdown_hits.Where(h => h.score >= 40).ToList();
this.raw_file = raw_file;
if (high_scoring_topdown_hits.Count < 5)
{
return(false);
}
myMsDataFile = Path.GetExtension(raw_file.complete_path) == ".raw" ?
ThermoStaticData.LoadAllStaticData(raw_file.complete_path) :
null;
if (myMsDataFile == null)
{
myMsDataFile = Mzml.LoadAllStaticData(raw_file.complete_path);
}
if (myMsDataFile == null)
{
return(false);
}
DataPointAquisitionResults dataPointAcquisitionResult = GetDataPoints();
if (dataPointAcquisitionResult.Ms1List.Count < 10)
{
return(false);
}
if (Sweet.lollipop.mass_calibration)
{
var myMs1DataPoints = new List <(double[] xValues, double yValue)>();
for (int i = 0; i < dataPointAcquisitionResult.Ms1List.Count; i++)
{
//x values
var explanatoryVariables = new double[4];
explanatoryVariables[0] = dataPointAcquisitionResult.Ms1List[i].mz;
explanatoryVariables[1] = dataPointAcquisitionResult.Ms1List[i].retentionTime;
explanatoryVariables[2] = dataPointAcquisitionResult.Ms1List[i].logTotalIonCurrent;
explanatoryVariables[3] = dataPointAcquisitionResult.Ms1List[i].logInjectionTime;
//yvalue
double mzError = dataPointAcquisitionResult.Ms1List[i].massError;
myMs1DataPoints.Add((explanatoryVariables, mzError));
}
var ms1Model = GetRandomForestModel(myMs1DataPoints);
CalibrateHitsAndComponents(ms1Model);
if (Sweet.lollipop.calibrate_raw_files)
{
MzmlMethods.CreateAndWriteMyMzmlWithCalibratedSpectra(myMsDataFile,
raw_file.directory + "\\" + raw_file.filename + "_calibrated.mzML", false);
}
}
if (Sweet.lollipop.retention_time_calibration)
{
var myMs1DataPoints = new List <(double[] xValues, double yValue)>();
List <SpectrumMatch> firstElutingTopDownHit = new List <SpectrumMatch>();
List <string> PFRs = high_scoring_topdown_hits.Select(h => h.pfr_accession).Distinct().ToList();
foreach (var PFR in PFRs)
{
var firstHitWithPFR = high_scoring_topdown_hits
.Where(h => h.pfr_accession == PFR).OrderBy(h => h.ms2_retention_time).First();
firstElutingTopDownHit.Add(firstHitWithPFR);
}
for (int i = 0; i < dataPointAcquisitionResult.Ms1List.Count; i++)
{
if (firstElutingTopDownHit.Contains(dataPointAcquisitionResult.Ms1List[i].identification))
{
//x values
var explanatoryVariables = new double[1];
explanatoryVariables[0] = dataPointAcquisitionResult.Ms1List[i].retentionTime;
//yvalue
double RTError = dataPointAcquisitionResult.Ms1List[i].RTError;
myMs1DataPoints.Add((explanatoryVariables, RTError));
}
}
if (myMs1DataPoints.Count < 10)
{
return(false);
}
var ms1Model = GetRandomForestModel(myMs1DataPoints);
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))
{
c.rt_apex = c.rt_apex - ms1Model.Predict(new double[] { c.rt_apex });
}
}
return(true);
}
