/// <summary>
/// Gets the appropriate IMassSpecDataReader for the supplied path.
/// It is recommended that "NormalizeDatasetPath" be called prior to calling this function, and that the returned string be used instead of the original path
/// </summary>
/// <param name="filePath"></param>
/// <returns></returns>
/// <remarks>It is recommended that "NormalizeDatasetPath" be called prior to calling this function, and that the returned string be used instead of the original path</remarks>
public static IMassSpecDataReader GetMassSpecDataReader(string filePath)
{
filePath = NormalizeDatasetPath(filePath);
var type = GetMassSpecDataType(filePath);
IMassSpecDataReader reader = null;
switch (type)
{
case MassSpecDataType.XCaliburRun:
reader = new XCaliburReader(filePath);
break;
case MassSpecDataType.MzMLFile:
reader = new MzMLReader(filePath);
break;
case MassSpecDataType.PbfFile:
reader = new PbfLcMsRun(filePath);
break;
case MassSpecDataType.Unknown:
if (_pwizAvailable)
{
reader = new ProteoWizardReader(filePath);
}
break;
}
return(reader);
}
/// <summary>
/// Gets the appropriate IMassSpecDataReader for the supplied path.
/// It is recommended that "NormalizeDatasetPath" be called prior to calling this function, and that the returned string be used instead of the original path
/// </summary>
/// <param name="filePath"></param>
/// <returns></returns>
/// <remarks>It is recommended that "NormalizeDatasetPath" be called prior to calling this function, and that the returned string be used instead of the original path</remarks>
public static IMassSpecDataReader GetMassSpecDataReader(string filePath)
{
filePath = NormalizeDatasetPath(filePath);
var type = GetMassSpecDataType(filePath);
IMassSpecDataReader reader = null;
switch (type)
{
case MassSpecDataType.XCaliburRun:
reader = new XCaliburReader(filePath);
break;
case MassSpecDataType.MzMLFile:
reader = new MzMLReader(filePath);
break;
case MassSpecDataType.PbfFile:
reader = new PbfLcMsRun(filePath);
break;
case MassSpecDataType.Unknown:
if (_pwizAvailable)
{
reader = new ProteoWizardReader(filePath);
}
break;
}
return reader;
}
/// <summary>
/// Gets the appropriate IMassSpecDataReader for the supplied path.
/// It is recommended that "NormalizeDatasetPath" be called prior to calling this function, and that the returned string be used instead of the original path
/// </summary>
/// <param name="filePath"></param>
/// <returns></returns>
/// <remarks>It is recommended that "NormalizeDatasetPath" be called prior to calling this function, and that the returned string be used instead of the original path</remarks>
public static IMassSpecDataReader GetMassSpecDataReader(string filePath)
{
filePath = NormalizeDatasetPath(filePath);
var type = GetMassSpecDataType(filePath);
IMassSpecDataReader reader = null;
switch (type)
{
case MassSpecDataType.XCaliburRun:
reader = new XCaliburReader(filePath);
break;
case MassSpecDataType.MzMLFile:
reader = new MzMLReader(filePath);
break;
case MassSpecDataType.PbfFile:
reader = new PbfLcMsRun(filePath);
break;
case MassSpecDataType.DeconvolutedPbfFile:
reader = new DPbfLcMsRun(filePath);
break;
case MassSpecDataType.Unknown:
if (_pwizAvailable)
{
reader = new ProteoWizardReader(filePath);
}
else
{
ConsoleMsgUtils.ShowWarning(string.Format("WARNING: Could not find a reader for file \"{0}\"." +
" Is MSFileReader and/or ProteoWizard installed?", filePath));
}
break;
}
return(reader);
}
public void CompareRtFusion()
{
var methodName = MethodBase.GetCurrentMethod().Name;
TestUtils.ShowStarting(methodName);
// Fusion
const string qeDdaResult = @"D:\Research\Data\UW\Fusion\DDA_Summary.tsv";
const string qeDiaResult = @"D:\Research\Data\UW\Fusion\DIA_Summary.tsv";
const string specFileDda = @"D:\Research\Data\UW\Fusion\WT_D_DDA_130412065618.raw";
var ddaReader = new XCaliburReader(specFileDda);
const string specFileDia = @"D:\Research\Data\UW\Fusion\WT_D_DIA_130412091220.raw";
var diaReader = new XCaliburReader(specFileDia);
const string resultPath1 = qeDdaResult;
const string resultPath2 = qeDiaResult;
var result1 = new TsvFileParser(resultPath1);
var result2 = new TsvFileParser(resultPath2);
const double pepQValueThreshold = 0.01;
var vennDiagram = new VennDiagram<string>(result1.GetPeptides(pepQValueThreshold),
result2.GetPeptides(pepQValueThreshold));
var intersectionPeptides = vennDiagram.Intersection;
var result1Peptides = result1.GetData("Peptide");
var result1ScanNums = result1.GetData("ScanNum");
var result2Peptides = result2.GetData("Peptide");
var result2ScanNums = result2.GetData("ScanNum");
Console.WriteLine("Peptide\tScanNum1\tScanNum2\tRt1\tRt2");
foreach (var peptide in intersectionPeptides)
{
var index1 = result1Peptides.IndexOf(peptide);
var index2 = result2Peptides.IndexOf(peptide);
var scanNum1 = Convert.ToInt32(result1ScanNums[index1]);
var scanNum2 = Convert.ToInt32(result2ScanNums[index2]);
var reader1 = ddaReader;
var reader2 = diaReader;
Console.WriteLine("{0}\t{1}\t{2}\t{3}\t{4}", peptide.Replace("C+57.021", "C"), scanNum1, scanNum2, reader1.RtFromScanNum(scanNum1), reader2.RtFromScanNum(scanNum2));
}
}
public void CompareRt()
{
var methodName = MethodBase.GetCurrentMethod().Name;
TestUtils.ShowStarting(methodName);
// Q-Exactive
//const string qeDdaResult = @"D:\Research\Data\UW\QExactive\DDA_All_Summary.tsv";
//const string qeDiaResult = @"D:\Research\Data\UW\QExactive\DIA_All_Summary.tsv";
// Fusion
const string qeDdaResult = @"D:\Research\Data\UW\Fusion\DDA_Summary.tsv";
const string qeDiaResult = @"D:\Research\Data\UW\Fusion\DIA_Summary.tsv";
const string specFileDda = @"D:\Research\Data\UW\QExactive\82593_lv_mcx_DDA.raw";
var ddaReader = new XCaliburReader(specFileDda);
var specFileToReader = new Dictionary<string, XCaliburReader>();
var specFilesDia = Directory.GetFiles(@"D:\Research\Data\UW\QExactive\", "*_DIA_*.raw");
foreach (var specFile in specFilesDia)
{
var specFileNoExt = Path.GetFileNameWithoutExtension(specFile);
if (specFileNoExt == null) continue;
var reader = new XCaliburReader(specFile);
specFileToReader.Add(specFileNoExt, reader);
}
const string resultPath1 = qeDdaResult;
const string resultPath2 = qeDiaResult;
var result1 = new TsvFileParser(resultPath1);
var result2 = new TsvFileParser(resultPath2);
const double pepQValueThreshold = 0.01;
var vennDiagram = new VennDiagram<string>(result1.GetPeptides(pepQValueThreshold),
result2.GetPeptides(pepQValueThreshold));
var intersectionPeptides = vennDiagram.Intersection;
var result1Peptides = result1.GetData("Peptide");
var result1ScanNums = result1.GetData("ScanNum");
var result2Peptides = result2.GetData("Peptide");
var result2ScanNums = result2.GetData("ScanNum");
var result2SpecFile = result2.GetData("#SpecFile");
Console.WriteLine("Peptide\tScanNum1\tScanNum2\tRt1\tRt2");
foreach (var peptide in intersectionPeptides)
{
var index1 = result1Peptides.IndexOf(peptide);
var index2 = result2Peptides.IndexOf(peptide);
var scanNum1 = Convert.ToInt32(result1ScanNums[index1]);
var scanNum2 = Convert.ToInt32(result2ScanNums[index2]);
var diaFile = Path.GetFileNameWithoutExtension(result2SpecFile[index2]);
var reader1 = ddaReader;
var reader2 = specFileToReader[diaFile];
Console.WriteLine("{0}\t{1}\t{2}\t{3}\t{4}", peptide.Replace("C+57.021", "C"), scanNum1, scanNum2, reader1.RtFromScanNum(scanNum1), reader2.RtFromScanNum(scanNum2));
}
}
public void TestReadingCorruptedRawFile()
{
var methodName = MethodBase.GetCurrentMethod().Name;
TestUtils.ShowStarting(methodName);
const string rawFilePath = @"\\proto-2\UnitTest_Files\InformedProteomics_TestFiles\Corrupted\YS_Shew_testHCD_CID.raw";
if (!File.Exists(rawFilePath))
{
Assert.Ignore(@"Skipping test {0} since file not found: {1}", methodName, rawFilePath);
}
var reader = new XCaliburReader(rawFilePath);
reader.ReadMassSpectrum(17957);
try
{
reader.ReadMassSpectrum(17957);
}
catch (System.Runtime.InteropServices.COMException e)
{
Console.WriteLine(e.Message);
}
Console.Write("Done");
}
public void TestXCaliburReader()
{
var methodName = MethodBase.GetCurrentMethod().Name;
TestUtils.ShowStarting(methodName);
var xcaliburReader = new XCaliburReader(TestTopDownRawFilePathCid);
var scans = new[] {423, 425};
foreach (var scan in scans)
{
var spec = xcaliburReader.ReadMassSpectrum(scan) as ProductSpectrum;
Assert.True(spec != null);
var isolationWindow = spec.IsolationWindow;
Console.WriteLine("MsLevel: {0}", spec.MsLevel);
Console.WriteLine("ActivationMethod: {0}", spec.ActivationMethod);
Console.WriteLine("Rt: {0}", spec.ElutionTime);
Console.WriteLine("IsolationWindowTargetMz: {0}", isolationWindow.IsolationWindowTargetMz);
Console.WriteLine("IsolationWindowLowerOffset: {0}", isolationWindow.IsolationWindowLowerOffset);
Console.WriteLine("IsolationWindowUpperOffset: {0}", isolationWindow.IsolationWindowUpperOffset);
Console.WriteLine("MonoisotopicMz: {0}", isolationWindow.MonoisotopicMz);
Console.WriteLine("PrecursorCharge: {0}", isolationWindow.Charge);
}
}
public void GeneratePrmInfo(string resultFilePath, string outputFilePath)
{
Console.Write("Processing {0}", Path.GetFileName(resultFilePath));
Console.Out.Flush();
var rawFilePath =
@"D:\Research\Data\EDRN\DDA\raw\" + Path.GetFileNameWithoutExtension(resultFilePath) + ".raw";
var reader = new XCaliburReader(rawFilePath);
var run = InMemoryLcMsRun.GetLcMsRun(rawFilePath);
var tolerance = new Tolerance(10, ToleranceUnit.Ppm);
const string spikedInPeptideFile = @"D:\Research\Data\EDRN\SpikedPeptides.txt";
var spikedInPeptides = File.ReadAllLines(spikedInPeptideFile);
var spikedInPepSet = new HashSet<string>();
foreach (var p in spikedInPeptides)
{
spikedInPepSet.Add(p);
}
// const string resultFilePath = @"D:\Research\Data\EDRN\DDA\Frac7_NTT2.tsv";
//const string resultFilePath = @"D:\Research\Data\EDRN\DDA\Heavy\342865_EDRN_Serum_07_DDA_1_12Nov13_Samwise_13-07-28.tsv";
// const string resultFilePath = @"D:\Research\Data\EDRN\DDA\NTT1_NoMod\342865_EDRN_Serum_07_DDA_1_12Nov13_Samwise_13-07-28.tsv";
const double qValueThreshold = 0.01;
var pepSet = new HashSet<string>();
MsGfPlusHeaderInformation headerInfo = null;
//var prefix = new HashSet<string>();
//var suffix = new HashSet<string>();
var numPeptides = 0;
var prevScanNum = -1;
using (var writer = new StreamWriter(outputFilePath))
{
writer.WriteLine("Peptide\tCharge\tMonoMz\tMostAbundantMz\tMs2ScanNum\tRtMs2\tRtApex\tRtStart\tRtEnd\tSpecEValue\tPepQValue");
foreach (var line in File.ReadLines(resultFilePath))
{
if (line.StartsWith("#"))
{
headerInfo = new MsGfPlusHeaderInformation(line);
continue;
}
var match = new MsGfMatch(line, headerInfo);
if (match.ScanNum == prevScanNum) continue;
prevScanNum = match.ScanNum;
if (!match.IsValid || match.Protein.StartsWith(FastaDatabase.DecoyProteinPrefix)) continue;
if (match.PepQValue > qValueThreshold) continue;
var peptide = match.Peptide.Replace("C+57.021", "C").Replace("K+8.014", "K").Replace("R+10.008", "R");
if (pepSet.Contains(peptide)) continue;
pepSet.Add(peptide);
if (spikedInPepSet.Contains(peptide))
{
var ion = new Ion(match.Formula, match.Charge);
var mostAbundantIonMz = ion.GetMostAbundantIsotopeMz();
var xic = run.GetPrecursorExtractedIonChromatogram(mostAbundantIonMz, tolerance, match.ScanNum);
if (xic.Count == 0) continue;
var minScan = xic.Min().ScanNum;
var maxScan = xic.Max().ScanNum;
writer.WriteLine("{0}\t{1}\t{2}\t{3}\t{4}\t{5}\t{6}\t{7}\t{8}\t{9}\t{10}",
peptide,
match.Charge,
ion.GetMonoIsotopicMz(),
mostAbundantIonMz,
match.ScanNum,
reader.RtFromScanNum(match.ScanNum),
reader.RtFromScanNum(xic.GetApexScanNum()), // Rt apex
reader.RtFromScanNum(minScan), // Rt start
reader.RtFromScanNum(maxScan), // Rt end
match.SpecEValue,
match.PepQValue);
++numPeptides;
}
//else
//{
// foreach (var spikedInPeptide in spikedInPeptides)
// {
// if (spikedInPeptide.StartsWith(peptide)) prefix.Add(spikedInPeptide + "\t" + peptide + "\t" + match.ScanNum);
// else if (spikedInPeptide.EndsWith(peptide)) suffix.Add(spikedInPeptide + "\t" + peptide + "\t" + match.ScanNum);
// }
//}
}
}
//Console.WriteLine("*********Prefix");
//foreach(var p in prefix) Console.WriteLine(p);
//Console.WriteLine("*********Suffix");
//foreach (var p in suffix) Console.WriteLine(p);
Console.WriteLine("\t{0}", numPeptides);
}