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.MS2ChildScanDissociationType == DissociationType.LowCID || commonParameters.MS3ChildScanDissociationType == 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
{
MyMsDataFiles[origDataFile] = ThermoRawFileReaderData.LoadAllStaticData(origDataFile, filter, commonParameters.MaxThreadsToUsePerFile);
}
return(MyMsDataFiles[origDataFile]);
}
}
public static void TestLoadMgf()
{
try
{
Mgf.LoadAllStaticData(Path.Combine(TestContext.CurrentContext.TestDirectory, "DataFiles", "ThereIsNothingHerePleaseDoNotGenerateThisFile.mgf"));
Assert.IsTrue(false);
}
catch
{
//woohoo, there was an exception!
}
Mgf a = Mgf.LoadAllStaticData(Path.Combine(TestContext.CurrentContext.TestDirectory, "DataFiles", "tester.mgf"));
var ya = a.GetOneBasedScan(14);
Assert.AreEqual(192, ya.MassSpectrum.Size);
Assert.AreEqual(2, ya.MsnOrder);
Assert.AreEqual(14, ya.OneBasedScanNumber);
Assert.AreEqual(MassSpectrometry.Polarity.Positive, ya.Polarity);
Assert.AreEqual(0.26666666666666666, ya.RetentionTime);
Assert.AreEqual(571.806916, ya.IsolationMz);
Assert.AreEqual(571.806916, ya.SelectedIonMZ);
Assert.AreEqual(2, ya.SelectedIonChargeStateGuess);
Assert.AreEqual(571.806916, ya.SelectedIonMonoisotopicGuessMz);
Assert.AreEqual(1294963.5999999996, ya.TotalIonCurrent);
Assert.AreEqual(110.0719, ya.ScanWindowRange.Minimum);
Assert.AreEqual(1038.8018, ya.ScanWindowRange.Maximum);
var ya2 = a.GetOneBasedScan(20).MassSpectrum;
Assert.AreEqual(165, ya2.Size);
var ya3 = a.GetOneBasedScan(2).MassSpectrum;
Assert.AreEqual(551, ya3.Size);
}
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 void TestFolderMgfs()
{
// Get temp path for writing the test MGF
var tempFilePath = Path.Combine(Path.GetTempPath(), Path.GetRandomFileName());
Directory.CreateDirectory(tempFilePath);
var testRawFolder = Path.Combine(AppDomain.CurrentDomain.BaseDirectory, @"Data/TestFolderMgfs");
var parseInput = new ParseInput(null, testRawFolder, tempFilePath, OutputFormat.MGF);
RawFileParser.Parse(parseInput);
var numFiles = Directory.GetFiles(tempFilePath, "*.mgf");
Assert.AreEqual(numFiles.Length, 2);
var mgfData = Mgf.LoadAllStaticData(Path.Combine(tempFilePath, "small1.mgf"));
Assert.AreEqual(34, mgfData.NumSpectra);
var mgfData2 = Mgf.LoadAllStaticData(Path.Combine(tempFilePath, "small2.mgf"));
Assert.AreEqual(34, mgfData2.NumSpectra);
Directory.Delete(tempFilePath, true);
}
public void TestMgf()
{
// Get temp path for writing the test MGF
var tempFilePath = Path.GetTempPath();
var testRawFile = Path.Combine(AppDomain.CurrentDomain.BaseDirectory, @"Data/small.RAW");
var parseInput = new ParseInput(testRawFile, null, tempFilePath, OutputFormat.MGF);
RawFileParser.Parse(parseInput);
var mgfData = Mgf.LoadAllStaticData(Path.Combine(tempFilePath, "small.mgf"));
Assert.AreEqual(34, mgfData.NumSpectra);
}
public static void TestLoadCorruptMgf()
{
//tester_corrupt.mgf is extracted from tester.mgf except it contains empty lines or unknow words. You can compare the two files and find the differences.
Mgf a = Mgf.LoadAllStaticData(Path.Combine(TestContext.CurrentContext.TestDirectory, "DataFiles", "tester_corrupt.mgf"));
var ya = a.GetOneBasedScan(14);
Assert.AreEqual(192, ya.MassSpectrum.Size);
Assert.AreEqual(2, ya.MsnOrder);
Assert.AreEqual(14, ya.OneBasedScanNumber);
Assert.AreEqual(MassSpectrometry.Polarity.Positive, ya.Polarity);
Assert.AreEqual(0.26666666666666666, ya.RetentionTime);
Assert.AreEqual(571.806916, ya.IsolationMz);
Assert.AreEqual(571.806916, ya.SelectedIonMZ);
Assert.AreEqual(2, ya.SelectedIonChargeStateGuess);
Assert.AreEqual(571.806916, ya.SelectedIonMonoisotopicGuessMz);
Assert.AreEqual(1294963.5999999996, ya.TotalIonCurrent);
Assert.AreEqual(110.0719, ya.ScanWindowRange.Minimum);
Assert.AreEqual(1038.8018, ya.ScanWindowRange.Maximum);
}
public void TestMgf()
{
// Get temp path for writing the test MGF
var tempFilePath = Path.GetTempPath();
var testRawFile = Path.Combine(AppDomain.CurrentDomain.BaseDirectory, @"small.RAW");
var parseInput = new ParseInput(testRawFile, tempFilePath, null, OutputFormat.MGF);
RawFileParser.Parse(parseInput);
// Do this for the mzLib library issue
var tempFileName = Path.GetTempPath() + "elements.dat";
Loaders.LoadElements(tempFileName);
var mgfData = Mgf.LoadAllStaticData(Path.Combine(tempFilePath, "small.mgf"));
Assert.AreEqual(34, mgfData.NumSpectra);
}
public void TestMgf()
{
// Get temp path for writing the test MGF
var tempFilePath = Path.GetTempPath();
var testRawFile = Path.Combine(AppDomain.CurrentDomain.BaseDirectory, @"small.RAW");
var parseInput = new ParseInput(testRawFile, tempFilePath, OutputFormat.Mgf, false, MetadataFormat.NON, false,
"coll",
"run", "sub");
RawFileParser.Parse(parseInput);
// Do this for the mzLib library issue
var tempFileName = Path.GetTempPath() + "elements.dat";
UsefulProteomicsDatabases.Loaders.LoadElements(tempFileName);
var mgfData = Mgf.LoadAllStaticData(Path.Combine(tempFilePath, "small.mgf"));
Assert.AreEqual(34, mgfData.NumSpectra);
Assert.IsEmpty(mgfData.GetMS1Scans());
}
public static List <ScanHeaderInfo> FileScanHeaderInfo(string fullFilePathWithExtension)
{
string filename = Path.GetFileName(fullFilePathWithExtension);
List <ScanHeaderInfo> scanHeaderInfoList = new();
switch (GetDataFileType(fullFilePathWithExtension))
{
case DataFileType.Thermo:
ThermoRawFileReader staticRaw = ThermoRawFileReader.LoadAllStaticData(fullFilePathWithExtension);
foreach (MsDataScan item in staticRaw)
{
scanHeaderInfoList.Add(new ScanHeaderInfo(fullFilePathWithExtension, filename, item.OneBasedScanNumber, item.RetentionTime));
}
break;
case DataFileType.mzML:
List <MsDataScan> mzmlDataScans = Mzml.LoadAllStaticData(fullFilePathWithExtension).GetAllScansList();
foreach (MsDataScan item in mzmlDataScans)
{
scanHeaderInfoList.Add(new ScanHeaderInfo(fullFilePathWithExtension, filename, item.OneBasedScanNumber, item.RetentionTime));
}
break;
case DataFileType.mgf:
List <MsDataScan> mgfDataScans = Mgf.LoadAllStaticData(fullFilePathWithExtension).GetAllScansList();
foreach (MsDataScan item in mgfDataScans)
{
scanHeaderInfoList.Add(new ScanHeaderInfo(fullFilePathWithExtension, filename, item.OneBasedScanNumber, item.RetentionTime));
}
break;
case DataFileType.unknown:
default:
break;
}
return(scanHeaderInfoList);
}
public static void TestDynamicMgf(string fileName)
{
string filePath = Path.Combine(TestContext.CurrentContext.TestDirectory, "DataFiles", fileName);
Mgf staticMgf = Mgf.LoadAllStaticData(filePath);
MgfDynamicData dynamicMgf = new MgfDynamicData(filePath);
foreach (MsDataScan staticScan in staticMgf.GetAllScansList())
{
MsDataScan dynamicScan = dynamicMgf.GetOneBasedScanFromDynamicConnection(staticScan.OneBasedScanNumber);
Assert.That(dynamicScan.OneBasedScanNumber == staticScan.OneBasedScanNumber);
Assert.That(dynamicScan.MsnOrder == staticScan.MsnOrder);
if (!double.IsNaN(dynamicScan.RetentionTime) || !double.IsNaN(staticScan.RetentionTime))
{
Assert.That(dynamicScan.RetentionTime == staticScan.RetentionTime);
}
Assert.That(dynamicScan.Polarity == staticScan.Polarity);
Assert.That(dynamicScan.ScanWindowRange.Minimum == staticScan.ScanWindowRange.Minimum);
Assert.That(dynamicScan.ScanWindowRange.Maximum == staticScan.ScanWindowRange.Maximum);
Assert.That(dynamicScan.ScanFilter == staticScan.ScanFilter);
Assert.That(dynamicScan.NativeId == staticScan.NativeId);
Assert.That(dynamicScan.IsCentroid == staticScan.IsCentroid);
Assert.That(dynamicScan.IsCentroid == staticScan.IsCentroid);
Assert.That(dynamicScan.InjectionTime == staticScan.InjectionTime);
Assert.That(dynamicScan.NoiseData == staticScan.NoiseData);
Assert.That(dynamicScan.IsolationMz == staticScan.IsolationMz);
Assert.That(dynamicScan.SelectedIonChargeStateGuess == staticScan.SelectedIonChargeStateGuess);
Assert.That(dynamicScan.SelectedIonIntensity == staticScan.SelectedIonIntensity);
Assert.That(dynamicScan.SelectedIonMZ == staticScan.SelectedIonMZ);
Assert.That(dynamicScan.DissociationType == staticScan.DissociationType);
Assert.That(dynamicScan.IsolationWidth == staticScan.IsolationWidth);
Assert.That(dynamicScan.OneBasedPrecursorScanNumber == staticScan.OneBasedPrecursorScanNumber);
Assert.That(dynamicScan.SelectedIonMonoisotopicGuessIntensity == staticScan.SelectedIonMonoisotopicGuessIntensity);
Assert.That(dynamicScan.SelectedIonMonoisotopicGuessMz == staticScan.SelectedIonMonoisotopicGuessMz);
if (dynamicScan.IsolationRange != null || staticScan.IsolationRange != null)
{
Assert.That(dynamicScan.IsolationRange.Minimum == staticScan.IsolationRange.Minimum);
Assert.That(dynamicScan.IsolationRange.Maximum == staticScan.IsolationRange.Maximum);
}
Assert.That(dynamicScan.MassSpectrum.XArray.Length == staticScan.MassSpectrum.XArray.Length);
Assert.That(dynamicScan.MassSpectrum.YArray.Length == staticScan.MassSpectrum.YArray.Length);
for (int i = 0; i < staticScan.MassSpectrum.XArray.Length; i++)
{
double staticMz = staticScan.MassSpectrum.XArray[i];
double staticIntensity = staticScan.MassSpectrum.YArray[i];
double dynamicMz = dynamicScan.MassSpectrum.XArray[i];
double dynamicIntensity = dynamicScan.MassSpectrum.YArray[i];
Assert.That(dynamicMz == staticMz);
Assert.That(dynamicIntensity == staticIntensity);
}
}
}
