/** {@inheritDoc} */
@SuppressWarnings("null")
@Override
public RawDataFile execute() throws MSDKException {
String osName = System.getProperty("os.name").toUpperCase();
if (!osName.contains("WINDOWS")) {
throw new MSDKException("Native data format import only works on MS Windows");
}
logger.info("Started parsing file " + sourceFile);
try {
// Decompress the thermo raw dump executable to a temporary folder
File tempFolder = Files.createTempDirectory("msdk").toFile();
tempFolder.deleteOnExit();
InputStream dumpArchive =
this.getClass().getClassLoader().getResourceAsStream("thermorawdump.zip");
if (dumpArchive == null)
throw new MSDKException("Failed to load the thermorawdump.zip archive from the MSDK jar");
ZipUtils.extractStreamToFolder(dumpArchive, tempFolder);
// Path to the rawdump executable
File rawDumpPath = new File(tempFolder, "ThermoRawDump.exe");
if (!rawDumpPath.canExecute())
throw new MSDKException("Cannot execute program " + rawDumpPath);
// Create a separate process and execute RAWdump.exe
final String cmdLine[] = new String[] {rawDumpPath.getPath(), sourceFile.getPath()};
dumperProcess = Runtime.getRuntime().exec(cmdLine);
// Get the stdout of RAWdump process as InputStream
InputStream dumpStream = dumperProcess.getInputStream();
// Create the new RawDataFile
String fileName = sourceFile.getName();
newRawFile = MSDKObjectBuilder.getRawDataFile(fileName, sourceFile, fileType, dataStore);
// Read the dump data
parser = new RawDumpParser(newRawFile, dataStore);
parser.readRAWDump(dumpStream);
// Cleanup
dumpStream.close();
dumperProcess.destroy();
try {
FileUtils.deleteDirectory(tempFolder);
} catch (IOException e) {
// Ignore errors while deleting the tmp folder
}
if (canceled) return null;
} catch (Throwable e) {
if (dumperProcess != null) dumperProcess.destroy();
throw new MSDKException(e);
}
logger.info("Finished parsing " + sourceFile);
return newRawFile;
}
/**
* {@inheritDoc}
*
* <p>endElement()
*/
@SuppressWarnings("null")
public void endElement(String namespaceURI, String sName, String qName) throws SAXException {
if (canceled) throw new SAXException("Parsing Cancelled");
// <spectrumInstrument>
if (qName.equalsIgnoreCase("spectrumInstrument")) {
spectrumInstrumentFlag = false;
}
// <precursor>
if (qName.equalsIgnoreCase("precursor")) {
precursorFlag = false;
}
// <spectrum>
if (qName.equalsIgnoreCase("spectrum")) {
spectrumInstrumentFlag = false;
// Auto-detect whether this scan is centroided
MsSpectrumType spectrumType =
SpectrumTypeDetectionAlgorithm.detectSpectrumType(mzBuffer, intensityBuffer, peaksCount);
// Create a new scan
MsFunction msFunction = MSDKObjectBuilder.getMsFunction(msLevel);
MsScan newScan = MSDKObjectBuilder.getMsScan(dataStore, scanNumber, msFunction);
newScan.setDataPoints(mzBuffer, intensityBuffer, peaksCount);
newScan.setSpectrumType(spectrumType);
newScan.setPolarity(polarity);
if (retentionTime != null) {
ChromatographyInfo chromInfo =
MSDKObjectBuilder.getChromatographyInfo1D(SeparationType.UNKNOWN, retentionTime);
newScan.setChromatographyInfo(chromInfo);
}
if (precursorMz != null) {
IsolationInfo isolation =
MSDKObjectBuilder.getIsolationInfo(
Range.singleton(precursorMz), null, precursorMz, precursorCharge, null);
newScan.getIsolations().add(isolation);
}
// Add the scan to the file
newRawFile.addScan(newScan);
parsedScans++;
}
// <mzArrayBinary>
if (qName.equalsIgnoreCase("mzArrayBinary")) {
mzArrayBinaryFlag = false;
// Allocate space for the whole array
if (mzBuffer.length < peaksCount) mzBuffer = new double[peaksCount * 2];
byte[] peakBytes = Base64.decodeBase64(charBuffer.toString().getBytes());
ByteBuffer currentMzBytes = ByteBuffer.wrap(peakBytes);
if (endian.equals("big")) {
currentMzBytes = currentMzBytes.order(ByteOrder.BIG_ENDIAN);
} else {
currentMzBytes = currentMzBytes.order(ByteOrder.LITTLE_ENDIAN);
}
for (int i = 0; i < peaksCount; i++) {
if (precision == null || precision.equals("32"))
mzBuffer[i] = (double) currentMzBytes.getFloat();
else mzBuffer[i] = currentMzBytes.getDouble();
}
}
// <intenArrayBinary>
if (qName.equalsIgnoreCase("intenArrayBinary")) {
intenArrayBinaryFlag = false;
// Allocate space for the whole array
if (intensityBuffer.length < peaksCount) intensityBuffer = new float[peaksCount * 2];
byte[] peakBytes = Base64.decodeBase64(charBuffer.toString().getBytes());
ByteBuffer currentIntensityBytes = ByteBuffer.wrap(peakBytes);
if (endian.equals("big")) {
currentIntensityBytes = currentIntensityBytes.order(ByteOrder.BIG_ENDIAN);
} else {
currentIntensityBytes = currentIntensityBytes.order(ByteOrder.LITTLE_ENDIAN);
}
for (int i = 0; i < peaksCount; i++) {
if (precision == null || precision.equals("32"))
intensityBuffer[i] = currentIntensityBytes.getFloat();
else intensityBuffer[i] = (float) currentIntensityBytes.getDouble();
}
}
}
@SuppressWarnings("null")
@Test
public void testOrbitrap() throws MSDKException {
// Create the data structures
final DataPointStore dataStore = DataPointStoreFactory.getMemoryDataStore();
// Import the file
File inputFile = new File(TEST_DATA_PATH + "orbitrap_300-600mz.mzML");
Assert.assertTrue("Cannot read test data", inputFile.canRead());
MzMLFileImportMethod importer = new MzMLFileImportMethod(inputFile);
RawDataFile rawFile = importer.execute();
Assert.assertNotNull(rawFile);
Assert.assertEquals(1.0, importer.getFinishedPercentage(), 0.0001);
// Ion 1
List<IonAnnotation> ionAnnotations = new ArrayList<IonAnnotation>();
IonAnnotation ion1 = MSDKObjectBuilder.getSimpleIonAnnotation();
ion1.setExpectedMz(332.56);
ion1.setAnnotationId("Feature 332.56");
ion1.setChromatographyInfo(
MSDKObjectBuilder.getChromatographyInfo1D(SeparationType.LC, (float) 772.8));
ionAnnotations.add(ion1);
// Ion 2
IonAnnotation ion2 = MSDKObjectBuilder.getSimpleIonAnnotation();
ion2.setExpectedMz(508.004);
ion2.setAnnotationId("Feature 508.004");
ion2.setChromatographyInfo(
MSDKObjectBuilder.getChromatographyInfo1D(SeparationType.LC, (float) 868.8));
ionAnnotations.add(ion2);
// Ion 3
IonAnnotation ion3 = MSDKObjectBuilder.getSimpleIonAnnotation();
ion3.setExpectedMz(362.102);
ion3.setAnnotationId("Feature 362.102");
ion3.setChromatographyInfo(
MSDKObjectBuilder.getChromatographyInfo1D(SeparationType.LC, (float) 643.2));
ionAnnotations.add(ion3);
// Variables
final MZTolerance mzTolerance = new MZTolerance(0.003, 5.0);
final RTTolerance rtTolerance = new RTTolerance(3, false);
final Double intensityTolerance = 0.10d;
final Double noiseLevel = 5000d;
TargetedDetectionMethod chromBuilder =
new TargetedDetectionMethod(
ionAnnotations,
rawFile,
dataStore,
mzTolerance,
rtTolerance,
intensityTolerance,
noiseLevel);
final List<Chromatogram> chromatograms = chromBuilder.execute();
Assert.assertEquals(1.0, chromBuilder.getFinishedPercentage(), 0.0001);
Assert.assertNotNull(chromatograms);
Assert.assertEquals(3, chromatograms.size());
// Create a new feature table
FeatureTable featureTable = MSDKObjectBuilder.getFeatureTable("orbitrap_300-600mz", dataStore);
Sample sample = MSDKObjectBuilder.getSimpleSample("orbitrap_300-600mz");
ChromatogramToFeatureTableMethod tableBuilder =
new ChromatogramToFeatureTableMethod(chromatograms, featureTable, sample);
tableBuilder.execute();
// 1. Filter parameters
boolean filterByMz = true;
boolean filterByRt = true;
boolean filterByDuration = true;
boolean filterByCount = true;
boolean filterByIsotopes = true;
boolean filterByIonAnnotation = true;
boolean requireAnnotation = false;
boolean removeDuplicates = false;
boolean duplicateRequireSameID = true;
Range<Double> mzRange = Range.closed(300.0, 600.0);
Range<Double> rtRange = Range.closed(600.0, 900.0); // Seconds
Range<Double> durationRange = Range.closed(0.0, 47.0); // Seconds
final MZTolerance duplicateMzTolerance = new MZTolerance(0.003, 5.0);
final RTTolerance duplicateRtTolerance = new RTTolerance(0.2, false);
int minCount = 1;
int minIsotopes = 1;
String ionAnnotation = null;
String nameSuffix = "-rowFiltered";
// 1. Filter the rows
RowFilterMethod filterMethod =
new RowFilterMethod(
featureTable,
dataStore,
nameSuffix,
filterByMz,
filterByRt,
filterByDuration,
filterByCount,
filterByIsotopes,
filterByIonAnnotation,
requireAnnotation,
mzRange,
rtRange,
durationRange,
minCount,
minIsotopes,
ionAnnotation,
removeDuplicates,
duplicateMzTolerance,
duplicateRtTolerance,
duplicateRequireSameID);
filterMethod.execute();
Assert.assertEquals(1.0, filterMethod.getFinishedPercentage(), 0.0001);
// 1. Verify data
FeatureTable filteredTable = filterMethod.getResult();
Assert.assertNotNull(filteredTable);
Assert.assertEquals(3, filteredTable.getRows().size());
// 2. Filter parameters
mzRange = Range.closed(350.0, 600.0);
durationRange = Range.closed(46.0, 47.0); // Seconds
// 2. Filter the features
filterMethod =
new RowFilterMethod(
featureTable,
dataStore,
nameSuffix,
filterByMz,
filterByRt,
filterByDuration,
filterByCount,
filterByIsotopes,
filterByIonAnnotation,
requireAnnotation,
mzRange,
rtRange,
durationRange,
minCount,
minIsotopes,
ionAnnotation,
removeDuplicates,
duplicateMzTolerance,
duplicateRtTolerance,
duplicateRequireSameID);
filterMethod.execute();
Assert.assertEquals(1.0, filterMethod.getFinishedPercentage(), 0.0001);
// 2. Verify data
filteredTable = filterMethod.getResult();
Assert.assertNotNull(filteredTable);
Assert.assertEquals(1, filteredTable.getRows().size());
// 3. Filter parameters
minCount = 2;
// 3. Filter the features
filterMethod =
new RowFilterMethod(
filteredTable,
dataStore,
nameSuffix,
filterByMz,
filterByRt,
filterByDuration,
filterByCount,
filterByIsotopes,
filterByIonAnnotation,
requireAnnotation,
mzRange,
rtRange,
durationRange,
minCount,
minIsotopes,
ionAnnotation,
removeDuplicates,
duplicateMzTolerance,
duplicateRtTolerance,
duplicateRequireSameID);
filterMethod.execute();
Assert.assertEquals(1.0, filterMethod.getFinishedPercentage(), 0.0001);
// 3. Verify data
filteredTable = filterMethod.getResult();
Assert.assertNotNull(filteredTable);
Assert.assertEquals(0, filteredTable.getRows().size());
featureTable.dispose();
filteredTable.dispose();
}
@Override
public MsScan performFilter(MsScan scan) {
if (!Avalues.containsKey(numOfDataPoints) || !Hvalues.containsKey(numOfDataPoints)) {
return scan;
}
int[] aVals = Avalues.get(numOfDataPoints);
int h = Hvalues.get(numOfDataPoints);
int marginSize = (numOfDataPoints + 1) / 2 - 1;
float sumOfInts;
// Create data point list object and fill it with the scan data points
MsSpectrumDataPointList dataPoints = MSDKObjectBuilder.getMsSpectrumDataPointList();
scan.getDataPoints(dataPoints);
float intensityValues[] = dataPoints.getIntensityBuffer();
double mzValues[] = dataPoints.getMzBuffer();
int newDataPointsLength = dataPoints.getSize() - (marginSize * 2);
// only process MS level 1 scans
if (scan.getMsFunction().getMsLevel() != 1) {
return scan;
}
// only process scans with datapoints
if (newDataPointsLength < 1) {
return scan;
}
MsSpectrumDataPointList newDataPoints = MSDKObjectBuilder.getMsSpectrumDataPointList();
for (int spectrumInd = marginSize;
spectrumInd < (dataPoints.getSize() - marginSize);
spectrumInd++) {
// zero intensity data points must be left unchanged
if (intensityValues[spectrumInd] == 0) {
intensityValues[spectrumInd - marginSize] = intensityValues[spectrumInd];
continue;
}
sumOfInts = aVals[0] * intensityValues[spectrumInd];
for (int windowInd = 1; windowInd <= marginSize; windowInd++) {
sumOfInts +=
aVals[windowInd]
* (intensityValues[spectrumInd + windowInd]
+ intensityValues[spectrumInd - windowInd]);
}
sumOfInts = sumOfInts / h;
if (sumOfInts < 0) {
sumOfInts = 0;
}
newDataPoints.add(mzValues[spectrumInd], sumOfInts);
}
// Return a new scan with the new data points
MsScan result = MSDKObjectBuilder.getMsScan(store, scan.getScanNumber(), scan.getMsFunction());
result.setDataPoints(newDataPoints);
result.setChromatographyInfo(scan.getChromatographyInfo());
result.setRawDataFile(scan.getRawDataFile());
return result;
}