use of net.sf.mzmine.datamodel.Feature in project mzmine2 by mzmine.
the class PeakFilterTask method copyPeakRow.
/**
* Create a copy of a feature list row.
*/
private static PeakListRow copyPeakRow(final PeakListRow row, final boolean[] keepPeak) {
// Copy the feature list row.
final PeakListRow newRow = new SimplePeakListRow(row.getID());
PeakUtils.copyPeakListRowProperties(row, newRow);
// Copy the peaks.
int i = 0;
for (final Feature peak : row.getPeaks()) {
// Only keep peak if it fulfills the filter criteria
if (keepPeak[i]) {
final Feature newPeak = new SimpleFeature(peak);
PeakUtils.copyPeakProperties(peak, newPeak);
newRow.addPeak(peak.getDataFile(), newPeak);
}
i++;
}
return newRow;
}
use of net.sf.mzmine.datamodel.Feature in project mzmine2 by mzmine.
the class RowsFilterTask method filterPeakListRows.
/**
* Filter the feature list rows.
*
* @param peakList feature list to filter.
* @return a new feature list with rows of the original feature list that pass the filtering.
*/
private PeakList filterPeakListRows(final PeakList peakList) {
// Create new feature list.
final PeakList newPeakList = new SimplePeakList(peakList.getName() + ' ' + parameters.getParameter(RowsFilterParameters.SUFFIX).getValue(), peakList.getRawDataFiles());
// Copy previous applied methods.
for (final PeakListAppliedMethod method : peakList.getAppliedMethods()) {
newPeakList.addDescriptionOfAppliedTask(method);
}
// Add task description to peakList.
newPeakList.addDescriptionOfAppliedTask(new SimplePeakListAppliedMethod(getTaskDescription(), parameters));
// Get parameters.
final boolean onlyIdentified = parameters.getParameter(RowsFilterParameters.HAS_IDENTITIES).getValue();
final boolean filterByIdentityText = parameters.getParameter(RowsFilterParameters.IDENTITY_TEXT).getValue();
final boolean filterByCommentText = parameters.getParameter(RowsFilterParameters.COMMENT_TEXT).getValue();
final String groupingParameter = (String) parameters.getParameter(RowsFilterParameters.GROUPSPARAMETER).getValue();
final boolean filterByMinPeakCount = parameters.getParameter(RowsFilterParameters.MIN_PEAK_COUNT).getValue();
final boolean filterByMinIsotopePatternSize = parameters.getParameter(RowsFilterParameters.MIN_ISOTOPE_PATTERN_COUNT).getValue();
final boolean filterByMzRange = parameters.getParameter(RowsFilterParameters.MZ_RANGE).getValue();
final boolean filterByRtRange = parameters.getParameter(RowsFilterParameters.RT_RANGE).getValue();
final boolean filterByDuration = parameters.getParameter(RowsFilterParameters.PEAK_DURATION).getValue();
final boolean filterByFWHM = parameters.getParameter(RowsFilterParameters.FWHM).getValue();
final boolean filterByCharge = parameters.getParameter(RowsFilterParameters.CHARGE).getValue();
final boolean filterByKMD = parameters.getParameter(RowsFilterParameters.KENDRICK_MASS_DEFECT).getValue();
final boolean filterByMS2 = parameters.getParameter(RowsFilterParameters.MS2_Filter).getValue();
final String removeRowString = parameters.getParameter(RowsFilterParameters.REMOVE_ROW).getValue();
Double minCount = parameters.getParameter(RowsFilterParameters.MIN_PEAK_COUNT).getEmbeddedParameter().getValue();
final boolean renumber = parameters.getParameter(RowsFilterParameters.Reset_ID).getValue();
int rowsCount = 0;
boolean removeRow = false;
if (removeRowString.equals(RowsFilterParameters.removeRowChoices[0]))
removeRow = false;
else
removeRow = true;
// Keep rows that don't match any criteria. Keep by default.
boolean filterRowCriteriaFailed = false;
// Handle < 1 values for minPeakCount
if ((minCount == null) || (minCount < 1))
minCount = 1.0;
// Round value down to nearest hole number
int intMinCount = minCount.intValue();
// Filter rows.
final PeakListRow[] rows = peakList.getRows();
totalRows = rows.length;
for (processedRows = 0; !isCanceled() && processedRows < totalRows; processedRows++) {
filterRowCriteriaFailed = false;
final PeakListRow row = rows[processedRows];
final int peakCount = getPeakCount(row, groupingParameter);
// Check number of peaks.
if (filterByMinPeakCount) {
if (peakCount < intMinCount)
filterRowCriteriaFailed = true;
}
// Check identities.
if (onlyIdentified) {
if (row.getPreferredPeakIdentity() == null)
filterRowCriteriaFailed = true;
}
// Check average m/z.
if (filterByMzRange) {
final Range<Double> mzRange = parameters.getParameter(RowsFilterParameters.MZ_RANGE).getEmbeddedParameter().getValue();
if (!mzRange.contains(row.getAverageMZ()))
filterRowCriteriaFailed = true;
}
// Check average RT.
if (filterByRtRange) {
final Range<Double> rtRange = parameters.getParameter(RowsFilterParameters.RT_RANGE).getEmbeddedParameter().getValue();
if (!rtRange.contains(row.getAverageRT()))
filterRowCriteriaFailed = true;
}
// Search peak identity text.
if (filterByIdentityText) {
if (row.getPreferredPeakIdentity() == null)
filterRowCriteriaFailed = true;
if (row.getPreferredPeakIdentity() != null) {
final String searchText = parameters.getParameter(RowsFilterParameters.IDENTITY_TEXT).getEmbeddedParameter().getValue().toLowerCase().trim();
int numFailedIdentities = 0;
PeakIdentity[] identities = row.getPeakIdentities();
for (int index = 0; !isCanceled() && index < identities.length; index++) {
String rowText = identities[index].getName().toLowerCase().trim();
if (!rowText.contains(searchText))
numFailedIdentities += 1;
}
if (numFailedIdentities == identities.length)
filterRowCriteriaFailed = true;
}
}
// Search peak comment text.
if (filterByCommentText) {
if (row.getComment() == null)
filterRowCriteriaFailed = true;
if (row.getComment() != null) {
final String searchText = parameters.getParameter(RowsFilterParameters.COMMENT_TEXT).getEmbeddedParameter().getValue().toLowerCase().trim();
final String rowText = row.getComment().toLowerCase().trim();
if (!rowText.contains(searchText))
filterRowCriteriaFailed = true;
}
}
// Calculate average duration and isotope pattern count.
int maxIsotopePatternSizeOnRow = 1;
double avgDuration = 0.0;
final Feature[] peaks = row.getPeaks();
for (final Feature p : peaks) {
final IsotopePattern pattern = p.getIsotopePattern();
if (pattern != null && maxIsotopePatternSizeOnRow < pattern.getNumberOfDataPoints()) {
maxIsotopePatternSizeOnRow = pattern.getNumberOfDataPoints();
}
avgDuration += RangeUtils.rangeLength(p.getRawDataPointsRTRange());
}
// Check isotope pattern count.
if (filterByMinIsotopePatternSize) {
final int minIsotopePatternSize = parameters.getParameter(RowsFilterParameters.MIN_ISOTOPE_PATTERN_COUNT).getEmbeddedParameter().getValue();
if (maxIsotopePatternSizeOnRow < minIsotopePatternSize)
filterRowCriteriaFailed = true;
}
// Check average duration.
avgDuration /= peakCount;
if (filterByDuration) {
final Range<Double> durationRange = parameters.getParameter(RowsFilterParameters.PEAK_DURATION).getEmbeddedParameter().getValue();
if (!durationRange.contains(avgDuration))
filterRowCriteriaFailed = true;
}
// Filter by FWHM range
if (filterByFWHM) {
final Range<Double> FWHMRange = parameters.getParameter(RowsFilterParameters.FWHM).getEmbeddedParameter().getValue();
// If any of the peaks fail the FWHM criteria,
Double FWHM_value = row.getBestPeak().getFWHM();
if (FWHM_value != null && !FWHMRange.contains(FWHM_value))
filterRowCriteriaFailed = true;
}
// Filter by charge range
if (filterByCharge) {
final Range<Integer> chargeRange = parameters.getParameter(RowsFilterParameters.CHARGE).getEmbeddedParameter().getValue();
int charge = row.getBestPeak().getCharge();
if (charge == 0 || !chargeRange.contains(charge))
filterRowCriteriaFailed = true;
}
// Filter by KMD or RKM range
if (filterByKMD) {
// get embedded parameters
final Range<Double> rangeKMD = parameters.getParameter(RowsFilterParameters.KENDRICK_MASS_DEFECT).getEmbeddedParameters().getParameter(KendrickMassDefectFilterParameters.kendrickMassDefectRange).getValue();
final String kendrickMassBase = parameters.getParameter(RowsFilterParameters.KENDRICK_MASS_DEFECT).getEmbeddedParameters().getParameter(KendrickMassDefectFilterParameters.kendrickMassBase).getValue();
final double shift = parameters.getParameter(RowsFilterParameters.KENDRICK_MASS_DEFECT).getEmbeddedParameters().getParameter(KendrickMassDefectFilterParameters.shift).getValue();
final int charge = parameters.getParameter(RowsFilterParameters.KENDRICK_MASS_DEFECT).getEmbeddedParameters().getParameter(KendrickMassDefectFilterParameters.charge).getValue();
final int divisor = parameters.getParameter(RowsFilterParameters.KENDRICK_MASS_DEFECT).getEmbeddedParameters().getParameter(KendrickMassDefectFilterParameters.divisor).getValue();
final boolean useRemainderOfKendrickMass = parameters.getParameter(RowsFilterParameters.KENDRICK_MASS_DEFECT).getEmbeddedParameters().getParameter(KendrickMassDefectFilterParameters.useRemainderOfKendrickMass).getValue();
// get m/z
Double valueMZ = row.getBestPeak().getMZ();
// calc exact mass of Kendrick mass base
double exactMassFormula = FormulaUtils.calculateExactMass(kendrickMassBase);
// calc exact mass of Kendrick mass factor
double kendrickMassFactor = Math.round(exactMassFormula / divisor) / (exactMassFormula / divisor);
double defectOrRemainder = 0.0;
if (!useRemainderOfKendrickMass) {
// calc Kendrick mass defect
defectOrRemainder = Math.ceil(charge * (valueMZ * kendrickMassFactor)) - charge * (valueMZ * kendrickMassFactor);
} else {
// calc Kendrick mass remainder
defectOrRemainder = (charge * (divisor - Math.round(FormulaUtils.calculateExactMass(kendrickMassBase))) * valueMZ) / //
FormulaUtils.calculateExactMass(kendrickMassBase) - Math.floor((charge * (divisor - Math.round(FormulaUtils.calculateExactMass(kendrickMassBase))) * valueMZ) / FormulaUtils.calculateExactMass(kendrickMassBase));
}
// shift Kendrick mass defect or remainder of Kendrick mass
double kendrickMassDefectShifted = defectOrRemainder + shift - Math.floor(defectOrRemainder + shift);
// check if shifted Kendrick mass defect or remainder of Kendrick mass is in range
if (!rangeKMD.contains(kendrickMassDefectShifted))
filterRowCriteriaFailed = true;
}
// Check ms2 filter .
if (filterByMS2) {
// iterates the peaks
int failCounts = 0;
for (int i = 0; i < peakCount; i++) {
if (row.getPeaks()[i].getMostIntenseFragmentScanNumber() < 1) {
failCounts++;
// filterRowCriteriaFailed = true;
// break;
}
}
if (failCounts == peakCount) {
filterRowCriteriaFailed = true;
}
}
if (!filterRowCriteriaFailed && !removeRow) {
// Only add the row if none of the criteria have failed.
rowsCount++;
PeakListRow resetRow = copyPeakRow(row);
if (renumber) {
resetRow.setID(rowsCount);
}
newPeakList.addRow(resetRow);
}
if (filterRowCriteriaFailed && removeRow) {
// Only remove rows that match *all* of the criteria, so add
// rows that fail any of the criteria.
rowsCount++;
PeakListRow resetRow = copyPeakRow(row);
if (renumber) {
resetRow.setID(rowsCount);
}
newPeakList.addRow(resetRow);
}
}
return newPeakList;
}
use of net.sf.mzmine.datamodel.Feature in project mzmine2 by mzmine.
the class RowsFilterTask method copyPeakRow.
/**
* Create a copy of a feature list row.
*
* @param row the row to copy.
* @return the newly created copy.
*/
private static PeakListRow copyPeakRow(final PeakListRow row) {
// Copy the feature list row.
final PeakListRow newRow = new SimplePeakListRow(row.getID());
PeakUtils.copyPeakListRowProperties(row, newRow);
// Copy the peaks.
for (final Feature peak : row.getPeaks()) {
final Feature newPeak = new SimpleFeature(peak);
PeakUtils.copyPeakProperties(peak, newPeak);
newRow.addPeak(peak.getDataFile(), newPeak);
}
// Add PeakInformation
if (row.getPeakInformation() != null) {
SimplePeakInformation information = new SimplePeakInformation(new HashMap<>(row.getPeakInformation().getAllProperties()));
newRow.setPeakInformation(information);
}
return newRow;
}
use of net.sf.mzmine.datamodel.Feature in project mzmine2 by mzmine.
the class PeakFinderTask method run.
public void run() {
setStatus(TaskStatus.PROCESSING);
logger.info("Running gap filler on " + peakList);
// Calculate total number of scans in all files
for (RawDataFile dataFile : peakList.getRawDataFiles()) {
totalScans += dataFile.getNumOfScans(1);
}
processedScans = new AtomicInteger();
// Create new feature list
processedPeakList = new SimplePeakList(peakList + " " + suffix, peakList.getRawDataFiles());
// Fill new feature list with empty rows
for (int row = 0; row < peakList.getNumberOfRows(); row++) {
PeakListRow sourceRow = peakList.getRow(row);
PeakListRow newRow = new SimplePeakListRow(sourceRow.getID());
newRow.setComment(sourceRow.getComment());
for (PeakIdentity ident : sourceRow.getPeakIdentities()) {
newRow.addPeakIdentity(ident, false);
}
if (sourceRow.getPreferredPeakIdentity() != null) {
newRow.setPreferredPeakIdentity(sourceRow.getPreferredPeakIdentity());
}
processedPeakList.addRow(newRow);
}
if (rtCorrection) {
totalScans *= 2;
// Fill the gaps of a random sample using all the other samples and
// take it as master list
// to fill the gaps of the other samples
masterSample = (int) Math.floor(Math.random() * peakList.getNumberOfRawDataFiles());
fillList(MASTERLIST);
// Process all raw data files
fillList(!MASTERLIST);
} else {
// Process all raw data files
IntStream rawStream = IntStream.range(0, peakList.getNumberOfRawDataFiles());
if (useParallelStream)
rawStream = rawStream.parallel();
rawStream.forEach(i -> {
// Canceled?
if (isCanceled()) {
// inside stream - only skips this element
return;
}
RawDataFile dataFile = peakList.getRawDataFile(i);
List<Gap> gaps = new ArrayList<Gap>();
// if necessary
for (int row = 0; row < peakList.getNumberOfRows(); row++) {
// Canceled?
if (isCanceled()) {
// inside stream - only skips this element
return;
}
PeakListRow sourceRow = peakList.getRow(row);
PeakListRow newRow = processedPeakList.getRow(row);
Feature sourcePeak = sourceRow.getPeak(dataFile);
if (sourcePeak == null) {
// Create a new gap
Range<Double> mzRange = mzTolerance.getToleranceRange(sourceRow.getAverageMZ());
Range<Double> rtRange = rtTolerance.getToleranceRange(sourceRow.getAverageRT());
Gap newGap = new Gap(newRow, dataFile, mzRange, rtRange, intTolerance);
gaps.add(newGap);
} else {
newRow.addPeak(dataFile, sourcePeak);
}
}
// Stop processing this file if there are no gaps
if (gaps.size() == 0) {
processedScans.addAndGet(dataFile.getNumOfScans());
return;
}
// Get all scans of this data file
int[] scanNumbers = dataFile.getScanNumbers(1);
// Process each scan
for (int scanNumber : scanNumbers) {
// Canceled?
if (isCanceled()) {
// inside stream - only skips this element
return;
}
// Get the scan
Scan scan = dataFile.getScan(scanNumber);
// Feed this scan to all gaps
for (Gap gap : gaps) {
gap.offerNextScan(scan);
}
processedScans.incrementAndGet();
}
// Finalize gaps
for (Gap gap : gaps) {
gap.noMoreOffers();
}
});
}
// terminate - stream only skips all elements
if (isCanceled())
return;
// Append processed feature list to the project
project.addPeakList(processedPeakList);
// Add quality parameters to peaks
QualityParameters.calculateQualityParameters(processedPeakList);
// Add task description to peakList
processedPeakList.addDescriptionOfAppliedTask(new SimplePeakListAppliedMethod("Gap filling ", parameters));
// Remove the original peaklist if requested
if (removeOriginal)
project.removePeakList(peakList);
logger.info("Finished gap-filling on " + peakList);
setStatus(TaskStatus.FINISHED);
}
use of net.sf.mzmine.datamodel.Feature in project mzmine2 by mzmine.
the class MultiThreadPeakFinderTask method run.
public void run() {
setStatus(TaskStatus.PROCESSING);
logger.info("Running multithreaded gap filler " + taskIndex + " on raw files " + (start + 1) + "-" + endexcl + " of pkl:" + peakList);
// Calculate total number of scans in all files
for (int i = start; i < endexcl; i++) {
RawDataFile dataFile = peakList.getRawDataFile(i);
totalScans += dataFile.getNumOfScans(1);
}
// Process all raw data files
for (int i = start; i < endexcl; i++) {
RawDataFile dataFile = peakList.getRawDataFile(i);
// Canceled?
if (isCanceled()) {
return;
}
List<Gap> gaps = new ArrayList<Gap>();
// if necessary
for (int row = 0; row < peakList.getNumberOfRows(); row++) {
PeakListRow sourceRow = peakList.getRow(row);
PeakListRow newRow = processedPeakList.getRow(row);
Feature sourcePeak = sourceRow.getPeak(dataFile);
if (sourcePeak == null) {
// Create a new gap
Range<Double> mzRange = mzTolerance.getToleranceRange(sourceRow.getAverageMZ());
Range<Double> rtRange = rtTolerance.getToleranceRange(sourceRow.getAverageRT());
Gap newGap = new Gap(newRow, dataFile, mzRange, rtRange, intTolerance);
gaps.add(newGap);
} else {
newRow.addPeak(dataFile, sourcePeak);
}
}
// Stop processing this file if there are no gaps
if (gaps.isEmpty()) {
processedScans += dataFile.getNumOfScans();
continue;
}
// Get all scans of this data file
int[] scanNumbers = dataFile.getScanNumbers(1);
// Process each scan
for (int scanNumber : scanNumbers) {
// Canceled?
if (isCanceled()) {
return;
}
// Get the scan
Scan scan = dataFile.getScan(scanNumber);
// Feed this scan to all gaps
for (Gap gap : gaps) {
gap.offerNextScan(scan);
}
processedScans++;
}
// Finalize gaps
for (Gap gap : gaps) {
gap.noMoreOffers();
}
}
// first notify listener
listener.accept(processedPeakList);
logger.info("Finished sub task: Multithreaded gap filler " + taskIndex + " on raw files " + (start + 1) + "-" + endexcl + " of pkl:" + peakList);
setStatus(TaskStatus.FINISHED);
}
Aggregations