private void writeSingleSpectrum(string sourceFile, string nativeID, string outFileName)
{
MSDataFile.WriteConfig writeConfig = new MSDataFile.WriteConfig();
writeConfig.format = MSDataFile.Format.Format_MGF;
writeConfig.precision = MSDataFile.Precision.Precision_32;
//var predicate = new SpectrumList_FilterPredicate_IndexSet();
//predicate.indexSet.Add(nativeID);
var predicate = new SpectrumList_FilterPredicate_NativeIDSet();
predicate.nativeIDSet.Add(nativeID);
try
{
//Workspace.SetText("\r\nWriting selected spectrum to " + outFileName);
MainForm.SetText(this, "Start writing selected spectrum to " + outFileName + "\r\n");
using (MSDataFile msFile = new MSDataFile(sourceFile))
{
msFile.run.spectrumList = new SpectrumList_Filter(msFile.run.spectrumList, new SpectrumList_FilterAcceptSpectrum(predicate.accept));
msFile.write(outFileName, writeConfig);
}
MainForm.SetText(this, "Finished writing selected spectrum to " + outFileName + "\r\n");
}
catch (Exception exc)
{
//throw new Exception("Error in writiing new spectra file", exc);
//Workspace.SetText("\r\nError in writing new spectra file\r\n");
tbPepNovoResult.AppendText("\r\nError in writing new spectra file\r\n");
throw new Exception(exc.Message);
}
}
public static List<string> IDList(string idpXML, string mzML)
{
List<string> list = new List<string>();
MSDataFile foo = new MSDataFile(mzML);
SpectrumList sl = foo.run.spectrumList;
IDPicker.Workspace workspace = new IDPicker.Workspace();
Package.loadWorkspace(ref workspace, idpXML);
foreach (IDPicker.SourceGroupList.MapPair groupItr in workspace.groups)
foreach (IDPicker.SourceInfo source in groupItr.Value.getSources(true))
foreach (IDPicker.SpectrumList.MapPair sItr in source.spectra)
{
IDPicker.ResultInstance ri = sItr.Value.results[1];
IDPicker.VariantInfo vi = ri.info.peptides.Min;
bool boolCharge = sItr.Value.id.charge.Equals(3);
if (boolCharge)
{
string rawPepSequence = vi.ToString();
string interpretation = vi.ToSimpleString();
// Look up the index with nativeID
object idOrIndex = null;
if (sItr.Value.nativeID != null && sItr.Value.nativeID.Length > 0)
{
idOrIndex = sItr.Value.nativeID;
list.Add(idOrIndex.ToString());
}
}//end if (boolcharge)
}//end foreach
return list;
}
public IList <string> WriteSpectra(MSDataFile.WriteConfig config)
{
var outputPaths = new List <string>();
foreach (SpectrumSource ss in session.Query <SpectrumSource>())
{
if (ss.Metadata == null)
{
continue;
}
string outputSuffix;
switch (config.format)
{
case MSDataFile.Format.Format_mzML: outputSuffix = ".mzML"; break;
case MSDataFile.Format.Format_mzXML: outputSuffix = ".mzXML"; break;
case MSDataFile.Format.Format_MGF: outputSuffix = ".mgf"; break;
case MSDataFile.Format.Format_MS2: outputSuffix = ".ms2"; break;
default:
config.format = MSDataFile.Format.Format_mzML;
outputSuffix = ".mzML";
break;
}
MSDataFile.write(ss.Metadata, ss.Name + outputSuffix, config);
outputPaths.Add(ss.Name + outputSuffix);
}
return(outputPaths);
}
static void openButton_Click(object sender, EventArgs e)
{
string filepath = _fileTextBox.Text;
if (!File.Exists(filepath))
{
MessageBox.Show("That filepath does not exist.", "404 File not found", MessageBoxButtons.OK, MessageBoxIcon.Error);
return;
}
try
{
var msd = new MSDataFile(filepath);
var sl = msd.run.spectrumList;
MessageBox.Show(String.Format("The file has {0} spectra.", sl.size()), "Spectra Count");
}
catch (Exception ex)
{
string message = ex.ToString();
if (ex.InnerException != null)
{
message += "\n\nAdditional information: " + ex.InnerException.ToString();
}
MessageBox.Show(message,
"Error opening file",
MessageBoxButtons.OK, MessageBoxIcon.Error, MessageBoxDefaultButton.Button1,
0, false);
}
}
protected void calculateSHA1()
{
lock (calculateSHA1Mutex)
{
jobInfo.log("SHA1 Checking", "SHA1 Checking");
MSDataFile.calculateSHA1Checksums(msd);
}
}
public void SetRawFile(MSDataFile dataFile)
{
MsnDataScan scan = dataFile[ScanNumber] as MsnDataScan;
IsolationMZ = scan.IsolationRange.Mean;
Spectrum = dataFile.GetSpectrum(ScanNumber);
ScanWidth = scan.MzRange.Width;
}
public void MyTestInitialize()
{
dataFile = new MSDataFile(Properties.Settings.Default.mzXMLTestFile1);
spectrumCache = new SpectrumCache();
ticGenerator = new TicGenerator(dataFile.run, spectrumCache);
timer = new Stopwatch();
}
public DataSource( string filepath )
{
msDataFile = new MSDataFile(filepath);
sourceFilepath = filepath;
/*setInputFileWaitHandle = new EventWaitHandle( false, EventResetMode.ManualReset );
setInputFileDelegate = new ParameterizedThreadStart( startSetInputFile );
Thread setInputFileThread = new Thread( setInputFileDelegate );
setInputFileThread.Start( (object) filepath );*/
}
public void GenerateFromMSMS()
{
dataFile = new MSDataFile(Properties.Settings.Default.mzXMLTestFile2);
spectrumCache = new SpectrumCache();
xicGenerator = new XicGenerator(dataFile.run, spectrumCache);
IXYData xic = xicGenerator.Generate(592.3, 592.3, 0.01, TimeUnit.Seconds);
Assert.AreEqual(239, xic.XValues.Count);
Assert.AreEqual(7.6804, Math.Round(xic.GetXYPair(168).XValue, 10));
Assert.AreEqual(519, xic.GetXYPair(168).YValue);
}
public void Convert(string omssaCSV, MSDataFile dataFile)
{
string filePath = Path.ChangeExtension(omssaCSV, ".pepxml");
using (PepXmlWriter writer = new PepXmlWriter(filePath))
{
writer.WriteSampleProtease(Protease);
writer.StartSearchSummary("OMSSA", true, true);
writer.WriteProteinDatabase(FastaDatabaseFile);
writer.WriteSearchProtease(Protease, MissedClevages);
foreach (int modNumber in FixedMods)
{
OmssaModification mod;
if (OmssaModification.TryGetModification(modNumber, out mod))
{
writer.WriteModification(mod, mod.Sites, true);
}
}
foreach (int modNumber in VariableMods)
{
OmssaModification mod;
if (OmssaModification.TryGetModification(modNumber, out mod))
{
writer.WriteModification(mod, mod.Sites, false);
}
}
writer.SetCurrentStage(PepXmlWriter.Stage.Spectra, true);
using (OmssaCsvPsmReader reader = new OmssaCsvPsmReader(omssaCSV, UserModFile))
{
reader.AddMSDataFile(dataFile);
reader.LoadProteins(FastaDatabaseFile);
foreach (PeptideSpectralMatch psm in reader.ReadNextPsm())
{
writer.StartSpectrum(psm.SpectrumNumber, psm.Spectrum.RetentionTime, psm.Spectrum.PrecursorMz, psm.Spectrum.PrecursorCharge);
writer.WritePSM(psm);
writer.EndSpectrum();
}
}
}
}
private SourceInfo[] getSourceInfo(DirectoryInfo dirInfo, bool getDetails)
{
var sourceInfoList = new List <SourceInfo>();
sourceInfoList.Add(new SourceInfo());
sourceInfoList[0].type = getSourceType(dirInfo);
sourceInfoList[0].name = dirInfo.Name;
sourceInfoList[0].path = new MSDataRunPath(dirInfo.FullName, 0);
sourceInfoList[0].dateModified = dirInfo.LastWriteTime;
sourceInfoList[0].hasDetails = getDetails;
if (!getDetails)
{
return(sourceInfoList.ToArray());
}
if (sourceInfoList[0].type == "File Folder")
{
return(sourceInfoList.ToArray());
}
else if (sourceInfoList[0].type != String.Empty)
{
try
{
MSDataFile msInfo = new MSDataFile(dirInfo.FullName);
sourceInfoList[0].populateFromMSData(msInfo);
} catch (ThreadAbortException)
{
return(null);
} catch
{
sourceInfoList[0].spectra = 0;
sourceInfoList[0].type = "Invalid " + sourceInfoList[0].type;
}
sourceInfoList[0].size = 0;
sourceInfoList[0].dateModified = DateTime.MinValue;
foreach (FileInfo fileInfo in dirInfo.GetFiles("*", SearchOption.AllDirectories))
{
sourceInfoList[0].size += (UInt64)fileInfo.Length;
if (fileInfo.LastWriteTime > sourceInfoList[0].dateModified)
{
sourceInfoList[0].dateModified = fileInfo.LastWriteTime;
}
}
return(sourceInfoList.ToArray());
}
return(null);
}
public void Convert(string omssaCSV, MSDataFile dataFile)
{
string filePath = Path.ChangeExtension(omssaCSV, ".pepxml");
using (PepXmlWriter writer = new PepXmlWriter(filePath))
{
writer.WriteSampleProtease(Protease);
writer.StartSearchSummary("OMSSA", true, true);
writer.WriteProteinDatabase(FastaDatabaseFile);
writer.WriteSearchProtease(Protease, MissedClevages);
foreach (int modNumber in FixedMods)
{
OmssaModification mod;
if (OmssaModification.TryGetModification(modNumber, out mod))
{
writer.WriteModification(mod, mod.Sites, true);
}
}
foreach (int modNumber in VariableMods)
{
OmssaModification mod;
if (OmssaModification.TryGetModification(modNumber, out mod))
{
writer.WriteModification(mod, mod.Sites, false);
}
}
writer.SetCurrentStage(PepXmlWriter.Stage.Spectra, true);
using (OmssaCsvPsmReader reader = new OmssaCsvPsmReader(omssaCSV, UserModFile))
{
reader.AddMSDataFile(dataFile);
reader.LoadProteins(FastaDatabaseFile);
foreach (PeptideSpectralMatch psm in reader.ReadNextPsm())
{
writer.StartSpectrum(psm.SpectrumNumber, psm.Spectrum.RetentionTime, psm.Spectrum.PrecursorMz, psm.Spectrum.PrecursorCharge);
writer.WritePSM(psm);
writer.EndSpectrum();
}
}
}
}
public ParseSpectraFile(string mzmlPath, HashSet <int> scanNumSet, string ext)
{
int currentScanNum = -1;
try
{
MSDataFile msd = new MSDataFile(mzmlPath);
SpectrumList spectrumList = msd.run.spectrumList;
for (int i = 0; i < spectrumList.size(); ++i)
{
Spectrum spectrum = spectrumList.spectrum(i, true);
if (int.Parse(spectrum.cvParams[0].value) == 2)
{
Match match = scanNumPattern.Match(spectrum.id);
currentScanNum = int.Parse(match.Groups[1].Value);
if (scanNumSet.Contains(currentScanNum))
{
MZIntensityPairList mzIntensityPairs = new MZIntensityPairList();
spectrum.getMZIntensityPairs(ref mzIntensityPairs);
Dictionary <float, int> originalPeakList = new Dictionary <float, int>(mzIntensityPairs.Count);
foreach (MZIntensityPair mzIntensity in mzIntensityPairs)
{
originalPeakList[(float)mzIntensity.mz] = (int)mzIntensity.intensity;
}
spectraMap[currentScanNum] = originalPeakList;
}
}
}
}
catch (Exception ex)
{
MessageBox.Show(ex.Message + ": " + currentScanNum, "Error", MessageBoxButtons.OK, MessageBoxIcon.Error);
Application.Exit();
}
}
private void SetupMSMSData()
{
dataFile = new MSDataFile(Properties.Settings.Default.mzXMLTestFile2);
spectrumCache = new SpectrumCache();
timePointToRtConverter = new RtToTimePointConverter(dataFile.run, spectrumCache);
}
public void MyTestInitialize()
{
dataFile = new MSDataFile(Properties.Settings.Default.mzXMLTestFile1);
spectrumCache = new SpectrumCache();
timePointToRtConverter = new RtToTimePointConverter(dataFile.run, spectrumCache);
}
public void UpdatePsmInformation(MSDataFile dataFile, bool is2dFDR = true, bool useMedian = true, double evalueThreshold = 1e-3)
{
List <double> errors = new List <double>();
MaximumPrecursorMassError = 0;
int count = 0;
int msms = 0;
int ms = 0;
int localMSMS = -1;
List <int> msmsBetweenMS = new List <int>();
List <double> injectionTimes = new List <double>();
for (int sn = dataFile.FirstSpectrumNumber; sn <= dataFile.LastSpectrumNumber; sn++)
{
int order = dataFile.GetMsnOrder(sn);
if (order == 1)
{
ms++;
if (localMSMS >= 0)
{
msmsBetweenMS.Add(localMSMS);
}
localMSMS = 0;
}
else
{
localMSMS++;
msms++;
injectionTimes.Add(dataFile.GetInjectionTime(sn));
}
}
MaxMSMSScansBetweenMS = msmsBetweenMS.Max();
AverageMSMSSCansBetweenMS = msmsBetweenMS.Average();
TotalMSMSscans = msms;
TotalMSscans = ms;
AverageMSMSInjectionTime = injectionTimes.Average();
MaxMSMSInjectionTime = injectionTimes.Max();
foreach (KeyValuePair <int, SortedMaxSizedContainer <PSM> > kvp in _data)
{
int scanNumber = kvp.Key;
SortedMaxSizedContainer <PSM> psms = kvp.Value;
double isolationMZ = dataFile.GetPrecusorMz(scanNumber);
Polarity polarity = dataFile.GetPolarity(scanNumber);
foreach (PSM psm in psms)
{
psm.Charge *= (int)polarity; // For negative mode ions
psm.IsolationMz = isolationMZ;
double isolationMass = Mass.MassFromMz(isolationMZ, psm.Charge);
double theoreticalMass = psm.MonoisotopicMass;
int nominalMassOffset;
double adjustedIsolationMass;
Tolerance tolerancePPM = Tolerance.CalculatePrecursorMassError(theoreticalMass,
isolationMass, out nominalMassOffset, out adjustedIsolationMass);
psm.AdjustedIsolationMass = adjustedIsolationMass;
psm.IsotopeSelected = nominalMassOffset;
if (!HasPPMInfo)
{
psm.PrecursorMassError = tolerancePPM.Value;
}
double positive = Math.Abs(psm.PrecursorMassError);
if (positive > MaximumPrecursorMassError)
{
MaximumPrecursorMassError = positive;
}
if (psm.FdrScoreMetric <= evalueThreshold)
{
errors.Add(psm.PrecursorMassError);
}
count++;
}
}
SystematicPrecursorMassError = useMedian ? GetMedianValue(errors) : errors.Average();
// Adjust all psms to
foreach (PSM psm in PeptideSpectralMatches)
{
psm.CorrectedPrecursorMassError = psm.PrecursorMassError - SystematicPrecursorMassError;
}
}
public void GetMSMSSpectrum()
{
dataFile = new MSDataFile(Properties.Settings.Default.mzXMLTestFile2);
spectrumCache = new SpectrumCache();
averagedSpectrumExtractor = new AveragedSpectrumExtractor(dataFile.run, spectrumCache);
Domain.ISpectrum msmsSpectrum = averagedSpectrumExtractor.GetMSMSSpectrum(7.8, 1, 592.3, 0.5);
Assert.AreEqual(42279, msmsSpectrum.Count);
Assert.AreEqual(37, Math.Round(msmsSpectrum.GetXYPair(63).YValue, 5));
}
public static void quantify(Workspace ws, string rootInputDirectory, QuantitationInfo.Method method)
{
if (method == QuantitationInfo.Method.None)
return;
ws.groups.assembleParentGroups();
foreach (SourceInfo source in ws.groups["/"].getSources(true))
{
source.filepath = Util.FindSourceInSearchPath(source.name, rootInputDirectory);
using (MSDataFile msd = new MSDataFile(source.filepath))
using (pwiz.CLI.msdata.SpectrumList sl = msd.run.spectrumList)
{
foreach (SpectrumInfo si in source.spectra.Values)
{
int index = sl.find(si.nativeID);
if (index == sl.size())
throw new KeyNotFoundException("spectrum \"" + si.nativeID + "\" not found in " + source.filepath);
si.quantitation = new QuantitationInfo()
{
method = method,
ITRAQ_113_intensity = 0,
ITRAQ_114_intensity = 0,
ITRAQ_115_intensity = 0,
ITRAQ_116_intensity = 0,
ITRAQ_117_intensity = 0,
ITRAQ_118_intensity = 0,
ITRAQ_119_intensity = 0,
ITRAQ_121_intensity = 0
};
const double tolerance = 0.5; // TODO: make user configurable?
pwiz.CLI.msdata.Spectrum s = sl.spectrum(index, true);
BinaryData mzData = s.getMZArray().data;
BinaryData intensityData = s.getIntensityArray().data;
if (method == QuantitationInfo.Method.ITRAQ4Plex)
for (int i = 0; i < mzData.Count; ++i)
{
if (mzData[i] < 113) continue;
else if (inTolerance(mzData[i], 114, tolerance)) si.quantitation.ITRAQ_114_intensity += intensityData[i];
else if (inTolerance(mzData[i], 115, tolerance)) si.quantitation.ITRAQ_115_intensity += intensityData[i];
else if (inTolerance(mzData[i], 116, tolerance)) si.quantitation.ITRAQ_116_intensity += intensityData[i];
else if (inTolerance(mzData[i], 117, tolerance)) si.quantitation.ITRAQ_117_intensity += intensityData[i];
else if (mzData[i] > 117) break;
}
else if(method == QuantitationInfo.Method.ITRAQ8Plex)
for (int i = 0; i < mzData.Count; ++i)
{
if (mzData[i] < 112) continue;
else if (inTolerance(mzData[i], 113, tolerance)) si.quantitation.ITRAQ_113_intensity += intensityData[i];
else if (inTolerance(mzData[i], 114, tolerance)) si.quantitation.ITRAQ_114_intensity += intensityData[i];
else if (inTolerance(mzData[i], 115, tolerance)) si.quantitation.ITRAQ_115_intensity += intensityData[i];
else if (inTolerance(mzData[i], 116, tolerance)) si.quantitation.ITRAQ_116_intensity += intensityData[i];
else if (inTolerance(mzData[i], 117, tolerance)) si.quantitation.ITRAQ_117_intensity += intensityData[i];
else if (inTolerance(mzData[i], 118, tolerance)) si.quantitation.ITRAQ_118_intensity += intensityData[i];
else if (inTolerance(mzData[i], 119, tolerance)) si.quantitation.ITRAQ_119_intensity += intensityData[i];
else if (inTolerance(mzData[i], 121, tolerance)) si.quantitation.ITRAQ_121_intensity += intensityData[i];
else if (mzData[i] > 121) break;
}
}
}
}
}
public MsnDataScan(int spectrumNumber, int msnOrder, MSDataFile <TSpectrum> parentFile = null)
: base(spectrumNumber, msnOrder, parentFile)
{
}
//get pepSequence,source,scanID, write into a csv file.
//have tons of information: theretical ion intensity, pep info, chargeLabel...
public static void idpReader(string idpXMLFile, string mzMLFile, double TicCutoffPercentage, int z, int model)
{
//get the path and filename of output csv file:
string fileName = Path.GetFileNameWithoutExtension(idpXMLFile);
string filePath = Path.GetDirectoryName(idpXMLFile);
string csvFile = Path.Combine(filePath, fileName) + "_" + z.ToString() + ".csv";
IDPicker.Workspace workspace = new IDPicker.Workspace();
Package.loadWorkspace(ref workspace, idpXMLFile);
using (StreamWriter file = new StreamWriter(csvFile))
{
//TODO idOrIndex + "," + pepSequence + "," + pepBond + "," + AA + "," + bIons + "," + yIons;
file.WriteLine("nativeID,pepSequence,bond,b1,b2,y1,y2");
MSDataFile foo = new MSDataFile(mzMLFile);
SpectrumList sl = foo.run.spectrumList;
foreach (IDPicker.SourceGroupList.MapPair groupItr in workspace.groups)
foreach (IDPicker.SourceInfo source in groupItr.Value.getSources(true))
foreach (IDPicker.SpectrumList.MapPair sItr in source.spectra)
{
IDPicker.ResultInstance ri = sItr.Value.results[1];
IDPicker.VariantInfo vi = ri.info.peptides.Min;
string ss = vi.ToString() + "," + sItr.Value.id.source.name + "," + sItr.Value.nativeID;
bool boolCharge = sItr.Value.id.charge.Equals(z);
if (boolCharge)
{
string rawPepSequence = vi.ToString();
string pepSequence = vi.peptide.sequence;
int len = pepSequence.Length;
// Look up the index with nativeID
object idOrIndex = null;
if( sItr.Value.nativeID != null && sItr.Value.nativeID.Length > 0 )
idOrIndex = sItr.Value.nativeID;
int spectrumIndex = sl.find(idOrIndex as string);
// Trust the local index, if the nativeID lookup fails
if( spectrumIndex >= sl.size() )
spectrumIndex = sItr.Value.id.index;
// Bail of the loca index is larger than the spectrum list size
if( spectrumIndex >= sl.size() )
throw new Exception( "Can't find spectrum associated with the index." );
//get base peak and TIC and converted to string
Spectrum spec1 = sl.spectrum(spectrumIndex, true);
MZIntensityPairList peaks = new MZIntensityPairList();
spec1.getMZIntensityPairs(ref peaks);
Set<Peak> peakList = new Set<Peak>();
//get base peak and TIC
double basePeakValue = 0;
double TICValue = 0;
CVParamList list = spec1.cvParams;
foreach (CVParam CVP in list)
{
if (CVP.name == "base peak intensity")
{
basePeakValue = CVP.value;
}
if (CVP.name == "total ion current")
{
TICValue = CVP.value;
}
}
string basePeak = basePeakValue.ToString();
string TIC = TICValue.ToString();
//very important. Surendra put them here
//to change those with modifications {} into a format
//that fragment method will accept.
string interpretation = vi.ToSimpleString();
Peptide peptide = new Peptide(interpretation, ModificationParsing.ModificationParsing_Auto, ModificationDelimiter.ModificationDelimiter_Brackets);
Fragmentation fragmentation = peptide.fragmentation(true, true);
//prepare the qualified peaklist
double intenThreshhold = 0;
int totalIntenClass = 0;
double[] intenArray = new double[peaks.Count];
//used during the foreach loop
int indexPeaks = 0;
//get all the peaks no matter how small they are
//then calculate the threshhold TIC
//test here
foreach (MZIntensityPair mzIntensity in peaks)
{
//Peak p = new Peak(mzIntensity.mz, mzIntensity.intensity);
//peakList.Add(p);
intenArray[indexPeaks] = mzIntensity.intensity;
indexPeaks++;
}
Array.Sort(intenArray);
Array.Reverse(intenArray, 0, peaks.Count);
//if currTIC>=cutoff, then break
double currTIC = 0;
double cutOffTIC = TicCutoffPercentage * TICValue;
foreach (double inten in intenArray)
{
currTIC = currTIC + inten;
if (currTIC < cutOffTIC)
{
intenThreshhold = inten;
totalIntenClass++;
}
else break;
}
//then based on that, generate a new peaklist that contains only ABC peaks
//then calculate the intensity classes
foreach (MZIntensityPair mzIntensity in peaks)
{
if (mzIntensity.intensity >= intenThreshhold)
{
//note 0 here. This is to tell people that the orbiorbi fragment charge is unknown.
//the peaklist will be updated later.
Peak p = new Peak(mzIntensity.mz, mzIntensity.intensity,0);
peakList.Add(p);
}
}
Console.WriteLine("nativeID: =============" + idOrIndex);
//update peaklist for charge states.
peakList = Package.chargeAssignment(peakList);
//int ones = 0;
//int twos = 0;
//foreach (var peak in peakList)
//{
// //Console.WriteLine(peak.fragmentCharge);
// if (peak.fragmentCharge == 1) ones++;
// else if (peak.fragmentCharge == 2) twos++;
//}
//Console.WriteLine("charge 1: " + ones);
//Console.WriteLine("charge 2: " + twos);
//rowDic contains row information of each peptide bond
Dictionary<int, string> rowDic = new Dictionary<int, string>();
//intensityDic contains intensity information of fragment ions for each peptide bond
Dictionary<int, List<double>> intensityDic = new Dictionary<int, List<double>>();
//commonList contains the common intensities
List<double> duplicateList = new List<double>();
//call the method
List<double> completeIntensityList = new List<double>();
for (int k = 1; k < len; k++)
{
List<double> intensityList = new List<double>();
string bion = pepSequence.Substring(0, k);
string yion = pepSequence.Substring(k, len - k);
int NR = Package.parseAAResidues(bion, 'R');
int NK = Package.parseAAResidues(bion, 'K');
int NH = Package.parseAAResidues(bion, 'H');
int NL = k;
int CR = Package.parseAAResidues(yion, 'R');
int CK = Package.parseAAResidues(yion, 'K');
int CH = Package.parseAAResidues(yion, 'H');
int CL = len - k;
int pepBond = k;
int NBasicAA = NR + NK + NH;
int CBasicAA = CR + CK + CH;
string AA = NR + "," + NK + "," + NH + "," + NL + "," + CR + "," + CK + "," + CH + "," + CL;
double[] bCharge = new double[z + 1];
double[] yCharge = new double[z + 1];
//double[] bIntensity = new double[z + 1];
//double[] yIntensity = new double[z + 1];
//add variable for "real" charges
if (model == 0) //naive model
{
int[] bFragmentCharge = new int[z + 1];
int[] yFragmentCharge = new int[z + 1];
//return the b ion charge 1 Intensity, if matched
for (int i = 1; i < z; i++)
{
bCharge[i] = fragmentation.b(k, i);
yCharge[i] = fragmentation.y(len - k, i);
//change for ORBI-ORBI purposes.
Peak bmatched = Package.findClose(peakList, bCharge[i], bCharge[i] * 30 * Math.Pow(10, -6));
Peak ymatched = Package.findClose(peakList, yCharge[i], yCharge[i] * 30 * Math.Pow(10, -6));
if (bmatched != null)
{
//bIntensity[i] = bmatched.rankOrIntensity;
int fragmentCharge = bmatched.fragmentCharge;
if (fragmentCharge == i)
bFragmentCharge[i] = 3;
else bFragmentCharge[i] = 2;
//intensityList.Add(bmatched.rankOrIntensity);
//completeIntensityList.Add(bmatched.rankOrIntensity);
}
else bFragmentCharge[i] = 1;
//else bIntensity[i] = 0;
if (ymatched != null)
{
//yIntensity[i] = ymatched.rankOrIntensity;
//yFragmentCharge[i] = ymatched.fragmentCharge;
int fragmentCharge = ymatched.fragmentCharge;
if (fragmentCharge == i)
yFragmentCharge[i] = 3;
else yFragmentCharge[i] = 2;
//intensityList.Add(ymatched.rankOrIntensity);
//completeIntensityList.Add(ymatched.rankOrIntensity);
}
else yFragmentCharge[i] = 1;
//else yIntensity[i] = 0;
}
string finalString = idOrIndex + "," + pepSequence + "," + pepBond + "," + bFragmentCharge[1] + "," + bFragmentCharge[2] + "," + yFragmentCharge[1] + "," + yFragmentCharge[2];
file.WriteLine(finalString);
}
else if (model == 1) //my binary logistic regression basophile model
{
int b1=0, b2=0, y1=0, y2 = 0;
double y1_logit = 0.1098112 * NR + 0.2085831 * NK + 0.1512109 * NH + 0.0460839 * NL
- 0.3872417 * CR - 0.3684911 * CK - 0.1634741 * CH - 0.1693931 * CL + 1.2632997;
double y2_logit =-0.6345364 * NR - 0.3365917 * NK - 0.4577882 * NH - 0.1492703 * NL
+ 0.7738133 * CR + 0.6036758 * CK + 0.5942542 * CH + 0.0701467 * CL + 0.0806280;
double b1_logit = 0.0801432 * NR - 0.1088081 * NK - 0.1338220 * NH - 0.1413059 * NL
- 0.3157957 * CR - 0.2708274 * CK - 0.3703136 * CH + 0.0157418 * CL + 1.2124699;
double b2_logit = 0.8606449 * NR + 0.2763119 * NK + 0.4969152 * NH + 0.0685712 * NL
- 1.3346995 * CR - 1.0977316 * CK - 1.0973677 * CH - 0.2028884 * CL + 1.9355980;
if (b1_logit > -0.5)
{
double mz_b1 = fragmentation.b(k, 1);
Peak matched = Package.findClose(peakList, mz_b1, mz_b1 * 30 * Math.Pow(10, -6));
if (matched != null)
{
if (matched.fragmentCharge == 1) b1 = 3;
else b1 = 2;
}
else b1 = 1;
}
else b1 = 0;
if (b2_logit > 0)
{
double mz_b2 = fragmentation.b(k, 2);
Peak matched = Package.findClose(peakList, mz_b2, mz_b2 * 30 * Math.Pow(10, -6));
if (matched != null)
{
if (matched.fragmentCharge == 2) b2 = 3;
else b2 = 2;
}
else b2 = 1;
}
else b2 = 0;
if (y1_logit > -0.5)
{
double mz_y1 = fragmentation.y(len - k, 1);
Peak matched = Package.findClose(peakList, mz_y1, mz_y1 * 30 * Math.Pow(10, -6));
if (matched != null)
{
if (matched.fragmentCharge == 1) y1 = 3;
else y1 = 2;
}
else y1 = 1;
}
else y1 = 0;
if (y2_logit > -0.5)
{
double mz_y2 = fragmentation.y(len - k, 2);
Peak matched = Package.findClose(peakList, mz_y2, mz_y2 * 30 * Math.Pow(10, -6));
if (matched != null)
{
if (matched.fragmentCharge == 2) y2 = 3;
else y2 = 2;
}
else y2 = 1;
}
else y2 = 0;
string finalString = idOrIndex + "," + pepSequence + "," + pepBond + "," + b1 + "," + b2 + "," + y1 + "," + y2;
file.WriteLine(finalString);
}
else if (model == 2) //Surendra's ordinal model
{
int b1 = 0, b2 = 0, y1 = 0, y2 = 0;
double logit = NR * 0.9862 + NH * 0.8772 + NK * 0.7064 + NL * 0.4133
- CR * 1.1688 - CH * 0.3948 - CK * 0.6710 - CL * 0.4859;
//charge Label = "1", generate b+,y++
if (logit < -2.2502)
{
double mz_b1 = fragmentation.b(k, 1);
Peak b1matched = Package.findClose(peakList, mz_b1, mz_b1 * 30 * Math.Pow(10, -6));
if (b1matched != null)
{
if (b1matched.fragmentCharge == 1) b1 = 3; //matched, charge agree
else b1 = 2; //matched, charge does not agree
}
else b1 = 1; //unmatched, but predicted.
double mz_y2 = fragmentation.y(len - k, 2);
Peak y2matched = Package.findClose(peakList, mz_y2, mz_y2 * 30 * Math.Pow(10, -6));
if (y2matched != null)
{
if (y2matched.fragmentCharge == 2) y2 = 3; //matched, charge agree
else y2 = 2; //matched, charge does not agree
}
else y2 = 1; //unmatched, but predicted.
}
//ambiLabel = "2", generate b+, y+, b++, y++
else if (logit < 0.7872)
{
double mz_b1 = fragmentation.b(k, 1);
Peak b1matched = Package.findClose(peakList, mz_b1, mz_b1 * 30 * Math.Pow(10, -6));
if (b1matched != null)
{
if (b1matched.fragmentCharge == 1) b1 = 3; //matched, charge agree
else b1 = 2; //matched, charge does not agree
}
else b1 = 1; //unmatched, but predicted.
double mz_y1 = fragmentation.y(len - k, 1);
Peak y1matched = Package.findClose(peakList, mz_y1, mz_y1 * 30 * Math.Pow(10, -6));
if (y1matched != null)
{
if (y1matched.fragmentCharge == 1) y1 = 3; //matched, charge agree
else y1 = 2; //matched, charge does not agree
}
else y1 = 1; //unmatched, but predicted.
double mz_b2 = fragmentation.b(k, 2);
Peak b2matched = Package.findClose(peakList, mz_b2, mz_b2 * 30 * Math.Pow(10, -6));
if (b2matched != null)
{
if (b2matched.fragmentCharge == 2) b2 = 3; //matched, charge agree
else b2 = 2; //matched, charge does not agree
}
else b2 = 1; //unmatched, but predicted.
double mz_y2 = fragmentation.y(len - k, 2);
Peak y2matched = Package.findClose(peakList, mz_y2, mz_y2 * 30 * Math.Pow(10, -6));
if (y2matched != null)
{
if (y2matched.fragmentCharge == 2) y2 = 3; //matched, charge agree
else y2 = 2; //matched, charge does not agree
}
else y2 = 1; //unmatched, but predicted.
}
//ambiLabel = "3", generate b++,y+
else
{
double mz_b2 = fragmentation.b(k, 2);
Peak b2matched = Package.findClose(peakList, mz_b2, mz_b2 * 30 * Math.Pow(10, -6));
if (b2matched != null)
{
if (b2matched.fragmentCharge == 2) b2 = 3; //matched, charge agree
else b2 = 2; //matched, charge does not agree
}
else b2 = 1; //unmatched, but predicted.
double mz_y1 = fragmentation.y(len - k, 1);
Peak y1matched = Package.findClose(peakList, mz_y1, mz_y1 * 30 * Math.Pow(10, -6));
if (y1matched != null)
{
if (y1matched.fragmentCharge == 1) y1 = 3; //matched, charge agree
else y1 = 2; //matched, charge does not agree
}
else y1 = 1; //unmatched, but predicted.
}
string finalString = idOrIndex + "," + pepSequence + "," + pepBond + "," + b1 + "," + b2 + "," + y1 + "," + y2;
file.WriteLine(finalString);
}
//intensityDic.Add(pepBond, intensityList);
//rowDic.Add(pepBond, finalString);
}//end for each peptide bond
}//end if z==3
}//end foreach peptide
}//end using
}
public MSDataScan(int spectrumNumber, int msnOrder = 1, MSDataFile parentFile = null)
{
SpectrumNumber = spectrumNumber;
MsnOrder = msnOrder;
ParentFile = parentFile;
}
///<summary>
///original code for grabbing the required ions
///get pepSequence,source,scanID, write into a csv file.
///have tons of information: theretical ion intensity, pep info, chargeLabel...
///</summary>
public static List<string> idpReader_original(string idpXMLFile, string mzMLFile, double TicCutoffPercentage, int z, List<string> pepList, List<string> output)
{
//get the path and filename of output csv file:
string fileName = Path.GetFileNameWithoutExtension(idpXMLFile);
string filePath = Path.GetDirectoryName(idpXMLFile);
IDPicker.Workspace workspace = new IDPicker.Workspace();
Package.loadWorkspace(ref workspace, idpXMLFile);
MSDataFile foo = new MSDataFile(mzMLFile);
SpectrumList sl = foo.run.spectrumList;
foreach (IDPicker.SourceGroupList.MapPair groupItr in workspace.groups)
foreach (IDPicker.SourceInfo source in groupItr.Value.getSources(true))
foreach (IDPicker.SpectrumList.MapPair sItr in source.spectra)
{
IDPicker.ResultInstance ri = sItr.Value.results[1];
IDPicker.VariantInfo vi = ri.info.peptides.Min;
string ss = vi.ToString() + "," + sItr.Value.id.source.name + "," + sItr.Value.nativeID;
bool boolCharge = sItr.Value.id.charge.Equals(z);
if (boolCharge)
{
string rawPepSequence = vi.ToString();
string pepSequence = vi.peptide.sequence;
int len = pepSequence.Length;
//make sure that the peptide is what we want
if (pepList.Contains(pepSequence))
{
// Look up the index with nativeID
object idOrIndex = null;
if (sItr.Value.nativeID != null && sItr.Value.nativeID.Length > 0)
idOrIndex = sItr.Value.nativeID;
int spectrumIndex = sl.find(idOrIndex as string);
// Trust the local index, if the nativeID lookup fails
if (spectrumIndex >= sl.size())
spectrumIndex = sItr.Value.id.index;
// Bail of the loca index is larger than the spectrum list size
if (spectrumIndex >= sl.size())
throw new Exception("Can't find spectrum associated with the index.");
//Console.WriteLine(idOrIndex.ToString());
//get base peak and TIC and converted to string
Spectrum spec1 = sl.spectrum(spectrumIndex, true);
MZIntensityPairList peaks = new MZIntensityPairList();
spec1.getMZIntensityPairs(ref peaks);
Set<Peak> peakList = new Set<Peak>();
//get base peak and TIC
double basePeakValue = 0;
double TICValue = 0;
CVParamList list = spec1.cvParams;
foreach (CVParam CVP in list)
{
if (CVP.name == "base peak intensity")
{
basePeakValue = CVP.value;
}
if (CVP.name == "total ion current")
{
TICValue = CVP.value;
}
}
string basePeak = basePeakValue.ToString();
string TIC = TICValue.ToString();
//very important. Surendra put them here
//to change those with modifications {} into a format
//that fragment method will accept.
string interpretation = vi.ToSimpleString();
Peptide peptide = new Peptide(interpretation, ModificationParsing.ModificationParsing_Auto, ModificationDelimiter.ModificationDelimiter_Brackets);
Fragmentation fragmentation = peptide.fragmentation(true, true);
//prepare the qualified peaklist
double intenThreshhold = 0;
int totalIntenClass = 0;
double[] intenArray = new double[peaks.Count];
//used during the foreach loop
int indexPeaks = 0;
//get all the peaks no matter how small they are
//then calculate the threshhold TIC
//test here
foreach (MZIntensityPair mzIntensity in peaks)
{
//Peak p = new Peak(mzIntensity.mz, mzIntensity.intensity);
//peakList.Add(p);
intenArray[indexPeaks] = mzIntensity.intensity;
indexPeaks++;
}
Array.Sort(intenArray);
Array.Reverse(intenArray, 0, peaks.Count);
//if currTIC>=cutoff, then break
double currTIC = 0;
double cutOffTIC = TicCutoffPercentage * TICValue;
foreach (double inten in intenArray)
{
currTIC = currTIC + inten;
if (currTIC < cutOffTIC)
{
intenThreshhold = inten;
totalIntenClass++;
}
else break;
}
//then based on that, generate a new peaklist that contains only ABC peaks
//then calculate the intensity classes
foreach (MZIntensityPair mzIntensity in peaks)
{
if (mzIntensity.intensity >= intenThreshhold)
{
Peak p = new Peak(mzIntensity.mz, mzIntensity.intensity);
peakList.Add(p);
}
}
//rowDic contains row information of each peptide bond
Dictionary<int, string> rowDic = new Dictionary<int, string>();
//intensityDic contains intensity information of fragment ions for each peptide bond
Dictionary<int, List<double>> intensityDic = new Dictionary<int, List<double>>();
//commonList contains the common intensities
List<double> duplicateList = new List<double>();
//call the method
List<double> completeIntensityList = new List<double>();
for (int k = 1; k < len; k++)
{
List<double> intensityList = new List<double>();
string bion = pepSequence.Substring(0, k);
string yion = pepSequence.Substring(k, len - k);
int NR = Package.parseAAResidues(bion, 'R');
int NK = Package.parseAAResidues(bion, 'K');
int NH = Package.parseAAResidues(bion, 'H');
int NL = k;
int CR = Package.parseAAResidues(yion, 'R');
int CK = Package.parseAAResidues(yion, 'K');
int CH = Package.parseAAResidues(yion, 'H');
int CL = len - k;
int R = NR - CR;
int K = NK - CK;
int H = NH - CH;
int L = NL - CL;
int pepBond = k;
int NBasicAA = NR + NK + NH;
int CBasicAA = CR + CK + CH;
string AA = NBasicAA + "," + CBasicAA + "," + NR + "," + NK + "," + NH + "," + NL + "," + CR + "," + CK + "," + CH + "," + CL + "," + R + "," + K + "," + H + "," + L;
double[] bCharge = new double[z + 1];
double[] yCharge = new double[z + 1];
double[] bIntensity = new double[z + 1];
double[] yIntensity = new double[z + 1];
string bIonIntensity = "";
string yIonIntensity = "";
//to judge if the sum of intensities are 0
//so to exclude the case with all "0s"
double sumIntensity = 0;
//return the b ion charge 1 Intensity, if matched
for (int i = 1; i <= z; i++)
{
bCharge[i] = fragmentation.b(k, i);
yCharge[i] = fragmentation.y(len - k, i);
//change for Q-star purposes.
Peak bmatched = Package.findClose(peakList, bCharge[i], 70 * bCharge[i] * Math.Pow(10, -6));
Peak ymatched = Package.findClose(peakList, yCharge[i], 70 * yCharge[i] * Math.Pow(10, -6));
if (bmatched != null)
{
bIntensity[i] = bmatched.rankOrIntensity;
intensityList.Add(bmatched.rankOrIntensity);
completeIntensityList.Add(bmatched.rankOrIntensity);
}
else bIntensity[i] = 0;
if (ymatched != null)
{
yIntensity[i] = ymatched.rankOrIntensity;
intensityList.Add(ymatched.rankOrIntensity);
completeIntensityList.Add(ymatched.rankOrIntensity);
}
else yIntensity[i] = 0;
sumIntensity = sumIntensity + bIntensity[i] + yIntensity[i];
//record b/y ion intensity information into a string
bIonIntensity = bIonIntensity + "," + bIntensity[i];
yIonIntensity = yIonIntensity + "," + yIntensity[i];
}
intensityDic.Add(pepBond, intensityList);
//to determine charge label, need to split by precursor charge
//first need to make a metric to determine if all intensities are "0"
if (z == 3)
{
if (sumIntensity != 0)
{
////////////////////////////////////////////////
//set the ambiguity label as follows:
//-3: (0/+3) y3 only
//-2: (0/+3, +1/+2) y3, b1y2
//-1: (+1/+2): b1y2
//0: (+1/+2, +2/+1): b1y2, b2y1
//1: (+2/+1): b2y1
//2: (+2/+1, +3/0): b2y1, b3
//3: (+3/0): b3 only
////////////////////////////////////////////////
double b1 = bIntensity[1];
double b2 = bIntensity[2];
double y1 = yIntensity[1];
double y2 = yIntensity[2];
double b3 = bIntensity[3];
double y3 = yIntensity[3];
double b1y2 = b1 + y2;
double b2y1 = b2 + y1;
string ambiguityLabel = "";
//first part: set the intensity group: y3, b1y2, b2y1, b3
//if one group was found, set the label
//if two were found, but adjacent to each other, then ambiguity label is set
if (y3 != 0 && (b1y2 + b2y1 + b3) == 0) ambiguityLabel = "-3";
else if (y3 != 0 && b1y2 != 0 && (b2y1 + b3) == 0) ambiguityLabel = "-2";
else if (b1y2 != 0 && (y3 + b2y1 + b3) == 0) ambiguityLabel = "-1";
else if (b1y2 != 0 && b2y1 != 0 && (y3 + b3) == 0) ambiguityLabel = "0";
else if (b2y1 != 0 && (y3 + b1y2 + b3) == 0) ambiguityLabel = "1";
else if (b2y1 != 0 && b3 != 0 && (y3 + b1y2) == 0) ambiguityLabel = "2";
else if (b3 != 0 && (y3 + b1y2 + b2y1) == 0) ambiguityLabel = "3";
else ambiguityLabel = "error";
string finalString = idOrIndex + "," + pepSequence + "," + basePeak + "," + TIC + bIonIntensity + yIonIntensity + "," + len + "," + pepBond + "," + AA + "," + ambiguityLabel;
rowDic.Add(pepBond, finalString);
}
}
}//end for each peptide bond
//now we have: rowDic, intensityDic for each pep bond
//and we have: and completeIntensityList for each peptide
//the purpose of this is to remove such rows with duplicate matches
duplicateList = Package.findCommon(completeIntensityList);
foreach (int bond in rowDic.Keys)
{
bool unique = true;
foreach (double inten in duplicateList)
{
if (intensityDic[bond].Contains(inten))
{
unique = false;
Console.WriteLine("kick");
break;
}
}
if (unique)
{
output.Add(rowDic[bond]);
}
}
}//end of if peplist contains pepsequence
}//end if z==3
}//end foreach peptide
return output;
}
void processFile(string filename, Config config, ReaderList readers, Map <string, int> usedOutputFilenames)
{
// read in data file
using (var msdList = new MSDataList())
{
string msg = String.Format("Opening file \"{0}\" for read...", filename);
var stripCredentialsMatch = Regex.Match(filename, "https?://([^:]+:[^@]+@).*", RegexOptions.CultureInvariant | RegexOptions.IgnoreCase);
if (stripCredentialsMatch.Success)
{
msg = msg.Replace(stripCredentialsMatch.Groups[1].Value, "");
}
LogUpdate?.Invoke(msg, _info);
StatusUpdate?.Invoke(msg, ProgressBarStyle.Marquee, _info);
readers.read(filename, msdList, config.ReaderConfig);
foreach (var msd in msdList)
{
try
{
var outputFilename = config.outputFilename(filename, msd);
string deduplicatedFilename = outputFilename;
StatusUpdate?.Invoke("Waiting...", ProgressBarStyle.Marquee, _info);
// only one thread
lock (_calculateSHA1Mutex)
{
// if output name is same as input name, add a suffix
if (filename == outputFilename)
{
++usedOutputFilenames[outputFilename];
}
if (usedOutputFilenames.Contains(deduplicatedFilename))
{
deduplicatedFilename = deduplicatedFilename.Replace(Path.GetExtension(outputFilename), String.Format(" ({0}).{1}", usedOutputFilenames[outputFilename] + 1, Path.GetExtension(outputFilename)));
}
++usedOutputFilenames[outputFilename];
LogUpdate?.Invoke("Calculating SHA1 checksum...", _info);
StatusUpdate?.Invoke("Calculating SHA1 checksum...", ProgressBarStyle.Marquee, _info);
MSDataFile.calculateSHA1Checksums(msd);
}
var ilr = new IterationListenerRegistry();
ilr.addListenerWithTimer(this, 1);
LogUpdate?.Invoke("Processing...", _info);
StatusUpdate?.Invoke("Processing...", ProgressBarStyle.Marquee, _info);
SpectrumListFactory.wrap(msd, config.Filters, ilr);
config.WriteConfig.useWorkerThreads = msd.run.spectrumList.benefitsFromWorkerThreads();
if ((msd.run.spectrumList == null) || msd.run.spectrumList.empty())
{
if ((msd.run.chromatogramList != null) && !msd.run.chromatogramList.empty())
{
msg = "Note: input contains only chromatogram data.";
switch (config.WriteConfig.format)
{
case MSDataFile.Format.Format_MZ5:
case MSDataFile.Format.Format_mzML:
break;
default:
msg += " The selected output format can only represent spectra. Consider using mzML instead.";
break;
}
}
else
{
msg = "Note: input contains no spectra or chromatogram data.";
}
LogUpdate?.Invoke(msg, _info);
StatusUpdate?.Invoke(msg, ProgressBarStyle.Continuous, _info);
}
if (StatusUpdate != null && msd.run.spectrumList != null)
{
StatusUpdate(String.Format("Processing ({0} of {1})",
DataGridViewProgressCell.MessageSpecialValue.CurrentValue,
DataGridViewProgressCell.MessageSpecialValue.Maximum),
ProgressBarStyle.Continuous, _info);
}
// write out the new data file
msg = String.Format("Writing \"{0}\"...", deduplicatedFilename);
LogUpdate?.Invoke(msg, _info);
StatusUpdate?.Invoke(msg, ProgressBarStyle.Continuous, _info);
MSDataFile.write(msd, deduplicatedFilename, config.WriteConfig, ilr);
ilr.removeListener(this);
}
finally
{
msd.Dispose();
}
}
}
}
public MsnDataScan(int spectrumNumber, int msnOrder, MSDataFile parentFile = null)
: base(spectrumNumber, msnOrder, parentFile)
{
}
public void SetRawFile(MSDataFile dataFile)
{
MsnDataScan scan = dataFile[ScanNumber] as MsnDataScan;
IsolationMZ = scan.IsolationRange.Mean;
Spectrum = dataFile.GetReadOnlyMZSpectrum(ScanNumber, true);
ScanWidth = scan.MzRange.Width;
}
public static void RawFileToCsv <T>(MSDataFile <T> msDataFile, string outputFilePath) where T : ISpectrum
{
// See the BasicCsvWriting example for more details
Console.WriteLine("Writing file to: " + outputFilePath);
// The main field delimiter, for CSV it is a comma
const char delimiter = ',';
using (StreamWriter writer = new StreamWriter(outputFilePath))
{
// Now that the stream is open, we can a line of text to it to serve as the header row.
// CSV formats are just text files with fields separated by commas.
writer.WriteLine("Spectrum Number,MS Level,Precursor m/z,# of Peaks in Spectrum,m/z Range");
// The using statement on the msDataFile will ensure that things are properly disposed of after
// you are done using the file, or if an exception has occurred.
using (msDataFile)
{
// MsDataFiles require opening their data connection manually.
msDataFile.Open();
// Simply loop over every data scan in the file
foreach (MSDataScan <T> scan in msDataFile)
{
StringBuilder sb = new StringBuilder();
sb.Append(scan.SpectrumNumber);
sb.Append(delimiter);
sb.Append(scan.MsnOrder);
sb.Append(delimiter);
// We need to check if this is an MS1 or MS2 scan. Both scans are of type MSDataScan,
// but for MS2 scans, there is additional information (precursor m/z for example). So we need
// to cast it to MsnDataScan to access those properties.
// Try casting using the 'as' keyword. It will either return the cast object or null, so we need to
// check for null before trying to access a property of it.
MsnDataScan <T> msnScan = scan as MsnDataScan <T>;
if (msnScan != null)
{
// It is a MS2 scan
sb.Append(msnScan.GetPrecursorMz());
}
else
{
// It is a MS1 scan, so no precursor information. So lets put Not an Number in this column.
// you could skip this if you want to have blank cells.
sb.Append(double.NaN);
}
sb.Append(delimiter);
// We can just use the original scan object now
sb.Append(scan.MassSpectrum.Count);
sb.Append(delimiter);
sb.Append(scan.MzRange);
writer.WriteLine(sb.ToString());
}
}
}
}
public void UpdatePsmInformation(MSDataFile dataFile, bool is2dFDR = true, bool useMedian = true, double evalueThreshold = 1e-3)
{
List<double> errors = new List<double>();
MaximumPrecursorMassError = 0;
int count = 0;
int msms = 0;
int ms = 0;
int localMSMS = -1;
List<int> msmsBetweenMS = new List<int>();
List<double> injectionTimes = new List<double>();
for(int sn = dataFile.FirstSpectrumNumber; sn < dataFile.LastSpectrumNumber; sn++)
{
int order = dataFile.GetMsnOrder(sn);
if (order == 1)
{
ms++;
if(localMSMS >= 0)
msmsBetweenMS.Add(localMSMS);
localMSMS = 0;
}
else
{
localMSMS++;
msms++;
injectionTimes.Add(dataFile.GetInjectionTime(sn));
}
}
MaxMSMSScansBetweenMS = msmsBetweenMS.Max();
AverageMSMSSCansBetweenMS = msmsBetweenMS.Average();
TotalMSMSscans = msms;
TotalMSscans = ms;
AverageMSMSInjectionTime = injectionTimes.Average();
MaxMSMSInjectionTime = injectionTimes.Max();
foreach (KeyValuePair<int, SortedMaxSizedContainer<PSM>> kvp in _data)
{
int scanNumber = kvp.Key;
SortedMaxSizedContainer<PSM> psms = kvp.Value;
double isolationMZ = dataFile.GetPrecusorMz(scanNumber);
foreach (PSM psm in psms)
{
psm.IsolationMz = isolationMZ;
double isolationMass = Mass.MassFromMz(isolationMZ, psm.Charge);
double theoreticalMass = psm.MonoisotopicMass;
int nominalMassOffset;
double adjustedIsolationMass;
Tolerance tolerancePPM = Tolerance.CalculatePrecursorMassError(theoreticalMass,
isolationMass, out nominalMassOffset, out adjustedIsolationMass);
psm.AdjustedIsolationMass = adjustedIsolationMass;
psm.IsotopeSelected = nominalMassOffset;
if(!HasPPMInfo)
psm.PrecursorMassError = tolerancePPM.Value;
double positive = Math.Abs(psm.PrecursorMassError);
if (positive > MaximumPrecursorMassError)
{
MaximumPrecursorMassError = positive;
}
if (psm.FdrScoreMetric <= evalueThreshold)
{
errors.Add(psm.PrecursorMassError);
}
count++;
}
}
SystematicPrecursorMassError = useMedian ? GetMedianValue(errors) : errors.Average();
// Adjust all psms to
foreach (PSM psm in PeptideSpectralMatches)
{
psm.CorrectedPrecursorMassError = psm.PrecursorMassError - SystematicPrecursorMassError;
}
}
public bool SetInputFile( string filepath )
{
MSDataFile tempInterface;
try
{
OnStatusReport( "Loading metadata from source file..." );
OnProgressReport( 0 );
tempInterface = new MSDataFile(filepath);
pwiz.CLI.msdata.ChromatogramList cl = tempInterface.run.chromatogramList;
pwiz.CLI.msdata.SpectrumList sl = tempInterface.run.spectrumList;
int ticIndex = cl.findNative("TIC");
if( ticIndex < cl.size() )
{
pwiz.CLI.msdata.Chromatogram tic = cl.chromatogram(ticIndex, true);
chromatograms.Add( new Chromatogram( this, tic ) );
}
CVParam spectrumType = tempInterface.fileDescription.fileContent.cvParamChild( CVID.MS_spectrum_type );
if( spectrumType.cvid == CVID.CVID_Unknown && !sl.empty() )
spectrumType = sl.spectrum(0).cvParamChild( CVID.MS_spectrum_type );
if( spectrumType.cvid == CVID.MS_SRM_spectrum )
{
if( cl.empty() )
throw new Exception( "Error loading metadata: SRM file contains no chromatograms" );
// load the rest of the chromatograms
for( int i = 0; i < cl.size(); ++i )
{
if( i == ticIndex )
continue;
pwiz.CLI.msdata.Chromatogram c = cl.chromatogram( i );
OnStatusReport( String.Format( "Loading chromatograms from source file ({0} of {1})...",
( i + 1 ), cl.size() ) );
OnProgressReport( ( i + 1 ) * 100 / cl.size() );
chromatograms.Add( new Chromatogram( this, c ) );
}
} else if( spectrumType.cvid == CVID.MS_MS1_spectrum ||
spectrumType.cvid == CVID.MS_MSn_spectrum )
{
// get all scans by sequential access
for( int i = 0; i < sl.size(); ++i )
{
pwiz.CLI.msdata.Spectrum s = sl.spectrum( i );
if( ( ( i + 1 ) % 100 ) == 0 || ( i + 1 ) == sl.size() )
{
OnStatusReport( String.Format( "Loading spectra from source file ({0} of {1})...",
( i + 1 ), sl.size() ) );
OnProgressReport( ( i + 1 ) * 100 / sl.size() );
}
spectra.Add( new MassSpectrum( this, s ) );
}
} else
throw new Exception( "Error loading metadata: unable to open files with spectrum type \"" + spectrumType.name + "\"" );
OnStatusReport( "Finished loading source metadata." );
OnProgressReport( 100 );
} catch( Exception ex )
{
string message = "SeeMS encountered an error reading metadata from \"" + filepath + "\" (" + ex.Message + ")";
if( ex.InnerException != null )
message += "\n\nAdditional information: " + ex.InnerException.Message;
MessageBox.Show( message,
"Error reading source metadata",
MessageBoxButtons.OK, MessageBoxIcon.Error, MessageBoxDefaultButton.Button1,
0, false );
OnStatusReport( "Failed to read source metadata." );
return false;
}
return true;
}
/// <summary>
/// write out a subset of high quality spectra based on ScanRanker metrics file
/// using ProteoWizard library
/// </summary>
public void Write()
{
foreach (FileInfo file in inFileList)
{
string fileBaseName = Path.GetFileNameWithoutExtension(file.FullName);
string metricsFileName = fileBaseName + metricsFileSuffix + ".txt";
string outFileName = fileBaseName + outFileSuffix + "." + outFormat;
Workspace.SetText("\r\nStart writing high quality spectra for file: " + file.Name + " ...\r\n\r\n");
if (File.Exists(outFileName))
{
File.Delete(outFileName);
}
if (!File.Exists(metricsFileName))
{
Workspace.SetText("\r\nError: Cannot find quality metrics file: " + metricsFileName + " in output directory!");
Workspace.ChangeButtonTo("Close");
return;
}
//List<int> allIndices = new List<int>();
//List<int> highQualIndices = new List<int>();
List<string> allIndices = new List<string>();
List<string> highQualIndices = new List<string>();
// read metrics file, split and get high quality spectra indecies from the second column
try
{
Workspace.SetText("\r\nExtracting scan index from metrics file: " + metricsFileName);
using (TextReader tr = File.OpenText(metricsFileName))
{
tr.ReadLine(); // read the header line but do nothing, first three lines are header
tr.ReadLine(); // read the header line but do nothing
tr.ReadLine(); // read the header line but do nothing
string line = string.Empty;
while ((line = tr.ReadLine()) != null)
{
string[] items = line.Split('\t');
//int index = Convert.ToInt32(items[1]); //index
string index = Convert.ToString(items[1]); //nativeID
if (!allIndices.Exists(element => element == index)) // remove duplicate index
{
allIndices.Add(index);
}
}
}
}
catch (Exception exc)
{
//throw new Exception("Error in reading metrics file for spectra removal\r\n",exc);
Workspace.SetText("\r\nError in reading metrics file for spectra removal\r\n");
Workspace.ChangeButtonTo("Close");
throw new Exception(exc.Message);
}
// get indices for high quality spectra
Workspace.SetText("\r\nGenerating indices of high quality spectra");
int numOutputSpectra = Convert.ToInt32(allIndices.Count * cutoff);
highQualIndices = allIndices.GetRange(0, numOutputSpectra);
//highQualIndices.Sort();
//var predicate = new SpectrumList_FilterPredicate_IndexSet();
//foreach (int i in highQualIndices)
//{
// predicate.indexSet.Add(i);
//}
var predicate = new SpectrumList_FilterPredicate_NativeIDSet();
foreach (string i in highQualIndices)
{
predicate.nativeIDSet.Add(i);
}
//var sorterPredicate = new SpectrumList_SorterPredicate_IndexSet();
//foreach (int i in highQualIndices)
//{
// sorterPredicate.indexSet.Add(i);
//}
//MSDataFile.WriteConfig writeConfig = new MSDataFile.WriteConfig(MSDataFile.Format.Format_mzXML);
MSDataFile.WriteConfig writeConfig = new MSDataFile.WriteConfig();
if (outFormat.Equals("mzXML") || outFormat.Equals("mzxml"))
{
writeConfig.format = MSDataFile.Format.Format_mzXML;
}
else if (outFormat.Equals("mzML") || outFormat.Equals("mzml"))
{
writeConfig.format = MSDataFile.Format.Format_mzML;
}
else if (outFormat.Equals("MGF") || outFormat.Equals("mgf"))
{
writeConfig.format = MSDataFile.Format.Format_MGF;
}
else if (outFormat.Equals("MS2") || outFormat.Equals("ms2"))
{
writeConfig.format = MSDataFile.Format.Format_MS2;
}
else
{
MessageBox.Show("Plese select output format");
}
writeConfig.precision = MSDataFile.Precision.Precision_32;
try
{
Workspace.SetText("\r\nWriting high quality spectra to file: " + outFileName);
using (var msFile = new MSDataFile(file.FullName))
{
var indexSet = new string[highQualIndices.Count];
var sl = msFile.run.spectrumList;
for (int i=0; i < highQualIndices.Count; ++i)
{
string id = highQualIndices[i];
int index = sl.find(id);
if (index == sl.size())
throw new Exception("nativeID \"" + id + "\" not found in file");
indexSet[i] = index.ToString();
}
var indexSetString = String.Join(" ", indexSet);
var predicate2 = new SpectrumList_FilterPredicate_IndexSet(indexSetString);
var filter = new SpectrumList_Filter(msFile.run.spectrumList, predicate2);
msFile.run.spectrumList = filter;
//msFile.run.spectrumList = new SpectrumList_Sorter(msFile.run.spectrumList, new SpectrumList_Sorter_LessThan( sorterPredicate.lessThan ));
//msFile.run.spectrumList = new SpectrumList_Sorter(msFile.run.spectrumList, new SpectrumList_Sorter_LessThan(lessThan));
//Workspace.SetText("\r\nFinished msFile.run.spectrumList");
msFile.write(outFileName, writeConfig);
}
}
catch (Exception exc)
{
//throw new Exception("Error in writiing new spectra file", exc);
Workspace.SetText("\r\nError in writing new spectra file\r\n");
Workspace.ChangeButtonTo("Close");
throw new Exception(exc.Message);
}
Workspace.SetText("\r\nFinished writing high quality spectra for file: " + file.Name + " \r\n\r\n");
}// end of foreach file
Workspace.SetText("\r\nFinished writing high quality spectra!");
Workspace.ChangeButtonTo("Close");
} // end of write()
static void openButton_Click(object sender, EventArgs e)
{
string filepath = _fileTextBox.Text;
if (!File.Exists(filepath))
{
MessageBox.Show("That filepath does not exist.", "404 File not found", MessageBoxButtons.OK, MessageBoxIcon.Error);
return;
}
try
{
var msd = new MSDataFile(filepath);
var sl = msd.run.spectrumList;
MessageBox.Show(String.Format("The file has {0} spectra.", sl.size()), "Spectra Count");
}
catch (Exception ex)
{
string message = ex.ToString();
if (ex.InnerException != null)
message += "\n\nAdditional information: " + ex.InnerException.ToString();
MessageBox.Show(message,
"Error opening file",
MessageBoxButtons.OK, MessageBoxIcon.Error, MessageBoxDefaultButton.Button1,
0, false);
}
}
public void AddMSDataFile(MSDataFile<ISpectrum> dataFile)
{
_dataFiles.Add(dataFile.Name, dataFile);
}
public void AddMSDataFile(MSDataFile dataFile)
{
_dataFiles.Add(dataFile.Name, dataFile);
}
void processFile(string filename, Config config, ReaderList readers)
{
// read in data file
using (var msdList = new MSDataList())
{
string msg = String.Format("Opening file \"{0}\" for read...", filename);
if (LogUpdate != null)
{
LogUpdate(msg, _info);
}
if (StatusUpdate != null)
{
StatusUpdate(msg, ProgressBarStyle.Marquee, _info);
}
readers.read(filename, msdList);
foreach (var msd in msdList)
{
var outputFilename = config.outputFilename(filename, msd);
if (filename == outputFilename)
{
throw new ArgumentException("Output filepath is the same as input filepath");
}
if (StatusUpdate != null)
{
StatusUpdate("Waiting...", ProgressBarStyle.Marquee, _info);
}
// only one thread
lock (calculateSHA1Mutex)
{
if (LogUpdate != null)
{
LogUpdate("Calculating SHA1 checksum...", _info);
}
if (StatusUpdate != null)
{
StatusUpdate("Calculating SHA1 checksum...", ProgressBarStyle.Marquee, _info);
}
MSDataFile.calculateSHA1Checksums(msd);
}
if (LogUpdate != null)
{
LogUpdate("Processing...", _info);
}
if (StatusUpdate != null)
{
StatusUpdate("Processing...", ProgressBarStyle.Marquee, _info);
}
SpectrumListFactory.wrap(msd, config.Filters);
if ((msd.run.spectrumList == null) || msd.run.spectrumList.empty())
{
if ((msd.run.chromatogramList != null) && !msd.run.chromatogramList.empty())
{
msg = "Note: input contains only chromatogram data.";
switch (config.WriteConfig.format)
{
case MSDataFile.Format.Format_MZ5:
case MSDataFile.Format.Format_mzML:
break;
default:
msg += " The selected output format can only represent spectra. Consider using mzML instead.";
break;
}
}
else
{
msg = "Note: input contains no spectra or chromatogram data.";
}
if (LogUpdate != null)
{
LogUpdate(msg, _info);
}
if (StatusUpdate != null)
{
StatusUpdate(msg, ProgressBarStyle.Continuous, _info);
}
}
if (StatusUpdate != null && msd.run.spectrumList != null)
{
StatusUpdate(String.Format("Processing ({0} of {1})",
DataGridViewProgressCell.MessageSpecialValue.CurrentValue,
DataGridViewProgressCell.MessageSpecialValue.Maximum),
ProgressBarStyle.Continuous, _info);
}
// write out the new data file
var ilr = new IterationListenerRegistry();
ilr.addListener(this, 100);
msg = String.Format("Writing \"{0}\"...", outputFilename);
if (LogUpdate != null)
{
LogUpdate(msg, _info);
}
if (StatusUpdate != null)
{
StatusUpdate(msg, ProgressBarStyle.Continuous, _info);
}
MSDataFile.write(msd, outputFilename, config.WriteConfig, ilr);
ilr.removeListener(this);
}
}
}
private void TestPWiz(string strFilePath)
{
const bool RUN_BENCHMARKS = false;
try
{
var objPWiz2 = new MSDataFile(strFilePath);
Console.WriteLine("Spectrum count: " + objPWiz2.run.spectrumList.size());
Console.WriteLine();
if (objPWiz2.run.spectrumList.size() > 0)
{
var intSpectrumIndex = 0;
do
{
var oSpectrum = objPWiz2.run.spectrumList.spectrum(intSpectrumIndex, getBinaryData: true);
pwiz.CLI.data.CVParam param;
if (oSpectrum.scanList.scans.Count > 0)
{
if (clsProteowizardDataParser.TryGetCVParam(oSpectrum.scanList.scans[0].cvParams, pwiz.CLI.cv.CVID.MS_scan_start_time, out param))
{
var intScanNum = intSpectrumIndex + 1;
var dblStartTimeMinutes = param.timeInSeconds() / 60.0;
Console.WriteLine("ScanIndex " + intSpectrumIndex + ", Scan " + intScanNum + ", Elution Time " + dblStartTimeMinutes + " minutes");
}
}
// Use the following to determine info on this spectrum
if (clsProteowizardDataParser.TryGetCVParam(oSpectrum.cvParams, pwiz.CLI.cv.CVID.MS_ms_level, out param))
{
int.TryParse(param.value, out _);
}
// Use the following to get the MZs and Intensities
var oMZs = oSpectrum.getMZArray();
oSpectrum.getIntensityArray();
if (oMZs.data.Count > 0)
{
Console.WriteLine(" Data count: " + oMZs.data.Count);
// ReSharper disable once ConditionIsAlwaysTrueOrFalse
if (RUN_BENCHMARKS)
{
double dblTIC1 = 0;
double dblTIC2 = 0;
var dtStartTime = default(DateTime);
var dtEndTime = default(DateTime);
double dtRunTimeSeconds1 = 0;
double dtRunTimeSeconds2 = 0;
const int LOOP_ITERATIONS = 2000;
// Note from Matt Chambers (matt.chambers42 at gmail)
// Repeatedly accessing items directly via oMZs.data() can be very slow
// With 700 points and 2000 iterations, it takes anywhere from 0.6 to 1.1 seconds to run from dtStartTime to dtEndTime
dtStartTime = DateTime.Now;
for (var j = 1; j <= LOOP_ITERATIONS; j++)
{
for (var intIndex = 0; intIndex <= oMZs.data.Count - 1; intIndex++)
{
dblTIC1 += oMZs.data[intIndex];
}
}
dtEndTime = DateTime.Now;
dtRunTimeSeconds1 = dtEndTime.Subtract(dtStartTime).TotalSeconds;
// The preferred method is to copy the data from .data to a locally-stored mzArray var
// With 700 points and 2000 iterations, it takes 0.016 seconds to run from dtStartTime to dtEndTime
dtStartTime = DateTime.Now;
for (var j = 1; j <= LOOP_ITERATIONS; j++)
{
var oMzArray = oMZs.data;
for (var intIndex = 0; intIndex <= oMzArray.Count - 1; intIndex++)
{
dblTIC2 += oMzArray[intIndex];
}
}
dtEndTime = DateTime.Now;
dtRunTimeSeconds2 = dtEndTime.Subtract(dtStartTime).TotalSeconds;
Console.WriteLine(" " + oMZs.data.Count + " points with " + LOOP_ITERATIONS + " iterations gives Runtime1=" + dtRunTimeSeconds1.ToString("0.0##") + " sec. vs. Runtime2=" + dtRunTimeSeconds2.ToString("0.0##") + " sec.");
if (Math.Abs(dblTIC1 - dblTIC2) > float.Epsilon)
{
Console.WriteLine(" TIC values don't agree; this is unexpected");
}
}
}
if (intSpectrumIndex < 25)
{
intSpectrumIndex += 1;
}
else
{
intSpectrumIndex += 50;
}
} while (intSpectrumIndex < objPWiz2.run.spectrumList.size());
}
if (objPWiz2.run.chromatogramList.size() > 0)
{
var intChromIndex = 0;
do
{
var oTimeIntensityPairList = new TimeIntensityPairList();
// Note that even for a small .Wiff file (1.5 MB), obtaining the Chromatogram list will take some time (20 to 60 seconds)
// The chromatogram at index 0 should be the TIC
// The chromatogram at index >=1 will be each SRM
var oChromatogram = objPWiz2.run.chromatogramList.chromatogram(intChromIndex, getBinaryData: true);
// Determine the chromatogram type
if (clsProteowizardDataParser.TryGetCVParam(oChromatogram.cvParams, pwiz.CLI.cv.CVID.MS_TIC_chromatogram, out var param))
{
// Obtain the data
oChromatogram.getTimeIntensityPairs(ref oTimeIntensityPairList);
}
if (clsProteowizardDataParser.TryGetCVParam(oChromatogram.cvParams, pwiz.CLI.cv.CVID.MS_selected_reaction_monitoring_chromatogram, out param))
{
// Obtain the SRM scan
oChromatogram.getTimeIntensityPairs(ref oTimeIntensityPairList);
}
intChromIndex += 1;
} while (intChromIndex < 50 && intChromIndex < objPWiz2.run.chromatogramList.size());
}
}
catch (Exception ex)
{
OnErrorEvent("Error using ProteoWizard reader: " + ex.Message, ex);
}
}
private void writeUnidentifiedSpectra(string spectraFilename,
string outFileSuffix,
List <string> unidentifiedSpectra,
float cutoff,
string outFormat)
{
int numOutputSpectra = Convert.ToInt32(unidentifiedSpectra.Count * cutoff);
//List<int> highQualIndices;
List <string> highQualIndices;
highQualIndices = unidentifiedSpectra.GetRange(0, numOutputSpectra);
//var predicate = new SpectrumList_FilterPredicate_IndexSet();
//foreach (int i in highQualIndices)
//{
// predicate.indexSet.Add(i);
//}
var predicate = new SpectrumList_FilterPredicate_NativeIDSet();
foreach (string i in highQualIndices)
{
predicate.nativeIDSet.Add(i);
}
//MSDataFile.WriteConfig writeConfig = new MSDataFile.WriteConfig(MSDataFile.Format.Format_mzXML);
MSDataFile.WriteConfig writeConfig = new MSDataFile.WriteConfig();
if (outFormat.Equals("mzXML") || outFormat.Equals("mzxml"))
{
writeConfig.format = MSDataFile.Format.Format_mzXML;
}
else if (outFormat.Equals("mzML") || outFormat.Equals("mzml"))
{
writeConfig.format = MSDataFile.Format.Format_mzML;
}
else if (outFormat.Equals("MGF") || outFormat.Equals("mgf"))
{
writeConfig.format = MSDataFile.Format.Format_MGF;
}
else if (outFormat.Equals("MS2") || outFormat.Equals("ms2"))
{
writeConfig.format = MSDataFile.Format.Format_MS2;
}
else
{
MessageBox.Show("Plese select output format");
}
writeConfig.precision = MSDataFile.Precision.Precision_32;
try
{
string outFileName = Path.GetFileNameWithoutExtension(spectraFilename) + outFileSuffix + "-Top" + (recoveryCutoff * 100).ToString()
+ "PercUnidentSpec." + recoveryOutFormat;
Workspace.SetText("\r\nWriting unidentified high quality spectra to file: " + outFileName);
using (MSDataFile msFile = new MSDataFile(spectraFilename))
{
msFile.run.spectrumList = new SpectrumList_Filter(msFile.run.spectrumList, new SpectrumList_FilterAcceptSpectrum(predicate.accept));
msFile.write(outFileName, writeConfig);
}
}
catch (Exception exc)
{
//throw new Exception("Error in writiing new spectra file", exc);
Workspace.SetText("\r\nError in writing new spectra file\r\n");
Workspace.ChangeButtonTo("Close");
throw new Exception(exc.Message);
}
}
public static void RawFileToCsv(MSDataFile msDataFile, string outputFilePath)
{
// See the BasicCsvWriting example for more details
Console.WriteLine("Writing file to: " + outputFilePath);
// The main field delimiter, for CSV it is a comma
const char delimiter = ',';
using (StreamWriter writer = new StreamWriter(outputFilePath))
{
// Now that the stream is open, we can a line of text to it to serve as the header row.
// CSV formats are just text files with fields separated by commas.
writer.WriteLine("Spectrum Number,MS Level,Precursor m/z,# of Peaks in Spectrum,m/z Range");
// The using statement on the msDataFile will ensure that things are properly disposed of after
// you are done using the file, or if an exception has occurred.
using (msDataFile)
{
// MsDataFiles require opening their data connection manually.
msDataFile.Open();
// Simply loop over every data scan in the file
foreach (MSDataScan scan in msDataFile)
{
StringBuilder sb = new StringBuilder();
sb.Append(scan.SpectrumNumber);
sb.Append(delimiter);
sb.Append(scan.MsnOrder);
sb.Append(delimiter);
// We need to check if this is an MS1 or MS2 scan. Both scans are of type MSDataScan,
// but for MS2 scans, there is additional information (precursor m/z for example). So we need
// to cast it to MsnDataScan to access those properties.
// Try casting using the 'as' keyword. It will either return the cast object or null, so we need to
// check for null before trying to access a property of it.
MsnDataScan msnScan = scan as MsnDataScan;
if (msnScan != null)
{
// It is a MS2 scan
sb.Append(msnScan.PrecursorMz);
}
else
{
// It is a MS1 scan, so no precursor information. So lets put Not an Number in this column.
// you could skip this if you want to have blank cells.
sb.Append(double.NaN);
}
sb.Append(delimiter);
// We can just use the original scan object now
sb.Append(scan.MassSpectrum.Count);
sb.Append(delimiter);
sb.Append(scan.MzRange);
writer.WriteLine(sb.ToString());
}
}
}
}
void processFile(string filename, Config config, ReaderList readers)
{
if (LogUpdate != null)
{
LogUpdate("Opening file...", _info);
}
if (StatusUpdate != null)
{
StatusUpdate("Opening file...", ProgressBarStyle.Marquee, _info);
}
// read in data file
using (var msdList = new MSDataList())
{
readers.read(filename, msdList);
foreach (var msd in msdList)
{
var outputFilename = config.outputFilename(filename, msd);
if (filename == outputFilename)
{
throw new ArgumentException("Output filepath is the same as input filepath");
}
if (LogUpdate != null)
{
LogUpdate("Calculating SHA1 checksum...", _info);
}
if (StatusUpdate != null)
{
StatusUpdate("Calculating SHA1 checksum...", ProgressBarStyle.Marquee, _info);
}
// only one thread
lock (calculateSHA1Mutex)
MSDataFile.calculateSHA1Checksums(msd);
if (LogUpdate != null)
{
LogUpdate("Processing...", _info);
}
if (StatusUpdate != null)
{
StatusUpdate("Processing...", ProgressBarStyle.Marquee, _info);
}
SpectrumListFactory.wrap(msd, config.Filters);
if (StatusUpdate != null && msd.run.spectrumList != null)
{
StatusUpdate(String.Format("Processing ({0} of {1})",
DataGridViewProgressCell.MessageSpecialValue.CurrentValue,
DataGridViewProgressCell.MessageSpecialValue.Maximum),
ProgressBarStyle.Continuous, _info);
}
// write out the new data file
IterationListenerRegistry ilr = null;
ilr = new IterationListenerRegistry();
ilr.addListener(this, 100);
MSDataFile.write(msd, outputFilename, config.WriteConfig, ilr);
}
}
}
public void MyTestCleanup()
{
dataFile.Dispose();
dataFile = null;
}
/// <summary>
/// write out a subset of high quality spectra based on ScanRanker metrics file
/// using ProteoWizard library
/// </summary>
public void Write()
{
foreach (FileInfo file in inFileList)
{
string fileBaseName = Path.GetFileNameWithoutExtension(file.FullName);
string metricsFileName = fileBaseName + metricsFileSuffix + ".txt";
string outFileName = fileBaseName + outFileSuffix + "." + outFormat;
Workspace.SetText("\r\nStart writing high quality spectra for file: " + file.Name + " ...\r\n\r\n");
if (File.Exists(outFileName))
{
File.Delete(outFileName);
}
if (!File.Exists(metricsFileName))
{
Workspace.SetText("\r\nError: Cannot find quality metrics file: " + metricsFileName + " in output directory!");
Workspace.ChangeButtonTo("Close");
return;
}
//List<int> allIndices = new List<int>();
//List<int> highQualIndices = new List<int>();
List <string> allIndices = new List <string>();
List <string> highQualIndices = new List <string>();
// read metrics file, split and get high quality spectra indecies from the second column
try
{
Workspace.SetText("\r\nExtracting scan index from metrics file: " + metricsFileName);
using (TextReader tr = File.OpenText(metricsFileName))
{
tr.ReadLine(); // read the header line but do nothing, first three lines are header
tr.ReadLine(); // read the header line but do nothing
tr.ReadLine(); // read the header line but do nothing
string line = string.Empty;
while ((line = tr.ReadLine()) != null)
{
string[] items = line.Split('\t');
//int index = Convert.ToInt32(items[1]); //index
string index = Convert.ToString(items[1]); //nativeID
if (!allIndices.Exists(element => element == index)) // remove duplicate index
{
allIndices.Add(index);
}
}
}
}
catch (Exception exc)
{
//throw new Exception("Error in reading metrics file for spectra removal\r\n",exc);
Workspace.SetText("\r\nError in reading metrics file for spectra removal\r\n");
Workspace.ChangeButtonTo("Close");
throw new Exception(exc.Message);
}
// get indices for high quality spectra
Workspace.SetText("\r\nGenerating indices of high quality spectra");
int numOutputSpectra = Convert.ToInt32(allIndices.Count * cutoff);
highQualIndices = allIndices.GetRange(0, numOutputSpectra);
//highQualIndices.Sort();
//var predicate = new SpectrumList_FilterPredicate_IndexSet();
//foreach (int i in highQualIndices)
//{
// predicate.indexSet.Add(i);
//}
var predicate = new SpectrumList_FilterPredicate_NativeIDSet();
foreach (string i in highQualIndices)
{
predicate.nativeIDSet.Add(i);
}
//var sorterPredicate = new SpectrumList_SorterPredicate_IndexSet();
//foreach (int i in highQualIndices)
//{
// sorterPredicate.indexSet.Add(i);
//}
//MSDataFile.WriteConfig writeConfig = new MSDataFile.WriteConfig(MSDataFile.Format.Format_mzXML);
MSDataFile.WriteConfig writeConfig = new MSDataFile.WriteConfig();
if (outFormat.Equals("mzXML") || outFormat.Equals("mzxml"))
{
writeConfig.format = MSDataFile.Format.Format_mzXML;
}
else if (outFormat.Equals("mzML") || outFormat.Equals("mzml"))
{
writeConfig.format = MSDataFile.Format.Format_mzML;
}
else if (outFormat.Equals("MGF") || outFormat.Equals("mgf"))
{
writeConfig.format = MSDataFile.Format.Format_MGF;
}
else if (outFormat.Equals("MS2") || outFormat.Equals("ms2"))
{
writeConfig.format = MSDataFile.Format.Format_MS2;
}
else
{
MessageBox.Show("Plese select output format");
}
writeConfig.precision = MSDataFile.Precision.Precision_32;
try
{
Workspace.SetText("\r\nWriting high quality spectra to file: " + outFileName);
using (var msFile = new MSDataFile(file.FullName))
{
var indexSet = new string[highQualIndices.Count];
var sl = msFile.run.spectrumList;
for (int i = 0; i < highQualIndices.Count; ++i)
{
string id = highQualIndices[i];
int index = sl.find(id);
if (index == sl.size())
{
throw new Exception("nativeID \"" + id + "\" not found in file");
}
indexSet[i] = index.ToString();
}
var indexSetString = String.Join(" ", indexSet);
var predicate2 = new SpectrumList_FilterPredicate_IndexSet(indexSetString);
var filter = new SpectrumList_Filter(msFile.run.spectrumList, predicate2);
msFile.run.spectrumList = filter;
//msFile.run.spectrumList = new SpectrumList_Sorter(msFile.run.spectrumList, new SpectrumList_Sorter_LessThan( sorterPredicate.lessThan ));
//msFile.run.spectrumList = new SpectrumList_Sorter(msFile.run.spectrumList, new SpectrumList_Sorter_LessThan(lessThan));
//Workspace.SetText("\r\nFinished msFile.run.spectrumList");
msFile.write(outFileName, writeConfig);
}
}
catch (Exception exc)
{
//throw new Exception("Error in writiing new spectra file", exc);
Workspace.SetText("\r\nError in writing new spectra file\r\n");
Workspace.ChangeButtonTo("Close");
throw new Exception(exc.Message);
}
Workspace.SetText("\r\nFinished writing high quality spectra for file: " + file.Name + " \r\n\r\n");
}// end of foreach file
Workspace.SetText("\r\nFinished writing high quality spectra!");
Workspace.ChangeButtonTo("Close");
} // end of write()
private SourceInfo[] getSourceInfo( DirectoryInfo dirInfo, bool getDetails )
{
var sourceInfoList = new List<SourceInfo>();
sourceInfoList.Add( new SourceInfo() );
sourceInfoList[0].type = getSourceType( dirInfo );
sourceInfoList[0].name = dirInfo.Name;
sourceInfoList[0].dateModified = dirInfo.LastWriteTime;
sourceInfoList[0].hasDetails = getDetails;
if( !getDetails )
return sourceInfoList.ToArray();
if( sourceInfoList[0].type == "File Folder" )
{
return sourceInfoList.ToArray();
} else if( sourceInfoList[0].type != String.Empty )
{
try
{
MSDataFile msInfo = new MSDataFile( dirInfo.FullName );
sourceInfoList[0].populateFromMSData( msInfo );
} catch( ThreadAbortException )
{
return null;
} catch
{
sourceInfoList[0].spectra = 0;
sourceInfoList[0].type = "Invalid " + sourceInfoList[0].type;
}
sourceInfoList[0].size = 0;
sourceInfoList[0].dateModified = DateTime.MinValue;
foreach( FileInfo fileInfo in dirInfo.GetFiles( "*", SearchOption.AllDirectories ) )
{
sourceInfoList[0].size += (UInt64) fileInfo.Length;
if( fileInfo.LastWriteTime > sourceInfoList[0].dateModified )
sourceInfoList[0].dateModified = fileInfo.LastWriteTime;
}
return sourceInfoList.ToArray();
}
return null;
}
private void listView_ItemSelectionChanged( object sender, ListViewItemSelectionChangedEventArgs e )
{
if( listView.SelectedItems.Count > 1 )
{
List<string> dataSourceList = new List<string>();
foreach( ListViewItem item in listView.SelectedItems )
{
if( item.SubItems[1].Text != "File Folder" )
dataSourceList.Add( String.Format( "\"{0}\"", item.SubItems[0].Text ) );
}
sourcePathTextBox.Text = String.Join( " ", dataSourceList.ToArray() );
ticGraphControl.GraphPane.GraphObjList.Clear();
ticGraphControl.GraphPane.CurveList.Clear();
ticGraphControl.Visible = false;
} else if( listView.SelectedItems.Count > 0 )
{
sourcePathTextBox.Text = listView.SelectedItems[0].SubItems[0].Text;
ticGraphControl.GraphPane.GraphObjList.Clear();
ticGraphControl.GraphPane.CurveList.Clear();
string sourcePath = Path.Combine( CurrentDirectory, sourcePathTextBox.Text );
string sourceType = getSourceType( sourcePath );
if( !String.IsNullOrEmpty( sourceType ) &&
sourceType != "File Folder" )
{
using (MSDataFile msData = new MSDataFile( sourcePath ))
using (ChromatogramList cl = msData.run.chromatogramList)
{
if( cl != null && !cl.empty() && cl.find( "TIC" ) != cl.size() )
{
ticGraphControl.Visible = true;
pwiz.CLI.msdata.Chromatogram tic = cl.chromatogram( cl.find( "TIC" ), true );
Map<double, double> sortedFullPointList = new Map<double, double>();
IList<double> timeList = tic.binaryDataArrays[0].data;
IList<double> intensityList = tic.binaryDataArrays[1].data;
int arrayLength = timeList.Count;
for( int i = 0; i < arrayLength; ++i )
sortedFullPointList[timeList[i]] = intensityList[i];
ZedGraph.PointPairList points = new ZedGraph.PointPairList(
new List<double>( sortedFullPointList.Keys ).ToArray(),
new List<double>( sortedFullPointList.Values ).ToArray() );
ZedGraph.LineItem item = ticGraphControl.GraphPane.AddCurve( "TIC", points, Color.Black, ZedGraph.SymbolType.None );
item.Line.IsAntiAlias = true;
ticGraphControl.AxisChange();
ticGraphControl.Refresh();
} else
ticGraphControl.Visible = false;
}
} else
ticGraphControl.Visible = false;
} else
sourcePathTextBox.Text = "";
}
private void listView_ItemSelectionChanged(object sender, ListViewItemSelectionChangedEventArgs e)
{
if (listView.SelectedItems.Count > 1)
{
List <string> dataSourceList = new List <string>();
foreach (ListViewItem item in listView.SelectedItems)
{
if (item.SubItems[1].Text != "File Folder")
{
dataSourceList.Add(String.Format("\"{0}\"", item.SubItems[0].Text));
}
}
sourcePathTextBox.Text = String.Join(" ", dataSourceList.ToArray());
ticGraphControl.GraphPane.GraphObjList.Clear();
ticGraphControl.GraphPane.CurveList.Clear();
ticGraphControl.Visible = false;
}
else if (listView.SelectedItems.Count > 0)
{
sourcePathTextBox.Text = listView.SelectedItems[0].SubItems[0].Text;
ticGraphControl.GraphPane.GraphObjList.Clear();
ticGraphControl.GraphPane.CurveList.Clear();
string sourcePath = Path.Combine(CurrentDirectory, sourcePathTextBox.Text);
string sourceType = getSourceType(sourcePath);
if (!String.IsNullOrEmpty(sourceType) &&
sourceType != "File Folder")
{
using (MSDataFile msData = new MSDataFile(sourcePath))
using (ChromatogramList cl = msData.run.chromatogramList)
{
if (cl != null && !cl.empty() && cl.find("TIC") != cl.size())
{
ticGraphControl.Visible = true;
pwiz.CLI.msdata.Chromatogram tic = cl.chromatogram(cl.find("TIC"), true);
Map <double, double> sortedFullPointList = new Map <double, double>();
IList <double> timeList = tic.binaryDataArrays[0].data;
IList <double> intensityList = tic.binaryDataArrays[1].data;
int arrayLength = timeList.Count;
for (int i = 0; i < arrayLength; ++i)
{
sortedFullPointList[timeList[i]] = intensityList[i];
}
ZedGraph.PointPairList points = new ZedGraph.PointPairList(
new List <double>(sortedFullPointList.Keys).ToArray(),
new List <double>(sortedFullPointList.Values).ToArray());
ZedGraph.LineItem item = ticGraphControl.GraphPane.AddCurve("TIC", points, Color.Black, ZedGraph.SymbolType.None);
item.Line.IsAntiAlias = true;
ticGraphControl.AxisChange();
ticGraphControl.Refresh();
}
else
{
ticGraphControl.Visible = false;
}
}
}
else
{
ticGraphControl.Visible = false;
}
}
else
{
sourcePathTextBox.Text = "";
}
}
private void writeSingleSpectrum(string sourceFile, string nativeID, string outFileName)
{
MSDataFile.WriteConfig writeConfig = new MSDataFile.WriteConfig();
writeConfig.format = MSDataFile.Format.Format_MGF;
writeConfig.precision = MSDataFile.Precision.Precision_32;
//var predicate = new SpectrumList_FilterPredicate_IndexSet();
//predicate.indexSet.Add(nativeID);
var predicate = new SpectrumList_FilterPredicate_NativeIDSet();
predicate.nativeIDSet.Add(nativeID);
try
{
//Workspace.SetText("\r\nWriting selected spectrum to " + outFileName);
MainForm.SetText(this, "Start writing selected spectrum to " + outFileName + "\r\n");
using (MSDataFile msFile = new MSDataFile(sourceFile))
{
msFile.run.spectrumList = new SpectrumList_Filter(msFile.run.spectrumList, new SpectrumList_FilterAcceptSpectrum(predicate.accept));
msFile.write(outFileName, writeConfig);
}
MainForm.SetText(this, "Finished writing selected spectrum to " + outFileName + "\r\n");
}
catch (Exception exc)
{
//throw new Exception("Error in writiing new spectra file", exc);
//Workspace.SetText("\r\nError in writing new spectra file\r\n");
tbPepNovoResult.AppendText("\r\nError in writing new spectra file\r\n");
throw new Exception(exc.Message);
}
}
