public Dictionary <int, int> MakeSequence(string path)
{
Dictionary <int, int> sequence = new Dictionary <int, int>();
ISpectrumReader reader = new ThermoRawSpectrumReader();
reader.Init(path);
ISpectrumProcess process = new PeakPicking();
IFinder finder = new MSFinder(tol);
for (int i = reader.GetFirstScan(); i < reader.GetLastScan(); i++)
{
if (reader.GetMSnOrder(i) < 2)
{
ISpectrum spectrum = reader.GetSpectrum(i);
process.Process(spectrum);
int units = finder.FindGlucoseUnits(spectrum);
if (units > 0)
{
sequence[i] = units;
}
}
}
return(sequence);
}
public void test2()
{
string path = @"C:\Users\Rui Zhang\Downloads\Serum_1_C18_03292019_Ali.raw";
ISpectrumReader reader = new ThermoRawSpectrumReader();
reader.Init(path);
RidgeLineFinder coeffMatrix = new RidgeLineFinder(1.0, 2, 1, 2);
IProcess processer = new PeakPickingCWT(coeffMatrix);
//for (int i = reader.GetFirstScan(); i < reader.GetLastScan(); i++)
int i = 347;
{
if (reader.GetMSnOrder(i) < 2)
{
ISpectrum spectrum = reader.GetSpectrum(i);
List <IPeak> peaks = spectrum.GetPeaks();
spectrum = processer.Process(spectrum);
IAreaCalculator calculator = new TrapezoidalRule();
IBounder bounder = new PerpendicularDrop();
PeakAreaCalculator areaCalculator = new PeakAreaCalculator(calculator, bounder);
areaCalculator.Init(peaks);
foreach (IPeak peak in spectrum.GetPeaks())
{
Console.WriteLine(peak.GetMZ() + " : " + areaCalculator.Area(peak).ToString());
}
}
}
}
public void AreaTest()
{
NGlycanTheoryPeaksBuilder builder = new NGlycanTheoryPeaksBuilder();
builder.SetBuildType(true, false, false);
List <IGlycanPeak> glycans = builder.Build();
ISpectrumReader spectrumReader = new ThermoRawSpectrumReader();
spectrumReader.Init(@"C:\Users\iruiz\Downloads\GUI\compare\data\HBS1_dextrinspkd_C18_10252018.raw");
List <double> ions = new List <double>();
ions.Add(Calculator.proton);
Calculator.To.SetChargeIons(ions);
using (StreamWriter file = new(@"C:\Users\iruiz\Downloads\GUI\compare\data\WriteLines2.csv"))
{
file.WriteLine("glycan,mass,mz,charge,score,area");
//for (int scan = spectrumReader.GetFirstScan(); scan <= spectrumReader.GetLastScan(); scan++)
//{
int scan = 2931; // 3943;
if (spectrumReader.GetMSnOrder(scan) != 1)
{
return;
}
ISpectrum spectrum = spectrumReader.GetSpectrum(scan);
IResultFactory factory = new NGlycanResultFactory();
EnvelopeProcess envelopeProcess = new EnvelopeProcess(10, ToleranceBy.PPM);
MonoisotopicSearcher monoisotopicSearcher = new MonoisotopicSearcher(factory);
IProcess spectrumProcess = new LocalNeighborPicking();
ISpectrumSearch spectrumSearch = new NGlycanSpectrumSearch(glycans,
spectrumProcess, envelopeProcess, monoisotopicSearcher);
List <IResult> results = spectrumSearch.Search(spectrum);
//IAreaCalculator areaCalculator = new TrapezoidalRule();
IXIC xicer = new TIQ3XIC(spectrumReader, 0.01, ToleranceBy.Dalton);
//IXIC xicer = new PeakXIC(areaCalculator, spectrumReader, 0.01, ToleranceBy.Dalton);
foreach (IResult r in results)
{
double area = xicer.Area(r);
string output = r.Glycan().GetGlycan().Name() + "," +
r.Glycan().GetGlycan().Mass().ToString() + "," +
r.GetMZ().ToString() + "," +
r.GetCharge().ToString() + "," +
r.Score().ToString() + "," +
area.ToString();
file.WriteLine(output);
}
//}
}
Assert.Pass();
}
public void NGlycanSearch()
{
IResultFactory factory = new NGlycanResultFactory();
EnvelopeProcess envelopeProcess = new EnvelopeProcess(10, ToleranceBy.PPM);
MonoisotopicSearcher monoisotopicSearcher = new MonoisotopicSearcher(factory);
NGlycanTheoryPeaksBuilder builder = new NGlycanTheoryPeaksBuilder();
builder.SetBuildType(true, false, false);
List <IGlycanPeak> glycans = builder.Build();
IProcess spectrumProcess = new LocalNeighborPicking();
ISpectrumSearch spectrumSearch = new NGlycanSpectrumSearch(glycans,
spectrumProcess, envelopeProcess, monoisotopicSearcher);
ISpectrumReader spectrumReader = new ThermoRawSpectrumReader();
spectrumReader.Init(@"C:\Users\iruiz\Downloads\Serum_dextrinspiked_C18_10162018_2.raw");
for (int scan = spectrumReader.GetFirstScan(); scan <= spectrumReader.GetLastScan(); scan++)
{
if (spectrumReader.GetMSnOrder(scan) != 1)
{
continue;
}
ISpectrum spectrum = spectrumReader.GetSpectrum(scan);
List <IResult> results = spectrumSearch.Search(spectrum);
foreach (IResult r in results)
{
Console.WriteLine(r.Glycan().GetGlycan().Name()
+ ": " + r.Glycan().GetGlycan().Mass().ToString());
List <double> mzList = Calculator.To.ComputeMZ(r.Glycan().HighestPeak(), 3);
Console.WriteLine(string.Join(",", mzList));
Console.WriteLine(r.Score());
foreach (IPeak pk in r.Matches())
{
Console.WriteLine(pk.GetMZ() + " " + pk.GetIntensity());
}
Console.WriteLine();
}
break;
}
Assert.Pass();
}
public void test1()
{
var watch = new System.Diagnostics.Stopwatch();
watch.Start();
string path = @"C:\Users\Rui Zhang\Downloads\Serum_1_C18_03292019_Ali.raw";
ISpectrumReader reader = new ThermoRawSpectrumReader();
reader.Init(path);
//for (int i = reader.GetFirstScan(); i < reader.GetLastScan(); i++)
int i = 342;
RidgeLineFinder coeffMatrix = new RidgeLineFinder(1.0, 2, 1, 2);
{
if (reader.GetMSnOrder(i) < 2)
{
ISpectrum spectrum = reader.GetSpectrum(i);
List <IPeak> peaks = spectrum.GetPeaks();
double[] signal = peaks.Select(p => p.GetIntensity()).ToArray();
SortedDictionary <double, List <double> > matrix =
new SortedDictionary <double, List <double> >();
for (double a = 1; a <= 120; a += 6)
{
double[] processed = CWT.Transform(signal, a);
matrix[a] = processed.ToList();
}
List <RidgeLine> lines = coeffMatrix.Find(spectrum.GetPeaks().Select(p => p.GetMZ()).ToList(),
matrix);
Console.WriteLine(lines.Count);
Console.WriteLine(peaks.Count);
foreach (RidgeLine line in lines)
{
Console.WriteLine(line.Pos);
}
}
//break;
}
Console.WriteLine($"Execution Time: {watch.ElapsedMilliseconds} ms");
//Console.Read();
}
public static Spectrum GetMS1Spectrum(ref ThermoRawSpectrumReader reader,
int scan, ref ISpectrum ms1)
{
// scan header
Spectrum spectrum = new Spectrum
{
id = "scan=" + scan.ToString()
};
double dLowMass = 0;
double dHighMass = 0;
double dTIC = 0;
double dBasePeakMass = 0;
double dBasePeakIntensity = 0;
reader.GetScanHeaderInfoForScanNum(scan, ref dLowMass, ref dHighMass,
ref dTIC, ref dBasePeakMass, ref dBasePeakIntensity);
SetScanHeader(spectrum, dLowMass, dHighMass, dTIC,
dBasePeakMass, dBasePeakIntensity);
// binary data
spectrum.binaryDataArrayList = new BinaryDataArrayList();
SetBinaryDataArrayHeader(spectrum.binaryDataArrayList);
ms1 = reader.GetSpectrum(scan);
//majorPeaks = picking.Process(ms1.GetPeaks());
spectrum.cvParam[0] = new Component.CVParam()
{
cvRef = "MS",
accession = "MS:1000511",
name = "ms level",
value = "1",
};
spectrum.binaryDataArrayList.binaryDataArray[0].binary =
ms1.GetPeaks().SelectMany(p => BitConverter.GetBytes(p.GetMZ())).ToArray();
spectrum.binaryDataArrayList.binaryDataArray[1].binary =
ms1.GetPeaks().SelectMany(p => BitConverter.GetBytes(p.GetIntensity())).ToArray();
spectrum.defaultArrayLength = ms1.GetPeaks().Count.ToString();
spectrum.binaryDataArrayList.binaryDataArray[0].encodedLength =
Convert.ToBase64String(spectrum.binaryDataArrayList.binaryDataArray[0].binary).Length.ToString();
spectrum.binaryDataArrayList.binaryDataArray[1].encodedLength =
Convert.ToBase64String(spectrum.binaryDataArrayList.binaryDataArray[1].binary).Length.ToString();
return(spectrum);
}
public void Read()
{
ISpectrumReader spectrumReader = new ThermoRawSpectrumReader();
spectrumReader.Init(@"C:\Users\iruiz\Downloads\Serum_dextrinspiked_C18_10162018_1.raw");
int count = 0;
for (int scan = spectrumReader.GetFirstScan(); scan <= spectrumReader.GetLastScan(); scan++)
{
if (spectrumReader.GetMSnOrder(scan) == 1)
{
count++;
}
}
Console.WriteLine(count);
Assert.Pass();
}
public void Run()
{
ISpectrumReader reader = new ThermoRawSpectrumReader();
reader.Init(@"C:\Users\iruiz\Desktop\app\ZC_20171218_H95_R1.raw");
ISpectrumFactory creator = new GeneralSpectrumFactory(reader);
Console.WriteLine(creator.GetFirstScan());
Console.WriteLine(creator.GetLastScan());
for (int i = creator.GetFirstScan(); i < creator.GetLastScan(); i++)
{
if (creator.GetMSnOrder(i) == 2)
{
Console.WriteLine(creator.GetActivation(i).ToString());
List <IPeak> peaks = creator.GetSpectrum(i).GetPeaks();
}
}
Console.Read();
}
public void test1()
{
string path = @"C:\Users\Rui Zhang\Downloads\ZC_20171218_C16_R1.raw";
ThermoRawSpectrumReader reader = new ThermoRawSpectrumReader();
reader.Init(path);
ISpectrum ms2 = reader.GetSpectrum(7638);
//IProcess processer = new LocalNeighborPicking();
IProcess processer = new WeightedAveraging(new LocalNeighborPicking());
//RidgeLineFinder coeffMatrix = new RidgeLineFinder(1.0, 2, 1, 2);
//IProcess processer = new PeakPickingCWT(coeffMatrix);
ms2 = processer.Process(ms2);
using (StreamWriter outputFile = new StreamWriter(@"C:\Users\Rui Zhang\Downloads\peak.csv"))
{
outputFile.WriteLine("mz,intensity");
foreach (IPeak pk in ms2.GetPeaks())
{
outputFile.WriteLine(pk.GetMZ().ToString() + "," + pk.GetIntensity().ToString());
}
}
}
public void test2()
{
string path = @"C:\Users\Rui Zhang\Downloads\Serum_1_C18_03292019_Ali.raw";
ISpectrumReader reader = new ThermoRawSpectrumReader();
reader.Init(path);
RidgeLineFinder coeffMatrix = new RidgeLineFinder(1.0, 2, 1, 2);
IProcess processer = new PeakPickingCWT(coeffMatrix);
//for (int i = reader.GetFirstScan(); i < reader.GetLastScan(); i++)
int i = 342;
{
if (reader.GetMSnOrder(i) < 2)
{
ISpectrum spectrum = reader.GetSpectrum(i);
spectrum = processer.Process(spectrum);
foreach (var peak in spectrum.GetPeaks())
{
Console.WriteLine(peak.GetMZ().ToString() + ": " + peak.GetIntensity().ToString());
}
}
}
}
public void ParallelRun(string path, string outputDir, AveragineType type, ChargerType chargerType)
{
string file = Path.GetFileNameWithoutExtension(path) + ".mgf";
string output = Path.Combine(outputDir, file);
ThermoRawSpectrumReader reader = new ThermoRawSpectrumReader();
LocalMaximaPicking picking = new LocalMaximaPicking(ms1PrcisionPPM);
reader.Init(path);
Dictionary <int, List <int> > scanGroup = new Dictionary <int, List <int> >();
int current = -1;
int start = reader.GetFirstScan();
int end = reader.GetLastScan();
for (int i = start; i < end; i++)
{
if (reader.GetMSnOrder(i) == 1)
{
current = i;
scanGroup[i] = new List <int>();
}
else if (reader.GetMSnOrder(i) == 2)
{
scanGroup[current].Add(i);
}
}
List <MS2Info> ms2Infos = new List <MS2Info>();
Parallel.ForEach(scanGroup, (scanPair) =>
{
if (scanPair.Value.Count > 0)
{
ISpectrum ms1 = reader.GetSpectrum(scanPair.Key);
foreach (int i in scanPair.Value)
{
double mz = reader.GetPrecursorMass(i, reader.GetMSnOrder(i));
List <IPeak> ms1Peaks = FilterPeaks(ms1.GetPeaks(), mz, searchRange);
if (ms1Peaks.Count() == 0)
{
continue;
}
// insert pseudo peaks for large gap
List <IPeak> peaks = new List <IPeak>();
double precision = 0.02;
double last = ms1Peaks.First().GetMZ();
foreach (IPeak peak in ms1Peaks)
{
if (peak.GetMZ() - last > precision)
{
peaks.Add(new GeneralPeak(last + precision / 2, 0));
peaks.Add(new GeneralPeak(peak.GetMZ() - precision / 2, 0));
}
peaks.Add(peak);
last = peak.GetMZ();
}
List <IPeak> majorPeaks = picking.Process(peaks);
ICharger charger = new Patterson();
if (chargerType == ChargerType.Fourier)
{
charger = new Fourier();
}
else if (chargerType == ChargerType.Combined)
{
charger = new PattersonFourierCombine();
}
int charge = charger.Charge(peaks, mz - searchRange, mz + searchRange);
// find evelope cluster
EnvelopeProcess envelope = new EnvelopeProcess();
var cluster = envelope.Cluster(majorPeaks, mz, charge);
if (cluster.Count == 0)
{
continue;
}
// find monopeak
Averagine averagine = new Averagine(type);
BrainCSharp braincs = new BrainCSharp();
MonoisotopicSearcher searcher = new MonoisotopicSearcher(averagine, braincs);
MonoisotopicScore result = searcher.Search(mz, charge, cluster);
double precursorMZ = result.GetMZ();
// write mgf
ISpectrum ms2 = reader.GetSpectrum(i);
IProcess processer = new WeightedAveraging(new LocalNeighborPicking());
ms2 = processer.Process(ms2);
MS2Info ms2Info = new MS2Info
{
PrecursorMZ = result.GetMZ(),
PrecursorCharge = charge,
Scan = ms2.GetScanNum(),
Retention = ms2.GetRetention(),
Peaks = ms2.GetPeaks()
};
lock (resultLock)
{
ms2Infos.Add(ms2Info);
}
}
}
readingProgress.Add(scanGroup.Count);
});
ms2Infos = ms2Infos.OrderBy(m => m.Scan).ToList();
using (FileStream ostrm = new FileStream(output, FileMode.OpenOrCreate, FileAccess.Write))
{
using (StreamWriter writer = new StreamWriter(ostrm))
{
foreach (MS2Info ms2 in ms2Infos)
{
WriteMGF(writer, path + ",SCANS=" + ms2.Scan.ToString() + ",PRECURSOR=" + ms2.PrecursorMZ, ms2.PrecursorMZ, ms2.PrecursorCharge,
ms2.Scan, ms2.Retention * 60, reader.GetActivation(ms2.Scan), ms2.Peaks);
writer.Flush();
}
}
}
// update progress
progress.Add();
}
public Run Read(string path, AveragineType type, ChargerType charger, string defaultDataProcessingRef,
ProgressUpdate updater)
{
Run data = new Run();
// init reader
ThermoRawSpectrumReader reader = new ThermoRawSpectrumReader();
LocalMaximaPicking picking = new LocalMaximaPicking(ms1PrcisionPPM);
IProcess process = new WeightedAveraging(new LocalNeighborPicking());
reader.Init(path);
data.spectrumList = new SpectrumList();
Dictionary <int, Spectrum> spectrumMap = new Dictionary <int, Spectrum>();
int start = reader.GetFirstScan();
int end = reader.GetLastScan();
Dictionary <int, List <int> > scanGroup = new Dictionary <int, List <int> >();
int current = -1;
for (int i = start; i < end; i++)
{
if (reader.GetMSnOrder(i) == 1)
{
current = i;
scanGroup[i] = new List <int>();
}
else if (reader.GetMSnOrder(i) == 2)
{
scanGroup[current].Add(i);
}
}
Parallel.ForEach(scanGroup, (scanPair) => {
if (scanPair.Value.Count > 0)
{
int parentScan = scanPair.Key;
ISpectrum ms1 = null;
List <IPeak> majorPeaks = new List <IPeak>();
Spectrum ms1Spectrum =
ThermoRawRunFactoryHelper.GetMS1Spectrum(ref reader, parentScan, ref ms1);
if (ms1Spectrum != null)
{
lock (resultLock)
{
spectrumMap[parentScan] = ms1Spectrum;
}
}
foreach (int scan in scanPair.Value)
{
Spectrum ms2Spectrum =
ThermoRawRunFactoryHelper.GetMS2Spectrum(ref reader, scan, type, charger, picking, process, ms1);
if (ms2Spectrum != null)
{
lock (resultLock)
{
spectrumMap[scan] = ms2Spectrum;
}
}
}
}
updater(scanGroup.Count);
});
List <Spectrum> spectrumList =
spectrumMap.OrderBy(s => s.Key).Select(s => s.Value).ToList();
data.spectrumList.spectrum = new Spectrum[spectrumList.Count];
spectrumList = spectrumList.OrderBy(x => int.Parse(x.id.Substring(5))).ToList();
for (int i = 0; i < spectrumList.Count; i++)
{
int scan = int.Parse(spectrumList[i].id.Substring(5));
data.spectrumList.spectrum[i] = spectrumList[i];
data.spectrumList.spectrum[i].index = (scan - 1).ToString();
data.spectrumList.spectrum[i].defaultArrayLength = spectrumList[i].defaultArrayLength;
}
data.spectrumList.count = spectrumList.Count.ToString();
data.spectrumList.defaultDataProcessingRef = defaultDataProcessingRef;
return(data);
}
public void Test1()
{
string path = @"D:\Raw\ZC_20171218_N14_R2.raw";
ISpectrumReader reader = new ThermoRawSpectrumReader();
LocalMaximaPicking picking = new LocalMaximaPicking(10);
reader.Init(path);
Dictionary <int, int> scanMap = new Dictionary <int, int>();
int current = -1;
int start = reader.GetFirstScan();
int end = reader.GetLastScan();
for (int i = start; i < end; i++)
{
if (reader.GetMSnOrder(i) == 1)
{
current = i;
}
else if (reader.GetMSnOrder(i) == 2)
{
scanMap[i] = current;
}
}
double searchRange = 1;
int scan_num = 6223;
if (scanMap.ContainsKey(scan_num))
{
int paranet_scan = scanMap[scan_num];
ISpectrum ms1 = reader.GetSpectrum(paranet_scan);
double mz = reader.GetPrecursorMass(scan_num, reader.GetMSnOrder(scan_num));
List <IPeak> ms1Peaks = FilterPeaks(ms1.GetPeaks(), mz, searchRange);
if (ms1Peaks.Count() == 0)
{
return;
}
// insert pseudo peaks for large gap
List <IPeak> peaks = new List <IPeak>();
double precision = 0.02;
double last = ms1Peaks.First().GetMZ();
foreach (IPeak peak in ms1Peaks)
{
if (peak.GetMZ() - last > precision)
{
peaks.Add(new GeneralPeak(last + precision / 2, 0));
peaks.Add(new GeneralPeak(peak.GetMZ() - precision / 2, 0));
}
peaks.Add(peak);
last = peak.GetMZ();
}
List <IPeak> majorPeaks = picking.Process(peaks);
//Console.WriteLine("mz,intensity");
//foreach (IPeak pk in peaks)
//{
// Console.WriteLine(pk.GetMZ().ToString() + "," + pk.GetIntensity().ToString());
//}
Fourier charger = new Fourier();
int charge = charger.Charge(peaks, mz - searchRange, mz + searchRange);
Patterson charger2 = new Patterson();
PattersonFourierCombine charger3 = new PattersonFourierCombine();
Console.WriteLine(charge.ToString() + " "
+ charger2.Charge(peaks, mz - searchRange, mz + searchRange).ToString() + " "
+ charger3.Charge(peaks, mz - searchRange, mz + searchRange).ToString());
}
}
public void Run(string path, Counter counter)
{
ISpectrumReader reader = new ThermoRawSpectrumReader();
reader.Init(path);
IGUIFinder finder = new BinarySearchFinder(PPM);
IProcess picking = new LocalNeighborPicking();
Dictionary <int, List <GUI> > pointMaps = new Dictionary <int, List <GUI> >();
int start = reader.GetFirstScan();
int end = reader.GetLastScan();
Parallel.For(start, end, (i) =>
{
if (reader.GetMSnOrder(i) < 2)
{
ISpectrum spectrum = picking.Process(reader.GetSpectrum(i));
lock (resultLock)
{
pointMaps[i] = finder.FindGlucoseUnits(spectrum);
}
}
counter.Add(end - start);
});
List <List <GUI> > points =
pointMaps.OrderBy(p => p.Key).Select(p => p.Value).ToList();
IGUISequencer sequencer = new DynamicProgrammingSequencer();
List <GUI> guiPoints = sequencer.Choose(points);
Dictionary <int, GUI> guiSelected = new Dictionary <int, GUI>();
foreach (GUI gui in guiPoints)
{
if (guiSelected.ContainsKey(gui.Unit))
{
if (guiSelected[gui.Unit].Peak.GetIntensity() < gui.Peak.GetIntensity())
{
guiSelected[gui.Unit] = gui;
}
}
else
{
guiSelected[gui.Unit] = gui;
}
}
Retention.Clear();
Guis.Clear();
List <GUI> looped = guiSelected.Values.OrderBy(g => g.Scan).ToList();
string output = Path.Combine(Path.GetDirectoryName(path),
Path.GetFileNameWithoutExtension(path) + ".csv");
using (FileStream ostrm = new FileStream(output, FileMode.OpenOrCreate, FileAccess.Write))
{
using (StreamWriter writer = new StreamWriter(ostrm))
{
writer.WriteLine("scan,time,gui,peak,intensity");
foreach (GUI gui in looped)
{
int scan = gui.Scan;
double time = reader.GetRetentionTime(scan);
Retention.Add(time);
Guis.Add(gui.Unit);
writer.WriteLine(scan.ToString() + "," +
time.ToString() + "," +
gui.Unit.ToString() + "," +
gui.Peak.GetMZ().ToString() + "," +
gui.Peak.GetIntensity().ToString());
}
writer.Flush();
}
}
Fitter.Fit(Retention, Guis);
}
public void Test1()
{
string path = @"C:\Users\Rui Zhang\Downloads\ZC_20171218_C16_R1.raw";
ISpectrumReader reader = new ThermoRawSpectrumReader();
LocalMaximaPicking picking = new LocalMaximaPicking(10);
reader.Init(path);
Dictionary <int, List <int> > scanGroup = new Dictionary <int, List <int> >();
int current = -1;
int start = reader.GetFirstScan();
int end = reader.GetLastScan();
for (int i = start; i < end; i++)
{
if (reader.GetMSnOrder(i) == 1)
{
current = i;
scanGroup[i] = new List <int>();
}
else if (reader.GetMSnOrder(i) == 2)
{
scanGroup[current].Add(i);
}
}
double searchRange = 2;
foreach (KeyValuePair <int, List <int> > ScanPair in scanGroup)
{
if (ScanPair.Value.Count > 0)
{
ISpectrum ms1 = reader.GetSpectrum(ScanPair.Key);
List <IPeak> majorPeaks = picking.Process(ms1.GetPeaks());
foreach (int i in ScanPair.Value)
{
double mz = reader.GetPrecursorMass(i, reader.GetMSnOrder(i));
if (ms1.GetPeaks()
.Where(p => p.GetMZ() > mz - searchRange && p.GetMZ() < mz + searchRange)
.Count() == 0)
{
continue;
}
//Patterson charger = new Patterson();
if (ms1.GetPeaks()
.Where(p => p.GetMZ() > mz - searchRange && p.GetMZ() < mz + searchRange)
.Count() < 2)
{
continue;
}
Fourier charger = new Fourier();
int charge = charger.Charge(ms1.GetPeaks(), mz - searchRange, mz + searchRange);
Patterson charger2 = new Patterson();
Console.WriteLine(charge.ToString() + " "
+ charger2.Charge(ms1.GetPeaks(), mz - searchRange, mz + searchRange).ToString());
}
}
}
}
void GenerateTasks()
{
if (Path.GetExtension(msPath) == ".mgf")
{
MGFSpectrumReader reader = new MGFSpectrumReader();
reader.Init(msPath);
Dictionary <int, MS2Spectrum> spectraData = reader.GetSpectrum();
foreach (int scan in spectraData.Keys)
{
MS2Spectrum spectrum = spectraData[scan];
SearchTask searchTask = new SearchTask(spectrum,
spectrum.PrecursorMZ(), spectrum.PrecursorCharge());
tasks.Enqueue(searchTask);
readingCounter.Add(spectraData.Count);
}
}
else
{
ISpectrumReader reader = new ThermoRawSpectrumReader();
LocalMaximaPicking picking = new LocalMaximaPicking();
IProcess process = new WeightedAveraging(new LocalNeighborPicking());
reader.Init(msPath);
int start = reader.GetFirstScan();
int end = reader.GetLastScan();
Dictionary <int, List <int> > scanGroup = new Dictionary <int, List <int> >();
int current = -1;
for (int i = start; i < end; i++)
{
if (reader.GetMSnOrder(i) == 1)
{
current = i;
scanGroup[i] = new List <int>();
}
else if (reader.GetMSnOrder(i) == 2)
{
scanGroup[current].Add(i);
}
}
Parallel.ForEach(scanGroup,
new ParallelOptions {
MaxDegreeOfParallelism = SearchingParameters.Access.ThreadNums
},
(scanPair) =>
{
if (scanPair.Value.Count > 0)
{
ISpectrum ms1 = reader.GetSpectrum(scanPair.Key);
foreach (int i in scanPair.Value)
{
double mz = reader.GetPrecursorMass(i, reader.GetMSnOrder(i));
List <IPeak> ms1Peaks = FilterPeaks(ms1.GetPeaks(), mz, searchRange);
if (ms1Peaks.Count() == 0)
{
continue;
}
ICharger charger = new Patterson();
int charge = charger.Charge(ms1Peaks, mz - searchRange, mz + searchRange);
// insert pseudo peaks for large gap
List <IPeak> peaks = new List <IPeak>();
double precision = 0.02;
double last = ms1Peaks.First().GetMZ();
foreach (IPeak peak in ms1Peaks)
{
if (peak.GetMZ() - last > precision)
{
peaks.Add(new GeneralPeak(last + precision / 2, 0));
peaks.Add(new GeneralPeak(peak.GetMZ() - precision / 2, 0));
}
peaks.Add(peak);
last = peak.GetMZ();
}
List <IPeak> majorPeaks = picking.Process(peaks);
// find evelope cluster
EnvelopeProcess envelope = new EnvelopeProcess();
var cluster = envelope.Cluster(majorPeaks, mz, charge);
if (cluster.Count == 0)
{
continue;
}
// find monopeak
Averagine averagine = new Averagine(AveragineType.GlycoPeptide);
BrainCSharp braincs = new BrainCSharp();
MonoisotopicSearcher searcher = new MonoisotopicSearcher(averagine, braincs);
MonoisotopicScore result = searcher.Search(mz, charge, cluster);
double precursorMZ = result.GetMZ();
// search
ISpectrum ms2 = reader.GetSpectrum(i);
ms2 = process.Process(ms2);
SearchTask searchTask = new SearchTask(ms2, precursorMZ, charge);
tasks.Enqueue(searchTask);
}
}
readingCounter.Add(scanGroup.Count);
});
}
}
public void Run()
{
var watch = new System.Diagnostics.Stopwatch();
watch.Start();
// protein
IProteinDataBuilder proteinBuilder = new GeneralFastaDataBuilder();
IProteinCreator proteinCreator = new GeneralProteinCreator(proteinBuilder);
List <IProtein> proteins = proteinCreator.Create(@"C:\Users\iruiz\Desktop\app\HP.fasta");
// peptides
List <IPeptideSequencesGenerator> generatorList = new List <IPeptideSequencesGenerator>();
IPeptideSequencesGeneratorParameter parameter = new GeneralPeptideGeneratorParameter();
parameter.SetProtease(Proteases.GluC);
NGlycosylatedPeptideSequencesGenerator generatorGluc = new NGlycosylatedPeptideSequencesGenerator(parameter);
generatorList.Add(generatorGluc);
parameter = new GeneralPeptideGeneratorParameter();
parameter.SetProtease(Proteases.Trypsin);
NGlycosylatedPeptideSequencesGenerator generatorTrypsin = new NGlycosylatedPeptideSequencesGenerator(parameter);
generatorList.Add(generatorTrypsin);
IPeptideSequencesGenerator peptideSequencesGenerator = new DoubleDigestionPeptideSequencesGeneratorProxy(generatorList);
IPeptideCreator peptideCreator = new GeneralPeptideCreator(peptideSequencesGenerator);
List <IPeptide> peptides = new List <IPeptide>();
HashSet <string> seen = new HashSet <string>();
foreach (IProtein protein in proteins)
{
foreach (IPeptide peptide in peptideCreator.Create(protein))
{
if (!seen.Contains(peptide.GetSequence()))
{
seen.Add(peptide.GetSequence());
peptides.Add(peptide);
}
}
}
// glycans
ITableNGlycanProxyGenerator tableNGlycanProxyGenerator = new GeneralTableNGlycanMassProxyGenerator(12, 12, 5, 4, 0);
int[] structTable = new int[24];
structTable[0] = 1;
ITableNGlycanProxy root = new GeneralTableNGlycanMassProxy(new ComplexNGlycan(structTable));
IGlycanCreator glycanCreator = new GeneralTableNGlycanCreator(tableNGlycanProxyGenerator, root);
List <IGlycan> glycans = glycanCreator.Create();
// precursor
List <IPoint> points = new List <IPoint>();
foreach (IGlycan glycan in glycans)
{
points.Add(new GlycanPoint(glycan));
}
IComparer <IPoint> comparer = new ToleranceComparer(0.01);
ISearch matcher = new BucketSearch(comparer, 0.01);
matcher.setData(points);
IGlycoPeptideProxyGenerator glycoPeptideProxyGenerator = new GeneralTableNGlycoPeptideMassProxyGenerator();
IGlycoPeptideCreator glycoPeptideCreator = new GeneralNGlycoPeptideSingleSiteCreator(glycoPeptideProxyGenerator);
IPrecursorMatcher precursorMatcher = new GeneralPrecursorMatcher(matcher, glycoPeptideCreator);
precursorMatcher.SetGlycans(glycans);
precursorMatcher.SetPeptides(peptides);
// spectrum
ISpectrumReader spectrumReader = new ThermoRawSpectrumReader();
spectrumReader.Init(@"C:\Users\iruiz\Desktop\app\ZC_20171218_H95_R1.raw");
ISpectrumFactory spectrumFactory = new GeneralSpectrumFactory(spectrumReader);
ISpectrum spectrum = spectrumFactory.GetSpectrum(7039);
List <IGlycoPeptide> glycoPeptides = precursorMatcher.Match(spectrum);
watch.Stop();
Console.WriteLine(glycoPeptides.Count);
foreach (IGlycoPeptide glycoPeptide in glycoPeptides)
{
Console.WriteLine(glycoPeptide.GetType());
}
Console.WriteLine($"Execution Time: {watch.ElapsedMilliseconds} ms");
Console.Read();
}
static void Main(string[] args)
{
string dir = @"C:\Users\iruiz\Downloads\GUI\compare\data";
string[] files = Directory.GetFiles(dir);
List <double> ions = new List <double>();
ions.Add(Calculator.proton);
Calculator.To.SetChargeIons(ions);
foreach (string path in files)
{
Stopwatch stopWatch = new Stopwatch();
stopWatch.Start();
NGlycanTheoryPeaksBuilder builder = new NGlycanTheoryPeaksBuilder();
builder.SetBuildType(true, false, false);
List <IGlycanPeak> glycans = builder.Build();
IResultFactory factory = new NGlycanResultFactory();
EnvelopeProcess envelopeProcess = new EnvelopeProcess(10, ToleranceBy.PPM);
MonoisotopicSearcher monoisotopicSearcher = new MonoisotopicSearcher(factory);
IProcess spectrumProcess = new LocalNeighborPicking();
ISpectrumSearch spectrumSearch = new NGlycanSpectrumSearch(glycans,
spectrumProcess, envelopeProcess, monoisotopicSearcher);
ISpectrumReader spectrumReader = new ThermoRawSpectrumReader();
spectrumReader.Init(path);
ICurveFitting Fitter = new PolynomialFitting();
IResultSelect resultSelect = new ResultMaxSelect();
List <GUI> GuiPoints = Init(ref Fitter, spectrumReader);
List <IResult> final = new List <IResult>();
for (int scan = spectrumReader.GetFirstScan(); scan <= spectrumReader.GetLastScan(); scan++)
{
if (spectrumReader.GetMSnOrder(scan) != 1)
{
continue;
}
ISpectrum spectrum = spectrumReader.GetSpectrum(scan);
List <IResult> results = spectrumSearch.Search(spectrum);
resultSelect.Add(results);
final.AddRange(results);
}
// original
List <string> outputString = new List <string>();
foreach (IResult present in final)
{
int scan = present.GetScan();
double rt = present.GetRetention();
double index = Math.Round(Normalize(Fitter, rt), 2);
TIQ3XIC xicer = new TIQ3XIC(spectrumReader);
double area = xicer.OneArea(present);
List <string> output = new List <string>()
{
scan.ToString(), rt.ToString(),
index > 0? index.ToString():"0",
present.Glycan().GetGlycan().Name(),
present.GetMZ().ToString(),
area.ToString(),
};
outputString.Add(string.Join(",", output));
}
string outputPath = Path.Combine(Path.GetDirectoryName(path),
Path.GetFileNameWithoutExtension(path) + "_one_quant.csv");
using (FileStream ostrm = new FileStream(outputPath, FileMode.OpenOrCreate, FileAccess.Write))
{
using (StreamWriter writer = new StreamWriter(ostrm))
{
writer.WriteLine("scan,time,GUI,glycan,mz,area");
foreach (string output in outputString)
{
writer.WriteLine(output);
}
writer.Flush();
}
}
// merged
List <string> outputStringMerge = new List <string>();
Dictionary <string, List <SelectResult> > resultContainer = resultSelect.Produce();
foreach (string name in resultContainer.Keys)
{
//if (name == "5-6-1-2-0")
// Console.WriteLine("here");
List <SelectResult> selectResults = resultContainer[name];
foreach (SelectResult select in selectResults)
{
if (select.Results.Count == 0)
{
continue;
}
IResult present = select.Present;
int scan = present.GetScan();
double rt = present.GetRetention();
double index = Math.Round(Normalize(Fitter, rt), 2);
IXIC xicer = new TIQ3XIC(spectrumReader);
double area = xicer.Area(select);
List <string> output = new List <string>()
{
scan.ToString(), rt.ToString(),
index > 0? index.ToString():"0",
name,
present.GetMZ().ToString(),
area.ToString()
};
outputStringMerge.Add(string.Join(",", output));
}
}
string outputPathMerge = Path.Combine(Path.GetDirectoryName(path),
Path.GetFileNameWithoutExtension(path) + "_quant.csv");
using (FileStream ostrm = new FileStream(outputPathMerge, FileMode.OpenOrCreate, FileAccess.Write))
{
using (StreamWriter writer = new StreamWriter(ostrm))
{
writer.WriteLine("scan,time,GUI,glycan,mz,area");
foreach (string output in outputStringMerge)
{
writer.WriteLine(output);
}
writer.Flush();
}
}
stopWatch.Stop();
TimeSpan ts = stopWatch.Elapsed;
string elapsedTime = String.Format("{0:00}:{1:00}:{2:00}.{3:00}",
ts.Hours, ts.Minutes, ts.Seconds,
ts.Milliseconds / 10);
Console.WriteLine("RunTime " + elapsedTime);
}
}
public void Test1()
{
string path = @"C:\Users\Rui Zhang\Downloads\ZC_20171218_C16_R1.raw";
string fasta = @"C:\Users\Rui Zhang\Downloads\haptoglobin.fasta";
// peptides
IProteinReader proteinReader = new FastaReader();
List <IProtein> proteins = proteinReader.Read(fasta);
List <IProtein> decoyProteins = new List <IProtein>();
foreach (IProtein protein in proteins)
{
IProtein p = new BaseProtein();
p.SetSequence(Reverse(protein.Sequence()));
decoyProteins.Add(p);
}
List <Proteases> proteases = new List <Proteases>()
{
Proteases.Trypsin, Proteases.GluC
};
HashSet <string> peptides = new HashSet <string>();
ProteinDigest proteinDigest = new ProteinDigest(2, 5, proteases[0]);
foreach (IProtein protein in decoyProteins)
{
peptides.UnionWith(proteinDigest.Sequences(protein.Sequence(),
ProteinPTM.ContainsNGlycanSite));
}
for (int i = 1; i < proteases.Count; i++)
{
proteinDigest.SetProtease(proteases[i]);
List <string> peptidesList = peptides.ToList();
foreach (string seq in peptidesList)
{
peptides.UnionWith(proteinDigest.Sequences(seq,
ProteinPTM.ContainsNGlycanSite));
}
}
Assert.True(peptides.Contains("KDNLTYVGDGETR"));
// build glycan
GlycanBuilder glycanBuilder = new GlycanBuilder();
glycanBuilder.Build();
// search
List <SearchResult> searchResults = new List <SearchResult>();
ThermoRawSpectrumReader reader = new ThermoRawSpectrumReader();
LocalMaximaPicking picking = new LocalMaximaPicking();
IProcess process = new LocalNeighborPicking();
reader.Init(path);
double searchRange = 2;
ISpectrum ms1 = null;
List <IPeak> majorPeaks = new List <IPeak>();
ISearch <string> oneSearcher = new BucketSearch <string>(ToleranceBy.PPM, 10);
PrecursorMatch precursorMatcher = new PrecursorMatch(oneSearcher);
precursorMatcher.Init(peptides.ToList(), glycanBuilder.GlycanMaps());
ISearch <string> moreSearcher = new BucketSearch <string>(ToleranceBy.Dalton, 0.01);
SequenceSearch sequenceSearcher = new SequenceSearch(moreSearcher);
ISearch <int> extraSearcher = new BucketSearch <int>(ToleranceBy.Dalton, 0.01);
GlycanSearch glycanSearcher = new GlycanSearch(extraSearcher, glycanBuilder.GlycanMaps());
SearchAnalyzer searchAnalyzer = new SearchAnalyzer();
for (int i = reader.GetFirstScan(); i < reader.GetLastScan(); i++)
{
if (reader.GetMSnOrder(i) < 2)
{
ms1 = reader.GetSpectrum(i);
majorPeaks = picking.Process(ms1.GetPeaks());
}
else
{
double mz = reader.GetPrecursorMass(i, reader.GetMSnOrder(i));
if (ms1.GetPeaks()
.Where(p => p.GetMZ() > mz - searchRange && p.GetMZ() < mz + searchRange)
.Count() == 0)
{
continue;
}
Patterson charger = new Patterson();
int charge = charger.Charge(ms1.GetPeaks(), mz - searchRange, mz + searchRange);
// find evelope cluster
EnvelopeProcess envelope = new EnvelopeProcess();
var cluster = envelope.Cluster(majorPeaks, mz, charge);
if (cluster.Count == 0)
{
continue;
}
// find monopeak
Averagine averagine = new Averagine(AveragineType.GlycoPeptide);
BrainCSharp braincs = new BrainCSharp();
MonoisotopicSearcher searcher = new MonoisotopicSearcher(averagine, braincs);
MonoisotopicScore result = searcher.Search(mz, charge, cluster);
double precursorMZ = result.GetMZ();
// search
ISpectrum ms2 = reader.GetSpectrum(i);
ms2 = process.Process(ms2);
//precursor match
var pre_results = precursorMatcher.Match(precursorMZ, charge);
if (pre_results.Count == 0)
{
continue;
}
// spectrum search
var peptide_results = sequenceSearcher.Search(ms2.GetPeaks(), charge, pre_results);
if (peptide_results.Count == 0)
{
continue;
}
var glycan_results = glycanSearcher.Search(ms2.GetPeaks(), charge, pre_results);
if (glycan_results.Count == 0)
{
continue;
}
var temp_results = searchAnalyzer.Analyze(i, ms2.GetPeaks(), peptide_results, glycan_results);
break;
}
}
}
public static Spectrum GetMS2Spectrum(ref ThermoRawSpectrumReader reader,
int scan, AveragineType type, ChargerType chargerType, LocalMaximaPicking picking, IProcess process,
ISpectrum ms1)
{
// scan header
Spectrum spectrum = new Spectrum
{
id = "scan=" + scan.ToString()
};
double dLowMass = 0;
double dHighMass = 0;
double dTIC = 0;
double dBasePeakMass = 0;
double dBasePeakIntensity = 0;
reader.GetScanHeaderInfoForScanNum(scan, ref dLowMass, ref dHighMass,
ref dTIC, ref dBasePeakMass, ref dBasePeakIntensity);
SetScanHeader(spectrum, dLowMass, dHighMass, dTIC,
dBasePeakMass, dBasePeakIntensity);
// binary data
spectrum.binaryDataArrayList = new BinaryDataArrayList();
SetBinaryDataArrayHeader(spectrum.binaryDataArrayList);
spectrum.cvParam[0] = new Component.CVParam()
{
cvRef = "MS",
accession = "MS:1000511",
name = "ms level",
value = "2",
};
double mz = reader.GetPrecursorMass(scan, reader.GetMSnOrder(scan));
List <IPeak> ms1Peaks = FilterPeaks(ms1.GetPeaks(), mz, searchRange);
if (ms1Peaks.Count() == 0)
{
return(null);
}
// insert pseudo peaks for large gaps
List <IPeak> peaks = new List <IPeak>();
double precision = 0.02;
double last = ms1Peaks.First().GetMZ();
foreach (IPeak peak in ms1Peaks)
{
if (peak.GetMZ() - last > precision)
{
peaks.Add(new GeneralPeak(last + precision / 2, 0));
peaks.Add(new GeneralPeak(peak.GetMZ() - precision / 2, 0));
}
peaks.Add(peak);
last = peak.GetMZ();
}
List <IPeak> majorPeaks = picking.Process(peaks);
ICharger charger = new Patterson();
if (chargerType == ChargerType.Fourier)
{
charger = new Fourier();
}
else if (chargerType == ChargerType.Combined)
{
charger = new PattersonFourierCombine();
}
int charge = charger.Charge(peaks, mz - searchRange, mz + searchRange);
// find evelope cluster
EnvelopeProcess envelope = new EnvelopeProcess();
var cluster = envelope.Cluster(majorPeaks, mz, charge);
if (cluster.Count == 0)
{
return(null);
}
// find monopeak
Averagine averagine = new Averagine(type);
BrainCSharp braincs = new BrainCSharp();
MonoisotopicSearcher searcher = new MonoisotopicSearcher(averagine, braincs);
MonoisotopicScore result = searcher.Search(mz, charge, cluster);
// process spectrum
ISpectrum ms2 = reader.GetSpectrum(scan);
List <IPeak> ms2Peaks = process.Process(ms2).GetPeaks();
spectrum.binaryDataArrayList.binaryDataArray[0].binary =
ms2Peaks.SelectMany(p => BitConverter.GetBytes(p.GetMZ())).ToArray();
spectrum.binaryDataArrayList.binaryDataArray[1].binary =
ms2Peaks.SelectMany(p => BitConverter.GetBytes(p.GetIntensity())).ToArray();
spectrum.defaultArrayLength = ms2Peaks.Count.ToString();
spectrum.precursorList = new PrecursorList
{
count = "1",
precursor = new Precursor[1]
};
for (int i = 0; i < spectrum.precursorList.precursor.Length; i++)
{
spectrum.precursorList.precursor[i] = new Precursor();
}
spectrum.precursorList.precursor[0].selectedIonList = new SelectedIonList
{
count = "1",
selectedIon = new SelectedIon[1]
};
for (int i = 0; i < spectrum.precursorList.precursor[0].selectedIonList.selectedIon.Length; i++)
{
spectrum.precursorList.precursor[0].selectedIonList.selectedIon[i] = new SelectedIon();
}
spectrum.precursorList.precursor[0].selectedIonList.selectedIon[0].cvParam = new Component.CVParam[2];
spectrum.precursorList.precursor[0].selectedIonList.selectedIon[0].cvParam[0] = new Component.CVParam()
{
cvRef = "MS",
accession = "MS:1000744",
name = "selected ion m/z",
value = result.GetMZ().ToString(),
unitCvRef = "MS",
unitAccession = "MS:1000040",
unitName = "m/z"
};
spectrum.precursorList.precursor[0].selectedIonList.selectedIon[0].cvParam[1] = new Component.CVParam()
{
cvRef = "MS",
accession = "MS:1000041",
name = "charge state",
value = charge.ToString()
};
spectrum.precursorList.precursor[0].activation = new Activation
{
cvParam = new Component.CVParam[1]
};
spectrum.precursorList.precursor[0].activation.cvParam[0] =
ActivationCVParam(reader.GetActivation(scan));
spectrum.binaryDataArrayList.binaryDataArray[0].encodedLength =
Convert.ToBase64String(spectrum.binaryDataArrayList.binaryDataArray[0].binary).Length.ToString();
spectrum.binaryDataArrayList.binaryDataArray[1].encodedLength =
Convert.ToBase64String(spectrum.binaryDataArrayList.binaryDataArray[1].binary).Length.ToString();
return(spectrum);
}