/// <summary>
/// Retrieves a list of features.
/// </summary>
/// <param name="rawFile"></param>
/// <param name="featureFile"></param>
/// <returns></returns>
public List<UMCLight> FindFeatures(string rawFile, string featureFile)
{
List<UMCLight> features;
using (ISpectraProvider raw = new ThermoRawDataFileReader())
{
// Read the raw file summary data...
raw.AddDataFile(rawFile, 0);
var info = new DatasetInformation();
info.Features = new InputFile();
info.Features.Path = featureFile;
var finder = FeatureFinderFactory.CreateFeatureFinder(FeatureFinderType.TreeBased);
var tolerances = new FeatureTolerances
{
Mass = 8,
Net = .005
};
var options = new LcmsFeatureFindingOptions(tolerances);
// Load and create features
var msFeatures = UmcLoaderFactory.LoadMsFeatureData(info.Features.Path);
var provider = RawLoaderFactory.CreateFileReader(rawFile);
features = finder.FindFeatures(msFeatures, options, provider);
}
return features;
}
/// <summary>
/// Constructs a raw data file reader for reading the instrument (or equivalent) mass spectra.
/// </summary>
/// <param name="name"></param>
/// <param name="register"></param>
/// <returns></returns>
public static ISpectraProvider CreateFileReader(string name)
{
if (name == null)
return null;
ISpectraProvider reader = null;
var extension = Path.GetExtension(name);
// Otherwise create a new one.
switch (extension.ToLower())
{
case ".raw":
reader = new ThermoRawDataFileReader();
break;
case ".mzxml":
reader = new MzXMLReader();
break;
case ".mzml":
reader = new InformedProteomicsReader();
break;
case ".gz":
if (name.ToLower().EndsWith(".mzml.gz"))
{
reader = new InformedProteomicsReader();
}
break;
default:
reader = new InformedProteomicsReader();
break;
}
return reader;
}
public void ClusterMsMs(string name,
string resultPath,
string sequencePath,
SequenceFileType type,
string baseline,
string features,
double percent)
{
var baselineRaw = baseline.Replace("_isos.csv", ".raw");
var featuresRaw = features.Replace("_isos.csv", ".raw");
Console.WriteLine("Create Baseline Information");
var baselineInfo = new DatasetInformation
{
DatasetId = 0,
Features = new InputFile {Path = baseline},
Raw = new InputFile {Path = baselineRaw},
Sequence = new InputFile {Path = sequencePath}
};
Console.WriteLine("Create Alignee Information");
var aligneeInfo = new DatasetInformation
{
DatasetId = 1,
Features = new InputFile {Path = features},
Raw = new InputFile {Path = featuresRaw},
Sequence = new InputFile {Path = sequencePath}
};
var reader = new MsFeatureLightFileReader();
Console.WriteLine("Reading Baseline Features");
var baselineMsFeatures = reader.ReadFile(baseline).ToList();
baselineMsFeatures.ForEach(x => x.GroupId = baselineInfo.DatasetId);
Console.WriteLine("Reading Alignee Features");
var aligneeMsFeatures = reader.ReadFile(features).ToList();
aligneeMsFeatures.ForEach(x => x.GroupId = aligneeInfo.DatasetId);
var finder = FeatureFinderFactory.CreateFeatureFinder(FeatureFinderType.TreeBased);
var tolerances = new FeatureTolerances
{
Mass = 8,
Net = .005
};
var options = new LcmsFeatureFindingOptions(tolerances);
Console.WriteLine("Detecting Baseline Features");
var baselineFeatures = finder.FindFeatures(baselineMsFeatures, options, null);
Console.WriteLine("Detecting Alignee Features");
var aligneeFeatures = finder.FindFeatures(aligneeMsFeatures, options, null);
Console.WriteLine("Managing baseline and alignee features");
baselineFeatures.ForEach(x => x.GroupId = baselineInfo.DatasetId);
aligneeFeatures.ForEach(x => x.GroupId = aligneeInfo.DatasetId);
Console.WriteLine("Clustering MS/MS Spectra");
var clusterer = new MSMSClusterer();
clusterer.MzTolerance = .5;
clusterer.MassTolerance = 6;
clusterer.SpectralComparer = new SpectralNormalizedDotProductComparer
{
TopPercent = percent
};
clusterer.SimilarityTolerance = .5;
clusterer.ScanRange = 905;
clusterer.Progress += clusterer_Progress;
var allFeatures = new List<UMCLight>();
allFeatures.AddRange(baselineFeatures);
allFeatures.AddRange(aligneeFeatures);
List<MsmsCluster> clusters = null;
using (var rawReader = new ThermoRawDataFileReader())
{
rawReader.AddDataFile(baselineInfo.Raw.Path, baselineInfo.DatasetId);
rawReader.AddDataFile(aligneeInfo.Raw.Path, aligneeInfo.DatasetId);
clusters = clusterer.Cluster(allFeatures, rawReader);
Console.WriteLine("Found {0} Total Clusters", clusters.Count);
}
if (clusters != null)
{
var now = DateTime.Now;
var testResultPath = string.Format("{7}\\{0}-results-{1}-{2}-{3}-{4}-{5}-{6}_scans.txt",
name,
now.Year,
now.Month,
now.Day,
now.Hour,
now.Minute,
now.Second,
resultPath
);
using (TextWriter writer = File.CreateText(testResultPath))
{
writer.WriteLine("[Data]");
writer.WriteLine("{0}", baseline);
writer.WriteLine("{0}", features);
writer.WriteLine("[Scans]");
writer.WriteLine();
foreach (var cluster in clusters)
{
var scanData = "";
if (cluster.Features.Count == 2)
{
foreach (var feature in cluster.Features)
{
scanData += string.Format("{0},", feature.Scan);
}
scanData += string.Format("{0}", cluster.MeanScore);
writer.WriteLine(scanData);
}
}
}
testResultPath = string.Format("{7}\\{0}-results-{1}-{2}-{3}-{4}-{5}-{6}.txt",
name,
now.Year,
now.Month,
now.Day,
now.Hour,
now.Minute,
now.Second,
resultPath
);
using (TextWriter writer = File.CreateText(testResultPath))
{
writer.WriteLine("[Data]");
writer.WriteLine("{0}", baseline);
writer.WriteLine("{0}", features);
writer.WriteLine("[Scans]");
foreach (var cluster in clusters)
{
var scanData = "";
var data = "";
foreach (var feature in cluster.Features)
{
scanData += string.Format("{0},", feature.Scan);
data += string.Format("{0},{1},{2},{3},{4},{5}",
feature.GroupId,
feature.Id,
feature.MassMonoisotopic,
feature.Mz,
feature.ChargeState,
feature.Scan);
foreach (var spectrum in feature.MSnSpectra)
{
foreach (var peptide in spectrum.Peptides)
{
data += string.Format(",{0},{1}", peptide.Sequence, peptide.Score);
}
}
}
writer.WriteLine(scanData + "," + data);
}
writer.WriteLine("");
writer.WriteLine("");
writer.WriteLine("[Clusters]");
foreach (var cluster in clusters)
{
writer.WriteLine("cluster id, cluster score");
writer.WriteLine("{0}, {1}", cluster.Id, cluster.MeanScore);
writer.WriteLine("feature dataset id, id, monoisotopic mass, mz, charge, scan, peptides");
foreach (var feature in cluster.Features)
{
var data = string.Format("{0},{1},{2},{3},{4},{5}",
feature.GroupId,
feature.Id,
feature.MassMonoisotopic,
feature.Mz,
feature.ChargeState,
feature.Scan);
foreach (var spectrum in feature.MSnSpectra)
{
foreach (var peptide in spectrum.Peptides)
{
data += string.Format(",{0},{1}", peptide.Sequence, peptide.Score);
}
}
writer.WriteLine(data);
}
}
}
}
}
private MSSpectra GetSpectrum(string path, int scan)
{
ISpectraProvider reader = new ThermoRawDataFileReader();
reader.AddDataFile(path, 0);
return GetSpectrum(reader, scan, 0);
}
