/// <summary>
/// Creates LCMS Features
/// </summary>
public List <UMCLight> CreateLcmsFeatures(
DatasetInformation information,
List <MSFeatureLight> msFeatures,
LcmsFeatureFindingOptions options,
LcmsFeatureFilteringOptions filterOptions,
IScanSummaryProvider provider,
IProgress <ProgressData> progress = null)
{
// Make features
if (msFeatures.Count < 1)
{
throw new Exception("No features were found in the feature files provided.");
}
UpdateStatus("Finding features.");
ValidateFeatureFinderMaxScanLength(information, options, filterOptions);
var finder = FeatureFinderFactory.CreateFeatureFinder(FeatureFinderType.TreeBased);
finder.Progress += (sender, args) => UpdateStatus(args.Message);
var features = finder.FindFeatures(msFeatures, options, provider, progress);
UpdateStatus("Filtering features.");
List <UMCLight> filteredFeatures = LcmsFeatureFilters.FilterFeatures(features, filterOptions, provider);
UpdateStatus(string.Format("Filtered features from: {0} to {1}.", features.Count, filteredFeatures.Count));
return(filteredFeatures);
}
/// <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 InformedProteomicsReader())
{
// Read the raw file summary data...
raw.AddDataFile(rawFile, 0);
var info = new DatasetInformation();
info.InputFiles.Add(new InputFile {
Path = featureFile, FileType = InputFileType.Features
});
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);
provider.AddDataFile(rawFile, 0);
features = finder.FindFeatures(msFeatures, options, provider);
}
return(features);
}
public void TestMsFeatureScatterPlot(string path1, string path2, string pngPath)
{
// Convert relative paths to absolute paths
path1 = GetPath(path1);
path2 = GetPath(path2);
pngPath = GetPath(pngPath);
var fiOutput = new FileInfo(pngPath);
var didirectory = fiOutput.Directory;
if (didirectory == null)
{
throw new DirectoryNotFoundException(pngPath);
}
if (!didirectory.Exists)
{
didirectory.Create();
}
var aligner = new LcmsWarpFeatureAligner(new LcmsWarpAlignmentOptions());
var isosFilterOptions = new DeconToolsIsosFilterOptions();
var baselineMs = UmcLoaderFactory.LoadMsFeatureData(path1, isosFilterOptions);
var aligneeMs = UmcLoaderFactory.LoadMsFeatureData(path2, isosFilterOptions);
var finder = FeatureFinderFactory.CreateFeatureFinder(FeatureFinderType.TreeBased);
var tolerances = new FeatureTolerances
{
FragmentationWindowSize = .5,
Mass = 13,
DriftTime = .3,
Net = .01
};
var options = new LcmsFeatureFindingOptions(tolerances);
options.MaximumNetRange = .002;
var baseline = finder.FindFeatures(baselineMs, options, null);
var alignee = finder.FindFeatures(aligneeMs, options, null);
var alignmentResults = aligner.Align(baseline, alignee);
var plotModel1 = new PlotModel
{
Subtitle = "Interpolated, cartesian axes",
Title = "HeatMapSeries"
};
var palette = OxyPalettes.Hot(200);
var linearColorAxis1 = new LinearColorAxis
{
InvalidNumberColor = OxyColors.Gray,
Position = AxisPosition.Right,
Palette = palette
};
plotModel1.Axes.Add(linearColorAxis1);
// linearColorAxis1.
var linearAxis1 = new LinearAxis {
Position = AxisPosition.Bottom
};
plotModel1.Axes.Add(linearAxis1);
var linearAxis2 = new LinearAxis();
plotModel1.Axes.Add(linearAxis2);
var heatMapSeries1 = new HeatMapSeries
{
X0 = 0,
X1 = 1,
Y0 = 0,
Y1 = 1,
FontSize = .2
};
var scores = alignmentResults.HeatScores;
var width = scores.GetLength(0);
var height = scores.GetLength(1);
heatMapSeries1.Data = new double[width, height];
var seriesData = heatMapSeries1.Data;
for (var i = 0; i < width; i++)
{
for (var j = 0; j < height; j++)
{
seriesData[i, j] = Convert.ToDouble(scores[i, j]);
}
}
plotModel1.Series.Add(heatMapSeries1);
var svg = new SvgExporter();
var svgString = svg.ExportToString(plotModel1);
var xml = new XmlDocument();
xml.LoadXml(svgString);
var x = SvgDocument.Open(xml); // Svg.SvgDocument();
var bmp = x.Draw();
bmp.Save(pngPath);
var heatmap = HeatmapFactory.CreateAlignedHeatmap(alignmentResults.HeatScores, false);
var netHistogram = HistogramFactory.CreateHistogram(alignmentResults.NetErrorHistogram, "NET Error", "NET Error");
var massHistogram = HistogramFactory.CreateHistogram(alignmentResults.MassErrorHistogram, "Mass Error", "Mass Error (ppm)");
var baseName = Path.Combine(didirectory.FullName, Path.GetFileNameWithoutExtension(fiOutput.Name));
var encoder = new SvgEncoder();
PlotImageUtility.SaveImage(heatmap, baseName + "_heatmap.svg", encoder);
PlotImageUtility.SaveImage(netHistogram, baseName + "_netHistogram.svg", encoder);
PlotImageUtility.SaveImage(massHistogram, baseName + "_massHistogram.svg", encoder);
}
public void TestLcmsWarpAlignment(string path1, string path2, string svgPath)
{
// Convert relative paths to absolute paths
path1 = GetPath(path1);
path2 = GetPath(path2);
svgPath = GetPath(HEATMAP_RESULTS_FOLDER_BASE + svgPath);
var aligner = new LcmsWarpFeatureAligner(new LcmsWarpAlignmentOptions());
var isosFilterOptions = new DeconToolsIsosFilterOptions();
var baselineMs = UmcLoaderFactory.LoadMsFeatureData(path1, isosFilterOptions);
var aligneeMs = UmcLoaderFactory.LoadMsFeatureData(path2, isosFilterOptions);
var finder = FeatureFinderFactory.CreateFeatureFinder(FeatureFinderType.TreeBased);
var tolerances = new FeatureTolerances
{
FragmentationWindowSize = .5,
Mass = 13,
DriftTime = .3,
Net = .01
};
var options = new LcmsFeatureFindingOptions(tolerances)
{
MaximumNetRange = .002
};
var baseline = finder.FindFeatures(baselineMs, options, null);
var alignee = finder.FindFeatures(aligneeMs, options, null);
var data = aligner.Align(baseline, alignee);
var plotModel1 = new PlotModel
{
Subtitle = "Interpolated, cartesian axes",
Title = "HeatMapSeries"
};
var palette = OxyPalettes.Hot(200);
var linearColorAxis1 = new LinearColorAxis
{
InvalidNumberColor = OxyColors.Gray,
Position = AxisPosition.Right,
Palette = palette
};
plotModel1.Axes.Add(linearColorAxis1);
// linearColorAxis1.
var linearAxis1 = new LinearAxis {
Position = AxisPosition.Bottom
};
plotModel1.Axes.Add(linearAxis1);
var linearAxis2 = new LinearAxis();
plotModel1.Axes.Add(linearAxis2);
var heatMapSeries1 = new HeatMapSeries
{
X0 = 0,
X1 = 1,
Y0 = 0,
Y1 = 1,
FontSize = .2
};
var scores = data.HeatScores;
var width = scores.GetLength(0);
var height = scores.GetLength(1);
heatMapSeries1.Data = new double[width, height];
for (var i = 0; i < width; i++)
{
for (var j = 0; j < height; j++)
{
heatMapSeries1.Data[i, j] = Convert.ToDouble(scores[i, j]);
}
}
plotModel1.Series.Add(heatMapSeries1);
var svg = new SvgExporter();
var svgString = svg.ExportToString(plotModel1);
using (var writer = File.CreateText(svgPath + ".svg"))
{
writer.Write(svgString);
}
}
public void TestClustering(
string directory,
string outputPath,
FeatureAlignmentType alignmentType,
LcmsFeatureClusteringAlgorithmType clusterType)
{
var matchPath = string.Format("{0}.txt", outputPath);
var errorPath = string.Format("{0}-errors.txt", outputPath);
// Loads the supported MultiAlign types
var supportedTypes = DatasetLoader.SupportedFileTypes;
var extensions = new List <string>();
supportedTypes.ForEach(x => extensions.Add("*" + x.Extension));
// Find our datasets
var datasetLoader = new DatasetLoader();
var datasets = datasetLoader.GetValidDatasets(directory, extensions, SearchOption.TopDirectoryOnly);
// Setup our alignment options
var alignmentOptions = new AlignmentOptions();
var spectralOptions = new SpectralOptions
{
ComparerType = SpectralComparison.CosineDotProduct,
Fdr = .01,
IdScore = 1e-09,
MzBinSize = .5,
MzTolerance = .5,
NetTolerance = .1,
RequiredPeakCount = 32,
SimilarityCutoff = .75,
TopIonPercent = .8
};
// Options setup
var instrumentOptions = InstrumentPresetFactory.Create(InstrumentPresets.LtqOrbitrap);
var featureTolerances = new FeatureTolerances
{
Mass = instrumentOptions.Mass + 6,
Net = instrumentOptions.NetTolerance,
DriftTime = instrumentOptions.DriftTimeTolerance
};
var featureFindingOptions = new LcmsFeatureFindingOptions(featureTolerances)
{
MaximumNetRange = .002,
MaximumScanRange = 50
};
// Create our algorithms
var finder = FeatureFinderFactory.CreateFeatureFinder(FeatureFinderType.TreeBased);
var aligner = FeatureAlignerFactory.CreateDatasetAligner(alignmentType,
alignmentOptions.LCMSWarpOptions,
spectralOptions);
var clusterer = ClusterFactory.Create(clusterType);
clusterer.Parameters = new FeatureClusterParameters <UMCLight>
{
Tolerances = featureTolerances
};
RegisterProgressNotifier(aligner);
RegisterProgressNotifier(finder);
RegisterProgressNotifier(clusterer);
var lcmsFilters = new LcmsFeatureFilteringOptions
{
FeatureLengthRangeScans = new FilterRange(50, 300)
};
var msFilterOptions = new MsFeatureFilteringOptions
{
MinimumIntensity = 5000,
ChargeRange = new FilterRange(1, 6),
ShouldUseChargeFilter = true,
ShouldUseDeisotopingFilter = true,
ShouldUseIntensityFilter = true
};
for (var i = 0; i < 1; i++)
{
var aligneeDatasets = datasets.Where((t, j) => j != i).ToList();
PerformMultiAlignAnalysis(datasets[0],
aligneeDatasets,
featureFindingOptions,
msFilterOptions,
lcmsFilters,
spectralOptions,
finder,
aligner,
clusterer,
matchPath,
errorPath);
}
}
public void TestPeptideBands(string directory,
string matchPath)
{
// Loads the supported MultiAlign types
var supportedTypes = DatasetLoader.SupportedFileTypes;
var extensions = new List <string>();
supportedTypes.ForEach(x => extensions.Add("*" + x.Extension));
// Find our datasets
var datasetLoader = new DatasetLoader();
var datasets = datasetLoader.GetValidDatasets(directory, extensions, SearchOption.TopDirectoryOnly);
// Options setup
var instrumentOptions = InstrumentPresetFactory.Create(InstrumentPresets.LtqOrbitrap);
var featureTolerances = new FeatureTolerances
{
Mass = instrumentOptions.Mass,
Net = instrumentOptions.NetTolerance,
DriftTime = instrumentOptions.DriftTimeTolerance
};
var msFilterOptions = new MsFeatureFilteringOptions
{
MinimumIntensity = 5000,
ChargeRange = new FilterRange(1, 6),
ShouldUseChargeFilter = true,
ShouldUseDeisotopingFilter = true,
ShouldUseIntensityFilter = true
};
var featureFindingOptions = new LcmsFeatureFindingOptions(featureTolerances)
{
MaximumNetRange = .002,
MaximumScanRange = 50
};
var baselineDataset = datasets[0];
UpdateStatus("Loading baseline features.");
var msFeatures = UmcLoaderFactory.LoadMsFeatureData(baselineDataset.Features.Path);
msFeatures = LcmsFeatureFilters.FilterMsFeatures(msFeatures, msFilterOptions);
var finderFinder = FeatureFinderFactory.CreateFeatureFinder(FeatureFinderType.TreeBased);
var peptideOptions = new SpectralOptions
{
ComparerType = SpectralComparison.CosineDotProduct,
Fdr = .05,
IdScore = 1e-09,
MzBinSize = .5,
MzTolerance = .5,
NetTolerance = .1,
RequiredPeakCount = 32,
SimilarityCutoff = .75,
TopIonPercent = .8
};
var features = new List <MSFeatureLight>();
// Load the baseline reference set
using (var rawProviderX = RawLoaderFactory.CreateFileReader(baselineDataset.RawFile.Path))
{
rawProviderX.AddDataFile(baselineDataset.RawFile.Path, 0);
UpdateStatus("Creating Baseline LCMS Features.");
var baselineFeatures = finderFinder.FindFeatures(msFeatures,
featureFindingOptions,
rawProviderX);
LinkPeptidesToFeatures(baselineDataset.Sequence.Path,
baselineFeatures,
peptideOptions.Fdr,
peptideOptions.IdScore);
baselineFeatures.ForEach(x => features.AddRange(x.MsFeatures));
features = features.Where(x => x.HasMsMs()).ToList();
features = features.OrderBy(x => x.Mz).ToList();
var peptideList = new List <MSFeatureLight>();
foreach (var feature in features)
{
foreach (var spectrum in feature.MSnSpectra)
{
var peptideFound = false;
foreach (var peptide in spectrum.Peptides)
{
peptideList.Add(feature);
peptideFound = true;
break;
}
if (peptideFound)
{
break;
}
}
}
using (var writer = File.CreateText(matchPath))
{
writer.WriteLine("Charge\tpmz\tscan\tNET\t");
foreach (var feature in peptideList)
{
writer.WriteLine("{0}\t{1}\t{2}\t{3}\t", feature.ChargeState, feature.Mz, feature.Scan,
feature.Net);
}
}
}
}
public void CreateFeatureDatabase(string directoryPath, string databasePath)
{
var directory = GetPath(directoryPath);
databasePath = GetPath(databasePath);
// Loads the supported MultiAlign types
var supportedTypes = DatasetLoader.SupportedFileTypes;
var extensions = new List <string>();
supportedTypes.ForEach(x => extensions.Add("*" + x.Extension));
// Find our datasets
var datasetLoader = new DatasetLoader();
var datasets = datasetLoader.GetValidDatasets(directory, extensions, SearchOption.TopDirectoryOnly);
// Options setup
var instrumentOptions = InstrumentPresetFactory.Create(InstrumentPresets.LtqOrbitrap);
var featureTolerances = new FeatureTolerances
{
Mass = instrumentOptions.Mass + 6,
Net = instrumentOptions.NetTolerance,
DriftTime = instrumentOptions.DriftTimeTolerance
};
var featureFindingOptions = new LcmsFeatureFindingOptions(featureTolerances)
{
MaximumNetRange = .002,
MaximumScanRange = 50
};
var lcmsFilters = new LcmsFeatureFilteringOptions
{
FeatureLengthRangeScans = new FilterRange(50, 300)
};
var msFilterOptions = new MsFeatureFilteringOptions
{
MinimumIntensity = 5000,
ChargeRange = new FilterRange(1, 6),
ShouldUseChargeFilter = true,
ShouldUseDeisotopingFilter = true,
ShouldUseIntensityFilter = true
};
var spectralOptions = new SpectralOptions
{
ComparerType = SpectralComparison.CosineDotProduct,
Fdr = .01,
IdScore = 1e-09,
MzBinSize = .5,
MzTolerance = .5,
NetTolerance = .1,
RequiredPeakCount = 32,
SimilarityCutoff = .75,
TopIonPercent = .8
};
var finder = FeatureFinderFactory.CreateFeatureFinder(FeatureFinderType.TreeBased);
NHibernateUtil.CreateDatabase(databasePath);
// Synchronization and IO for serializing all data to the database.
var providers = DataAccessFactory.CreateDataAccessProviders(databasePath, true);
var cache = new FeatureLoader
{
Providers = providers
};
var datasetId = 0;
foreach (var dataset in datasets)
{
dataset.DatasetId = datasetId++;
var features = FindFeatures(dataset,
featureFindingOptions,
msFilterOptions,
lcmsFilters,
spectralOptions,
finder);
cache.CacheFeatures(features);
}
providers.DatasetCache.AddAll(datasets);
}
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,
};
baselineInfo.InputFiles.Add(new InputFile {
Path = baseline, FileType = InputFileType.Features
});
baselineInfo.InputFiles.Add(new InputFile {
Path = baselineRaw, FileType = InputFileType.Raw
});
baselineInfo.InputFiles.Add(new InputFile {
Path = sequencePath, FileType = InputFileType.Sequence
});
Console.WriteLine("Create Alignee Information");
var aligneeInfo = new DatasetInformation
{
DatasetId = 1,
};
aligneeInfo.InputFiles.Add(new InputFile {
Path = features, FileType = InputFileType.Features
});
aligneeInfo.InputFiles.Add(new InputFile {
Path = featuresRaw, FileType = InputFileType.Raw
});
aligneeInfo.InputFiles.Add(new InputFile {
Path = sequencePath, FileType = InputFileType.Sequence
});
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;
var spectraProviderCache = new SpectraProviderCache();
spectraProviderCache.GetSpectraProvider(baselineInfo.RawFile.Path, baselineInfo.DatasetId);
spectraProviderCache.GetSpectraProvider(aligneeInfo.RawFile.Path, aligneeInfo.DatasetId);
clusters = clusterer.Cluster(allFeatures, spectraProviderCache);
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);
}
}
}
}
}
