public void TestRestrictiveBoxMethod(string path, DistanceMetric dist, bool useBoxMethod)
{
var features = ReadFeatures(path);
var clusterer = new UMCAverageLinkageClusterer <UMCLight, UMCClusterLight>
{
ShouldTestClustersWithinTolerance = useBoxMethod,
Parameters =
{
CentroidRepresentation = ClusterCentroidRepresentation.Mean,
DistanceFunction = DistanceFactory <UMCLight> .CreateDistanceFunction(dist),
OnlyClusterSameChargeStates = true,
Tolerances =
{
Mass = 10,
DriftTime = .3,
Net = .03
}
}
};
var clusters = clusterer.Cluster(features);
var i = 0;
clusters.ForEach(x => x.Id = i++);
WriteClusters(clusters);
}
public void TestDistancesEuclidean(string path, DistanceMetric dist)
{
var func = DistanceFactory <UMCClusterLight> .CreateDistanceFunction(DistanceMetric.Euclidean);
var oldClusters = ReadClusters(path);
var clusters = CreateSingletonClustersFromClusteredFeatures(new List <UMCClusterLight> {
oldClusters[1]
});
Console.WriteLine("Distance, Mass, NET, DT, Mass, Net, DT");
for (var i = 0; i < clusters.Count; i++)
{
for (var j = i + 1; j < clusters.Count; j++)
{
var distance = func(clusters[i], clusters[j]);
Console.WriteLine("{0},{1},{2},{3},{4},{5},{6}",
distance,
clusters[i].MassMonoisotopic,
clusters[i].Net,
clusters[i].DriftTime,
clusters[j].MassMonoisotopic,
clusters[j].Net,
clusters[j].DriftTime);
}
}
}
/// <summary>
/// Resets the parameters to their default values.
/// </summary>
public virtual void Clear()
{
Tolerances = new FeatureTolerances();
OnlyClusterSameChargeStates = CONST_DEFAULT_ONLY_CLUSTER_SAME_CHARGE_STATES;
DistanceFunction = DistanceFactory <T> .CreateDistanceFunction(DistanceMetric.WeightedEuclidean);
RangeFunction = WithinRange;
CentroidRepresentation = ClusterCentroidRepresentation.Median;
}
public IActionResult ShowResult(HierarchicalCreateVM model)
{
var data = _fileService.GetData(model.UploadFile, model.DataType);
IDistance distance = DistanceFactory.GetDistance(model.DistanceType);
IClusterDistance clusterDistance = ClusterDistanceFactory.GetClusterDistance(model.ClusterUnionType);
var result = _service.Clustering(data, distance, clusterDistance, model.CountOfUnionsInStep);
return(View(result));
}
public IActionResult ShowResult(KMeansCreateVM model)
{
var data = _fileService.GetData(model.UploadFile, model.DataType);
IDistance distance = DistanceFactory.GetDistance(model.DistanceType);
var result = _kMeans.Clustering(data, distance, model.ClustersCount);
ViewBag.Centroids = result.Centroid;
return(View(result.Result));
}
public static FeatureClusterParameters <UMCLight> ConvertToOmics(LcmsClusteringOptions options)
{
var parameters = new FeatureClusterParameters <UMCLight>
{
Tolerances = options.InstrumentTolerances,
OnlyClusterSameChargeStates = (options.ShouldSeparateCharge == false),
CentroidRepresentation = options.ClusterCentroidRepresentation
};
parameters.DistanceFunction = DistanceFactory <UMCLight> .CreateDistanceFunction(options.DistanceFunction);
return(parameters);
}
public void TestDistanceDistributions(string path, DistanceMetric dist)
{
var features = ReadFeatures(path);
var clusterer = new UMCAverageLinkageClusterer <UMCLight, UMCClusterLight>
{
ShouldTestClustersWithinTolerance = false,
Parameters =
{
CentroidRepresentation = ClusterCentroidRepresentation.Mean,
DistanceFunction = DistanceFactory <UMCLight> .CreateDistanceFunction(dist),
OnlyClusterSameChargeStates = true,
Tolerances =
{
Mass = 10,
DriftTime = .3,
Net = .03
}
}
};
var clusters = clusterer.Cluster(features);
var distances = new List <double>();
foreach (var cluster in clusters)
{
var centroid = new UMCLight();
centroid.MassMonoisotopicAligned = cluster.MassMonoisotopic;
centroid.Net = cluster.Net;
centroid.DriftTime = cluster.DriftTime;
var func = clusterer.Parameters.DistanceFunction;
foreach (var feature in cluster.Features)
{
var distance = func(feature, centroid);
distances.Add(distance);
}
distances.Sort();
var sum = 0;
foreach (var distance in distances)
{
sum++;
Console.WriteLine("{0},{1}", distance, sum);
}
}
}
public static bool IsFuzzySimilar(this string input, string parameter, int fuzzyness = 3, FuzzyAlgorithm fuzzyAlgorithm = FuzzyAlgorithm.LevenshteinDistance)
{
if (string.IsNullOrEmpty(parameter))
{
throw new ArgumentNullException($"parameter can't be empty or null");
}
if (fuzzyness < 0)
{
throw new InvalidOperationException($"fuzzyness can't be less than 0");
}
var string1 = "";
var string2 = "";
return((DistanceFactory.GetDistances(GetCanonicalForm(input), GetCanonicalForm(parameter)) < fuzzyness) || input.Contains(parameter) || parameter.Contains(input));
}
/// <summary>
/// The main entry point for the application.
/// </summary>
static int Main(string [] args)
{
var handle = System.Diagnostics.Process.GetCurrentProcess().MainWindowHandle;
SetConsoleMode(handle, ENABLE_EXTENDED_FLAGS);
try
{
if (args.Length < 2)
{
Console.WriteLine(@"MultiAlignChargeStateProcessor databasePath chargeState crossTabPath [dataset List]");
Console.WriteLine(@"\tThe cross-tab file will be placed in the same directory as the database path");
return(1);
}
// Setup the analysis processing
var databasePath = args[0];
var databaseName = Path.GetFileNameWithoutExtension(databasePath);
var path = Path.GetDirectoryName(databasePath);
var crossPath = args[2];
var chargeState = Convert.ToInt32(args[1]);
List <string> datasetList = null;
if (args.Length == 4)
{
datasetList = File.ReadAllLines(args[3]).ToList();
}
if (path == null)
{
Console.WriteLine(@"The directory path is invalid");
return(1);
}
NHibernateUtil.ConnectToDatabase(databasePath, false);
IDatasetDAO datasetCache = new DatasetDAOHibernate();
var dateSuffix = AnalysisPathUtils.BuildDateSuffix();
Logger.LogPath = Path.Combine(path, string.Format("{0}_charge_{2}_{1}.txt", databaseName, dateSuffix, chargeState));
Logger.PrintMessage("Find all datasets", true);
var datasets = datasetCache.FindAll();
Logger.PrintMessage(string.Format("Found {0} datasets", datasets.Count), true);
// Create the clustering algorithm - average linkage
IClusterer <UMCLight, UMCClusterLight> clusterer = new UMCAverageLinkageClusterer <UMCLight, UMCClusterLight>();
// Create the DAO object to extract the features
var database = new UmcAdoDAO {
DatabasePath = databasePath
};
IUmcDAO featureDao = database;
Logger.PrintMessage(string.Format("Extracting Features"), true);
var tempFeatures = featureDao.FindByCharge(chargeState);
Logger.PrintMessage(string.Format("Found {0} features", tempFeatures.Count), true);
var features = new List <UMCLight>();
if (datasetList != null)
{
var featuremap = datasets.ToDictionary(info => info.DatasetName.ToLower());
var focusedDatasetList = new Dictionary <int, DatasetInformation>();
foreach (var name in datasetList)
{
var key = name.ToLower();
if (featuremap.ContainsKey(key))
{
Logger.PrintMessage("Using dataset: " + name);
focusedDatasetList.Add(featuremap[key].DatasetId, featuremap[key]);
}
else
{
throw new Exception("Didn't find the dataset required..." + name);
}
}
features.AddRange(from feature in tempFeatures let use = focusedDatasetList.ContainsKey(feature.GroupId) where use select feature);
Logger.PrintMessage(string.Format("Found {0} filtered features for dataset list", features.Count), true);
}
else
{
features = tempFeatures;
}
// Handle logging progress.
clusterer.Progress += clusterer_Progress;
clusterer.Parameters.Tolerances.DriftTime = .3;
clusterer.Parameters.Tolerances.Mass = 16;
clusterer.Parameters.Tolerances.Net = .014;
clusterer.Parameters.OnlyClusterSameChargeStates = true;
clusterer.Parameters.CentroidRepresentation = ClusterCentroidRepresentation.Mean;
clusterer.Parameters.DistanceFunction = DistanceFactory <UMCLight> .CreateDistanceFunction(DistanceMetric.WeightedEuclidean);
// Then cluster
var clusterWriter = new UmcClusterWriter();
IClusterWriter <UMCClusterLight> writer = clusterWriter; //new UMCClusterDummyWriter();
try
{
clusterWriter.Open(crossPath);
clusterWriter.WriteHeader(datasets);
clusterer.ClusterAndProcess(features, writer);
Logger.PrintMessage("", true);
Logger.PrintMessage("ANALYSIS SUCCESS", true);
return(0);
}
catch (Exception ex)
{
Logger.PrintMessage("Unhandled Error: " + ex.Message);
var innerEx = ex.InnerException;
while (innerEx != null)
{
Logger.PrintMessage("Inner Exception: " + innerEx.Message);
innerEx = innerEx.InnerException;
}
Logger.PrintMessage("Stack: " + ex.StackTrace);
Logger.PrintMessage("");
Logger.PrintMessage("ANALYSIS FAILED");
return(1);
}
finally
{
clusterWriter.Close();
}
}
catch (Exception ex)
{
Logger.PrintMessage("Unhandled Error: " + ex.Message, true);
var innerEx = ex.InnerException;
while (innerEx != null)
{
Logger.PrintMessage("Inner Exception: " + innerEx.Message);
innerEx = innerEx.InnerException;
}
Logger.PrintMessage("Stack: " + ex.StackTrace, true);
Logger.PrintMessage("");
Logger.PrintMessage("ANALYSIS FAILED");
return(1);
}
}
public LargeScaleClusterTests()
{
m_massComparer = FeatureLight.MassAlignedComparison;
DistanceFunction = DistanceFactory <UMCLight> .CreateDistanceFunction(DistanceMetric.Euclidean);
}
