/// <summary>
/// Initializes a new instance of the <see cref="T:ExFat.IO.ClusterStream" /> class.
/// </summary>
/// <param name="clusterReader">The cluster information reader.</param>
/// <param name="clusterWriter">The cluster writer.</param>
/// <param name="dataDescriptor">The data descriptor.</param>
/// <param name="onDisposed">Method invoked when stream is disposed.</param>
/// <exception cref="T:System.ArgumentException">If contiguous is true, the length must be specified</exception>
/// <inheritdoc />
public ClusterStream(IClusterReader clusterReader, IClusterWriter clusterWriter, DataDescriptor dataDescriptor, Action <DataDescriptor> onDisposed)
{
_clusterReader = clusterReader;
_clusterWriter = clusterWriter;
_startCluster = dataDescriptor.FirstCluster;
_contiguous = dataDescriptor.Contiguous;
_onDisposed = onDisposed;
_dataLength = (long)dataDescriptor.PhysicalLength;
_validDataLength = (long)dataDescriptor.LogicalLength;
_position = 0;
_currentCluster = _startCluster;
}
/// <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 void ClusterAndProcess(List <UMCLight> data, IClusterWriter <UMCClusterLight> writer, IProgress <ProgressData> progress = null)
{
throw new NotImplementedException();
}
/// <summary>
/// Clusters the data but does not store the results, instead immediately writes the data to the stream writer provided.
/// </summary>
/// <param name="data"></param>
/// <param name="writer"></param>
public void ClusterAndProcess(List <T> data, IClusterWriter <U> writer)
{
/*
* This clustering algorithm first sorts the list of input UMC's by mass. It then iterates
* through this list partitioning the data into blocks of UMC's based on a mass tolerance.
* When it finds gaps larger or equal to the mass (ppm) tolerance specified by the user,
* it will process the data before the gap (a block) until the current index of the features in question.
*/
// Make sure we have data to cluster first.
if (data == null)
{
throw new NullReferenceException("The input feature data list was null. Cannot process this data.");
}
// Make sure there is no null UMC data in the input list.
var nullIndex = data.FindIndex(delegate(T x) { return(x == null); });
if (nullIndex > 0)
{
throw new NullReferenceException("The feature at index " + nullIndex + " was null. Cannot process this data.");
}
OnNotify("Sorting cluster mass list");
// The first thing we do is to sort the features based on mass since we know that has the least variability in the data across runs.
data.Sort(m_massComparer);
// Now partition the data based on mass ranges and the parameter values.
var massTolerance = Parameters.Tolerances.Mass;
// This is the index of first feature of a given mass partition.
var startUMCIndex = 0;
var totalFeatures = data.Count;
OnNotify("Detecting mass partitions");
var tenPercent = Convert.ToInt32(totalFeatures * .1);
var counter = 0;
var percent = 0;
var clusterId = 0;
for (var i = 0; i < totalFeatures - 1; i++)
{
if (counter > tenPercent)
{
counter = 0;
percent += 10;
OnNotify(string.Format("Clustering Completed...{0}%", percent));
}
counter++;
// Here we compute the ppm mass difference between consecutive features (based on mass).
// This will determine if we cluster a block of data or not.
var umcX = data[i];
var umcY = data[i + 1];
var ppm = Math.Abs(FeatureLight.ComputeMassPPMDifference(umcX.MassMonoisotopicAligned, umcY.MassMonoisotopicAligned));
// If the difference is greater than the tolerance then we cluster
// - we dont check the sign of the ppm because the data should be sorted based on mass.
if (ppm > massTolerance)
{
// If start UMC Index is equal to one, then that means the feature at startUMCIndex
// could not find any other features near it within the mass tolerance specified.
if (startUMCIndex == i)
{
var cluster = new U();
cluster.AmbiguityScore = m_maxDistance;
umcX.SetParentFeature(cluster);
cluster.AddChildFeature(umcX);
cluster.CalculateStatistics(Parameters.CentroidRepresentation);
cluster.Id = clusterId++;
writer.WriteCluster(cluster);
}
else
{
// Otherwise we have more than one feature to to consider.
var distances = CalculatePairWiseDistances(startUMCIndex, i, data);
var localClusters = CreateSingletonClusters(data, startUMCIndex, i);
var blockClusters = LinkFeatures(distances, localClusters);
CalculateAmbiguityScore(blockClusters);
foreach (var cluster in localClusters.Values)
{
cluster.Id = clusterId++;
CalculateStatistics(cluster);
writer.WriteCluster(cluster);
}
}
startUMCIndex = i + 1;
}
}
// Make sure that we cluster what is left over.
if (startUMCIndex < totalFeatures)
{
OnNotify(string.Format("Clustering last partition...{0}%", percent));
var distances = CalculatePairWiseDistances(startUMCIndex, totalFeatures - 1, data);
var localClusters = CreateSingletonClusters(data, startUMCIndex, totalFeatures - 1);
var blockClusters = LinkFeatures(distances, localClusters);
CalculateAmbiguityScore(blockClusters);
if (localClusters.Count < 2)
{
foreach (var cluster in localClusters.Values)
{
cluster.Id = clusterId++;
CalculateStatistics(cluster);
writer.WriteCluster(cluster);
}
}
else
{
foreach (var cluster in blockClusters)
{
cluster.Id = clusterId++;
CalculateStatistics(cluster);
writer.WriteCluster(cluster);
}
}
}
// OnNotify("Generating cluster statistics");
}
public void ClusterAndProcess(List <TChildFeature> data, IClusterWriter <TParentFeature> writer, IProgress <ProgressData> progress = null)
{
throw new NotImplementedException();
}
