ClusterHierarchical.h

Go to the documentation of this file.

// --------------------------------------------------------------------------
//                   OpenMS -- Open-Source Mass Spectrometry
// --------------------------------------------------------------------------
// Copyright The OpenMS Team -- Eberhard Karls University Tuebingen,
// ETH Zurich, and Freie Universitaet Berlin 2002-2020.
//
// This software is released under a three-clause BSD license:
//  * Redistributions of source code must retain the above copyright
//    notice, this list of conditions and the following disclaimer.
//  * Redistributions in binary form must reproduce the above copyright
//    notice, this list of conditions and the following disclaimer in the
//    documentation and/or other materials provided with the distribution.
//  * Neither the name of any author or any participating institution
//    may be used to endorse or promote products derived from this software
//    without specific prior written permission.
// For a full list of authors, refer to the file AUTHORS.
// --------------------------------------------------------------------------
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
// AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
// IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
// ARE DISCLAIMED. IN NO EVENT SHALL ANY OF THE AUTHORS OR THE CONTRIBUTING
// INSTITUTIONS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
// EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
// PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS;
// OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
// WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
// OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
// ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
//
//
 
//  You should have received a copy of the GNU Lesser General Public
//  License along with this library; if not, write to the Free Software
//  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
//
// --------------------------------------------------------------------------
// $Maintainer: Mathias Walzer $
// $Authors: $
// --------------------------------------------------------------------------
//
#pragma once
 
#include <OpenMS/KERNEL/StandardTypes.h>
#include <OpenMS/DATASTRUCTURES/DistanceMatrix.h>
#include <OpenMS/COMPARISON/CLUSTERING/ClusterFunctor.h>
#include <OpenMS/COMPARISON/CLUSTERING/ClusterAnalyzer.h>
#include <OpenMS/COMPARISON/SPECTRA/PeakSpectrumCompareFunctor.h>
#include <OpenMS/COMPARISON/SPECTRA/BinnedSpectrum.h>
#include <OpenMS/COMPARISON/SPECTRA/BinnedSpectrumCompareFunctor.h>
#include <OpenMS/CONCEPT/Exception.h>
 
#include <vector>
 
namespace OpenMS
{
 
  class OPENMS_DLLAPI ClusterHierarchical
  {
private:
 
    double threshold_;
 
public:
    ClusterHierarchical() :
      threshold_(1.0)
    {
    }
 
    ClusterHierarchical(const ClusterHierarchical & source) :
      threshold_(source.threshold_)
    {
    }
 
    virtual ~ClusterHierarchical()
    {
    }
 
    template <typename Data, typename SimilarityComparator>
    void cluster(std::vector<Data> & data, 
      const SimilarityComparator & comparator, 
      const ClusterFunctor & clusterer, 
      std::vector<BinaryTreeNode> & cluster_tree,
      DistanceMatrix<float> & original_distance)
    {
      if (original_distance.dimensionsize() != data.size())
      {
        // create distance matrix for data using comparator
        original_distance.clear();
        original_distance.resize(data.size(), 1);
        for (Size i = 0; i < data.size(); i++)
        {
          for (Size j = 0; j < i; j++)
          {
            // distance value is 1-similarity value, since similarity is in range of [0,1]
            original_distance.setValueQuick(i, j, 1 - comparator(data[i], data[j]));
          }
        }
      }
 
      // create clustering with ClusterMethod, DistanceMatrix and Data
      clusterer(original_distance, cluster_tree, threshold_);
    }
 
    void cluster(std::vector<PeakSpectrum> & data, 
      const BinnedSpectrumCompareFunctor & comparator, 
      double sz, 
      UInt sp,
      float offset, 
      const ClusterFunctor & clusterer, 
      std::vector<BinaryTreeNode> & cluster_tree, 
      DistanceMatrix<float> & original_distance)
    {
      std::vector<BinnedSpectrum> binned_data;
      binned_data.reserve(data.size());
 
      //transform each PeakSpectrum to a corresponding BinnedSpectrum with given settings of size and spread
      for (Size i = 0; i < data.size(); i++)
      {
        //double sz(2), UInt sp(1);
        binned_data.push_back(BinnedSpectrum(data[i], sz, false, sp, offset));
      }
 
      //create distancematrix for data with comparator
      original_distance.clear();
      original_distance.resize(data.size(), 1);
 
      for (Size i = 0; i < binned_data.size(); i++)
      {
        for (Size j = 0; j < i; j++)
        {
          //distance value is 1-similarity value, since similarity is in range of [0,1]
          original_distance.setValue(i, j, 1 - comparator(binned_data[i], binned_data[j]));
        }
      }
 
      // create Clustering with ClusterMethod, DistanceMatrix and Data
      clusterer(original_distance, cluster_tree, threshold_);
    }
 
    double getThreshold()
    {
      return threshold_;
    }
 
    void setThreshold(double x)
    {
      threshold_ = x;
    }
 
  };
 
  class OPENMS_DLLAPI UnnormalizedComparator :
    public Exception::BaseException
  {
public:
    UnnormalizedComparator(const char * file, int line, const char * function, const char * message
                             = "Clustering with unnormalized similarity measurement requested, normalized is mandatory") throw();
    ~UnnormalizedComparator() throw() override;
  };
 
}