OpenMS  2.8.0
SvmTheoreticalSpectrumGeneratorTrainer.h
Go to the documentation of this file.
1 // --------------------------------------------------------------------------
2 // OpenMS -- Open-Source Mass Spectrometry
3 // --------------------------------------------------------------------------
4 // Copyright The OpenMS Team -- Eberhard Karls University Tuebingen,
5 // ETH Zurich, and Freie Universitaet Berlin 2002-2021.
6 //
7 // This software is released under a three-clause BSD license:
8 // * Redistributions of source code must retain the above copyright
9 // notice, this list of conditions and the following disclaimer.
10 // * Redistributions in binary form must reproduce the above copyright
11 // notice, this list of conditions and the following disclaimer in the
12 // documentation and/or other materials provided with the distribution.
13 // * Neither the name of any author or any participating institution
14 // may be used to endorse or promote products derived from this software
15 // without specific prior written permission.
16 // For a full list of authors, refer to the file AUTHORS.
17 // --------------------------------------------------------------------------
18 // THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
19 // AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
20 // IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
21 // ARE DISCLAIMED. IN NO EVENT SHALL ANY OF THE AUTHORS OR THE CONTRIBUTING
22 // INSTITUTIONS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
23 // EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
24 // PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS;
25 // OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
26 // WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
27 // OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
28 // ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
29 //
30 // --------------------------------------------------------------------------
31 // $Maintainer: Timo Sachsenberg $
32 // $Authors: Sandro Andreotti $
33 // --------------------------------------------------------------------------
34 
35 #pragma once
36 
41 
44 #include <OpenMS/FORMAT/TextFile.h>
45 
46 namespace OpenMS
47 {
66  public DefaultParamHandler
67  {
70  typedef std::map<std::pair<IonType, Size>, std::vector<double> > ObservedIntensMap;
71 
73  void countIntensities_(const PeakSpectrum & spectrum,
74  const AASequence & annotation,
75  IonType type,
76  std::map<std::pair<IonType, Size>, std::vector<double> > & observed_intensities,
77  double tolerance,
78  Size number_of_regions
79  );
80 
82  void trainSecondaryTypes_(TextFile & info_outfile,
83  Size number_of_regions,
84  Size number_of_intensity_levels,
85  ObservedIntensMap & observed_intensities,
86  const std::vector<IonType> & ion_types,
87  const std::vector<bool> & is_primary
88  );
89 public:
90 
96 
99 
103 
106 
108  void trainModel(const PeakMap & spectra, const std::vector<AASequence> & annotations, String filename, Int precursor_charge);
109 
112 
113 protected:
114 
116  void writeTrainingFile_(std::vector<DescriptorSet> & training_input, std::vector<double> & training_output, String filename);
117 
118  };
119 }
120 
Representation of a peptide/protein sequence.
Definition: AASequence.h:112
A base class for all classes handling default parameters.
Definition: DefaultParamHandler.h:93
In-Memory representation of a mass spectrometry run.
Definition: MSExperiment.h:73
The representation of a 1D spectrum.
Definition: MSSpectrum.h:70
A more convenient string class.
Definition: String.h:60
Train SVM models that are used by SvmTheoreticalSpectrumGenerator.
Definition: SvmTheoreticalSpectrumGeneratorTrainer.h:67
void writeTrainingFile_(std::vector< DescriptorSet > &training_input, std::vector< double > &training_output, String filename)
Write a training file that can be passed to libsvm command line tools.
SvmTheoreticalSpectrumGeneratorTrainer()
Default constructor.
SvmTheoreticalSpectrumGenerator::DescriptorSet DescriptorSet
Definition: SvmTheoreticalSpectrumGeneratorTrainer.h:69
SvmTheoreticalSpectrumGeneratorTrainer & operator=(const SvmTheoreticalSpectrumGeneratorTrainer &tsg)
Assignment operator.
std::map< std::pair< IonType, Size >, std::vector< double > > ObservedIntensMap
Definition: SvmTheoreticalSpectrumGeneratorTrainer.h:70
SvmTheoreticalSpectrumGeneratorTrainer(const SvmTheoreticalSpectrumGeneratorTrainer &source)
Copy constructor.
void trainSecondaryTypes_(TextFile &info_outfile, Size number_of_regions, Size number_of_intensity_levels, ObservedIntensMap &observed_intensities, const std::vector< IonType > &ion_types, const std::vector< bool > &is_primary)
trains the Bayesian secondary peak types models
void countIntensities_(const PeakSpectrum &spectrum, const AASequence &annotation, IonType type, std::map< std::pair< IonType, Size >, std::vector< double > > &observed_intensities, double tolerance, Size number_of_regions)
stores the observed intensities for each sector-type combination in a vector
void trainModel(const PeakMap &spectra, const std::vector< AASequence > &annotations, String filename, Int precursor_charge)
trains an SVM for each ion_type and stores them in files <filename>_residue_loss_charge....
void normalizeIntensity(PeakSpectrum &S) const
Normalizes the intensity of the peaks in the input data.
SvmTheoreticalSpectrumGenerator::IonType IonType
Definition: SvmTheoreticalSpectrumGeneratorTrainer.h:68
~SvmTheoreticalSpectrumGeneratorTrainer() override
Destructor.
A set of descriptors for a single training row.
Definition: SvmTheoreticalSpectrumGenerator.h:220
This class provides some basic file handling methods for text files.
Definition: TextFile.h:47
int Int
Signed integer type.
Definition: Types.h:102
size_t Size
Size type e.g. used as variable which can hold result of size()
Definition: Types.h:127
Main OpenMS namespace.
Definition: FeatureDeconvolution.h:47
nested class
Definition: SvmTheoreticalSpectrumGenerator.h:83