MultiplexFiltering.h

Go to the documentation of this file.

// Copyright (c) 2002-present, OpenMS Inc. -- EKU Tuebingen, ETH Zurich, and FU Berlin
// SPDX-License-Identifier: BSD-3-Clause
//
// --------------------------------------------------------------------------
// $Maintainer: Lars Nilse $
// $Authors: Lars Nilse $
// --------------------------------------------------------------------------
 
#pragma once
 
#include <OpenMS/KERNEL/BaseFeature.h>
#include <OpenMS/KERNEL/StandardTypes.h>
#include <OpenMS/KERNEL/MSExperiment.h>
#include <OpenMS/CONCEPT/ProgressLogger.h>
#include <OpenMS/PROCESSING/CENTROIDING/PeakPickerHiRes.h>
#include <OpenMS/FEATUREFINDER/MultiplexIsotopicPeakPattern.h>
#include <OpenMS/FEATUREFINDER/MultiplexFilteredMSExperiment.h>
#include <OpenMS/FEATUREFINDER/MultiplexFilteredPeak.h>
#include <OpenMS/MATH/MISC/CubicSpline2d.h>
 
#include <functional>
#include <map>
#include <optional>
#include <string>
#include <vector>
#include <algorithm>
#include <iostream>
 
 
namespace OpenMS
{
  class IsotopeDistribution;
 
  class OPENMS_DLLAPI MultiplexFiltering :
    public ProgressLogger
  {
public:
    typedef std::vector<std::vector<int> > White2Original;
 
    MultiplexFiltering(const MSExperiment& exp_centroided, const std::vector<MultiplexIsotopicPeakPattern>& patterns, int isotopes_per_peptide_min,
                       int isotopes_per_peptide_max, double intensity_cutoff, double rt_band, double mz_tolerance, bool mz_tolerance_unit,
                       double peptide_similarity, double averagine_similarity, double averagine_similarity_scaling, std::string averagine_type="peptide");
    MSExperiment& getCentroidedExperiment();
    
    MSExperiment getBlacklist();
 
    struct BlacklistWriter
    {
      unsigned pattern_idx;
      unsigned peak_idx;
      int mass_trace;
    };
 
    struct BlacklistOwner
    {
      BlacklistWriter first;
      BlacklistWriter last;
    };
 
    std::vector<std::vector<BlacklistOwner>> getBlacklistOwners() const;
 
    std::vector<BlacklistOwner> getBlacklistOwners(Size spectrum_index) const;
 
    struct DeuteriumLabel
    {
      unsigned deuterium = 0;  
      double enrichment = 1.0; 
    };
 
    void setDeuteriumLabels(const std::map<std::string, DeuteriumLabel>& labels);
 
    static double deuteriumLowerFraction(unsigned deuterium, double enrichment, const IsotopeDistribution& isotopes);
 
    static double deuteriumAllowance(unsigned deuterium, double enrichment, const IsotopeDistribution& isotopes);
 
protected:
    struct BlacklistEntry
    {
      size_t rt_idx;
      size_t mz_idx;
      int value;
    };
 
    struct BlacklistOwnerRecord
    {
      int first;
      int first_value;
      int last;
    };
 
    void updateWhiteMSExperiment_();
 
    int checkForSignificantPeak_(double mz, double mz_tolerance, MSExperiment::ConstIterator& it_rt, double intensity_first_peak,
                                 double fraction = 0.3) const;
 
    double deuteriumAllowance_(const MultiplexIsotopicPeakPattern& pattern, size_t peptide, double mz) const;
 
    bool filterPeakPositions_(double mz, const MSExperiment::ConstIterator& it_rt_begin, const MSExperiment::ConstIterator& it_rt_band_begin, const MSExperiment::ConstIterator& it_rt_band_end, const MultiplexIsotopicPeakPattern& pattern, MultiplexFilteredPeak& peak, std::vector<BlacklistEntry>* blacklist_reads = nullptr) const;
 
    void blacklistPeak_(const MultiplexFilteredPeak& peak, unsigned pattern_idx, size_t peak_idx);
 
    void applyBlacklistEntries_(const std::vector<BlacklistEntry>& entries, unsigned pattern_idx, size_t peak_idx);
 
    void blacklistEntries_(const MultiplexFilteredPeak& peak, unsigned pattern_idx, std::vector<BlacklistEntry>& entries) const;
 
    typedef std::function<std::optional<MultiplexFilteredPeak>(SignedSize, std::vector<BlacklistEntry>*)> PeakFilter;
 
    void filterSpectrum_(size_t idx_rt, unsigned pattern_idx, const PeakFilter& filter_peak, MultiplexFilteredMSExperiment& result);
 
    bool filterAveragineModel_(const MultiplexIsotopicPeakPattern& pattern, const MultiplexFilteredPeak& peak) const;
 
    const IsotopeDistribution& averagineDistribution_(double mass) const;
    
    bool filterPeptideCorrelation_(const MultiplexIsotopicPeakPattern& pattern, const MultiplexFilteredPeak& peak) const;
 
    MSExperiment exp_centroided_;
 
    std::vector<std::vector<int> > blacklist_;
 
    std::vector<std::vector<int>> blacklist_owner_;
 
    std::vector<BlacklistOwnerRecord> blacklist_owner_records_;
 
    std::vector<std::pair<unsigned, unsigned>> filtered_peaks_;
    
    std::vector<std::vector<BlacklistEntry>> blacklist_reads_;
 
    std::vector<std::vector<BlacklistEntry>> blacklist_writes_;
 
    std::vector<std::optional<MultiplexFilteredPeak>> passed_;
 
    MSExperiment exp_centroided_white_;
    
    White2Original exp_centroided_mapping_;
 
    std::vector<MultiplexIsotopicPeakPattern> patterns_;
 
    size_t isotopes_per_peptide_min_;
 
    size_t isotopes_per_peptide_max_;
 
    double intensity_cutoff_;
 
    double rt_band_;
    
    double mz_tolerance_;
 
    bool mz_tolerance_unit_in_ppm_;
 
    double peptide_similarity_;
 
    double averagine_similarity_;
 
    double averagine_similarity_scaling_;
 
    std::string averagine_type_;
 
    std::vector<std::vector<DeuteriumLabel>> deuterium_;
 
  };
 
}