FragmentIndex.h

Go to the documentation of this file.

// Copyright (c) 2002-present, The OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin
// SPDX-License-Identifier: BSD-3-Clause
//
// --------------------------------------------------------------------------
// $Maintainer:  $
// $Authors:  $
// --------------------------------------------------------------------------
 
#pragma once
 
#include <OpenMS/CHEMISTRY/AASequence.h>
#include <OpenMS/DATASTRUCTURES/DefaultParamHandler.h>
#include <OpenMS/FORMAT/FASTAFile.h>
#include <OpenMS/KERNEL/MSExperiment.h>
#include <OpenMS/KERNEL/Peak1D.h>
 
 
#include <vector>
#include <functional>
 
namespace OpenMS
{
  class OPENMS_DLLAPI FragmentIndex : public DefaultParamHandler
  {
  public:
 
 
    struct Peptide {
 
      // We need a constructor in order to emplace back
      Peptide(UInt32 protein_idx, UInt32 modification_idx, std::pair<uint16_t , uint16_t> sequence, float precursor_mz):
          protein_idx(protein_idx),
        modification_idx_(modification_idx),
        sequence_(sequence),
        precursor_mz_(precursor_mz)
        {}
 
        UInt32 protein_idx;            
        UInt32 modification_idx_;      
        std::pair<uint16_t , uint16_t> sequence_; 
        float precursor_mz_;           
    };
 
    struct SpectrumMatch
    {
      uint32_t num_matched_{};      
      uint16_t precursor_charge_{};  
      int16_t isotope_error_{};      
      size_t peptide_idx_{};         
    };
 
 
    struct SpectrumMatchesTopN
    {
      std::vector<SpectrumMatch> hits_;     
 
 
      SpectrumMatchesTopN() = default;
 
      SpectrumMatchesTopN& operator+=(const SpectrumMatchesTopN& other)
      {
 
        this->hits_.insert(this->hits_.end(), other.hits_.begin(), other.hits_.end());
        return *this;
      }
 
      void clear()
      {
        hits_.clear();
 
      }
    };
    FragmentIndex();
 
    ~FragmentIndex() override = default;
 
    bool isBuild() const;
 
    const std::vector<Peptide>& getPeptides() const;
 
#ifdef DEBUG_FRAGMENT_INDEX
    void addSpecialPeptide(AASequence& peptide, Size source_idx);
#endif
 
    void build(const std::vector<FASTAFile::FASTAEntry> & fasta_entries);
 
    void clear();
 
 
    std::pair<size_t, size_t> getPeptidesInPrecursorRange(float precursor_mass,
                                                          const std::pair<float, float>& window);
 
    struct Hit
    {
      Hit(UInt32 peptide_idx, float fragment_mz) :
        peptide_idx(peptide_idx),
        fragment_mz(fragment_mz)
      {}
      UInt32 peptide_idx; // index in database
      float fragment_mz;
    };
 
    std::vector<Hit> query(const Peak1D& peak,
                           const std::pair<size_t,size_t>& peptide_idx_range,
                           uint16_t peak_charge);
 
    void querySpectrum(const MSSpectrum& spectrum,
                       SpectrumMatchesTopN& sms);
 
protected:
 
 
  struct Fragment
  {
      Fragment(UInt32 peptide_idx, float fragment_mz):
          peptide_idx_(peptide_idx),
          fragment_mz_(fragment_mz)
      {}
      UInt32 peptide_idx_; // 32 bit in sage
      float fragment_mz_;
  };
 
    bool is_build_{false};              
 
    void updateMembers_() override;
 
    void generatePeptides(const std::vector<FASTAFile::FASTAEntry>& fasta_entries);
 
    std::vector<Peptide> fi_peptides_;   
    std::vector<Fragment> fi_fragments_; 
 
    float fragment_min_mz_;  
    float fragment_max_mz_;  
    size_t bucketsize_;       
    std::vector<float> bucket_min_mz_;  
    float precursor_mz_tolerance_;
    bool precursor_mz_tolerance_unit_ppm_{true};
    float fragment_mz_tolerance_;
    bool fragment_mz_tolerance_unit_ppm_{true};    
private:
 
 
    void queryPeaks(SpectrumMatchesTopN& candidates,
                   const MSSpectrum& spectrum,
                   const std::pair<size_t, size_t>& candidates_range,
                   const int16_t isotope_error,
                   const uint16_t precursor_charge);
    void searchDifferentPrecursorRanges(const MSSpectrum& spectrum,
                                        float precursor_mass,
                                        SpectrumMatchesTopN& sms,
                                        uint16_t charge);
 
    void trimHits(SpectrumMatchesTopN& init_hits) const;
 
    //since we work with TheoreticalSpectrumGenerator, we must transfer some of those member variables
    bool add_b_ions_;
    bool add_y_ions_;
    bool add_a_ions_;
    bool add_c_ions_;
    bool add_x_ions_;
    bool add_z_ions_;
 
    // SpectrumGenerator independend member variables
    std::string digestion_enzyme_;
 
    size_t missed_cleavages_; 
    float peptide_min_mass_;
    float peptide_max_mass_;
    size_t peptide_min_length_;
    size_t peptide_max_length_;
  
    StringList modifications_fixed_;    
    StringList modifications_variable_; 
    size_t max_variable_mods_per_peptide_;
 
    // Search Related member variables
 
    uint16_t min_matched_peaks_;  
    int16_t min_isotope_error_;   
    int16_t max_isotope_error_;   
    uint16_t min_precursor_charge_; 
    uint16_t max_precursor_charge_; 
    uint16_t max_fragment_charge_;  
    uint32_t max_processed_hits_;   
    
    bool isOpenSearchMode_() const
    {
      return precursor_mz_tolerance_unit_ppm_
               ? (precursor_mz_tolerance_ > 1000.0)
               : (precursor_mz_tolerance_ > 1.0);
    }
    
    float open_precursor_window_lower_; 
    float open_precursor_window_upper_; 
 
 
  };
 
}