DecoyGenerator.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: Timo Sachsenberg $
// $Authors: Timo Sachsenberg $
// --------------------------------------------------------------------------
 
#pragma once
 
#include <OpenMS/CONCEPT/Types.h>
#include <OpenMS/MATH/MathFunctions.h>
 
#include <unordered_map>
 
namespace OpenMS
{
  class AASequence;
  class DigestionEnzymeProtein;
 
  class OPENMS_DLLAPI DecoyGenerator
  {
    public:
      // initializes random generator
      DecoyGenerator();
 
      // destructor
      ~DecoyGenerator() = default;
 
      // random seed for shuffling
      void setSeed(UInt64 seed);
 
      /* 
         @brief reverses the protein sequence. 
         note: modifications are discarded
      */
      AASequence reverseProtein(const AASequence& protein) const;
    
      /* 
          @brief reverses the protein's peptide sequences between enzymatic cutting positions. 
          With 'unspecific cleavage' (no enzymatic termini to keep), the whole protein is reversed (reverseProtein()).
          note: modifications are discarded
      */
      AASequence reversePeptides(const AASequence& protein, const std::string& protease) const;
 
      std::vector<AASequence> shuffle(const AASequence& protein, const std::string& protease, int decoy_factor = 1);
 
      /*
          @brief shuffle the protein's peptide sequences between enzymatic cutting positions.
          each peptide is shuffled @p max_attempts times to minimize sequence identity.
          With 'unspecific cleavage' (no enzymatic termini to keep), the whole protein is shuffled as one sequence.
 
          Note: 
            - Generated decoys are retrieved from a cache to prevent that same peptide (in different proteins) 
              leads to different decoys.
            - modifications are discarded 
      */
      AASequence shufflePeptides(
            const AASequence& aas,
            const std::string& protease,
            const int max_attempts = 100
            );
    
    private:
      // sequence identity by matching AAs
      static double SequenceIdentity_(const std::string& decoy, const std::string& target);
 
      // portable shuffle
      Math::RandomShuffler shuffler_;
 
      // ensures that shuffling same peptide (in different proteins) leads to same decoy
      std::unordered_map<std::string, std::string> td_cache_;
  };
}