RNaseDigestion.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: Hendrik Weisser $
// $Authors: Hendrik Weisser, Samuel Wein $
// --------------------------------------------------------------------------
 
#pragma once
 
#include <OpenMS/CHEMISTRY/EnzymaticDigestion.h>
#include <OpenMS/CHEMISTRY/NASequence.h>
#include <OpenMS/METADATA/ID/IdentificationData.h>
 
#include <OpenMS/DATASTRUCTURES/RegularExpression.h>
 
#include <set>
 
namespace OpenMS
{
  class OPENMS_DLLAPI RNaseDigestion: public EnzymaticDigestion
  {
  public:
    using ConstRibonucleotidePtr = const Ribonucleotide*;
 
    struct DigestionProduct
    {
      NASequence fragment;
      std::pair<Size, Size> position;
    };
 
    struct CleavageSensitiveModGroups
    {
      std::set<ConstRibonucleotidePtr> cuts_before_sensitive;
      std::set<ConstRibonucleotidePtr> cuts_after_sensitive;
 
      std::set<ConstRibonucleotidePtr> combined() const
      {
        std::set<ConstRibonucleotidePtr> all = cuts_before_sensitive;
        all.insert(cuts_after_sensitive.begin(), cuts_after_sensitive.end());
        return all;
      }
    };
 
 
    void setEnzyme(const DigestionEnzyme* enzyme) override;
 
    void setEnzyme(const std::string& name);
 
    void digest(const NASequence& rna, std::vector<NASequence>& output,
                Size min_length = 0, Size max_length = 0) const;
 
    void digest(const NASequence& rna, std::vector<DigestionProduct>& output,
                Size min_length = 0, Size max_length = 0) const;
 
    std::vector<std::pair<Size, Size>> getFragmentPositions(
      const NASequence& rna, Size min_length = 0, Size max_length = 0) const;
 
    CleavageSensitiveModGroups inferCleavageSensitiveMods(
      const std::set<ConstRibonucleotidePtr>& variable_modifications) const;
 
    void digestWithCleavageSensitiveMods(
      const NASequence& rna,
      const CleavageSensitiveModGroups& cleavage_sensitive_mods,
      Size max_sensitive_mods_per_fragment,
      std::vector<DigestionProduct>& output,
      Size min_length = 0,
      Size max_length = 0) const;
 
    void digest(IdentificationData& id_data, Size min_length = 0,
                Size max_length = 0) const;
 
  protected:
    const Ribonucleotide* five_prime_gain_; 
    const Ribonucleotide* three_prime_gain_; 
    std::vector<RegularExpression>
      cuts_after_regexes_; 
    std::vector<RegularExpression> cuts_before_regexes_; 
 
    std::vector<std::pair<Size, Size>> getFragmentPositions_(
      const NASequence& rna, Size min_length, Size max_length)
      const;
 
    void applyTerminalGains_(NASequence& fragment,
                         const std::pair<Size, Size>& pos,
                         Size parent_size) const;
  };
 
} // namespace OpenMS