EnzymaticDigestion.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: Chris Bielow, Xiao Liang $
// $Authors: Marc Sturm, Chris Bielow, Jeremi Maciejewski $
// --------------------------------------------------------------------------
 
#pragma once
 
#include <OpenMS/CHEMISTRY/DigestionEnzyme.h>
#include <OpenMS/CONCEPT/Types.h>
#include <OpenMS/DATASTRUCTURES/RegularExpression.h>
#include <functional>          // for std::function
#include <string>
#include <string_view>
#include <vector>
 
namespace OpenMS
{
 
  class OPENMS_DLLAPI EnzymaticDigestion
  {
  public:
    enum Specificity
    { // note: the value of the first three items is important, since some engines just report the number of required termini (0, 1, 2)
      SPEC_NONE = 0, 
      SPEC_SEMI = 1, 
      SPEC_FULL = 2, 
      SPEC_UNKNOWN = 3,
      SPEC_NOCTERM = 8, 
      SPEC_NONTERM = 9, 
      SIZE_OF_SPECIFICITY = 10
    };
    static const std::string NamesOfSpecificity[SIZE_OF_SPECIFICITY];
 
    static const std::string NoCleavage;
 
    static const std::string UnspecificCleavage;
 
    EnzymaticDigestion();
 
    EnzymaticDigestion(const EnzymaticDigestion& rhs);
 
    EnzymaticDigestion& operator=(const EnzymaticDigestion& rhs);
 
    virtual ~EnzymaticDigestion();
 
    Size getMissedCleavages() const;
 
    void setMissedCleavages(Size missed_cleavages);
 
    std::string getEnzymeName() const;
 
    virtual void setEnzyme(const DigestionEnzyme* enzyme);
 
    Specificity getSpecificity() const;
 
    void setSpecificity(Specificity spec);
 
    static Specificity getSpecificityByName(const std::string& name);
 
    Size digestUnmodified(const std::string_view& sequence, std::vector<std::string_view>& output, Size min_length = 1, Size max_length = 0) const;
 
    Size digestUnmodified(const std::string_view& sequence, std::vector<std::pair<Size, Size>>& output, Size min_length = 1, Size max_length = 0) const;
 
    bool isValidProduct(const std::string& protein, int pep_pos, int pep_length, bool ignore_missed_cleavages = true) const;
 
    Size countInternalCleavageSites(const std::string& sequence) const;
 
    bool filterByMissedCleavages(const std::string& sequence, const std::function<bool(const Int)>& filter) const;
 
 
  protected:
    bool isValidProduct_(const std::string& sequence,
                         int pos,
                         int length,
                         bool ignore_missed_cleavages,
                         bool allow_nterm_protein_cleavage,
                         bool allow_random_asp_pro_cleavage) const;
    std::vector<int> tokenize_(const std::string& sequence, int start = 0, int end = -1) const;
 
    Size semiSpecificDigestion_(const std::vector<int>& cleavage_positions, std::vector<std::pair<Size, Size>>& output, Size min_length = 0, Size max_length = -1) const;
 
    Size digestAfterTokenize_(const std::vector<int>& fragment_positions, const std::string_view& sequence, std::vector<std::string_view>& output, Size min_length = 0, Size max_length = -1) const;
    Size digestAfterTokenize_(const std::vector<int>& fragment_positions, const std::string_view& sequence, std::vector<std::pair<Size, Size>>& output, Size min_length = 0, Size max_length = -1) const;
 
    Size countMissedCleavages_(const std::vector<int>& cleavage_positions, Size seq_start, Size seq_end) const;
 
    Size missed_cleavages_;
 
    const DigestionEnzyme* enzyme_;
    RegularExpression re_; 
 
    Specificity specificity_;
  };
 
} // namespace OpenMS