PeptDeepUtils.h

Go to the documentation of this file.

// Copyright (c) 2002-present, OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin
// SPDX-License-Identifier: BSD-3-Clause
//
// --------------------------------------------------------------------------
// $Maintainer: Timo Sachsenberg $
// $Authors: Satyam Yadav, Justin Sing $
// --------------------------------------------------------------------------
#pragma once
 
#include <OpenMS/CONCEPT/Types.h>
#include <OpenMS/CONCEPT/Exception.h>
#include <string>
#include <vector>
#include <array>
#include <string_view>
 
namespace OpenMS {
  namespace ML {
 
    // --- Shared PeptDeep Architecture Constants ---
    constexpr int64_t PEPTDEEP_MOD_ELEMENTS = 109;
 
    inline constexpr std::array<std::string_view, 109> ALPHAPEPTDEEP_MOD_ELEMENTS = {
    "C", "H", "N", "O", "P", "S", "B", "F", "I", "K", "U", "V", "W", "X", "Y",
    "Ac", "Ag", "Al", "Am", "Ar", "As", "At", "Au", "Ba", "Be", "Bi", "Bk",
    "Br", "Ca", "Cd", "Ce", "Cf", "Cl", "Cm", "Co", "Cr", "Cs", "Cu", "Dy",
    "Er", "Es", "Eu", "Fe", "Fm", "Fr", "Ga", "Gd", "Ge", "He", "Hf", "Hg",
    "Ho", "In", "Ir", "Kr", "La", "Li", "Lr", "Lu", "Md", "Mg", "Mn", "Mo",
    "Na", "Nb", "Nd", "Ne", "Ni", "No", "Np", "Os", "Pa", "Pb", "Pd", "Pm",
    "Po", "Pr", "Pt", "Pu", "Ra", "Rb", "Re", "Rh", "Rn", "Ru", "Sb", "Sc",
    "Se", "Si", "Sm", "Sn", "Sr", "Ta", "Tb", "Tc", "Te", "Th", "Ti", "Tl",
    "Tm", "Xe", "Yb", "Zn", "Zr", "2H", "13C", "15N", "18O", "?"
    };
 
    constexpr int64_t PEPTDEEP_MAX_INSTRUMENT_NUM = 8;
 
    constexpr int64_t PEPTDEEP_UNKNOWN_INSTRUMENT_INDEX = PEPTDEEP_MAX_INSTRUMENT_NUM - 1;
 
    inline constexpr std::array<std::string_view, 5> ALPHAPEPTDEEP_INSTRUMENTS = {
      "QE", "Lumos", "timsTOF", "SciexTOF", "ThermoTOF"
    };
 
    inline int64_t instrumentIndex(std::string_view name)
    {
      auto upper = [](char c) { return (c >= 'a' && c <= 'z') ? static_cast<char>(c - ('a' - 'A')) : c; };
 
      for (Size i = 0; i < ALPHAPEPTDEEP_INSTRUMENTS.size(); ++i)
      {
        const std::string_view candidate = ALPHAPEPTDEEP_INSTRUMENTS[i];
        if (candidate.size() != name.size()) { continue; }
 
        bool same = true;
        for (Size c = 0; c < name.size(); ++c)
        {
          if (upper(name[c]) != upper(candidate[c])) { same = false; break; }
        }
        if (same) { return static_cast<int64_t>(i); }
      }
      return PEPTDEEP_UNKNOWN_INSTRUMENT_INDEX;
    }
 
    inline void validateInstrumentIndices(const std::vector<int64_t>& instrument_indices)
    {
      for (int64_t index : instrument_indices)
      {
        if (index < 0 || index >= PEPTDEEP_MAX_INSTRUMENT_NUM)
        {
          throw Exception::IllegalArgument(__FILE__, __LINE__, OPENMS_PRETTY_FUNCTION,
            "Instrument index " + std::to_string(index) + " is outside the range [0, "
            + std::to_string(PEPTDEEP_MAX_INSTRUMENT_NUM) + ") that the MS2 model encodes. Derive "
            "indices from ML::instrumentIndex() rather than passing literals.");
        }
      }
    }
 
    inline OpenMS::Int64 getAAIndex(char aa) {
      if (aa >= 'A' && aa <= 'Z') return aa - 'A' + 1;
      if (aa >= 'a' && aa <= 'z') return aa - 'a' + 1;
      return 0; // 0 serves as the padding and unknown token
    }
 
    inline void validatePeptide(const std::string& peptide) {
        if (peptide.empty()) {
            throw Exception::IllegalArgument(__FILE__, __LINE__, OPENMS_PRETTY_FUNCTION, "Peptide sequence cannot be empty.");
        }
    }
 
  }
}