aa10murphy.hpp

Go to the documentation of this file.

// SPDX-FileCopyrightText: 2006-2024 Knut Reinert & Freie Universität Berlin
// SPDX-FileCopyrightText: 2016-2024 Knut Reinert & MPI für molekulare Genetik
// SPDX-License-Identifier: BSD-3-Clause
 
#pragma once
 
#include <vector>
 
#include <seqan3/alphabet/aminoacid/aminoacid_base.hpp>
#include <seqan3/alphabet/aminoacid/concept.hpp>
#include <seqan3/utility/char_operations/transform.hpp>
 
namespace seqan3
{
 
class aa10murphy : public aminoacid_base<aa10murphy, 10>
{
private:
    using base_t = aminoacid_base<aa10murphy, 10>;
 
    friend base_t;
    friend base_t::base_t;
 
public:
    constexpr aa10murphy() noexcept = default;                               
    constexpr aa10murphy(aa10murphy const &) noexcept = default;             
    constexpr aa10murphy(aa10murphy &&) noexcept = default;                  
    constexpr aa10murphy & operator=(aa10murphy const &) noexcept = default; 
    constexpr aa10murphy & operator=(aa10murphy &&) noexcept = default;      
    ~aa10murphy() noexcept = default;                                        
 
    using base_t::base_t;
 
private:
    static constexpr char_type rank_to_char_table[alphabet_size]{'A', 'B', 'C', 'F', 'G', 'H', 'I', 'K', 'P', 'S'};
 
    static constexpr char_type rank_to_char(rank_type const rank)
    {
        return rank_to_char_table[rank];
    }
 
    static constexpr rank_type char_to_rank(char_type const chr)
    {
        using index_t = std::make_unsigned_t<char_type>;
        return char_to_rank_table[static_cast<index_t>(chr)];
    }
 
    // clang-format off
    static constexpr std::array<rank_type, 256> char_to_rank_table{
        []() constexpr {
            std::array<rank_type, 256> ret{};
 
            // initialize with 'S' because that appears most frequently
            ret.fill(9u);
 
            // reverse mapping for characters and their lowercase
            for (rank_type rnk = 0u; rnk < alphabet_size; ++rnk)
            {
                ret[static_cast<rank_type>(rank_to_char_table[rnk])] = rnk;
                ret[static_cast<rank_type>(to_lower(rank_to_char_table[rnk]))] = rnk;
            }
 
            ret['D'] = ret['B'];
            ret['d'] = ret['B']; // Convert D to B (either D/N).
            ret['E'] = ret['B'];
            ret['e'] = ret['B']; // Convert E to B (either D/N).
            ret['J'] = ret['I'];
            ret['j'] = ret['I']; // Convert J (either I/L) to I.
            ret['L'] = ret['I'];
            ret['l'] = ret['I']; // Convert L to I.
            ret['M'] = ret['I'];
            ret['m'] = ret['I']; // Convert M to I.
            ret['N'] = ret['B'];
            ret['n'] = ret['B']; // Convert N to B (either D/N).
            ret['O'] = ret['K'];
            ret['o'] = ret['K']; // Convert Pyrrolysine to K.
            ret['Q'] = ret['B'];
            ret['q'] = ret['B']; // Convert Q to B (either D/N).
            ret['R'] = ret['K'];
            ret['r'] = ret['K']; // Convert R to K.
            ret['T'] = ret['S'];
            ret['t'] = ret['S']; // Convert T to S.
            ret['U'] = ret['C'];
            ret['u'] = ret['C']; // Convert Selenocysteine to C.
            ret['V'] = ret['I'];
            ret['v'] = ret['I']; // Convert V to I.
            ret['W'] = ret['F'];
            ret['w'] = ret['F']; // Convert W to F.
            ret['X'] = ret['S'];
            ret['x'] = ret['S']; // Convert unknown amino acids to Serine.
            ret['Y'] = ret['F'];
            ret['y'] = ret['F']; // Convert Y to F.
            ret['Z'] = ret['B'];
            ret['z'] = ret['B']; // Convert Z (either E/Q) to B (either D/N).
            ret['*'] = ret['F']; // The most common stop codon is UGA. This is most similar to a Tryptophan which in
                                 // this alphabet gets converted to Phenylalanine.
 
            return ret;
        }()
    };
};
// clang-format on
 
// ------------------------------------------------------------------
// containers
// ------------------------------------------------------------------
 
using aa10murphy_vector = std::vector<aa10murphy>;
 
// ------------------------------------------------------------------
// literals
// ------------------------------------------------------------------
inline namespace literals
{
 
constexpr aa10murphy operator""_aa10murphy(char const c) noexcept
{
    return aa10murphy{}.assign_char(c);
}
 
SEQAN3_WORKAROUND_LITERAL aa10murphy_vector operator""_aa10murphy(char const * const s, size_t const n)
{
    aa10murphy_vector r;
    r.resize(n);
 
    for (size_t i = 0; i < n; ++i)
        r[i].assign_char(s[i]);
 
    return r;
}
 
} // namespace literals
 
} // namespace seqan3