dna4.hpp

Go to the documentation of this file.

// SPDX-FileCopyrightText: 2006-2025 Knut Reinert & Freie Universität Berlin
// SPDX-FileCopyrightText: 2016-2025 Knut Reinert & MPI für molekulare Genetik
// SPDX-License-Identifier: BSD-3-Clause

 
#pragma once
 
#include <vector>
 
#include <seqan3/alphabet/nucleotide/nucleotide_base.hpp>
 
// ------------------------------------------------------------------
// dna4
// ------------------------------------------------------------------
 
namespace seqan3
{
 
class rna4;

class dna4 : public nucleotide_base<dna4, 4>
{
private:
    using base_t = nucleotide_base<dna4, 4>;

    friend base_t;
    friend base_t::base_t;
    friend rna4;
 
public:
    constexpr dna4() noexcept = default;                         
    constexpr dna4(dna4 const &) noexcept = default;             
    constexpr dna4(dna4 &&) noexcept = default;                  
    constexpr dna4 & operator=(dna4 const &) noexcept = default; 
    constexpr dna4 & operator=(dna4 &&) noexcept = default;      
    ~dna4() noexcept = default;                                  
 
    using base_t::base_t;

    template <std::same_as<rna4> t> // template parameter t to accept incomplete type
    constexpr dna4(t const & r) noexcept
    {
        assign_rank(r.to_rank());
    }


    constexpr dna4 complement() const noexcept
    {
        return dna4{}.assign_rank(to_rank() ^ 0b11);
    }
 
private:
    static constexpr char_type rank_to_char_table[alphabet_size]{'A', 'C', 'G', 'T'};

    static constexpr rank_type rank_complement_table[alphabet_size]{
        3, // T is complement of 'A'_dna4
        2, // G is complement of 'C'_dna4
        1, // C is complement of 'G'_dna4
        0  // A is complement of 'T'_dna4
    };

    static constexpr rank_type rank_complement(rank_type const rank)
    {
        return rank_complement_table[rank];
    }

    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)];
    }

    static constexpr std::array<rank_type, 256> char_to_rank_table{[]() constexpr
                                                                   {
                                                                       std::array<rank_type, 256> ret{};
 
                                                                       // reverse mapping for characters and their lowercase
                                                                       for (size_t rnk = 0u; rnk < alphabet_size; ++rnk)
                                                                       {
                                                                           ret[rank_to_char_table[rnk]] = rnk;
                                                                           ret[to_lower(rank_to_char_table[rnk])] = rnk;
                                                                       }
 
                                                                       // set U equal to T
                                                                       ret['U'] = ret['T'];
                                                                       ret['u'] = ret['t'];
 
                                                                       // iupac characters get special treatment, because there is no N
                                                                       ret['R'] = ret['A'];
                                                                       ret['r'] = ret['A']; // A or G
                                                                       ret['Y'] = ret['C'];
                                                                       ret['y'] = ret['C']; // C or T
                                                                       ret['S'] = ret['C'];
                                                                       ret['s'] = ret['C']; // C or G
                                                                       ret['W'] = ret['A'];
                                                                       ret['w'] = ret['A']; // A or T
                                                                       ret['K'] = ret['G'];
                                                                       ret['k'] = ret['G']; // G or T
                                                                       ret['M'] = ret['A'];
                                                                       ret['m'] = ret['A']; // A or T
                                                                       ret['B'] = ret['C'];
                                                                       ret['b'] = ret['C']; // C or G or T
                                                                       ret['D'] = ret['A'];
                                                                       ret['d'] = ret['A']; // A or G or T
                                                                       ret['H'] = ret['A'];
                                                                       ret['h'] = ret['A']; // A or C or T
                                                                       ret['V'] = ret['A'];
                                                                       ret['v'] = ret['A']; // A or C or G
 
                                                                       return ret;
                                                                   }()};
};
 
// ------------------------------------------------------------------
// containers
// ------------------------------------------------------------------

using dna4_vector = std::vector<dna4>;
 
inline namespace literals
{
 
// ------------------------------------------------------------------
// literals
// ------------------------------------------------------------------



constexpr dna4 operator""_dna4(char const c) noexcept
{
    return dna4{}.assign_char(c);
}

SEQAN3_WORKAROUND_LITERAL dna4_vector operator""_dna4(char const * s, std::size_t n)
{
    dna4_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