dna4.hpp

Go to the documentation of this file.

// -----------------------------------------------------------------------------------------------------
// Copyright (c) 2006-2020, Knut Reinert & Freie Universität Berlin
// Copyright (c) 2016-2020, Knut Reinert & MPI für molekulare Genetik
// This file may be used, modified and/or redistributed under the terms of the 3-clause BSD-License
// shipped with this file and also available at: https://github.com/seqan/seqan3/blob/master/LICENSE.md
// -----------------------------------------------------------------------------------------------------
 
#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>    // Accept incomplete type
    constexpr dna4(t const & r) noexcept
    {
        assign_rank(r.to_rank());
    }
 
protected:
 
    static constexpr char_type rank_to_char[alphabet_size]
    {
        'A',
        'C',
        'G',
        'T'
    };
 
    static constexpr std::array<rank_type, 256> char_to_rank
    {
        [] () 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[rnk] ] = rnk;
                ret[to_lower(rank_to_char[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']; // or G
            ret['Y'] = ret['C']; ret['y'] = ret['C']; // or T
            ret['S'] = ret['C']; ret['s'] = ret['C']; // or G
            ret['W'] = ret['A']; ret['w'] = ret['A']; // or T
            ret['K'] = ret['G']; ret['k'] = ret['G']; // or T
            ret['M'] = ret['A']; ret['m'] = ret['A']; // or T
            ret['B'] = ret['C']; ret['b'] = ret['C']; // or G or T
            ret['D'] = ret['A']; ret['d'] = ret['A']; // or G or T
            ret['H'] = ret['A']; ret['h'] = ret['A']; // or C or T
            ret['V'] = ret['A']; ret['v'] = ret['A']; // or C or G
 
            return ret;
        }()
    };
 
    static const std::array<dna4, alphabet_size> complement_table;
};
 
// ------------------------------------------------------------------
// containers
// ------------------------------------------------------------------
 
using dna4_vector = std::vector<dna4>;
 
// ------------------------------------------------------------------
// literals
// ------------------------------------------------------------------
 
constexpr dna4 operator""_dna4(char const c) noexcept
{
    return dna4{}.assign_char(c);
}
 
inline 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;
}
 
// ------------------------------------------------------------------
// dna4 (deferred definition)
// ------------------------------------------------------------------
 
constexpr std::array<dna4, dna4::alphabet_size> dna4::complement_table
{
    'T'_dna4,    // complement of 'A'_dna4
    'G'_dna4,    // complement of 'C'_dna4
    'C'_dna4,    // complement of 'G'_dna4
    'A'_dna4     // complement of 'T'_dna4
};
 
} // namespace seqan3