SeqAn3 3.1.0
The Modern C++ library for sequence analysis.
dna5.hpp
Go to the documentation of this file.
1// -----------------------------------------------------------------------------------------------------
2// Copyright (c) 2006-2021, Knut Reinert & Freie Universität Berlin
3// Copyright (c) 2016-2021, Knut Reinert & MPI für molekulare Genetik
4// This file may be used, modified and/or redistributed under the terms of the 3-clause BSD-License
5// shipped with this file and also available at: https://github.com/seqan/seqan3/blob/master/LICENSE.md
6// -----------------------------------------------------------------------------------------------------
7
13#pragma once
14
15#include <vector>
16
19
20// ------------------------------------------------------------------
21// dna5
22// ------------------------------------------------------------------
23
24namespace seqan3
25{
26
27class rna5;
28
50class dna5 : public nucleotide_base<dna5, 5>
51{
52private:
55
57 friend base_t;
59 friend base_t::base_t;
62 friend rna5;
63
64public:
68 constexpr dna5() noexcept = default;
69 constexpr dna5(dna5 const &) noexcept = default;
70 constexpr dna5(dna5 &&) noexcept = default;
71 constexpr dna5 & operator=(dna5 const &) noexcept = default;
72 constexpr dna5 & operator=(dna5 &&) noexcept = default;
73 ~dna5() noexcept = default;
74
75 using base_t::base_t;
76
84 template <std::same_as<rna5> t> // Accept incomplete type
85 constexpr dna5(t const & r) noexcept
86 {
87 assign_rank(r.to_rank());
88 }
90
91private:
93 static constexpr char_type rank_to_char_table[alphabet_size]
94 {
95 'A',
96 'C',
97 'G',
98 'N',
99 'T'
100 };
101
103 static constexpr std::array<rank_type, 256> char_to_rank_table
104 {
105 [] () constexpr
106 {
108
109 // initialize with UNKNOWN (std::array::fill unfortunately not constexpr)
110 for (auto & c : ret)
111 c = 3; // == 'N'
112
113 // reverse mapping for characters and their lowercase
114 for (size_t rnk = 0u; rnk < alphabet_size; ++rnk)
115 {
116 ret[rank_to_char_table[rnk]] = rnk;
117 ret[to_lower(rank_to_char_table[rnk])] = rnk;
118 }
119
120 // set U equal to T
121 ret['U'] = ret['T']; ret['u'] = ret['t'];
122
123 // iupac characters are implicitly "UNKNOWN"
124 return ret;
125 }()
126 };
127
129 static constexpr rank_type rank_complement_table[alphabet_size]
130 {
131 4, // T is complement of 'A'_dna5
132 2, // G is complement of 'C'_dna5
133 1, // C is complement of 'G'_dna5
134 3, // N is complement of 'N'_dna5
135 0 // A is complement of 'T'_dna5
136 };
137
139 static constexpr rank_type rank_complement(rank_type const rank)
140 {
141 return rank_complement_table[rank];
142 }
143
145 static constexpr char_type rank_to_char(rank_type const rank)
146 {
147 return rank_to_char_table[rank];
148 }
149
151 static constexpr rank_type char_to_rank(char_type const chr)
152 {
153 using index_t = std::make_unsigned_t<char_type>;
154 return char_to_rank_table[static_cast<index_t>(chr)];
155 }
156};
157
158// ------------------------------------------------------------------
159// containers
160// ------------------------------------------------------------------
161
168
169// ------------------------------------------------------------------
170// literals
171// ------------------------------------------------------------------
172inline namespace literals
173{
174
189constexpr dna5 operator""_dna5(char const c) noexcept
190{
191 return dna5{}.assign_char(c);
192}
193
203inline dna5_vector operator""_dna5(char const * s, std::size_t n)
204{
205 dna5_vector r;
206 r.resize(n);
207
208 for (size_t i = 0; i < n; ++i)
209 r[i].assign_char(s[i]);
210
211 return r;
212}
214
215} // inline namespace literals
216
217} // namespace seqan3
A CRTP-base that makes defining a custom alphabet easier.
Definition: alphabet_base.hpp:57
constexpr derived_type & assign_char(char_type const chr) noexcept
Assign from a character, implicitly converts invalid characters.
Definition: alphabet_base.hpp:165
detail::min_viable_uint_t< size - 1 > rank_type
The type of the alphabet when represented as a number (e.g. via to_rank()).
Definition: alphabet_base.hpp:80
static constexpr detail::min_viable_uint_t< size > alphabet_size
The size of the alphabet, i.e. the number of different values it can take.
Definition: alphabet_base.hpp:203
std::conditional_t< std::same_as< char_t, void >, char, char_t > char_type
The char representation; conditional needed to make semi alphabet definitions legal.
Definition: alphabet_base.hpp:72
constexpr derived_type & assign_rank(rank_type const c) noexcept
Assign from a numeric value.
Definition: alphabet_base.hpp:191
The five letter DNA alphabet of A,C,G,T and the unknown character N..
Definition: dna5.hpp:51
constexpr dna5() noexcept=default
Defaulted.
A CRTP-base that refines seqan3::alphabet_base and is used by the nucleotides.
Definition: nucleotide_base.hpp:43
The five letter RNA alphabet of A,C,G,U and the unknown character N..
Definition: rna5.hpp:49
The main SeqAn3 namespace.
Definition: cigar_operation_table.hpp:2
constexpr char_type to_lower(char_type const c) noexcept
Converts 'A'-'Z' to 'a'-'z' respectively; other characters are returned as is.
Definition: transform.hpp:81
SeqAn specific customisations in the standard namespace.
Provides seqan3::nucleotide_base.
T resize(T... args)
Provides utilities for modifying characters.