SeqAn3 3.4.0-rc.1
The Modern C++ library for sequence analysis.
Loading...
Searching...
No Matches
aa10li.hpp
Go to the documentation of this file.
1// -----------------------------------------------------------------------------------------------------
2// Copyright (c) 2006-2023, Knut Reinert & Freie Universität Berlin
3// Copyright (c) 2016-2023, 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
20
21namespace seqan3
22{
82class aa10li : public aminoacid_base<aa10li, 10>
83{
84private:
87
89 friend base_t;
92 friend base_t::base_t;
94
95public:
99 constexpr aa10li() noexcept = default;
100 constexpr aa10li(aa10li const &) noexcept = default;
101 constexpr aa10li(aa10li &&) noexcept = default;
102 constexpr aa10li & operator=(aa10li const &) noexcept = default;
103 constexpr aa10li & operator=(aa10li &&) noexcept = default;
104 ~aa10li() noexcept = default;
105
107 using base_t::base_t;
109
110private:
112 static constexpr char_type rank_to_char_table[alphabet_size]{'A', 'B', 'C', 'F', 'G', 'H', 'I', 'J', 'K', 'P'};
113
115 static constexpr rank_type char_to_rank(char_type const chr)
116 {
117 using index_t = std::make_unsigned_t<char_type>;
118 return char_to_rank_table[static_cast<index_t>(chr)];
119 }
120
122 static constexpr char_type rank_to_char(rank_type const rank)
123 {
124 return rank_to_char_table[rank];
125 }
126
127 // clang-format off
129 static constexpr std::array<rank_type, 256> char_to_rank_table
130 {
131 []() constexpr {
133
134 // initialize with 'A' because S appears most frequently and gets converted to A in this alphabet
135 ret.fill(0u); // Value-initialisation of std::array does usually initialise. `fill` is explicit.
136
137 // reverse mapping for characters and their lowercase
138 for (rank_type rnk = 0u; rnk < alphabet_size; ++rnk)
139 {
140 ret[static_cast<rank_type>(rank_to_char_table[rnk])] = rnk;
141 ret[static_cast<rank_type>(to_lower(rank_to_char_table[rnk]))] = rnk;
142 }
143
144 ret['D'] = ret['B'];
145 ret['d'] = ret['B']; // Convert D to B (either D/N).
146 ret['E'] = ret['B'];
147 ret['e'] = ret['B']; // Convert E to B (either D/N).
148 ret['L'] = ret['J'];
149 ret['l'] = ret['J']; // Convert L to J (either I/L).
150 ret['M'] = ret['J'];
151 ret['m'] = ret['J']; // Convert M to J (either I/L).
152 ret['N'] = ret['H'];
153 ret['n'] = ret['H']; // Convert N to H.
154 ret['O'] = ret['K'];
155 ret['o'] = ret['K']; // Convert Pyrrolysine to K.
156 ret['Q'] = ret['B'];
157 ret['q'] = ret['B']; // Convert Q to B (either D/N).
158 ret['R'] = ret['K'];
159 ret['r'] = ret['K']; // Convert R to K.
160 ret['S'] = ret['A'];
161 ret['s'] = ret['A']; // Convert S to A.
162 ret['T'] = ret['A'];
163 ret['t'] = ret['A']; // Convert T to A.
164 ret['U'] = ret['C'];
165 ret['u'] = ret['C']; // Convert Selenocysteine to C.
166 ret['V'] = ret['I'];
167 ret['v'] = ret['I']; // Convert V to I.
168 ret['W'] = ret['F'];
169 ret['w'] = ret['F']; // Convert W to F.
170 ret['X'] = ret['A'];
171 ret['x'] = ret['A']; // Convert unknown amino acids to Alanine.
172 ret['Y'] = ret['F'];
173 ret['y'] = ret['F']; // Convert Y to F.
174 ret['Z'] = ret['B'];
175 ret['z'] = ret['B']; // Convert Z (either E/Q) to B (either D/N).
176 ret['*'] = ret['F']; // The most common stop codon is UGA. This is most similar to a Tryptophan which in
177 // this alphabet gets converted to Phenylalanine.
178
179 return ret;
180 }()
181 };
182};
183// clang-format of
184
185// ------------------------------------------------------------------
186// containers
187// ------------------------------------------------------------------
188
195
196// ------------------------------------------------------------------
197// literals
198// ------------------------------------------------------------------
199inline namespace literals
200{
201
215constexpr aa10li operator""_aa10li(char const c) noexcept
216{
217 return aa10li{}.assign_char(c);
218}
219
231SEQAN3_WORKAROUND_LITERAL aa10li_vector operator""_aa10li(char const * const s, size_t const n)
232{
234 r.resize(n);
235
236 for (size_t i = 0; i < n; ++i)
237 r[i].assign_char(s[i]);
238
239 return r;
240}
242
243} // namespace literals
244
245} // namespace seqan3
Provides seqan3::aminoacid_alphabet.
Provides seqan3::aminoacid_base.
The reduced Li amino acid alphabet..
Definition: aa10li.hpp:83
constexpr aa10li() noexcept=default
Defaulted.
constexpr derived_type & assign_char(char_type const chr) noexcept
Assign from a character, implicitly converts invalid characters.
Definition: alphabet_base.hpp:163
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:199
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
A CRTP-base that refines seqan3::alphabet_base and is used by the amino acids.
Definition: aminoacid_base.hpp:32
T fill(T... args)
The main SeqAn3 namespace.
Definition: aligned_sequence_concept.hpp:29
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:83
#define SEQAN3_WORKAROUND_LITERAL
Our char literals returning std::vector should be constexpr if constexpr std::vector is supported.
Definition: platform.hpp:258
T resize(T... args)
Provides utilities for modifying characters.