SeqAn3  3.0.3
The Modern C++ library for sequence analysis.
aa20.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 
20 
21 namespace seqan3
22 {
23 
63 class aa20 : public aminoacid_base<aa20, 20>
64 {
65 private:
68 
70  friend base_t;
72  friend base_t::base_t;
74 
75 public:
79  constexpr aa20() noexcept = default;
80  constexpr aa20(aa20 const &) noexcept = default;
81  constexpr aa20(aa20 &&) noexcept = default;
82  constexpr aa20 & operator=(aa20 const &) noexcept = default;
83  constexpr aa20 & operator=(aa20 &&) noexcept = default;
84  ~aa20() noexcept = default;
85 
86  using base_t::base_t;
88 
89 private:
91  static constexpr char_type rank_to_char_table[alphabet_size]
92  {
93  'A',
94  'C',
95  'D',
96  'E',
97  'F',
98  'G',
99  'H',
100  'I',
101  'K',
102  'L',
103  'M',
104  'N',
105  'P',
106  'Q',
107  'R',
108  'S',
109  'T',
110  'V',
111  'W',
112  'Y'
113  };
114 
116  static constexpr std::array<rank_type, 256> char_to_rank_table
117  {
118  [] () constexpr
119  {
121 
122  // initialize with UNKNOWN (std::array::fill unfortunately not constexpr)
123  for (auto & c : ret)
124  c = 15; // value of 'S', because that appears most frequently
125 
126  // reverse mapping for characters and their lowercase
127  for (rank_type rnk = 0u; rnk < alphabet_size; ++rnk)
128  {
129  ret[static_cast<rank_type>(rank_to_char_table[rnk])] = rnk;
130  ret[static_cast<rank_type>(to_lower(rank_to_char_table[rnk]))] = rnk;
131  }
132 
133  ret['B'] = ret['D']; ret['b'] = ret['D']; // Convert b (either D/N) to D, since D occurs more frequently.
134  ret['J'] = ret['L']; ret['j'] = ret['L']; // Convert j (either I/L) to L, since L occurs more frequently.
135  ret['O'] = ret['L']; ret['o'] = ret['L']; // Convert Pyrrolysine to lysine.
136  ret['U'] = ret['C']; ret['u'] = ret['C']; // Convert Selenocysteine to cysteine.
137  ret['X'] = ret['S']; ret['x'] = ret['S']; // Convert unknown amino acids to serine.
138  ret['Z'] = ret['E']; ret['z'] = ret['E']; // Convert z (either E/Q) to E, since E occurs more frequently.
139  ret['*'] = ret['W']; // The most common stop codon is UGA. This is most similar to a Tryptophan.
140  return ret;
141  }()
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 // ------------------------------------------------------------------
172 inline namespace literals
173 {
174 
188 constexpr aa20 operator""_aa20(char const c) noexcept
189 {
190  return aa20{}.assign_char(c);
191 }
192 
204 inline aa20_vector operator""_aa20(char const * const s, size_t const n)
205 {
206  aa20_vector r;
207  r.resize(n);
208 
209  for (size_t i = 0; i < n; ++i)
210  r[i].assign_char(s[i]);
211 
212  return r;
213 }
215 
216 } // inline namespace literals
217 
218 } // namespace seqan3
Provides seqan3::aminoacid_alphabet.
Provides seqan3::aminoacid_base.
The canonical amino acid alphabet.
Definition: aa20.hpp:64
constexpr aa20() noexcept=default
Defaulted.
A CRTP-base that makes defining a custom alphabet easier.
Definition: alphabet_base.hpp:81
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:104
constexpr derived_type & assign_char(char_type const chr) noexcept
Assign from a character, implicitly converts invalid characters.
Definition: alphabet_base.hpp:211
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:276
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:96
A CRTP-base that refines seqan3::alphabet_base and is used by the amino acids.
Definition: aminoacid_base.hpp:32
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:81
T resize(T... args)
Provides utilities for modifying characters.