1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461
// Copyright 2014-2015 Johannes Köster, Peer Aramillo Irizar.
// Licensed under the MIT license (http://opensource.org/licenses/MIT)
// This file may not be copied, modified, or distributed
// except according to those terms.
//! Implementation of alphabets and useful utilities.
//!
//! # Example
//!
//! ```rust
//! use bio::alphabets;
//! let alphabet = alphabets::dna::alphabet();
//! assert!(alphabet.is_word(b"AACCTgga"));
//! assert!(!alphabet.is_word(b"AXYZ"));
//! ```
use std::borrow::Borrow;
use std::mem;
use bit_set::BitSet;
use vec_map::VecMap;
pub mod dna;
pub mod protein;
pub mod rna;
pub type SymbolRanks = VecMap<u8>;
/// Representation of an alphabet.
#[derive(Default, Clone, Eq, PartialEq, Ord, PartialOrd, Hash, Debug)]
pub struct Alphabet {
pub symbols: BitSet,
}
impl Alphabet {
/// Create new alphabet from given symbols.
///
/// Complexity: O(n), where n is the number of symbols in the alphabet.
///
/// # Example
///
/// ```
/// use bio::alphabets;
///
/// // Create an alphabet (note that a DNA alphabet is already available in bio::alphabets::dna).
/// let dna_alphabet = alphabets::Alphabet::new(b"ACGTacgt");
/// // Check whether a given text is a word over the alphabet.
/// assert!(dna_alphabet.is_word(b"GAttACA"));
/// ```
pub fn new<C, T>(symbols: T) -> Self
where
C: Borrow<u8>,
T: IntoIterator<Item = C>,
{
let mut s = BitSet::new();
s.extend(symbols.into_iter().map(|c| *c.borrow() as usize));
Alphabet { symbols: s }
}
/// Insert symbol into alphabet.
///
/// Complexity: O(1)
///
/// # Example
///
/// ```
/// use bio::alphabets;
///
/// let mut dna_alphabet = alphabets::Alphabet::new(b"ACGTacgt");
/// assert!(!dna_alphabet.is_word(b"N"));
/// dna_alphabet.insert(78);
/// assert!(dna_alphabet.is_word(b"N"));
/// ```
pub fn insert(&mut self, a: u8) {
self.symbols.insert(a as usize);
}
/// Check if given text is a word over the alphabet.
///
/// Complexity: O(n), where n is the length of the text.
///
/// # Example
///
/// ```
/// use bio::alphabets;
///
/// let dna_alphabet = alphabets::Alphabet::new(b"ACGTacgt");
/// assert!(dna_alphabet.is_word(b"GAttACA"));
/// assert!(!dna_alphabet.is_word(b"42"));
/// ```
pub fn is_word<C, T>(&self, text: T) -> bool
where
C: Borrow<u8>,
T: IntoIterator<Item = C>,
{
text.into_iter()
.all(|c| self.symbols.contains(*c.borrow() as usize))
}
/// Return lexicographically maximal symbol.
///
/// Complexity: O(n), where n is the number of symbols in the alphabet.
///
/// # Example
///
/// ```
/// use bio::alphabets;
///
/// let dna_alphabet = alphabets::Alphabet::new(b"acgtACGT");
/// assert_eq!(dna_alphabet.max_symbol(), Some(116)); // max symbol is "t"
/// let empty_alphabet = alphabets::Alphabet::new(b"");
/// assert_eq!(empty_alphabet.max_symbol(), None);
/// ```
pub fn max_symbol(&self) -> Option<u8> {
self.symbols.iter().max().map(|a| a as u8)
}
/// Return size of the alphabet.
///
/// Upper and lower case representations of the same character
/// are counted as distinct characters.
///
/// Complexity: O(n), where n is the number of symbols in the alphabet.
///
/// # Example
///
/// ```
/// use bio::alphabets;
///
/// let dna_alphabet = alphabets::Alphabet::new(b"acgtACGT");
/// assert_eq!(dna_alphabet.len(), 8);
/// ```
pub fn len(&self) -> usize {
self.symbols.len()
}
/// Is this alphabet empty?
///
/// Complexity: O(n), where n is the number of symbols in the alphabet.
///
/// # Example
///
/// ```
/// use bio::alphabets;
///
/// let dna_alphabet = alphabets::Alphabet::new(b"acgtACGT");
/// assert!(!dna_alphabet.is_empty());
/// let empty_alphabet = alphabets::Alphabet::new(b"");
/// assert!(empty_alphabet.is_empty());
/// ```
pub fn is_empty(&self) -> bool {
self.symbols.is_empty()
}
/// Return a new alphabet taking the intersect between this and other.
///
/// # Example
/// ```
/// use bio::alphabets;
///
/// let alpha_a = alphabets::Alphabet::new(b"acgtACGT");
/// let alpha_b = alphabets::Alphabet::new(b"atcgMVP");
/// let intersect_alpha = alpha_a.intersection(&alpha_b);
///
/// assert_eq!(intersect_alpha, alphabets::Alphabet::new(b"atcg"));
/// ```
pub fn intersection(&self, other: &Alphabet) -> Self {
return Alphabet {
symbols: self.symbols.intersection(&other.symbols).collect(),
};
}
/// Return a new alphabet taking the difference between this and other.
///
/// # Example
/// ```
/// use bio::alphabets;
///
/// let dna_alphabet = alphabets::Alphabet::new(b"acgtACGT");
/// let dna_alphabet_upper = alphabets::Alphabet::new(b"ACGT");
/// let dna_lower = dna_alphabet.difference(&dna_alphabet_upper);
///
/// assert_eq!(dna_lower, alphabets::Alphabet::new(b"atcg"));
/// ```
pub fn difference(&self, other: &Alphabet) -> Self {
return Alphabet {
symbols: self.symbols.difference(&other.symbols).collect(),
};
}
/// Return a new alphabet taking the union between this and other.
///
/// # Example
/// ```
/// use bio::alphabets;
///
/// let dna_alphabet = alphabets::Alphabet::new(b"ATCG");
/// let tokenize_alpha = alphabets::Alphabet::new(b"?|");
/// let alpha = dna_alphabet.union(&tokenize_alpha);
///
/// assert_eq!(alpha, alphabets::Alphabet::new(b"ATCG?|"));
/// ```
pub fn union(&self, other: &Alphabet) -> Self {
return Alphabet {
symbols: self.symbols.union(&other.symbols).collect(),
};
}
}
/// Tools based on transforming the alphabet symbols to their lexicographical ranks.
///
/// Lexicographical rank is computed using `u8` representations,
/// i.e. ASCII codes, of the input characters.
/// For example, assuming that the alphabet consists of the symbols `A`, `C`, `G`, and `T`, this
/// will yield ranks `0`, `1`, `2`, `3` for them, respectively.
///
/// `RankTransform` can be used in to perform bit encoding for texts over a
/// given alphabet via `bio::data_structures::bitenc`.
#[derive(Default, Clone, Eq, PartialEq, Ord, PartialOrd, Hash, Debug, Serialize, Deserialize)]
pub struct RankTransform {
pub ranks: SymbolRanks,
}
impl RankTransform {
/// Construct a new `RankTransform`.
///
/// Complexity: O(n), where n is the number of symbols in the alphabet.
///
/// # Example
///
/// ```
/// use bio::alphabets;
///
/// let dna_alphabet = alphabets::Alphabet::new(b"acgtACGT");
/// let dna_ranks = alphabets::RankTransform::new(&dna_alphabet);
/// ```
pub fn new(alphabet: &Alphabet) -> Self {
let mut ranks = VecMap::new();
for (r, c) in alphabet.symbols.iter().enumerate() {
ranks.insert(c, r as u8);
}
RankTransform { ranks }
}
/// Get the rank of symbol `a`.
///
/// This method panics for characters not contained in the alphabet.
///
/// Complexity: O(1)
///
/// # Example
///
/// ```
/// use bio::alphabets;
///
/// let dna_alphabet = alphabets::Alphabet::new(b"acgtACGT");
/// let dna_ranks = alphabets::RankTransform::new(&dna_alphabet);
/// assert_eq!(dna_ranks.get(65), 0); // "A"
/// assert_eq!(dna_ranks.get(116), 7); // "t"
/// ```
pub fn get(&self, a: u8) -> u8 {
*self.ranks.get(a as usize).expect("Unexpected character.")
}
/// Transform a given `text` into a vector of rank values.
///
/// Complexity: O(n), where n is the length of the text.
///
/// # Example
///
/// ```
/// use bio::alphabets;
///
/// let dna_alphabet = alphabets::Alphabet::new(b"ACGTacgt");
/// let dna_ranks = alphabets::RankTransform::new(&dna_alphabet);
/// let text = b"aAcCgGtT";
/// assert_eq!(dna_ranks.transform(text), vec![4, 0, 5, 1, 6, 2, 7, 3]);
/// ```
pub fn transform<C, T>(&self, text: T) -> Vec<u8>
where
C: Borrow<u8>,
T: IntoIterator<Item = C>,
{
text.into_iter()
.map(|c| {
*self
.ranks
.get(*c.borrow() as usize)
.expect("Unexpected character in text.")
})
.collect()
}
/// Iterate over q-grams (substrings of length q) of given `text`. The q-grams are encoded
/// as `usize` by storing the symbol ranks in log2(|A|) bits (with |A| being the alphabet size).
///
/// If q is larger than usize::BITS / log2(|A|), this method fails with an assertion.
///
/// Complexity: O(n), where n is the length of the text.
///
/// # Example
///
/// ```
/// use bio::alphabets;
///
/// let dna_alphabet = alphabets::Alphabet::new(b"ACGTacgt");
/// let dna_ranks = alphabets::RankTransform::new(&dna_alphabet);
///
/// let q_grams: Vec<usize> = dna_ranks.qgrams(2, b"ACGT").collect();
/// assert_eq!(q_grams, vec![1, 10, 19]);
/// ```
pub fn qgrams<C, T>(&self, q: u32, text: T) -> QGrams<'_, C, T::IntoIter>
where
C: Borrow<u8>,
T: IntoIterator<Item = C>,
{
let bits = (self.ranks.len() as f32).log2().ceil() as u32;
assert!(
(bits * q) as usize <= mem::size_of::<usize>() * 8,
"Expecting q to be smaller than usize / log2(|A|)"
);
let mut qgrams = QGrams {
text: text.into_iter(),
ranks: self,
bits,
mask: 1usize.checked_shl(q * bits).unwrap_or(0).wrapping_sub(1),
qgram: 0,
};
for _ in 0..q - 1 {
qgrams.next();
}
qgrams
}
/// Restore alphabet from transform.
///
/// Complexity: O(n), where n is the number of symbols in the alphabet.
///
/// # Example
///
/// ```
/// use bio::alphabets;
///
/// let dna_alphabet = alphabets::Alphabet::new(b"acgtACGT");
/// let dna_ranks = alphabets::RankTransform::new(&dna_alphabet);
/// assert_eq!(dna_ranks.alphabet().symbols, dna_alphabet.symbols);
/// ```
pub fn alphabet(&self) -> Alphabet {
let mut symbols = BitSet::with_capacity(self.ranks.len());
symbols.extend(self.ranks.keys());
Alphabet { symbols }
}
/// Compute the number of bits required to encode the largest rank value.
///
/// For example, the alphabet `b"ACGT"` with 4 symbols has the maximal rank
/// 3, which can be encoded in 2 bits.
///
/// This value can be used to create a `data_structures::bitenc::BitEnc`
/// bit encoding tailored to the given alphabet.
///
/// Complexity: O(n), where n is the number of symbols in the alphabet.
///
/// # Example
///
/// ```
/// use bio::alphabets;
///
/// let dna_alphabet = alphabets::Alphabet::new(b"ACGT");
/// let dna_ranks = alphabets::RankTransform::new(&dna_alphabet);
/// assert_eq!(dna_ranks.get_width(), 2);
/// let dna_n_alphabet = alphabets::Alphabet::new(b"ACGTN");
/// let dna_n_ranks = alphabets::RankTransform::new(&dna_n_alphabet);
/// assert_eq!(dna_n_ranks.get_width(), 3);
/// ```
pub fn get_width(&self) -> usize {
(self.ranks.len() as f32).log2().ceil() as usize
}
}
/// Iterator over q-grams.
#[derive(Copy, Clone, Eq, PartialEq, Ord, PartialOrd, Hash, Debug, Serialize)]
pub struct QGrams<'a, C, T>
where
C: Borrow<u8>,
T: Iterator<Item = C>,
{
text: T,
ranks: &'a RankTransform,
bits: u32,
mask: usize,
qgram: usize,
}
impl<'a, C, T> QGrams<'a, C, T>
where
C: Borrow<u8>,
T: Iterator<Item = C>,
{
/// Push a new character into the current qgram.
fn qgram_push(&mut self, a: u8) {
self.qgram <<= self.bits;
self.qgram |= a as usize;
self.qgram &= self.mask;
}
}
impl<'a, C, T> Iterator for QGrams<'a, C, T>
where
C: Borrow<u8>,
T: Iterator<Item = C>,
{
type Item = usize;
fn next(&mut self) -> Option<usize> {
match self.text.next() {
Some(a) => {
let b = self.ranks.get(*a.borrow());
self.qgram_push(b);
Some(self.qgram)
}
None => None,
}
}
}
/// Returns the english ascii lower case alphabet.
pub fn english_ascii_lower_alphabet() -> Alphabet {
Alphabet::new(&b"abcdefghijklmnopqrstuvwxyz"[..])
}
/// Returns the english ascii upper case alphabet.
pub fn english_ascii_upper_alphabet() -> Alphabet {
Alphabet::new(&b"ABCDEFGHIJKLMNOPQRSTUVWXYZ"[..])
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn test_alphabet_eq() {
assert_eq!(Alphabet::new(b"ATCG"), Alphabet::new(b"ATCG"));
assert_eq!(Alphabet::new(b"ATCG"), Alphabet::new(b"TAGC"));
assert_ne!(Alphabet::new(b"ATCG"), Alphabet::new(b"ATC"));
}
/// When `q * bits == usize::BITS`, make sure that `1<<(1*bits)` does not overflow.
#[test]
fn test_qgram_shiftleft_overflow() {
let alphabet = Alphabet::new(b"ACTG");
let transform = RankTransform::new(&alphabet);
let text = b"ACTG".repeat(100);
transform.qgrams(usize::BITS / 2, text);
}
}