bio 3.0.0

A bioinformatics library for Rust. This library provides implementations of many algorithms and data structures that are useful for bioinformatics, but also in other fields.
Documentation 
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

// Copyright 2017 Ryan Hagenson.
// 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 the RNA alphabet.
//!
//! # Example
//!
//! ```
//! use bio::alphabets;
//! let alphabet = alphabets::rna::alphabet();
//! assert!(alphabet.is_word(b"GAUUACA"));
//! assert!(alphabet.is_word(b"gauuaca"));
//! assert!(!alphabet.is_word(b"ACGT"));
//! ```

use crate::alphabets::Alphabet;
use std::borrow::Borrow;
use std::sync::LazyLock;

/// The RNA alphabet (uppercase and lowercase).
pub fn alphabet() -> Alphabet {
    Alphabet::new(b"ACGUacgu")
}

/// The RNA alphabet including N (uppercase and lowercase).
pub fn n_alphabet() -> Alphabet {
    Alphabet::new(b"ACGUNacgun")
}

/// The IUPAC RNA alphabet (uppercase and lowercase).
pub fn iupac_alphabet() -> Alphabet {
    Alphabet::new(b"ACGURYSWKMBDHVNZacguryswkmbdhvnz")
}

static COMPLEMENT: LazyLock<[u8; 256]> = LazyLock::new(|| {
    let mut comp = [0; 256];
    comp.iter_mut().enumerate().for_each(|(v, a)| {
        *a = v as u8;
    });
    b"AGCUYRWSKMDVHBNZ"
        .iter()
        .zip(b"UCGARYWSMKHBDVNZ".iter())
        .for_each(|(&a, &b)| {
            comp[a as usize] = b;
            comp[a as usize + 32] = b + 32;
        });
    comp
});

/// Return complement of given RNA alphabet character (IUPAC alphabet supported).
///
/// Casing of input character is preserved, e.g. `u` → `a`, but `U` → `A`.
/// All `N`s and `Z`s remain as they are.
///
/// ```
/// use bio::alphabets::rna;
///
/// assert_eq!(rna::complement(65), 85); // A → U
/// assert_eq!(rna::complement(103), 99); // g → c
/// assert_eq!(rna::complement(89), 82); // Y → R
/// assert_eq!(rna::complement(115), 115); // s → s
/// assert_eq!(rna::complement(78), 78); // N → N
/// ```
#[inline]
pub fn complement(a: u8) -> u8 {
    COMPLEMENT[a as usize]
}

/// Calculate reverse complement of given text (IUPAC alphabet supported).
///
/// Casing of characters is preserved, e.g. `b"uAGg"` → `b"cCUa"`.
/// All `N`s and `Z`s remain as they are.
///
/// ```
/// use bio::alphabets::rna;
///
/// assert_eq!(rna::revcomp(b"ACGUN"), b"NACGU");
/// assert_eq!(rna::revcomp(b"GaUuaCA"), b"UGuaAuC");
/// assert_eq!(rna::revcomp(b"AGCUYRWSKMDVHBNZ"), b"ZNVDBHKMSWYRAGCU");
pub fn revcomp<C, T>(text: T) -> Vec<u8>
where
    C: Borrow<u8>,
    T: IntoIterator<Item = C>,
    T::IntoIter: DoubleEndedIterator,
{
    text.into_iter()
        .rev()
        .map(|a| complement(*a.borrow()))
        .collect()
}

#[cfg(test)]
mod tests {
    use super::*;

    #[test]
    fn is_word() {
        assert!(alphabet().is_word(b"GAUUACA"));
    }

    #[test]
    fn is_no_word() {
        assert!(!alphabet().is_word(b"gaTTaca"));
    }

    #[test]
    fn symbol_is_no_word() {
        assert!(!alphabet().is_word(b"#"));
    }

    #[test]
    fn number_is_no_word() {
        assert!(!alphabet().is_word(b"42"));
    }

    #[test]
    fn test_reverse_complement() {
        assert_eq!(revcomp(b"GAUUACA"), b"UGUAAUC");
    }
}