sciforge 0.0.3

A comprehensive scientific computing library in pure Rust with zero dependencies
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
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

pub fn smith_waterman_score(
    seq1: &[u8],
    seq2: &[u8],
    match_score: i32,
    mismatch: i32,
    gap: i32,
) -> i32 {
    let m = seq1.len();
    let n = seq2.len();
    let mut matrix = vec![vec![0i32; n + 1]; m + 1];
    let mut max_score = 0;
    for i in 1..=m {
        for j in 1..=n {
            let s = if seq1[i - 1] == seq2[j - 1] {
                match_score
            } else {
                mismatch
            };
            let diag = matrix[i - 1][j - 1] + s;
            let up = matrix[i - 1][j] + gap;
            let left = matrix[i][j - 1] + gap;
            matrix[i][j] = 0_i32.max(diag).max(up).max(left);
            if matrix[i][j] > max_score {
                max_score = matrix[i][j];
            }
        }
    }
    max_score
}

pub fn needleman_wunsch_score(
    seq1: &[u8],
    seq2: &[u8],
    match_score: i32,
    mismatch: i32,
    gap: i32,
) -> i32 {
    let m = seq1.len();
    let n = seq2.len();
    let mut matrix = vec![vec![0i32; n + 1]; m + 1];
    for (i, row) in matrix.iter_mut().enumerate() {
        row[0] = i as i32 * gap;
    }
    for (j, val) in matrix[0].iter_mut().enumerate() {
        *val = j as i32 * gap;
    }
    for i in 1..=m {
        for j in 1..=n {
            let s = if seq1[i - 1] == seq2[j - 1] {
                match_score
            } else {
                mismatch
            };
            let diag = matrix[i - 1][j - 1] + s;
            let up = matrix[i - 1][j] + gap;
            let left = matrix[i][j - 1] + gap;
            matrix[i][j] = diag.max(up).max(left);
        }
    }
    matrix[m][n]
}

pub fn edit_distance(seq1: &[u8], seq2: &[u8]) -> usize {
    let m = seq1.len();
    let n = seq2.len();
    let mut dp = vec![vec![0usize; n + 1]; m + 1];
    for (i, row) in dp.iter_mut().enumerate() {
        row[0] = i;
    }
    for (j, val) in dp[0].iter_mut().enumerate() {
        *val = j;
    }
    for i in 1..=m {
        for j in 1..=n {
            if seq1[i - 1] == seq2[j - 1] {
                dp[i][j] = dp[i - 1][j - 1];
            } else {
                dp[i][j] = 1 + dp[i - 1][j - 1].min(dp[i - 1][j]).min(dp[i][j - 1]);
            }
        }
    }
    dp[m][n]
}

pub fn hamming_distance(seq1: &[u8], seq2: &[u8]) -> usize {
    let n = seq1.len().min(seq2.len());
    (0..n).filter(|&i| seq1[i] != seq2[i]).count()
}

pub fn alignment_gc_content(seq: &[u8]) -> f64 {
    if seq.is_empty() {
        return 0.0;
    }
    let gc = seq
        .iter()
        .filter(|&&b| b == b'G' || b == b'C' || b == b'g' || b == b'c')
        .count();
    gc as f64 / seq.len() as f64
}

pub fn sequence_identity(seq1: &[u8], seq2: &[u8]) -> f64 {
    let n = seq1.len().min(seq2.len());
    if n == 0 {
        return 0.0;
    }
    let matches = (0..n).filter(|&i| seq1[i] == seq2[i]).count();
    matches as f64 / n as f64
}

pub fn codon_frequency(seq: &[u8]) -> Vec<(u32, usize)> {
    let mut counts = Vec::new();
    let mut i = 0;
    while i + 2 < seq.len() {
        let codon = (seq[i] as u32) << 16 | (seq[i + 1] as u32) << 8 | seq[i + 2] as u32;
        let mut found = false;
        for entry in counts.iter_mut() {
            let (c, count): &mut (u32, usize) = entry;
            if *c == codon {
                *count += 1;
                found = true;
                break;
            }
        }
        if !found {
            counts.push((codon, 1));
        }
        i += 3;
    }
    counts
}

pub fn reverse_complement(seq: &[u8]) -> Vec<u8> {
    seq.iter()
        .rev()
        .map(|&b| match b {
            b'A' | b'a' => b'T',
            b'T' | b't' => b'A',
            b'G' | b'g' => b'C',
            b'C' | b'c' => b'G',
            other => other,
        })
        .collect()
}

pub fn melting_temperature_basic(
    a_count: usize,
    t_count: usize,
    g_count: usize,
    c_count: usize,
) -> f64 {
    let len = a_count + t_count + g_count + c_count;
    if len < 14 {
        2.0 * (a_count + t_count) as f64 + 4.0 * (g_count + c_count) as f64
    } else {
        64.9 + 41.0 * (g_count + c_count) as f64 / len as f64 - 500.0 / len as f64
    }
}