geopagg 0.3.1

An implementation of the geopagg algorithm for p-value aggregation of sgRNAs across gene groupings
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
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175

use std::collections::HashMap;

use itertools::Itertools;

/// Exact string matching for a needle in a haystack
pub fn index_mask(needle: &str, haystack: &[String]) -> Vec<usize> {
    haystack
        .iter()
        .enumerate()
        .filter(|(_, target)| *target == needle)
        .map(|(i, _)| i)
        .collect()
}

/// Prefix matching for a needle in a haystack
pub fn index_prefix_mask(prefix: &str, haystack: &[String]) -> Vec<usize> {
    haystack
        .iter()
        .enumerate()
        .filter(|(_, target)| target.contains(prefix))
        .map(|(i, _)| i)
        .collect()
}

/// Transforms a vector of values into z-scores
pub fn zscore_transform(values: &[f64]) -> Vec<f64> {
    let mean = values.iter().sum::<f64>() / values.len() as f64;
    let variance = values.iter().map(|x| (x - mean).powi(2)).sum::<f64>() / values.len() as f64;
    let std_dev = variance.sqrt();
    values.iter().map(|x| (x - mean) / std_dev).collect()
}

pub fn select_indices<T: Copy>(indices: &[usize], data: &[T]) -> Vec<T> {
    indices.iter().map(|i| data[*i]).collect()
}

/// Calculates the membership sizes of each gene and the occurence of each membership size
pub fn calculate_group_sizes(genes: &[String], unique_genes: &[&String]) -> Vec<(usize, usize)> {
    let mut group_sizes = HashMap::new();
    for gene in unique_genes {
        let gene_indices = index_mask(gene, genes);
        let membership_size = gene_indices.len();
        if let Some(group_size) = group_sizes.get_mut(&membership_size) {
            *group_size += 1;
        } else {
            group_sizes.insert(membership_size, 1);
        }
    }
    group_sizes.into_iter().sorted().collect()
}

#[cfg(test)]
mod testing {
    use itertools::Itertools;

    #[test]
    fn test_index_mask() {
        let haystack = vec!["a".to_string(), "b".to_string(), "c".to_string()];
        let needle = "a";
        let result = super::index_mask(needle, &haystack);
        assert_eq!(result, vec![0]);
    }

    #[test]
    fn test_index_mask_shared_prefix() {
        let haystack = vec![
            "gene_a".to_string(),
            "gene_a_b".to_string(),
            "gene_a_c".to_string(),
        ];
        let needle = "gene_a";
        let result = super::index_prefix_mask(needle, &haystack);
        assert_eq!(result, vec![0, 1, 2]);
    }

    #[test]
    fn test_index_prefix_mask() {
        let haystack = vec![
            "non-targeting_0001".to_string(),
            "non-targeting_0002".to_string(),
            "some_gene".to_string(),
            "non-targeting_0003".to_string(),
        ];
        let needle = "non-targeting";
        let result = super::index_prefix_mask(needle, &haystack);
        assert_eq!(result, vec![0, 1, 3]);
    }

    #[test]
    fn test_index_prefix_mask_shared_prefix() {
        let haystack = vec![
            "gene_a".to_string(),
            "gene_a_b".to_string(),
            "gene_a_c".to_string(),
        ];
        let needle = "gene_a";
        let result = super::index_mask(needle, &haystack);
        assert_eq!(result, vec![0]);
    }

    #[test]
    fn test_select_indices() {
        let data = vec!["a", "b", "c"];
        let indices = vec![0, 2];
        let result = super::select_indices(&indices, &data);
        assert_eq!(result, vec!["a", "c"]);
    }

    #[test]
    fn test_calculate_group_sizes() {
        let genes = vec![
            "a".to_string(),
            "a".to_string(),
            "b".to_string(),
            "c".to_string(),
        ];
        let unique_genes = [String::from("a"), String::from("b"), String::from("c")];
        let unique_gene_references = unique_genes.iter().collect::<Vec<_>>();
        let result = super::calculate_group_sizes(&genes, &unique_gene_references);

        assert!(result.iter().contains(&(1, 2)));
        assert!(result.iter().contains(&(2, 1)));
        assert_eq!(result.len(), 2);
    }

    #[test]
    fn test_calculate_group_sizes_with_duplicates() {
        let genes = vec![
            "a".to_string(),
            "a".to_string(),
            "b".to_string(),
            "b".to_string(),
            "c".to_string(),
        ];
        let unique_genes = [String::from("a"), String::from("b"), String::from("c")];
        let unique_gene_references = unique_genes.iter().collect::<Vec<_>>();
        let result = super::calculate_group_sizes(&genes, &unique_gene_references);

        assert!(result.iter().contains(&(2, 2)));
        assert!(result.iter().contains(&(1, 1)));
        assert_eq!(result.len(), 2);
    }

    #[test]
    fn test_zscore_transform() {
        let x = vec![1.0, 2.0, 3.0, 4.0, 5.0];
        let z = super::zscore_transform(&x);
        let expected = [
            -f64::sqrt(2.0),
            -0.7071067811865475,
            0.0,
            0.7071067811865475,
            f64::sqrt(2.0),
        ];
        for (a, b) in z.iter().zip(expected.iter()) {
            assert!((a - b).abs() < 1e-10);
        }
    }

    #[test]
    fn test_zscore_transform_ooo() {
        let x = vec![5.0, 4.0, 3.0, 2.0, 1.0];
        let z = super::zscore_transform(&x);
        let expected = [
            f64::sqrt(2.0),
            0.7071067811865475,
            0.0,
            -0.7071067811865475,
            -f64::sqrt(2.0),
        ];
        for (a, b) in z.iter().zip(expected.iter()) {
            assert!((a - b).abs() < 1e-10);
        }
    }
}