Function chordclust::cluster_slice

pub fn cluster_slice(
    sequences: &[String], 
    k: usize, 
    similarity_threshold: u32
) -> BucketCluster<'_>

Cluster a slice of Strings by similarity. The elements of each cluster have s similarity > similarity_threshold with the centroid. k is the size of the k-mers used to perform the search.

Examples

use std::fs::File;
use std::io::BufReader;
use chordclust::{read_fasta_sorted, cluster_slice};

let f = File::open("examples/UP000000425_122586_DNA_sample.fasta").unwrap();
let reader = BufReader::new(f);
let sequences = read_fasta_sorted(reader);
let cluster_db = cluster_slice(&sequences, 8, 85);
let n_clusters = cluster_db.clusters.len();
assert!(1 < n_clusters);
assert!(n_clusters < sequences.len());