Struct debruijn::dna_string::DnaString

pub struct DnaString { /* fields omitted */ }

A container for sequence of DNA bases.

use debruijn::dna_string::DnaString;
use debruijn::kmer::Kmer8;
use debruijn::{Mer, Vmer};

let dna_string = DnaString::from_dna_string("ATCGTACGTACGTAGTC");

// Iterate over 8-mers
for k in dna_string.iter_kmers::<Kmer8>() {
    println!("{:?}", k);
}

// Get a base, encoded as a byte in 0-3 range
assert_eq!(dna_string.get(0), 0);
assert_eq!(dna_string.get(1), 3);

// Make a read-only 'slice' of a DnaString
let slc = dna_string.slice(1, 10);

 assert_eq!(slc.iter_kmers::<Kmer8>().next(), dna_string.iter_kmers::<Kmer8>().skip(1).next());

Implementations

impl DnaString

pub fn new() -> DnaString

Create an empty DNA string

pub fn len(&self) -> usize

Length of the sequence

pub fn with_capacity(n: usize) -> Self

Create a new instance with a given capacity.

pub fn blank(n: usize) -> Self

Create a DnaString of length n initialized to all A’s

pub fn from_dna_string(dna: &str) -> DnaString

Create a DnaString corresponding to an ACGT-encoded str.

pub fn from_dna_only_string(dna: &str) -> Vec<DnaString>

Create a DnaString corresponding to an ACGT-encoded str.

pub fn from_acgt_bytes(bytes: &[u8]) -> DnaString

Create a DnaString from an ASCII ACGT-encoded byte slice. Non ACGT positions will be converted to ‘A’

pub fn from_acgt_bytes_hashn(bytes: &[u8], read_name: &[u8]) -> DnaString

Create a DnaString from an ACGT-encoded byte slice, Non ACGT positions will be converted to repeatable random base determined by a hash of the read name and the position within the string.

pub fn from_bytes(bytes: &[u8]) -> DnaString

Create a DnaString from a 0-4 encoded byte slice

pub fn to_string(&self) -> String

Convert sequence to a String

pub fn to_bytes(&self) -> Vec<u8>

Convert sequence to a Vector of 0-4 encoded bytes

pub fn to_ascii_vec(&self) -> Vec<u8>

Convert sequence to a Vector of ascii-encoded bytes

pub fn push(&mut self, value: u8)

Append a 0-4 encoded base.

pub fn extend(&mut self, bytes: impl Iterator<Item = u8>)

pub fn push_bytes(&mut self, bytes: &Vec<u8>, seq_length: usize)

Push 0-4 encoded bases from a byte array.

Arguments

bytes: byte array to read values from seq_length: how many values to read from the byte array. Note that this is number of values not number of elements of the byte array.

pub fn iter(&self) -> DnaStringIter<'_>

Iterate over stored values (values will be unpacked into bytes).

pub fn clear(&mut self)

Clear the sequence.

pub fn is_empty(&self) -> bool

pub fn prefix(&self, k: usize) -> DnaStringSlice<'_>

Get the length k prefix of the DnaString

pub fn suffix(&self, k: usize) -> DnaStringSlice<'_>

Get the length k suffix of the DnaString

pub fn slice(&self, start: usize, end: usize) -> DnaStringSlice<'_>

Get slice containing the interval [start, end) of self

pub fn reverse(&self) -> DnaString

Create a fresh DnaString containing the reverse of self

pub fn hamming_distance(&self, other: &DnaString) -> usize

Compute Hamming distance between this DnaString and another DnaString. The two strings must have the same length.

Trait Implementations

impl Clone for DnaString

fn clone(&self) -> DnaString

Returns a copy of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for DnaString

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for DnaString

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error> where
    __D: Deserializer<'de>, 

Deserialize this value from the given Serde deserializer.

impl Hash for DnaString

fn hash<__H: Hasher>(&self, state: &mut __H)

Feeds this value into the given Hasher.

fn hash_slice<H>(data: &[Self], state: &mut H) where
    H: Hasher, 

Feeds a slice of this type into the given Hasher.

impl<'a> IntoIterator for &'a DnaString

type Item = u8

The type of the elements being iterated over.

type IntoIter = DnaStringIter<'a>

Which kind of iterator are we turning this into?

fn into_iter(self) -> DnaStringIter<'a>

Creates an iterator from a value.

impl Mer for DnaString

fn get(&self, i: usize) -> u8

Get the value at position i.

fn set_mut(&mut self, i: usize, value: u8)

Set the value as position i.

fn len(&self) -> usize

Length of DNA sequence

fn set_slice_mut(&mut self, _: usize, _: usize, _: u64)

Set nbases positions in the sequence, starting at pos. Values must be packed into the upper-most bits of value.

fn rc(&self) -> DnaString

Return a new object containing the reverse complement of the sequence

fn iter<'a>(&'a self) -> MerIter<'a, Self>

Iterate over the bases in the sequence

fn at_count(&self) -> u32

Count the number of A/T bases in the kmer

fn gc_count(&self) -> u32

Count the number of G/C bases in the kmer

impl Ord for DnaString

fn cmp(&self, other: &DnaString) -> Ordering

This method returns an Ordering between self and other.

fn max(self, other: Self) -> Self

Compares and returns the maximum of two values.

fn min(self, other: Self) -> Self

Compares and returns the minimum of two values.

fn clamp(self, min: Self, max: Self) -> Self

Restrict a value to a certain interval.

impl PartialEq<DnaString> for DnaString

fn eq(&self, other: &DnaString) -> bool

This method tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &DnaString) -> bool

This method tests for !=.

impl PartialOrd<DnaString> for DnaString

fn partial_cmp(&self, other: &DnaString) -> Option<Ordering>

This method returns an ordering between self and other values if one exists.

fn lt(&self, other: &Rhs) -> bool

This method tests less than (for self and other) and is used by the < operator.

fn le(&self, other: &Rhs) -> bool

This method tests less than or equal to (for self and other) and is used by the <= operator.

fn gt(&self, other: &Rhs) -> bool

This method tests greater than (for self and other) and is used by the > operator.

fn ge(&self, other: &Rhs) -> bool

This method tests greater than or equal to (for self and other) and is used by the >= operator.

impl Serialize for DnaString

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error> where
    __S: Serializer, 

Serialize this value into the given Serde serializer.

impl Vmer for DnaString

fn get_kmer<K: Kmer>(&self, pos: usize) -> K

Get the kmer starting at position pos

fn new(len: usize) -> Self

Create a new sequence with length len, initialized to all A’s

fn max_len() -> usize

Maximum sequence length that can be stored in this type

fn from_slice(seq: &[u8]) -> Self

Create a Vmer from a sequence of bytes

fn first_kmer<K: Kmer>(&self) -> K

Get the first Kmer from the sequence

fn last_kmer<K: Kmer>(&self) -> K

Get the last kmer in the sequence

fn both_term_kmer<K: Kmer>(&self) -> (K, K)

Get the terminal kmer of the sequence, on the both side of the sequence

fn term_kmer<K: Kmer>(&self, dir: Dir) -> K

Get the terminal kmer of the sequence, on the side of the sequence given by dir

fn iter_kmers<K: Kmer>(&self) -> KmerIter<'_, K, Self>

Iterate over the kmers in the sequence

fn iter_kmer_exts<K: Kmer>(&self, seq_exts: Exts) -> KmerExtsIter<'_, K, Self>

Iterate over the kmers and their extensions, given the extensions of the whole sequence

impl Eq for DnaString

impl StructuralEq for DnaString

impl StructuralPartialEq for DnaString