Struct bio::data_structures::fmindex::FMDIndex

pub struct FMDIndex<DBWT: Borrow<BWT>, DLess: Borrow<Less>, DOcc: Borrow<Occ>> { /* private fields */ }

The FMD-Index for linear time search of supermaximal exact matches on forward and reverse strand of DNA texts (Li, 2012).

Implementations

impl<DBWT: Borrow<BWT>, DLess: Borrow<Less>, DOcc: Borrow<Occ>> FMDIndex<DBWT, DLess, DOcc>

pub fn smems( &self, pattern: &[u8], i: usize, l: usize ) -> Vec<(BiInterval, usize, usize)>

Find supermaximal exact matches (of length >= l) of given pattern that overlap position i in the pattern. Complexity O(m) with pattern of length m.

Example

use bio::alphabets::dna;
use bio::data_structures::bwt::{bwt, less, Occ};
use bio::data_structures::fmindex::{FMDIndex, FMIndex};
use bio::data_structures::suffix_array::suffix_array;

let text = b"ATTC$GAAT$";
let alphabet = dna::n_alphabet();
let sa = suffix_array(text);
let bwt = bwt(text, &sa);
let less = less(&bwt, &alphabet);
let occ = Occ::new(&bwt, 3, &alphabet);
let fm = FMIndex::new(&bwt, &less, &occ);
let fmdindex = FMDIndex::from(fm);

let pattern = b"ATT";
let intervals = fmdindex.smems(pattern, 2, 0);

let forward_positions = intervals[0].0.forward().occ(&sa);
let revcomp_positions = intervals[0].0.revcomp().occ(&sa);
let pattern_position = intervals[0].1;
let smem_len = intervals[0].2;

assert_eq!(forward_positions, [0]);
assert_eq!(revcomp_positions, [6]);
assert_eq!(pattern_position, 0);
assert_eq!(smem_len, 3);

pub fn all_smems( &self, pattern: &[u8], l: usize ) -> Vec<(BiInterval, usize, usize)>

Find all supermaximal exact matches (of length >= l) of given pattern. Complexity O(m^2) with pattern of length m.

Example

use bio::alphabets::dna;
use bio::data_structures::bwt::{bwt, less, Occ};
use bio::data_structures::fmindex::{FMDIndex, FMIndex};
use bio::data_structures::suffix_array::suffix_array;

let text = b"ATTCGGGG$CCCCGAAT$";
let alphabet = dna::n_alphabet();
let sa = suffix_array(text);
let bwt = bwt(text, &sa);
let less = less(&bwt, &alphabet);
let occ = Occ::new(&bwt, 3, &alphabet);
let fm = FMIndex::new(&bwt, &less, &occ);
let fmdindex = FMDIndex::from(fm);

let pattern = b"ATTGGGG";
let intervals = fmdindex.all_smems(pattern, 0);
assert_eq!(intervals.len(), 2);

let solutions = vec![[0, 14, 0, 3], [4, 9, 3, 4]];
for (i, interval) in intervals.iter().enumerate() {
    let forward_positions = interval.0.forward().occ(&sa);
    let revcomp_positions = interval.0.revcomp().occ(&sa);
    let pattern_position = interval.1;
    let smem_len = interval.2;
    assert_eq!(
        [
            forward_positions[0],
            revcomp_positions[0],
            pattern_position,
            smem_len
        ],
        solutions[i]
    );
}

pub fn init_interval_with(&self, a: u8) -> BiInterval

Initialize interval with given start character.

pub fn init_interval(&self) -> BiInterval

Initialize interval for empty pattern. The interval points at the whole suffix array.

pub fn backward_ext(&self, interval: &BiInterval, a: u8) -> BiInterval

Backward extension of given interval with given character.

pub fn forward_ext(&self, interval: &BiInterval, a: u8) -> BiInterval

pub unsafe fn from_fmindex_unchecked( fmindex: FMIndex<DBWT, DLess, DOcc> ) -> FMDIndex<DBWT, DLess, DOcc>

Construct a new instance of the FMD index (see Heng Li (2012) Bioinformatics) without checking whether the text is over the DNA alphabet with N. This expects a BWT that was created from a text over the DNA alphabet with N (alphabets::dna::n_alphabet()) consisting of the concatenation with its reverse complement, separated by the sentinel symbol $. I.e., let T be the original text and R be its reverse complement. Then, the expected text is T$R$. Further, multiple concatenated texts are allowed, e.g. T1$R1$T2$R2$T3$R3$. It is unsafe to construct an FMD index from an FM index that is not built on the DNA alphabet.

Trait Implementations

impl<DBWT: Clone + Borrow<BWT>, DLess: Clone + Borrow<Less>, DOcc: Clone + Borrow<Occ>> Clone for FMDIndex<DBWT, DLess, DOcc>

fn clone(&self) -> FMDIndex<DBWT, DLess, DOcc>

Returns a copy of the value.

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

Performs copy-assignment from source.

impl<DBWT: Debug + Borrow<BWT>, DLess: Debug + Borrow<Less>, DOcc: Debug + Borrow<Occ>> Debug for FMDIndex<DBWT, DLess, DOcc>

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

Formats the value using the given formatter.

impl<DBWT: Default + Borrow<BWT>, DLess: Default + Borrow<Less>, DOcc: Default + Borrow<Occ>> Default for FMDIndex<DBWT, DLess, DOcc>

fn default() -> FMDIndex<DBWT, DLess, DOcc>

Returns the “default value” for a type.

impl<'de, DBWT, DLess, DOcc> Deserialize<'de> for FMDIndex<DBWT, DLess, DOcc>where DBWT: Deserialize<'de> + Borrow<BWT>, DLess: Deserialize<'de> + Borrow<Less>, DOcc: Deserialize<'de> + Borrow<Occ>,

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

Deserialize this value from the given Serde deserializer.

impl<DBWT: Borrow<BWT>, DLess: Borrow<Less>, DOcc: Borrow<Occ>> FMIndexable for FMDIndex<DBWT, DLess, DOcc>

fn bwt(&self) -> &BWT

Provide a reference to the underlying BWT.

fn occ(&self, r: usize, a: u8) -> usize

Get occurrence count of symbol a in BWT[..r+1].

fn less(&self, a: u8) -> usize

Also known as

fn backward_search<'b, P: Iterator<Item = &'b u8> + DoubleEndedIterator>( &self, pattern: P ) -> BackwardSearchResult

Perform backward search, yielding BackwardSearchResult enum that contains the suffix array interval denoting exact occurrences of the given pattern of length m in the text if it exists, or the suffix array interval denoting the exact occurrences of a maximal matching suffix of the given pattern if it does not exist. If none of the pattern can be matched, the BackwardSearchResult is Absent. Complexity: O(m).

impl<DBWT: Borrow<BWT>, DLess: Borrow<Less>, DOcc: Borrow<Occ>> From<FMIndex<DBWT, DLess, DOcc>> for FMDIndex<DBWT, DLess, DOcc>

fn from(fmindex: FMIndex<DBWT, DLess, DOcc>) -> FMDIndex<DBWT, DLess, DOcc>

Construct a new instance of the FMD index (see Heng Li (2012) Bioinformatics). This expects a BWT that was created from a text over the DNA alphabet with N (alphabets::dna::n_alphabet()) consisting of the concatenation with its reverse complement, separated by the sentinel symbol $. I.e., let T be the original text and R be its reverse complement. Then, the expected text is T$R$. Further, multiple concatenated texts are allowed, e.g. T1$R1$T2$R2$T3$R3$.

impl<DBWT: Hash + Borrow<BWT>, DLess: Hash + Borrow<Less>, DOcc: Hash + Borrow<Occ>> Hash for FMDIndex<DBWT, DLess, DOcc>

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, Self: Sized,

Feeds a slice of this type into the given Hasher.

impl<DBWT: Ord + Borrow<BWT>, DLess: Ord + Borrow<Less>, DOcc: Ord + Borrow<Occ>> Ord for FMDIndex<DBWT, DLess, DOcc>

fn cmp(&self, other: &FMDIndex<DBWT, DLess, DOcc>) -> Ordering

This method returns an Ordering between self and other.

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

Compares and returns the maximum of two values.

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

Compares and returns the minimum of two values.

fn clamp(self, min: Self, max: Self) -> Selfwhere Self: Sized + PartialOrd<Self>,

Restrict a value to a certain interval.

impl<DBWT: PartialEq + Borrow<BWT>, DLess: PartialEq + Borrow<Less>, DOcc: PartialEq + Borrow<Occ>> PartialEq<FMDIndex<DBWT, DLess, DOcc>> for FMDIndex<DBWT, DLess, DOcc>

fn eq(&self, other: &FMDIndex<DBWT, DLess, DOcc>) -> bool

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

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

This method tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl<DBWT: PartialOrd + Borrow<BWT>, DLess: PartialOrd + Borrow<Less>, DOcc: PartialOrd + Borrow<Occ>> PartialOrd<FMDIndex<DBWT, DLess, DOcc>> for FMDIndex<DBWT, DLess, DOcc>

fn partial_cmp(&self, other: &FMDIndex<DBWT, DLess, DOcc>) -> 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<DBWT, DLess, DOcc> Serialize for FMDIndex<DBWT, DLess, DOcc>where DBWT: Serialize + Borrow<BWT>, DLess: Serialize + Borrow<Less>, DOcc: Serialize + Borrow<Occ>,

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

Serialize this value into the given Serde serializer.

impl<DBWT: Copy + Borrow<BWT>, DLess: Copy + Borrow<Less>, DOcc: Copy + Borrow<Occ>> Copy for FMDIndex<DBWT, DLess, DOcc>

impl<DBWT: Eq + Borrow<BWT>, DLess: Eq + Borrow<Less>, DOcc: Eq + Borrow<Occ>> Eq for FMDIndex<DBWT, DLess, DOcc>

impl<DBWT: Borrow<BWT>, DLess: Borrow<Less>, DOcc: Borrow<Occ>> StructuralEq for FMDIndex<DBWT, DLess, DOcc>

impl<DBWT: Borrow<BWT>, DLess: Borrow<Less>, DOcc: Borrow<Occ>> StructuralPartialEq for FMDIndex<DBWT, DLess, DOcc>