Struct Transcript

Source

pub struct Transcript {Show 14 fields
    pub id: String,
    pub gene_symbol: Option<String>,
    pub strand: Strand,
    pub sequence: String,
    pub cds_start: Option<u64>,
    pub cds_end: Option<u64>,
    pub exons: Vec<Exon>,
    pub chromosome: Option<String>,
    pub genomic_start: Option<u64>,
    pub genomic_end: Option<u64>,
    pub genome_build: GenomeBuild,
    pub mane_status: ManeStatus,
    pub refseq_match: Option<String>,
    pub ensembl_match: Option<String>,
    /* private fields */
}

Expand description

A transcript with its exon structure and sequence

Fields§

§id: String

Transcript accession (e.g., “NM_000088.3”)

§gene_symbol: Option<String>

Gene symbol (e.g., “COL1A1”)

§strand: Strand

Strand orientation

§sequence: String

Full transcript sequence

§cds_start: Option<u64>

CDS start position (1-based, in transcript coordinates)

§cds_end: Option<u64>

CDS end position (1-based, in transcript coordinates)

§exons: Vec<Exon>

List of exons

§chromosome: Option<String>

Chromosome name (e.g., “chr1”, “1”, “X”)

§genomic_start: Option<u64>

Genomic start position of transcript (1-based, inclusive)

§genomic_end: Option<u64>

Genomic end position of transcript (1-based, inclusive)

§genome_build: GenomeBuild

Genome build/assembly version

§mane_status: ManeStatus

MANE (Matched Annotation from NCBI and EBI) status

§refseq_match: Option<String>

RefSeq accession matched to this transcript (for Ensembl transcripts)

§ensembl_match: Option<String>

Ensembl accession matched to this transcript (for RefSeq transcripts)

Implementations§

Source §

impl Transcript

Source

pub fn new( id: String, gene_symbol: Option<String>, strand: Strand, sequence: String, cds_start: Option<u64>, cds_end: Option<u64>, exons: Vec<Exon>, chromosome: Option<String>, genomic_start: Option<u64>, genomic_end: Option<u64>, genome_build: GenomeBuild, mane_status: ManeStatus, refseq_match: Option<String>, ensembl_match: Option<String>, ) -> Self

Create a new Transcript with the given fields

Source

pub fn sequence_length(&self) -> u64

Get the length of the transcript sequence

Source

pub fn is_coding(&self) -> bool

Check if this is a coding transcript

Source

pub fn cds_length(&self) -> Option<u64>

Get the CDS length

Source

pub fn get_sequence(&self, start: u64, end: u64) -> Option<&str>

Get sequence at a position range (0-based)

Source

pub fn exon_at(&self, pos: u64) -> Option<&Exon>

Find which exon contains a position using binary search

Assumes exons are sorted by start position (which they typically are). Falls back to linear search if exons are not sorted.

Source

pub fn utr5_length(&self) -> Option<u64>

Get the 5’ UTR length

Source

pub fn utr3_length(&self) -> Option<u64>

Get the 3’ UTR length

Source

pub fn has_genomic_coords(&self) -> bool

Check if this transcript has genomic coordinates

Source

pub fn genomic_length(&self) -> Option<u64>

Get the genomic length (span) of the transcript

Source

pub fn contains_genomic_pos(&self, pos: u64) -> bool

Check if a genomic position falls within this transcript’s span

Source

pub fn is_mane_select(&self) -> bool

Check if this is a MANE Select transcript

Source

pub fn is_mane_plus_clinical(&self) -> bool

Check if this is a MANE Plus Clinical transcript

Source

pub fn is_mane(&self) -> bool

Check if this is any type of MANE transcript

Source

pub fn introns(&self) -> &[Intron]

Get cached introns, computing them lazily if not already cached

This method provides O(1) access to introns after the first call, avoiding recalculation on every lookup.

Source

pub fn calculate_introns(&self) -> Vec<Intron>

Calculate introns from exon boundaries

Returns a vector of Intron structs derived from adjacent exon pairs. Exons should be sorted by transcript position.

Note: This method uses caching internally. For repeated access, prefer introns() which returns a slice reference.

Source

pub fn find_intron_at_genomic( &self, genomic_pos: u64, ) -> Option<(Intron, IntronPosition)>

Find which intron contains a genomic position

Returns the intron and the offset from the nearest exon boundary. Positive offset means downstream from 5’ boundary (c.N+offset notation). Negative offset means upstream from 3’ boundary (c.N-offset notation).

Source