[−][src]Trait rust_htslib::bam::ext::BamRecordExtensions
Extra functionality for BAM records
Inspired by pysam
Required methods
fn aligned_blocks(&self) -> Vec<[i64; 2]>
get a list of start and end positions of aligned gapless blocks
The start and end positions are in genomic coordinates. There is not necessarily a gap between blocks on the genome, this happens on insertions.
pysam: blocks
fn introns(&self) -> Vec<[i64; 2]>
find intron positions (start, stop)
This scans the CIGAR for reference skips and reports their positions.
pysam: get_introns
fn aligned_pairs(&self) -> Vec<[i64; 2]>
a list of aligned read and reference positions
No entry for insertions, deletions or skipped pairs
pysam: get_aligned_pairs(matches_only = True)
fn aligned_pairs_full(&self) -> Vec<[Option<i64>; 2]>
a list of aligned read and reference positions
None in either the read positions or the reference position for insertions, deletions or skipped pairs
pysam: aligned_pairs(matches_only = False)
fn cigar_stats_nucleotides(&self) -> HashMap<Cigar, i32>
the number of nucleotides covered by each Cigar:: possibility
Result is a Hashmap Cigar::xyz(0) => covered nucleotides
pysam: first result from get_cigar_stats
fn cigar_stats_blocks(&self) -> HashMap<Cigar, i32>
the number of occurances of each each Cigar:: possibility
Result is a Hashmap Cigar::xyz(0) => number of times this Cigar:: appeared
pysam: second result from get_cigar_stats
fn reference_positions(&self) -> Vec<i64>
a Vec of reference positions that this read aligns to
only returns positions that are aligned, excluding any soft-clipped or unaligned positions within the read
pysam: get_reference_positions(full_length=False)
fn reference_positions_full(&self) -> Vec<Option<i64>>
a Vec of reference positions that this read aligns to
include soft-clipped or skipped positions as None
pysam: get_reference_positions(full_length=True)
fn reference_start(&self) -> i64
left most aligned reference position of the read on the reference genome.
fn reference_end(&self) -> i64
right most aligned reference position of the read on the reference genome.
fn seq_len_from_cigar(&self, include_hard_clip: bool) -> usize
infer the query length from the cigar string, optionally include hard clipped bases
Contrast with record::seq_len which returns the length of the sequence stored in the BAM file, and as such is 0 if the BAM file omits sequences
pysam: infer_query_length / infer_read_length