BioKotlin/biokotlin.seq/NucSeqRecord

NucSeqRecord

class NucSeqRecord(val sequence: NucSeq, val id: String, val name: String? = null, val description: String? = null, val annotations: ImmutableMap<String, String> = ImmutableMap.of(), val letterAnnotations: ImmutableMap<String, Array<out Any>> = ImmutableMap.of()) : SeqRecord, NucSeq

A NucSeqRecord consists of a NucSeq and several optional annotations.

Main attributes:

id - Identifier such as a locus tag (string)
seq - The sequence itself (NucSeq) Additional attributes:
name - Sequence name, e.g. gene name (string)
description - Additional text (string)
annotations - A map of strings containing key-value pairs of annotations for different features
letterAnnotations - Per letter/symbol annotation. This holds an ImmutableList whose length matches that of the sequence. A typical use would be to hold a list of integers representing sequencing quality scores.

from Bio.Seq import NucSeq from Bio.Seq import NucSeqRecord val record_1 = NucSeqRecord(NucSeq("ATCG"), "1", "seq1", "the first sequence")

Constructors

NucSeqRecord

constructor(sequence: NucSeq, id: String, name: String? = null, description: String? = null, annotations: ImmutableMap<String, String> = ImmutableMap.of(), letterAnnotations: ImmutableMap<String, Array<out Any>> = ImmutableMap.of())

Properties

annotations

val annotations: ImmutableMap<String, String>

description

val description: String?

val id: String

letterAnnotations

val letterAnnotations: ImmutableMap<String, Array<out Any>>

name

val name: String?

nucSet

open override val nucSet: NucSet

The type of nucleotides - DNA or RNA and ambiguous or not

sequence

val sequence: NucSeq

Functions

back_transcribe

open override fun back_transcribe(): NucSeq

Transcribes a NucSeq - essentially changes the NucSet from NUC.RNA to NUC.DNA

compareTo

open operator override fun compareTo(other: Seq): Int

complement

open override fun complement(): NucSeq

Returns the complement sequence of DNA or RNA, ambiguity is preserved

fun complement(id: String, name: String? = null, description: String? = null, annotations: ImmutableMap<String, String>? = null): NucSeqRecord

Return a new SeqRecord with the complement sequence. The sequence will have id id. If the other parameters are not specified, they will be taken from the original SeqRecord.

contains

open operator override fun contains(element: NucSeq): Boolean

copyOfBytes

open override fun copyOfBytes(): ByteArray

count

open override fun count(query: NUC): Int

open override fun count(query: NucSeq): Int

count_overlap

open override fun count_overlap(query: NucSeq): Int

find

open override fun find(query: NucSeq, start: Int, end: Int): Int

open override fun gc(): Int

Counts the NUC.G + NUC.C within a NucSeq

get

open operator override fun get(i: Int): NUC

Returns the NUC of this NucSeq at the specified index i with i starting at zero Negative index start from the end of the sequence, i.e. -1 is the last base

open operator override fun get(x: IntRange): NucSeq

Returns a subset NucSeq based on the IntRange of Nucleotides. Kotlin range operator is "..". Indices start at zero. Note Kotlin IntRange are inclusive end, while Python slices exclusive end Negative slices "-3..-1" start from the last base (i.e. would return the last three bases)

open operator override fun get(i: Int, j: Int): NucSeq

Returns a subset NucSeq based on the inclusive start i and inclusive last j Indices start at zero. Negative index start from the end of the sequence, i.e. -1 is the last base

indexOf

open override fun indexOf(query: NucSeq, start: Int, end: Int): Int

join

open override fun join(vararg seqs: NucSeq): NucSeq

kmers

open override fun kmers(kmerSize: Int, bothStrands: Boolean, stepSize: Int): KmerMultiSet

Extracts the kmer count from a nucleotide sequence NucSeq. In general kmers from both strands should be extracted, unless strand specificity is really known. No kmers that include an ambiguous base pair will be included Using stepSize subsets of the kmers can be sampled

lastIndexOf

open override fun lastIndexOf(query: NucSeq, start: Int, end: Int): Int

plus

open operator override fun plus(seq2: NucSeq): NucSeq

position

fun SeqRecord.position(site: Int): SeqPosition

range

fun SeqRecord.range(range: IntRange): SRange

repr

open override fun repr(): String

Returns (truncated) representation of the sequence for debugging

reverse_complement

open override fun reverse_complement(): NucSeq

Returns the complement sequence of DNA or RNA

fun reverse_complement(id: String, name: String? = null, description: String? = null, annotations: ImmutableMap<String, String>? = null): NucSeqRecord

Return a new SeqRecord with the reverse complement sequence. The sequence will have id id. If the other parameters are not specified, they will be taken from the original SeqRecord.

rfind