BioKotlin/biokotlin.util

Package-level declarations

Types

data class AltHeaderMetaData(val id: String, val description: String, val source: String, val sampleGamete: SampleGamete, val regions: List<Pair<Position, Position>>, val checksum: String, val refRange: String, val refChecksum: String = "")

BedUtils

object BedUtils

FastaLineWrapper

class FastaLineWrapper(val wrapSize: Int = 60)

Simple class to place newline characters at fixed intervals while writing to output

GetVCFVariants

class GetVCFVariants(inputFiles: List<String>, debug: Boolean = false)

Get the variant lines for the given positions from the VCF files. Input files, VCF Readers, Sample lists, and variants are kept in the same order. Sorted by the first sample name in each VCF file.

MergeGVCFUtils

object MergeGVCFUtils

Merges GVCF files into a single VCF file. The GVCF files should have only one sample each. If a bedfile is provided, then the output VCF file is split into multiple files based on the ranges in the bedfile.

MissingType

enum MissingType : Enum<MissingType>

MutateProteinsUtils

object MutateProteinsUtils

SimpleVariant

data class SimpleVariant(val contig: String, val start: Int, val end: Int, val refAllele: String, val altAlleles: List<String>, val samples: List<String>, val genotypes: List<String>, val originalText: String? = null) : Comparable<SimpleVariant>

Data class to represent a simple VCF variant

TypeMutation

enum TypeMutation : Enum<TypeMutation>

ValidateGVCFsUtils

object ValidateGVCFsUtils

ValidateVCFResults

data class ValidateVCFResults(val valid: Boolean, val mergedContigs: List<String>)

VCFReader

data class VCFReader(val filename: String, val altHeaders: Map<String, AltHeaderMetaData>, val samples: List<String>, variants: Channel<Deferred<LinkedList<SimpleVariant>>>, scope: CoroutineScope = CoroutineScope(Dispatchers.Default))

Properties

numProteinLetters

val numProteinLetters: Int

proteinLetters

val proteinLetters: CharArray

Functions

bufferedReader

fun bufferedReader(filename: String): BufferedReader

bufferedWriter

fun bufferedWriter(filename: String, append: Boolean = false): BufferedWriter

convertGVCFToFasta

fun convertGVCFToFasta(gvcfFile: String, refFasta: String, outFile: String, sampleName: String? = null, missingRecordsAs: MissingType = MissingType.asRef, missingGenotypeAs: MissingType = MissingType.asN, alleleIdx: Int = 0)

Function to convert a genotype in a GVCF file to a fasta sequence. All records must use non-symbloic alleles (except ), and duplicated positions are not allowed. Supports multisample VCFs. Parameters: gvcfFile: path to the GVCF file to use. The script accepts VCF file format, but GVCFs should be used to ensure that all variants are accounted for refFasta: path to the reference FASTA file outFile: path to the output FASTA file sampleName: optional, the sample name to use in a multisample VCF. Defaults to the first sample listed missingRecordAs: optional, default asRef. Behavior for positions that lack a GVCF record (variant site or ref block). Option asRef treats missing positions like reference blocks. Option asN fills the region with N's. Option asNone omits the region entirely. missingGenotypeAs: optional, default asN. Behavior for records with a missing or no-call genotype (.). Option asRef treats missing genotypes as reference alleles. Option asN fills missing genotypes with N. The number of N's is equal to the length of the record on the reference. Option asNone omits the position entirely. alleleIdx: optional. In a diploid or polyploid, the index of the allele to use. Defaults to 0.

createGenericVCFHeaders

fun createGenericVCFHeaders(taxaNames: List<String>): VCFHeader

Function creates generic headers for a g/VCF file

getAllVCFFiles

fun getAllVCFFiles(vcfDir: String): List<String>

Function to get all VCF files in a directory. Includes extensions .g.vcf, .g.vcf.gz, .gvcf, .gvcf.gz, .h.vcf, .h.vcf.gz, .hvcf, .hvcf.gz, .vcf, .vcf.gz

getGVCFFiles

fun getGVCFFiles(gvcfDir: String): List<String>

Function to get all GVCF files in a directory. Includes extensions .g.vcf, .g.vcf.gz, .gvcf, .gvcf.gz

getVCFVariantsExample

fun getVCFVariantsExample(inputDir: String)

This is an example use of GetVCFVariants. See MergeGVCFs.kt for a similar example.

parseALTHeader

fun parseALTHeader(header: VCFHeader): Map<String, AltHeaderMetaData>

Helper function to parse out the ALT headers from the VCF file.

setupDebugLogging

fun setupDebugLogging()

Sends all logging messages (including log4j) to standard out. The logging level will be DEBUG.

validateVCFs

suspend fun validateVCFs(inputDir: String): ValidateVCFResults

suspend fun validateVCFs(inputFiles: List<String>): ValidateVCFResults

vcfReader

fun vcfReader(inputFile: String, debug: Boolean = false): VCFReader

Function to create a VCF reader from a file.