nrvk.h File Reference

Functions to retrieve REF and ALT values by VariantKey from binary data file. More...

#include <stdio.h>
#include <string.h>
#include "binsearch.h"
#include "variantkey.h"

Go to the source code of this file.

Data Structures
struct	variantkey_rev_t
struct	nrvk_cols_t

Macros
#define	ALLELE_MAXSIZE   256
	Maximum allele length. More...

Typedefs
typedef struct variantkey_rev_t	variantkey_rev_t
typedef struct nrvk_cols_t	nrvk_cols_t

Functions
static void	mmap_nrvk_file (const char *file, mmfile_t *mf, nrvk_cols_t *nvc)
static size_t	get_nrvk_ref_alt_by_pos (nrvk_cols_t nvc, uint64_t pos, char *ref, size_t *sizeref, char *alt, size_t *sizealt)
static size_t	find_ref_alt_by_variantkey (nrvk_cols_t nvc, uint64_t vk, char *ref, size_t *sizeref, char *alt, size_t *sizealt)
static size_t	reverse_variantkey (nrvk_cols_t nvc, uint64_t vk, variantkey_rev_t *rev)
static size_t	get_variantkey_ref_length (nrvk_cols_t nvc, uint64_t vk)
static uint32_t	get_variantkey_endpos (nrvk_cols_t nvc, uint64_t vk)
static uint64_t	get_variantkey_chrom_startpos (uint64_t vk)
	Get the CHROM + START POS encoding from VariantKey. More...
static uint64_t	get_variantkey_chrom_endpos (nrvk_cols_t nvc, uint64_t vk)
	Get the CHROM + END POS encoding from VariantKey. More...
static size_t	nrvk_bin_to_tsv (nrvk_cols_t nvc, const char *tsvfile)

Detailed Description

The functions provided here allows to retrieve the REF and ALT strings for a given VariantKey from a binary file.

The input binary files can be generated from a normalized VCF file using the resources/tools/vkhexbin.sh. The VCF file can be normalized using the resources/tools/vcfnorm.sh script.

The binary file can be generated by the `resources/tools/nrvk.sh' script from a TSV file with the following format:

[16 BYTE VARIANTKEY HEX]\t[REF STRING]\t[ALT STRING]\n...

for example:

b800c35bbcece603    AAAAAAAAGG      AG
1800c351f61f65d3    A       AAGAAAGAAAG

Macro Definition Documentation

#define ALLELE_MAXSIZE   256

Typedef Documentation

typedef struct nrvk_cols_t nrvk_cols_t

Struct containing the NRVK memory mapped file column info.

typedef struct variantkey_rev_t variantkey_rev_t

VariantKey decoded struct

Function Documentation

static size_t find_ref_alt_by_variantkey ( nrvk_cols_t  nvc, uint64_t  vk, char *  ref, size_t *  sizeref, char *  alt, size_t *  sizealt  )

inlinestatic

Retrieve the REF and ALT strings for the specified VariantKey.

Parameters

nvc	Structure containing the pointers to the memory mapped file columns.
vk	VariantKey to search.
ref	REF string buffer to be returned.
sizeref	Pointer to the size of the ref buffer, excluding the terminating null byte. This will contain the final ref size.
alt	ALT string buffer to be returned.
sizealt	Pointer to the size of the alt buffer, excluding the terminating null byte. This will contain the final alt size.

Returns

REF+ALT length or 0 if the VariantKey is not found.

static size_t get_nrvk_ref_alt_by_pos ( nrvk_cols_t  nvc, uint64_t  pos, char *  ref, size_t *  sizeref, char *  alt, size_t *  sizealt  )

inlinestatic

static uint64_t get_variantkey_chrom_endpos ( nrvk_cols_t  nvc, uint64_t  vk  )

inlinestatic

Parameters

nvc	Structure containing the pointers to the memory mapped file columns.
vk	VariantKey code.

Returns

CHROM + END POS.

static uint64_t get_variantkey_chrom_startpos ( uint64_t  vk )

inlinestatic

Parameters

vk	VariantKey code.

Returns

CHROM + START POS.

static uint32_t get_variantkey_endpos ( nrvk_cols_t  nvc, uint64_t  vk  )

inlinestatic

Get the VariantKey end position (POS + REF length).

Parameters

nvc	Structure containing the pointers to the memory mapped file columns.
vk	VariantKey.

Returns

Variant end position (POS + REF length).

static size_t get_variantkey_ref_length ( nrvk_cols_t  nvc, uint64_t  vk  )

inlinestatic

Retrieve the REF length for the specified VariantKey.

Parameters

nvc	Structure containing the pointers to the memory mapped file columns.
vk	VariantKey.

Returns

REF length or 0 if the VariantKey is not reversible and not found.

static void mmap_nrvk_file ( const char *  file, mmfile_t *  mf, nrvk_cols_t *  nvc  )

inlinestatic

Memory map the NRVK binary file.

Parameters

file	Path to the file to map.
mf	Structure containing the memory mapped file.
nvc	Structure containing the pointers to the memory mapped file columns.

Returns

Returns the memory-mapped file descriptors.

static size_t nrvk_bin_to_tsv ( nrvk_cols_t  nvc, const char *  tsvfile  )

inlinestatic

Convert a vrnr.bin file to a simple TSV. For the reverse operation see the resources/tools/nrvk.sh script.

Parameters

nvc	Structure containing the pointers to the memory mapped file columns.
tsvfile	Output tsv file name. NOTE: existing files will be replaced.

Returns

Number of written bytes or 0 in case of error.

static size_t reverse_variantkey ( nrvk_cols_t  nvc, uint64_t  vk, variantkey_rev_t *  rev  )

inlinestatic

Reverse a VariantKey code and returns the normalized components as variantkey_rev_t structure.

Parameters

nvc	Structure containing the pointers to the memory mapped file columns.
vk	VariantKey code.
rev	Structure containing the return values.

Returns

A variantkey_rev_t structure.