RegionKey main functions. More...

#include <stdio.h>
#include "nrvk.h"

Data Structures
struct	regionkey_t

struct	regionkey_rev_t

Macros
#define	RK_MAX_POS 0x000000000FFFFFFF
	Maximum position value (2^28 - 1) More...

#define	RKMASK_CHROM 0xF800000000000000
	RegionKey binary mask for CHROM [ 11111000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 ]. More...

#define	RKMASK_STARTPOS 0x07FFFFFF80000000
	RegionKey binary mask for START POS [ 00000111 11111111 11111111 11111111 10000000 00000000 00000000 00000000 ]. More...

#define	RKMASK_ENDPOS 0x000000007FFFFFF8
	RegionKey binary mask for END POS [ 00000000 00000000 00000000 00000000 01111111 11111111 11111111 11111000 ]. More...

#define	RKMASK_STRAND 0x0000000000000006
	RegionKey binary mask for STRAND [ 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000110 ]. More...

#define	RKMASK_NOPOS 0xF800000000000007
	RegionKey binary mask WITHOUT POS [ 11111000 00000000 00000000 00000000 00000000 00000000 00000000 00000111 ]. More...

#define	RKSHIFT_CHROM 59
	CHROM LSB position from the VariantKey LSB. More...

#define	RKSHIFT_STARTPOS 31
	START POS LSB position from the VariantKey LSB. More...

#define	RKSHIFT_ENDPOS 3
	END POS LSB position from the VariantKey LSB. More...

#define	RKSHIFT_STRAND 1
	STRAND LSB position from the VariantKey LSB. More...

#define	RK_CHROM ((rk & RKMASK_CHROM) >> RKSHIFT_CHROM)
	Extract the CHROM code from RegionKey. More...

#define	RK_STARTPOS ((rk & RKMASK_STARTPOS) >> RKSHIFT_STARTPOS)
	Extract the START POS code from RegionKey. More...

#define	RK_ENDPOS ((rk & RKMASK_ENDPOS) >> RKSHIFT_ENDPOS)
	Extract the END POS code from RegionKey. More...

#define	RK_STRAND ((rk & RKMASK_STRAND) >> RKSHIFT_STRAND)
	Extract the STRAND from RegionKey. More...

Typedefs
typedef struct regionkey_t	regionkey_t

typedef struct regionkey_rev_t	regionkey_rev_t

Functions
static uint8_t	encode_region_strand (int8_t strand)
	Encode the strand direction (-1 > 2, 0 > 0, +1 > 1). More...

static int8_t	decode_region_strand (uint8_t strand)
	Decode the strand direction code (0 > 0, 1 > +1, 2 > -1). More...

static uint64_t	encode_regionkey (uint8_t chrom, uint32_t startpos, uint32_t endpos, uint8_t strand)
	Returns a 64 bit regionkey. More...

static uint8_t	extract_regionkey_chrom (uint64_t rk)
	Extract the CHROM code from RegionKey. More...

static uint32_t	extract_regionkey_startpos (uint64_t rk)
	Extract the START POS code from RegionKey. More...

static uint32_t	extract_regionkey_endpos (uint64_t rk)
	Extract the END POS code from RegionKey. More...

static uint8_t	extract_regionkey_strand (uint64_t rk)
	Extract the STRAND from RegionKey. More...

static void	decode_regionkey (uint64_t code, regionkey_t *rk)
	Decode a RegionKey code and returns the components as regionkey_t structure. More...

static void	reverse_regionkey (uint64_t rk, regionkey_rev_t *rev)

static uint64_t	regionkey (const char *chrom, size_t sizechrom, uint32_t startpos, uint32_t endpos, int8_t strand)
	Returns a 64 bit regionkey based on CHROM, START POS (0-based), END POS and STRAND. More...

static uint64_t	extend_regionkey (uint64_t rk, uint32_t size)
	Extend a regionkey region by a fixed amount from the start and end position. More...

static size_t	regionkey_hex (uint64_t rk, char *str)
	Returns RegionKey hexadecimal string (16 characters). More...

static uint64_t	parse_regionkey_hex (const char *rs)
	Parses a RegionKey hexadecimal string and returns the code. More...

static uint64_t	get_regionkey_chrom_startpos (uint64_t rk)
	Get the CHROM + START POS encoding from RegionKey. More...

static uint64_t	get_regionkey_chrom_endpos (uint64_t rk)
	Get the CHROM + END POS encoding from RegionKey. More...

static uint8_t	are_overlapping_regions (uint8_t a_chrom, uint32_t a_startpos, uint32_t a_endpos, uint8_t b_chrom, uint32_t b_startpos, uint32_t b_endpos)
	Check if two regions are overlapping. More...

static uint8_t	are_overlapping_region_regionkey (uint8_t chrom, uint32_t startpos, uint32_t endpos, uint64_t rk)
	Check if a region and a regionkey are overlapping. More...

static uint8_t	are_overlapping_regionkeys (uint64_t rka, uint64_t rkb)
	Check if two regionkeys are overlapping. More...

static uint8_t	are_overlapping_variantkey_regionkey (nrvk_cols_t nvc, uint64_t vk, uint64_t rk)
	Check if variantkey and regionkey are overlapping. More...

static uint64_t	variantkey_to_regionkey (nrvk_cols_t nvc, uint64_t vk)
	Get RegionKey from VariantKey. More...

Detailed Description

The functions provided here allows to generate and process a 64 bit Unsigned Integer Keys for Human Genomic Regions. The RegionKey is sortable for chromosome and start position, and it is also fully reversible.

Macro Definition Documentation

#define RK_CHROM ((rk & RKMASK_CHROM) >> RKSHIFT_CHROM)

#define RK_ENDPOS ((rk & RKMASK_ENDPOS) >> RKSHIFT_ENDPOS)

#define RK_MAX_POS 0x000000000FFFFFFF

#define RK_STARTPOS ((rk & RKMASK_STARTPOS) >> RKSHIFT_STARTPOS)

#define RK_STRAND ((rk & RKMASK_STRAND) >> RKSHIFT_STRAND)

#define RKMASK_CHROM 0xF800000000000000

#define RKMASK_ENDPOS 0x000000007FFFFFF8

#define RKMASK_NOPOS 0xF800000000000007

#define RKMASK_STARTPOS 0x07FFFFFF80000000

#define RKMASK_STRAND 0x0000000000000006

#define RKSHIFT_CHROM 59

#define RKSHIFT_ENDPOS 3

#define RKSHIFT_STARTPOS 31

#define RKSHIFT_STRAND 1

Typedef Documentation

typedef struct regionkey_rev_t regionkey_rev_t

RegionKey decoded struct

typedef struct regionkey_t regionkey_t

RegionKey struct. Contains the numerically encoded RegionKey components (CHROM, STARTPOS, ENDPOS, STRAND).

Function Documentation

static uint8_t are_overlapping_region_regionkey	(	uint8_t	chrom,
		uint32_t	startpos,
		uint32_t	endpos,
		uint64_t	rk
	)

inlinestatic

Parameters

chrom	Region A chromosome code.
startpos	Region A start position.
endpos	Region A end position (startpos + region length).
rk	RegionKey or region B.

Returns: 1 if the regions overlap, 0 otherwise.

static uint8_t are_overlapping_regionkeys	(	uint64_t	rka,
		uint64_t	rkb
	)

inlinestatic

Parameters

rka	RegionKey A.
rkb	RegionKey B.

Returns: 1 if the regions overlap, 0 otherwise.

static uint8_t are_overlapping_regions	(	uint8_t	a_chrom,
		uint32_t	a_startpos,
		uint32_t	a_endpos,
		uint8_t	b_chrom,
		uint32_t	b_startpos,
		uint32_t	b_endpos
	)

inlinestatic

Parameters

a_chrom	Region A chromosome code.
a_startpos	Region A start position.
a_endpos	Region A end position (startpos + region length).
b_chrom	Region B chromosome code.
b_startpos	Region B start position.
b_endpos	Region B end position (startpos + region length).

Returns: 1 if the regions overlap, 0 otherwise.

static uint8_t are_overlapping_variantkey_regionkey	(	nrvk_cols_t	nvc,
		uint64_t	vk,
		uint64_t	rk
	)

inlinestatic

Parameters

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

Returns: 1 if the regions overlap, 0 otherwise.

static int8_t decode_region_strand ( uint8_t strand )

inlinestatic

Parameters

strand Strand code.

Returns: Strand direction.

static void decode_regionkey	(	uint64_t	code,
		regionkey_t *	rk
	)

inlinestatic

Parameters

code	RegionKey code.
rk	Decoded regionkey structure.

static uint8_t encode_region_strand ( int8_t strand )

inlinestatic

Parameters

strand Strand direction (-1, 0, +1).

Returns: Strand code.

static uint64_t encode_regionkey	(	uint8_t	chrom,
		uint32_t	startpos,
		uint32_t	endpos,
		uint8_t	strand
	)

inlinestatic

Parameters

chrom	Encoded Chromosome (see encode_chrom).
startpos	Start position (zero based).
endpos	End position (startpos + region_length).
strand	Encoded Strand direction (-1 > 2, 0 > 0, +1 > 1)

Returns: RegionKey 64 bit code.

static uint64_t extend_regionkey	(	uint64_t	rk,
		uint32_t	size
	)

inlinestatic

Parameters

rk	RegionKey code.
size	Amount to extend the region.

static uint8_t extract_regionkey_chrom ( uint64_t rk )

inlinestatic

Parameters

rk	RegionKey code.

Returns: CHROM code.

static uint32_t extract_regionkey_endpos ( uint64_t rk )

inlinestatic

Parameters

rk	RegionKey code.

Returns: END POS.

static uint32_t extract_regionkey_startpos ( uint64_t rk )

inlinestatic

Parameters

rk	RegionKey code.

Returns: START POS.

static uint8_t extract_regionkey_strand ( uint64_t rk )

inlinestatic

Parameters

rk	RegionKey code.

Returns: STRAND.

static uint64_t get_regionkey_chrom_endpos ( uint64_t rk )

inlinestatic

Parameters

rk	RegionKey code.

Returns: CHROM + END POS.

static uint64_t get_regionkey_chrom_startpos ( uint64_t rk )

inlinestatic

Parameters

rk	RegionKey code.

Returns: CHROM + START POS.

static uint64_t parse_regionkey_hex ( const char * rs )

inlinestatic

Parameters

rs	RegionKey hexadecimal string (it must contain 16 hexadecimal characters).

Returns: A RegionKey code.

static uint64_t regionkey	(	const char *	chrom,
		size_t	sizechrom,
		uint32_t	startpos,
		uint32_t	endpos,
		int8_t	strand
	)

inlinestatic

Parameters

chrom	Chromosome. An identifier from the reference genome, no white-space or leading zeros permitted.
sizechrom	Length of the chrom string, excluding the terminating null byte.
startpos	Start position (zero based).
endpos	End position (startpos + region_length).
strand	Strand direction (-1, 0, +1)

Returns: RegionKey 64 bit code.

static size_t regionkey_hex	(	uint64_t	rk,
		char *	str
	)

inlinestatic

Parameters

rk	RegionKey code.
str	String buffer to be returned (it must be sized 17 bytes at least).

Returns: Upon successful return, these function returns the number of characters processed (excluding the null byte used to end output to strings). If the buffer size is not sufficient, then the return value is the number of characters required for buffer string, including the terminating null byte.

static void reverse_regionkey	(	uint64_t	rk,
		regionkey_rev_t *	rev
	)

inlinestatic

Reverse a RegionKey code and returns the normalized components as regionkey_rev_t structure.

Parameters

rk	RegionKey code.
rev	Structure containing the return values.

static uint64_t variantkey_to_regionkey	(	nrvk_cols_t	nvc,
		uint64_t	vk
	)

inlinestatic

Parameters

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

Returns: RegionKey.

Data Structures

Macros

Typedefs

Functions

Detailed Description

Macro Definition Documentation

Typedef Documentation

Function Documentation