ibf.hpp File Reference

#include <filesystem>
#include <iostream>
#include <math.h>
#include <numeric>
#include <string>
#include <seqan3/alphabet/container/concatenated_sequences.hpp>
#include <seqan3/alphabet/nucleotide/dna4.hpp>
#include "shared.hpp"

Go to the source code of this file.

Classes
struct	minimiser_arguments
struct	RandomGenerator
	Generates a random integer not greater than a given maximum. More...

Functions
void	count (min_arguments const &args, std::vector< std::filesystem::path > sequence_files, std::filesystem::path include_file, std::filesystem::path genome_file, bool paired)
	Get the concrete expression values (= median of all counts of one transcript) for given experiments. This function can be used to estimate how good the median approach can be, if all count values are available.
void	count_genome (min_arguments const &args, std::filesystem::path include_file, std::filesystem::path exclude_file)
	Creates a set of minimizers to ignore, which should be used as an input to count.
void	read_binary (std::filesystem::path filename, robin_hood::unordered_node_map< uint64_t, uint16_t > &hash_table)
	Reads a binary file that needle minimiser creates.
void	read_binary_start (min_arguments &args, std::filesystem::path filename, uint64_t &num_of_minimisers, uint8_t &cutoff)
	Reads the beginning of a binary file that needle minimiser creates.
std::vector< uint16_t >	ibf (std::vector< std::filesystem::path > const &sequence_files, estimate_ibf_arguments &ibf_args, minimiser_arguments &minimiser_args, std::vector< double > &fpr, std::vector< uint8_t > &cutoffs, std::filesystem::path const expression_by_genome_file="", size_t num_hash=1)
	Creates IBFs.
std::vector< uint16_t >	ibf (std::vector< std::filesystem::path > const &minimiser_files, estimate_ibf_arguments &ibf_args, std::vector< double > &fpr, std::filesystem::path const expression_by_genome_file="", size_t num_hash=1)
	Creates IBFs based on the minimiser files.
void	minimiser (std::vector< std::filesystem::path > const &sequence_files, min_arguments const &args, minimiser_arguments &minimiser_args, std::vector< uint8_t > &cutoffs)
	Create minimiser and header files.
std::vector< uint16_t >	insert (std::vector< std::filesystem::path > const &sequence_files, estimate_ibf_arguments &ibf_args, minimiser_arguments &minimiser_args, std::vector< uint8_t > &cutoffs, std::filesystem::path const expression_by_genome_file, std::filesystem::path path_in, bool samplewise)
	Insert into IBFs.
std::vector< uint16_t >	insert (std::vector< std::filesystem::path > const &minimiser_files, estimate_ibf_arguments &ibf_args, std::filesystem::path const expression_by_genome_file, std::filesystem::path path_in, bool samplewise)
	Insert into IBFs based on the minimiser files.
void	delete_bin (std::vector< uint64_t > const &delete_files, estimate_ibf_arguments &ibf_args, std::filesystem::path path_in, bool samplewise)
	Delete bins from ibfs.

Function Documentation

count()

void count	(	min_arguments const &	args,
		std::vector< std::filesystem::path >	sequence_files,
		std::filesystem::path	include_file,
		std::filesystem::path	genome_file,
		bool	paired )

Get the concrete expression values (= median of all counts of one transcript) for given experiments. This function can be used to estimate how good the median approach can be, if all count values are available.

Parameters

args	The minimiser arguments to use (seed, shape, window size).
sequence_files	The sequence files, which contains the reads.
include_file	A file containing the transcripts which expression values should be determined.
genome_file	A "*.genome" file constructed with the command genome.
paired	Flag to indicate if input data is paired or not.

count_genome()

void count_genome	(	min_arguments const &	args,
		std::filesystem::path	include_file,
		std::filesystem::path	exclude_file )

Creates a set of minimizers to ignore, which should be used as an input to count.

Parameters

args	The minimiser arguments to use (seed, shape, window size).
include_file	A file containing the transcripts which expression values should be determined.
exclude_file	A file containing minimizers which should be ignored.

delete_bin()

void delete_bin	(	std::vector< uint64_t > const &	delete_files,
		estimate_ibf_arguments &	ibf_args,
		std::filesystem::path	path_in,
		bool	samplewise )

Delete bins from ibfs.

Parameters

delete_files	A vector of integers specifiying the bins to delete.
ibf_args	The IBF specific arguments to use (bin size, number of hash functions, ...). See struct ibf_arguments.
path_in	Input directory.
samplewise	True, if expression levels were set beforehand.

ibf() [1/2]

std::vector< uint16_t > ibf	(	std::vector< std::filesystem::path > const &	minimiser_files,
		estimate_ibf_arguments &	ibf_args,
		std::vector< double > &	fpr,
		std::filesystem::path const	expression_by_genome_file = "",
		size_t	num_hash = 1 )

Creates IBFs based on the minimiser files.

Parameters

minimiser_files	A vector of minimiser file paths.
ibf_args	The IBF specific arguments to use (bin size, number of hash functions, ...). See struct ibf_arguments.
fpr	The average false positive rate that should be used.
expression_by_genome_file	File that contains the only minimisers that should be comnsidered for the determination of the expression_thresholds.
num_hash	The number of hash functions to use.

Returns

The expression thresholds per experiment.

ibf() [2/2]

std::vector< uint16_t > ibf	(	std::vector< std::filesystem::path > const &	sequence_files,
		estimate_ibf_arguments &	ibf_args,
		minimiser_arguments &	minimiser_args,
		std::vector< double > &	fpr,
		std::vector< uint8_t > &	cutoffs,
		std::filesystem::path const	expression_by_genome_file = "",
		size_t	num_hash = 1 )

Creates IBFs.

Parameters

sequence_files	A vector of sequence file paths.
ibf_args	The IBF specific arguments to use (bin size, number of hash functions, ...). See struct ibf_arguments.
minimiser_args	The minimiser specific arguments to use.
fpr	The average false positive rate that should be used.
cutoffs	List of cutoffs.
expression_by_genome_file	File that contains the only minimisers that should be considered for the determination of the expression thresholds.
num_hash	The number of hash functions to use.

Returns

The expression thresholds per experiment.

insert() [1/2]

std::vector< uint16_t > insert	(	std::vector< std::filesystem::path > const &	minimiser_files,
		estimate_ibf_arguments &	ibf_args,
		std::filesystem::path const	expression_by_genome_file,
		std::filesystem::path	path_in,
		bool	samplewise )

Insert into IBFs based on the minimiser files.

Parameters

minimiser_files	A vector of minimiser file paths.
ibf_args	The IBF specific arguments to use (bin size, number of hash functions, ...). See struct ibf_arguments.
expression_by_genome_file	File that contains the only minimisers that should be comnsidered for the determination of the expression_thresholds.
path_in	Input directory.
samplewise	True, if expression levels were set beforehand.

Returns

The expression thresholds per experiment.

insert() [2/2]

std::vector< uint16_t > insert	(	std::vector< std::filesystem::path > const &	sequence_files,
		estimate_ibf_arguments &	ibf_args,
		minimiser_arguments &	minimiser_args,
		std::vector< uint8_t > &	cutoffs,
		std::filesystem::path const	expression_by_genome_file,
		std::filesystem::path	path_in,
		bool	samplewise )

Insert into IBFs.

Parameters

sequence_files	A vector of sequence file paths.
ibf_args	The IBF specific arguments to use (bin size, number of hash functions, ...). See struct ibf_arguments.
minimiser_args	The minimiser specific arguments to use.
cutoffs	List of cutoffs.
expression_by_genome_file	File that contains the only minimisers that should be considered for the determination of the expression thresholds.
path_in	Input directory.
samplewise	True, if expression levels were set beforehand.

Returns

The expression thresholds per experiment.

minimiser()

void minimiser	(	std::vector< std::filesystem::path > const &	sequence_files,
		min_arguments const &	args,
		minimiser_arguments &	minimiser_args,
		std::vector< uint8_t > &	cutoffs )

Create minimiser and header files.

Parameters

sequence_files	A vector of sequence file paths.
args	The minimiser arguments to use (seed, shape, window size).
minimiser_args	The minimiser specific arguments to use.
cutoffs	List of cutoffs.

read_binary()

void read_binary	(	std::filesystem::path	filename,
		robin_hood::unordered_node_map< uint64_t, uint16_t > &	hash_table )

Reads a binary file that needle minimiser creates.

Parameters

filename	The filename of the binary file.
hash_table	The hash table to store minimisers into.

read_binary_start()

void read_binary_start	(	min_arguments &	args,
		std::filesystem::path	filename,
		uint64_t &	num_of_minimisers,
		uint8_t &	cutoff )

Reads the beginning of a binary file that needle minimiser creates.

Parameters

args	Min arguments.
filename	The filename of the binary file.
num_of_minimisers	Variable, where to number of minimisers should be stored.
cutoff	cutoff value.