Genomic analyses helper functions. More...

#include <memory>
#include <array>
#include <string>
#include <utility>
#include <vector>
#include "sam.h"
#include "isoseqAlgn.hpp"

Include dependency graph for helperFunctions.hpp:

Typedefs
using	isaSpace::bamGFFvector = std::vector< std::pair<BAMrecord, ExonGroup> >
	Alias for BAM record and exon group pair vector.

Functions
std::string	isaSpace::extractAttributeName (const TokenAttibuteListPair &tokenAndAttrList)
	Extract a name.
std::string	isaSpace::extractParentName (const std::string &attributeString)
	Extract parent name.
bool	isaSpace::rangesOverlap (const std::pair< hts_pos_t, hts_pos_t > &range1, const std::pair< hts_pos_t, hts_pos_t > &range2) noexcept
	Test for range overlap.
std::array< std::string, nGFFfields >	isaSpace::parseGFFline (const std::string &gffLine)
	Parse a GFF line into fields.
std::unordered_map< std::string, std::vector< ExonGroup > >	isaSpace::parseGFF (const std::string &gffFileName)
	Parse a GFF file.
std::vector< std::vector< float >::const_iterator >	isaSpace::getPeaks (const std::vector< float > &values, const float &threshold)
	Identify peaks in numerical data.
std::vector< std::vector< float >::const_iterator >	isaSpace::getValleys (const std::vector< float > &values, const float &threshold)
	Identify valleys in numerical data.
std::vector< float >	isaSpace::getReferenceMatchStatus (const std::vector< uint32_t > &cigar)
	Read match status along the reference.
ReadExonCoverage	isaSpace::getExonCoverageStats (const std::pair< BAMrecord, ExonGroup > &readAndExons)
	Extract exon coverage statistics for a read.
std::string	isaSpace::stringifyExonCoverage (const ReadExonCoverage &readRecord, char separator='\t')
	Convert ReadExonCoverage to string.
std::string	isaSpace::stringifyAlignmentRange (const bamGFFvector::const_iterator &begin, const bamGFFvector::const_iterator &end)
	Produce a string from a range of read alignments.
std::string	isaSpace::stringifyUnmappedRegions (const bamGFFvector::const_iterator &begin, const bamGFFvector::const_iterator &end, const BinomialWindowParameters &windowParameters)
	Produce a string of poorly aligned region statistics from an alignment range.
std::pair< std::string, std::string >	isaSpace::getUnmappedRegionsAndFASTQ (const bamGFFvector::const_iterator &begin, const bamGFFvector::const_iterator &end, const BinomialWindowParameters &windowParameters)
	Produce a string of poorly aligned region statistics and corresponding FASTQ records from an alignment range.
ReadPortion	isaSpace::parseRemappedReadName (const std::string &remappedReadName)
	Extract original read name and coordinates.
std::unique_ptr< bam1_t, BAMrecordDeleter >	isaSpace::modifyCIGAR (const ReadPortion &modRange, const std::unique_ptr< bam1_t, BAMrecordDeleter > &bamRecord)
	Modify the BAM CIGAR string to erase alignment in a range.
void	isaSpace::addRemappedSecondaryAlignment (const std::unique_ptr< sam_hdr_t, BAMheaderDeleter > &newRecordHeader, const std::unique_ptr< bam1_t, BAMrecordDeleter > &newRecord, const ReadPortion &remapInfo, const std::unique_ptr< sam_hdr_t, BAMheaderDeleter > &originalHeader, const float &remapIdentityCutoff, std::vector< std::unique_ptr< bam1_t, BAMrecordDeleter > > &readMapVector)
	Add a re-mapped secondary alignment.
std::unique_ptr< BGZF, BGZFhandleDeleter >	isaSpace::openBGZFtoAppend (const std::string &bamFileName)
	Open a BGZF file handle for appending.
std::vector< std::pair< bamGFFvector::const_iterator, bamGFFvector::const_iterator > >	isaSpace::makeThreadRanges (const bamGFFvector &targetVector, const size_t &threadCount)
	Make per-thread alignment record/annotation vector ranges.
std::unordered_map< std::string, std::string >	isaSpace::parseCL (int &argc, char **argv)
	Command line parser.
void	isaSpace::extractCLinfo (const std::unordered_map< std::string, std::string > &parsedCLI, std::unordered_map< std::string, int > &intVariables, std::unordered_map< std::string, float > &floatVariables, std::unordered_map< std::string, std::string > &stringVariables)
	Extract parameters from parsed command line interface flags.

Variables
constexpr size_t	isaSpace::nGFFfields {9UL}
	Number of GFF file fields.

Detailed Description

Genomic analyses helper functions.

Author: Anthony J. Greenberg and Rebekah Rogers

Copyright: Copyright (c) 2024 Anthony J. Greenberg and Rebekah Rogers

Version: 0.2

Definitions of class-external functions needed by genomic analyses.

Function Documentation

◆ addRemappedSecondaryAlignment()

void isaSpace::addRemappedSecondaryAlignment	(	const std::unique_ptr< sam_hdr_t, BAMheaderDeleter > &	newRecordHeader,
		const std::unique_ptr< bam1_t, BAMrecordDeleter > &	newRecord,
		const ReadPortion &	remapInfo,
		const std::unique_ptr< sam_hdr_t, BAMheaderDeleter > &	originalHeader,
		const float &	remapIdentityCutoff,
		std::vector< std::unique_ptr< bam1_t, BAMrecordDeleter > > &	readMapVector )

Add a re-mapped secondary alignment.

Add a read portion remap as a secondary alignment to a vector of BAM records. Only reads that pass the identity threshold are added.

Parameters

[in]	newRecordHeader	header corresponding to the re-mapped record
[in]	newRecord	remapped BAM record
[in]	remapInfo	original name and read segment range
[in]	originalHeader	header corresponding to the original record
[in]	remapIdentityCutoff	fraction of sites in the remapped read that are identical to the reference
[in,out]	readMapVector	vector of alignments of a read, first element is the primary alignment

◆ extractAttributeName()

std::string isaSpace::extractAttributeName ( const TokenAttibuteListPair & tokenAndAttrList )

nodiscard

Extract a name.

Extract a token name from GFF attributes.

Parameters

[in] tokenAndAttrList field token and the list of attributes

◆ extractCLinfo()

void isaSpace::extractCLinfo	(	const std::unordered_map< std::string, std::string > &	parsedCLI,
		std::unordered_map< std::string, int > &	intVariables,
		std::unordered_map< std::string, float > &	floatVariables,
		std::unordered_map< std::string, std::string > &	stringVariables )

Extract parameters from parsed command line interface flags.

Extracts needed variable values, indexed by std::string encoded variable names.

Parameters

[in]	parsedCLI	flag values parsed from the command line
[out]	intVariables	indexed int variables for use by main()
[out]	floatVariables	indexed float variables for use by main()
[out]	stringVariables	indexed std::string variables for use by main()

◆ extractParentName()

std::string isaSpace::extractParentName ( const std::string & attributeString )

nodiscard

Extract parent name.

Extract the value of the Parent= attribute from the provided GFF attribute string.

Parameters

[in] attributeString GFF attribute string

Returns: parent name

◆ getExonCoverageStats()

ReadExonCoverage isaSpace::getExonCoverageStats ( const std::pair< BAMrecord, ExonGroup > & readAndExons )

nodiscard

Extract exon coverage statistics for a read.

Parameters

[in] readAndExons read alignment with the corresponding exon group

Returns: exon coverage object

◆ getPeaks()

std::vector< std::vector< float >::const_iterator > isaSpace::getPeaks	(	const std::vector< float > &	values,
		const float &	threshold )

nodiscard

Identify peaks in numerical data.

Returns iterators to the elements in a vector that correspond to peaks above the provided threshold. Last element is the const_iterator to the end of the vector unless it is empty, and is the only element if there are no peaks.

Parameters

[in]	values	vector of values
[in]	threshold	value that must be exceeded for a peak call

Returns: vector of iterators to peak elements

◆ getReferenceMatchStatus()

std::vector< float > isaSpace::getReferenceMatchStatus ( const std::vector< uint32_t > & cigar )

nodiscard

Read match status along the reference.

Parses CIGAR to track read (query) match/mismatch (1.0 for match, 0.0 for mismatch) status along the reference. This means that insertions in the read are ignored. The vector start begins at the position closest to the first exon start regardless of strand.

Parameters

[in] cigar CIGAR vector

Returns: vector of match status

◆ getUnmappedRegionsAndFASTQ()

std::pair< std::string, std::string > isaSpace::getUnmappedRegionsAndFASTQ	(	const bamGFFvector::const_iterator &	begin,
		const bamGFFvector::const_iterator &	end,
		const BinomialWindowParameters &	windowParameters )

nodiscard

Produce a string of poorly aligned region statistics and corresponding FASTQ records from an alignment range.

Only saves information from reads that have poorly mapped regions, potentially multiple per read.

Parameters

[in]	begin	start iterator
[in]	end	end iterator
[in]	windowParameters	sliding window parameters

Returns: strings with coverage information (.first) and FASTQ (.second)

◆ getValleys()

std::vector< std::vector< float >::const_iterator > isaSpace::getValleys	(	const std::vector< float > &	values,
		const float &	threshold )

nodiscard

Identify valleys in numerical data.

Returns iterators to the elements in a vector that correspond to valleys below the provided threshold. Last element is the const_iterator to the end of the vector unless it is empty, and is the only element if there are no valleys.

Parameters

[in]	values	vector of values
[in]	threshold	value that must exceed the valley values

Returns: vector of iterators to valley elements

◆ makeThreadRanges()

std::vector< std::pair< bamGFFvector::const_iterator, bamGFFvector::const_iterator > > isaSpace::makeThreadRanges	(	const bamGFFvector &	targetVector,
		const size_t &	threadCount )

nodiscard

Make per-thread alignment record/annotation vector ranges.

Constructs a vector of iterator pairs bracketing chunks of a vector to be processed in parallel.

Parameters

[in]	targetVector	the vector to be processed
[in]	threadCount	number of threads

Returns: vector of iterator pairs for each thread

◆ modifyCIGAR()

std::unique_ptr< bam1_t, BAMrecordDeleter > isaSpace::modifyCIGAR	(	const ReadPortion &	modRange,
		const std::unique_ptr< bam1_t, BAMrecordDeleter > &	bamRecord )

nodiscard

Modify the BAM CIGAR string to erase alignment in a range.

Substitute operations in a BAM record within the given range with non-matching operations.

Parameters

[in]	modRange	modification range
[in]	bamRecord	BAM record to be modified

Returns: BAM record with the CIGAR vector replaced

◆ openBGZFtoAppend()

std::unique_ptr< BGZF, BGZFhandleDeleter > isaSpace::openBGZFtoAppend ( const std::string & bamFileName )

Open a BGZF file handle for appending.

Opens a handle to the BAM file for appending, deleting the original if it exists.

Parameters

[in] bamFileName BAM file name

◆ parseCL()

std::unordered_map< std::string, std::string > isaSpace::parseCL	(	int &	argc,
		char **	argv )

nodiscard

Command line parser.

Maps flags to values. Flags assumed to be of the form --flag-name value.

Parameters

[in]	argc	size of the argv array
[in]	argv	command line input array

Returns: map of tags to values

◆ parseGFF()

std::unordered_map< std::string, std::vector< ExonGroup > > isaSpace::parseGFF ( const std::string & gffFileName )

nodiscard

Parse a GFF file.

Extract exons from a GFF file and group them by gene and chromosome/linkage group. The map keys are linkage groups, scaffolds, or chromosomes plus strand ID.

Parameters

[in] gffFileName GFF file name

Returns: collection of exon group vectors by chromosome and strand

◆ parseGFFline()

std::array< std::string, nGFFfields > isaSpace::parseGFFline ( const std::string & gffLine )

nodiscard

Parse a GFF line into fields.

Places FAIL in the first element if the number of fields is not nGFFfields as required by the GFF specification.

Parameters

[in] gffLine one line of a GFF file

Returns: each GFF field in a separate element

◆ parseRemappedReadName()

ReadPortion isaSpace::parseRemappedReadName ( const std::string & remappedReadName )

nodiscard

Extract original read name and coordinates.

The remapped read names are original names, with _-separated start and end coordinates. Underscores in the original read name are allowed. If the coordinates are absent, returns an empty object.

Parameters

[in] remappedReadName re-mapped read portion name

Returns: original read name and segment coordinates

◆ rangesOverlap()

bool isaSpace::rangesOverlap	(	const std::pair< hts_pos_t, hts_pos_t > &	range1,
		const std::pair< hts_pos_t, hts_pos_t > &	range2 )

nodiscardnoexcept

Test for range overlap.

The first position in each range need not be before the second in the same range.

Parameters

[in]	range1	first range
[in]	range2	second range

Returns: true if there is overlap

◆ stringifyAlignmentRange()

std::string isaSpace::stringifyAlignmentRange	(	const bamGFFvector::const_iterator &	begin,
		const bamGFFvector::const_iterator &	end )

nodiscard

Produce a string from a range of read alignments.

Parameters

[in]	begin	start iterator
[in]	end	end iterator

Returns: string with coverage information

◆ stringifyExonCoverage()

std::string isaSpace::stringifyExonCoverage	(	const ReadExonCoverage &	readRecord,
		char	separator = '\t' )

nodiscard

Convert ReadExonCoverage to string.

Parameters

[in]	readRecord	individual read record
[in]	separator	field separator

Returns: std::string with the read record elements, without a new line at the end

◆ stringifyUnmappedRegions()

std::string isaSpace::stringifyUnmappedRegions	(	const bamGFFvector::const_iterator &	begin,
		const bamGFFvector::const_iterator &	end,
		const BinomialWindowParameters &	windowParameters )

nodiscard

Produce a string of poorly aligned region statistics from an alignment range.

Only saves information from reads that have poorly mapped regions, potentially multiple per read.

Parameters

[in]	begin	start iterator
[in]	end	end iterator
[in]	windowParameters	sliding window parameters

Returns: string with coverage information

Typedefs

Functions

Variables

Detailed Description

Function Documentation

◆ addRemappedSecondaryAlignment()

◆ extractAttributeName()

◆ extractCLinfo()

◆ extractParentName()

◆ getExonCoverageStats()

◆ getPeaks()

◆ getReferenceMatchStatus()

◆ getUnmappedRegionsAndFASTQ()

◆ getValleys()

◆ makeThreadRanges()

◆ modifyCIGAR()

◆ openBGZFtoAppend()

◆ parseCL()

◆ parseGFF()

◆ parseGFFline()

◆ parseRemappedReadName()

◆ rangesOverlap()

◆ stringifyAlignmentRange()

◆ stringifyExonCoverage()

◆ stringifyUnmappedRegions()