#include <algo/blast/vdb/vdb2blast_util.hpp>

Inheritance diagram for CVDBBlastUtil:

Collaboration diagram for CVDBBlastUtil:

Public Types
enum	IDType { eSRAId = 0 , eWGSId , eCSRALocalRefId , eCSRARefId , eUnknownId }

Public Types inherited from CObject
enum	EAllocFillMode { eAllocFillNone = 1 , eAllocFillZero , eAllocFillPattern }
	Control filling of newly allocated memory. More...

typedef CObjectCounterLocker	TLockerType
	Default locker type for CRef. More...

typedef atomic< Uint8 >	TCounter
	Counter type is CAtomiCounter. More...

typedef Uint8	TCount
	Alias for value type of counter. More...

Public Member Functions
	CVDBBlastUtil (const string &strAllRuns, bool bOwnSeqSrc=false, bool bCSRA=false, bool bIncludeFilteredReads=false)
	Constructor that creates and stores the SRA BlastSeqSrc object. More...

virtual	~CVDBBlastUtil ()
	Destructor. More...

BlastSeqSrc *	GetSRASeqSrc ()
	Return the stored SRA BlastSeqSrc object. More...

CRef< blast::IBlastSeqInfoSrc >	GetSRASeqInfoSrc ()
	Return the SRA BlastSeqInfoSrc object (create if none exists). More...

Uint4	GetOIDFromVDBSeqId (CRef< objects::CSeq_id > seqId)
	Get the ordinal number (OID) for the given SRA sequence. More...

CRef< objects::CSeq_id >	GetVDBSeqIdFromOID (Uint4 oid)
	Get the SRA sequence SeqID given its ordinal number (OID). More...

CRef< objects::CBioseq >	CreateBioseqFromVDBSeqId (CRef< objects::CSeq_id > seqId)
	Construct a Bioseq object for the given SRA sequence. More...

CRef< objects::CBioseq >	CreateBioseqFromOid (Uint8 oid)

void	AddSubjectsToScope (CRef< CScope > scope, CConstRef< CSeq_align_set > alnSet)
	Populate the CScope object with subject sequence Bioseqs. More...

void	FillVDBInfo (vector< CBlastFormatUtil::SDbInfo > &vecDbInfo)
	Populate the DB info list with information on open SRA runs. More...

bool	IsCSRAUtil ()

void	GetOidsFromSeqIds_WGS (const vector< string > &ids, vector< int > &oids)

bool	IsWGS ()

Public Member Functions inherited from CObject
	CObject (void)
	Constructor. More...

	CObject (const CObject &src)
	Copy constructor. More...

virtual	~CObject (void)
	Destructor. More...

CObject &	operator= (const CObject &src) THROWS_NONE
	Assignment operator. More...

bool	CanBeDeleted (void) const THROWS_NONE
	Check if object can be deleted. More...

bool	IsAllocatedInPool (void) const THROWS_NONE
	Check if object is allocated in memory pool (not system heap) More...

bool	Referenced (void) const THROWS_NONE
	Check if object is referenced. More...

bool	ReferencedOnlyOnce (void) const THROWS_NONE
	Check if object is referenced only once. More...

void	AddReference (void) const
	Add reference to object. More...

void	RemoveReference (void) const
	Remove reference to object. More...

void	ReleaseReference (void) const
	Remove reference without deleting object. More...

virtual void	DoNotDeleteThisObject (void)
	Mark this object as not allocated in heap – do not delete this object. More...

virtual void	DoDeleteThisObject (void)
	Mark this object as allocated in heap – object can be deleted. More...

void *	operator new (size_t size)
	Define new operator for memory allocation. More...

void *	operator new[] (size_t size)
	Define new[] operator for 'array' memory allocation. More...

void	operator delete (void *ptr)
	Define delete operator for memory deallocation. More...

void	operator delete[] (void *ptr)
	Define delete[] operator for memory deallocation. More...

void *	operator new (size_t size, void *place)
	Define new operator. More...

void	operator delete (void ptr, void place)
	Define delete operator. More...

void *	operator new (size_t size, CObjectMemoryPool *place)
	Define new operator using memory pool. More...

void	operator delete (void ptr, CObjectMemoryPool place)
	Define delete operator. More...

virtual void	DebugDump (CDebugDumpContext ddc, unsigned int depth) const
	Define method for dumping debug information. More...

Public Member Functions inherited from CDebugDumpable
	CDebugDumpable (void)

virtual	~CDebugDumpable (void)

void	DebugDumpText (ostream &out, const string &bundle, unsigned int depth) const

void	DebugDumpFormat (CDebugDumpFormatter &ddf, const string &bundle, unsigned int depth) const

void	DumpToConsole (void) const

Static Public Member Functions
static Uint4	SetupVDBManager ()
	Note Call this in main thread first, if you are going to instantiate this object or use any of the static menthod in a thread More...

static void	ReleaseVDBManager ()
	Call this release vdb manager if SetupManger has been explicitly called in the main thread. More...

static bool	IsSRA (const string &db_name)

static bool	IsCSRA (const string &db_name)

static IDType	VDBIdType (const CSeq_id &id)

static void	GetVDBStats (const string &strAllRuns, Uint8 &num_seqs, Uint8 &length, bool getRefStats=false)
	Fucntion to get around the OID (blastseqsrc) limit So num of seqs > int4 can be returned. More...

static void	GetVDBStats (const string &strAllRuns, Uint8 &num_seqs, Uint8 &length, Uint8 &max_seq_length, Uint8 &av_seq_length, bool getRefStats=false)

static void	GetAllStats (const string &strAllRuns, Uint8 &num_seqs, Uint8 &length, Uint8 &ref_num_seqs, Uint8 &ref_length)

static void	CheckVDBs (const vector< string > &vdbs)
	Function to check a list of dbs if they can be opened Throw an exception if any of the db cannot be opened. More...

static Uint4	GetMaxNumCSRAThread (void)

Static Public Member Functions inherited from CObject
static NCBI_XNCBI_EXPORT void	ThrowNullPointerException (void)
	Define method to throw null pointer exception. More...

static NCBI_XNCBI_EXPORT void	ThrowNullPointerException (const type_info &type)

static EAllocFillMode	GetAllocFillMode (void)

static void	SetAllocFillMode (EAllocFillMode mode)

static void	SetAllocFillMode (const string &value)
	Set mode from configuration parameter value. More...

Static Public Member Functions inherited from CDebugDumpable
static void	EnableDebugDump (bool on)

Static Public Attributes
static const Uint8	REF_SEQ_ID_MASK = (0x8000000000000000)

Static Public Attributes inherited from CObject
static const TCount	eCounterBitsCanBeDeleted = 1 << 0
	Define possible object states. More...

static const TCount	eCounterBitsInPlainHeap = 1 << 1
	Heap signature was found. More...

static const TCount	eCounterBitsPlaceMask
	Mask for 'in heap' state flags. More...

static const int	eCounterStep = 1 << 2
	Skip over the "in heap" bits. More...

static const TCount	eCounterValid = TCount(1) << (sizeof(TCount) * 8 - 2)
	Minimal value for valid objects (reference counter is zero) Must be a single bit value. More...

static const TCount	eCounterStateMask
	Valid object, and object in heap. More...

Private Member Functions
	CVDBBlastUtil (bool bCSRA, const string &strAllRuns)
	Temporary hack to get around oid limit (used by GetVDBStats) Shoudl be remove when. More...

void	x_GetSRARunAccessions (vector< string > &vecSRARunAccessions)
	Tokenize the stored whitespace-delimited string of SRA runs. More...

BlastSeqSrc *	x_MakeVDBSeqSrc ()
	Construct an SRA BlastSeqSrc object from the given strings. More...

Private Attributes
bool	m_bOwnSeqSrc
	Release the BlastSeqSrc object in destructor. More...

string	m_strAllRuns
	Space-delimited list of opened SRA run accessions. More...

BlastSeqSrc *	m_seqSrc
	Pointer to a properly initialized SRA BlastSeqSrc. More...

bool	m_isCSRAUtil

bool	m_IncludeFilteredReads

Additional Inherited Members
Protected Member Functions inherited from CObject
virtual void	DeleteThis (void)
	Virtual method "deleting" this object. More...

Detailed Description

CVDBBlastUtil.

High-level functions used for setting up and running Blast with SRAs.

This class provides several high-level functions for creating and managing the SRA BlastSeqSrc and SRA BlastSeqInfoSrc objects. It also provides conversions between OIDs and high-level sequence objects containing SRA-specific information (SeqIDs, Bioseqs).

Definition at line 66 of file vdb2blast_util.hpp.

Member Enumeration Documentation

◆ IDType

enum CVDBBlastUtil::IDType

Enumerator
eSRAId
eWGSId
eCSRALocalRefId
eCSRARefId
eUnknownId

Definition at line 165 of file vdb2blast_util.hpp.

Constructor & Destructor Documentation

◆ CVDBBlastUtil() [1/2]

CVDBBlastUtil::CVDBBlastUtil	(	const string &	strAllRuns,
		bool	bOwnSeqSrc = `false`,
		bool	bCSRA = `false`,
		bool	bIncludeFilteredReads = `false`
	)

Constructor that creates and stores the SRA BlastSeqSrc object.

Parameters

strAllRuns	Space-delimited SRA run accessions to open. [in]
bOwnSeqSrc	Release the BlastSeqSrc object in destructor. [in]

Exceptions

CException

Definition at line 280 of file vdb2blast_util.cpp.

References BlastSeqSrcGetNumSeqs(), eUnknown, m_seqSrc, NCBI_THROW, VDBSRC_OVERFLOW_RV, and x_MakeVDBSeqSrc().

◆ ~CVDBBlastUtil()

CVDBBlastUtil::~CVDBBlastUtil ( )

virtual

Destructor.

Definition at line 293 of file vdb2blast_util.cpp.

References BlastSeqSrcFree(), m_bOwnSeqSrc, and m_seqSrc.

◆ CVDBBlastUtil() [2/2]

CVDBBlastUtil::CVDBBlastUtil	(	bool	bCSRA,
		const string &	strAllRuns
	)

private

Temporary hack to get around oid limit (used by GetVDBStats) Shoudl be remove when.

Definition at line 661 of file vdb2blast_util.cpp.

References m_seqSrc, and x_MakeVDBSeqSrc().

Member Function Documentation

◆ AddSubjectsToScope()

void CVDBBlastUtil::AddSubjectsToScope	(	CRef< CScope >	scope,
		CConstRef< CSeq_align_set >	alnSet
	)

Populate the CScope object with subject sequence Bioseqs.

This function must be called to populate the CScope object with the Bioseqs of every SRA sequence present in the Blast results. Without these Bioseqs, the Blast formatter would have no way to access and display the subject sequence data for the alignments.

Parameters

scope	CScope object to populate [in]
alnSet	Set of alignments representing the Blast results [in]

Exceptions

CException

Definition at line 623 of file vdb2blast_util.cpp.

References CScope::AddBioseq(), CSeq_id::Assign(), CreateBioseqFromVDBSeqId(), CScope::eExist_Get, CConstRef< C, Locker >::Empty(), CSeq_align_set_Base::Get(), CSeq_align::GetSeq_id(), and CScope::kPriority_Default.

◆ CheckVDBs()

void CVDBBlastUtil::CheckVDBs ( const vector< string > & vdbs )

static

Function to check a list of dbs if they can be opened Throw an exception if any of the db cannot be opened.

Definition at line 700 of file vdb2blast_util.cpp.

References ctll::empty(), free(), AutoPtr< X, Del >::get(), kEmptyStr, NCBI_THROW, SRABlastSeqSrcInit(), and strdup.

Referenced by CVDBAliasNode::x_ResolveVDBList().

◆ CreateBioseqFromOid()

CRef< CBioseq > CVDBBlastUtil::CreateBioseqFromOid ( Uint8 oid )

◆ CreateBioseqFromVDBSeqId()

CRef< CBioseq > CVDBBlastUtil::CreateBioseqFromVDBSeqId ( CRef< objects::CSeq_id > seqId )

Construct a Bioseq object for the given SRA sequence.

This function takes a SeqID indentifying an SRA sequence and constructs a Bioseq object with the same SeqID and the actual sequence data stored in IUPACNA format.

Parameters

seqId SeqID of the SRA sequence [in]

Returns: Newly constructed Bioseq for the given SRA sequence.

Exceptions

CException

Definition at line 459 of file vdb2blast_util.cpp.

References _BlastSeqSrcImpl_GetDataStructure(), CSeq_data_Base::e_Iupacna, CSeq_inst_Base::eMol_dna, CSeq_inst_Base::eRepr_raw, eUnknown, free(), CSeq_inst_Base::GetLength(), GetOIDFromVDBSeqId(), m_seqSrc, NCBI_THROW, CRef< C, Locker >::Reset(), CBioseq_Base::SetDescr(), CBioseq_Base::SetId(), CBioseq_Base::SetInst(), CSeq_inst_Base::SetLength(), CSeq_inst_Base::SetMol(), CSeq_inst_Base::SetRepr(), CSeq_inst_Base::SetSeq_data(), CSeqdesc_Base::SetTitle(), NStr::UInt8ToString(), NStr::UIntToString(), VDBSRC_FormatErrorMsg(), VDBSRC_Get4naSequenceAsString(), VDBSRC_InitEmptyErrorMsg(), and VDBSRC_ReleaseErrorMsg().

Referenced by AddSubjectsToScope(), and CVdbFastaExtractor::Write().

◆ FillVDBInfo()

void CVDBBlastUtil::FillVDBInfo ( vector< CBlastFormatUtil::SDbInfo > & vecDbInfo )

Populate the DB info list with information on open SRA runs.

Parameters

vecDbInfo DB info list to populate [out]

Exceptions

CException

Definition at line 644 of file vdb2blast_util.cpp.

References BlastSeqSrcGetName(), BlastSeqSrcGetNumSeqs(), BlastSeqSrcGetTotLen(), eUnknown, m_seqSrc, NCBI_THROW, and NStr::Replace().

◆ GetAllStats()

void CVDBBlastUtil::GetAllStats	(	const string &	strAllRuns,
		Uint8 &	num_seqs,
		Uint8 &	length,
		Uint8 &	ref_num_seqs,
		Uint8 &	ref_length
	)

static

Definition at line 769 of file vdb2blast_util.cpp.

References _BlastSeqSrcImpl_GetDataStructure(), eUnknown, SVDBSRC_ErrMsg::isError, NCBI_THROW, SVBDSRC_SeqSrc_Data::numSeqs, VDBSRC_GetTotSeqLen(), VDBSRC_InitEmptyErrorMsg(), and VDBSRC_MakeCSRASeqSrcFromSRASeqSrc().

Referenced by CLocalVDBBlast::PreprocessDBs().

◆ GetMaxNumCSRAThread()

Uint4 CVDBBlastUtil::GetMaxNumCSRAThread ( void )

static

Definition at line 822 of file vdb2blast_util.cpp.

References CSystemInfo::GetTotalPhysicalMemorySize(), and VDB_2NA_CHUNK_BUF_SIZE.

Referenced by CLocalVDBBlast::PreprocessDBs().

◆ GetOIDFromVDBSeqId()

Uint4 CVDBBlastUtil::GetOIDFromVDBSeqId ( CRef< objects::CSeq_id > seqId )

Get the ordinal number (OID) for the given SRA sequence.

This function takes a SeqID identifying an SRA sequence (a single read, e.g. gnl|SRA|SRR000002.123691.1) and converts it to the internal ordinal number used by the SRA BlastSeqSrc.

Parameters

seqId SeqID of the SRA sequence [in]

Returns: OID corresponding to the given SRA sequence.

Exceptions

CException

Definition at line 338 of file vdb2blast_util.cpp.

References _BlastSeqSrcImpl_GetDataStructure(), CDbtag_Base::CanGetDb(), CDbtag_Base::CanGetTag(), eUnknown, CSeq_id_Base::GetGeneral(), CSeq_id::GetSeqIdString(), CObject_id_Base::GetStr(), CDbtag_Base::GetTag(), CSeq_id_Base::IsGeneral(), CObject_id_Base::IsStr(), kEmptyStr, m_seqSrc, NCBI_THROW, NULL, and VDBSRC_GetOIDFromReadName().

Referenced by CreateBioseqFromVDBSeqId(), and CVdbFastaExtractor::Write().

◆ GetOidsFromSeqIds_WGS()

void CVDBBlastUtil::GetOidsFromSeqIds_WGS	(	const vector< string > &	ids,
		vector< int > &	oids
	)

Definition at line 832 of file vdb2blast_util.cpp.

References _BlastSeqSrcImpl_GetDataStructure(), Empty(), eUnknown, CSeq_id::GetSeqIdString(), GetSRASeqSrc(), GetVDBSeqIdFromOID(), i, NCBI_THROW, and SVBDSRC_SeqSrc_Data::numSeqs.

◆ GetSRASeqInfoSrc()

CRef< IBlastSeqInfoSrc > CVDBBlastUtil::GetSRASeqInfoSrc ( )

Return the SRA BlastSeqInfoSrc object (create if none exists).

Returns: CRef to the SRA BlastSeqInfoSrc object.

Exceptions

CException

Definition at line 313 of file vdb2blast_util.cpp.

References eUnknown, m_seqSrc, and NCBI_THROW.

Referenced by s_RunLocalVDBSearch(), and s_RunPsiVDBSearch().

◆ GetSRASeqSrc()

BlastSeqSrc * CVDBBlastUtil::GetSRASeqSrc ( )

Return the stored SRA BlastSeqSrc object.

Returns: Pointer to the SRA BlastSeqSrc object.

Exceptions

CException

Definition at line 302 of file vdb2blast_util.cpp.

References eUnknown, m_seqSrc, and NCBI_THROW.

Referenced by CVdbFastaExtractor::DumpAll(), CVDBSeqInfoSrc::GetLength(), GetOidsFromSeqIds_WGS(), IsWGS(), s_RunLocalVDBSearch(), s_RunPsiVDBSearch(), and CVDBSeqInfoSrc::Size().

◆ GetVDBSeqIdFromOID()

CRef< CSeq_id > CVDBBlastUtil::GetVDBSeqIdFromOID ( Uint4 oid )

Get the SRA sequence SeqID given its ordinal number (OID).

This function returns the SeqID identifying an SRA sequence (a single read, e.g. gnl|SRA|SRR000002.123691.1) given its internal ordinal number (OID) used by the SRA BlastSeqSrc. It is guaranteed that one will get the same results by calling the GetId method of the BlastSeqInfoSrc object and taking the first General SeqId in the returned list.

Parameters

oid	OID of the SRA sequence [in]

Returns: corresponding SeqID of the SRA sequence.

Exceptions

CException

Definition at line 403 of file vdb2blast_util.cpp.

References _BlastSeqSrcImpl_GetDataStructure(), CSeq_id::eAcc_unknown, eUnknown, NStr::Find(), FindBestChoice(), CSeq_id::fParse_RawText, NStr::fSplit_Tokenize, CSeq_id::IdentifyAccession(), m_isCSRAUtil, m_seqSrc, NCBI_THROW, NPOS, CSeq_id::ParseFastaIds(), CRef< C, Locker >::Reset(), s_IsWGSId(), CSeq_id::Score(), NStr::Split(), string, tmp, and VDBSRC_GetReadNameForOID().

Referenced by CreateBioseqFromOid(), CVDBSeqInfoSrc::GetId(), and GetOidsFromSeqIds_WGS().

◆ GetVDBStats() [1/2]

void CVDBBlastUtil::GetVDBStats	(	const string &	strAllRuns,
		Uint8 &	num_seqs,
		Uint8 &	length,
		bool	getRefStats = `false`
	)

static

Fucntion to get around the OID (blastseqsrc) limit So num of seqs > int4 can be returned.

Definition at line 667 of file vdb2blast_util.cpp.

References _BlastSeqSrcImpl_GetDataStructure(), eUnknown, NCBI_THROW, SVBDSRC_SeqSrc_Data::numSeqs, and VDBSRC_GetTotSeqLen().

Referenced by CLocalVDBBlast::PreprocessDBs(), s_FillDBInfo(), and CBlastVdbCmdApp::x_PrintBlastDatabaseInformation().

◆ GetVDBStats() [2/2]

void CVDBBlastUtil::GetVDBStats	(	const string &	strAllRuns,
		Uint8 &	num_seqs,
		Uint8 &	length,
		Uint8 &	max_seq_length,
		Uint8 &	av_seq_length,
		bool	getRefStats = `false`
	)