Functions
RDKIT_FINGERPRINTS_EXPORT SparseIntVect< std::int32_t > *	getAtomPairFingerprint (const ROMol &mol, unsigned int minLength, unsigned int maxLength, const std::vector< std::uint32_t > fromAtoms=nullptr, const std::vector< std::uint32_t > ignoreAtoms=nullptr, const std::vector< std::uint32_t > *atomInvariants=nullptr, bool includeChirality=false, bool use2D=true, int confId=-1)
	returns the atom-pair fingerprint for a molecule

RDKIT_FINGERPRINTS_EXPORT SparseIntVect< std::int32_t > *	getAtomPairFingerprint (const ROMol &mol, const std::vector< std::uint32_t > fromAtoms=nullptr, const std::vector< std::uint32_t > ignoreAtoms=nullptr, const std::vector< std::uint32_t > *atomInvariants=nullptr, bool includeChirality=false, bool use2D=true, int confId=-1)
	This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.

RDKIT_FINGERPRINTS_EXPORT SparseIntVect< std::int32_t > *	getHashedAtomPairFingerprint (const ROMol &mol, unsigned int nBits=2048, unsigned int minLength=1, unsigned int maxLength=maxPathLen - 1, const std::vector< std::uint32_t > fromAtoms=nullptr, const std::vector< std::uint32_t > ignoreAtoms=nullptr, const std::vector< std::uint32_t > *atomInvariants=nullptr, bool includeChirality=false, bool use2D=true, int confId=-1)
	returns the hashed atom-pair fingerprint for a molecule

RDKIT_FINGERPRINTS_EXPORT ExplicitBitVect *	getHashedAtomPairFingerprintAsBitVect (const ROMol &mol, unsigned int nBits=2048, unsigned int minLength=1, unsigned int maxLength=maxPathLen - 1, const std::vector< std::uint32_t > fromAtoms=nullptr, const std::vector< std::uint32_t > ignoreAtoms=nullptr, const std::vector< std::uint32_t > *atomInvariants=nullptr, unsigned int nBitsPerEntry=4, bool includeChirality=false, bool use2D=true, int confId=-1)
	returns the hashed atom-pair fingerprint for a molecule as a bit vector

RDKIT_FINGERPRINTS_EXPORT SparseIntVect< boost::int64_t > *	getTopologicalTorsionFingerprint (const ROMol &mol, unsigned int targetSize=4, const std::vector< std::uint32_t > fromAtoms=nullptr, const std::vector< std::uint32_t > ignoreAtoms=nullptr, const std::vector< std::uint32_t > *atomInvariants=nullptr, bool includeChirality=false)
	returns the topological-torsion fingerprint for a molecule

RDKIT_FINGERPRINTS_EXPORT SparseIntVect< boost::int64_t > *	getHashedTopologicalTorsionFingerprint (const ROMol &mol, unsigned int nBits=2048, unsigned int targetSize=4, const std::vector< std::uint32_t > fromAtoms=nullptr, const std::vector< std::uint32_t > ignoreAtoms=nullptr, const std::vector< std::uint32_t > *atomInvariants=nullptr, bool includeChirality=false)
	returns a hashed topological-torsion fingerprint for a molecule

RDKIT_FINGERPRINTS_EXPORT ExplicitBitVect *	getHashedTopologicalTorsionFingerprintAsBitVect (const ROMol &mol, unsigned int nBits=2048, unsigned int targetSize=4, const std::vector< std::uint32_t > fromAtoms=nullptr, const std::vector< std::uint32_t > ignoreAtoms=nullptr, const std::vector< std::uint32_t > *atomInvariants=nullptr, unsigned int nBitsPerEntry=4, bool includeChirality=false)

RDKIT_FINGERPRINTS_EXPORT std::uint32_t	getAtomCode (const Atom *atom, unsigned int branchSubtract=0, bool includeChirality=false)

RDKIT_FINGERPRINTS_EXPORT std::uint32_t	getAtomPairCode (std::uint32_t codeI, std::uint32_t codeJ, unsigned int dist, bool includeChirality=false)

RDKIT_FINGERPRINTS_EXPORT std::uint64_t	getTopologicalTorsionCode (const std::vector< std::uint32_t > &atomCodes, bool includeChirality=false)

RDKIT_FINGERPRINTS_EXPORT std::uint32_t	getTopologicalTorsionHash (const std::vector< std::uint32_t > &pathCodes)

Variables
const std::string	atomPairsVersion = "1.1.0"

const unsigned int	numTypeBits = 4

const unsigned int	atomNumberTypes [1<< numTypeBits]

const unsigned int	numPiBits = 2

const unsigned int	maxNumPi = (1 << numPiBits) - 1

const unsigned int	numBranchBits = 3

const unsigned int	maxNumBranches = (1 << numBranchBits) - 1

const unsigned int	numChiralBits = 2

const unsigned int	codeSize = numTypeBits + numPiBits + numBranchBits

const unsigned int	numPathBits = 5

const unsigned int	maxPathLen = (1 << numPathBits) - 1

const unsigned int	numAtomPairFingerprintBits

Function Documentation

◆ getAtomCode()

RDKIT_FINGERPRINTS_EXPORT std::uint32_t RDKit::AtomPairs::getAtomCode	(	const Atom *	atom,
		unsigned int	branchSubtract = `0`,
		bool	includeChirality = `false`
	)

returns a numeric code for the atom (the atom's hash in the atom-pair scheme)

Parameters

atom	the atom to be considered
branchSubtract	(optional) a constant to subtract from the number of neighbors when the hash is calculated (used in the topological torsions code)
includeChirality	toggles the inclusions of bits indicating R/S chirality

◆ getAtomPairCode()

RDKIT_FINGERPRINTS_EXPORT std::uint32_t RDKit::AtomPairs::getAtomPairCode	(	std::uint32_t	codeI,
		std::uint32_t	codeJ,
		unsigned int	dist,
		bool	includeChirality = `false`
	)

returns an atom pair hash based on two atom hashes and the distance between the atoms.

Parameters

codeI	the hash for the first atom
codeJ	the hash for the second atom
dist	the distance (number of bonds) between the two atoms
includeChirality	toggles the inclusions of bits indicating R/S chirality

◆ getAtomPairFingerprint() [1/2]

RDKIT_FINGERPRINTS_EXPORT SparseIntVect< std::int32_t > * RDKit::AtomPairs::getAtomPairFingerprint	(	const ROMol &	mol,
		const std::vector< std::uint32_t > *	fromAtoms = `nullptr`,
		const std::vector< std::uint32_t > *	ignoreAtoms = `nullptr`,
		const std::vector< std::uint32_t > *	atomInvariants = `nullptr`,
		bool	includeChirality = `false`,
		bool	use2D = `true`,
		int	confId = `-1`
	)

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.

◆ getAtomPairFingerprint() [2/2]

RDKIT_FINGERPRINTS_EXPORT SparseIntVect< std::int32_t > * RDKit::AtomPairs::getAtomPairFingerprint	(	const ROMol &	mol,
		unsigned int	minLength,
		unsigned int	maxLength,
		const std::vector< std::uint32_t > *	fromAtoms = `nullptr`,
		const std::vector< std::uint32_t > *	ignoreAtoms = `nullptr`,
		const std::vector< std::uint32_t > *	atomInvariants = `nullptr`,
		bool	includeChirality = `false`,
		bool	use2D = `true`,
		int	confId = `-1`
	)

returns the atom-pair fingerprint for a molecule

The algorithm used is described here: R.E. Carhart, D.H. Smith, R. Venkataraghavan; "Atom Pairs as Molecular Features in Structure-Activity Studies: Definition and Applications" JCICS 25, 64-73 (1985).

Parameters

mol	the molecule to be fingerprinted
minLength	minimum distance between atoms to be considered in a pair. Default is 1 bond.
maxLength	maximum distance between atoms to be considered in a pair. Default is maxPathLen-1 bonds.
fromAtoms	if provided, only atom pairs that involve the specified atoms will be included in the fingerprint
ignoreAtoms	if provided, any atom pairs that include the specified atoms will not be included in the fingerprint
atomInvariants	a list of invariants to use for the atom hashes note: only the first `codeSize` bits of each invariant are used.
includeChirality	if set, chirality will be used in the atom invariants (note: this is ignored if atomInvariants are provided)
use2D	if set, the 2D (topological) distance matrix is used.
confId	the conformation to use if 3D distances are being used

Returns: a pointer to the fingerprint. The client is responsible for calling delete on this.

◆ getHashedAtomPairFingerprint()

RDKIT_FINGERPRINTS_EXPORT SparseIntVect< std::int32_t > * RDKit::AtomPairs::getHashedAtomPairFingerprint	(	const ROMol &	mol,
		unsigned int	nBits = `2048`,
		unsigned int	minLength = `1`,
		unsigned int	maxLength = `maxPathLen - 1`,
		const std::vector< std::uint32_t > *	fromAtoms = `nullptr`,
		const std::vector< std::uint32_t > *	ignoreAtoms = `nullptr`,
		const std::vector< std::uint32_t > *	atomInvariants = `nullptr`,
		bool	includeChirality = `false`,
		bool	use2D = `true`,
		int	confId = `-1`
	)

returns the hashed atom-pair fingerprint for a molecule

Parameters

mol	the molecule to be fingerprinted
nBits	the length of the fingerprint to generate
minLength	minimum distance between atoms to be considered in a pair. Default is 1 bond.
maxLength	maximum distance between atoms to be considered in a pair. Default is maxPathLen-1 bonds.
fromAtoms	if provided, only atom pairs that involve the specified atoms will be included in the fingerprint
ignoreAtoms	if provided, any atom pairs that include the specified atoms will not be included in the fingerprint
atomInvariants	a list of invariants to use for the atom hashes note: only the first `codeSize` bits of each invariant are used.
includeChirality	if set, chirality will be used in the atom invariants (note: this is ignored if atomInvariants are provided)
use2D	if set, the 2D (topological) distance matrix is used.

Returns: a pointer to the fingerprint. The client is responsible for calling delete on this.

◆ getHashedAtomPairFingerprintAsBitVect()

RDKIT_FINGERPRINTS_EXPORT ExplicitBitVect * RDKit::AtomPairs::getHashedAtomPairFingerprintAsBitVect	(	const ROMol &	mol,
		unsigned int	nBits = `2048`,
		unsigned int	minLength = `1`,
		unsigned int	maxLength = `maxPathLen - 1`,
		const std::vector< std::uint32_t > *	fromAtoms = `nullptr`,
		const std::vector< std::uint32_t > *	ignoreAtoms = `nullptr`,
		const std::vector< std::uint32_t > *	atomInvariants = `nullptr`,
		unsigned int	nBitsPerEntry = `4`,
		bool	includeChirality = `false`,
		bool	use2D = `true`,
		int	confId = `-1`
	)

returns the hashed atom-pair fingerprint for a molecule as a bit vector

Parameters

mol	the molecule to be fingerprinted
nBits	the length of the fingerprint to generate
minLength	minimum distance between atoms to be considered in a pair. Default is 1 bond.
maxLength	maximum distance between atoms to be considered in a pair. Default is maxPathLen-1 bonds.
fromAtoms	if provided, only atom pairs that involve the specified atoms will be included in the fingerprint
ignoreAtoms	if provided, any atom pairs that include the specified atoms will not be included in the fingerprint
atomInvariants	a list of invariants to use for the atom hashes note: only the first `codeSize` bits of each invariant are used.
nBitsPerEntry	number of bits to use in simulating counts
includeChirality	if set, chirality will be used in the atom invariants (note: this is ignored if atomInvariants are provided)
use2D	if set, the 2D (topological) distance matrix is used.
confId	the conformation to use if 3D distances are being used

Returns: a pointer to the fingerprint. The client is responsible for calling delete on this.

◆ getHashedTopologicalTorsionFingerprint()

RDKIT_FINGERPRINTS_EXPORT SparseIntVect< boost::int64_t > * RDKit::AtomPairs::getHashedTopologicalTorsionFingerprint	(	const ROMol &	mol,
		unsigned int	nBits = `2048`,
		unsigned int	targetSize = `4`,
		const std::vector< std::uint32_t > *	fromAtoms = `nullptr`,
		const std::vector< std::uint32_t > *	ignoreAtoms = `nullptr`,
		const std::vector< std::uint32_t > *	atomInvariants = `nullptr`,
		bool	includeChirality = `false`
	)

returns a hashed topological-torsion fingerprint for a molecule

The algorithm used is described here: R. Nilakantan, N. Bauman, J. S. Dixon, R. Venkataraghavan; "Topological Torsion: A New Molecular Descriptor for SAR Applications. Comparison with Other Descriptors" JCICS 27, 82-85 (1987).

Parameters

mol	the molecule to be fingerprinted
nBits	number of bits to include in the fingerprint
targetSize	the number of atoms to include in the "torsions"
fromAtoms	if provided, only torsions that start or end at the specified atoms will be included in the fingerprint
ignoreAtoms	if provided, any torsions that include the specified atoms will not be included in the fingerprint
atomInvariants	a list of invariants to use for the atom hashes note: only the first `codeSize` bits of each invariant are used.
includeChirality	if set, chirality will be used in the atom invariants (note: this is ignored if atomInvariants are provided)

Returns: a pointer to the fingerprint. The client is responsible for calling delete on this.

◆ getHashedTopologicalTorsionFingerprintAsBitVect()

RDKIT_FINGERPRINTS_EXPORT ExplicitBitVect * RDKit::AtomPairs::getHashedTopologicalTorsionFingerprintAsBitVect	(	const ROMol &	mol,
		unsigned int	nBits = `2048`,
		unsigned int	targetSize = `4`,
		const std::vector< std::uint32_t > *	fromAtoms = `nullptr`,
		const std::vector< std::uint32_t > *	ignoreAtoms = `nullptr`,
		const std::vector< std::uint32_t > *	atomInvariants = `nullptr`,
		unsigned int	nBitsPerEntry = `4`,
		bool	includeChirality = `false`
	)

returns a hashed topological-torsion fingerprint for a molecule as a bit vector

Parameters

mol	the molecule to be fingerprinted
nBits	number of bits to include in the fingerprint
targetSize	the number of atoms to include in the "torsions"
fromAtoms	if provided, only torsions that start or end at the specified atoms will be included in the fingerprint
ignoreAtoms	if provided, any torsions that include the specified atoms will not be included in the fingerprint
atomInvariants	a list of invariants to use for the atom hashes note: only the first `codeSize` bits of each invariant are used.
nBitsPerEntry	number of bits to use in simulating counts
includeChirality	if set, chirality will be used in the atom invariants (note: this is ignored if atomInvariants are provided)

Returns: a pointer to the fingerprint. The client is responsible for calling delete on this.

◆ getTopologicalTorsionCode()

RDKIT_FINGERPRINTS_EXPORT std::uint64_t RDKit::AtomPairs::getTopologicalTorsionCode	(	const std::vector< std::uint32_t > &	atomCodes,
		bool	includeChirality = `false`
	)

returns an topological torsion hash based on the atom hashes passed in

Parameters

atomCodes the vector of atom hashes

◆ getTopologicalTorsionFingerprint()

RDKIT_FINGERPRINTS_EXPORT SparseIntVect< boost::int64_t > * RDKit::AtomPairs::getTopologicalTorsionFingerprint	(	const ROMol &	mol,
		unsigned int	targetSize = `4`,
		const std::vector< std::uint32_t > *	fromAtoms = `nullptr`,
		const std::vector< std::uint32_t > *	ignoreAtoms = `nullptr`,
		const std::vector< std::uint32_t > *	atomInvariants = `nullptr`,
		bool	includeChirality = `false`
	)

returns the topological-torsion fingerprint for a molecule

The algorithm used is described here: R. Nilakantan, N. Bauman, J. S. Dixon, R. Venkataraghavan; "Topological Torsion: A New Molecular Descriptor for SAR Applications. Comparison with Other Descriptors" JCICS 27, 82-85 (1987).

Parameters

mol	the molecule to be fingerprinted
targetSize	the number of atoms to include in the "torsions"
fromAtoms	if provided, only torsions that start or end at the specified atoms will be included in the fingerprint
ignoreAtoms	if provided, any torsions that include the specified atoms will not be included in the fingerprint
atomInvariants	a list of invariants to use for the atom hashes note: only the first `codeSize` bits of each invariant are used.
includeChirality	if set, chirality will be used in the atom invariants (note: this is ignored if atomInvariants are provided)

Returns: a pointer to the fingerprint. The client is responsible for calling delete on this.

◆ getTopologicalTorsionHash()

RDKIT_FINGERPRINTS_EXPORT std::uint32_t RDKit::AtomPairs::getTopologicalTorsionHash ( const std::vector< std::uint32_t > & pathCodes )

Variable Documentation

◆ atomNumberTypes

const unsigned int RDKit::AtomPairs::atomNumberTypes[1<< numTypeBits]

Initial value:

= {

5, 6, 7, 8, 9, 14, 15, 16, 17, 33, 34, 35, 51, 52, 43}

Definition at line 29 of file FingerprintUtil.h.

◆ atomPairsVersion

const std::string RDKit::AtomPairs::atomPairsVersion = "1.1.0"

Definition at line 44 of file AtomPairs.h.

◆ codeSize

const unsigned int RDKit::AtomPairs::codeSize = numTypeBits + numPiBits + numBranchBits

Definition at line 36 of file FingerprintUtil.h.

◆ maxNumBranches

const unsigned int RDKit::AtomPairs::maxNumBranches = (1 << numBranchBits) - 1

Definition at line 34 of file FingerprintUtil.h.

◆ maxNumPi

const unsigned int RDKit::AtomPairs::maxNumPi = (1 << numPiBits) - 1

Definition at line 32 of file FingerprintUtil.h.

◆ maxPathLen

const unsigned int RDKit::AtomPairs::maxPathLen = (1 << numPathBits) - 1

Definition at line 38 of file FingerprintUtil.h.

◆ numAtomPairFingerprintBits

const unsigned int RDKit::AtomPairs::numAtomPairFingerprintBits

Initial value:

=

numPathBits + 2 * codeSize

RDKit::AtomPairs::numPathBits

const unsigned int numPathBits

Definition FingerprintUtil.h:37

RDKit::AtomPairs::codeSize

const unsigned int codeSize

Definition FingerprintUtil.h:36

Definition at line 39 of file FingerprintUtil.h.

◆ numBranchBits

const unsigned int RDKit::AtomPairs::numBranchBits = 3

Definition at line 33 of file FingerprintUtil.h.

◆ numChiralBits

const unsigned int RDKit::AtomPairs::numChiralBits = 2

Definition at line 35 of file FingerprintUtil.h.

◆ numPathBits

const unsigned int RDKit::AtomPairs::numPathBits = 5

Definition at line 37 of file FingerprintUtil.h.

◆ numPiBits

const unsigned int RDKit::AtomPairs::numPiBits = 2

Definition at line 31 of file FingerprintUtil.h.

◆ numTypeBits

const unsigned int RDKit::AtomPairs::numTypeBits = 4

Definition at line 28 of file FingerprintUtil.h.

Functions

Variables

Function Documentation

◆ getAtomCode()

◆ getAtomPairCode()

◆ getAtomPairFingerprint() [1/2]

◆ getAtomPairFingerprint() [2/2]

◆ getHashedAtomPairFingerprint()

◆ getHashedAtomPairFingerprintAsBitVect()

◆ getHashedTopologicalTorsionFingerprint()

◆ getHashedTopologicalTorsionFingerprintAsBitVect()

◆ getTopologicalTorsionCode()

◆ getTopologicalTorsionFingerprint()

◆ getTopologicalTorsionHash()

Variable Documentation

◆ atomNumberTypes

◆ atomPairsVersion

◆ codeSize

◆ maxNumBranches

◆ maxNumPi

◆ maxPathLen

◆ numAtomPairFingerprintBits

◆ numBranchBits

◆ numChiralBits

◆ numPathBits

◆ numPiBits

◆ numTypeBits