Functions
boost::uint32_t	getAtomCode (const Atom *atom, unsigned int branchSubtract=0)
boost::uint32_t	getAtomPairCode (boost::uint32_t codeI, boost::uint32_t codeJ, unsigned int dist)
SparseIntVect< boost::int32_t > *	getAtomPairFingerprint (const ROMol &mol, unsigned int minLength, unsigned int maxLength, const std::vector< boost::uint32_t > fromAtoms=0, const std::vector< boost::uint32_t > ignoreAtoms=0)
	returns the atom-pair fingerprint for a molecule
SparseIntVect< boost::int32_t > *	getAtomPairFingerprint (const ROMol &mol, const std::vector< boost::uint32_t > fromAtoms=0, const std::vector< boost::uint32_t > ignoreAtoms=0)
SparseIntVect< boost::int32_t > *	getHashedAtomPairFingerprint (const ROMol &mol, unsigned int nBits=2048, unsigned int minLength=1, unsigned int maxLength=maxPathLen-1, const std::vector< boost::uint32_t > fromAtoms=0, const std::vector< boost::uint32_t > ignoreAtoms=0)
	returns the hashed atom-pair fingerprint for a molecule
ExplicitBitVect *	getHashedAtomPairFingerprintAsBitVect (const ROMol &mol, unsigned int nBits=2048, unsigned int minLength=1, unsigned int maxLength=maxPathLen-1, const std::vector< boost::uint32_t > fromAtoms=0, const std::vector< boost::uint32_t > ignoreAtoms=0, unsigned int nBitsPerEntry=4)
	returns the hashed atom-pair fingerprint for a molecule as a bit vector
boost::uint64_t	getTopologicalTorsionCode (const std::vector< boost::uint32_t > &atomCodes)
SparseIntVect< boost::int64_t > *	getTopologicalTorsionFingerprint (const ROMol &mol, unsigned int targetSize=4, const std::vector< boost::uint32_t > fromAtoms=0, const std::vector< boost::uint32_t > ignoreAtoms=0)
	returns the topological-torsion fingerprint for a molecule
SparseIntVect< boost::int64_t > *	getHashedTopologicalTorsionFingerprint (const ROMol &mol, unsigned int nBits=2048, unsigned int targetSize=4, const std::vector< boost::uint32_t > fromAtoms=0, const std::vector< boost::uint32_t > ignoreAtoms=0)
	returns a hashed topological-torsion fingerprint for a molecule
ExplicitBitVect *	getHashedTopologicalTorsionFingerprintAsBitVect (const ROMol &mol, unsigned int nBits=2048, unsigned int targetSize=4, const std::vector< boost::uint32_t > fromAtoms=0, const std::vector< boost::uint32_t > ignoreAtoms=0, unsigned int nBitsPerEntry=4)
	returns a hashed topological-torsion fingerprint for a molecule as a bit vector
Variables
const std::string	atomPairsVersion = "1.1.0"
const unsigned int	numTypeBits = 4
const unsigned int	atomNumberTypes [1<< numTypeBits] = {5,6,7,8,9,14,15,16,17,33,34,35,51,52,43}
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	codeSize = numTypeBits+numPiBits+numBranchBits
const unsigned int	numPathBits = 5
const unsigned int	maxPathLen = (1<<numPathBits)-1
const unsigned int	numAtomPairFingerprintBits = numPathBits+2*codeSize

Function Documentation

boost::uint32_t RDKit::AtomPairs::getAtomCode	(	const Atom *	atom,
		unsigned int	branchSubtract = `0`
	)

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)

boost::uint32_t RDKit::AtomPairs::getAtomPairCode	(	boost::uint32_t	codeI,
		boost::uint32_t	codeJ,
		unsigned int	dist
	)

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

SparseIntVect<boost::int32_t>* RDKit::AtomPairs::getAtomPairFingerprint	(	const ROMol &	mol,
		const std::vector< boost::uint32_t > *	fromAtoms = `0`,
		const std::vector< boost::uint32_t > *	ignoreAtoms = `0`
	)

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

SparseIntVect<boost::int32_t>* RDKit::AtomPairs::getAtomPairFingerprint	(	const ROMol &	mol,
		unsigned int	minLength,
		unsigned int	maxLength,
		const std::vector< boost::uint32_t > *	fromAtoms = `0`,
		const std::vector< boost::uint32_t > *	ignoreAtoms = `0`
	)

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

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

SparseIntVect<boost::int32_t>* RDKit::AtomPairs::getHashedAtomPairFingerprint	(	const ROMol &	mol,
		unsigned int	nBits = `2048`,
		unsigned int	minLength = `1`,
		unsigned int	maxLength = `maxPathLen-1`,
		const std::vector< boost::uint32_t > *	fromAtoms = `0`,
		const std::vector< boost::uint32_t > *	ignoreAtoms = `0`
	)

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

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

ExplicitBitVect* RDKit::AtomPairs::getHashedAtomPairFingerprintAsBitVect	(	const ROMol &	mol,
		unsigned int	nBits = `2048`,
		unsigned int	minLength = `1`,
		unsigned int	maxLength = `maxPathLen-1`,
		const std::vector< boost::uint32_t > *	fromAtoms = `0`,
		const std::vector< boost::uint32_t > *	ignoreAtoms = `0`,
		unsigned int	nBitsPerEntry = `4`
	)

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
	nBitsPerEntry,:	number of bits to use in simulating counts

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

SparseIntVect<boost::int64_t >* RDKit::AtomPairs::getHashedTopologicalTorsionFingerprint	(	const ROMol &	mol,
		unsigned int	nBits = `2048`,
		unsigned int	targetSize = `4`,
		const std::vector< boost::uint32_t > *	fromAtoms = `0`,
		const std::vector< boost::uint32_t > *	ignoreAtoms = `0`
	)

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

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

ExplicitBitVect* RDKit::AtomPairs::getHashedTopologicalTorsionFingerprintAsBitVect	(	const ROMol &	mol,
		unsigned int	nBits = `2048`,
		unsigned int	targetSize = `4`,
		const std::vector< boost::uint32_t > *	fromAtoms = `0`,
		const std::vector< boost::uint32_t > *	ignoreAtoms = `0`,
		unsigned int	nBitsPerEntry = `4`
	)

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
	nBitsPerEntry,:	number of bits to use in simulating counts

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

boost::uint64_t RDKit::AtomPairs::getTopologicalTorsionCode ( const std::vector< boost::uint32_t > & atomCodes )

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

Parameters:

atomCodes

the vector of atom hashes

SparseIntVect<boost::int64_t >* RDKit::AtomPairs::getTopologicalTorsionFingerprint	(	const ROMol &	mol,
		unsigned int	targetSize = `4`,
		const std::vector< boost::uint32_t > *	fromAtoms = `0`,
		const std::vector< boost::uint32_t > *	ignoreAtoms = `0`
	)

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