# fingerprint module¶

2016.11.15

@author: Zhijiang Yao and Dongsheng Cao

fingerprint.CalculateAtomPairsFingerprint(mol)[source]

Calculate atom pairs fingerprints

Usage:

result=CalculateAtomPairsFingerprint(mol)

Input: mol is a molecule object.

Output: result is a tuple form. The first is the number of

fingerprints. The second is a dict form whose keys are the

position which this molecule has some substructure. The third

is the DataStructs which is used for calculating the similarity.

fingerprint.CalculateDaylightFingerprint(mol)[source]

Calculate Daylight-like fingerprint or topological fingerprint

(2048 bits).

Usage:

result=CalculateDaylightFingerprint(mol)

Input: mol is a molecule object.

Output: result is a tuple form. The first is the number of

fingerprints. The second is a dict form whose keys are the

position which this molecule has some substructure. The third

is the DataStructs which is used for calculating the similarity.

fingerprint.CalculateECFP2Fingerprint(mol, radius=1)[source]

Calculate ECFP2

Usage:

result=CalculateECFP2Fingerprint(mol)

Input: mol is a molecule object.

Output: result is a tuple form. The first is the vector of

fingerprints. The second is a dict form whose keys are the

position which this molecule has some substructure. The third

is the DataStructs which is used for calculating the similarity.

fingerprint.CalculateECFP4Fingerprint(mol, radius=2)[source]

Calculate ECFP4

Usage:

result=CalculateECFP4Fingerprint(mol)

Input: mol is a molecule object.

Output: result is a tuple form. The first is the vector of

fingerprints. The second is a dict form whose keys are the

position which this molecule has some substructure. The third

is the DataStructs which is used for calculating the similarity.

fingerprint.CalculateECFP6Fingerprint(mol, radius=3)[source]

Calculate ECFP6

Usage:

result=CalculateECFP6Fingerprint(mol)

Input: mol is a molecule object.

Output: result is a tuple form. The first is the vector of

fingerprints. The second is a dict form whose keys are the

position which this molecule has some substructure. The third

is the DataStructs which is used for calculating the similarity.

fingerprint.CalculateEstateFingerprint(mol)[source]

Calculate E-state fingerprints (79 bits).

Usage:

result=CalculateEstateFingerprint(mol)

Input: mol is a molecule object.

Output: result is a tuple form. The first is the number of

fingerprints. The second is a dict form whose keys are the

position which this molecule has some substructure. The third

is the DataStructs which is used for calculating the similarity.

fingerprint.CalculateFCFP2Fingerprint(mol, radius=1, nBits=1024)[source]

Calculate FCFP2

Usage:

result=CalculateFCFP2Fingerprint(mol)

Input: mol is a molecule object.

Output: result is a tuple form. The first is the vector of

fingerprints. The second is a dict form whose keys are the

position which this molecule has some substructure. The third

is the DataStructs which is used for calculating the similarity.

fingerprint.CalculateFCFP4Fingerprint(mol, radius=2, nBits=1024)[source]

Calculate FCFP4

Usage:

result=CalculateFCFP4Fingerprint(mol)

Input: mol is a molecule object.

Output: result is a tuple form. The first is the vector of

fingerprints. The second is a dict form whose keys are the

position which this molecule has some substructure. The third

is the DataStructs which is used for calculating the similarity.

fingerprint.CalculateFCFP6Fingerprint(mol, radius=3, nBits=1024)[source]

Calculate FCFP6

Usage:

result=CalculateFCFP4Fingerprint(mol)

Input: mol is a molecule object.

Output: result is a tuple form. The first is the vector of

fingerprints. The second is a dict form whose keys are the

position which this molecule has some substructure. The third

is the DataStructs which is used for calculating the similarity.

fingerprint.CalculateFP2Fingerprint(mol)[source]

Calculate FP2 fingerprints (1024 bits).

Usage:

result=CalculateFP2Fingerprint(mol)

Input: mol is a molecule object.

Output: result is a tuple form. The first is the number of

fingerprints. The second is a dict form whose keys are the

position which this molecule has some substructure. The third

is the DataStructs which is used for calculating the similarity.

fingerprint.CalculateFP3Fingerprint(mol)[source]

Calculate FP3 fingerprints (210 bits).

Usage:

result=CalculateFP3Fingerprint(mol)

Input: mol is a molecule object.

Output: result is a tuple form. The first is the number of

fingerprints. The second is a dict form whose keys are the

position which this molecule has some substructure. The third

is the DataStructs which is used for calculating the similarity.

fingerprint.CalculateFP4Fingerprint(mol)[source]

Calculate FP4 fingerprints (307 bits).

Usage:

result=CalculateFP4Fingerprint(mol)

Input: mol is a molecule object.

Output: result is a tuple form. The first is the number of

fingerprints. The second is a dict form whose keys are the

position which this molecule has some substructure. The third

is the DataStructs which is used for calculating the similarity.

fingerprint.CalculateGhoseCrippenFingerprint(mol, count=False)[source]

Calculate GhoseCrippen Fingerprints

fingerprint.CalculateMACCSFingerprint(mol)[source]

Calculate MACCS keys (166 bits).

Usage:

result=CalculateMACCSFingerprint(mol)

Input: mol is a molecule object.

Output: result is a tuple form. The first is the number of

fingerprints. The second is a dict form whose keys are the

position which this molecule has some substructure. The third

is the DataStructs which is used for calculating the similarity.

fingerprint.CalculateMorganFingerprint(mol, radius=2)[source]

Calculate Morgan

Usage:

result=CalculateMorganFingerprint(mol)

Input: mol is a molecule object.

Output: result is a tuple form. The first is the number of

fingerprints. The second is a dict form whose keys are the

position which this molecule has some substructure. The third

is the DataStructs which is used for calculating the similarity.

fingerprint.CalculatePharm2D2pointFingerprint(mol, featFactory=<rdkit.Chem.rdMolChemicalFeatures.MolChemicalFeatureFactory object at 0x070D38F0>)[source]

Calculate Pharm2D2point Fingerprints

fingerprint.CalculatePharm2D3pointFingerprint(mol, featFactory=<rdkit.Chem.rdMolChemicalFeatures.MolChemicalFeatureFactory object at 0x070D38F0>)[source]

Calculate Pharm2D3point Fingerprints

fingerprint.CalculatePubChemFingerprint(mol)[source]

Calculate PubChem Fingerprints

fingerprint.CalculateSimilarityPybel(fp1, fp2)[source]

Calculate Tanimoto similarity between two molecules.

Usage:

result=CalculateSimilarityPybel(fp1,fp2)

Input: fp1 and fp2 are two DataStructs.

Output: result is a Tanimoto similarity value.

fingerprint.CalculateSimilarityRdkit(fp1, fp2, similarity='Tanimoto')[source]

Calculate similarity between two molecules.

Usage:

result=CalculateSimilarity(fp1,fp2) Users can choose 11 different types: Tanimoto, Dice, Cosine, Sokal, Russel, RogotGoldberg, AllBit, Kulczynski, McConnaughey, Asymmetric, BraunBlanquet Input: fp1 and fp2 are two DataStructs.

Output: result is a similarity value.

fingerprint.CalculateTopologicalTorsionFingerprint(mol)[source]

Calculate Topological Torsion Fingerprints

Usage:

result=CalculateTopologicalTorsionFingerprint(mol)

Input: mol is a molecule object.

Output: result is a tuple form. The first is the number of

fingerprints. The second is a dict form whose keys are the

position which this molecule has some substructure. The third

is the DataStructs which is used for calculating the similarity.