def make_fingerprints(data, length=512, verbose=False):
fp_list = [
fingerprint(Chem.rdMolDescriptors.GetHashedTopologicalTorsionFingerprintAsBitVect,
"Torsion "),
fingerprint(lambda x: GetMorganFingerprintAsBitVect(x, 2, nBits=length),
"Morgan"),
fingerprint(FingerprintMol, "Estate (1995)"),
fingerprint(lambda x: GetAvalonFP(x, nBits=length),
"Avalon bit based (2006)"),
fingerprint(lambda x: np.append(GetAvalonFP(x, nBits=length), Descriptors.MolWt(x)),
"Avalon+mol. weight"),
fingerprint(lambda x: GetErGFingerprint(x), "ErG fingerprint (2006)"),
fingerprint(lambda x: RDKFingerprint(x, fpSize=length),
"RDKit fingerprint"),
fingerprint(lambda x: MACCSkeys.GenMACCSKeys(x),
"MACCS fingerprint"),
fingerprint(lambda x: get_fingerprint(x,fp_type='pubchem'), "PubChem"),
# fingerprint(lambda x: get_fingerprint(x, fp_type='FP4'), "FP4")
fingerprint(lambda x: Generate.Gen2DFingerprint(x,Gobbi_Pharm2D.factory,dMat=Chem.Get3DDistanceMatrix(x)),
"3D pharmacophore"),
]
for fp in fp_list:
if (verbose): print("doing", fp.name)
fp.apply_fp(data)
return fp_list
def get_pubchem_fingerprint(smiles):
"""Generate pubchem fingerprint from SMILES.
Args:
smiles (str): the SMILES string
"""
from PyFingerprint.All_Fingerprint import get_fingerprint
return get_fingerprint(smiles, fp_type="pubchem", output="vector")
def CDKFingerprint(self):
import pandas as pd
import os
os.chdir(r"G:\マイドライブ\Data\Meram Chronic Data")
df = pd.read_csv('extChronicStrcture.csv', engine='python')
from PyFingerprint.All_Fingerprint import get_fingerprint
df = df[['CAS', 'canonical_smiles']]
df = df.dropna(how='any')
columns = np.arange(0, 4860, 1).tolist()
columns.insert(0, 'CAS')
resultDf = pd.DataFrame(columns=columns)
for cas, smiles in zip(df['CAS'], df['canonical_smiles']):
fps = get_fingerprint(smiles, fp_type='klekota-roth')
tempdf = self.num2fingerprint(fps, cas)
resultDf = pd.concat([resultDf, tempdf])
resultDf.to_csv('klekotaRoth.csv', index=False)
def get_filtered_fingerprint(smiles):
""" Get filtered PubChem fingerprint. The digits related to elements other than C,
H, O, N, S, F, Cl, and Br are discarded.
Args:
smiles (str): SMILES string.
Return:
fp (np.ndarray): The filtered PubChem fingerprint as a vector.
length (int): length of the filtered vector.
"""
from PyFingerprint.All_Fingerprint import get_fingerprint
fp = get_fingerprint(smiles, fp_type="pubchem", output="vector")
del_pos = ([
26,
27,
28,
29,
30,
31,
32,
41,
42,
46,
47,
48,
295,
296,
298,
303,
304,
348,
354,
369,
407,
411,
415,
456,
525,
627,
] + list(range(49, 115)) + list(range(263, 283)) + list(range(288, 293)) +
list(range(310, 317)) + list(range(318, 327)) +
list(range(327, 332)) + list(range(424, 427)))
fp = np.delete(fp, del_pos)
return fp
def pubChemFP(mol):
fp = get_fingerprint(mol, fp_type='pubchem')
bitvect = [0] * 881
for val in fp:
bitvect[val - 1] = 1
return np.array(list(bitvect))