有什么方法可以将微笑 .csv 文件转换为一种热编码？

Question

I have converted one single smile in one hot encoding using RDKIT library while converting entire .csv file which contain smiles i am getting error.

Successful Experiment :

 new = 'O=C(O)C1=C(N2N=CC=N2)C=CC(N)=N1'

   output :
   array([[0., 0., 0., ..., 0., 0., 0.],
   [0., 0., 0., ..., 0., 0., 0.],
   [0., 0., 0., ..., 0., 0., 0.],
   ...,
   [0., 0., 0., ..., 0., 0., 0.],
   [0., 0., 0., ..., 0., 0., 0.],
   [0., 0., 0., ..., 0., 0., 0.]])

but while trying multiple smiles I am getting this error

   TypeError: No registered converter was able to produce a C++ rvalue of type class 
   std::basic_string<wchar_t,struct std::char_traits<wchar_t>,class std::allocator<wchar_t> > from 
    this Python object of type DataFrame

I am sharing my code file while you can see that demo

Experimental code

Demo dataset

If anyone can help me please let me know.

Answer 1

Chem.MolToSmiles(Chem.MolFromSmiles( smiles )) can only convert one SMILES after the other, but you tried the whole dataframe. You have to to loop over the SMILES in your dataframe.

This should work.

df = pd.read_csv('RouteSynthesisPrediction_o2h.csv')

for smi in df['Target']:
    smiles = Chem.CanonSmiles(smi)
    mat = smiles_encoder(smiles)
    dec = smiles_decoder(mat)
    print(mat)
    print(smi)
    print(smiles)
    print(dec)
    print()

Output:

[[0. 0. 0. ... 0. 0. 0.]
 [0. 0. 0. ... 0. 0. 0.]
 [0. 0. 0. ... 0. 0. 0.]
 ...
 [0. 0. 0. ... 0. 0. 0.]
 [0. 0. 0. ... 0. 0. 0.]
 [0. 0. 0. ... 0. 0. 0.]]
O=C(O)C1=C(N2N=CC=N2)C=CC(N)=N1
Nc1ccc(-n2nccn2)c(C(=O)O)n1
Nc1ccc(-n2nccn2)c(C(=O)O)n1

[[0. 0. 0. ... 0. 0. 0.]
 [0. 0. 0. ... 0. 0. 0.]
 [0. 0. 0. ... 0. 0. 0.]
 ...
 [0. 0. 0. ... 0. 0. 0.]
 [0. 0. 0. ... 0. 0. 0.]
 [0. 0. 0. ... 0. 0. 0.]]
O=C(OC)C1=C(N2N=CC=N2)C=CC(N)=N1
COC(=O)c1nc(N)ccc1-n1nccn1
COC(=O)c1nc(N)ccc1-n1nccn1

.
.
.

Answer 2

There really isn't enough info here to do a full answer. The output looks like a Numpy array, and Numpy needs to preallocate the length of the floats. If you have line one be 10 floats then when appending line two it has to fit within 10 and not go over. It's not able to allocate the memory for it.