I am getting a Sanitization Error when running the train_ogan code, any suggestions on getting over with it?

[redBirdTx]

Hi, I am trying to run the train_ogan, but getting the following. Any suggestions on getting over with it? Thanks!

Traceback (most recent call last):

File "", line 1, in
runfile('C:/Users/AAA/Documents/Deep learning/GAN/ChemGAN-challenge-master/model/train_ogan.py', wdir='C:/Users/AAA/Documents/Deep learning/GAN/ChemGAN-challenge-master/model')

File "C:\ProgramData\Anaconda3\lib\site-packages\spyder\utils\site\sitecustomize.py", line 710, in runfile
execfile(filename, namespace)

File "C:\ProgramData\Anaconda3\lib\site-packages\spyder\utils\site\sitecustomize.py", line 101, in execfile
exec(compile(f.read(), filename, 'exec'), namespace)

File "C:/Users/AAA/Documents/Deep learning/GAN/ChemGAN-challenge-master/model/train_ogan.py", line 379, in
return

File "C:/Users/AAA/Documents/Deep learning/GAN/ChemGAN-challenge-master/model/train_ogan.py", line 309, in main
print('\t* LOAD_PRETRAIN was set to false.')

File "C:/Users/AAA/Documents/Deep learning/GAN/ChemGAN-challenge-master/model/train_ogan.py", line 193, in pretrain
mm.compute_results(samples, train_samples, ord_dict, results)

File "C:\Users\AAA\Documents\Deep learning\GAN\ChemGAN-challenge-master\model\mol_metrics.py", line 176, in compute_results
results[objective] = np.mean(func(verified_samples, train_data))

File "C:\Users\AAA\Documents\Deep learning\GAN\ChemGAN-challenge-master\model\mol_metrics.py", line 292, in batch_solubility
vals = [logP(s, train_smiles) if verify_sequence(s) else 0 for s in smiles]

File "C:\Users\AAA\Documents\Deep learning\GAN\ChemGAN-challenge-master\model\mol_metrics.py", line 292, in
vals = [logP(s, train_smiles) if verify_sequence(s) else 0 for s in smiles]

File "C:\Users\AAA\Documents\Deep learning\GAN\ChemGAN-challenge-master\model\mol_metrics.py", line 299, in logP
logp = Crippen.MolLogP(Chem.MolFromSmiles(smile))

File "C:\ProgramData\Anaconda3\lib\site-packages\rdkit\Chem\Crippen.py", line 170, in
MolLogP = lambda *x, **y: rdMolDescriptors.CalcCrippenDescriptors(*x, **y)[0]

ValueError: Sanitization error: Explicit valence for atom # 3 O, 3, is greater than permitted

[benstaf]

It's an error with rdkit, so it's better to isolate this problem and ask this question in the rdkit project

…

On Feb 9, 2018 4:03 AM, "redBirdTx" ***@***.***> wrote: Hi, I am trying to run the train_ogan, but getting the following. Any suggestions on getting over with it? Thanks! Traceback (most recent call last): File "", line 1, in runfile('C:/Users/AAA/Documents/Deep learning/GAN/ChemGAN- challenge-master/model/train_ogan.py', wdir='C:/Users/AAA/Documents/Deep learning/GAN/ChemGAN-challenge-master/model') File "C:\ProgramData\Anaconda3\lib\site-packages\spyder\utils\site\sitecustomize.py", line 710, in runfile execfile(filename, namespace) File "C:\ProgramData\Anaconda3\lib\site-packages\spyder\utils\site\sitecustomize.py", line 101, in execfile exec(compile(f.read(), filename, 'exec'), namespace) File "C:/Users/AAA/Documents/Deep learning/GAN/ChemGAN- challenge-master/model/train_ogan.py", line 379, in return File "C:/Users/AAA/Documents/Deep learning/GAN/ChemGAN- challenge-master/model/train_ogan.py", line 309, in main print('\t* LOAD_PRETRAIN was set to false.') File "C:/Users/AAA/Documents/Deep learning/GAN/ChemGAN- challenge-master/model/train_ogan.py", line 193, in pretrain mm.compute_results(samples, train_samples, ord_dict, results) File "C:\Users\AAA\Documents\Deep learning\GAN\ChemGAN- challenge-master\model\mol_metrics.py", line 176, in compute_results results[objective] = np.mean(func(verified_samples, train_data)) File "C:\Users\AAA\Documents\Deep learning\GAN\ChemGAN- challenge-master\model\mol_metrics.py", line 292, in batch_solubility vals = [logP(s, train_smiles) if verify_sequence(s) else 0 for s in smiles] File "C:\Users\AAA\Documents\Deep learning\GAN\ChemGAN- challenge-master\model\mol_metrics.py", line 292, in vals = [logP(s, train_smiles) if verify_sequence(s) else 0 for s in smiles] File "C:\Users\AAA\Documents\Deep learning\GAN\ChemGAN- challenge-master\model\mol_metrics.py", line 299, in logP logp = Crippen.MolLogP(Chem.MolFromSmiles(smile)) File "C:\ProgramData\Anaconda3\lib\site-packages\rdkit\Chem\Crippen.py", line 170, in MolLogP = lambda *x, **y: rdMolDescriptors.CalcCrippenDescriptors(*x, **y)[0] ValueError: Sanitization error: Explicit valence for atom # 3 O, 3, is greater than permitted — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub <#1>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AHzfFMRUEEXWrU8YTLmE1ZDyQ7HbYlzMks5tS6dsgaJpZM4R_T5y> .

[redBirdTx]

I see. Thanks! Did you run into the problem before? If not, would you mind letting me know which rdkit version you have? Thanks best regards Jenn On Thu, Feb 8, 2018 at 11:10 PM, Mostafa Benhenda <notifications@github.com> wrote:

…

It's an error with rdkit, so it's better to isolate this problem and ask this question in the rdkit project On Feb 9, 2018 4:03 AM, "redBirdTx" ***@***.***> wrote: > Hi, I am trying to run the train_ogan, but getting the following. Any > suggestions on getting over with it? Thanks! > > Traceback (most recent call last): > > File "", line 1, in > runfile('C:/Users/AAA/Documents/Deep learning/GAN/ChemGAN- > challenge-master/model/train_ogan.py', wdir='C:/Users/AAA/Documents/Deep > learning/GAN/ChemGAN-challenge-master/model') > > File "C:\ProgramData\Anaconda3\lib\site-packages\spyder\utils\ site\sitecustomize.py", > line 710, in runfile > execfile(filename, namespace) > > File "C:\ProgramData\Anaconda3\lib\site-packages\spyder\utils\ site\sitecustomize.py", > line 101, in execfile > exec(compile(f.read(), filename, 'exec'), namespace) > > File "C:/Users/AAA/Documents/Deep learning/GAN/ChemGAN- > challenge-master/model/train_ogan.py", line 379, in > return > > File "C:/Users/AAA/Documents/Deep learning/GAN/ChemGAN- > challenge-master/model/train_ogan.py", line 309, in main > print('\t* LOAD_PRETRAIN was set to false.') > > File "C:/Users/AAA/Documents/Deep learning/GAN/ChemGAN- > challenge-master/model/train_ogan.py", line 193, in pretrain > mm.compute_results(samples, train_samples, ord_dict, results) > > File "C:\Users\AAA\Documents\Deep learning\GAN\ChemGAN- > challenge-master\model\mol_metrics.py", line 176, in compute_results > results[objective] = np.mean(func(verified_samples, train_data)) > > File "C:\Users\AAA\Documents\Deep learning\GAN\ChemGAN- > challenge-master\model\mol_metrics.py", line 292, in batch_solubility > vals = [logP(s, train_smiles) if verify_sequence(s) else 0 for s in smiles] > > File "C:\Users\AAA\Documents\Deep learning\GAN\ChemGAN- > challenge-master\model\mol_metrics.py", line 292, in > vals = [logP(s, train_smiles) if verify_sequence(s) else 0 for s in smiles] > > File "C:\Users\AAA\Documents\Deep learning\GAN\ChemGAN- > challenge-master\model\mol_metrics.py", line 299, in logP > logp = Crippen.MolLogP(Chem.MolFromSmiles(smile)) > > File "C:\ProgramData\Anaconda3\lib\site-packages\rdkit\Chem\Crippen.py", > line 170, in > MolLogP = lambda *x, **y: rdMolDescriptors.CalcCrippenDescriptors(*x, > **y)[0] > > ValueError: Sanitization error: Explicit valence for atom # 3 O, 3, is > greater than permitted > > — > You are receiving this because you are subscribed to this thread. > Reply to this email directly, view it on GitHub > <#1>, or mute > the thread > <https://github.com/notifications/unsubscribe-auth/ AHzfFMRUEEXWrU8YTLmE1ZDyQ7HbYlzMks5tS6dsgaJpZM4R_T5y> > . > — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub <#1 (comment)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/Aby1VPSpaAkpnye_9WeXr-xB9H9VcAxFks5tS9NRgaJpZM4R_T5y> .

[benstaf]

I don't remember this error.
Requirements: Rdkit version 2017.03.3 from Anaconda,

see README.md

[redBirdTx]

Thanks! I'll try. I had the 2017 09 release.

…

On Fri, Feb 9, 2018 at 9:40 AM, Mostafa Benhenda ***@***.***> wrote: I don't remember this error. Requirements: Rdkit version 2017.03.3 from Anaconda, see README.md — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub <#1 (comment)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/Aby1VKwWZz1hr799-FQNRsCh_zje1OoRks5tTGb3gaJpZM4R_T5y> .