Xuhan Liu

Thank you, this is a good suggestion. I will do that after the second version of DrugEx has been released.

Because of the limitation of storage, I did not upload the generated molecules. Here, 'mol_p.txt' is the file including molecules generated by the pre-trained model, "mol_ex.txt" is the file including...

Hi, The reason is that '[BH-]' is not contained in the data/voc.txt, you can add it manually. Cheers, Xuhan ------------------ 原始邮件 ------------------ 发件人: "Charles Tapley Hoyt"; 发送时间: 2019年6月24日(星期一) 晚上11:10 收件人:...

1. Collecting your own data from public database, e.g. ChEMBL, and then encode them to the token series of SMILES format. (dataset.py) 2. Constructing the QSAR model as the predictor...

I think DrugEx v2 is suitable for your scenarios. 2k data points are enough to construct predictors. But for the generator, you need to find some similar molecules to enlarge...

Hi @SaraiQX, Thanks for having interest with my works. I noticed that TgtData is useless. Therefore I have removed this class. If you want to try the latest version. I...

Firstly, you have to check how you dumped your machine learning pkl model ever before with pickle? This is what I did in the environ.py. >>> joblib.dump(model, out, compress=3) param...