ChemTS
ChemTS copied to clipboard
tsudalab
Molecule Design using Monte Carlo Tree Search with Neural Rollout
Why do we need to normalize logP score， sas score and ring score in ./mcts_logp_improved_version/add_node_type.py:213 ? The octanol-water partitioncoefficient logP in your paper is without normalize.
Hi Xiufeng! Nice paper published! I went through your paper and your codes. Your thought inspired me a lot. But I got some trouble. Are these data true values of...
Hi Xiufeng, Nice paper published! I went through your paper and your codes, and found somewhere that me a little bit confused. i.e how to generate molecules in your model?...
After 19th epoch, I got loss: 0.3925 - acc: 0.8709 - val_loss: 0.3650 - val_acc: 0.8786 but after 20th epoch, loss increases a lot loss: 0.8816 - acc: 0.7350 -...
I use your train_RNN.py, I got Using TensorFlow backend. 2018-06-13 17:21:01.080746: I tensorflow/core/platform/cpu_feature_guard.cc:140] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA But it...
Hi, after saving the model in train_RNN.py, I loaded the model using `model_from_json("model.json")` and `model.load_weights("model.h5")` I called the generate_smile(model,'CCCC') I got the following error: `ValueError: substring not found` What's wrong...
Nice Paper！I have two questions: 1. Could you plz tell me how to De No generate molecules from MCTS, and RNN is enough why we need MCTS? 2. **scores.csv in...
