keras-molecules
keras-molecules copied to clipboard
maxhodak
Autoencoder network for learning a continuous representation of molecular structures.
Currently the requirements.txt file references keras from git: -e git+https://github.com/fchollet/keras.git#egg=keras however, keras is in PyPI. if it's not impossible, I suggest using the one from pip with a defined version...
It's not clear to me this code belongs here, I'm happy to make a new repo to hold this kind of code.
I've been trying to package up keras-molecules as a module so I can run it on Google Cloud Machine Learning. Unfortunately, the top-level of keras-molecules (with train.py etc) isn't really...
preprocess.py loads the entire pre-preprocessed data into RAM, does transforms that require more RAM. I'm trying to preprocess GDB-17 w/ 50M SMILES strings and it's just about filling up my...
--smiles can be used to encode smiles strings that are not in the dataset. The dataset is still used to do the charset one-hot encoding correctly. --save_json was also added...
Using SMILES makes this problem unnecessarily hard, likely detracting from the smoothness of the latent space and causing the majority of sampled SMILES to be invalid even after extended training....
This codebase works well for me and I'm able to replicate the current results. Having worked a good bit with other latent spaces, I'm curious to find out what other...
LogP calculations for the 50k dataset. Same order as original SMILES file.
I'm trying to do eLSA (expanded local similarity analysis) published in https://bitbucket.org/charade/elsa/src/master/ and the installation is fine. I did check_data and is ok. I also check all the packages necessary...
I got error when i run **"python download_dataset.py --dataset zinc12"** Traceback (most recent call last): File "download_dataset.py", line 69, in main() File "download_dataset.py", line 54, in main urllib.urlretrieve(uri, fd.name, reporthook...
