-
Thanks for this wonderful paper; I'm truly inspired by your work. When I test the code on the BACE_b dataset with the default parameter settings, the outputs for small molecule generation always show …
-
Getting a new error in `calculate_outcomes`. I wonder if it is related to #247? But at this point, all the SMILES that are getting passed into `calculate_outcomes` have been roundtripped through SMILE…
-
Dear Author's，
I am currently working on a project focused on molecular generation using diffusion models. I have come across the code for the two-stage generation process from your research on Gene…
-
Hi,
Congrats on this extrordinary work.
Here's one draws my curiosity also in [Dr. Huang's paper](https://pubs.rsc.org/en/content/articlelanding/2021/sc/d1sc04105c), and coding-unrelated, thoug…
-
Hi, Thanks for your awesome work! When I want to train L1000 auto encoder using
python train_l1000.py \
--layer_type=FiLMConv \
--model_architecture=aae \
--gradient_clip_val=0.0 \
…
-
Dear All,
Thanks for creating this tool.
I am trying to generate big molecules with surge tool. I know that the tool is working pretty good with small molecules but I am having some errors when …
-
Adding a new tab with most potent molecule generation tools
-
Matteo is providing a new set of molecules that need to be added to the graph database. The expectation is that there will be about 200M molecules.
To process this we need to re-instate the fragmentat…
-
Plot calculation speeds on different CPU cores (1, 2, 8 cores) for DFT and compare it with AIMNet speeds on different GPUs (laptop, server GPU, v100s).
-
Dear Author,
I hope this message finds you well. I've been working with the model. The provided [README](https://github.com/acharkq/MolCA/blob/main/README.md) includes a script for fine-tuning spec…