Arne Schneuing
Arne Schneuing
A cutoff of 3.0 still seems rather low but it might work because information is also propagated through several layers of message passing. However, I haven't tried this value myself...
It's hard to tell. The cutoff value could cause your molecules to be less realistic but I'm still surprised by the `0.0` diversity value. Have you visually inspected some of...
Yes, it determines which atoms (nodes) are connected in the graph that the neural network processes.
Hey, what are the exact PyTorch and torch-scatter versions you use?
Hi @anjie-qiao and @joneswong, the parameters in this config file should be correct: https://github.com/igashov/RetroBridge/blob/main/configs/retrobridge.yaml Best, Arne
Hi @Jesse-zjx, thanks for your message and sorry for the slow response. Unfortunately, I'm afraid this is not possible because we never used chirality information in this project.
Hi @psamanta10, thanks for your message. It seems processing fails for all inputs which is causing this downstream error. You should get some intermediate error messages before. Could you please...
You can also use this service which runs Maxit under the hood: https://mmcif.pdbj.org/converter/index.php?l=en