Ian Dunn

Hey Clement, Thanks for bringing this to my attention! I made a copy of the dataset available here: [https://bits.csb.pitt.edu/files/geom_raw/](https://bits.csb.pitt.edu/files/geom_raw/) I'll update the instructions in this repository soon. I think I...

Hi there, so glad you to hear you want to use FlowMol for a class demo! I'm able to recreate your error from a fresh mamba environment with python 3.10...

And to answer your question, I don't know if there would be performance effects loading the existing checkpoints and running inference in python 3.11. It's probably fine. Especially for an...

The FlowMol environment, as designed, depends on python 3.10. I have not had luck trying to rebuild it with python 3.11, but I have put that much time into it....

Nice catch! So the reason its in our code is that we took the valency look-up table from MiDi. Here's how I think these strange valencies got there: It turns...

I cannot evaluate whether this is simply how the model behaves or if there is something going wrong in your environment from just a few cherry-picked examples. Starting from the...

So the current situation is: 1. neutral 3-valence carbon and neutral 2-valence nitrogen appear in the valid valence lookup table likely due to a bug in valency computation 2. but...

We're hosting the raw files [here](https://bits.csb.pitt.edu/files/geom_raw/). The [directions in the readme ](https://github.com/Dunni3/FlowMol?tab=readme-ov-file#geom-drugs) point to this same location. These files are the starting point for our pipeline (`process_geom.py`). I will note...

We recently wrote a paper about issues with the "stability" metric commonly used, including the one being discussed here. We propose a few solutions and provide some code for them....