Hunter Nisonoff

Thanks for the quick reply! That helped but now I have another issue... ``` nvcc fatal : Unsupported gpu architecture 'compute_80' src/CMakeFiles/libmolgrid_shared.dir/build.make:185: recipe for target 'src/CMakeFiles/libmolgrid_shared.dir/grid_maker.cu.o' failed make[5]: *** [src/CMakeFiles/libmolgrid_shared.dir/grid_maker.cu.o]...

Thanks! Tried that but ran into issues: ``` Step 3/4 : RUN apt update ; apt upgrade -y ; apt-get -y install build-essential git cmake wget libboost-all-dev libeigen3-dev libgoogle-glog-dev libprotobuf-dev...

I don't think it is a copying and pasting error. I am using your exact file with the same issue ``` git clone https://github.com/gnina/gnina.git cd gnina/docker/ubuntu-22.04/ docker build -t gnina...

Yeah it is strange... the good news Is I was able to install with your Ubuntu18 version. Thanks for all the help!!

I am running into this issue and have been unable to resolve it by running `conda install -c conda-forge glib` before installing `pytorch-spline-conv`. Does anyone have suggestions for other solutions?...

@rolweber it looks. like they now support 11.8. https://www.dgl.ai/pages/start.html

Update I was able to fix this by adding a tiny constant (1e-6) to all of the discrete factors. Not sure why this is necessary though.

I am describing the 5c28 example from `PDBbind2016.tar.gz`. I just double check by redownloading everything. Here is an image showing what happens when I load the docked molecule and the...

Here is the directory. Files are 5c28_docked.sdf and 5c28_ligand.sdf [5c28.zip](https://github.com/gnina/models/files/9203095/5c28.zip)

Sorry you are right. I apologize for the inconvenience. For RMSDs I was using rdkit CalcRMS and spyrmsd. I'll go back and fill this out with more detail. Sorry again...