CLG68

python main_eval.py --data-dir [directory storing data hdf and csv files] --mlhdf-fn [hdf file name] --model-path [full path to model checkpoint file (.pth)] --complex-type [1: crystal, 2: docking] to me it...

Maybe it is related to this: https://github.com/rdkit/rdkit/issues/6365 but I'm currently using the latest RDKIT so it should have been fixed. I also get: UFFTYPER: Unrecognized atom type: S_5+6

I screened 100000 structures from a focussed library from a Panther/ShaEP VS, on Unimol docking V2. I had a hard time with rescoring the resuts as 650 poses either had...

Thank you v much for helping with this. I attached the target, the json file, the ref ligand used for generating the json file as well as ex of structures...

Hi, Was it ok in a zip archive or it would be better as individual files? Thank you, Christian

Thank you very much for running some tests with my files. Many docking poses are missing/rejected from the screen because of the "Unrecognized atom type error", of poses without coordinates...

I still have to solve that one... I'll try the problematic files with different versions of RDKit and I'll let you know if one works better.. If not, I could...

I tried the corrected file from Bug in result #167 and it worked. So I transformed my pdb to look like it and then I used the PLIP server. What...

If you do not use --no_kernels, I think it is going to use cuEquivariance kernels. I also installed the nightly build as I had problem with support with my Blackwell...

My 5070ti works with cuda 12.8 and I have no problem with torch. Maybe it would be best to downgrade to 12,8.