DiffSBDD processing the CrossDocked data and then training are not working.

Hi, I am having the same issue as previously raised here with the CrossDocked set to process and then train (https://github.com/arneschneuing/DiffSBDD/issues/12)

On running python ./DiffSBDD/process_crossdock.py /content/crossdocked_pocket10 --no_H I am getting the same error as before: #failed: 100000: 100% 100000/100000 [00:10<00:00, 9586.86it/s] Traceback (most recent call last): File "/process_crossdock.py", line 353, in lig_coords = np.concatenate(lig_coords, axis=0) File "<array_function internals>", line 5, in concatenate ValueError: need at least one array to concatenate

Was this resolved? Thank you in advance.

Feb 15 '25 18:02 psamanta10

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 share those too?

Feb 23 '25 11:02 arneschneuing

This should be about the wrong path for a parameter called 'basedir' in the .py file. command python ./DiffSBDD/process_crossdock.py /content/crossdocked_pocket10 --no_H is wrong

Mar 12 '25 09:03 caiyf03