Gabriele Corso

Dear @wang1215789 I think there may be a few levels of miscomprehension: 1. The other machine learning baselines (GeoMol and GeoDiff) are trained with the exact same data. On the...

Sorry, could you specify a bit more about the error and the environment you are running it with (e.g. e3nn version)?

Hi @CaptainCuong, sorry for the delay we did not manage to replicate the issue. Could you try to see if this fix solves the problem? https://github.com/gcorso/DiffDock/issues/14

Apologies for the late response. If the issue persists you can probably remove the dependence all together substituting the relaxant functions with code.

Hi, I'm not sure I'm understanding the issue, as long as the various PHP files are on the server and visible via a URL to the application it is fine

Of course if it is left on local host it won't be picked up by the application for two reasons: it is not accessible from the app and the app...

Hi, unfortunately the server that was hosting the backend of the app has been shut down so it is impossible to access the app on the Play Store at the...

No, we did not use the perturbed conformers to train the other methods, but we don't see any reason why it would help them. When we test we use the...

Sorry for the delay and thank you very much @MatthewMasters for the answer! All Matthew said is correct, moreover, if you don't use the Boltzmann weighted sampling (this is the...

Closing for inactivity, feel free to reopen if the issue arises again