Gabriele Corso

Hi, yes we made a few changes

Hi @amir-tagh Yes indeed one could train a version of DiffDock for docking to RNA structures, however, there are further challenges such as relatively limited data and higher receptor flexibility...

I would not recommend to use it to dock RNA (there is none in the training data as far as I know, and the method is not designed for molecules...

Hi @Xu-kexin Are you sure that you are looking at the filtered_rmsd_below_2 metric? The rmsd_below_2 metric only indicates the performance before the use of the confidence model, which makes a...

top5_rmsds_below_2 corresponds to the the proportion of complexes with RMSD below 2A when taking the pose with lowest RMSD out of 5 poses (the 5 highest ranked poses in the...

Hi @RafiBrent, if running the DiffDock code directly you should also be able to see the specific error that occurs with that specific complex. Given the relatively complex ligand, I...

Hi @JeongSooNa , This error occurs because the preprocessing for all your complexes has failed. To get better insight into the issue you can remove the cache and add a...

Hi @JeongSooNa, could you try to redo the same process but removing the underscore from the title of the receptor (i.e. 6vl4-3chain instead of 6vl4_3chain)? Gabriele

Hi, This error occurs at `from torch_geometric.loader import DataLoader` so it must be a problem with (the installation of) PyTorch Geometric and its related packages. My recommendation is to uninstall...

Hi @yukisoya could you check whether the issue is still there with the fixes of the recent commits?