mask_attend calculation

Kuhlman-Lab / ThermoMPNN

GNN trained to predict changes in thermodynamic stability for protein point mutants

MIT License

125 stars 19 forks source link

mask_attend calculation #18

Closed farbod-nobar closed 8 months ago

farbod-nobar commented 8 months ago

Hi, In protein_mpnn_utils.py, line 1396, there seems to be a typo (an additional character E in mask_attendE):

mask_attend = mask.unsqueeze(-1) * mask_attendE

hdieckhaus commented 8 months ago

Hi, thanks for letting us know! Not sure how this got introduced, but we don't ever use that function in ThermoMPNN, so I guess it never triggered an error on our end. In any case, it has been patched and the repo has been updated!