Skip to content
Discussion options

You must be logged in to vote

Hello.
Sorry for the scarce documentation, but the repository is still very much WIP. The .types file you linked is a test file, therefore it contains all possible labels.

Currently gnina-torch supports the following combinations:

  • Ligand pose prediction: you only need the pose label (--label_pos )
  • Ligand pose and binding affinity prediction (multi-task): you need the pose label (--label_pos) and the affinity label (--affinity_pos)
  • Ligand pose and flexible residues pose prediction (multi-task): you need the ligand pose label (--label_pos) and the flexible residues pose label (--flexlabel_pos)

The CLI arguments --label_pos (default 0), --affinity_pos (default 1), and --flexlabel_pos (expe…

Replies: 1 comment 1 reply

Comment options

You must be logged in to vote
1 reply
@kjogr12
Comment options

Answer selected by kjogr12
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Category
Q&A
2 participants
Converted from issue

This discussion was converted from issue #41 on July 20, 2022 08:46.