-
Hi Sean,
Amazing work. Thank you for sharing your work and your code.
I am curious about the protein MPNN score. Why do you give the chain to design as "A" and take the local score only? Why not u…
-
# Repro steps
1. Create multiple desings with rfdiff, e. g. `num_designs_rfdiff: 2`, and e. g. `num_seq_per_target_mpnn: 2`
2. Set cycles to more than two, e. g. `af2_mpnn_cycles: 3`
3. Run the scr…
-
Hi，when i run "3.1: Performing binding site design with ligandMPNN / FastRelax"，I got a eror: ModuleNotFoundError: No module named 'mpnn_api'. how can i find mpnn_api in heme_pocket_ligMPNN.py? thank…
-
### 📚 Describe the documentation issue
There is an inspector instance inside MPNN that [removes any argument with the same name](https://github.com/pyg-team/pytorch_geometric/blob/master/torch_geom…
-
Dear Zihan,
I am testing your software since we wold like to use an in-house made database on specific reactions which are not covered by USPTO database.
However, before to test our dataset we dec…
-
Hi, all!
I'm wondering the other pre-trained models in Table 1 and 2 are models in their original papers or if you trained separate models using their strategies? Are these models publicly available …
-
Why do I get an error running protein_mpnn_run.py saying there is no chain_set_test.jsonl file in the root directory?
-
There was "/" in the sequence of the the output .fasta file, does anyone know why this happened, like:
```
>test, score=1.7249, global_score=1.7249, fixed_chains=[], designed_chains=['A', 'B'], mod…
-
Hello,
i found out that MPNN model (tensorflow) eats a new portion of GPU memory after each new epoch. Is that supposed to be so?
Thanks
-
Hello,
Before I ask my query, I would like to congratulate everybody involved in building this great framework.
I was trying to train an MPNN-CNN model on the latest BindingDB data and while explo…