boltz
boltz copied to clipboard
jwohlwend
Official repository for the Boltz biomolecular interaction models
Hi, I am currently trying to install Boltz 1.0.0 on a server equipped with AMD GPUs. However, the *trifast* library, which is a required dependency, does not appear to be...
Hi authors, I wonder if there's any way to recycle the generated MSA if I am doing multiple inferences on the same protein but with different ligands. So far, using...
Use the `--rosetta_relax` switch to relax the predicted structure in PyRosetta and resolve potential clashes. PyRosetta installation and a valid license are required. Two relaxed structures will be saved in...
PR to create the CI setup, fix some minor issue with torch and centrilized the testing config. 1. Added a CI workflow. 2. Skipped tests that require CUDA through imports...
Dear Authors, I noticed that in AF3, Algorithm 7 tries to implement local atom attention, as illustrated by the following pseudo code After reading Boltz-1's implementation in [this code](https://github.com/jwohlwend/boltz/blob/main/src/boltz/model/layers/attention.py#L8)., i...
I had installed Boltz-1 about 5 days ago and then I was able to run withouut a gpu using the `--accelerator cpu` option. But now I reinstalled it to use...
Using the following smiles: `C#CCN=C1CCN(C(=O)OC(C)(C)C)C1`, the model creates a molecule that has neither the necessary planarity/double bonds nor the triple bond that it should have. This is what the molecule...
I encountered a RATELIMIT issue while running your program. The remote server has set a limit on the request frequency. 
Fixes #263. This allows predicting structures with 40% more residues without running out of GPU memory. I tested on a half-dozen PDB structures and did not see any loss of...
Several issues here and on the slack are related to VRAM limitations: #71, #83, #106, #167, #169, #197, #214 By tweaking the chunking parameters, you can significantly reduce the VRAM...
