boltz
boltz copied to clipboard
jwohlwend
Official repository for the Boltz biomolecular interaction models
@latkins love the triton kernel 🎉 Not sure if Triton [supports python3.12 yet](https://github.com/triton-lang/triton/issues/2707) - see error below. Could change [pyproject.toml](https://github.com/jwohlwend/boltz/blob/1f7acb18f279858bc292a8a0f9fbb5d96d6491f1/pyproject.toml#L8C1-L8C27) until we're sure. ``` requires-python = ">=3.10,
Hi, super cool model - I'm really excited to try it out. I was just wondering if it would be possible to clarify what the affinity output is actually predicting....
Such a great contribution. It occurred to me, can boltz do reverse screening, i.e. for a drug screen a library of targets (drug repurposing goal)?
Having run the yaml_prediction of receptor and smile_ligand ,the chirality of ligand did not generate like the smile describe, which can be distinct from boltz_1x
Hello all! Thank you very kindly for your latest boltz-2 contribution to the structure prediction world. As per usual, you guys have provided nothing short of gold. Unfortunately, I think...
I was getting the following error when running with templates: ``` Traceback (most recent call last): File "/home/user/bin/boltz-v2/src/boltz/main.py", line 499, in process_input target = parse_yaml(path, ccd, mol_dir, boltz2) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File...
The affinity.yaml example runs without errors with my Boltz 2.0.2 installation (Github SHA faa24790861edfc87dd52555d2bd8ad39a39aa85) and produces correct output but if I replace the SMILES string ligand with a CCD ligand...
Is this project for offline inference of the model or for online real-time inference and prediction?
As the title suggests, I'm looking to compute affinity scores for things that aren't strictly speaking small molecule ligands (ones that require SMILES strings), which I think Boltz-2 is currently...
Hey Boltz team, Great work! I noticed that when I run predictions for multiple diffusion samples in a single run, affinity is only predicted for one of them. It would...
