boltz icon indicating copy to clipboard operation
boltz copied to clipboard

Official repository for the Boltz biomolecular interaction models

Results 249 boltz issues
Sort by recently updated
recently updated
newest added

I encountered a `KeyError: 'test_'` when running Boltz-1 with a custom FASTA file. The traceback indicates the issue arises from the chain name not matching the expected keys in `chain_to_msa`....

There's a bug where timed out MSA submission requests from the mmseqs2 API result in an infinite loop since the error count code is not properly referenced. This PR addresses...

A major limitation of Boltz is that it uses a lot of GPU memory compared say to AlphaFold 3 so predictions run out of memory. This is especially problematic on...

It seems that boltz1x steering only calculates residue_constraints when handling non-standard residues, without considering standard residues to impose physical constraints. What is the reasoning behind this? https://github.com/jwohlwend/boltz/blob/091b424cb40c09a77c67786f45260bddb38e84bf/src/boltz/data/parse/schema.py#L647

Hi, I'm attempting to reproduce the results on **macOS**, but since the [last merge](https://github.com/jwohlwend/boltz/commit/b8b6373842e7295d03ea347c20729967c487f745), it's no longer possible to install the environment directly from the GitHub repository due to a...

Hello, I'm trying to install Boltz-1 on a M2 Mac. I have been using homebrew for installing other things, and I think it may be the cause of an error...

CIF output of predictions truncates lines at 79 characters [ETA: actually 80 characters], introducing a newline. Example: ``` ... ATOM 1057 C CB . THR 135 135 ? A -8.90867...

Output of `boltz predict` gives the pLDDT as percent (0,100) when reported in the B-factor column, but as a fraction (0,1) in the `_ma_qa_metric_local` loop.

As noted by @jbderoo in a comment on PR #249 (and related to #243), training with `fk_steering` and `guidance_update` set to `True` results in a `KeyError`. This is because `compute_constraint_features`...

Hi, I am not able to make reproducible predictions with fixed pytorch seeds and random.seed. What can I do for stable predictions? ``` from pytorch_lightning import seed_everything import random seed...