openfold

openfold copied to clipboard

Hi, I am not sure if this is a bug or not but when I am using `precompute_alignments_mmseqs.py` to create an alignment for a single protein with ~300 amino acids...

hnisonoff

Hi, Is there a list of identifiers defining which sequences are included in the uniclust30_unfiltered data? Ideally, if we can tell which sequence MSAs each zip file contains, that would...

pgmikhael

multimer using mmseqs generated sequence alignments?

2

Hello, I'm trying to run openfold multimer inference on some fasta files I have. I've been using the collabfold databases to generate the sequence alignments as these are smaller than...

emzodls

Since np.object is no longer supported in the new versions of numpy, is it possible to replace np.object by object to fix this problem?

Zoesgithub

libtorch_cuda_cpp.so missing after installation (rtx4090 with cuda driver 12.1)

1

I am trying to use openfold on a machine with an rtx 4090 with cuda driver 12.1 I install the package using the environment file and I get this problem...

cifnik

Flash Attention Installation Error

3

Using the current environment.yml file with mamba results in the following errors. Looks like the hash for the flash attention version might not be current? Pip subprocess output: Collecting git+https://github.com/NVIDIA/dllogger.git...

LaurinLang

Hello, I have tested the optimization effects of the evoformer attention in deepspeed-evo-attention branch, but encountered an accuracy issue. After enabling the optimization, the output of openfold differs significantly from...

WhenMelancholy

a big gap between the pdb results from openfold and alphafold2 (colab)

4

Hi! After running openfold according to the default configuration, I found that there was a big difference between the output pdb file of openfold and alphafold (colab version). After comparing...

Melo-1017

* Fixes the periodicity batching bug for `supervised_chi_loss` discovered in https://github.com/aqlaboratory/openfold/issues/381. * Fixes the shape of `unnormalized_angles_sin_cos` for (batched) angle norm loss calculation. * Also corrects the docstring for this...

amorehead

Hello. Thank you all for making this work fully open-source. I had a question about the `supervised_chi_loss()` function. When constructing `chi_pi_periodic`, shouldn't the einsum equation be `...ij,jk->...ik` rather than `...ij,jk->ik`...

amorehead