openfold icon indicating copy to clipboard operation
openfold copied to clipboard

Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2

Results 183 openfold issues
Sort by recently updated
recently updated
newest added

In the README it states that template finding for SoloSeq will be skipped if no tools or dbs are passed, and the fold will happen using ESM alone. However I...

No module named `attn_core_inplace_cuda` was found during inference on A100. Preinstalled CUDA 11.6 outside of conda. ``` Traceback (most recent call last): File "run_pretrained_openfold.py", line 21, in from openfold.utils.script_utils import...

The way the FASTA file is loaded in `precompute_alignments_mmseqs.py` is very fragile. https://github.com/aqlaboratory/openfold/blob/ef0c9face788001b1624b3b2dbfa951072841835/scripts/precompute_alignments_mmseqs.py#L36-L40 As written, it assumes that the FASTA file is written with headers and sequences alternating every other...

Hi @christinaflo and @jnwei Sorry I forgot to update the unittest for multi-chain permutations after the major updates on the functions. Here I have added necessary steps to prepare fake...

Based on the "help" output, it seems like the parameters "hhsearch_binary_path" and "pdb70" are optional. However, in the 'main' function, hhsearch_pdb70_runner is forced to run regardless of whether these parameters...

I installed openfold on a local server machine using recommanded installation steps ``` scripts/install_third_party_dependencies.sh source scripts/deactivate_conda_env.sh python3 setup.py install scripts/install_hh_suite.sh bash scripts/download_alphafold_dbs.sh data/ ``` Then when using inference with ```...

Thanks for the amazing work you put together. I'm trying to run openfold multimer branch with the following command python3 run_pretrained_openfold.py \ ./FASTA \ data/pdb_mmcif/mmcif_files/ \ --uniref90_database_path data/uniref90/uniref90.fasta \ --mgnify_database_path...

Hello, I downloaded the entire uniclust30 filtered database from [AWS](https://registry.opendata.aws/openfold/) and I see that some clusters have only the `pdb` folder and are missing the `a3m` folder with the MSA....

When I try to run the following command under test folder: python test_data_pipeline.py I have met the following issues: ====================================================================== ERROR: test_fasta_compare (__main__.TestDataPipeline) ---------------------------------------------------------------------- Traceback (most recent call last): File...