openfold
openfold copied to clipboard
Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2
Colab is broken. Please consider my PR #432 which makes it work again. Colab now fails with `module 'numpy' has no attribute 'object'` because the depricated `np.object` now throws error,...
Hi, it seems that `openfold.utils.rigid_utils.Rigid.from_3_points` module is actually different from the algorithm 21 in Alphafold paper. Your code seems to write as v1 = x2 - x1 and v2 =...
 I noticed that every time when 3 epochs training were done, the training process failed.  Here you can see the process is still running, and memories are...
I clone the repo, cd into it, run the provided command `mamba env create -n openfold_env -f environment.yml` and run into the following error: ``` Channels: - conda-forge - bioconda...
OpenFold seems to be required for a different software I want to run: LigandMPNN, however it seems like there's an issue with my openfold install: Programs\Python\Python310\lib\importlib\__init__.py", line 126, in import_module...
Hi, I am encountering an issue similar to issue #421 where I attempted to fine-tune a model using the AF_multimer pretrained parameters (resume_from_jax_params: params_model_1_multimer_v3.npz). However, the loss is unusually high,...
Hi, I'm trying to train this model from an AF-multimer pretrained parameters. I notice that although it resumes from jax parameters, the loss is still pretty high and this model...
When I build the docker image and try to run open fold this is my error. Has anyone else experienced this? what is the work around? [2024-03-28 16:02:57,801] [INFO] [real_accelerator.py:161:get_accelerator]...
Dear OpenFold community, I was encountering an error when running inference using precomputed alignments. I precomputed the alignments by: ``` python3 scripts/precompute_alignments_mmseqs.py \ ${OPENFOLD_RESULTS}/input/T1050.fasta \ ${OPENFOLD_DB}/mmseqs_dbs \ uniref30_2103_db \ ${OPENFOLD_RESULTS}/output/alignments...