openfold
openfold copied to clipboard
Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2
Just hoping someone has an idea of what might be going on, because I'm completely puzzled by this behavior. After reducing "no_blocks" from 48 to 12 I get an OOM...
Now that we have a dockerfile, we can push it somewhere. Dockerhub (https://hub.docker.com/) is probably a reasonable place since it's free for open source projects and the de facto standard....
Hello and so happy to see you use Pytorch-Lightning! :tada: Just wondering if you already heard about quite the new **Pytorch Lightning (PL) ecosystem CI** where we would like to...
```python Traceback (most recent call last): File "/ocean/projects/bio210060p/kadyan/openfold-release/scripts/precompute_te mplate_hits.py", line 224, in main(args, template_pipeline_runner) File "/ocean/projects/bio210060p/kadyan/openfold-release/scripts/precompute_te mplate_hits.py", line 116, in main feature_dict = template_pipeline_runner.run(a3m_dir, fasta_file_path) File "/ocean/projects/bio210060p/kadyan/openfold-release/scripts/precompute_te mplate_hits.py", line 80,...
When I use openfold to infer proteins, some of them can be inferred, but some of them will report errors. The reason for the error is probably: the template name...
device: 1 A100 with 40GB memory cuda: 11.3 Compared with https://github.com/dptech-corp/Uni-Fold, using `model_2` setting, and the same data (only use one sample, and use `DummyDataLoader` in openfold). And I follow...
Hi, Thank for the last time it helped me. However, now I have another error. After running the training from ProteinNet input: python /data/openfold/train_openfold.py /data/af_databases/pdb_mmcif/mmcif_files/ /home/ubuntu/ProteinNet_parsed/ProteinNet_lc/ /data/af_databases/pdb_mmcif/mmcif_files/ /home/ubuntu/OF_train_from_Protein_Net/try_1_Dec29_2021/ 2021-10-10 --template_release_dates_cache_path...
Hello everyone. I am doing some evaluation jobs of the inference pipeline. I am wondering how to evaluate the result pdb file such like TM-score, for those proteins that CASP14...
I've implemented low-memory attention (9670958) using an algorithm from a recent preprint (https://arxiv.org/pdf/2112.05682.pdf), enhanced a little bit with the ability to add multiple biases + batch dimensions. Lacking the JAX...
The `chunk_layer` function in `openfold/utils/tensor_utils.py`, which implements the "chunking" procedure described in subsection 1.11.8 of the Alphafold 2 supplement, relies on a memory-expensive expand/reshape operation at the top to standardize...