FastFold
FastFold copied to clipboard
hpcaitech
Optimizing AlphaFold Training and Inference on GPU Clusters
I've tried to use FastFold for a large hetero-multimer protein complex, but I encountered this issue. ``` 2023-07-25 14:53:20,908 INFO worker.py:1518 -- Started a local Ray instance. 2023-07-25 14:53:22,253 INFO...
**Description:** Running inference with the enable_workflow (Ray Workflow) option causes all processes to be pinned to a single core. **Steps to Reproduce:** Follow the conda or container installation instructions and...
Would it be possible to use this to run nodes of a cluster of computers which would be normal computers/laptops to create a beowulf-like infraestructure approach? How would in that...
Hi! Alphafold's multimer model produces iptm scores that are saved within the pickle file as below: ``` distogram experimentally_resolved masked_msa predicted_aligned_error predicted_lddt structure_module plddt aligned_confidence_probs max_predicted_aligned_error ptm iptm ranking_confidence ```...
when I submit the task an error occurred, how can I fix it? Traceback (most recent call last): File "/Share/app/FastFold/inference.py", line 36, in from fastfold.model.fastnn import set_chunk_size File "/Share/app/FastFold/fastfold/model/fastnn/__init__.py", line...
When using DAP, I encountered the following error: ``` File "/home/pdengad/protein/fastfold/fastfold/model/fastnn/ops.py", line 153, in forward norm = torch.einsum('bsid,bsjd->bijd', M_mask_col, M_mask) + 1e-3 File "/home/pdengad/anaconda3/envs/fastfold/lib/python3.8/site-packages/torch/functional.py", line 360, in einsum return _VF.einsum(equation,...
I used two 40G graphics cards, but still encountered an error of insufficient video memory. The dap_size is 2 and the tensor parallel size is 2, with no other configurations....
I found that an additional dimension representing the number of iterations was added to the input data. I'm wondering what is the purpose of this dimension? Will all model parameters...
Hi While checking the multimer outputs, I realized that for homodimers, there is only a single chain, B. `python /global/scratch/users/skyungyong/Software/FastFold/inference.py --output_dir ./ --model_preset multimer --use_precomputed_alignments Alignments --enable_workflow --inplace --param_path /global/scratch/users/skyungyong/Software/FastFold/data/params/params_model_1_multimer_v3.npz...