Open DrJesseHansen opened 1 year ago
Hi! Has the code been adapted at all? There is no 2.3.4 tag.
I got the same error below. Has anyone figured out how to fix this? Thanks.
Traceback (most recent call last):
File "/apps/eb/AlphaFold/2.3.4-foss-2022a-CUDA-11.7.0-ColabFold/bin/alphafold", line 507, in
Can you provide more details of what and how you are running thing?
Looks like there is mention of colabfold in the error message...
I am running AlphaFold 2.3.4, which was installed with EasyBuild on a Rocky 8 Linux cluster. Thanks.
"This package of AlphaFold contains patches for ColabFold."
https://docs.easybuild.io/version-specific/supported-software/#alphafold
DrJesseHansen did you ever resolve this issue? Same TypeError as my runs.
yes, but unfortunately I don't recall how. We had tons of errors during that time and eventually all got resolved. Are you running the latest ver of AF2? I remember upgrading helped a lot.
Hi, thanks for the response. Alphafold is installed on my workplace's cluster so I am not in control of updating it. We currently run "AlphaFold/2.3.4-foss-2022a-CUDA-11.7.0-ColabFold" which I believe is the latest iteration. Others in my workplace are getting the same error.
Hi there,
exact same error here, on all submitted jobs. Using AlphaFold/2.3.4-foss-2022a-CUDA-11.7.0-ColabFold
.
Command:
alphafold \
--fasta_paths=${input} \
--max_template_date=2023-03-10 \
--db_preset=full_dbs \
--data_dir ${ALPHAFOLD_DATA_DIR}\
--model_preset=multimer \
--output_dir ${outdir}
Error:
I0206 23:12:05.705442 22790460397376 model.py:201] Output shape was {'aligned_confidence_probs': (1066, 1066, 64), 'distogram': {'bin_edges': (63,), 'logits': (1066, 1066, 64)}, 'experimentally_resolved': {'logits': (1066, 37)}, 'iptm': (), 'masked_msa': {'logits': (508, 1066, 22)}, 'max_predicted_aligned_error': (), 'mean_plddt': (), 'plddt': (1066,), 'predicted_aligned_error': (1066, 1066), 'predicted_lddt': {'logits': (1066, 50)}, 'ptm': (), 'ranking_confidence': (), 'structure_module': {'final_atom_mask': (1066, 37), 'final_atom_positions': (1066, 37, 3)}, 'tol': ()}
I0206 23:12:05.706495 22790460397376 alphafold:269] Total JAX model model_1_multimer_v3_pred_0 on XXXX predict time (includes compilation time, see --benchmark): 252.4s
Traceback (most recent call last):
File "/apps/gent/RHEL8/cascadelake-volta-ib/software/AlphaFold/2.3.4-foss-2022a-CUDA-11.7.0-ColabFold/bin/alphafold", line 507, in <module>
app.run(main)
File "/apps/gent/RHEL8/cascadelake-volta-ib/software/jax/0.3.25-foss-2022a-CUDA-11.7.0/lib/python3.10/site-packages/absl/app.py", line 308, in run
_run_main(main, args)
File "/apps/gent/RHEL8/cascadelake-volta-ib/software/jax/0.3.25-foss-2022a-CUDA-11.7.0/lib/python3.10/site-packages/absl/app.py", line 254, in _run_main
sys.exit(main(argv))
File "/apps/gent/RHEL8/cascadelake-volta-ib/software/AlphaFold/2.3.4-foss-2022a-CUDA-11.7.0-ColabFold/bin/alphafold", line 488, in main
predict_structure(
File "/apps/gent/RHEL8/cascadelake-volta-ib/software/AlphaFold/2.3.4-foss-2022a-CUDA-11.7.0-ColabFold/bin/alphafold", line 283, in predict_structure
plddt = prediction_result['plddt']
TypeError: tuple indices must be integers or slices, not str
Going to try a previous version for now, but fixes are welcome.
Regards Mattias
Also getting this on AlphaFold/2.3.4-foss-2022a-CUDA-11.7.0-ColabFold built with EasyBuild
Hi all,
I have been getting the same error for AlphaFoldv2 as well on a HPC cluster. I have tried three different versions that was available on the system (AlphaFold/2.3.1-foss-2022a-CUDA-11.7.0, AlphaFold/2.3.4-foss-2022a-ColabFold or AlphaFold/2.3.4-foss-2022a-CUDA-11.7.0-ColabFold) and having the following error related to plddt:
plddt = prediction_result['plddt']
TypeError: tuple indices must be integers or slices, not str
Since, I couldn't access the AlphaFold scripts as a non-sudo user, I was trying to figure our if it was related to the input file and I though it might be related to string parsing of the sequence header.
Editing the Fasta header to include the accession only helped me to solve the problem. I am not sure if this was the exact solution but I figured you might want to try if your header is long and contains a series of 'strings' especially separated with black spaces.
Example Fasta header format that worked for me:
>NZ_CP032157.1_5712
MNNFSSHIASRYKQKGKFFLPPLFLILFLLVFTDKFT...
I hope this would help some of you to troubleshoot on your servers.
Regards,
Murat
Hi all,
I have resubmitted the same job as my previous issue, except this time on GeForce RTX 2080 Ti rather than A10 or A40s (under the assumption that these latter two need to have drivers updated). This gave a new error below.
thanks in advance!