Minimization failed after 100 attempts.

[dahaigui]

The driver version is 11.7

The cudatoolkit version is 11.7

I0922 20:54:25.670873 139785783146304 amber_minimize.py:407] Minimizing protein, attempt 98 of 100. I0922 20:54:27.095493 139785783146304 amber_minimize.py:68] Restraining 5073 / 10077 particles. I0922 20:54:27.823423 139785783146304 amber_minimize.py:417] Error compiling program: nvrtc: error: invalid value for --gpu-architecture (-arch)

I0922 20:54:27.830594 139785783146304 amber_minimize.py:407] Minimizing protein, attempt 99 of 100. I0922 20:54:28.679339 139785783146304 amber_minimize.py:68] Restraining 5073 / 10077 particles. I0922 20:54:29.414243 139785783146304 amber_minimize.py:417] Error compiling program: nvrtc: error: invalid value for --gpu-architecture (-arch)

I0922 20:54:29.421343 139785783146304 amber_minimize.py:407] Minimizing protein, attempt 100 of 100. I0922 20:54:30.978424 139785783146304 amber_minimize.py:68] Restraining 5073 / 10077 particles. I0922 20:54:31.718168 139785783146304 amber_minimize.py:417] Error compiling program: nvrtc: error: invalid value for --gpu-architecture (-arch)

Traceback (most recent call last): File "/22t/chenhx/software/alphafold-2.2.0/run_alphafold.py", line 422, in app.run(main) File "/22t/chenhx/miniconda3/envs/testalphafold/lib/python3.8/site-packages/absl/app.py", line 312, in run _run_main(main, args) File "/22t/chenhx/miniconda3/envs/testalphafold/lib/python3.8/site-packages/absl/app.py", line 258, in _run_main sys.exit(main(argv)) File "/22t/chenhx/software/alphafold-2.2.0/run_alphafold.py", line 398, in main predict_structure( File "/22t/chenhx/software/alphafold-2.2.0/run_alphafold.py", line 242, in predict_structure relaxed_pdbstr, , _ = amber_relaxer.process(prot=unrelaxed_protein) File "/22t/chenhx/software/alphafold-2.2.0/alphafold/relax/relax.py", line 61, in process out = amber_minimize.run_pipeline( File "/22t/chenhx/software/alphafold-2.2.0/alphafold/relax/amber_minimize.py", line 475, in run_pipeline ret = _run_one_iteration( File "/22t/chenhx/software/alphafold-2.2.0/alphafold/relax/amber_minimize.py", line 419, in _run_one_iteration raise ValueError(f"Minimization failed after {max_attempts} attempts.") ValueError: Minimization failed after 100 attempts.

[dahaigui]

How can I address this issue?

[Old-Shatterhand]

Hi @dahaigui,

sorry for the late response. We're experiencing this issue from time to time when the input sequences are very long and AlphaFold is close to some out-of-memory issues. Can you check this out?

Anyways, have you installed AlphaFold following the description in this repo? From the trace, I can see that the program flow goes out of the conda environment.

Best, Roman

[johnsnowgo]

I met the same error with you. I solved it by set -r false when bash run_alphafold.sh. Hope it can help you.

[dahaigui]

I solved the problem, but I forgot the solution, it was roughly caused by nvrtc reporting an error, solving the dependency should be fine!