Index error when running alpha-analysis.sif (solved in updated version of the singularity image. Please download again) #158
Description
Hi, thanks for wonderful software that runs smoothly on our clusters and can simulate large amounts of interactions quickly. This is what I'm doing, and I am very interested in proper evaluation of the simulations through mean interface-PAE and pDockQ parameters. I saw in your example sheet the inclusion of the singularity file 'alpha-analysis.sif'. When running it, I get an index error like this:
I0727 09:59:41.868614 139799888663744 get_good_inter_pae.py:111] now processing SANT_dom_and_sp_A6H8Y1_BDP1_HUMAN_Transcription_factor_TFIIIB_component_B''_homolog_OS_Homo_sapiens_OX_9606_GN_BDP1_PE_1_SV_3
2023-07-27 09:59:43.272972: W external/org_tensorflow/tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /software/lib64::/.singularity.d/libs
2023-07-27 09:59:43.720279: W external/org_tensorflow/tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /software/lib64::/.singularity.d/libs
2023-07-27 09:59:43.753281: W external/org_tensorflow/tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /software/lib64::/.singularity.d/libs
I0727 09:59:44.940740 139799888663744 xla_bridge.py:333] Unable to initialize backend 'tpu_driver': NOT_FOUND: Unable to find driver in registry given worker:
2023-07-27 09:59:44.943518: W external/org_tensorflow/tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcuda.so.1'; dlerror: libcuda.so.1: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /software/lib64::/.singularity.d/libs
2023-07-27 09:59:44.943562: W external/org_tensorflow/tensorflow/stream_executor/cuda/cuda_driver.cc:263] failed call to cuInit: UNKNOWN ERROR (303)
I0727 09:59:44.945541 139799888663744 xla_bridge.py:333] Unable to initialize backend 'cuda': FAILED_PRECONDITION: No visible GPU devices.
I0727 09:59:44.945811 139799888663744 xla_bridge.py:333] Unable to initialize backend 'rocm': NOT_FOUND: Could not find registered platform with name: "rocm". Available platform names are: Host Interpreter CUDA
I0727 09:59:44.946258 139799888663744 xla_bridge.py:333] Unable to initialize backend 'tpu': module 'jaxlib.xla_extension' has no attribute 'get_tpu_client'
W0727 09:59:44.946407 139799888663744 xla_bridge.py:340] No GPU/TPU found, falling back to CPU. (Set TF_CPP_MIN_LOG_LEVEL=0 and rerun for more info.)
Traceback (most recent call last):
File "/app/alpha-analysis/get_good_inter_pae.py", line 150, in <module>
app.run(main)
File "/opt/conda/lib/python3.9/site-packages/absl/app.py", line 308, in run
_run_main(main, args)
File "/opt/conda/lib/python3.9/site-packages/absl/app.py", line 254, in _run_main
sys.exit(main(argv))
File "/app/alpha-analysis/get_good_inter_pae.py", line 126, in main
mpDockq_score = obtain_mpdockq(os.path.join(FLAGS.output_dir,job))
File "/app/alpha-analysis/get_good_inter_pae.py", line 43, in obtain_mpdockq
mpDockq_or_pdockq = calc_pdockq(chain_coords,plddt_per_chain,t=8)
File "/app/alpha-analysis/calculate_mpdockq.py", line 193, in calc_pdockq
avg_if_plddt = np.average(np.concatenate([plddt1[np.unique(contacts[:,0])], plddt2[np.unique(contacts[:,1])]]))
IndexError: index 663 is out of bounds for axis 0 with size 166
The index-error number is different for each protein and does not correspond to amino acid length. Perhaps anyone have experienced similar issues?
Thanks!