ERROR:Cannot open model directory iphop_db/Test_db_rw/db/wish_models.

[machuang]

When I run the following test code

iphop predict --fa_file iphop-test/test_input_phages.fna --db_dir iphop_db/Test_db_rw/ --out_dir iphop_test_results/test_input_phages_iphop

I get the following error

[3/2/Run] Get relevant WIsH hits...
Traceback (most recent call last):
  File "/data4/machuang/miniconda3/envs/ViWrap-iPHoP/bin/iphop", line 10, in <module>
    sys.exit(cli())
  File "/data4/machuang/miniconda3/envs/ViWrap-iPHoP/lib/python3.8/site-packages/iphop/iphop.py", line 122, in cli
    args["func"](args)
  File "/data4/machuang/miniconda3/envs/ViWrap-iPHoP/lib/python3.8/site-packages/iphop/modules/master_predict.py", line 79, in main
    wish.run_and_parse_wish(args)
  File "/data4/machuang/miniconda3/envs/ViWrap-iPHoP/lib/python3.8/site-packages/iphop/modules/wish.py", line 48, in run_and_parse_wish
    get_wish_results(args["fasta_file"],args["wishrawresult"],args["wishparsed"],args['messages'])
  File "/data4/machuang/miniconda3/envs/ViWrap-iPHoP/lib/python3.8/site-packages/iphop/modules/wish.py", line 61, in get_wish_results
    with open(pred_file, newline='') as csvfile:
FileNotFoundError: [Errno 2] No such file or directory: 'iphop_test_results/test_input_phages_iphop/Wdir/wish_results/prediction.list'

I started with the following, but it didn't work.

#查看LD_LIBRARY_PATH
 echo $LD_LIBRARY_PATH  #/data4/machuang/miniconda3/envs/ViWrap-iPHoP/lib/:/data4/machuang/miniconda3/envs/ViWrap-iPHoP/lib/:
echo $CONDA_PREFIX  # /data4/machuang/miniconda3/envs/ViWrap-iPHoP
#github解决方案Locate the directory for the conda environment, such as /home/user/anaconda3/envs/iphop. Create the files needed to update the LD_LIBRARY_PATH variable:
$ touch miniconda3/envs/ViWrap-iPHoP/etc/conda/activate.d/LD_env_vars.sh
$ touch miniconda3/envs/ViWrap-iPHoP/etc/conda/deactivate.d/LD_env_vars.sh
#Edit ./etc/conda/activate.d/LD_env_vars.sh as follows, while replacing the example path by the real path on your system:
export OLD_LD_LIBRARY_PATH=${LD_LIBRARY_PATH}
export LD_LIBRARY_PATH=${CONDA_PREFIX}/lib/:${LD_LIBRARY_PATH}
#Edit ./etc/conda/deactivate.d/LD_env_vars.sh as follows
export LD_LIBRARY_PATH=${OLD_LD_LIBRARY_PATH}
unset OLD_LD_LIBRARY_PATH

The log describes it like this：ERROR:Cannot open model directory iphop_db/Test_db_rw/db/wish_models.Where do I go to download this wish_models.Thank you for answering the questions!

[Simon Roux]

Hi,

Can you check which version of iPHoP you are running, and update if possible ? It seems like the program is looking for an old version of the database (the folder “wish_models” has been removed in the latest version). Thanks !

[machuang]

Thank you so much, I installed iphop version 1.2.0 through VirWrap, and after upgrading to 1.3.3, I solved the above problem, and then I encountered the problem of not being able to find "pandas", and I installed pandas in both conda-env and base environment== 1.3.5, and finally ran successfully，and I got three csv tables, but there was a small problem in step 8, and I don't know if it has any effect on the final result. It is displayed like this：

[8] Running the convolution networks...
[8/1] Loading data as tensors..
[8/1.1] Getting blast-based scores..
2023-11-28 15:33:23.746773: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudnn.so.8'; dlerror: libcudnn.so.8: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /data4/machuang/miniconda3/envs/ViWrap-iPHoP/x86_64-conda-linux-gnu/lib/:/data4/machuang/miniconda3/envs/ViWrap-iPHoP/lib/:/data4/machuang/miniconda3/envs/ViWrap-iPHoP/lib/:/data4/machuang/miniconda3/envs/ViWrap-iPHoP/lib/:
2023-11-28 15:33:23.746817: W tensorflow/core/common_runtime/gpu/gpu_device.cc:1850] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform.
Skipping registering GPU devices...
2023-11-28 15:33:23.759618: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2 AVX512F FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.

‌

[Simon Roux]

This looks like only a warning, so if you did get a result in the end (with final score, etc), then everything should be ok. Glad that you were able to fix the different issues !