-
Notifications
You must be signed in to change notification settings - Fork 6
Description
Hi there,
Thanks for developing this tool. I tried to download the latest version v2.1.11 via conda and tried to install it on our HPC cluster and my local desktop (M2 pro arm64, with conda create --platform 'osx-64' -n phabox for installation). However, I encountered some issues when running a test using example_contigs.fa provided and my viral contigs.fasta.
On my local desktop, my command is: phabox2 --task end_to_end --skip Y --contigs merged_uvigs.fasta -o ./test_out -d /Users/Databases/phabox_db_v2 --len 500 --threads 8
And an error was as follows:
PhaBOX2 is running with: 8 threads!
Running program: Data preprocessing
[1/7] filtering the length of contigs...
[2/7] calling genes with prodigal...
[3/7] running all-against-all alignment...
[4/7] converting sequences to sentences for language model...
[5/7] Analyzing the seuqences...
0%| | 0/4 [00:00<?, ?it/s]Intel MKL WARNING: Support of Intel(R) Streaming SIMD Extensions 4.2 (Intel(R) SSE4.2) enabled only processors has been deprecated. Intel oneAPI Math Kernel Library 2025.0 will require Intel(R) Advanced Vector Extensions (Intel(R) AVX) instructions.
100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 4/4 [00:00<00:00, 16.77it/s]
[6/7] summarizing the results...
[7/7] writing the results...
Command 'sed -i '1i\qseqid sseqid pident length mismatch gapopen qstart qend sstart send evalue bitscore' ./test_out/final_prediction//preprocessing_supplementary/alignment_results.tab' failed with exit code 1
sed: 1: "./test_out/final_predic ...": invalid command code .
please run the command manually to check the error
Then, I also ran it on HPC using the example_contigs.fa for a test: (phabox2) bash-4.4$ phabox2 --task end_to_end --contigs example_contigs.fa --outpth phabox_test_out --threads 16 --dbdir /mnt/scratch2/users/3058727/databases/phabox_db_v2
And an error was like below:
PhaBOX2 is running with: 16 threads!
Running program: PhaMer (virus identification)
[1/7] filtering the length of contigs...
[2/7] calling genes with prodigal...
[3/7] running all-against-all alignment...
[4/7] converting sequences to sentences for language model...
[5/7] Predicting the viruses...
100%|████████████████████████████████████████████████████████████████████████████████████████████████████| 351/351 [00:02<00:00, 139.19it/s]
[6/7] summarizing the results...
[7/7] writing the results...
Run time: 13.17 seconds
PhaMer finished! please check the results in phabox_test_out/final_prediction
Running program: PhaGCN (taxonomy classification)
[1/8] reusing existing filtered contigs...
[2/8] reusing existing protein file...
[3/8] using existing all-against-all alignment results...
[4/8] generating phagcn networks...
[5/8] predicting the taxonomy...
100%|███████████████████████████████████████████████████████████████████████████████████████████████████| 292/292 [00:00<00:00, 7168.11it/s]
[6/8] summarizing the results...
[7/8] generating genus level clusters...
[8/8] writing the results...
Run time: 36.82 seconds
PhaGCN finished! please check the results in phabox_test_out/final_prediction
Running program: CHERRY (Host prediction)
[1/10] reusing existing filtered contigs...
[2/10] no MAGs provided, skipping MAG CRISPRs prediction...
[3/10] will continue running CHERRY with database bersion...
[4/10] predicting DB CRISPRs...
[5/10] reusing existing protein file...
[6/10] reusing all-against-all alignment from PhaGCN...
[7/10] generating cherry networks...
100%|███████████████████████████████████████████████████████████████████████████████████████████████████| 292/292 [00:00<00:00, 8159.69it/s]
[8/10] predicting the host...
[9/10] summarizing the results...
[10/10] writing the results...
Run time: 67.05 seconds
Cherry finished! please check the results in phabox_test_out/final_prediction
Running program: PhaTYP (Lifestyle prediction)
running with cpu
[1/7] reusing existing filtered contigs...
[2/7] reusing existing protein file...
[3/7] using existing all-against-all alignment results...
[4/7] converting sequences to sentences for language model...
[5/7] Predicting the lifestyle...
Map: 100%|███████████████████████████████████████████████████████████████████████████████████████| 288/288 [00:00<00:00, 9472.04 examples/s]
Traceback (most recent call last):
File "/mnt/scratch2/users/3058727/conda/envs/phabox2/bin/phabox2", line 10, in <module>
sys.exit(main())
^^^^^^
File "/mnt/scratch2/users/3058727/conda/envs/phabox2/lib/python3.12/site-packages/phabox2/phabox2.py", line 385, in main
phatyp.run(inputs)
File "/mnt/scratch2/users/3058727/conda/envs/phabox2/lib/python3.12/site-packages/phabox2/phatyp.py", line 166, in run
trainer, tokenized_data = init_bert(rootpth, midfolder, parampth)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/scratch2/users/3058727/conda/envs/phabox2/lib/python3.12/site-packages/phabox2/scripts/ulity.py", line 217, in init_bert
model = AutoModelForSequenceClassification.from_pretrained(f'{parampth}/bert', num_labels=2)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/scratch2/users/3058727/conda/envs/phabox2/lib/python3.12/site-packages/transformers/models/auto/auto_factory.py", line 571, in from_pretrained
return model_class.from_pretrained(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/scratch2/users/3058727/conda/envs/phabox2/lib/python3.12/site-packages/transformers/modeling_utils.py", line 309, in _wrapper
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/mnt/scratch2/users/3058727/conda/envs/phabox2/lib/python3.12/site-packages/transformers/modeling_utils.py", line 4574, in from_pretrained
) = cls._load_pretrained_model(
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/scratch2/users/3058727/conda/envs/phabox2/lib/python3.12/site-packages/transformers/modeling_utils.py", line 4833, in _load_pretrained_model
load_state_dict(checkpoint_files[0], map_location="meta", weights_only=weights_only).keys()
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/scratch2/users/3058727/conda/envs/phabox2/lib/python3.12/site-packages/transformers/modeling_utils.py", line 554, in load_state_dict
check_torch_load_is_safe()
File "/mnt/scratch2/users/3058727/conda/envs/phabox2/lib/python3.12/site-packages/transformers/utils/import_utils.py", line 1417, in check_torch_load_is_safe
raise ValueError(
ValueError: Due to a serious vulnerability issue in `torch.load`, even with `weights_only=True`, we now require users to upgrade torch to at least v2.6 in order to use the function. This version restriction does not apply when loading files with safetensors.
See the vulnerability report here https://nvd.nist.gov/vuln/detail/CVE-2025-32434
Do you have and ideas and advice about how to resolve these issues? Many thanks in advance for looking into these problems!
Best