Question: Still have erros related with MSA serve when I run localcolabfold on HPC System, with --templates --custom-template-path been added

[Neo-xbx-00]

Caution: Please only report your issue related to the installation on your local PC or macOS. If you can get the help message by colabfold_batch --help or run a test prediction successfully, your installation is successful. Requests or questions regarding ColabFold features should be directed to ColabFold repo's issues.

---

What is your installation issue?

No installation issus

Computational environment

• OS: [e.g. Ubuntu 22.04, Windows10 & WSL2, macOS...]
• CUDA version if Linux (Show the output of /usr/local/cuda/bin/nvcc --version.) HPC system, Linux CUDA 12.4

To Reproduce

Steps to reproduce the behavior:

1. Go to '...'
2. Click on '....'
3. Scroll down to '....'
4. See error My script: #!/bin/bash #JSUB -J ADPGK_colab #JSUB -n 8 #JSUB -m i56m512ga800 #JSUB -e err.log #JSUB -o out.log module load cuda/12.4 export PATH=~/App/colab-1.5.5/localcolabfold/colabfold-conda/bin/:$PATH colabfold_batch --amber --num-recycle 3 --num-model 5 --templates --custom-template-path ./model ADPGK_pep.csv ./results

log.txt in results: (Multiple Errors like this:) 2024-03-19 14:47:39,192 Error while fetching result from MSA server. Retrying... (1/5) 2024-03-19 14:47:39,193 Error: HTTPSConnectionPool(host='api.colabfold.com', port=443): Max retries exceeded with url: /ticket/msa (Caused by NameResolutionError("<urllib3.connection.HTTPSConnection object at 0x148af4508dc0>: Failed to resolve 'api.colabfold.com' ([Errno -2] Name or service not known)"))

Expected behavior

A clear and concise description of what you expected to happen.

[Neo-xbx-00]

Why I can not stop MSA Serve in my script? Even if I use --templates --custom-template-path

[allcatsaregrey]

Also having an issue where the script attempts to connect to the server even though I've precomputed my msas with the commands

colabfold_search --mmseqs /path/to/bin/mmseqs input_sequences.fasta /path/to/db_folder msas colabfold_batch msas predictions

[Cs-eason]

am experiencing the same issue. My DNS appears to be functioning correctly, but I have a question: Could the current queue size of 122 be the reason why my MSA server is unable to connect? Here’s the result I got:

curl https://api.colabfold.com/queue
{"queued":122}