Hello, may I ask if you can provide a chromosome dataset for training purposes

[a-piece-of-teemo]

Hello, may I ask if you can provide a chromosome dataset for training purposes

[dpellow]

This repo has the scripts I used to download and generate datasets: https://github.com/dpellow/data-download.

(I haven't used them in a while so they may not be fully up to date - open an issue there if you find anything that doesn't work any more and I can update)

[dpellow]

@a-piece-of-teemo did it work?

[a-piece-of-teemo]

I ran the command scripts/download_script.sh, and the following error messages occurred during execution:
2023-12-06 16:39:00 (3.71 MB/s) - ‘archaea_summary.txt’ saved [8532546]
/var/spool/slurmd/job18464/slurm_script: line 48: /usr/bin/gunzip: Argument list too long
cat: 'bacteria/*.fna': No such file or directory
I'm not sure which part went wrong, nor do I know if the command to download the dataset was completed.

[dpellow]

Please put issues in that repo there.
Can you say which directories were created and which files were downloaded?
From the information you posted, it looks like the expansion of * in the gunzip produces a command that is too long since there are too many files.
You should be able to replace the line gunzip bacteria/*.gz with find ./bacteria -name "*.gz" -exec gunzip {} +