deepbgc pipeline does not seem to use more than 2 cores?

Hello,

Thank you for taking the time to develop this tool, it does exactly what I need it to do for my odd gene clusters. However, the only issue is that it takes more than 20 minutes per fasta file for some bacterial genomes. Is this normal?

I have made a simple model both locally on my macbook and on my university's computational cluster and ran deepbgc pipeline on a single bacterial genome fasta file and in both cases there is no improvement in processing speed past 2 cores. When reading the HMMER user manual, it suggests that it should be capable of utilizing all of the cores available. However, deepbgc pipeline --help does not suggest there is a command to specify how many cpu's it can utilize.

Am I missing something obvious here? Should it take 20 minutes for one fasta file? It seems like it would take decades to get through a metagenome at that rate. My apologies for the ignorance, but how does deepbgc call hmmscan/search?

I looked through some of the other issue reports, but we do not seem to be having the same problems. Any advice you can offer is greatly appreciated, I really would like to use this tool for my work.

Thanks

Start with the deepbgc pipeline --help entry point and inspect how the pipeline calls hmmscan/search; compare the observed two-core behavior with the HMMER user manual. Done means determining whether the runtime and core usage are expected and documenting the relevant CPU option or limitation.