sokrypton / sokrypton/ColabFold

Specifications for local mmseqs server

Open
#328 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Jupyter Notebook
Stars
2.9k
Forks
747
PR merge metrics
No merged PRs in 30d

Description

More a question than an issue. I'm in the purchasing phase for a local mmseqs server and vendor asks for CPU specs etc. etc.

From the Readme I know:
(2) single query searches require the full index (the .idx files) to be kept in memory. This can be done with e.g. by using vmtouch. Thus, this type of search requires a machine with at least 768GB RAM for the ColabfoldDB

My plan is to use colabfold_batch --host-url myserver and submit the gpu part to our Slurm cluster. "myserver" should be strong enough. Would be 768G as a "minimum" sufficient or should I go higher? How many CPUs/Cores etc. should I order?

Are there any recommendations for CPU, SSD etc.? Which hardware is the public mmseqs server running on?
Should I ask this question in the mmseqs2-App repo?

Thanks for your recommendations in advance!

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with the README's ColabFoldDB memory guidance and the referenced mmseqs2-App context; no files, tests, or code entry points are named. Done would require a maintainer-provided hardware recommendation or documentation update covering memory, CPU, storage, and the appropriate repository.

Written by the indexing model from the issue text.

Assessment

Domain
bioinformatics
Issue type
Documentation
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
15/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.