sokrypton / sokrypton/ColabFold
update container to support gpuserver
Open
Nobody has claimed this yet.
- Dominant language
- Jupyter Notebook
- Stars
- 2.9k
- Forks
- 747
- PR merge metrics
- No merged PRs in 30d
Description
I made an apptainer container from:
ghcr.io/sokrypton/colabfold:1.5.5-cuda12.2.2
When I run colabfold_search
I get the error:
colabfold_search [-h] [-s S] [--db1 DB1] [--db2 DB2] [--db3 DB3]
[--use-env {0,1}] [--use-templates {0,1}]
[--filter {0,1}] [--mmseqs MMSEQS]
[--expand-eval EXPAND_EVAL] [--align-eval ALIGN_EVAL]
[--diff DIFF] [--qsc QSC] [--max-accept MAX_ACCEPT]
[--pairing_strategy PAIRING_STRATEGY]
[--db-load-mode DB_LOAD_MODE] [--threads THREADS]
query dbbase base
colabfold_search: error: unrecognized arguments: --gpu-server --prefilter-mode --gpu cleaned_contigs.fasta /data/sequence_databases/colabfold_db msas
I guess because the container has not been updated with recent releases that inculde colabfold_search --gpu-server
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by locating the Apptainer container definition used for ghcr.io/sokrypton/colabfold:1.5.5-cuda12.2.2 and inspect how colabfold_search is installed. Reproduce the shown command and compare the available options with the requested --gpu-server, --prefilter-mode, and --gpu arguments. Done means the container accepts that command without the unrecognized-arguments error.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- github
- Domain
- bioinformatics, devops
- Issue type
- Feature
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100