sokrypton / sokrypton/ColabFold

issue about MSA server storage space

Open
#827 5 comments 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

Hello. I am posting this because I encountered the following error. It seems to be an error caused by insufficient storage space. Is there a way to fix this?

MSA server enabled: https://api.colabfold.com
MSA server authentication: no credentials provided
Checking input data.
Found 0 existing processed inputs, skipping them.
Processing 1 inputs with 1 threads.
0%| | 0/1 [00:00<?, ?it/s]Generating MSA for batch_inputs_ab_only_top0001/nb_0001.yaml with 2 protein entities.
Calling MSA server for target nb_0001 with 2 sequences
MSA server URL: https://api.colabfold.com
MSA pairing strategy: greedy
No authentication provided for MSA server
Server didn't reply with json: mkdir /mnt/scratch/mmirdit/jobs/YuTOikp-5lZxanD0b_mUo8UZ-UdSAyMfta-hPw: no space left on device0 remaining: ?]

SUBMIT: 0%| | 0/300 [elapsed: 00:05 remaining: ?]
Traceback (most recent call last):
File "/lwork01/boltz/src/boltz/main.py", line 588, in process_input
compute_msa(
File "/lwork01/boltz/src/boltz/main.py", line 470, in compute_msa
paired_msas = run_mmseqs2(
^^^^^^^^^^^^
File "/lwork01/boltz/src/boltz/data/msa/mmseqs2.py", line 215, in run_mmseqs2
raise Exception(msg)
Exception: MMseqs2 API is giving errors. Please confirm your input is a valid protein sequence. If error persists, please try again an hour later.
Failed to process batch_inputs_ab_only_top0001/nb_0001.yaml. Skipping. Error: MMseqs2 API is giving errors. Please confirm your input is a valid protein sequence. If error persists, please try again an hour later..
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:05<00:00, 5.79s/it]
Using bfloat16 Automatic Mixed Precision (AMP)
GPU available: True (cuda), used: True
TPU available: False, using: 0 TPU cores
HPU available: False, using: 0 HPUs
/opt/conda/envs/boltz/lib/python3.11/site-packages/pytorch_lightning/trainer/connectors/logger_connector/logger_connector.py:76: Starting from v1.9.0, tensorboardX has been removed as a dependency of the pytorch_lightning package, due to potential conflicts with other packages in the ML ecosystem. For this reason, logger=True will use CSVLogger as the default logger, unless the tensorboard or tensorboardX packages are found. Please pip install lightning[extra] or one of them to enable TensorBoard support by default
(boltz) user1@G81-83-0:/lwork01/AntiBMPNN$

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 boltz/data/msa/mmseqs2.py around run_mmseqs2 and boltz/main.py around compute_msa, then review the reported MSA server response from https://api.colabfold.com. Confirm whether the failure is caused by the server's full /mnt/scratch storage rather than the input sequence, and document or implement the repository-supported remediation if one exists.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
bioinformatics, infrastructure
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.