Exception: MMseqs2 API is giving errors.

Expected Behavior

Colabfold outputs 5 models.

Current Behavior

Error in the Run Prediction cell

Steps to Reproduce (for bugs)

query sequence: "GAGAGAGAGAGAGAGAGAGAGAGAGAGAGA"

ColabFold Output (for bugs)

2023-10-17 10:51:18,684 Running on GPU
2023-10-17 10:51:18,687 Found 4 citations for tools or databases
2023-10-17 10:51:18,688 Query 1/1: TESTgaga_f5906 (length 30)
PENDING: 0%| | 0/150 [elapsed: 00:00 remaining: ?]
2023-10-17 10:51:19,292 Sleeping for 9s. Reason: PENDING
ERROR: 0%| | 0/150 [elapsed: 00:10 remaining: ?]
2023-10-17 10:51:28,948 Could not get MSA/templates for TESTgaga_f5906: MMseqs2 API is giving errors. Please confirm your input is a valid protein sequence. If error persists, please try again an hour later.
Traceback (most recent call last):
File "/content/colabfold/batch.py", line 1384, in run
= get_msa_and_templates(jobname, query_sequence, a3m_lines, result_dir, msa_mode, use_templates,
File "/content/colabfold/batch.py", line 820, in get_msa_and_templates
a3m_lines = run_mmseqs2(
File "/content/colabfold/colabfold.py", line 238, in run_mmseqs2
raise Exception(f'MMseqs2 API is giving errors. Please confirm your input is a valid protein sequence. If error persists, please try again an hour later.')
Exception: MMseqs2 API is giving errors. Please confirm your input is a valid protein sequence. If error persists, please try again an hour later.
2023-10-17 10:51:28,948 Done

Context

This error persists both using the Colab Notebook and using the local colabfold_batch.
Is the only peptide sequence from a varied and vast list that results in this error.

Your Environment

Include as many relevant details about the environment you experienced the bug in.
NOTEBOOK

• ColabFold v1.5.2-patch: AlphaFold2 using MMseqs2
  LOCAL
• Operating system and version: Ubuntu 16.04.7 LTS; Cuda compilation tools, release 11.0, V11.0.167

Start with the Run Prediction path in colabfold/batch.py, especially get_msa_and_templates, and then inspect run_mmseqs2 in colabfold/colabfold.py using the reported peptide sequence. Compare the notebook and local colabfold_batch behavior and determine why this sequence receives the MMseqs2 API error. Done means the cause is identified and the reported sequence is handled or the failure is clearly explained.