app/data/benchmarks/msa_alignment.json

{
  "category": "msa_alignment",
  "benchmarks": [
    {
      "name": "MSA_VALID_ALIGNMENT",
      "category": "msa_alignment",
      "description": "A multiple sequence alignment result must contain at least 2 aligned sequences.",
      "input": {"mode": "multi-sequence alignment"},
      "section": "msa",
      "expected_output": {"sequence_count": {"min": 2}},
      "tolerance": {},
      "ground_truth": "Biologically meaningful MSAs contain 2+ sequences; a count below 2 indicates a degenerate single-sequence alignment.",
      "citation": "Madeira F. et al. Nucleic Acids Res. 2022 (EBI ClustalO/MUSCLE services).",
      "source": "EBI Multiple Sequence Alignment",
      "stage": "curated",
      "difficulty": "easy",
      "version": 1
    },
    {
      "name": "MSA_ALIGNMENT_METHOD_RECORDED",
      "category": "msa_alignment",
      "description": "The alignment result must declare its alignment method (clustalo or muscle).",
      "input": {"mode": "multi-sequence alignment"},
      "section": "msa",
      "expected_output": {"method": {"contains": "clustal"}},
      "tolerance": {},
      "ground_truth": "Reproducibility ledger needs the aligner identity; the pipeline default tool is ClustalO.",
      "citation": "Madeira F. et al. Nucleic Acids Res. 2022.",
      "source": "EBI Multiple Sequence Alignment",
      "stage": "curated",
      "difficulty": "easy",
      "version": 1
    }
  ]
}