Variant evidence review
Use literature as source-linked evidence, not a shortcut to pathogenicity
A paper mentioning a variant is not automatically evidence that the variant is pathogenic. Agents should resolve identity first, preserve publication identifiers and distinguish association, functional observations and criterion-level use.
Agent question
Which publications are linked to this resolved variant, and what question does each source actually answer?
Compose through the canonical key
Resolve the public variant, then pass the returned canonical key to variant-linked literature search. Inspect publication details only for identifiers returned by the search.
Separate evidence roles
Report what a publication studies and whether the current structured result uses it. Do not infer causality, pathogenicity or criterion strength from title relevance alone.
- Resolved variant identity
- PMID or DOI
- Publication date
- Study design and population where stated
- Observed functional or clinical claim
- Whether the structured result applies a criterion
- Limitations and conflicting sources
Public references
Clinical and data boundary
Folklore Clinical Variant Interpretation MCP is published by Helena Bioinformatics. It accepts public variant-level queries only, not patient, phenotype, family, segregation or private case data. Its results are automated decision support for qualified professional review, not a diagnosis or treatment recommendation.