uniprot_get_evidence_summary
Summarizes ECO evidence codes for a UniProt entry, computing a confidence score (0-100) based on experimental, manual, and automatic annotations to distinguish wet-lab confirmed from computationally inferred evidence.
Instructions
Summarise and grade the ECO (Evidence and Conclusion Ontology) codes
attached to a UniProt entry's annotations. Counts how many features and
comments cite each evidence code, then classifies every occurrence as
experimental (wet-lab, ECO:0000269), manual (curator-reviewed inference),
or automatic (un-reviewed pipeline call) and collapses that into a single
0-100 evidence-confidence score with a high / moderate / low / very-low
band. A score near 100 means the entry is dominated by direct experimental
evidence; a score near 10 means it is almost entirely computationally
inferred. Critical for any downstream agent that must distinguish
'wet-lab confirmed' annotations from 'inferred by similarity'. JSON output
adds an evidence_confidence block (score, band, per-class breakdown,
weights) alongside the raw evidence_counts.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| accession | Yes | UniProt accession, e.g. 'P04637' (human TP53) or 'P38398' (human BRCA1). Both reviewed (Swiss-Prot) and unreviewed (TrEMBL) accessions are accepted; case-sensitive. | |
| response_format | No | 'markdown' (default) for a human-readable report with a provenance footer, or 'json' for a machine-parseable structured payload with the same data. Any other value is rejected. | markdown |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |