Fetch a predicted structure,
confidence attached.
AlphaFold predicted structures for nearly every known protein. alphafold_structure pulls the model for a UniProt accession with its confidence — a mean pLDDT and a PAE matrix — so an agent knows not just the fold but how much to trust it, sitting beside experimental PDB for comparison.
What the instrument does
AlphaFold DB (EMBL-EBI) hosts the DeepMind-predicted 3D structure for a UniProt protein, with per-residue confidence (pLDDT) and predicted aligned error (PAE) that quantify how reliable each region is.
On the console, alphafold_structure takes a UniProt accession and returns the model version, mean pLDDT, and download URLs for the CIF/PDB coordinates and the PAE.
Tools this powers on the console
alphafold_structure
Research use only. Service names belong to their owners; no partnership or endorsement is implied.
How Perslis integrates AlphaFold DB
Prediction is only useful with its confidence attached, so the instrument never returns a fold without its pLDDT. A high score (hemoglobin's is 98.06) says the model is reliable; a low one is a warning the console passes through unedited rather than hiding.
Because AlphaFold keys on the same UniProt accession as everything else on the protein bench, a predicted model and an experimental PDB structure line up for one protein automatically — the anchor is what lets the console show measured and predicted side by side.
Ask
One question at the console — no per-service query language, no tab-hopping.
Route
Lois calls this instrument alongside the others and gathers what returns.
Pin
Every field keeps its source: database, accession, URL. A result that cannot name its source is refused by construction.
Admit
The PEEL gate decides what enters the lab record. Reported values stay verbatim; unsupported claims stay out.
A real, source-pinned result
Pulled live from the service and pinned to its identifier — the same contract every answer on the console is held to.
| Protein | HBA_HUMAN (Hemoglobin subunit alpha) |
|---|---|
| Model version | v6 |
| Mean pLDDT | 98.06 (very high confidence) |
| Coordinates | AF-P69905-F1-model_v6.cif / .pdb |
| PAE | predicted_aligned_error_v6.json |
Source: alphafold · P69905 · retrieved 2026-09-18
Why route AlphaFold through one console
Prediction with a trust score
Every model returns its pLDDT — an agent weighs the fold instead of assuming it.
Predicted beside measured
The shared UniProt accession lines an AlphaFold model up against its experimental PDB structure.
Low confidence is not hidden
A weak pLDDT is passed through verbatim — the console reports uncertainty, it does not smooth it away.
Instruments AlphaFold talks to
A prediction earns its place beside the measurement. AlphaFold answers next to UniProt, PDB and InterPro.
UniProt
Curated proteins — function, disease links, domains, sequence.
uniprot_search · uniprot_entry
RCSB PDB
Experimental structures — method, resolution, primary citation.
pdb_search · pdb_entryInterPro
Protein families, domains and sites — and an honest zero when nothing matches.
interpro_domains · interpro_entry