# Seeing the shape of life.

Researchers used AlphaFold to predict protein structures with accuracy competitive with experimental structures on many CASP14 targets. Bright's interactive p53 view uses a separate, later AlphaFold DB prediction: human p53 AF-P04637-F1 model v6, created on 2025-08-01.

Canonical: https://brightaifuture.com/discoveries/alphafold
Format: story
Source publication: 2021-07-15
Bright publication: 2026-09-05
Substantive update: 2026-09-08
Evidence and review: Demonstrated; confidence: unassessed; source-checked; legacy source check. Legacy source check; no named human reviewer is recorded in this projection.

## The human problem

A protein’s shape helps explain its function, but determining that shape can be difficult.

## The prior constraint

Experimental structure determination required specialized instruments and substantial work.

## AI’s actual role

A neural network integrated sequence and structural information to predict three-dimensional structure.

## The documented result

Strong performance in the blind CASP14 assessment.

## Why it may matter

Researchers gained another way to investigate biological mechanisms.

## Limitations

Predictions carry uncertainty. A predicted structure does not establish function or prove a treatment works.

The p53 view is a static single-chain prediction, not an experimental structure or a simulation of protein folding.

The model's pLDDT values describe local confidence and do not establish the arrangement of distant regions.

## Unresolved questions

Combine predictions with experiments and investigate harder biological systems.

## Provenance and history

{
  "dates": {
    "eventDate": null,
    "publicationDate": "2021-07-15",
    "captureDate": null,
    "lastReviewedDate": "2026-09-05"
  },
  "provenance": {
    "origin": "legacy-projection",
    "externalId": "alphafold"
  },
  "revisions": [
    {
      "id": "revision:before:correction:93390fe58fc2e79c464f",
      "recordedAt": "2026-09-08",
      "summary": "Assessment before correction: Clarified that Bright's p53 view uses the 2025 AlphaFold DB AF-P04637-F1 model v6 asset, while the discovery's scientific claim and publication date remain those of the 2021 AlphaFold paper. Added the model source and the limits of the predicted single-chain view.",
      "sourceIds": [],
      "snapshot": {
        "plainLanguage": "Researchers used AlphaFold to predict protein structures with accuracy competitive with experimental structures on many CASP14 targets.",
        "limitations": [
          "Predictions carry uncertainty. A predicted structure does not establish function or prove a treatment works."
        ],
        "sources": [
          {
            "id": "source:alphafold",
            "title": "Highly accurate protein structure prediction with AlphaFold · Nature",
            "url": "https://www.nature.com/articles/s41586-021-03819-2",
            "type": "paper"
          }
        ]
      }
    }
  ],
  "corrections": [
    {
      "id": "correction:93390fe58fc2e79c464f",
      "issuedAt": "2026-09-08",
      "summary": "Clarified that Bright's p53 view uses the 2025 AlphaFold DB AF-P04637-F1 model v6 asset, while the discovery's scientific claim and publication date remain those of the 2021 AlphaFold paper. Added the model source and the limits of the predicted single-chain view.",
      "sourceIds": [],
      "supersedesRevisionId": "revision:before:correction:93390fe58fc2e79c464f",
      "reviewerId": "codex-ai-assisted",
      "sourceUrl": "https://alphafold.ebi.ac.uk/files/AF-P04637-F1-model_v6.pdb"
    }
  ]
}

## Original sources

- [Highly accurate protein structure prediction with AlphaFold · Nature](https://www.nature.com/articles/s41586-021-03819-2)
- [AlphaFold DB human p53 AF-P04637-F1 model v6](https://alphafold.ebi.ac.uk/files/AF-P04637-F1-model_v6.pdb)

## Continue exploring

- [Concise evidence record](https://brightaifuture.com/discoveries/alphafold)