Why this evidence?
It is linked to a specific model version, scientific task, dataset, split, metric and source. That makes the claim inspectable rather than a detached marketing score.
AlphaFold 2 / 3: Protein structure prediction
Top-performing CASP14 system; consult the primary paper for target-level metrics.
Model versionAlphaFold 3
TaskProtein structure prediction
DatasetCASP14 / complex evaluations
SplitCASP14 blinded targets
MetricStructure accuracy and confidence
Replicationmultiple-independent-uses
Reported byIndependent community assessment and model developers
Review statuscurated
Evidence confidence · strong
Confidence is multidimensional, not a universal model score.
Evidence completenessstrongModel version, task, dataset, split, metric, source and provenance fields.
Independent validationstrongmultiple-independent-uses
Source qualitystrongPeer-reviewed
Reproducibility evidencestrongReflects documented replication status, not a universal reproducibility score.
Version specificitystrongAlphaFold 3
Context applicabilitystrongDepends on task, split and explicit caveats; users must still validate their own context.
Contradiction reviewclearNo direct contradiction signal is currently queued.
BioAtlas reports evidence dimensions separately so a strong source cannot hide weak applicability, incomplete replication or unresolved contradiction.
Why?
Why should this evidence influence a decision?
Why not a universal score?
Performance can change with dataset, split, preprocessing, metric and context of use. BioAtlas therefore keeps confidence dimensions separate.
What could change the conclusion?
Independent replication, a better matched prospective dataset, a version change, a contradictory result or a more relevant validation protocol can reopen this evidence record.
Evidence boundary
What this claim does not prove.
- CASP performance does not establish equal accuracy for every target class or drug-relevant complex.
- AlphaFold 2 and AlphaFold 3 require separate evaluation contexts.
BioAtlas groups benchmark claims only when task, dataset, split, metric and protocol context align. This record is not a universal model score.
Model context
AlphaFold predicts a protein's 3D structure directly from its amino-acid sequence with near-experimental accuracy. AlphaFold 2 (2020) triggered a revolution at CASP14; AlphaFold 3 (2024, with Isomorphic Labs) extended prediction to proteins bound to ligands, DNA, RNA and ions — the interactions that matter for drugs. Hassabis and Jumper shared the 2024 Nobel Prize in Chemistry with David Baker.
Full evidence passport →Known model limitations
- Performance depends on the evaluation dataset and operating conditions.
- Task-specific benchmark results should not be compared across unlike domains.
- Outputs require task-specific scientific and experimental validation.