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.
RoseTTAFold / All-Atom: Protein structure prediction
Competitive three-track structure prediction reported in the primary publication.
Model versionRoseTTAFold All-Atom
TaskProtein structure prediction
DatasetCASP14 / complex modelling
SplitCASP14 and held-out structure targets
MetricStructure prediction
Replicationindependent-use-documented
Reported byModel developers with community benchmark context
Review statuscurated
Evidence confidence · moderate
Confidence is multidimensional, not a universal model score.
Evidence completenessstrongModel version, task, dataset, split, metric, source and provenance fields.
Independent validationmoderateindependent-use-documented
Source qualitystrongPeer-reviewed
Reproducibility evidencemoderateReflects documented replication status, not a universal reproducibility score.
Version specificitystrongRoseTTAFold All-Atom
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.
- Results across RoseTTAFold generations are not interchangeable.
- All-atom complex evaluation requires a task-specific benchmark.
BioAtlas groups benchmark claims only when task, dataset, split, metric and protocol context align. This record is not a universal model score.
Model context
RoseTTAFold introduced a 'three-track' architecture reasoning jointly over sequence, distances and coordinates. RoseTTAFold All-Atom (2024) models proteins together with small molecules, nucleic acids and covalent modifications. David Baker's lab is the epicenter of open protein AI and shared the 2024 Nobel Prize in Chemistry.
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.