MODEL INTELLIGENCE / VERIFIED RESEARCH
RoseTTAFold3 (RF3)
RosettaCommons all-atom biomolecular structure prediction in Foundry.
Developer: Institute for Protein Design / RosettaCommons, University of Washington
Overview
- Developer
- Institute for Protein Design / RosettaCommons, University of Washington
- Category
- structure and complex prediction
- Commercial rights
- Commercial OK
- License fee
- No license fee identified
- Open weights
- Yes
- Last verified
- 2026-10-16
- Added to FoldScout
- 2026-10-16
Capabilities
Foundry's RF3 biomolecular structure prediction model, including protein-containing complexes; it accepts structure/sequence inputs and predicts atomic coordinates and confidence signals. Outputs are computational predictions, not affinity measurements.
When to use it
Use RF3 to predict biomolecular complexes and independently assess candidate structures alongside Boltz or other methods. Predictions require uncertainty checks and experimental validation.
Compute
Compute classification: single-gpu. This is a planning estimate, not a throughput benchmark; check the linked model installation documents for exact requirements.
Commercial licensing
Commercial permission — Commercial OK
Foundry's root BSD-3-Clause LICENSE.md explicitly covers source code and referenced model checkpoints; commercial use is permitted with preservation of attribution and no endorsement. Review any separately sourced component or data.
License fee — No license fee identified
The official Foundry code and referenced checkpoints have no commercial license fee; infrastructure and outside dependencies may cost money.
Free downloads do not necessarily permit company use. Code, checkpoints, external dependencies and compute expenses require separate review.
Official references
From computational design to experimental evidence
Validate your designed binder.
Seq2Study connects AI-designed proteins and antibodies with expression, affinity, stability and developability testing.