Boltz-2 (AlphaFold3)
Open-source AlphaFold3-class model (Boltz-2) with built-in affinity prediction.
.webp)
Boltz-2 is the next-generation open-source deep-learning model family that reaches AlphaFold3-level accuracy for 3-D biomolecular complex prediction and adds a dedicated head for near-FEP binding-affinity estimation. Architectural depth, physics-aware Boltz-steering potentials, ensemble-based training, and fine-grained controllability together deliver fast, clash-free structures and quantitative interaction scores across proteins, nucleic acids, and small molecules. Released under the permissive MIT license, Boltz-2 ships with full training code, pretrained weights, and curated datasets to accelerate discovery in drug design and structural biology.
Estimated resource cost: 0.0024025
Categories: Structure Prediction & Folding
Tags: Co-Folding Conformation Generation Macrocyclic Nucleotides Protein Folding Proteins Protein–Ligand Docking Protein–Protein Docking Small Molecules
Key Capabilities
- Dedicated affinity-prediction head with near-FEP accuracy for binding-energy estimation.
- Ensemble-based training on NMR and MD trajectories to capture conformational dynamics.
- Fine-grained controllability via experimental-method, template, and pocket/distance constraints.
- Boltz-steering physics potentials yield clash-free, stereochemically correct structures.
- Deeper mixed-precision PairFormer (64 layers) with larger crops for faster inference on large complexes.
- Extended input representation (cyclic/modified flags, bond-order, symmetric positional encodings).
- Millions of curated biochemical-assay measurements for reliable affinity and generalization.
- Random MSA dropout and ensemble supervision boost single-sequence robustness.
Runtime Statistics
| Metric | Value |
|---|---|
| runtime_mean | 199 |
| runtime_median | 129 |
| runtime_std | 271 |
| runtime_90th_percentile | 380 |
| runtime_max | 9321 |
Similar Tools
- Boltz-1 (AlphaFold3)
- Chai-1 (AlphaFold3)
- IntelliFold (AlphaFold3)
- OpenFold3 (AlphaFold3)
Ready to submit your job?
Review your configuration, then confirm the estimated credit cost before you run the job. Note that credit estimates are not guaranteed and runtime can vary depending on inputs and settings.
Estimated Credits: 0.0024025
Invite-only, limited-time access. Please contact ztang@getantibody.com.
Invite-only, limited-time access. Please contact ztang@getantibody.com.