What it is
Chai-1 is a multi-modal biomolecular structure model on par with AlphaFold 3 for predicting proteins with ligands, nucleic acids and multimers. Chai Discovery (backed by OpenAI and Thrive) released it free for research and drug discovery, and followed with Chai-2 for zero-shot antibody design.
Evidence trail
BioAtlas keeps the path from source to decision visible. A connection records provenance; it does not imply that evidence is sufficient for every context.
Model passport
How Chai-1 / Chai-2 represents biology
Category is navigation. These fields describe the model-specific computational transformation and deliberately override broad category defaults.
Biological scale
Modalities & tasks
Registry, claims and frontier intelligence
Chai-2
2 version records · latest curated year 2025. Model-family identity remains separate from capability and access changes.
Explore version lineage →1 normalized claim
Biomolecular complex prediction · Complex and antibody-design evaluations
Open claim intelligence →3 connected frontiers
Open DDEs · Recent preprint
Inspect research horizon →Connected research frontiers
These records describe active research directions, not guaranteed capabilities of this model. Evidence stages and unresolved questions are preserved separately.
Open reproductions of frontier drug-design engines
Aureka AI OpenDDE project · 2026-07-04Can the community reproduce and extend proprietary all-atom drug-design engines with open training code, checkpoints and benchmarks?
Evidence boundary and unresolved questions
OpenDDE is a very recent July 2026 preprint. Its claimed parity has not yet received broad independent evaluation.
- Can external teams reproduce the reported training and benchmark results?
- What data provenance and leakage controls are documented?
- How do open checkpoints perform in prospective discovery projects?
open science · co-folding · reproducibility · scaling lawsOpen frontier record →Induced-fit co-folding beyond familiar targets
Isomorphic Labs · 2026-02-10Can structure models represent large ligand-driven protein rearrangements when the target, pocket or conformational transition is far from training examples?
Evidence boundary and unresolved questions
Out-of-distribution claims depend strongly on benchmark construction, training-set leakage controls and exact success thresholds.
- How are unseen chemotypes and target families isolated from training data?
- Does structural accuracy translate into enrichment or medicinal-chemistry decisions?
- How stable are alternative conformational ensembles?
co-folding · induced fit · OOD generalization · protein flexibilityOpen frontier record →High-fidelity antibody and biologic interfaces
Isomorphic Labs · 2026-02-10Can general co-folding models accurately resolve antibody–antigen and other biologic interfaces with low sequence homology?
Evidence boundary and unresolved questions
Benchmark composition, success thresholds and independent reproduction will determine how broadly the reported advantage generalizes.
- How does performance vary across CDR loops, nanobodies and multispecific formats?
- Can interface prediction improve prospective affinity maturation?
- How are glycosylation and conformational heterogeneity handled?
antibodies · biologics · interfaces · low homologyOpen frontier record →Inputs and outputs
Inputs
Biomolecular sequence / complex contextTarget or epitope context for design releasesOutputs
Complex structuresDesigned antibody / binder candidatesScientific and technical profile
Scientific principles
Technology
Scientific lineage
These are transparent concept matches—not claims that one scientist alone caused this model. Each connection is based on the model’s recorded domain, scientific principles, technical terms or an explicit lineage link.
Anfinsen’s dogma—the thermodynamic hypothesis
Christian B. AnfinsenProtein structure prediction, inverse folding and generative protein design all assume that sequence strongly constrains structure and function.
Denoising diffusion generative models
Jascha Sohl-Dickstein, Jonathan Ho and collaboratorsModern protein-backbone, molecular-pose and biomolecular-complex generators use diffusion to sample valid three-dimensional structures and designs.
Atomic structures of biologically important molecules by X-ray crystallography
Dorothy Crowfoot HodgkinStructure-based drug design depends on the experimental structural tradition she helped establish.
X-ray evidence for the helical structure of DNA
Rosalind Franklin & Raymond GoslingStructural genomics and sequence-to-structure reasoning began with experimentally grounded molecular geometry.
Levinthal’s paradox and efficient folding pathways
Cyrus LevinthalModern folding algorithms, energy landscapes, learned priors and diffusion models solve a constrained search problem rather than brute-force conformational enumeration.
The alpha helix, beta sheet and hydrogen-bonded protein structure
Linus Pauling, Robert Corey & Herman BransonProtein representation, fold recognition, structural priors and generative protein design all encode these recurring geometric motifs.
Evaluation evidence
Task-specific evidence only; not comparable as a universal leaderboard score.
Complex and antibody-design evaluations
Chai-2 · PoseBusters and complex-evaluation setsDeveloper-reported AF3-class complex-prediction performance.
Claim caveats
- Preprint and developer-reported comparisons require independent reproduction.
- Benchmark protocol and entity coverage determine comparability.
Known 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.
Milestones
Backed by OpenAI Startup Fund and Thrive Capital.
Chai-2 designs antibodies zero-shot in a 24-well plate.