Model type
Biomolecular structure predictor; this record is the paper-specific evaluated configuration.
Configuration
Chai-1
This structure-prediction configuration is evaluated for antibody–antigen complex and interface quality.
Sources
Enhancing antibody-antigen interaction prediction with atomic flexibility · Results/Fold quality affects predictive performance/Folding quality declines across models without MSAs or templates. (paragraph 3); Results/Fold quality affects predictive performance/AF3 and Chai-1 (no-MSA/template) effectively preserve prediction quality. (paragraph 3)How it worksEvaluated procedure (conceptual)
Conceptual input–method–output guide. Check the procedure text and linked evaluation for fitted components, additional inputs and exact settings.
Sources
Enhancing antibody-antigen interaction prediction with atomic flexibility · Results/Fold quality affects predictive performance/Folding quality declines across models without MSAs or templates. (paragraph 3); Results/Fold quality affects predictive performance/Folding quality declines across models without MSAs or templates. (paragraph 2)At a glance
Biological inputs
Antibody and antigen sequences; MSA/template availability is explicitly configuration-dependent.
Sources
Enhancing antibody-antigen interaction prediction with atomic flexibility · Results/Flexibility improves antibody-antigen interaction prediction/Binary flexibility patterns emerge despite linear flexibility modeling. (paragraph 3); Results/Flexibility improves antibody-antigen interaction prediction (paragraph 1)Outputs
Predicted antibody–antigen complex coordinates
Sources
Enhancing antibody-antigen interaction prediction with atomic flexibility · Results/Fold quality affects predictive performance/Folding quality declines across models without MSAs or templates. (paragraph 1); Results/Fold quality affects predictive performance/AF3 and Chai-1 (no-MSA/template) effectively preserve prediction quality. (paragraph 3)limited source coverage · Automated source review, 2026-09-16. All specifications and missing details
Evaluations and results
Release 2026-09-17-d277315f7d76 · 1 evaluation · 1 metric row. Different protocols are not a single leaderboard.
| Metric and finding | Coverage and uncertainty | Evidence |
|---|---|---|
| Chai-1: Antibody–antigen interaction prediction using folded complexes Configuration: Chai-1Task: Antibody–antigen interaction prediction using folded complexesDataset: Antibody–antigen GEP test set Interaction classifier evaluated using Chai-1-folded input complexes; this is pipeline AUC, not DockQ. Independent external evaluation · Evaluation metadata: needs review | ||
| 0.86 AUC-ROC Unit: unitless · Direction: unknown | Uncertainty: ± 0.07 Scored: Not reported · Eligible: Not reported | source checkedEnhancing antibody-antigen interaction prediction with atomic flexibility · Table 5, Folded row, Chai-1 (no MSA) column Source checking is not independent reproduction. |
How it works
How the evaluated method works
The generative co-folding predictor builds antibody–antigen structures that are then assessed for interface quality and downstream paratope/epitope prediction.
Sources
Enhancing antibody-antigen interaction prediction with atomic flexibility · Results/Fold quality affects predictive performance/Folding quality declines across models without MSAs or templates. (paragraph 3); Results/Fold quality affects predictive performance/Folding quality declines across models without MSAs or templates. (paragraph 2)Underlying method and version boundaries
Chai-1 predicts biomolecular structures through the released inference implementation. Its input options, MSA/template use and sampling budget are part of each evaluated configuration.
Sources
github.com/chaidiscovery/chai-lab README.md · README.md; introduction, model description, pretrained-model and usage sections at pinned revisionWhat was evaluated
The linked evaluation record identifies Chai-1: Antibody–antigen interaction prediction using folded complexes. Its dataset, split, adaptation and evidence origin remain attached to the reported results.
Sources
Enhancing antibody-antigen interaction prediction with atomic flexibility · The named evaluation’s methods and comparison table; exact preserved evaluation IDs: evaluation-lit-b3-037Strengths and limitations
Strengths and considerations
- Examines how predicted structures affect downstream interface-site analysis.
Sources
Enhancing antibody-antigen interaction prediction with atomic flexibility · Results/Fold quality affects predictive performance/Folding quality declines across models without MSAs or templates. (paragraph 3); Results/Fold quality affects predictive performance/AF3 and Chai-1 (no-MSA/template) effectively preserve prediction quality. (paragraph 4)
Limitations and conditions
- The paper reports configuration-dependent differences and limited antibody–antigen accuracy; general complex-folding scores cannot substitute for this task.
Sources
Enhancing antibody-antigen interaction prediction with atomic flexibility · Results/Flexibility improves antibody-antigen interaction prediction/Binary flexibility patterns emerge despite linear flexibility modeling. (paragraph 3); Results/Fold quality affects predictive performance (paragraph 1)
Profile review details
Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction.
Stable record: reported-model-b3fdf259d51533Specifications
Inputs, training, access and other details
Explanatory profile: limited source coverage · Automated source review, 2026-09-16. Review applies to the cited claims; unresolved fields are listed below. Numerical results retain their own review status.
| Property | Description and evidence |
|---|---|
| Model type | Biomolecular structure predictor; this record is the paper-specific evaluated configuration.Sourcesgithub.com/chaidiscovery/chai-lab README.md · README.md model description |
| Architecture / procedure | The generative co-folding predictor builds antibody–antigen structures that are then assessed for interface quality and downstream paratope/epitope prediction.SourcesEnhancing antibody-antigen interaction prediction with atomic flexibility · Results/Fold quality affects predictive performance/Folding quality declines across models without MSAs or templates. (paragraph 3); Results/Fold quality affects predictive performance/Folding quality declines across models without MSAs or templates. (paragraph 2) |
| Biological inputs | Antibody and antigen sequences; MSA/template availability is explicitly configuration-dependent.SourcesEnhancing antibody-antigen interaction prediction with atomic flexibility · Results/Flexibility improves antibody-antigen interaction prediction/Binary flexibility patterns emerge despite linear flexibility modeling. (paragraph 3); Results/Flexibility improves antibody-antigen interaction prediction (paragraph 1) |
| Outputs | Predicted antibody–antigen complex coordinatesSourcesEnhancing antibody-antigen interaction prediction with atomic flexibility · Results/Fold quality affects predictive performance/Folding quality declines across models without MSAs or templates. (paragraph 1); Results/Fold quality affects predictive performance/AF3 and Chai-1 (no-MSA/template) effectively preserve prediction quality. (paragraph 3) |
| Parameters | An aggregate parameter total for this exact evaluated configuration is not established by the inspected sources. · Not reported in inspected sourcesSources (2)Enhancing antibody-antigen interaction prediction with atomic flexibility; github.com/chaidiscovery/chai-lab README.md · Materials and methods; Materials and methods/Dataset; Materials and methods/Method; Materials and methods/Method/Data representation.; Materials and methods/Method/Flexibility score with ESMFold.; Materials and methods/Method/Model architecture.; inspected for aggregate parameter count (component sizes are not added without an exact configuration); README.md at pinned repository revision |
| Known versions / configuration | Chai-1 without MSA/template information in the identified comparisonSourcesEnhancing antibody-antigen interaction prediction with atomic flexibility · Table pcbi.1013576.t005 (paragraph 1); Results/Fold quality affects predictive performance/Folding quality declines across models without MSAs or templates. (paragraph 1) |
| Training data / fitting | The released source implementation supplies prefolded antibody–antigen complexes for the GEP test set, with neither MSAs nor templates. No retraining of the structure predictor is described; downstream interface prediction is a separate component.SourcesEnhancing antibody-antigen interaction prediction with atomic flexibility · Results / Fold quality affects predictive performance |
| Context limits | A maximum input/context length for this exact evaluated configuration is not established by the inspected sources. · Not reported in inspected sourcesSources (2)Enhancing antibody-antigen interaction prediction with atomic flexibility; github.com/chaidiscovery/chai-lab README.md · Materials and methods; Materials and methods/Dataset; Materials and methods/Method; Materials and methods/Method/Data representation.; Materials and methods/Method/Flexibility score with ESMFold.; Materials and methods/Method/Model architecture.; inspected for explicit maximum input length (dataset lengths and family-wide limits are not substituted); README.md at pinned repository revision |
| Access | Official upstream implementation and usage documentation: https://github.com/chaidiscovery/chai-lab/blob/66c38d1fe5c6756a89ff8596b1dea87d305ec06f/README.md. This pinned documentation revision is not automatically the evaluated weight revision.Sourcesgithub.com/chaidiscovery/chai-lab README.md · README.md; installation, model download and usage instructions |
| Code licence | Apache 2.0 (upstream repository code at the cited revision; this does not establish every dependency or historical checkpoint licence).Sourcesgithub.com/chaidiscovery/chai-lab LICENSE · LICENSE; complete licence text |
| Weights licence | Apache 2.0 for both Chai-1 code and model weights, explicitly stated in the official README; paper-specific derived artifacts are separate.Sourcesgithub.com/chaidiscovery/chai-lab README.md · README.md; Licence section |
Evidence table
Inspect claims, sources and review details
Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.
One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.
22 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Diagram caption Conceptual input–method–output guide. Check the procedure text and linked evaluation for fitted components, additional inputs and exact settings. Individual claims | Enhancing antibody-antigen interaction prediction with atomic flexibility Results/Fold quality affects predictive performance/Folding quality declines across models without MSAs or templates. (paragraph 3); Results/Fold quality affects predictive performance/Folding quality declines across models without MSAs or templates. (paragraph 2) Version: version of record | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Diagram steps ["Antibody and antigen sequences","Chai-1","Predicted antibody–antigen complex coordinates"] Individual claims | Enhancing antibody-antigen interaction prediction with atomic flexibility Results/Fold quality affects predictive performance/Folding quality declines across models without MSAs or templates. (paragraph 3); Results/Fold quality affects predictive performance/Folding quality declines across models without MSAs or templates. (paragraph 2) Version: version of record | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Diagram title Evaluated procedure (conceptual) Individual claims | Enhancing antibody-antigen interaction prediction with atomic flexibility Results/Fold quality affects predictive performance/Folding quality declines across models without MSAs or templates. (paragraph 3); Results/Fold quality affects predictive performance/Folding quality declines across models without MSAs or templates. (paragraph 2) Version: version of record | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Model type Biomolecular structure predictor; this record is the paper-specific evaluated configuration. Individual claims | github.com/chaidiscovery/chai-lab README.md README.md model description Version: 66c38d1fe5c6756a89ff8596b1dea87d305ec06f | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Architecture / procedure The generative co-folding predictor builds antibody–antigen structures that are then assessed for interface quality and downstream paratope/epitope prediction. Individual claims | Enhancing antibody-antigen interaction prediction with atomic flexibility Results/Fold quality affects predictive performance/Folding quality declines across models without MSAs or templates. (paragraph 3); Results/Fold quality affects predictive performance/Folding quality declines across models without MSAs or templates. (paragraph 2) Version: version of record | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Weights licence Apache 2.0 for both Chai-1 code and model weights, explicitly stated in the official README; paper-specific derived artifacts are separate. Individual claims | github.com/chaidiscovery/chai-lab README.md README.md; Licence section Version: 66c38d1fe5c6756a89ff8596b1dea87d305ec06f | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Biological inputs Antibody and antigen sequences; MSA/template availability is explicitly configuration-dependent. Individual claims | Enhancing antibody-antigen interaction prediction with atomic flexibility Results/Flexibility improves antibody-antigen interaction prediction/Binary flexibility patterns emerge despite linear flexibility modeling. (paragraph 3); Results/Flexibility improves antibody-antigen interaction prediction (paragraph 1) Version: version of record | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Outputs Predicted antibody–antigen complex coordinates Individual claims | Enhancing antibody-antigen interaction prediction with atomic flexibility Results/Fold quality affects predictive performance/Folding quality declines across models without MSAs or templates. (paragraph 1); Results/Fold quality affects predictive performance/AF3 and Chai-1 (no-MSA/template) effectively preserve prediction quality. (paragraph 3) Version: version of record | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Parameters An aggregate parameter total for this exact evaluated configuration is not established by the inspected sources. Individual claims | Enhancing antibody-antigen interaction prediction with atomic flexibility Materials and methods; Materials and methods/Dataset; Materials and methods/Method; Materials and methods/Method/Data representation.; Materials and methods/Method/Flexibility score with ESMFold.; Materials and methods/Method/Model architecture.; inspected for aggregate parameter count (component sizes are not added without an exact configuration); README.md at pinned repository revision Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: version of record | unreported automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Parameters An aggregate parameter total for this exact evaluated configuration is not established by the inspected sources. Individual claims | github.com/chaidiscovery/chai-lab README.md Materials and methods; Materials and methods/Dataset; Materials and methods/Method; Materials and methods/Method/Data representation.; Materials and methods/Method/Flexibility score with ESMFold.; Materials and methods/Method/Model architecture.; inspected for aggregate parameter count (component sizes are not added without an exact configuration); README.md at pinned repository revision Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 66c38d1fe5c6756a89ff8596b1dea87d305ec06f | unreported automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Sources and history
Release 2026-09-17-d277315f7d76 · Record review: needs review
3 source records and release history
- Enhancing antibody-antigen interaction prediction with atomic flexibility · Original source · version of record
- github.com/chaidiscovery/chai-lab README.md · Original source · 66c38d1fe5c6756a89ff8596b1dea87d305ec06f
- github.com/chaidiscovery/chai-lab LICENSE · Original source · 66c38d1fe5c6756a89ff8596b1dea87d305ec06f
Technical metadata and extraction receipts
Stable ID: reported-model-b3fdf259d51533
- areas
- molecular-interactions
- entity level
- method
- version
- Not reported
- reported name
- Chai-1
- historical missing metadata
- version: not_reported_in_legacy_extract; checkpoint revision: not_reported_in_legacy_extract; training data: not_reported_in_legacy_extract; licence: not_reported_in_legacy_extract
- metadata review scope
- historical_missing_metadata preserves the original discovery state. Current descriptive evidence and missingness are recorded in profile.facts; numerical-result review is separate.
- legacy kinds
- model
- entity classification
- review date: 2026-09-17; rationale: This source-scoped entry preserves the method/configuration actually named in an evaluation. It is neither a global family identity nor proof of an immutable checkpoint; the linked evaluation retains adaptation, fitting and scoring details.; source ids: antibody-flexibility-2025; evidence-reported-base-chai-readme-md; source locator: Results/Fold quality affects predictive performance/Folding quality declines across models without MSAs or templates. (paragraph 3); Results/Fold quality affects predictive performance/Folding quality declines across models without MSAs or templates. (paragraph 2) | README.md model description | Results/Fold quality affects predictive performance/Folding quality declines across models without MSAs or templates. (paragraph 3); Results/Fold quality affects predictive performance/AF3 and Chai-1 (no-MSA/template) effectively preserve prediction quality. (paragraph 3); ambiguities: Configuration means the source-labelled evaluated identity. It does not establish missing checkpoint hashes, default settings or equivalence to same-named records in other papers.