Datasets
PDB-derived complexes curated for validation and testing.
Task
Protein–ligand pose prediction
Boltz-1 evaluates complex and interface predictions with both confidence-selected and best-of-sample reporting.
Sources
Boltz-1 Democratizing Biomolecular Interaction Modeling · Methods: Validation and test sets curation; Evaluation criteria; cached text lines 24–26, 158–160; comparative evaluation and ablation passagesOverview
Metrics
OpenStructure 2.8.0 computes LDDT-PLI, DockQ and ligand RMSD success. Interface values are averaged within complexes and then across complexes.
Allowed inputs
Protein/ligand descriptions for complex-structure prediction.
Sources
Boltz-1 Democratizing Biomolecular Interaction Modeling · Methods: Validation and test sets curation; Evaluation criteria; cached text lines 24–26, 158–160; comparative evaluation and ablation passagesEvaluation procedure diagram
How it worksComputational evaluation flow
Conceptual summary of the cited evaluation; exact task configuration and source version remain part of the protocol.
Sources
Boltz-1 Democratizing Biomolecular Interaction Modeling · Methods: Validation and test sets curation; Evaluation criteria; cached text lines 24–26, 158–160; comparative evaluation and ablation passageslimited source coverage · Automated source review, 2026-09-16. All specifications and missing details
Results
Results are available, but no reviewed comparison panel is linked in this release.
All evaluations
1 evaluation · 1 result. Different protocols are not a single leaderboard.
Filter evaluations
Applied filters: All linked evaluations
| Tested configuration | Protocol and dataset | Finding | Evidence and details |
|---|---|---|---|
| Configuration: Boltz-1 | Task: Protein–ligand pose prediction Dataset: Boltz-1 structure test set | 0.545 Top-1 ligand RMSD <2 Å rate unitless · unknown Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceBoltz-1: Protein–ligand pose prediction Highest-confidence pose from five samples; precomputed MSAs up to 4,096 sequences. Aggregation: Not reported Boltz-1 Democratizing Biomolecular Interaction Modeling · Table 1, 3 recycling rounds / 200 steps row, L-RMSD <2Å top-1 column |
Source checking is not independent reproduction. Release 2026-09-29-06401fd5b220.
Methods and evaluation design
Procedure, tasks and evaluated configurations
How it works
Evaluation methodology
PDB-derived complexes curated for validation and testing. OpenStructure 2.8.0 computes LDDT-PLI, DockQ and ligand RMSD success. Interface values are averaged within complexes and then across complexes. AlphaFold3 and Chai-1; Boltz-1x is assessed separately for physical-validity constraints.
Sources
Boltz-1 Democratizing Biomolecular Interaction Modeling · Methods: Validation and test sets curation; Evaluation criteria; cached text lines 24–26, 158–160; comparative evaluation and ablation passages; Methods: Validation and test sets curation; Evaluation criteria; cached text lines 24–26, 158–160; comparative evaluation and ablation passages; Methods: Validation and test sets curation; Evaluation criteria; cached text lines 24–26, 158–160; comparative evaluation and ablation passagesRecorded evaluations
Each evaluation records what was tested and under which conditions.
Run instructions
No runnable recipe has been reviewed for this task. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.
A task describes a biological question. Choose a linked protocol to obtain concrete split and scoring instructions.
Strengths, limitations and unresolved questions
Strengths and limitations
Strengths and considerations
No source-reviewed explanatory claims are recorded here yet.
Limitations and conditions
- Best-of-five is not equivalent to a deployable top-1 result. The summary does not infer a checkpoint or merge distinct evaluation subsets.
Sources
Boltz-1 Democratizing Biomolecular Interaction Modeling · Methods: Validation and test sets curation; Evaluation criteria; cached text lines 24–26, 158–160; comparative evaluation and ablation passages
Profile review details
Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged.
Stable record: reported-task-c04bb5ee6ecea6Specifications
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 |
|---|---|
| Datasets | PDB-derived complexes curated for validation and testing.SourcesBoltz-1 Democratizing Biomolecular Interaction Modeling · Methods: Validation and test sets curation; Evaluation criteria; cached text lines 24–26, 158–160; comparative evaluation and ablation passages |
| Splits | Validation and test structures are selected by release date and protein/ligand similarity exclusions. Test curation uses a 2023-01-13 cutoff relative to earlier structures; reported comparisons additionally restrict to structures all tested tools can process. CASP15 is evaluated as a separate collection.SourcesBoltz-1 Democratizing Biomolecular Interaction Modeling · Data pipeline: Validation and test sets curation; Evaluation filtering |
| Metrics | OpenStructure 2.8.0 computes LDDT-PLI, DockQ and ligand RMSD success. Interface values are averaged within complexes and then across complexes.SourcesBoltz-1 Democratizing Biomolecular Interaction Modeling · Methods: Validation and test sets curation; Evaluation criteria; cached text lines 24–26, 158–160; comparative evaluation and ablation passages |
| Baselines | AlphaFold3 and Chai-1; Boltz-1x is assessed separately for physical-validity constraints.SourcesBoltz-1 Democratizing Biomolecular Interaction Modeling · Methods: Validation and test sets curation; Evaluation criteria; cached text lines 24–26, 158–160; comparative evaluation and ablation passages |
| Leakage controls | Protein chains are excluded using sequence clusters formed at 40% identity. Ligand filtering requires at least one ligand sufficiently dissimilar to earlier ligands, rather than requiring every ligand to be novel. Test exclusion compares against all structures preceding the test cutoff.SourcesBoltz-1 Democratizing Biomolecular Interaction Modeling · Data pipeline §2.2 Validation and test sets curation, full-XML filter list |
| Uncertainty | Five samples per method are evaluated as both confidence-selected top-1 and oracle-best predictions; these are selection regimes, not confidence intervals.SourcesBoltz-1 Democratizing Biomolecular Interaction Modeling · Methods: Validation and test sets curation; Evaluation criteria; cached text lines 24–26, 158–160; comparative evaluation and ablation passages |
| Entity type | Paper-specific computational evaluation protocol.SourcesBoltz-1 Democratizing Biomolecular Interaction Modeling · Methods: Validation and test sets curation; Evaluation criteria; cached text lines 24–26, 158–160; comparative evaluation and ablation passages |
| Organisms | Evaluation spans PDB complexes and eligible CASP15 structures, grouped by molecular/interface type. Data curation and evaluation sections do not provide organism-stratified membership; taxonomy used to pair MSA rows is a separate input-processing property. · Not reported in inspected sourcesSourcesBoltz-1 Democratizing Biomolecular Interaction Modeling · Data pipeline: structural data and test curation; Evaluation |
| Assays | Protein–ligand complex structures.SourcesBoltz-1 Democratizing Biomolecular Interaction Modeling · Methods: Validation and test sets curation; Evaluation criteria; cached text lines 24–26, 158–160; comparative evaluation and ablation passages |
| Allowed inputs | Protein/ligand descriptions for complex-structure prediction.SourcesBoltz-1 Democratizing Biomolecular Interaction Modeling · Methods: Validation and test sets curation; Evaluation criteria; cached text lines 24–26, 158–160; comparative evaluation and ablation passages |
| Adaptation | Released structure prediction model; task-specific retraining is not established by this evaluation excerpt.SourcesBoltz-1 Democratizing Biomolecular Interaction Modeling · Methods: Validation and test sets curation; Evaluation criteria; cached text lines 24–26, 158–160; comparative evaluation and ablation passages |
Evidence
Source checking verifies the cited claim or transcription. It does not establish independent reproduction.
Papers and result coverage
Last literature check: 2026-09-17. Primary-source discovery and table/protocol screening; source checked is not independently reproduced. Raw acquisitions not automatically numerical publication approval.
| Paper or primary resource | Version | Reference |
|---|---|---|
| Boltz-1 Democratizing Biomolecular Interaction Modeling | PMC archival version PMC11601547.4 | Read source DOI: 10.1101/2024.11.19.624167 |
Historical gaps recorded on 2026-09-17
The catalogue now holds 1 result rows for this benchmark. A note below about pending extraction describes the state on 2026-09-17 and may since have been answered by a later batch. The result rows and their sources are the current record.
- Pose benchmark values are mainly in figures; Table 1 reports ablation/cycling conditions and cannot substitute for complete competitor pose matrix. Source artifacts acquired; no scores estimated from pixels.
Search and extraction details
source found structured extraction pending
Searches
- Boltz-1 Democratizing Biomolecular Interaction Modeling primary paper benchmark results
Evidence locations
- Main performance figures and Table1 ablation; sampling budget
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.
17 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Diagram caption Conceptual summary of the cited evaluation; exact task configuration and source version remain part of the protocol. Individual claims | Boltz-1 Democratizing Biomolecular Interaction Modeling Methods: Validation and test sets curation; Evaluation criteria; cached text lines 24–26, 158–160; comparative evaluation and ablation passages Version: PMC archival version PMC11601547.4 | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Diagram steps
| Boltz-1 Democratizing Biomolecular Interaction Modeling Methods: Validation and test sets curation; Evaluation criteria; cached text lines 24–26, 158–160; comparative evaluation and ablation passages Version: PMC archival version PMC11601547.4 | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Diagram title Computational evaluation flow Individual claims | Boltz-1 Democratizing Biomolecular Interaction Modeling Methods: Validation and test sets curation; Evaluation criteria; cached text lines 24–26, 158–160; comparative evaluation and ablation passages Version: PMC archival version PMC11601547.4 | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Datasets PDB-derived complexes curated for validation and testing. Individual claims | Boltz-1 Democratizing Biomolecular Interaction Modeling Methods: Validation and test sets curation; Evaluation criteria; cached text lines 24–26, 158–160; comparative evaluation and ablation passages Version: PMC archival version PMC11601547.4 | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Splits Validation and test structures are selected by release date and protein/ligand similarity exclusions. Test curation uses a 2023-01-13 cutoff relative to earlier structures; reported comparisons additionally restrict to structures all tested tools can process. CASP15 is evaluated as a separate collection. Individual claims | Boltz-1 Democratizing Biomolecular Interaction Modeling Data pipeline: Validation and test sets curation; Evaluation filtering Version: PMC archival version PMC11601547.4 | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Adaptation Released structure prediction model; task-specific retraining is not established by this evaluation excerpt. Individual claims | Boltz-1 Democratizing Biomolecular Interaction Modeling Methods: Validation and test sets curation; Evaluation criteria; cached text lines 24–26, 158–160; comparative evaluation and ablation passages Version: PMC archival version PMC11601547.4 | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Metrics OpenStructure 2.8.0 computes LDDT-PLI, DockQ and ligand RMSD success. Interface values are averaged within complexes and then across complexes. Individual claims | Boltz-1 Democratizing Biomolecular Interaction Modeling Methods: Validation and test sets curation; Evaluation criteria; cached text lines 24–26, 158–160; comparative evaluation and ablation passages Version: PMC archival version PMC11601547.4 | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Baselines AlphaFold3 and Chai-1; Boltz-1x is assessed separately for physical-validity constraints. Individual claims | Boltz-1 Democratizing Biomolecular Interaction Modeling Methods: Validation and test sets curation; Evaluation criteria; cached text lines 24–26, 158–160; comparative evaluation and ablation passages Version: PMC archival version PMC11601547.4 | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Leakage controls Protein chains are excluded using sequence clusters formed at 40% identity. Ligand filtering requires at least one ligand sufficiently dissimilar to earlier ligands, rather than requiring every ligand to be novel. Test exclusion compares against all structures preceding the test cutoff. Individual claims | Boltz-1 Democratizing Biomolecular Interaction Modeling Data pipeline §2.2 Validation and test sets curation, full-XML filter list Version: PMC archival version PMC11601547.4 | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Uncertainty Five samples per method are evaluated as both confidence-selected top-1 and oracle-best predictions; these are selection regimes, not confidence intervals. Individual claims | Boltz-1 Democratizing Biomolecular Interaction Modeling Methods: Validation and test sets curation; Evaluation criteria; cached text lines 24–26, 158–160; comparative evaluation and ablation passages Version: PMC archival version PMC11601547.4 | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Sources and history
View linked audit checks and correction history
Release 2026-09-29-06401fd5b220 · Record review: needs review
2 source records and release history
- Boltz-1 Democratizing Biomolecular Interaction Modeling · Original source · PMC archival version PMC11601547.4
- Boltz-1 Democratizing Biomolecular Interaction Modeling · Original source · PMC archival version PMC11601547.4
Technical metadata and extraction receipts
Stable ID: reported-task-c04bb5ee6ecea6
- areas
- molecular-interactions
- tasks
- Protein–ligand pose prediction
- entity level
- task
- version
- Not reported
- task
- Protein–ligand pose prediction
- scope note
- Paper-specific evaluation task; protocol completeness requires further extraction.
- benchmark research
- review date: 2026-09-17; status: source_found_structured_extraction_pending; primary sources: evidence-expansion-p2-boltz1-2025-1ebf712314d9; inspected locators: Main performance figures and Table1 ablation; sampling budget; searched queries: Boltz-1 Democratizing Biomolecular Interaction Modeling primary paper benchmark results; gaps: Pose benchmark values are mainly in figures; Table 1 reports ablation/cycling conditions and cannot substitute for complete competitor pose matrix. Source artifacts acquired; no scores estimated from pixels.; claim scope: Primary-source discovery and table/protocol screening; source checked is not independently reproduced. Raw acquisitions not automatically numerical publication approval.
- historical missing metadata
- protocol version: not_reported_in_legacy_extract; split: 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
- benchmark
- entity classification
- review date: 2026-09-17; rationale: This source-scoped record identifies the biological prediction task and holds its paper context. Preserve the existing task identity; exact split, model adaptation and scoring remain in linked evaluations or separate protocol records.; source ids: boltz1-2025; source locator: Methods: Validation and test sets curation; Evaluation criteria; cached text lines 24–26, 158–160; comparative evaluation and ablation passages; ambiguities: A paper- or suite-specific task may constrain some inputs or metrics; that alone does not make it interchangeable with a complete versioned protocol. No protocol equivalence is inferred.; Some legacy profile Entity type facts use the generic phrase computational evaluation protocol. That boilerplate is not sufficient to establish a single fixed protocol identity or to merge this task with another protocol record.
Related records
- dataset: Boltz-1 structure test set
- benchmark: Boltz-1: Protein–ligand pose prediction