Benchmark

CAPRI

CAPRI assesses blind predictions of protein-complex structures supplied before experimental publication.

Sources

capri official source · Official CAPRI homepage: introductory description

100 evaluations · 400 results

Overview

Datasets

Challenge-round protein-complex targets supplied by experimental contributors.

Sources

capri official source · Official CAPRI homepage: introductory description

Metrics

Interface contact recovery (Fnat), interface RMSD and ligand RMSD define classical CAPRI quality classes. DockQ combines these complementary structural measures into a continuous score.

Sources

dockq primary benchmark evidence · Introduction and Methods: CAPRI criteria and DockQ

Allowed inputs

Target information distributed for each challenge round.

Sources

capri official source · Official CAPRI homepage: introductory description

Evaluation procedure diagram

How it worksEvaluation procedure

Conceptual procedure. Task variants and protocol versions retain their separate scoring conditions.

Sources (2)

capri official source; dockq primary benchmark evidence · Official CAPRI homepage: introductory description; Introduction and Methods: CAPRI criteria and DockQ

limited source coverage · Automated source review, 2026-09-16. All specifications and missing details

Results

Each comparison retains its reviewed evaluation scope, dataset and metric. Results are shown without a pooled ranking.

Find a protocol, dataset or metric

Evaluation scope and datasetMetric and reported setup

CAPRI round 61 predictor; submitted model 1; T312.1 · CAPRI round 61 T312.1: dockq

dockq (fraction) · Higher values are better.

CAPRI round 61 predictor; submitted model 1; T312.1 · CAPRI round 61 T312.1 · CAPRI round 61 T312.1

Evidence origin: Independent external evaluation.

CAPRI: CAPRI round 61, snapshot 2026-09-19 · line 7; identification=T312_P01.M01; column dockq through line 1444; identification=T312_P37.M01; column dockq

Missing source cells and quarantined conflicts are recorded in acquisition and audit tables. Per-result scoring denominators may be unreported.

Comparison details and limitations

Complete selected source table is retained across source-order panels. These point estimates do not establish statistical significance or a universal ranking.

Source-specific evaluation. No equivalence to other releases, protocols or model families is inferred.
Exact source-defined evaluation scope; reported scores are not rewire reproductions.

Automated source review: 2026-09-19. Numerical source review does not establish independent reproduction.

Dots show point estimates. Whiskers show only explicitly defined uncertainty (standard deviation, standard error or a labelled interval); their definitions remain in Table. Unresolved uncertainty is not plotted. Differences do not establish statistical significance.

Find a tested model or method

Showing 12 of 25 matching rows.

Zoom to observed range

Tested configuration

00.250.50.751

Reported score

Methods and evaluation design

Procedure, tasks and evaluated configurations

How it works

Evaluation methodology

CAPRI is a blinded interaction-structure challenge. Predictors submit complex models, while scoring tracks select promising models from candidate sets. Assessors compare submitted interfaces with withheld experimental structures; quality classes and DockQ-based summaries retain the target and round context.

Sources

capri primary benchmark evidence · Assessment page: joint CASP-CAPRI Round 57 and Round 58

Evaluation design

Benchmarks bring together tasks and protocols. A task describes the biological question; a protocol defines a particular test.

Protocols

These source-backed links do not make different protocols or scores interchangeable.

Baseline coverage

Reference methods help show what a model adds beyond simple controls. We track a null control and a conventional method for each protocol.

0 of 8 active baseline roles have published Rewire measurements in this release. Measurements on a selected protocol do not establish coverage of an entire suite.

Baseline status by linked protocol

CAPRI round 61 predictor; submitted model 1; T312.1 · CAPRI round 61 T312.1 · 0/2 roles measured
CAPRI round 61 predictor; submitted model 1; T314.1 · CAPRI round 61 T314.1 · 0/2 roles measured
CAPRI round 61 predictor; submitted model 1; T316.1 · CAPRI round 61 T316.1 · 0/2 roles measured
CAPRI round 61 predictor; submitted model 1; T315.1 · CAPRI round 61 T315.1 · 0/2 roles measured

Protocol coverage CSV · Model evaluation matrix · Source table · Release and checksums

Coverage is derived from release 2026-09-29-06401fd5b220. Source citations describe the original records; they do not validate an unreviewed baseline proposal. No results have been generated by this audit.

Run this benchmark

Choose a concrete protocol before running an evaluation. Its inputs, split and scoring rules determine which results can be compared.

Run this benchmark

CAPRI is a blind, round-based assessment of protein-complex predictions. This landing page introduces the challenge but does not provide an end-to-end local scoring command. Use the exact round target set and assessment instructions; do not treat a generic docking run as a CAPRI submission.

A maintained rewire runner has not been verified for this benchmark. Check data access, weights, licences, dependencies and hardware in the linked official documentation; requirements have not been fully extracted.

capri official run documentation · Official landing page: Welcome to the CAPRI web site

Strengths, limitations and unresolved questions

Strengths and limitations

Strengths and considerations

Blind rounds separate predictor submissions from the assessment structures.
Sources
capri official source · Official CAPRI homepage: introductory description

Limitations and conditions

A model-selection round with supplied structures is different from docking from sequence or component structures. Reference inputs, candidate pools and assessment-unit definitions must stay visible.
Sources
capri primary benchmark evidence · Assessment page: joint CASP-CAPRI Round 57 and Round 58

Profile review details

Primary paper and/or task implementation reviewed for the explicitly cited methodology claims. Scope-limited absence is recorded only after the documented source search; no model runs or independent reproduction.

Stable record: discovery-benchmark-capri

Specifications

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.

Data, procedure and scoring
Property	Description and evidence
Datasets	Challenge-round protein-complex targets supplied by experimental contributors. Sources capri official source · Official CAPRI homepage: introductory description
Splits	Target structures are unreleased to predictors during the blind prediction phase. Sources capri official source · Official CAPRI homepage: introductory description
Metrics	Interface contact recovery (Fnat), interface RMSD and ligand RMSD define classical CAPRI quality classes. DockQ combines these complementary structural measures into a continuous score. Sources dockq primary benchmark evidence · Introduction and Methods: CAPRI criteria and DockQ
Baselines	Round 57 assessment compares submissions with ColabFold and an AlphaFold 3 submission. Round 58 supplies MassiveFold candidate models and tests improvement over that model pool; other rounds have different reference conditions. Sources capri primary benchmark evidence · Assessment page: joint CASP-CAPRI Round 57 and Round 58
Leakage controls	The prospective blind-target design separates submissions from public experimental structures. Sources capri official source · Official CAPRI homepage: introductory description
Uncertainty	The inspected assessment page provides round-specific rankings and quality classes but does not define one common bootstrap interval for all CAPRI targets and rounds. · Not reported in inspected sources Sources capri primary benchmark evidence · Assessment page: joint CASP-CAPRI Round 57 and Round 58
Entity type	Blind protein-complex prediction challenge. Sources capri official source · Official CAPRI homepage: introductory description
Organisms	Target-dependent protein complexes; this is not a single-species benchmark. Sources capri official source · Official CAPRI homepage: introductory description
Assays	Experimentally determined complex structures withheld for assessment. Sources capri official source · Official CAPRI homepage: introductory description
Allowed inputs	Target information distributed for each challenge round. Sources capri official source · Official CAPRI homepage: introductory description
Adaptation	Prediction submissions are assessed against subsequently available experimental structures. Sources capri official source · Official CAPRI homepage: introductory description

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-paper discovery and source inspection. Source-checked results are not independently reproduced experiments.

Paper or primary resource	Version	Reference
CAPRI Assessment results	Official assessment page inspected 2026-09-17, web text snapshot	Read source

Historical gaps recorded on 2026-09-17

The catalogue now holds 400 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.

Round 54 has 37 targets and 38 assessment units; round 57 has 34 targets and 47 units. These are different denominators.
Official page says data may change; pin each round CSV before numerical ingestion.
Freshly discovered Rosetta CAPRI rounds 47–55 paper (PMC12462888) was blocked: Europe PMC HTTP 500 and PMC browser challenge. It is not a universal all-participant assessment.

Search and extraction details

primary assessment located paper access blocked

Searches

Open Problems single cell label projection benchmark v1.0.0 paper
CAPRI assessment rounds 46 54 protein docking results
GEARS predicting transcriptional outcomes multigene perturbations 2023
scVI scANVI reference mapping benchmark primary paper

Evidence locations

Official assessment: rounds 54, 55, 57–58 and 61; linked per-interface CSVs

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.

21 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-09-29-06401fd5b220
Property and statement	Original source and location	Review and provenance
Diagram caption Conceptual procedure. Task variants and protocol versions retain their separate scoring conditions. Individual claims	capri official source Original source ↗ Official CAPRI homepage: introductory description; Introduction and Methods: CAPRI criteria and DockQ Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Retrieved website snapshot sha256:5e22606895cf0c30565ed4456bc680ca97c10c8c5d38054f82a6e4677c8d8c24 Retrieved: 2026-09-16T10:31:54.812767+00:00	source checked automated source review · 2026-09-16 Audit details Primary paper and/or task implementation reviewed for the explicitly cited methodology claims. Scope-limited absence is recorded only after the documented source search; no model runs or independent reproduction. Field: `attributes.profile.diagram.caption` Source artifact SHA-256: `5e22606895cf0c30565ed4456bc680ca97c10c8c5d38054f82a6e4677c8d8c24` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Diagram caption Conceptual procedure. Task variants and protocol versions retain their separate scoring conditions. Individual claims	dockq primary benchmark evidence Original source ↗ Official CAPRI homepage: introductory description; Introduction and Methods: CAPRI criteria and DockQ Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: PMC4999177 Retrieved: 2026-09-16T21:11:45.113639+00:00	source checked automated source review · 2026-09-16 Audit details Primary paper and/or task implementation reviewed for the explicitly cited methodology claims. Scope-limited absence is recorded only after the documented source search; no model runs or independent reproduction. Field: `attributes.profile.diagram.caption` Source artifact SHA-256: `013ceed0e054f971a81caf7cdcac10c3f4241ecec0532e326a1fca124e69dbe9` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Diagram steps Allowed inputs: Target information distributed for each challenge round. Splits: Target structures are unreleased to predictors during the blind prediction phase. Metrics: Interface contact recovery (Fnat), interface RMSD and ligand RMSD define classical CAPRI quality classes. DockQ combines these complementary structural measures into a continuous score. Individual claims	capri official source Original source ↗ Official CAPRI homepage: introductory description; Introduction and Methods: CAPRI criteria and DockQ Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Retrieved website snapshot sha256:5e22606895cf0c30565ed4456bc680ca97c10c8c5d38054f82a6e4677c8d8c24 Retrieved: 2026-09-16T10:31:54.812767+00:00	source checked automated source review · 2026-09-16 Audit details Primary paper and/or task implementation reviewed for the explicitly cited methodology claims. Scope-limited absence is recorded only after the documented source search; no model runs or independent reproduction. Field: `attributes.profile.diagram.steps` Source artifact SHA-256: `5e22606895cf0c30565ed4456bc680ca97c10c8c5d38054f82a6e4677c8d8c24` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Diagram steps Allowed inputs: Target information distributed for each challenge round. Splits: Target structures are unreleased to predictors during the blind prediction phase. Metrics: Interface contact recovery (Fnat), interface RMSD and ligand RMSD define classical CAPRI quality classes. DockQ combines these complementary structural measures into a continuous score. Individual claims	dockq primary benchmark evidence Original source ↗ Official CAPRI homepage: introductory description; Introduction and Methods: CAPRI criteria and DockQ Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: PMC4999177 Retrieved: 2026-09-16T21:11:45.113639+00:00	source checked automated source review · 2026-09-16 Audit details Primary paper and/or task implementation reviewed for the explicitly cited methodology claims. Scope-limited absence is recorded only after the documented source search; no model runs or independent reproduction. Field: `attributes.profile.diagram.steps` Source artifact SHA-256: `013ceed0e054f971a81caf7cdcac10c3f4241ecec0532e326a1fca124e69dbe9` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Diagram title Evaluation procedure Individual claims	capri official source Original source ↗ Official CAPRI homepage: introductory description; Introduction and Methods: CAPRI criteria and DockQ Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Retrieved website snapshot sha256:5e22606895cf0c30565ed4456bc680ca97c10c8c5d38054f82a6e4677c8d8c24 Retrieved: 2026-09-16T10:31:54.812767+00:00	source checked automated source review · 2026-09-16 Audit details Primary paper and/or task implementation reviewed for the explicitly cited methodology claims. Scope-limited absence is recorded only after the documented source search; no model runs or independent reproduction. Field: `attributes.profile.diagram.title` Source artifact SHA-256: `5e22606895cf0c30565ed4456bc680ca97c10c8c5d38054f82a6e4677c8d8c24` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Diagram title Evaluation procedure Individual claims	dockq primary benchmark evidence Original source ↗ Official CAPRI homepage: introductory description; Introduction and Methods: CAPRI criteria and DockQ Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: PMC4999177 Retrieved: 2026-09-16T21:11:45.113639+00:00	source checked automated source review · 2026-09-16 Audit details Primary paper and/or task implementation reviewed for the explicitly cited methodology claims. Scope-limited absence is recorded only after the documented source search; no model runs or independent reproduction. Field: `attributes.profile.diagram.title` Source artifact SHA-256: `013ceed0e054f971a81caf7cdcac10c3f4241ecec0532e326a1fca124e69dbe9` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Datasets Challenge-round protein-complex targets supplied by experimental contributors. Individual claims	capri official source Original source ↗ Official CAPRI homepage: introductory description Version: Retrieved website snapshot sha256:5e22606895cf0c30565ed4456bc680ca97c10c8c5d38054f82a6e4677c8d8c24 Retrieved: 2026-09-16T10:31:54.812767+00:00	source checked automated source review · 2026-09-16 Audit details Primary paper and/or task implementation reviewed for the explicitly cited methodology claims. Scope-limited absence is recorded only after the documented source search; no model runs or independent reproduction. Field: `attributes.profile.facts.0.value` Source artifact SHA-256: `5e22606895cf0c30565ed4456bc680ca97c10c8c5d38054f82a6e4677c8d8c24` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Splits Target structures are unreleased to predictors during the blind prediction phase. Individual claims	capri official source Original source ↗ Official CAPRI homepage: introductory description Version: Retrieved website snapshot sha256:5e22606895cf0c30565ed4456bc680ca97c10c8c5d38054f82a6e4677c8d8c24 Retrieved: 2026-09-16T10:31:54.812767+00:00	source checked automated source review · 2026-09-16 Audit details Primary paper and/or task implementation reviewed for the explicitly cited methodology claims. Scope-limited absence is recorded only after the documented source search; no model runs or independent reproduction. Field: `attributes.profile.facts.1.value` Source artifact SHA-256: `5e22606895cf0c30565ed4456bc680ca97c10c8c5d38054f82a6e4677c8d8c24` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Adaptation Prediction submissions are assessed against subsequently available experimental structures. Individual claims	capri official source Original source ↗ Official CAPRI homepage: introductory description Version: Retrieved website snapshot sha256:5e22606895cf0c30565ed4456bc680ca97c10c8c5d38054f82a6e4677c8d8c24 Retrieved: 2026-09-16T10:31:54.812767+00:00	source checked automated source review · 2026-09-16 Audit details Primary paper and/or task implementation reviewed for the explicitly cited methodology claims. Scope-limited absence is recorded only after the documented source search; no model runs or independent reproduction. Field: `attributes.profile.facts.10.value` Source artifact SHA-256: `5e22606895cf0c30565ed4456bc680ca97c10c8c5d38054f82a6e4677c8d8c24` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Metrics Interface contact recovery (Fnat), interface RMSD and ligand RMSD define classical CAPRI quality classes. DockQ combines these complementary structural measures into a continuous score. Individual claims	dockq primary benchmark evidence Original source ↗ Introduction and Methods: CAPRI criteria and DockQ Version: PMC4999177 Retrieved: 2026-09-16T21:11:45.113639+00:00	source checked automated source review · 2026-09-16 Audit details Primary paper and/or task implementation reviewed for the explicitly cited methodology claims. Scope-limited absence is recorded only after the documented source search; no model runs or independent reproduction. Field: `attributes.profile.facts.2.value` Source artifact SHA-256: `013ceed0e054f971a81caf7cdcac10c3f4241ecec0532e326a1fca124e69dbe9` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact

All evidence (CSV)All evidence (JSONL)How to read the evidence

Sources and history

View linked audit checks and correction history

Release 2026-09-29-06401fd5b220 · Record review: discovered

6 source records and release history

capri official source · Original source · Not reported
CAPRI Assessment results · Original source · Official assessment page inspected 2026-09-17, web text snapshot
capri official source · Original source · Retrieved website snapshot sha256:5e22606895cf0c30565ed4456bc680ca97c10c8c5d38054f82a6e4677c8d8c24
capri official run documentation · Original source · Official documentation snapshot 2026-09-17; mutable website
capri primary benchmark evidence · Original source · Retrieved 2026-09-16 assessment page
dockq primary benchmark evidence · Original source · PMC4999177

Download this release

Technical metadata and extraction receipts

Stable ID: discovery-benchmark-capri

areas: protein-structure
entity level: challenge
scope note: Specialist molecular or omics evaluation; protocol details require review before numerical comparison.
task: Protein interaction docking assessment
version: Not reported
benchmark research: review date: 2026-09-17; status: primary_assessment_located_paper_access_blocked; primary sources: expansion-p3-capri-assessment; inspected locators: Official assessment: rounds 54, 55, 57–58 and 61; linked per-interface CSVs; searched queries: Open Problems single cell label projection benchmark v1.0.0 paper; CAPRI assessment rounds 46 54 protein docking results; GEARS predicting transcriptional outcomes multigene perturbations 2023; scVI scANVI reference mapping benchmark primary paper; gaps: Round 54 has 37 targets and 38 assessment units; round 57 has 34 targets and 47 units. These are different denominators.; Official page says data may change; pin each round CSV before numerical ingestion.; Freshly discovered Rosetta CAPRI rounds 47–55 paper (PMC12462888) was blocked: Europe PMC HTTP 500 and PMC browser challenge. It is not a universal all-participant assessment.; claim scope: Primary-paper discovery and source inspection. Source-checked results are not independently reproduced experiments.
historical missing metadata: dataset release: unextracted; metric implementation: unextracted; split manifest: unextracted; version: unextracted
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.
entity classification: review date: 2026-09-17; rationale: The cited profile describes an organized challenge with category- or round-specific evaluation rules; retain it as a top-level benchmark, without conflating different editions or protocols.; source ids: evidence-benchmark-capri-snapshot; source locator: Official CAPRI homepage: introductory description; ambiguities: None recorded
run documentation: record id: discovery-benchmark-capri; source ids: run-doc-capri-official-20260917; status: official_documentation_linked; summary: CAPRI is a blind, round-based assessment of protein-complex predictions. This landing page introduces the challenge but does not provide an end-to-end local scoring command. Use the exact round target set and assessment instructions; do not treat a generic docking run as a CAPRI submission.; source locator: Official landing page: Welcome to the CAPRI web site

Related records

Suggest a correction