Evaluator

PoseBusters

PoseBusters checks the plausibility of predicted molecular poses.

Sources

maabuu/posebusters official source · Pinned README: description; Usage; paper/data links

No reviewed evaluations are linked here in this release. See the sources and separately identified configurations below.

0 evaluations · 0 results

Overview

Datasets

Predicted molecular coordinates, optionally with the conditioning protein, and paper-linked evaluation data.

Sources

maabuu/posebusters official source · Pinned README: description; Usage; paper/data links

Metrics

Chemical identity/stereochemistry, bond and angle geometry, aromatic planarity, internal clashes and protein–ligand clashes are checked separately. The paper evaluates native-like pose recovery jointly with passing the validity checks; its intramolecular tolerances are 25% for bond lengths/angles and 30% for nonbonded distances.

Sources

posebusters primary benchmark evidence · Methods: chemical, intramolecular and intermolecular validity

Allowed inputs

Predicted molecule coordinates, optionally paired with a protein structure.

Sources

maabuu/posebusters official source · Pinned README: description; Usage; paper/data links

Evaluation procedure diagram

How it worksEvaluation procedure

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

Sources (2)

maabuu/posebusters official source; posebusters primary benchmark evidence · Pinned README: description; Usage; paper/data links; Methods: chemical, intramolecular and intermolecular validity

Source reviewed · Automated source review, 2026-09-16. All specifications and missing details

Results

All evaluations

0 evaluations · 0 results. Different protocols are not a single leaderboard.

Applied filters: All linked evaluations

No evaluations linked in this release.

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

Predicted molecular coordinates, optionally with the conditioning protein, and paper-linked evaluation data. The evaluator scores supplied outputs; predictor train/test partitions belong to the dataset/run being evaluated. Chemical identity/stereochemistry, bond and angle geometry, aromatic planarity, internal clashes and protein–ligand clashes are checked separately. The paper evaluates native-like pose recovery jointly with passing the validity checks; its intramolecular tolerances are 25% for bond lengths/angles and 30% for nonbonded distances. The PoseBusters benchmark selects recent PDB complexes absent from the PDBbind v2020 training source used by evaluated learned docking methods. The paper further examines protein-sequence similarity to training data; new deposition date alone does not imply remote homology.

Sources (2)

maabuu/posebusters official source; posebusters primary benchmark evidence · Pinned README: description; Usage; paper/data links; Methods: chemical, intramolecular and intermolecular validity; Methods: benchmark construction and evaluation of generalization

Run instructions

No runnable recipe has been reviewed for this evaluator. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.

Strengths, limitations and unresolved questions

Strengths and limitations

Strengths supported by sources

Checks plausibility separately from pose agreement, preventing the two criteria being conflated.
Sources
maabuu/posebusters official source · Pinned README: description; Usage; paper/data links

Limitations and conditions

PoseBusters checks physical plausibility and geometric agreement. Passing those checks does not establish binding affinity, biological activity or complete independence from every external training corpus.
Sources
posebusters primary benchmark evidence · Methods: benchmark construction and evaluation of generalization

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-posebusters

Specifications

Inputs, training, access and other details

Explanatory profile: source reviewed · 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	Predicted molecular coordinates, optionally with the conditioning protein, and paper-linked evaluation data. Sources maabuu/posebusters official source · Pinned README: description; Usage; paper/data links
Splits	The evaluator scores supplied outputs; predictor train/test partitions belong to the dataset/run being evaluated. · Not applicable Sources maabuu/posebusters official source · Pinned README: description; Usage; paper/data links
Metrics	Chemical identity/stereochemistry, bond and angle geometry, aromatic planarity, internal clashes and protein–ligand clashes are checked separately. The paper evaluates native-like pose recovery jointly with passing the validity checks; its intramolecular tolerances are 25% for bond lengths/angles and 30% for nonbonded distances. Sources posebusters primary benchmark evidence · Methods: chemical, intramolecular and intermolecular validity
Baselines	The evaluator does not prescribe a universal baseline predictor; comparisons require methods run on the same selected dataset. · Not applicable Sources maabuu/posebusters official source · Pinned README: description; Usage; paper/data links
Leakage controls	The PoseBusters benchmark selects recent PDB complexes absent from the PDBbind v2020 training source used by evaluated learned docking methods. The paper further examines protein-sequence similarity to training data; new deposition date alone does not imply remote homology. Sources posebusters primary benchmark evidence · Methods: benchmark construction and evaluation of generalization
Uncertainty	Uncertainty across samples, datasets or training runs must be defined by the evaluation study; this evaluator entry does not fix one experiment. · Not applicable Sources maabuu/posebusters official source · Pinned README: description; Usage; paper/data links
Entity type	Molecular-pose plausibility evaluator. Sources maabuu/posebusters official source · Pinned README: description; Usage; paper/data links
Organisms	Plausibility checks concern molecular geometry rather than organism identity. · Not applicable Sources maabuu/posebusters official source · Pinned README: description; Usage; paper/data links
Assays	Predicted poses assessed against molecular validity criteria. Sources maabuu/posebusters official source · Pinned README: description; Usage; paper/data links
Allowed inputs	Predicted molecule coordinates, optionally paired with a protein structure. Sources maabuu/posebusters official source · Pinned README: description; Usage; paper/data links
Adaptation	The checker evaluates poses; it does not train or fine-tune the pose predictor. · Not applicable Sources maabuu/posebusters official source · Pinned README: description; Usage; paper/data links
Implementation	Not extracted or verified for this record.

Applicable tests and references

Applicability is distinct from a completed evaluation.

AutoDock Vina · Proposed association

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
PoseBusters: AI-based docking methods fail to generate physically valid poses or generalise to novel sequences†	PMC10901501	Read source DOI: 10.1039/d3sc04185a

Historical gaps recorded on 2026-09-17

Main tables define benchmark/validity tests, not a complete method score matrix. Individual docking output data at Zenodo 8278563 identified for next extraction. RMSD-only and RMSD-plus-validity must stay distinct.

Search and extraction details

source found structured extraction pending

Searches

PoseBusters benchmark 2024 docking physical validity paper

Evidence locations

Main Tables1–2 and benchmark result figures; Zenodo8278563 discovery link

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

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	posebusters primary benchmark evidence Original source ↗ Pinned README: description; Usage; paper/data links; Methods: chemical, intramolecular and intermolecular validity Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: PMC10901501 Retrieved: 2026-09-16T21:05:51.089997+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: `8bbc6eadc59d33f7433b610d91c0b0d2d3094cacb3c0bdfa83bf89239580c763` 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	maabuu/posebusters official source Original source ↗ Pinned README: description; Usage; paper/data links; Methods: chemical, intramolecular and intermolecular validity Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 6236d07017493531851cce775e8ef834d4763d2f Retrieved: 2026-09-16T10:30:23.520671+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: `71fee661aba53ea2285b776d572982a57c8637275687dfe4c5b7f5113a807d0e` Hash scope: Hash scope not separately documented; inspect source record
Diagram steps Allowed inputs: Predicted molecule coordinates, optionally paired with a protein structure. Splits: The evaluator scores supplied outputs; predictor train/test partitions belong to the dataset/run being evaluated. Metrics: Chemical identity/stereochemistry, bond and angle geometry, aromatic planarity, internal clashes and protein–ligand clashes are checked separately. The paper evaluates native-like pose recovery jointly with passing the validity checks; its intramolecular tolerances are 25% for bond lengths/angles and 30% for nonbonded distances. Individual claims	posebusters primary benchmark evidence Original source ↗ Pinned README: description; Usage; paper/data links; Methods: chemical, intramolecular and intermolecular validity Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: PMC10901501 Retrieved: 2026-09-16T21:05:51.089997+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: `8bbc6eadc59d33f7433b610d91c0b0d2d3094cacb3c0bdfa83bf89239580c763` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Diagram steps Allowed inputs: Predicted molecule coordinates, optionally paired with a protein structure. Splits: The evaluator scores supplied outputs; predictor train/test partitions belong to the dataset/run being evaluated. Metrics: Chemical identity/stereochemistry, bond and angle geometry, aromatic planarity, internal clashes and protein–ligand clashes are checked separately. The paper evaluates native-like pose recovery jointly with passing the validity checks; its intramolecular tolerances are 25% for bond lengths/angles and 30% for nonbonded distances. Individual claims	maabuu/posebusters official source Original source ↗ Pinned README: description; Usage; paper/data links; Methods: chemical, intramolecular and intermolecular validity Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 6236d07017493531851cce775e8ef834d4763d2f Retrieved: 2026-09-16T10:30:23.520671+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: `71fee661aba53ea2285b776d572982a57c8637275687dfe4c5b7f5113a807d0e` Hash scope: Hash scope not separately documented; inspect source record
Diagram title Evaluation procedure Individual claims	posebusters primary benchmark evidence Original source ↗ Pinned README: description; Usage; paper/data links; Methods: chemical, intramolecular and intermolecular validity Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: PMC10901501 Retrieved: 2026-09-16T21:05:51.089997+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: `8bbc6eadc59d33f7433b610d91c0b0d2d3094cacb3c0bdfa83bf89239580c763` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Diagram title Evaluation procedure Individual claims	maabuu/posebusters official source Original source ↗ Pinned README: description; Usage; paper/data links; Methods: chemical, intramolecular and intermolecular validity Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 6236d07017493531851cce775e8ef834d4763d2f Retrieved: 2026-09-16T10:30:23.520671+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: `71fee661aba53ea2285b776d572982a57c8637275687dfe4c5b7f5113a807d0e` Hash scope: Hash scope not separately documented; inspect source record
Datasets Predicted molecular coordinates, optionally with the conditioning protein, and paper-linked evaluation data. Individual claims	maabuu/posebusters official source Original source ↗ Pinned README: description; Usage; paper/data links Version: 6236d07017493531851cce775e8ef834d4763d2f Retrieved: 2026-09-16T10:30:23.520671+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: `71fee661aba53ea2285b776d572982a57c8637275687dfe4c5b7f5113a807d0e` Hash scope: Hash scope not separately documented; inspect source record
Splits The evaluator scores supplied outputs; predictor train/test partitions belong to the dataset/run being evaluated. Individual claims	maabuu/posebusters official source Original source ↗ Pinned README: description; Usage; paper/data links Version: 6236d07017493531851cce775e8ef834d4763d2f Retrieved: 2026-09-16T10:30:23.520671+00:00	inapplicable 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: `71fee661aba53ea2285b776d572982a57c8637275687dfe4c5b7f5113a807d0e` Hash scope: Hash scope not separately documented; inspect source record
Adaptation The checker evaluates poses; it does not train or fine-tune the pose predictor. Individual claims	maabuu/posebusters official source Original source ↗ Pinned README: description; Usage; paper/data links Version: 6236d07017493531851cce775e8ef834d4763d2f Retrieved: 2026-09-16T10:30:23.520671+00:00	inapplicable 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: `71fee661aba53ea2285b776d572982a57c8637275687dfe4c5b7f5113a807d0e` Hash scope: Hash scope not separately documented; inspect source record
Metrics Chemical identity/stereochemistry, bond and angle geometry, aromatic planarity, internal clashes and protein–ligand clashes are checked separately. The paper evaluates native-like pose recovery jointly with passing the validity checks; its intramolecular tolerances are 25% for bond lengths/angles and 30% for nonbonded distances. Individual claims	posebusters primary benchmark evidence Original source ↗ Methods: chemical, intramolecular and intermolecular validity Version: PMC10901501 Retrieved: 2026-09-16T21:05:51.089997+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: `8bbc6eadc59d33f7433b610d91c0b0d2d3094cacb3c0bdfa83bf89239580c763` 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

3 source records and release history

maabuu/posebusters official source · Original source · 6236d07017493531851cce775e8ef834d4763d2f
PoseBusters: AI-based docking methods fail to generate physically valid poses or generalise to novel sequences† · Original source · PMC10901501
posebusters primary benchmark evidence · Original source · PMC10901501

Download this release

Technical metadata and extraction receipts

Stable ID: discovery-benchmark-posebusters

areas: molecular-interactions
entity level: evaluator
scope note: Specialist molecular or omics evaluation; protocol details require review before numerical comparison.
task: Geometric and chemical plausibility of molecular poses
version: Not reported
benchmark research: review date: 2026-09-17; status: source_found_structured_extraction_pending; primary sources: evidence-expansion-p2-evidence-discovery-final-posebusters-8bbc6eadc59d; inspected locators: Main Tables1–2 and benchmark result figures; Zenodo8278563 discovery link; searched queries: PoseBusters benchmark 2024 docking physical validity paper; gaps: Main tables define benchmark/validity tests, not a complete method score matrix. Individual docking output data at Zenodo 8278563 identified for next extraction. RMSD-only and RMSD-plus-validity must stay distinct.; 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: 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.
legacy kinds: benchmark
entity classification: review date: 2026-09-17; rationale: The cited profile describes scoring or assessment software/procedures applied to predictions, rather than the biological target or the underlying dataset.; source ids: src-discovery-maabuu-posebusters; source locator: Pinned README: description; Usage; paper/data links; ambiguities: None recorded

Related records

applicable to: AutoDock Vina

Suggest a correction