Configuration

DiffDock

This protein–ligand pose predictor is evaluated for stereochemical validity as well as pose accuracy.

Sources

Improving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction · Results/Benchmark of Protein–Ligand Complex Structure Prediction (paragraph 6); Methods/Benchmark Dataset (paragraph 1)

1 evaluation · 1 metric row

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

Improving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction · Results/Case Studies for Bond and Angle Geometries of Ligands (paragraph 3); Results/Structure Prediction Using Restraint-Guided Inference (paragraph 1)

At a glance

Model type

Molecular docking model; this record is the paper-specific evaluated configuration.

Sources

gcorso/DiffDock README.md · README.md model description

Biological inputs

Protein and ligand information under the method-specific docking or co-folding protocol

Sources

Improving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction · Results/Benchmark of Protein–Ligand Complex Structure Prediction (paragraph 1); Results/Case Studies for Bond and Angle Geometries of Ligands (paragraph 1)

Outputs

Predicted protein–ligand binding poses

Sources

Improving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction · Results/Case Studies for Bond and Angle Geometries of Ligands (paragraph 2); Methods/Implementation of the Restraints (paragraph 1)

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.

Evaluation setupMetricEvidence origin

Results grouped by the exact reported evaluation
Metric and finding	Coverage and uncertainty	Evidence
DiffDock: Protein–ligand pose prediction Configuration: DiffDockTask: Protein–ligand pose predictionDataset: PLINDER-L95 All entries; rigid-protein docking comparator; authors note this dataset contains structures seen during model training. Independent external evaluation · Evaluation metadata: needs review
1.342 Median ligand RMSD Unit: Å · Direction: unknown	Uncertainty: not reported in legacy extract Scored: Not reported · Eligible: Not reported	source checkedImproving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction · Table 1, DiffDock row, Ligand RMSD (Å) column Source checking is not independent reproduction.

How it works

How the evaluated method works

The study compares generated ligand poses and protein–ligand complexes under a shared geometry assessment. The unrestrained baseline is distinct from the proposed restraint-guided Boltz inference.

Sources

Underlying method and version boundaries

DiffDock is a molecular-docking implementation that produces ligand poses and confidence estimates. Its confidence values and predicted coordinates are different outputs from an experimentally calibrated binding-affinity measurement.

Sources

gcorso/DiffDock README.md · README.md; introduction, model description, pretrained-model and usage sections at pinned revision

What was evaluated

The linked evaluation record identifies DiffDock: Protein–ligand pose prediction. Its dataset, split, adaptation and evidence origin remain attached to the reported results.

Sources

Improving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction · The named evaluation’s methods and comparison table; exact preserved evaluation IDs: evaluation-lit-046

Strengths and limitations

Strengths and considerations

Reports chirality, bond geometry and steric clashes alongside RMSD.
Sources
Improving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction · Results/Benchmark of Protein–Ligand Complex Structure Prediction (paragraph 6); Results/Structure Prediction Using Restraint-Guided Inference (paragraph 4)

Limitations and conditions

Pose accuracy deteriorates on filtered post-cutoff data, and low RMSD alone does not imply physically valid ligand geometry.
Sources
Improving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction · Results/Benchmark of Protein–Ligand Complex Structure Prediction (paragraph 6); Methods/Evaluation Metrics (paragraph 3)

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-7f6ffd9e2a08be

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.

Inputs, outputs and configuration
Property	Description and evidence
Model type	Molecular docking model; this record is the paper-specific evaluated configuration. Sources gcorso/DiffDock README.md · README.md model description
Architecture / procedure	The study compares generated ligand poses and protein–ligand complexes under a shared geometry assessment. The unrestrained baseline is distinct from the proposed restraint-guided Boltz inference. Sources Improving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction · Results/Case Studies for Bond and Angle Geometries of Ligands (paragraph 3); Results/Structure Prediction Using Restraint-Guided Inference (paragraph 1)
Biological inputs	Protein and ligand information under the method-specific docking or co-folding protocol Sources Improving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction · Results/Benchmark of Protein–Ligand Complex Structure Prediction (paragraph 1); Results/Case Studies for Bond and Angle Geometries of Ligands (paragraph 1)
Outputs	Predicted protein–ligand binding poses Sources Improving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction · Results/Case Studies for Bond and Angle Geometries of Ligands (paragraph 2); Methods/Implementation of the Restraints (paragraph 1)
Parameters	An aggregate parameter total for this exact evaluated configuration is not established by the inspected sources. · Not reported in inspected sources Sources (2) Improving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction; gcorso/DiffDock README.md · Methods/Benchmark Dataset; Methods/Evaluation Metrics; Methods/Improving Geometry through Restraints; Methods/Implementation of the Restraints; Methods/Multiple Sequence Alignment and Structure Prediction; inspected for aggregate parameter count (component sizes are not added without an exact configuration); README.md at pinned repository revision
Known versions / configuration	DiffDock is the comparison-table label; that label does not specify an immutable weight revision. · Not reported in inspected sources Sources Improving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction · Model identification in the comparison table and corresponding Methods; immutable checkpoint revision is not supplied by the table label.
Training data / fitting	The evaluation separates structures before and after training-date cutoffs and adds chemical/protein similarity filters. Sources Improving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction · Methods/Benchmark Dataset (paragraph 3); Methods/Benchmark Dataset (paragraph 4)
Context limits	A maximum input/context length for this exact evaluated configuration is not established by the inspected sources. · Not reported in inspected sources Sources (2) Improving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction; gcorso/DiffDock README.md · Methods/Benchmark Dataset; Methods/Evaluation Metrics; Methods/Improving Geometry through Restraints; Methods/Implementation of the Restraints; Methods/Multiple Sequence Alignment and Structure Prediction; 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/gcorso/DiffDock/blob/85c49b60d3e0b0182a59ee43a34a6d7036981284/README.md. This pinned documentation revision is not automatically the evaluated weight revision. Sources gcorso/DiffDock README.md · README.md; installation, model download and usage instructions
Code licence	MIT (upstream repository code at the cited revision; this does not establish every dependency or historical checkpoint licence). Sources gcorso/DiffDock LICENSE · LICENSE; complete licence text
Weights licence	The inspected model-access documentation does not explicitly identify terms for this exact evaluated checkpoint or fitted head; repository code terms are shown separately. · Not reported in inspected sources Sources gcorso/DiffDock README.md · README.md; checkpoint/access documentation and licence scope

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 2026-09-17-d277315f7d76
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	Improving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction Original source ↗ Results/Case Studies for Bond and Angle Geometries of Ligands (paragraph 3); Results/Structure Prediction Using Restraint-Guided Inference (paragraph 1) Version: version of record Retrieved: 2026-09-16T10:41:16.555674+00:00	source checked automated source review · 2026-09-16 Audit 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. Field: `attributes.profile.diagram.caption` Source artifact SHA-256: `78a77b9a0ab8bfa371f5b9baef3f443f4590d6e71cf864d67e90e9ebdfa7fc1b` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Diagram steps ["Protein and ligand information under the method-specific docking or co-folding protocol","DiffDock","Predicted protein–ligand binding poses"] Individual claims	Improving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction Original source ↗ Results/Case Studies for Bond and Angle Geometries of Ligands (paragraph 3); Results/Structure Prediction Using Restraint-Guided Inference (paragraph 1) Version: version of record Retrieved: 2026-09-16T10:41:16.555674+00:00	source checked automated source review · 2026-09-16 Audit 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. Field: `attributes.profile.diagram.steps` Source artifact SHA-256: `78a77b9a0ab8bfa371f5b9baef3f443f4590d6e71cf864d67e90e9ebdfa7fc1b` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Diagram title Evaluated procedure (conceptual) Individual claims	Improving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction Original source ↗ Results/Case Studies for Bond and Angle Geometries of Ligands (paragraph 3); Results/Structure Prediction Using Restraint-Guided Inference (paragraph 1) Version: version of record Retrieved: 2026-09-16T10:41:16.555674+00:00	source checked automated source review · 2026-09-16 Audit 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. Field: `attributes.profile.diagram.title` Source artifact SHA-256: `78a77b9a0ab8bfa371f5b9baef3f443f4590d6e71cf864d67e90e9ebdfa7fc1b` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Model type Molecular docking model; this record is the paper-specific evaluated configuration. Individual claims	gcorso/DiffDock README.md Original source ↗ README.md model description Version: 85c49b60d3e0b0182a59ee43a34a6d7036981284 Retrieved: 2026-09-16T20:00:00.818010+00:00	source checked automated source review · 2026-09-16 Audit 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. Field: `attributes.profile.facts.0.value` Source artifact SHA-256: `6f63088d85b5f05d58416ede319387c1b7f3661b27741a36314ada861f2056de` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Architecture / procedure The study compares generated ligand poses and protein–ligand complexes under a shared geometry assessment. The unrestrained baseline is distinct from the proposed restraint-guided Boltz inference. Individual claims	Improving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction Original source ↗ Results/Case Studies for Bond and Angle Geometries of Ligands (paragraph 3); Results/Structure Prediction Using Restraint-Guided Inference (paragraph 1) Version: version of record Retrieved: 2026-09-16T10:41:16.555674+00:00	source checked automated source review · 2026-09-16 Audit 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. Field: `attributes.profile.facts.1.value` Source artifact SHA-256: `78a77b9a0ab8bfa371f5b9baef3f443f4590d6e71cf864d67e90e9ebdfa7fc1b` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Weights licence The inspected model-access documentation does not explicitly identify terms for this exact evaluated checkpoint or fitted head; repository code terms are shown separately. Individual claims	gcorso/DiffDock README.md Original source ↗ README.md; checkpoint/access documentation and licence scope Version: 85c49b60d3e0b0182a59ee43a34a6d7036981284 Retrieved: 2026-09-16T20:00:00.818010+00:00	unreported automated source review · 2026-09-16 Audit 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. Field: `attributes.profile.facts.10.value` Source artifact SHA-256: `6f63088d85b5f05d58416ede319387c1b7f3661b27741a36314ada861f2056de` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Biological inputs Protein and ligand information under the method-specific docking or co-folding protocol Individual claims	Improving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction Original source ↗ Results/Benchmark of Protein–Ligand Complex Structure Prediction (paragraph 1); Results/Case Studies for Bond and Angle Geometries of Ligands (paragraph 1) Version: version of record Retrieved: 2026-09-16T10:41:16.555674+00:00	source checked automated source review · 2026-09-16 Audit 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. Field: `attributes.profile.facts.2.value` Source artifact SHA-256: `78a77b9a0ab8bfa371f5b9baef3f443f4590d6e71cf864d67e90e9ebdfa7fc1b` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Outputs Predicted protein–ligand binding poses Individual claims	Improving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction Original source ↗ Results/Case Studies for Bond and Angle Geometries of Ligands (paragraph 2); Methods/Implementation of the Restraints (paragraph 1) Version: version of record Retrieved: 2026-09-16T10:41:16.555674+00:00	source checked automated source review · 2026-09-16 Audit 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. Field: `attributes.profile.facts.3.value` Source artifact SHA-256: `78a77b9a0ab8bfa371f5b9baef3f443f4590d6e71cf864d67e90e9ebdfa7fc1b` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Parameters An aggregate parameter total for this exact evaluated configuration is not established by the inspected sources. Individual claims	Improving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction Original source ↗ Methods/Benchmark Dataset; Methods/Evaluation Metrics; Methods/Improving Geometry through Restraints; Methods/Implementation of the Restraints; Methods/Multiple Sequence Alignment and Structure Prediction; 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 Retrieved: 2026-09-16T10:41:16.555674+00:00	unreported automated source review · 2026-09-16 Audit 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. Field: `attributes.profile.facts.4.value` Source artifact SHA-256: `78a77b9a0ab8bfa371f5b9baef3f443f4590d6e71cf864d67e90e9ebdfa7fc1b` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Parameters An aggregate parameter total for this exact evaluated configuration is not established by the inspected sources. Individual claims	gcorso/DiffDock README.md Original source ↗ Methods/Benchmark Dataset; Methods/Evaluation Metrics; Methods/Improving Geometry through Restraints; Methods/Implementation of the Restraints; Methods/Multiple Sequence Alignment and Structure Prediction; 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: 85c49b60d3e0b0182a59ee43a34a6d7036981284 Retrieved: 2026-09-16T20:00:00.818010+00:00	unreported automated source review · 2026-09-16 Audit 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. Field: `attributes.profile.facts.4.value` Source artifact SHA-256: `6f63088d85b5f05d58416ede319387c1b7f3661b27741a36314ada861f2056de` 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

Release 2026-09-17-d277315f7d76 · Record review: needs review

3 source records and release history

Improving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction · Original source · version of record
gcorso/DiffDock README.md · Original source · 85c49b60d3e0b0182a59ee43a34a6d7036981284
gcorso/DiffDock LICENSE · Original source · 85c49b60d3e0b0182a59ee43a34a6d7036981284

Download this release

Technical metadata and extraction receipts

Stable ID: reported-model-7f6ffd9e2a08be

areas: molecular-interactions
entity level: method
version: Not reported
reported name: DiffDock
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: boltz-stereochemistry-2025; evidence-reported-base-diffdock-readme-md; source locator: Results/Case Studies for Bond and Angle Geometries of Ligands (paragraph 3); Results/Structure Prediction Using Restraint-Guided Inference (paragraph 1) | README.md model description | Results/Benchmark of Protein–Ligand Complex Structure Prediction (paragraph 6); Methods/Benchmark Dataset (paragraph 1); 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.

Related records

model: DiffDock: Protein–ligand pose prediction

Suggest a correction