ATOM3D LEP-AUROC: Ligand efficacy prediction
Ligand efficacy prediction. Scored with AUROC on ATOM3D LEP. Trained and scored under the ATOM3D split for this task. Asterisks in the paper mark a run whose training data differed.
Overview
Ligand efficacy prediction. Scored with AUROC on ATOM3D LEP. Trained and scored under the ATOM3D split for this task. Asterisks in the paper mark a run whose training data differed.
Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.
Evaluation design
Benchmarks bring together tasks and protocols. A task describes the biological question; a protocol defines a particular test.
Benchmarks
These source-backed links do not make different protocols or scores interchangeable.
Recorded 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.
Published comparisons
Explore the results reported under one evaluation protocol. Each figure keeps its source, dataset and metric together; it is not a ranking across studies. The pooled view gathers every source table that reports the same metric and names what it does not hold constant.
ATOM3D LEP-AUROC: Ligand efficacy prediction
auroc (fraction) · Higher values are better for this metric.
Every method ATOM3D reports on Ligand efficacy prediction, scored with AUROC on ATOM3D LEP.
- 3DCNN · Method · Author-reported evaluation0.589
- GNN · Method · Author-reported evaluation0.681
- ENN · Method · Author-reported evaluation0.663
- [Öztürk et al., 2018] · Configuration · Author-reported evaluation0.696
Source order is preserved. Plotted marks show point estimates; uncertainty, where reported, is retained in the printed values and table. Differences do not establish statistical significance.
ATOM3D: Tasks On Molecules in Three Dimensions · Table 5, row(LEP AUROC)Values, uncertainty and evidence
| Tested entity | Printed value | Uncertainty | Evidence |
|---|---|---|---|
| 3DCNN · Method | 0.589 fraction | Not reported | Author-reported evaluation · source checkedATOM3D: Tasks On Molecules in Three Dimensions · Table 5, row(LEP AUROC), column(3DCNN) |
| GNN · Method | 0.681 fraction | Not reported | Author-reported evaluation · source checkedATOM3D: Tasks On Molecules in Three Dimensions · Table 5, row(LEP AUROC), column(GNN) |
| ENN · Method | 0.663 fraction | Not reported | Author-reported evaluation · source checkedATOM3D: Tasks On Molecules in Three Dimensions · Table 5, row(LEP AUROC), column(ENN) |
| [Öztürk et al., 2018] · Configuration | 0.696 fraction | Not reported | Author-reported evaluation · source checkedATOM3D: Tasks On Molecules in Three Dimensions · Table 5, row(LEP AUROC), column([Öztürk et al., 2018]) |
Scope and limitations
- Author-reported numbers, source checked but not independently reproduced.
- MAE and RMSE are errors, better when lower. The other metrics are better when higher.
- Comparison methods are named by the citation the table prints; the paper's text says which method each is.
- The paper marks some runs with an asterisk to say their training data differed, though the splitting criteria were the same.
Source transcription and grouping reviewed by automated source review on 2026-09-18. These experiments were not independently reproduced by rewire.
Tested entities and results
Release 2026-09-17-134cd1815de8 · 4 evaluations · 4 metric rows. Different protocols are not a single leaderboard. Where several source tables report the same metric, the published comparisons above offer a pooled view that names what it does not hold constant.
| Metric and finding | Coverage and uncertainty | Evidence |
|---|---|---|
| 3DCNN on ATOM3D LEP-AUROC: Ligand efficacy prediction Method: 3DCNNTask: ATOM3D LEP-AUROC: Ligand efficacy predictionDataset subset: ATOM3D LEP (ATOM3D split) Trained and scored under the ATOM3D split for this task. Asterisks in the paper mark a run whose training data differed. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.589 auroc Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedATOM3D: Tasks On Molecules in Three Dimensions · Table 5, row(LEP AUROC), column(3DCNN) Source checking is not independent reproduction. |
| ENN on ATOM3D LEP-AUROC: Ligand efficacy prediction Method: ENNTask: ATOM3D LEP-AUROC: Ligand efficacy predictionDataset subset: ATOM3D LEP (ATOM3D split) Trained and scored under the ATOM3D split for this task. Asterisks in the paper mark a run whose training data differed. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.663 auroc Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedATOM3D: Tasks On Molecules in Three Dimensions · Table 5, row(LEP AUROC), column(ENN) Source checking is not independent reproduction. |
| GNN on ATOM3D LEP-AUROC: Ligand efficacy prediction Method: GNNTask: ATOM3D LEP-AUROC: Ligand efficacy predictionDataset subset: ATOM3D LEP (ATOM3D split) Trained and scored under the ATOM3D split for this task. Asterisks in the paper mark a run whose training data differed. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.681 auroc Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedATOM3D: Tasks On Molecules in Three Dimensions · Table 5, row(LEP AUROC), column(GNN) Source checking is not independent reproduction. |
| [Öztürk et al., 2018] on ATOM3D LEP-AUROC: Ligand efficacy prediction Configuration: [Öztürk et al., 2018]Task: ATOM3D LEP-AUROC: Ligand efficacy predictionDataset subset: ATOM3D LEP (ATOM3D split) Trained and scored under the ATOM3D split for this task. Asterisks in the paper mark a run whose training data differed. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.696 auroc Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedATOM3D: Tasks On Molecules in Three Dimensions · Table 5, row(LEP AUROC), column([Öztürk et al., 2018]) Source checking is not independent reproduction. |
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.
1 evidence row matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Relationship: part of discovery-benchmark-atom3d Individual claims | ATOM3D: Tasks On Molecules in Three Dimensions Table 5, row(LEP AUROC) Version: Primary full-text snapshot retrieved 2026-09-17; exact bytes pinned by SHA-256 | source checked automated source review · 2026-09-18 Audit detailsPrimary-source transcription with no human sign-off and no independent reproduction. Field: Claim: atom3d-association-lep-auroc Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
Sources and history
Release 2026-09-17-134cd1815de8 · Record review: source checked
1 source records and release history
- ATOM3D: Tasks On Molecules in Three Dimensions · Original source · Primary full-text snapshot retrieved 2026-09-17; exact bytes pinned by SHA-256
Technical metadata and extraction receipts
Stable ID: atom3d-task-lep-auroc
- areas
- molecular-interactions
- tasks
- Ligand efficacy prediction
- metric
- AUROC
- metric direction
- higher
- dataset
- ATOM3D LEP
- protocol
- Trained and scored under the ATOM3D split for this task. Asterisks in the paper mark a run whose training data differed.
- source locator
- Table 5, row(LEP AUROC)
- comparison panels
- id: atom3d-panel-lep-auroc; title: ATOM3D LEP-AUROC: Ligand efficacy prediction; protocol id: atom3d-task-lep-auroc; dataset id: atom3d-dataset-atom3d-lep; metric: auroc; unit: fraction; direction: higher; result ids: atom3d-result-3dcnn-lep-auroc-auroc; atom3d-result-gnn-lep-auroc-auroc; atom3d-result-enn-lep-auroc-auroc; atom3d-result-zt-rk-et-al-2018-lep-auroc-auroc; source ids: evidence-expansion-atom3d-92656c20; source locator: Table 5, row(LEP AUROC); context: Every method ATOM3D reports on Ligand efficacy prediction, scored with AUROC on ATOM3D LEP.; caveats: Author-reported numbers, source checked but not independently reproduced.; MAE and RMSE are errors, better when lower. The other metrics are better when higher.; Comparison methods are named by the citation the table prints; the paper's text says which method each is.; The paper marks some runs with an asterisk to say their training data differed, though the splitting criteria were the same.; review: method: automated_source_review; date: 2026-09-18
Related records
- part of: ATOM3D
- subject: ATOM3D LEP-AUROC: part of discovery-benchmark-atom3d
- benchmark: 3DCNN on ATOM3D LEP-AUROC: Ligand efficacy prediction
- benchmark: ENN on ATOM3D LEP-AUROC: Ligand efficacy prediction
- benchmark: GNN on ATOM3D LEP-AUROC: Ligand efficacy prediction
- benchmark: [Öztürk et al., 2018] on ATOM3D LEP-AUROC: Ligand efficacy prediction