Strengths and considerations
No source-reviewed explanatory claims are recorded here yet.
Protocol
PDBbind-2016 core set (Protein–ligand binding affinity scoring)
PDBbind-2016 core set · MAE. Training uses 3,772 PDBbind-2016 refined-set complexes after removal of the 285-complex core test set. CASF separates scoring, ranking and docking power.
Sources
AK-Score: Accurate Protein-Ligand Binding Affinity Prediction Using an Ensemble of 3D-Convolutional Neural Networks · Assessment of prediction accuracy of ResNext-ensemble, ResNext, and K DEEP using the PDBbind-2016 dataset and mean absolute error and root mean square error metrics.; Table 1 (ijms-21-08424-t001), row 2 K DEEP, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 3 K DEEP, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 4 K DEEP, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 5 K DEEP, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 6 AK-score-single, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 7 AK-score-single, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 8 AK-score-single, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 9 AK-score-single, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 10 AK-score-ensemble, column 3: PDBbind-2016 core set MAEAt a glance
Inputs, training, access and other details
Explanatory profile: limited source coverage · Automated source review, 2026-09-17. Review applies to the cited claims; unresolved fields are listed below. Numerical results retain their own review status.
| Property | Description and evidence |
|---|---|
| Datasets | Not extracted or verified for this record. |
| Organisms | Not extracted or verified for this record. |
| Assays | Not extracted or verified for this record. |
| Splits | Not extracted or verified for this record. |
| Allowed inputs | Not extracted or verified for this record. |
| Adaptation | Not extracted or verified for this record. |
| Metrics | Not extracted or verified for this record. |
| Baselines | Not extracted or verified for this record. |
How it works
Evaluation in this paper
Training uses 3,772 PDBbind-2016 refined-set complexes after removal of the 285-complex core test set. CASF separates scoring, ranking and docking power.
Sources
AK-Score: Accurate Protein-Ligand Binding Affinity Prediction Using an Ensemble of 3D-Convolutional Neural Networks · Assessment of prediction accuracy of ResNext-ensemble, ResNext, and K DEEP using the PDBbind-2016 dataset and mean absolute error and root mean square error metrics.; Table 1 (ijms-21-08424-t001), row 2 K DEEP, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 3 K DEEP, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 4 K DEEP, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 5 K DEEP, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 6 AK-score-single, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 7 AK-score-single, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 8 AK-score-single, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 9 AK-score-single, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 10 AK-score-ensemble, column 3: PDBbind-2016 core set MAEEvaluation design
Benchmarks bring together tasks and protocols. A task describes the biological question; a protocol defines a particular test.
These source-backed links do not make different protocols or scores interchangeable.
Recorded evaluations
Each evaluation records what was tested and under which conditions.
- K DEEP · 0.0006: PDBbind-2016 core set
- AK-score-ensemble · 0.0007: PDBbind-2016 core set
- AK-score-single · 0.0010: PDBbind-2016 core set
- K DEEP · 0.0005: PDBbind-2016 core set
- K DEEP · 0.0001: PDBbind-2016 core set
- AK-score-single · 0.0005: PDBbind-2016 core set
- AK-score-single · 0.0007: PDBbind-2016 core set
- K DEEP · 0.0010: PDBbind-2016 core set
- AK-score-single · 0.0001: PDBbind-2016 core set
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.
PDBbind-2016 core set · MAE
MAE (kcal/mol) · Lower values are better for this metric.
Training uses 3,772 PDBbind-2016 refined-set complexes after removal of the 285-complex core test set. CASF separates scoring, ranking and docking power.
- K DEEP · 0.0001 · Configuration · Independent external evaluation1.131
- K DEEP · 0.0005 · Configuration · Independent external evaluation1.200
- K DEEP · 0.0006 · Configuration · Independent external evaluation1.164
- K DEEP · 0.0010 · Configuration · Independent external evaluation1.219
- AK-score-single · 0.0001 · Configuration · Author-reported evaluation1.159
- AK-score-single · 0.0005 · Configuration · Author-reported evaluation1.101
- AK-score-single · 0.0007 · Configuration · Author-reported evaluation1.130
- AK-score-single · 0.0010 · Configuration · Author-reported evaluation1.110
- AK-score-ensemble · 0.0007 · Configuration · Author-reported evaluation 1.014
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.
AK-Score: Accurate Protein-Ligand Binding Affinity Prediction Using an Ensemble of 3D-Convolutional Neural Networks · Assessment of prediction accuracy of ResNext-ensemble, ResNext, and K DEEP using the PDBbind-2016 dataset and mean absolute error and root mean square error metrics.; Table 1 (ijms-21-08424-t001), row 2 K DEEP, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 3 K DEEP, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 4 K DEEP, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 5 K DEEP, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 6 AK-score-single, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 7 AK-score-single, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 8 AK-score-single, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 9 AK-score-single, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 10 AK-score-ensemble, column 3: PDBbind-2016 core set MAEValues, uncertainty and evidence
| Tested entity | Printed value | Uncertainty | Evidence |
|---|---|---|---|
| K DEEP · 0.0001 · Configuration | 1.131 kcal/mol | Not reported | Independent external evaluation · source checkedAK-Score: Accurate Protein-Ligand Binding Affinity Prediction Using an Ensemble of 3D-Convolutional Neural Networks · Table 1 (ijms-21-08424-t001), row 2 K DEEP, column 3: PDBbind-2016 core set MAE |
| K DEEP · 0.0005 · Configuration | 1.200 kcal/mol | Not reported | Independent external evaluation · source checkedAK-Score: Accurate Protein-Ligand Binding Affinity Prediction Using an Ensemble of 3D-Convolutional Neural Networks · Table 1 (ijms-21-08424-t001), row 3 K DEEP, column 3: PDBbind-2016 core set MAE |
| K DEEP · 0.0006 · Configuration | 1.164 kcal/mol | Not reported | Independent external evaluation · source checkedAK-Score: Accurate Protein-Ligand Binding Affinity Prediction Using an Ensemble of 3D-Convolutional Neural Networks · Table 1 (ijms-21-08424-t001), row 4 K DEEP, column 3: PDBbind-2016 core set MAE |
| K DEEP · 0.0010 · Configuration | 1.219 kcal/mol | Not reported | Independent external evaluation · source checkedAK-Score: Accurate Protein-Ligand Binding Affinity Prediction Using an Ensemble of 3D-Convolutional Neural Networks · Table 1 (ijms-21-08424-t001), row 5 K DEEP, column 3: PDBbind-2016 core set MAE |
| AK-score-single · 0.0001 · Configuration | 1.159 kcal/mol | Not reported | Author-reported evaluation · source checkedAK-Score: Accurate Protein-Ligand Binding Affinity Prediction Using an Ensemble of 3D-Convolutional Neural Networks · Table 1 (ijms-21-08424-t001), row 6 AK-score-single, column 3: PDBbind-2016 core set MAE |
| AK-score-single · 0.0005 · Configuration | 1.101 kcal/mol | Not reported | Author-reported evaluation · source checkedAK-Score: Accurate Protein-Ligand Binding Affinity Prediction Using an Ensemble of 3D-Convolutional Neural Networks · Table 1 (ijms-21-08424-t001), row 7 AK-score-single, column 3: PDBbind-2016 core set MAE |
| AK-score-single · 0.0007 · Configuration | 1.130 kcal/mol | Not reported | Author-reported evaluation · source checkedAK-Score: Accurate Protein-Ligand Binding Affinity Prediction Using an Ensemble of 3D-Convolutional Neural Networks · Table 1 (ijms-21-08424-t001), row 8 AK-score-single, column 3: PDBbind-2016 core set MAE |
| AK-score-single · 0.0010 · Configuration | 1.110 kcal/mol | Not reported | Author-reported evaluation · source checkedAK-Score: Accurate Protein-Ligand Binding Affinity Prediction Using an Ensemble of 3D-Convolutional Neural Networks · Table 1 (ijms-21-08424-t001), row 9 AK-score-single, column 3: PDBbind-2016 core set MAE |
| AK-score-ensemble · 0.0007 · Configuration | 1.014 kcal/mol | Not reported | Author-reported evaluation · source checkedAK-Score: Accurate Protein-Ligand Binding Affinity Prediction Using an Ensemble of 3D-Convolutional Neural Networks · Table 1 (ijms-21-08424-t001), row 10 AK-score-ensemble, column 3: PDBbind-2016 core set MAE |
Scope and limitations
- Learning rates define distinct evaluated configurations. Table 2 ensemble Pearson 0.812 is distinct from the 30-network ensemble Pearson 0.827 in Figure 3. Do not transfer the 285-complex scoring denominator to ranking or docking rows without their appropriate grouping. Origins are labelled per method; appearance in one table does not constitute independent replication of every model.
Source transcription and grouping reviewed by automated source review on 2026-09-17. These experiments were not independently reproduced by rewire.
Tested entities and results
Release 2026-09-17-d277315f7d76 · 9 evaluations · 18 metric rows. Different protocols are not a single leaderboard.
| Metric and finding | Coverage and uncertainty | Evidence |
|---|---|---|
| AK-score-single · 0.0010: PDBbind-2016 core set Configuration: AK-score-single · 0.0010Protocol: PDBbind-2016 core set (Protein–ligand binding affinity scoring)Dataset: PDBbind-2016 core set Training uses 3,772 PDBbind-2016 refined-set complexes after removal of the 285-complex core test set. CASF separates scoring, ranking and docking power. Author-reported evaluation · Evaluation metadata: needs review | ||
| 1.110 MAE Unit: kcal/mol · Direction: lower | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedAK-Score: Accurate Protein-Ligand Binding Affinity Prediction Using an Ensemble of 3D-Convolutional Neural Networks · Table 1 (ijms-21-08424-t001), row 9 AK-score-single, column 3: PDBbind-2016 core set MAE Source checking is not independent reproduction. |
| 1.406 RMSE Unit: kcal/mol · Direction: lower | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedAK-Score: Accurate Protein-Ligand Binding Affinity Prediction Using an Ensemble of 3D-Convolutional Neural Networks · Table 1 (ijms-21-08424-t001), row 9 AK-score-single, column 4: PDBbind-2016 core set RMSE Source checking is not independent reproduction. |
| K DEEP · 0.0005: PDBbind-2016 core set Configuration: K DEEP · 0.0005Protocol: PDBbind-2016 core set (Protein–ligand binding affinity scoring)Dataset: PDBbind-2016 core set Training uses 3,772 PDBbind-2016 refined-set complexes after removal of the 285-complex core test set. CASF separates scoring, ranking and docking power. Independent external evaluation · Evaluation metadata: needs review | ||
| 1.200 MAE Unit: kcal/mol · Direction: lower | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedAK-Score: Accurate Protein-Ligand Binding Affinity Prediction Using an Ensemble of 3D-Convolutional Neural Networks · Table 1 (ijms-21-08424-t001), row 3 K DEEP, column 3: PDBbind-2016 core set MAE Source checking is not independent reproduction. |
| 1.519 RMSE Unit: kcal/mol · Direction: lower | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedAK-Score: Accurate Protein-Ligand Binding Affinity Prediction Using an Ensemble of 3D-Convolutional Neural Networks · Table 1 (ijms-21-08424-t001), row 3 K DEEP, column 4: PDBbind-2016 core set RMSE Source checking is not independent reproduction. |
| K DEEP · 0.0010: PDBbind-2016 core set Configuration: K DEEP · 0.0010Protocol: PDBbind-2016 core set (Protein–ligand binding affinity scoring)Dataset: PDBbind-2016 core set Training uses 3,772 PDBbind-2016 refined-set complexes after removal of the 285-complex core test set. CASF separates scoring, ranking and docking power. Independent external evaluation · Evaluation metadata: needs review | ||
| 1.219 MAE Unit: kcal/mol · Direction: lower | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedAK-Score: Accurate Protein-Ligand Binding Affinity Prediction Using an Ensemble of 3D-Convolutional Neural Networks · Table 1 (ijms-21-08424-t001), row 5 K DEEP, column 3: PDBbind-2016 core set MAE Source checking is not independent reproduction. |
| 1.536 RMSE Unit: kcal/mol · Direction: lower | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedAK-Score: Accurate Protein-Ligand Binding Affinity Prediction Using an Ensemble of 3D-Convolutional Neural Networks · Table 1 (ijms-21-08424-t001), row 5 K DEEP, column 4: PDBbind-2016 core set RMSE Source checking is not independent reproduction. |
| K DEEP · 0.0001: PDBbind-2016 core set Configuration: K DEEP · 0.0001Protocol: PDBbind-2016 core set (Protein–ligand binding affinity scoring)Dataset: PDBbind-2016 core set Training uses 3,772 PDBbind-2016 refined-set complexes after removal of the 285-complex core test set. CASF separates scoring, ranking and docking power. Independent external evaluation · Evaluation metadata: needs review | ||
| 1.131 MAE Unit: kcal/mol · Direction: lower | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedAK-Score: Accurate Protein-Ligand Binding Affinity Prediction Using an Ensemble of 3D-Convolutional Neural Networks · Table 1 (ijms-21-08424-t001), row 2 K DEEP, column 3: PDBbind-2016 core set MAE Source checking is not independent reproduction. |
| 1.462 RMSE Unit: kcal/mol · Direction: lower | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedAK-Score: Accurate Protein-Ligand Binding Affinity Prediction Using an Ensemble of 3D-Convolutional Neural Networks · Table 1 (ijms-21-08424-t001), row 2 K DEEP, column 4: PDBbind-2016 core set RMSE Source checking is not independent reproduction. |
| AK-score-ensemble · 0.0007: PDBbind-2016 core set Configuration: AK-score-ensemble · 0.0007Protocol: PDBbind-2016 core set (Protein–ligand binding affinity scoring)Dataset: PDBbind-2016 core set Training uses 3,772 PDBbind-2016 refined-set complexes after removal of the 285-complex core test set. CASF separates scoring, ranking and docking power. Author-reported evaluation · Evaluation metadata: needs review | ||
|
1.014
MAE Unit: kcal/mol · Direction: lower | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedAK-Score: Accurate Protein-Ligand Binding Affinity Prediction Using an Ensemble of 3D-Convolutional Neural Networks · Table 1 (ijms-21-08424-t001), row 10 AK-score-ensemble, column 3: PDBbind-2016 core set MAE Source checking is not independent reproduction. |
|
1.293
RMSE Unit: kcal/mol · Direction: lower | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedAK-Score: Accurate Protein-Ligand Binding Affinity Prediction Using an Ensemble of 3D-Convolutional Neural Networks · Table 1 (ijms-21-08424-t001), row 10 AK-score-ensemble, column 4: PDBbind-2016 core set RMSE Source checking is not independent reproduction. |
| K DEEP · 0.0006: PDBbind-2016 core set Configuration: K DEEP · 0.0006Protocol: PDBbind-2016 core set (Protein–ligand binding affinity scoring)Dataset: PDBbind-2016 core set Training uses 3,772 PDBbind-2016 refined-set complexes after removal of the 285-complex core test set. CASF separates scoring, ranking and docking power. Independent external evaluation · Evaluation metadata: needs review | ||
| 1.534 RMSE Unit: kcal/mol · Direction: lower | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedAK-Score: Accurate Protein-Ligand Binding Affinity Prediction Using an Ensemble of 3D-Convolutional Neural Networks · Table 1 (ijms-21-08424-t001), row 4 K DEEP, column 4: PDBbind-2016 core set RMSE Source checking is not independent reproduction. |
| 1.164 MAE Unit: kcal/mol · Direction: lower | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedAK-Score: Accurate Protein-Ligand Binding Affinity Prediction Using an Ensemble of 3D-Convolutional Neural Networks · Table 1 (ijms-21-08424-t001), row 4 K DEEP, column 3: PDBbind-2016 core set MAE Source checking is not independent reproduction. |
| AK-score-single · 0.0007: PDBbind-2016 core set Configuration: AK-score-single · 0.0007Protocol: PDBbind-2016 core set (Protein–ligand binding affinity scoring)Dataset: PDBbind-2016 core set Training uses 3,772 PDBbind-2016 refined-set complexes after removal of the 285-complex core test set. CASF separates scoring, ranking and docking power. Author-reported evaluation · Evaluation metadata: needs review | ||
| 1.130 MAE Unit: kcal/mol · Direction: lower | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedAK-Score: Accurate Protein-Ligand Binding Affinity Prediction Using an Ensemble of 3D-Convolutional Neural Networks · Table 1 (ijms-21-08424-t001), row 8 AK-score-single, column 3: PDBbind-2016 core set MAE Source checking is not independent reproduction. |
| 1.425 RMSE Unit: kcal/mol · Direction: lower | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedAK-Score: Accurate Protein-Ligand Binding Affinity Prediction Using an Ensemble of 3D-Convolutional Neural Networks · Table 1 (ijms-21-08424-t001), row 8 AK-score-single, column 4: PDBbind-2016 core set RMSE Source checking is not independent reproduction. |
| AK-score-single · 0.0001: PDBbind-2016 core set Configuration: AK-score-single · 0.0001Protocol: PDBbind-2016 core set (Protein–ligand binding affinity scoring)Dataset: PDBbind-2016 core set Training uses 3,772 PDBbind-2016 refined-set complexes after removal of the 285-complex core test set. CASF separates scoring, ranking and docking power. Author-reported evaluation · Evaluation metadata: needs review | ||
| 1.159 MAE Unit: kcal/mol · Direction: lower | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedAK-Score: Accurate Protein-Ligand Binding Affinity Prediction Using an Ensemble of 3D-Convolutional Neural Networks · Table 1 (ijms-21-08424-t001), row 6 AK-score-single, column 3: PDBbind-2016 core set MAE Source checking is not independent reproduction. |
| 1.511 RMSE Unit: kcal/mol · Direction: lower | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedAK-Score: Accurate Protein-Ligand Binding Affinity Prediction Using an Ensemble of 3D-Convolutional Neural Networks · Table 1 (ijms-21-08424-t001), row 6 AK-score-single, column 4: PDBbind-2016 core set RMSE Source checking is not independent reproduction. |
| AK-score-single · 0.0005: PDBbind-2016 core set Configuration: AK-score-single · 0.0005Protocol: PDBbind-2016 core set (Protein–ligand binding affinity scoring)Dataset: PDBbind-2016 core set Training uses 3,772 PDBbind-2016 refined-set complexes after removal of the 285-complex core test set. CASF separates scoring, ranking and docking power. Author-reported evaluation · Evaluation metadata: needs review | ||
| 1.101 MAE Unit: kcal/mol · Direction: lower | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedAK-Score: Accurate Protein-Ligand Binding Affinity Prediction Using an Ensemble of 3D-Convolutional Neural Networks · Table 1 (ijms-21-08424-t001), row 7 AK-score-single, column 3: PDBbind-2016 core set MAE Source checking is not independent reproduction. |
| 1.415 RMSE Unit: kcal/mol · Direction: lower | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedAK-Score: Accurate Protein-Ligand Binding Affinity Prediction Using an Ensemble of 3D-Convolutional Neural Networks · Table 1 (ijms-21-08424-t001), row 7 AK-score-single, column 4: PDBbind-2016 core set RMSE Source checking is not independent reproduction. |
Papers and result coverage
Last literature check: 2026-09-17. Dated primary-source discovery and protocol/table screening. Source checking does not mean experimental reproduction. Only separately extracted and independently reviewed numeric batches are publishable.
| Paper or primary resource | Version | Reference |
|---|---|---|
| AK-Score: Accurate Protein-Ligand Binding Affinity Prediction Using an Ensemble of 3D-Convolutional Neural Networks | version of record | Read source DOI: 10.3390/ijms21228424 |
What is still missing
- exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
Search and extraction details
complete tables extracted
Searches
- AK-Score: Accurate Protein-Ligand Binding Affinity Prediction Using an Ensemble of 3D-Convolutional Neural Networks 10.3390/ijms21228424
Evidence locations
- Assessment of prediction accuracy of ResNext-ensemble, ResNext, and K DEEP using the PDBbind-2016 dataset and mean absolute error and root mean square error metrics.; Table 1 (ijms-21-08424-t001), row 2 K DEEP, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 3 K DEEP, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 4 K DEEP, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 5 K DEEP, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 6 AK-score-single, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 7 AK-score-single, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 8 AK-score-single, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 9 AK-score-single, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 10 AK-score-ensemble, column 3: PDBbind-2016 core set MAE
Strengths and limitations
Limitations and conditions
No source-reviewed explanatory claims are recorded here yet.
Profile review details
Primary-source transcription and separate automated review. No human sign-off or experimental reproduction.
Stable record: paper-protocol-d2055666ed2da8d7d7Evidence 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.
3 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Evaluation in this paper Training uses 3,772 PDBbind-2016 refined-set complexes after removal of the 285-complex core test set. CASF separates scoring, ranking and docking power. Individual claims | AK-Score: Accurate Protein-Ligand Binding Affinity Prediction Using an Ensemble of 3D-Convolutional Neural Networks Assessment of prediction accuracy of ResNext-ensemble, ResNext, and K DEEP using the PDBbind-2016 dataset and mean absolute error and root mean square error metrics.; Table 1 (ijms-21-08424-t001), row 2 K DEEP, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 3 K DEEP, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 4 K DEEP, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 5 K DEEP, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 6 AK-score-single, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 7 AK-score-single, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 8 AK-score-single, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 9 AK-score-single, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 10 AK-score-ensemble, column 3: PDBbind-2016 core set MAE Version: version of record | source checked automated source review · 2026-09-17 Audit detailsPrimary-source transcription and separate automated review. No human sign-off or experimental reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Introduction PDBbind-2016 core set · MAE. Training uses 3,772 PDBbind-2016 refined-set complexes after removal of the 285-complex core test set. CASF separates scoring, ranking and docking power. Individual claims | AK-Score: Accurate Protein-Ligand Binding Affinity Prediction Using an Ensemble of 3D-Convolutional Neural Networks Assessment of prediction accuracy of ResNext-ensemble, ResNext, and K DEEP using the PDBbind-2016 dataset and mean absolute error and root mean square error metrics.; Table 1 (ijms-21-08424-t001), row 2 K DEEP, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 3 K DEEP, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 4 K DEEP, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 5 K DEEP, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 6 AK-score-single, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 7 AK-score-single, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 8 AK-score-single, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 9 AK-score-single, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 10 AK-score-ensemble, column 3: PDBbind-2016 core set MAE Version: version of record | source checked automated source review · 2026-09-17 Audit detailsPrimary-source transcription and separate automated review. No human sign-off or experimental reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Relationship: evaluates task reported-task-a78312d5df6dad Individual claims | AK-Score: Accurate Protein-Ligand Binding Affinity Prediction Using an Ensemble of 3D-Convolutional Neural Networks Assessment of prediction accuracy of ResNext-ensemble, ResNext, and K DEEP using the PDBbind-2016 dataset and mean absolute error and root mean square error metrics.; Table 1 (ijms-21-08424-t001), row 2 K DEEP, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 3 K DEEP, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 4 K DEEP, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 5 K DEEP, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 6 AK-score-single, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 7 AK-score-single, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 8 AK-score-single, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 9 AK-score-single, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 10 AK-score-ensemble, column 3: PDBbind-2016 core set MAE Version: version of record | source checked automated source review · 2026-09-17 Audit detailsField: Claim: paper-claim-89e6e93347f7f017fe Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Sources and history
Release 2026-09-17-d277315f7d76 · Record review: needs review
1 source records and release history
- AK-Score: Accurate Protein-Ligand Binding Affinity Prediction Using an Ensemble of 3D-Convolutional Neural Networks · Original source · version of record
Technical metadata and extraction receipts
Stable ID: paper-protocol-d2055666ed2da8d7d7
- areas
- molecular-interactions
- tasks
- Protein–ligand binding affinity scoring
- entity level
- protocol
- protocol
- Training uses 3,772 PDBbind-2016 refined-set complexes after removal of the 285-complex core test set. CASF separates scoring, ranking and docking power.
- comparison panels
- id: akscore-2020-ijms-21-08424-t001-mae; title: PDBbind-2016 core set · MAE; protocol id: paper-protocol-d2055666ed2da8d7d7; dataset id: paper-dataset-b882219f61119f515b; metric: MAE; unit: kcal/mol; direction: lower; result ids: paper-result-2937b9a198c2ffe40c; paper-result-0cef59103b4c628552; paper-result-d80662bd72b1a95c2d; paper-result-1a479712bc41f21505; paper-result-554c59f6399b6ba950; paper-result-63d495bd9e454cfcd5; paper-result-4eab2cf242097371e4; paper-result-01a1e373e034e1d96b; paper-result-42921822c26167495c; source ids: akscore-2020; source locator: Assessment of prediction accuracy of ResNext-ensemble, ResNext, and K DEEP using the PDBbind-2016 dataset and mean absolute error and root mean square error metrics.; Table 1 (ijms-21-08424-t001), row 2 K DEEP, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 3 K DEEP, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 4 K DEEP, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 5 K DEEP, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 6 AK-score-single, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 7 AK-score-single, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 8 AK-score-single, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 9 AK-score-single, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 10 AK-score-ensemble, column 3: PDBbind-2016 core set MAE; context: Training uses 3,772 PDBbind-2016 refined-set complexes after removal of the 285-complex core test set. CASF separates scoring, ranking and docking power.; caveats: Learning rates define distinct evaluated configurations. Table 2 ensemble Pearson 0.812 is distinct from the 30-network ensemble Pearson 0.827 in Figure 3. Do not transfer the 285-complex scoring denominator to ranking or docking rows without their appropriate grouping. Origins are labelled per method; appearance in one table does not constitute independent replication of every model.; review: method: automated_source_review; date: 2026-09-17; id: akscore-2020-ijms-21-08424-t001-rmse; title: PDBbind-2016 core set · RMSE; protocol id: paper-protocol-d2055666ed2da8d7d7; dataset id: paper-dataset-b882219f61119f515b; metric: RMSE; unit: kcal/mol; direction: lower; result ids: paper-result-3c5790191bbab267ae; paper-result-23becb504fd247078e; paper-result-4b5b00557aa8abe03a; paper-result-d4f4f883f2596117e4; paper-result-bf54f8428bcdf902eb; paper-result-c924af293e1a3a8081; paper-result-8369e556ec65212435; paper-result-c9a3dfa12bfe1226e6; paper-result-7c4fb33077af93ea22; source ids: akscore-2020; source locator: Assessment of prediction accuracy of ResNext-ensemble, ResNext, and K DEEP using the PDBbind-2016 dataset and mean absolute error and root mean square error metrics.; Table 1 (ijms-21-08424-t001), row 2 K DEEP, column 4: PDBbind-2016 core set RMSE; Table 1 (ijms-21-08424-t001), row 3 K DEEP, column 4: PDBbind-2016 core set RMSE; Table 1 (ijms-21-08424-t001), row 4 K DEEP, column 4: PDBbind-2016 core set RMSE; Table 1 (ijms-21-08424-t001), row 5 K DEEP, column 4: PDBbind-2016 core set RMSE; Table 1 (ijms-21-08424-t001), row 6 AK-score-single, column 4: PDBbind-2016 core set RMSE; Table 1 (ijms-21-08424-t001), row 7 AK-score-single, column 4: PDBbind-2016 core set RMSE; Table 1 (ijms-21-08424-t001), row 8 AK-score-single, column 4: PDBbind-2016 core set RMSE; Table 1 (ijms-21-08424-t001), row 9 AK-score-single, column 4: PDBbind-2016 core set RMSE; Table 1 (ijms-21-08424-t001), row 10 AK-score-ensemble, column 4: PDBbind-2016 core set RMSE; context: Training uses 3,772 PDBbind-2016 refined-set complexes after removal of the 285-complex core test set. CASF separates scoring, ranking and docking power.; caveats: Learning rates define distinct evaluated configurations. Table 2 ensemble Pearson 0.812 is distinct from the 30-network ensemble Pearson 0.827 in Figure 3. Do not transfer the 285-complex scoring denominator to ranking or docking rows without their appropriate grouping. Origins are labelled per method; appearance in one table does not constitute independent replication of every model.; review: method: automated_source_review; date: 2026-09-17
- benchmark research
- review date: 2026-09-17; status: complete_tables_extracted; primary sources: akscore-2020; inspected locators: Assessment of prediction accuracy of ResNext-ensemble, ResNext, and K DEEP using the PDBbind-2016 dataset and mean absolute error and root mean square error metrics.; Table 1 (ijms-21-08424-t001), row 2 K DEEP, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 3 K DEEP, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 4 K DEEP, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 5 K DEEP, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 6 AK-score-single, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 7 AK-score-single, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 8 AK-score-single, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 9 AK-score-single, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 10 AK-score-ensemble, column 3: PDBbind-2016 core set MAE; searched queries: AK-Score: Accurate Protein-Ligand Binding Affinity Prediction Using an Ensemble of 3D-Convolutional Neural Networks 10.3390/ijms21228424; gaps: exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.; claim scope: Dated primary-source discovery and protocol/table screening. Source checking does not mean experimental reproduction. Only separately extracted and independently reviewed numeric batches are publishable.
- legacy kinds
- benchmark
- entity classification
- review date: 2026-09-17; rationale: The source-backed record identifies a specified evaluated procedure and its dataset/split/scoring context. Classify it as a protocol while preserving version and comparison restrictions.; source ids: akscore-2020; source locator: Assessment of prediction accuracy of ResNext-ensemble, ResNext, and K DEEP using the PDBbind-2016 dataset and mean absolute error and root mean square error metrics.; Table 1 (ijms-21-08424-t001), row 2 K DEEP, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 3 K DEEP, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 4 K DEEP, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 5 K DEEP, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 6 AK-score-single, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 7 AK-score-single, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 8 AK-score-single, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 9 AK-score-single, column 3: PDBbind-2016 core set MAE; Table 1 (ijms-21-08424-t001), row 10 AK-score-ensemble, column 3: PDBbind-2016 core set MAE; ambiguities: None recorded
Related records
- evaluates task: Protein–ligand binding affinity scoring
- subject: PDBbind-2016 core set (Protein–ligand binding affinity scoring): links:evaluates_task:reported-task-a78312d5df6dad
- benchmark: K DEEP · 0.0006: PDBbind-2016 core set
- benchmark: AK-score-ensemble · 0.0007: PDBbind-2016 core set
- benchmark: AK-score-single · 0.0010: PDBbind-2016 core set
- benchmark: K DEEP · 0.0005: PDBbind-2016 core set
- benchmark: K DEEP · 0.0001: PDBbind-2016 core set
- benchmark: AK-score-single · 0.0005: PDBbind-2016 core set
- benchmark: AK-score-single · 0.0007: PDBbind-2016 core set
- benchmark: K DEEP · 0.0010: PDBbind-2016 core set
- benchmark: AK-score-single · 0.0001: PDBbind-2016 core set