rewirebio.iobenchmarks
Task

Protein–ligand binding energy prediction

Protein–ligand energy prediction compares alternative fingerprint descriptors and regression methods.

SourcesMachine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints · Results and Discussion; Conclusion; cached text lines 44–46, 61

2 evaluations · 2 results

Overview

Evaluation procedure diagram
How it worksComputational evaluation flow
Computational evaluation flow1. Input: Protein/ligand fingerprint combinations.. Then: 2. Evaluation: Supervised regression using LASSO or LightGBM.. Then: 3. Readout: Pearson correlation and root-mean-square error.Computational evaluation flow1. Input: Protein/ligand fingerprint combinations.. Then: 2. Evaluation: Supervised regression using LASSO or LightGBM.. Then: 3. Readout: Pearson correlation and root-mean-square error.Computational evaluation flow1. Input: Protein/ligand fingerprint combinations.. Then: 2. Evaluation: Supervised regression using LASSO or LightGBM.. Then: 3. Readout: Pearson correlation and root-mean-square error.

Conceptual summary of the cited evaluation; exact task configuration and source version remain part of the protocol.

SourcesMachine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints · Results and Discussion; Conclusion; cached text lines 44–46, 61

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

2 recorded evaluations, 2 metric rows. A comparison chart has not yet been validated for these results. The table retains the individual findings and their sources.

View coverage and remaining gaps across all benchmarks

Results

Results are available, but no reviewed comparison panel is linked in this release.

All evaluations

2 evaluations · 2 results. Different protocols are not a single leaderboard.

Filter evaluations

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configurationProtocol and datasetFindingEvidence and details
Configuration: PMF + ECFP + PF (LightGBM)Task: Protein–ligand binding energy prediction
Dataset: Fingerprint-scoring benchmark
0.79 Pearson
unitless · unknown

Uncertainty: Not yet extracted

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

PMF + ECFP + PF (LightGBM): Protein–ligand binding energy prediction

Binding-energy model using ligand and protein fingerprints with LightGBM.

Aggregation: Not reported

Machine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints · Table 1, PMF + ECFP + PF / LightGBM row, R column
Configuration: PMF (LASSO)Task: Protein–ligand binding energy prediction
Dataset: Fingerprint-scoring benchmark
0.67 Pearson
unitless · unknown

Uncertainty: Not yet extracted

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

PMF (LASSO): Protein–ligand binding energy prediction

PMF-only LASSO baseline evaluated by the same authors.

Aggregation: Not reported

Machine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints · Table 1, PMF / LASSO row, R column

Source checking is not independent reproduction. Release 2026-11-21-adc15377fab2.

Methods and evaluation design

Procedure, tasks and evaluated configurations

How it works

Evaluation methodology

Kd-labelled complexes from PDBbind v2019, with the corresponding CASF-2016 core structures reserved as the external test subset. Pearson correlation and root-mean-square error. LASSO and LightGBM with alternative protein/ligand fingerprint combinations.

SourcesMachine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints · Computational Details, cached paragraph 30; Results and Discussion; Conclusion; cached text lines 44–46, 61; Results and Discussion; Conclusion; cached text lines 44–46, 61

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.

Strengths, limitations and unresolved questions

Strengths and limitations

Strengths and considerations

No source-reviewed explanatory claims are recorded here yet.

Profile review details

Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged.

Stable record: reported-task-94802534b7026d

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
PropertyDescription and evidence
DatasetsKd-labelled complexes from PDBbind v2019, with the corresponding CASF-2016 core structures reserved as the external test subset.
SourcesMachine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints · Computational Details, cached paragraph 30
SplitsKd-labelled PDBbind v2019 complexes are divided into training, hyperparameter-selection (“pretest”) and an external CASF-2016 core test subset. Ten random training/pretest allocations are assessed, and the allocation with correlation closest to their average is retained; the external test set is not used for fitting.
SourcesMachine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints · Computational Details; cached paragraphs 30–35
MetricsPearson correlation and root-mean-square error.
SourcesMachine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints · Results and Discussion; Conclusion; cached text lines 44–46, 61
BaselinesLASSO and LightGBM with alternative protein/ligand fingerprint combinations.
SourcesMachine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints · Results and Discussion; Conclusion; cached text lines 44–46, 61
Leakage controlsThe checked fingerprint-comparison passages do not define scaffold- or protein-target-disjoint evaluation. · Not reported in inspected sources
SourcesMachine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints · Results and Discussion; Conclusion; cached text lines 44–46, 61
UncertaintyThe cited text-accessible evaluation sections give no confidence-interval, resampling or repeat-run error-bar specification. Image-only tables and uninspected supplements are outside this absence claim. · Not reported in inspected sources
SourcesMachine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints · Results and Discussion; Conclusion; cached text lines 44–46, 61
Entity typePaper-specific computational evaluation protocol.
SourcesMachine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints · Results and Discussion; Conclusion; cached text lines 44–46, 61
OrganismsPDBbind v2019 complexes with Kd measurements are selected for binding-energy assessment. Computational Details does not tabulate their source organisms or a species-specific evaluation subset. · Not reported in inspected sources
SourcesMachine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints · Computational Details, dataset selection and external CASF test
AssaysProtein–ligand binding-energy labels.
SourcesMachine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints · Results and Discussion; Conclusion; cached text lines 44–46, 61
Allowed inputsProtein/ligand fingerprint combinations.
SourcesMachine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints · Results and Discussion; Conclusion; cached text lines 44–46, 61
AdaptationSupervised regression using LASSO or LightGBM.
SourcesMachine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints · Results and Discussion; Conclusion; cached text lines 44–46, 61

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 resourceVersionReference
Machine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein FingerprintsPMC archival version PMC9178954.1Read source
DOI: 10.1021/acsomega.2c02822
Historical gaps recorded on 2026-09-17

The catalogue now holds 2 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.

  • RMSE is lower-is-better; do not mix correlation and energy errors.
  • Conventional-function rows must retain software suffixes and scoring settings; exact common test/context needs methods review before merging Tables 1–2 into one chart.
Search and extraction details

primary comparison table screened

Searches

  • "PMC9178954"

Evidence locations

  • Tables 1–2
  • Results: scoring functions

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.

17 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-11-21-adc15377fab2
Property and statementOriginal source and locationReview and provenance
Diagram caption
Conceptual summary of the cited evaluation; exact task configuration and source version remain part of the protocol.
Individual claims
Machine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints

Original source ↗

Results and Discussion; Conclusion; cached text lines 44–46, 61

Version: PMC archival version PMC9178954.1
Retrieved: 2026-09-16T10:44:03.439460+00:00

source checked

automated source review · 2026-09-16

Audit details

Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged.

Field: attributes.profile.diagram.caption

Source artifact SHA-256: 47bd60c6392b801095fdb604de06c0d4bda6f555bae58e9955e491a5abf60576

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Diagram steps
  • Input: Protein/ligand fingerprint combinations.
  • Evaluation: Supervised regression using LASSO or LightGBM.
  • Readout: Pearson correlation and root-mean-square error.
Individual claims
Machine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints

Original source ↗

Results and Discussion; Conclusion; cached text lines 44–46, 61

Version: PMC archival version PMC9178954.1
Retrieved: 2026-09-16T10:44:03.439460+00:00

source checked

automated source review · 2026-09-16

Audit details

Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged.

Field: attributes.profile.diagram.steps

Source artifact SHA-256: 47bd60c6392b801095fdb604de06c0d4bda6f555bae58e9955e491a5abf60576

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Diagram title
Computational evaluation flow
Individual claims
Machine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints

Original source ↗

Results and Discussion; Conclusion; cached text lines 44–46, 61

Version: PMC archival version PMC9178954.1
Retrieved: 2026-09-16T10:44:03.439460+00:00

source checked

automated source review · 2026-09-16

Audit details

Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged.

Field: attributes.profile.diagram.title

Source artifact SHA-256: 47bd60c6392b801095fdb604de06c0d4bda6f555bae58e9955e491a5abf60576

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Datasets
Kd-labelled complexes from PDBbind v2019, with the corresponding CASF-2016 core structures reserved as the external test subset.
Individual claims
Machine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints

Original source ↗

Computational Details, cached paragraph 30

Version: PMC archival version PMC9178954.1
Retrieved: 2026-09-16T10:44:03.439460+00:00

source checked

automated source review · 2026-09-16

Audit details

Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged.

Field: attributes.profile.facts.0.value

Source artifact SHA-256: 47bd60c6392b801095fdb604de06c0d4bda6f555bae58e9955e491a5abf60576

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Splits
Kd-labelled PDBbind v2019 complexes are divided into training, hyperparameter-selection (“pretest”) and an external CASF-2016 core test subset. Ten random training/pretest allocations are assessed, and the allocation with correlation closest to their average is retained; the external test set is not used for fitting.
Individual claims
Machine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints

Original source ↗

Computational Details; cached paragraphs 30–35

Version: PMC archival version PMC9178954.1
Retrieved: 2026-09-16T10:44:03.439460+00:00

source checked

automated source review · 2026-09-16

Audit details

Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged.

Field: attributes.profile.facts.1.value

Source artifact SHA-256: 47bd60c6392b801095fdb604de06c0d4bda6f555bae58e9955e491a5abf60576

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Adaptation
Supervised regression using LASSO or LightGBM.
Individual claims
Machine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints

Original source ↗

Results and Discussion; Conclusion; cached text lines 44–46, 61

Version: PMC archival version PMC9178954.1
Retrieved: 2026-09-16T10:44:03.439460+00:00

source checked

automated source review · 2026-09-16

Audit details

Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged.

Field: attributes.profile.facts.10.value

Source artifact SHA-256: 47bd60c6392b801095fdb604de06c0d4bda6f555bae58e9955e491a5abf60576

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Metrics
Pearson correlation and root-mean-square error.
Individual claims
Machine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints

Original source ↗

Results and Discussion; Conclusion; cached text lines 44–46, 61

Version: PMC archival version PMC9178954.1
Retrieved: 2026-09-16T10:44:03.439460+00:00

source checked

automated source review · 2026-09-16

Audit details

Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged.

Field: attributes.profile.facts.2.value

Source artifact SHA-256: 47bd60c6392b801095fdb604de06c0d4bda6f555bae58e9955e491a5abf60576

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Baselines
LASSO and LightGBM with alternative protein/ligand fingerprint combinations.
Individual claims
Machine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints

Original source ↗

Results and Discussion; Conclusion; cached text lines 44–46, 61

Version: PMC archival version PMC9178954.1
Retrieved: 2026-09-16T10:44:03.439460+00:00

source checked

automated source review · 2026-09-16

Audit details

Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged.

Field: attributes.profile.facts.3.value

Source artifact SHA-256: 47bd60c6392b801095fdb604de06c0d4bda6f555bae58e9955e491a5abf60576

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Leakage controls
The checked fingerprint-comparison passages do not define scaffold- or protein-target-disjoint evaluation.
Individual claims
Machine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints

Original source ↗

Results and Discussion; Conclusion; cached text lines 44–46, 61

Version: PMC archival version PMC9178954.1
Retrieved: 2026-09-16T10:44:03.439460+00:00

unreported

automated source review · 2026-09-16

Audit details

Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged.

Field: attributes.profile.facts.4.value

Source artifact SHA-256: 47bd60c6392b801095fdb604de06c0d4bda6f555bae58e9955e491a5abf60576

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Uncertainty
The cited text-accessible evaluation sections give no confidence-interval, resampling or repeat-run error-bar specification. Image-only tables and uninspected supplements are outside this absence claim.
Individual claims
Machine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints

Original source ↗

Results and Discussion; Conclusion; cached text lines 44–46, 61

Version: PMC archival version PMC9178954.1
Retrieved: 2026-09-16T10:44:03.439460+00:00

unreported

automated source review · 2026-09-16

Audit details

Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged.

Field: attributes.profile.facts.5.value

Source artifact SHA-256: 47bd60c6392b801095fdb604de06c0d4bda6f555bae58e9955e491a5abf60576

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

How to read the evidence

Sources and history

Release 2026-11-21-adc15377fab2 · Record review: needs review

2 source records and release historyDownload this release (gzip)
Technical metadata and record identifiers

Technical metadata for this record is tracked under stable ID reported-task-94802534b7026d.

Related records

Suggest a correction