Evaluation

ABFE on the FEP+ benchmark four-target subset

Published comparison transcribed from the pinned source; not reproduced.

Evaluation results

1 evaluation · 10 results. Different protocols are not a single leaderboard.

Protocol: FEP+ benchmark four-target subset, affinity ranking and cost · Dataset: Four-target subset of the public FEP benchmark

Sorted by Accelerator time (per-method cost as printed beside the accuracy columns) (lower is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.

Tested configuration	Accelerator time (per-method cost as printed beside the accuracy columns)	Kendall tau (target average as printed, computed per assay and weighted by compound count)	MAE (centered, computed per assay and averaged across assays weighted by compound count)	MAE (non-centered, computed per assay and averaged across assays weighted by compound count)	MAE (pairwise, target average as printed, computed per assay and weighted by compound count)	Pearson (target average as printed, computed per assay and weighted by compound count)	Proportion (within 1 kcal/mol, centered, computed per assay and averaged across assays weighted by compound count)	Proportion (within 1 kcal/mol, non-centered, computed per assay and averaged across assays weighted by compound count)	Proportion (within 2 kcal/mol, centered, computed per assay and averaged across assays weighted by compound count)	Proportion (within 2 kcal/mol, non-centered, computed per assay and averaged across assays weighted by compound count)
ABFE protocol optimised on the four-target subsetEvaluation	>20 GPU hours	0.54	0.65	2.47	0.95	0.75	0.79	0.11	0.98	0.4

All 10 result rows with coverage, uncertainty and sources

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configuration	Protocol and dataset	Finding	Evidence and details
Configuration: ABFE protocol optimised on the four-target subset	Protocol: FEP+ benchmark four-target subset, affinity ranking and cost Dataset: Four-target subset of the public FEP benchmark	0.54 Kendall tau (target average as printed, computed per assay and weighted by compound count) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source ABFE on the FEP+ benchmark four-target subset uc-leadopt-20261022-protocol-boltz2-fep-4target Aggregation: Not reported Boltz-2: Towards Accurate and Efficient Binding Affinity Prediction, supplementary appendix · Table 12, row "ABFE", column "Kendall tau", sub-column "target avg." (text-layer line 1712)
Configuration: ABFE protocol optimised on the four-target subset	Protocol: FEP+ benchmark four-target subset, affinity ranking and cost Dataset: Four-target subset of the public FEP benchmark	0.65 MAE (centered, computed per assay and averaged across assays weighted by compound count) kilocalorie-per-mole · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source ABFE on the FEP+ benchmark four-target subset uc-leadopt-20261022-protocol-boltz2-fep-4target Aggregation: Not reported Boltz-2: Towards Accurate and Efficient Binding Affinity Prediction, supplementary appendix · Table 12, row "ABFE", column "MAE", sub-column "cent." (text-layer line 1712)
Configuration: ABFE protocol optimised on the four-target subset	Protocol: FEP+ benchmark four-target subset, affinity ranking and cost Dataset: Four-target subset of the public FEP benchmark	2.47 MAE (non-centered, computed per assay and averaged across assays weighted by compound count) kilocalorie-per-mole · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source ABFE on the FEP+ benchmark four-target subset uc-leadopt-20261022-protocol-boltz2-fep-4target Aggregation: Not reported Boltz-2: Towards Accurate and Efficient Binding Affinity Prediction, supplementary appendix · Table 12, row "ABFE", column "MAE", sub-column "non-cent." (text-layer line 1712)
Configuration: ABFE protocol optimised on the four-target subset	Protocol: FEP+ benchmark four-target subset, affinity ranking and cost Dataset: Four-target subset of the public FEP benchmark	0.75 Pearson (target average as printed, computed per assay and weighted by compound count) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source ABFE on the FEP+ benchmark four-target subset uc-leadopt-20261022-protocol-boltz2-fep-4target Aggregation: Not reported Boltz-2: Towards Accurate and Efficient Binding Affinity Prediction, supplementary appendix · Table 12, row "ABFE", column "Pearson R", sub-column "target avg." (text-layer line 1712)
Configuration: ABFE protocol optimised on the four-target subset	Protocol: FEP+ benchmark four-target subset, affinity ranking and cost Dataset: Four-target subset of the public FEP benchmark	0.95 MAE (pairwise, target average as printed, computed per assay and weighted by compound count) kilocalorie-per-mole · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source ABFE on the FEP+ benchmark four-target subset uc-leadopt-20261022-protocol-boltz2-fep-4target Aggregation: Not reported Boltz-2: Towards Accurate and Efficient Binding Affinity Prediction, supplementary appendix · Table 12, row "ABFE", column "PMAE", sub-column "target avg." (text-layer line 1712)
Configuration: ABFE protocol optimised on the four-target subset	Protocol: FEP+ benchmark four-target subset, affinity ranking and cost Dataset: Four-target subset of the public FEP benchmark	>20 GPU hours Accelerator time (per-method cost as printed beside the accuracy columns) hour · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source ABFE on the FEP+ benchmark four-target subset uc-leadopt-20261022-protocol-boltz2-fep-4target Aggregation: Not reported Boltz-2: Towards Accurate and Efficient Binding Affinity Prediction, supplementary appendix · Table 12, row "ABFE", column "time" (text-layer line 1712)
Configuration: ABFE protocol optimised on the four-target subset	Protocol: FEP+ benchmark four-target subset, affinity ranking and cost Dataset: Four-target subset of the public FEP benchmark	0.79 Proportion (within 1 kcal/mol, centered, computed per assay and averaged across assays weighted by compound count) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source ABFE on the FEP+ benchmark four-target subset uc-leadopt-20261022-protocol-boltz2-fep-4target Aggregation: Not reported Boltz-2: Towards Accurate and Efficient Binding Affinity Prediction, supplementary appendix · Table 12, row "ABFE", column "Perc. within 1", sub-column "cent." (text-layer line 1712)
Configuration: ABFE protocol optimised on the four-target subset	Protocol: FEP+ benchmark four-target subset, affinity ranking and cost Dataset: Four-target subset of the public FEP benchmark	0.11 Proportion (within 1 kcal/mol, non-centered, computed per assay and averaged across assays weighted by compound count) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source ABFE on the FEP+ benchmark four-target subset uc-leadopt-20261022-protocol-boltz2-fep-4target Aggregation: Not reported Boltz-2: Towards Accurate and Efficient Binding Affinity Prediction, supplementary appendix · Table 12, row "ABFE", column "Perc. within 1", sub-column "non-cent." (text-layer line 1712)
Configuration: ABFE protocol optimised on the four-target subset	Protocol: FEP+ benchmark four-target subset, affinity ranking and cost Dataset: Four-target subset of the public FEP benchmark	0.98 Proportion (within 2 kcal/mol, centered, computed per assay and averaged across assays weighted by compound count) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source ABFE on the FEP+ benchmark four-target subset uc-leadopt-20261022-protocol-boltz2-fep-4target Aggregation: Not reported Boltz-2: Towards Accurate and Efficient Binding Affinity Prediction, supplementary appendix · Table 12, row "ABFE", column "Perc. within 2", sub-column "cent." (text-layer line 1712)
Configuration: ABFE protocol optimised on the four-target subset	Protocol: FEP+ benchmark four-target subset, affinity ranking and cost Dataset: Four-target subset of the public FEP benchmark	0.4 Proportion (within 2 kcal/mol, non-centered, computed per assay and averaged across assays weighted by compound count) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source ABFE on the FEP+ benchmark four-target subset uc-leadopt-20261022-protocol-boltz2-fep-4target Aggregation: Not reported Boltz-2: Towards Accurate and Efficient Binding Affinity Prediction, supplementary appendix · Table 12, row "ABFE", column "Perc. within 2", sub-column "non-cent." (text-layer line 1712)

Source checking is not independent reproduction. Release 2026-10-22-1b7cf027e4f6.

Research readiness

0 of 4 readiness checks met. These checks assess whether the evidence supports a reproducible investigation; a source-checked score alone does not meet them.

Readiness checks, gaps and artifacts

Release 2026-10-22-1b7cf027e4f6 · Evidence verified: Not verified

Evidence incomplete

Replay metrics

Exact outcomes, predictions, identifiers and evaluator are connected.

Missing or unresolved evidence

No verified artifact manifest is linked to this exact record.
File checksums match the recorded files: not yet verified
Predictions are matched to the right samples: not yet verified
Score meaning and direction are confirmed: not yet verified
Metrics are recomputed from the saved predictions: not yet verified

Verified: Not verified

Evidence incomplete

Investigate discrepancies

Replay evidence includes annotations and an assessment of dependence. Unknown independence permits descriptive analysis only.

Missing or unresolved evidence

No verified artifact manifest is linked to this exact record.
File checksums match the recorded files: not yet verified
Predictions are matched to the right samples: not yet verified
Score meaning and direction are confirmed: not yet verified
Metrics are recomputed from the saved predictions: not yet verified
Sample annotations are recorded: not yet verified
Dependence between samples is assessed: not yet verified

Verified: Not verified

Evidence incomplete

Run locally

A pinned recipe describes the inputs, environment and resource requirements.

Missing or unresolved evidence

No verified artifact manifest is linked to this exact record.
File checksums match the recorded files: not yet verified
Predictions are matched to the right samples: not yet verified
Score meaning and direction are confirmed: not yet verified
A pinned run recipe exists: not yet verified
Compute requirements are estimated: not yet verified

Verified: Not verified

Evidence incomplete

Validate independently

Separate data and exposure records support an independent test.

Missing or unresolved evidence

No verified artifact manifest is linked to this exact record.
File checksums match the recorded files: not yet verified
Predictions are matched to the right samples: not yet verified
Score meaning and direction are confirmed: not yet verified
Independent validation data exist: not yet verified
Overlap with training data is checked: not yet verified

Verified: Not verified

Readiness describes the evidence in this release. Availability on your computer is checked separately when an investigation runs. Existing data exposure can prevent independent validation even when files are available.

Artifacts and reproduction

No verified artifact manifest is connected to this record yet. The gaps above identify what is needed before analysis can begin.

Evaluation procedure

FEP+ benchmark four-target subset, affinity ranking and cost

Configuration: ABFE protocol optimised on the four-target subset
Protocol: FEP+ benchmark four-target subset, affinity ranking and cost
Dataset: Four-target subset of the public FEP benchmark

origin: Evaluation origin not reported
configuration: Primary source as retrieved 2026-10-22
protocol id: uc-leadopt-20261022-protocol-boltz2-fep-4target
dataset version: the FEP+ benchmark four-target subset
split: Held-out affinity test set
population: 87 neutral compounds over 4 targets (CDK2, TYK2, JNK1, P38)
inputs: Not reported
adaptation: Protocol optimised on this same data set
metric implementation: Appendix D.2.2 'Evaluation metrics': Pearson R, Kendall tau, pairwise MAE (PMAE), MAE and the fraction of predictions within 1 and 2 kcal/mol, each computed per assay and averaged across assays weighted by compound count, with predictions converted to kcal/mol first; the centered variants translate each assay's predictions to the ground-truth mean
aggregation: Calculated per assay and averaged across assays with weight proportional to the number of compounds in each assay (appendix D.2.2, 'Evaluation metrics'). The Pearson R, Kendall tau and PMAE columns are printed under the label 'target avg.'; assays and targets are not the same unit, and the source does not reconcile the printed label with the stated computation.
budget: >20 GPU hours

Metadata review: source checked. Unreported conditions prevent automatic comparisons.

Reproduction

Split: Held-out affinity test set
Adaptation: Protocol optimised on this same data set
Scoring implementation: Appendix D.2.2 'Evaluation metrics': Pearson R, Kendall tau, pairwise MAE (PMAE), MAE and the fraction of predictions within 1 and 2 kcal/mol, each computed per assay and averaged across assays weighted by compound count, with predictions converted to kcal/mol first; the centered variants translate each assay's predictions to the ground-truth mean

No execution recipe has been verified for this exact configuration and evaluation. A benchmark's general instructions may use different inputs, splits or model settings.

Reproducing this published result requires matching its model configuration, data, split and scorer. Source checking or a successful smoke test does not establish score reproduction.

Evidence

Source checking verifies the cited claim or transcription. It does not establish 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.

19 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-10-22-1b7cf027e4f6
Property and statement	Original source and location	Review and provenance
Comparison: adaptation Protocol optimised on this same data set Context-only references	Boltz-2: Towards Accurate and Efficient Binding Affinity Prediction, supplementary appendix Original source ↗ Table 12, row 'ABFE' (text-layer line 1712) Version: bioRxiv v1 posted 2025-06-18; supplement PDF as deposited in Europe PMC PMC12262699 (PPR1038344) Retrieved: 2026-10-22T11:52:00Z	not individually reviewed No individual claim review recorded unreported Audit details Field: `attributes.comparison.adaptation` Source artifact SHA-256: `be867a5d92add8b223d47d882a4213ad489741f3e4d5081a0901a54370342569` Hash scope: The recorded hash is of the supplement PDF itself, extracted from the Europe PMC supplementaryFiles ZIP (ZIP SHA-256 25050dabd9c66fdb955704095023037f1bbabc3a93b7b61f00344c75df8bdb70 on 2026-10-22; the ZIP is rebuilt per request and its hash is not stable). Archive member: NIHPP2025.06.14.659707v1-supplement-1.pdf Inspected artifact
Comparison: aggregation Calculated per assay and averaged across assays with weight proportional to the number of compounds in each assay (appendix D.2.2, 'Evaluation metrics'). The Pearson R, Kendall tau and PMAE columns are printed under the label 'target avg.'; assays and targets are not the same unit, and the source does not reconcile the printed label with the stated computation. Context-only references	Boltz-2: Towards Accurate and Efficient Binding Affinity Prediction, supplementary appendix Original source ↗ Table 12, row 'ABFE' (text-layer line 1712) Version: bioRxiv v1 posted 2025-06-18; supplement PDF as deposited in Europe PMC PMC12262699 (PPR1038344) Retrieved: 2026-10-22T11:52:00Z	not individually reviewed No individual claim review recorded unreported Audit details Field: `attributes.comparison.aggregation` Source artifact SHA-256: `be867a5d92add8b223d47d882a4213ad489741f3e4d5081a0901a54370342569` Hash scope: The recorded hash is of the supplement PDF itself, extracted from the Europe PMC supplementaryFiles ZIP (ZIP SHA-256 25050dabd9c66fdb955704095023037f1bbabc3a93b7b61f00344c75df8bdb70 on 2026-10-22; the ZIP is rebuilt per request and its hash is not stable). Archive member: NIHPP2025.06.14.659707v1-supplement-1.pdf Inspected artifact
Comparison: budget >20 GPU hours Context-only references	Boltz-2: Towards Accurate and Efficient Binding Affinity Prediction, supplementary appendix Original source ↗ Table 12, row 'ABFE' (text-layer line 1712) Version: bioRxiv v1 posted 2025-06-18; supplement PDF as deposited in Europe PMC PMC12262699 (PPR1038344) Retrieved: 2026-10-22T11:52:00Z	not individually reviewed No individual claim review recorded unreported Audit details Field: `attributes.comparison.budget` Source artifact SHA-256: `be867a5d92add8b223d47d882a4213ad489741f3e4d5081a0901a54370342569` Hash scope: The recorded hash is of the supplement PDF itself, extracted from the Europe PMC supplementaryFiles ZIP (ZIP SHA-256 25050dabd9c66fdb955704095023037f1bbabc3a93b7b61f00344c75df8bdb70 on 2026-10-22; the ZIP is rebuilt per request and its hash is not stable). Archive member: NIHPP2025.06.14.659707v1-supplement-1.pdf Inspected artifact
Comparison: dataset version the FEP+ benchmark four-target subset Context-only references	Boltz-2: Towards Accurate and Efficient Binding Affinity Prediction, supplementary appendix Original source ↗ Table 12, row 'ABFE' (text-layer line 1712) Version: bioRxiv v1 posted 2025-06-18; supplement PDF as deposited in Europe PMC PMC12262699 (PPR1038344) Retrieved: 2026-10-22T11:52:00Z	not individually reviewed No individual claim review recorded unreported Audit details Field: `attributes.comparison.dataset_version` Source artifact SHA-256: `be867a5d92add8b223d47d882a4213ad489741f3e4d5081a0901a54370342569` Hash scope: The recorded hash is of the supplement PDF itself, extracted from the Europe PMC supplementaryFiles ZIP (ZIP SHA-256 25050dabd9c66fdb955704095023037f1bbabc3a93b7b61f00344c75df8bdb70 on 2026-10-22; the ZIP is rebuilt per request and its hash is not stable). Archive member: NIHPP2025.06.14.659707v1-supplement-1.pdf Inspected artifact
Comparison: inputs Not reported Context-only references	Boltz-2: Towards Accurate and Efficient Binding Affinity Prediction, supplementary appendix Original source ↗ Table 12, row 'ABFE' (text-layer line 1712) Version: bioRxiv v1 posted 2025-06-18; supplement PDF as deposited in Europe PMC PMC12262699 (PPR1038344) Retrieved: 2026-10-22T11:52:00Z	missing or unspecified No individual claim review recorded unreported Audit details Field: `attributes.comparison.inputs` Source artifact SHA-256: `be867a5d92add8b223d47d882a4213ad489741f3e4d5081a0901a54370342569` Hash scope: The recorded hash is of the supplement PDF itself, extracted from the Europe PMC supplementaryFiles ZIP (ZIP SHA-256 25050dabd9c66fdb955704095023037f1bbabc3a93b7b61f00344c75df8bdb70 on 2026-10-22; the ZIP is rebuilt per request and its hash is not stable). Archive member: NIHPP2025.06.14.659707v1-supplement-1.pdf Inspected artifact
Comparison: metric implementation Appendix D.2.2 'Evaluation metrics': Pearson R, Kendall tau, pairwise MAE (PMAE), MAE and the fraction of predictions within 1 and 2 kcal/mol, each computed per assay and averaged across assays weighted by compound count, with predictions converted to kcal/mol first; the centered variants translate each assay's predictions to the ground-truth mean Context-only references	Boltz-2: Towards Accurate and Efficient Binding Affinity Prediction, supplementary appendix Original source ↗ Table 12, row 'ABFE' (text-layer line 1712) Version: bioRxiv v1 posted 2025-06-18; supplement PDF as deposited in Europe PMC PMC12262699 (PPR1038344) Retrieved: 2026-10-22T11:52:00Z	not individually reviewed No individual claim review recorded unreported Audit details Field: `attributes.comparison.metric_implementation` Source artifact SHA-256: `be867a5d92add8b223d47d882a4213ad489741f3e4d5081a0901a54370342569` Hash scope: The recorded hash is of the supplement PDF itself, extracted from the Europe PMC supplementaryFiles ZIP (ZIP SHA-256 25050dabd9c66fdb955704095023037f1bbabc3a93b7b61f00344c75df8bdb70 on 2026-10-22; the ZIP is rebuilt per request and its hash is not stable). Archive member: NIHPP2025.06.14.659707v1-supplement-1.pdf Inspected artifact
Comparison: population 87 neutral compounds over 4 targets (CDK2, TYK2, JNK1, P38) Context-only references	Boltz-2: Towards Accurate and Efficient Binding Affinity Prediction, supplementary appendix Original source ↗ Table 12, row 'ABFE' (text-layer line 1712) Version: bioRxiv v1 posted 2025-06-18; supplement PDF as deposited in Europe PMC PMC12262699 (PPR1038344) Retrieved: 2026-10-22T11:52:00Z	not individually reviewed No individual claim review recorded unreported Audit details Field: `attributes.comparison.population` Source artifact SHA-256: `be867a5d92add8b223d47d882a4213ad489741f3e4d5081a0901a54370342569` Hash scope: The recorded hash is of the supplement PDF itself, extracted from the Europe PMC supplementaryFiles ZIP (ZIP SHA-256 25050dabd9c66fdb955704095023037f1bbabc3a93b7b61f00344c75df8bdb70 on 2026-10-22; the ZIP is rebuilt per request and its hash is not stable). Archive member: NIHPP2025.06.14.659707v1-supplement-1.pdf Inspected artifact
Comparison: protocol id uc-leadopt-20261022-protocol-boltz2-fep-4target Context-only references	Boltz-2: Towards Accurate and Efficient Binding Affinity Prediction, supplementary appendix Original source ↗ Table 12, row 'ABFE' (text-layer line 1712) Version: bioRxiv v1 posted 2025-06-18; supplement PDF as deposited in Europe PMC PMC12262699 (PPR1038344) Retrieved: 2026-10-22T11:52:00Z	not individually reviewed No individual claim review recorded unreported Audit details Field: `attributes.comparison.protocol_id` Source artifact SHA-256: `be867a5d92add8b223d47d882a4213ad489741f3e4d5081a0901a54370342569` Hash scope: The recorded hash is of the supplement PDF itself, extracted from the Europe PMC supplementaryFiles ZIP (ZIP SHA-256 25050dabd9c66fdb955704095023037f1bbabc3a93b7b61f00344c75df8bdb70 on 2026-10-22; the ZIP is rebuilt per request and its hash is not stable). Archive member: NIHPP2025.06.14.659707v1-supplement-1.pdf Inspected artifact
Comparison: split Held-out affinity test set Context-only references	Boltz-2: Towards Accurate and Efficient Binding Affinity Prediction, supplementary appendix Original source ↗ Table 12, row 'ABFE' (text-layer line 1712) Version: bioRxiv v1 posted 2025-06-18; supplement PDF as deposited in Europe PMC PMC12262699 (PPR1038344) Retrieved: 2026-10-22T11:52:00Z	not individually reviewed No individual claim review recorded unreported Audit details Field: `attributes.comparison.split` Source artifact SHA-256: `be867a5d92add8b223d47d882a4213ad489741f3e4d5081a0901a54370342569` Hash scope: The recorded hash is of the supplement PDF itself, extracted from the Europe PMC supplementaryFiles ZIP (ZIP SHA-256 25050dabd9c66fdb955704095023037f1bbabc3a93b7b61f00344c75df8bdb70 on 2026-10-22; the ZIP is rebuilt per request and its hash is not stable). Archive member: NIHPP2025.06.14.659707v1-supplement-1.pdf Inspected artifact
Limitations 1 values The supplement cites prior work for this arm and does not say whether the values were re-run here or taken from that work Context-only references	Boltz-2: Towards Accurate and Efficient Binding Affinity Prediction, supplementary appendix Original source ↗ Table 12, row 'ABFE' (text-layer line 1712) Version: bioRxiv v1 posted 2025-06-18; supplement PDF as deposited in Europe PMC PMC12262699 (PPR1038344) Retrieved: 2026-10-22T11:52:00Z	not individually reviewed No individual claim review recorded unreported Audit details Field: `attributes.limitations` Source artifact SHA-256: `be867a5d92add8b223d47d882a4213ad489741f3e4d5081a0901a54370342569` Hash scope: The recorded hash is of the supplement PDF itself, extracted from the Europe PMC supplementaryFiles ZIP (ZIP SHA-256 25050dabd9c66fdb955704095023037f1bbabc3a93b7b61f00344c75df8bdb70 on 2026-10-22; the ZIP is rebuilt per request and its hash is not stable). Archive member: NIHPP2025.06.14.659707v1-supplement-1.pdf Inspected artifact

How to read the evidence

Sources and history

Release 2026-10-22-1b7cf027e4f6 · Record review: source checked

1 source record and release history

Boltz-2: Towards Accurate and Efficient Binding Affinity Prediction, supplementary appendix · Original source · bioRxiv v1 posted 2025-06-18; supplement PDF as deposited in Europe PMC PMC12262699 (PPR1038344)

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: uc-leadopt-20261022-eval-t12-abfe

areas: molecular-interactions
contexts: research
origin: unreported
protocol: uc-leadopt-20261022-protocol-boltz2-fep-4target
version: Primary source as retrieved 2026-10-22
comparison: protocol id: uc-leadopt-20261022-protocol-boltz2-fep-4target; dataset version: the FEP+ benchmark four-target subset; split: Held-out affinity test set; population: 87 neutral compounds over 4 targets (CDK2, TYK2, JNK1, P38); inputs: Not reported; adaptation: Protocol optimised on this same data set; metric implementation: Appendix D.2.2 'Evaluation metrics': Pearson R, Kendall tau, pairwise MAE (PMAE), MAE and the fraction of predictions within 1 and 2 kcal/mol, each computed per assay and averaged across assays weighted by compound count, with predictions converted to kcal/mol first; the centered variants translate each assay's predictions to the ground-truth mean; aggregation: Calculated per assay and averaged across assays with weight proportional to the number of compounds in each assay (appendix D.2.2, 'Evaluation metrics'). The Pearson R, Kendall tau and PMAE columns are printed under the label 'target avg.'; assays and targets are not the same unit, and the source does not reconcile the printed label with the stated computation.; budget: >20 GPU hours
source locator: Table 12, row 'ABFE' (text-layer line 1712)
missing metadata: comparison.inputs: reason: unreported
limitations: The supplement cites prior work for this arm and does not say whether the values were re-run here or taken from that work
review: method: source-hash-verification; pdf-text-parse; independent-cell-check; rendered-source-visual-check; ai-assisted-source-review; method note: Re-retrieved all three sources and matched each pinned SHA-256. Re-rendered the Boltz-2 supplement with pdftotext -layout (poppler 26.08.0) and matched the text layer's recorded SHA-256. Re-read all 256 cells with a parser written for this review that does not import the extraction script, matching each result to its cell through its own source_locator, and separately read appendix tables 11, 12 and 14 from PNG renderings of PDF pages 29 and 30 at 160 dpi, and Ross Table 3 from the pinned XML markup. Checked printed value, numeric value, locator, metric concept, qualifier, direction, unit, uncertainty and the linked configuration, protocol and dataset, and that every N/A or '-' cell is recorded as missing with a reason.; reviewer: claude; reviewer note: Claude review agent, independent of the extraction agent; no human review claimed; reviewed at: 2026-10-22T13:40:00Z; artifact sha256: be867a5d92add8b223d47d882a4213ad489741f3e4d5081a0901a54370342569; retrieval url: https://www.ebi.ac.uk/europepmc/webservices/rest/PMC12262699/supplementaryFiles

Related records

system: ABFE protocol optimised on the four-target subset
assessment: FEP+ benchmark four-target subset, affinity ranking and cost
data: Four-target subset of the public FEP benchmark
evaluation: ABFE kendall tau on the FEP+ benchmark four-target subset
evaluation: ABFE mae centered on the FEP+ benchmark four-target subset
evaluation: ABFE mae non centered on the FEP+ benchmark four-target subset
evaluation: ABFE pearson on the FEP+ benchmark four-target subset
evaluation: ABFE pmae on the FEP+ benchmark four-target subset
evaluation: ABFE compute cost on the FEP+ benchmark four-target subset
evaluation: ABFE within 1 centered on the FEP+ benchmark four-target subset
evaluation: ABFE within 1 non centered on the FEP+ benchmark four-target subset
evaluation: ABFE within 2 centered on the FEP+ benchmark four-target subset
evaluation: ABFE within 2 non centered on the FEP+ benchmark four-target subset

Suggest a correction