Hidden bias in DUD-E misleads deep-learning virtual screening
Reported finding of DUD-E (Directory of Useful Decoys, Enhanced)
Chen et al. 2019 report that convolutional neural network models trained on 3D structural images of protein-ligand complexes from DUD-E are subject to a hidden bias in that dataset, so their apparent ability to distinguish binding from non-binding ligands in structure-based virtual screening is misleading rather than a measure of molecular recognition.
The finding that convolutional neural network performance on DUD-E reflects decoy construction rather than binding.
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.
6 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Claimed field reported_finding Context-only references | Chen et al. 2019, PLoS ONE 14:e0220113 (hidden bias in DUD-E, Europe PMC full text) Title; Abstract Version: PMC6701836 (PLoS ONE 2019) | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Source location Title; Abstract Context-only references | Chen et al. 2019, PLoS ONE 14:e0220113 (hidden bias in DUD-E, Europe PMC full text) Title; Abstract Version: PMC6701836 (PLoS ONE 2019) | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Claimed value Chen et al. 2019 report that convolutional neural network models trained on 3D structural images of protein-ligand complexes from DUD-E are subject to a hidden bias in that dataset, so their apparent ability to distinguish binding from non-binding ligands in structure-based virtual screening is misleading rather than a measure of molecular recognition. Context-only references | Chen et al. 2019, PLoS ONE 14:e0220113 (hidden bias in DUD-E, Europe PMC full text) Title; Abstract Version: PMC6701836 (PLoS ONE 2019) | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Description The finding that convolutional neural network performance on DUD-E reflects decoy construction rather than binding. Context-only references | Chen et al. 2019, PLoS ONE 14:e0220113 (hidden bias in DUD-E, Europe PMC full text) Title; Abstract Version: PMC6701836 (PLoS ONE 2019) | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Relationship: subject hitdisc-20261022-benchmark-dude Context-only references | Chen et al. 2019, PLoS ONE 14:e0220113 (hidden bias in DUD-E, Europe PMC full text) Title; Abstract Version: PMC6701836 (PLoS ONE 2019) | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Name Hidden bias in DUD-E misleads deep-learning virtual screening Context-only references | Chen et al. 2019, PLoS ONE 14:e0220113 (hidden bias in DUD-E, Europe PMC full text) Title; Abstract Version: PMC6701836 (PLoS ONE 2019) | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Sources and history
Release 2026-11-02-a7f03c9e55a5 · Record review: source checked
1 source record and release history
- Chen et al. 2019, PLoS ONE 14:e0220113 (hidden bias in DUD-E, Europe PMC full text) · Original source · PMC6701836 (PLoS ONE 2019)
Technical metadata and extraction receipts
Stable ID: hitdisc-20261022-claim-dude-hidden-bias
- areas
- molecular-interactions
- contexts
- research
- field
- reported_finding
- value
- Chen et al. 2019 report that convolutional neural network models trained on 3D structural images of protein-ligand complexes from DUD-E are subject to a hidden bias in that dataset, so their apparent ability to distinguish binding from non-binding ligands in structure-based virtual screening is misleading rather than a measure of molecular recognition.
- source locator
- Title; Abstract
- review
- method: scope-review; automated-source-review; reviewer: claude; reviewer note: Claude review agent, independent of the extraction agent; no human review claimed; date: 2026-10-22; method note: Read the record against the pinned sources and against docs/use-cases.md and docs/record-contract.md.; note: Claim checked against the pinned source. Every figure it states was matched to a result record in this batch.; artifact sha256: b845c78815bb0c4eabb3e05e65212b343269c91292fedf00fae9ac00c7840f09; retrieval url: https://www.ebi.ac.uk/europepmc/webservices/rest/PMC6701836/fullTextXML; receipt: data/omics/use-case-coverage-hitdisc-20261022/review.json