rewirebio.iobenchmarks
Task

RNA-small-molecule binding-site prediction

RNA small-molecule binding-site prediction uses independent RNA–ligand test collections with explicit redundancy filtering.

SourcesRNA language model and graph attention network for RNA and small molecule binding sites prediction · Methods §§2.1, 2.7; cached text lines 13–15, 57–58

1 evaluation · 1 result

Overview

Datasets

Combined RNAglib/RNAsite training data; T18, T3 and newly curated T10 tests.

Metrics

Precision, recall, MCC and ROC-AUC.

Allowed inputs

RNA representations for site prediction.

SourcesRNA language model and graph attention network for RNA and small molecule binding sites prediction · Methods §§2.1, 2.7; cached text lines 13–15, 57–58
Evaluation procedure diagram
How it worksComputational evaluation flow
Computational evaluation flow1. Input: RNA representations for site prediction.. Then: 2. Evaluation: Supervised fitting on the combined training data; later PDB entries supply one held-out test.. Then: 3. Readout: Precision, recall, MCC and ROC-AUC.Computational evaluation flow1. Input: RNA representations for site prediction.. Then: 2. Evaluation: Supervised fitting on the combined training data; later PDB entries supply one held-out test.. Then: 3. Readout: Precision, recall, MCC and ROC-AUC.Computational evaluation flow1. Input: RNA representations for site prediction.. Then: 2. Evaluation: Supervised fitting on the combined training data; later PDB entries supply one held-out test.. Then: 3. Readout: Precision, recall, MCC and ROC-AUC.

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

SourcesRNA language model and graph attention network for RNA and small molecule binding sites prediction · Methods §§2.1, 2.7; cached text lines 13–15, 57–58

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

1 recorded evaluation, 1 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

1 evaluation · 1 result. 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: RLsiteTask: RNA-small-molecule binding-site prediction
Dataset: T18
0.828 AUROC
unitless · unknown

Uncertainty: Not yet extracted

Coverage: Not reported scored / Not reported eligible

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

RLsite: RNA-small-molecule binding-site prediction

RNA language-model plus graph-attention classifier

Aggregation: Not reported

RNA language model and graph attention network for RNA and small molecule binding sites prediction · Table 1, RLsite row, T18 AUC 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

Combined RNAglib/RNAsite training data; T18, T3 and newly curated T10 tests. The named test collections are held separate; T10 uses later PDB entries. Precision, recall, MCC and ROC-AUC. Training data align with MultiModRLBP for comparison. T3 removes high-similarity RNAs relative to training; T10 is clustered and filtered against training RNA. The paper reports t-tests comparing metrics; the exact replication unit should be confirmed before interpreting them as independent-sample uncertainty.

SourcesRNA language model and graph attention network for RNA and small molecule binding sites prediction · Methods §§2.1, 2.7; cached text lines 13–15, 57–58

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-b00a636d1ed8d9

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
DatasetsCombined RNAglib/RNAsite training data; T18, T3 and newly curated T10 tests.
SourcesRNA language model and graph attention network for RNA and small molecule binding sites prediction · Methods §§2.1, 2.7; cached text lines 13–15, 57–58
SplitsThe named test collections are held separate; T10 uses later PDB entries.
SourcesRNA language model and graph attention network for RNA and small molecule binding sites prediction · Methods §§2.1, 2.7; cached text lines 13–15, 57–58
MetricsPrecision, recall, MCC and ROC-AUC.
SourcesRNA language model and graph attention network for RNA and small molecule binding sites prediction · Methods §§2.1, 2.7; cached text lines 13–15, 57–58
BaselinesTraining data align with MultiModRLBP for comparison.
SourcesRNA language model and graph attention network for RNA and small molecule binding sites prediction · Methods §§2.1, 2.7; cached text lines 13–15, 57–58
Leakage controlsT3 removes high-similarity RNAs relative to training; T10 is clustered and filtered against training RNA.
SourcesRNA language model and graph attention network for RNA and small molecule binding sites prediction · Methods §§2.1, 2.7; cached text lines 13–15, 57–58
UncertaintyThe paper reports t-tests comparing metrics; the exact replication unit should be confirmed before interpreting them as independent-sample uncertainty.
SourcesRNA language model and graph attention network for RNA and small molecule binding sites prediction · Methods §§2.1, 2.7; cached text lines 13–15, 57–58
Entity typePaper-specific computational evaluation protocol.
SourcesRNA language model and graph attention network for RNA and small molecule binding sites prediction · Methods §§2.1, 2.7; cached text lines 13–15, 57–58
OrganismsRNAglib/RNAsite-derived RNA chains and PDB-derived test sets define this benchmark. Section 2.1 reports chain and ligand membership criteria but not a taxonomic inventory; synthetic aptamer examples cannot be assigned an organism from the surrounding disease discussion. · Not reported in inspected sources
SourcesRNA language model and graph attention network for RNA and small molecule binding sites prediction · §2.1 Benchmark datasets; RNA–ligand test examples
AssaysRNA–small-molecule binding-site annotations.
SourcesRNA language model and graph attention network for RNA and small molecule binding sites prediction · Methods §§2.1, 2.7; cached text lines 13–15, 57–58
Allowed inputsRNA representations for site prediction.
SourcesRNA language model and graph attention network for RNA and small molecule binding sites prediction · Methods §§2.1, 2.7; cached text lines 13–15, 57–58
AdaptationSupervised fitting on the combined training data; later PDB entries supply one held-out test.
SourcesRNA language model and graph attention network for RNA and small molecule binding sites prediction · Methods §§2.1, 2.7; cached text lines 13–15, 57–58

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
RNA language model and graph attention network for RNA and small molecule binding sites predictionjournal full text in PMCRead source
DOI: 10.1093/bioinformatics/btaf447
Historical gaps recorded on 2026-09-17

The catalogue now holds 1 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.

  • Most baseline values are copied from original publications; RNABind is a web-server run.
  • T18/T3/T10 are separate protocols and cannot be pooled as one model score.
  • Unavailable RNet AUC is a dash, not zero.
Search and extraction details

primary comparison table screened

Searches

  • "PMC12417085"

Evidence locations

  • Tables 1–3 footnotes
  • Section 2.1 Benchmark datasets

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
RNA language model and graph attention network for RNA and small molecule binding sites prediction

Original source ↗

Methods §§2.1, 2.7; cached text lines 13–15, 57–58

Version: journal full text in PMC
Retrieved: 2026-09-16T10:38:57.558222+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: a50f344e253162ae43f51d7120cfb35a1d0f6114fd8176d760aceb6d05fd95bd

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

Inspected artifact

Diagram steps
  • Input: RNA representations for site prediction.
  • Evaluation: Supervised fitting on the combined training data; later PDB entries supply one held-out test.
  • Readout: Precision, recall, MCC and ROC-AUC.
Individual claims
RNA language model and graph attention network for RNA and small molecule binding sites prediction

Original source ↗

Methods §§2.1, 2.7; cached text lines 13–15, 57–58

Version: journal full text in PMC
Retrieved: 2026-09-16T10:38:57.558222+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: a50f344e253162ae43f51d7120cfb35a1d0f6114fd8176d760aceb6d05fd95bd

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

Inspected artifact

Diagram title
Computational evaluation flow
Individual claims
RNA language model and graph attention network for RNA and small molecule binding sites prediction

Original source ↗

Methods §§2.1, 2.7; cached text lines 13–15, 57–58

Version: journal full text in PMC
Retrieved: 2026-09-16T10:38:57.558222+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: a50f344e253162ae43f51d7120cfb35a1d0f6114fd8176d760aceb6d05fd95bd

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

Inspected artifact

Datasets
Combined RNAglib/RNAsite training data; T18, T3 and newly curated T10 tests.
Individual claims
RNA language model and graph attention network for RNA and small molecule binding sites prediction

Original source ↗

Methods §§2.1, 2.7; cached text lines 13–15, 57–58

Version: journal full text in PMC
Retrieved: 2026-09-16T10:38:57.558222+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: a50f344e253162ae43f51d7120cfb35a1d0f6114fd8176d760aceb6d05fd95bd

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

Inspected artifact

Splits
The named test collections are held separate; T10 uses later PDB entries.
Individual claims
RNA language model and graph attention network for RNA and small molecule binding sites prediction

Original source ↗

Methods §§2.1, 2.7; cached text lines 13–15, 57–58

Version: journal full text in PMC
Retrieved: 2026-09-16T10:38:57.558222+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: a50f344e253162ae43f51d7120cfb35a1d0f6114fd8176d760aceb6d05fd95bd

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

Inspected artifact

Adaptation
Supervised fitting on the combined training data; later PDB entries supply one held-out test.
Individual claims
RNA language model and graph attention network for RNA and small molecule binding sites prediction

Original source ↗

Methods §§2.1, 2.7; cached text lines 13–15, 57–58

Version: journal full text in PMC
Retrieved: 2026-09-16T10:38:57.558222+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: a50f344e253162ae43f51d7120cfb35a1d0f6114fd8176d760aceb6d05fd95bd

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

Inspected artifact

Metrics
Precision, recall, MCC and ROC-AUC.
Individual claims
RNA language model and graph attention network for RNA and small molecule binding sites prediction

Original source ↗

Methods §§2.1, 2.7; cached text lines 13–15, 57–58

Version: journal full text in PMC
Retrieved: 2026-09-16T10:38:57.558222+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: a50f344e253162ae43f51d7120cfb35a1d0f6114fd8176d760aceb6d05fd95bd

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

Inspected artifact

Baselines
Training data align with MultiModRLBP for comparison.
Individual claims
RNA language model and graph attention network for RNA and small molecule binding sites prediction

Original source ↗

Methods §§2.1, 2.7; cached text lines 13–15, 57–58

Version: journal full text in PMC
Retrieved: 2026-09-16T10:38:57.558222+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: a50f344e253162ae43f51d7120cfb35a1d0f6114fd8176d760aceb6d05fd95bd

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

Inspected artifact

Leakage controls
T3 removes high-similarity RNAs relative to training; T10 is clustered and filtered against training RNA.
Individual claims
RNA language model and graph attention network for RNA and small molecule binding sites prediction

Original source ↗

Methods §§2.1, 2.7; cached text lines 13–15, 57–58

Version: journal full text in PMC
Retrieved: 2026-09-16T10:38:57.558222+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.4.value

Source artifact SHA-256: a50f344e253162ae43f51d7120cfb35a1d0f6114fd8176d760aceb6d05fd95bd

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

Inspected artifact

Uncertainty
The paper reports t-tests comparing metrics; the exact replication unit should be confirmed before interpreting them as independent-sample uncertainty.
Individual claims
RNA language model and graph attention network for RNA and small molecule binding sites prediction

Original source ↗

Methods §§2.1, 2.7; cached text lines 13–15, 57–58

Version: journal full text in PMC
Retrieved: 2026-09-16T10:38:57.558222+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.5.value

Source artifact SHA-256: a50f344e253162ae43f51d7120cfb35a1d0f6114fd8176d760aceb6d05fd95bd

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-b00a636d1ed8d9.

Related records

Suggest a correction