rewirebio.iobenchmarks
Task

human RNA 2-prime-O-methylation site prediction

Human RNA methylation-site classification is evaluated on a curated, balanced dataset and an independent test partition.

Sources2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Methods §§2.1, 2.4; Results §§3.1–3.2; cached text lines 11–14, 35–36, 43–48

12 evaluations · 84 results

Overview

Datasets

RMBase v3.0 and multiple experimentally annotated RNA modification datasets supply positive and negative examples.

Metrics

Accuracy, F1, precision, recall, AUROC, AUPR and MCC; cross-validation results are averaged across folds.

Allowed inputs

RNA sequence windows around candidate modification sites.

Sources2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Methods §§2.1, 2.4; Results §§3.1–3.2; cached text lines 11–14, 35–36, 43–48
Evaluation procedure diagram
How it worksComputational evaluation flow
Computational evaluation flow1. Input: RNA sequence windows around candidate modification sites.. Then: 2. Evaluation: Supervised site classifier; comparator servers and retrained models have distinct training provenance.. Then: 3. Readout: Accuracy, F1, precision, recall, AUROC, AUPR and MCC; cross-validation results are averaged across folds.Computational evaluation flow1. Input: RNA sequence windows around candidate modification sites.. Then: 2. Evaluation: Supervised site classifier; comparator servers and retrained models have distinct training provenance.. Then: 3. Readout: Accuracy, F1, precision, recall, AUROC, AUPR and MCC; cross-validation results are averaged across folds.Computational evaluation flow1. Input: RNA sequence windows around candidate modification sites.. Then: 2. Evaluation: Supervised site classifier; comparator servers and retrained models have distinct training provenance.. Then: 3. Readout: Accuracy, F1, precision, recall, AUROC, AUPR and MCC; cross-validation results are averaged across folds.

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

Sources2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Methods §§2.1, 2.4; Results §§3.1–3.2; cached text lines 11–14, 35–36, 43–48

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

12 recorded evaluations, 84 metric rows. Explore 14 source-scoped charts.

View coverage and remaining gaps across all benchmarks

Results

Each comparison retains its reviewed evaluation scope, dataset and metric. Results are shown without a pooled ranking.

Human RNA 2OMe sites, five-fold cross-validation · ACC

accuracy (fraction) · Higher values are better.

Human RNA 2OMe sites, five-fold cross-validation (human RNA 2-prime-O-methylation site prediction) · human RNA 2OMe sites

Evidence origin: Author-reported evaluation.

2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Performance comparison of 2OMe-LM and deep learning baseline models using 5-fold CV. a; Table 1. (btaf417-T1), row 2 GloVe + MLP, column 2: Human RNA 2OMe sites, five-fold cross-validation ACC; Table 1. (btaf417-T1), row 3 GloVe + TextCNN + MLP, column 2: Human RNA 2OMe sites, five-fold cross-validation ACC; Table 1. (btaf417-T1), row 4 GloVe + Transformer + MLP, column 2: Human RNA 2OMe sites, five-fold cross-validation ACC; Table 1. (btaf417-T1), row 5 Word2vec + MLP, column 2: Human RNA 2OMe sites, five-fold cross-validation ACC; Table 1. (btaf417-T1), row 6 Word2vec + TextCNN + MLP, column 2: Human RNA 2OMe sites, five-fold cross-validation ACC; Table 1. (btaf417-T1), row 7 Word2Vec + Transformer + MLP, column 2: Human RNA 2OMe sites, five-fold cross-validation ACC; Table 1. (btaf417-T1), row 8 2OMe-LM, column 2: Human RNA 2OMe sites, five-fold cross-validation ACC
  • Do not pool cross-validation and independent-test scores. The 8:2 ratio is not converted into an exact test count. Training-data overlap for pre-existing predictors is not established by this table. Origins are labelled per method; appearance in one table does not constitute independent replication of every model.
Comparison details and limitations

41-nt centred RNA windows; balanced 8,037 positive and 8,037 negative samples after 80% identity filtering, then 8:2 train/test division. Average of five validation folds of the training set.

Automated source review: 2026-09-17. Numerical source review does not establish independent reproduction.

Dots show point estimates. Whiskers show only explicitly defined uncertainty (standard deviation, standard error or a labelled interval); their definitions remain in Table. Unresolved uncertainty is not plotted. Differences do not establish statistical significance.

Showing 7 of 7 matching rows.

Methods and evaluation design

Procedure, tasks and evaluated configurations

How it works

Evaluation methodology

RMBase v3.0 and multiple experimentally annotated RNA modification datasets supply positive and negative examples. An 80:20 training/test partition is followed by five-fold cross-validation within training data. Accuracy, F1, precision, recall, AUROC, AUPR and MCC; cross-validation results are averaged across folds. GloVe/word2vec neural baselines; NmRF, H2Opred and Meta-2OM web servers; BERT2OME retrained on the benchmark. The checked dataset/split passages specify sample partitioning but do not specify a gene-, donor- or overlapping-window exclusion rule. 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.

Sources2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Methods §§2.1, 2.4; Results §§3.1–3.2; cached text lines 11–14, 35–36, 43–48

Evaluation 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.

Run this benchmark

Choose a concrete protocol before running an evaluation. Its inputs, split and scoring rules determine which results can be compared.

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

Task-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced.

Stable record: reported-task-82fc7843f07324

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
DatasetsRMBase v3.0 and multiple experimentally annotated RNA modification datasets supply positive and negative examples.
Sources2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Methods §§2.1, 2.4; Results §§3.1–3.2; cached text lines 11–14, 35–36, 43–48
SplitsAn 80:20 training/test partition is followed by five-fold cross-validation within training data.
Sources2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Methods §§2.1, 2.4; Results §§3.1–3.2; cached text lines 11–14, 35–36, 43–48
MetricsAccuracy, F1, precision, recall, AUROC, AUPR and MCC; cross-validation results are averaged across folds.
Sources2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Methods §§2.1, 2.4; Results §§3.1–3.2; cached text lines 11–14, 35–36, 43–48
BaselinesGloVe/word2vec neural baselines; NmRF, H2Opred and Meta-2OM web servers; BERT2OME retrained on the benchmark.
Sources2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Methods §§2.1, 2.4; Results §§3.1–3.2; cached text lines 11–14, 35–36, 43–48
Leakage controlsThe checked dataset/split passages specify sample partitioning but do not specify a gene-, donor- or overlapping-window exclusion rule. · Not reported in inspected sources
Sources2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Methods §§2.1, 2.4; Results §§3.1–3.2; cached text lines 11–14, 35–36, 43–48
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
Sources2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Methods §§2.1, 2.4; Results §§3.1–3.2; cached text lines 11–14, 35–36, 43–48
Entity typePaper-specific computational evaluation protocol.
Sources2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Methods §§2.1, 2.4; Results §§3.1–3.2; cached text lines 11–14, 35–36, 43–48
OrganismsHuman.
Sources2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Methods §§2.1, 2.4; Results §§3.1–3.2; cached text lines 11–14, 35–36, 43–48
AssaysRNA modification-site annotations from RMBase and experimental datasets.
Sources2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Methods §§2.1, 2.4; Results §§3.1–3.2; cached text lines 11–14, 35–36, 43–48
Allowed inputsRNA sequence windows around candidate modification sites.
Sources2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Methods §§2.1, 2.4; Results §§3.1–3.2; cached text lines 11–14, 35–36, 43–48
AdaptationSupervised site classifier; comparator servers and retrained models have distinct training provenance.
Sources2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Methods §§2.1, 2.4; Results §§3.1–3.2; cached text lines 11–14, 35–36, 43–48

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. 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.

Historical gaps recorded on 2026-09-17

The catalogue now holds 84 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.

  • 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

  • 2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model 10.1093/bioinformatics/btaf417

Evidence locations

  • Table 1.; XML table btaf417-T1
  • Table 2.; XML table btaf417-T2

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
2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model

Original source ↗

Methods §§2.1, 2.4; Results §§3.1–3.2; cached text lines 11–14, 35–36, 43–48

Version: journal full text in PMC
Retrieved: 2026-09-16T10:33:38.332Z

source checked

automated source review · 2026-09-16

Audit details

Task-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced.

Field: attributes.profile.diagram.caption

Source artifact SHA-256: 54fe4db6f35c03d0d4f3ef4da720eb26a832199372c56d0956609ff07af750ee

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

Inspected artifact

Diagram steps
  • Input: RNA sequence windows around candidate modification sites.
  • Evaluation: Supervised site classifier; comparator servers and retrained models have distinct training provenance.
  • Readout: Accuracy, F1, precision, recall, AUROC, AUPR and MCC; cross-validation results are averaged across folds.
Individual claims
2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model

Original source ↗

Methods §§2.1, 2.4; Results §§3.1–3.2; cached text lines 11–14, 35–36, 43–48

Version: journal full text in PMC
Retrieved: 2026-09-16T10:33:38.332Z

source checked

automated source review · 2026-09-16

Audit details

Task-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced.

Field: attributes.profile.diagram.steps

Source artifact SHA-256: 54fe4db6f35c03d0d4f3ef4da720eb26a832199372c56d0956609ff07af750ee

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

Inspected artifact

Diagram title
Computational evaluation flow
Individual claims
2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model

Original source ↗

Methods §§2.1, 2.4; Results §§3.1–3.2; cached text lines 11–14, 35–36, 43–48

Version: journal full text in PMC
Retrieved: 2026-09-16T10:33:38.332Z

source checked

automated source review · 2026-09-16

Audit details

Task-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced.

Field: attributes.profile.diagram.title

Source artifact SHA-256: 54fe4db6f35c03d0d4f3ef4da720eb26a832199372c56d0956609ff07af750ee

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

Inspected artifact

Datasets
RMBase v3.0 and multiple experimentally annotated RNA modification datasets supply positive and negative examples.
Individual claims
2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model

Original source ↗

Methods §§2.1, 2.4; Results §§3.1–3.2; cached text lines 11–14, 35–36, 43–48

Version: journal full text in PMC
Retrieved: 2026-09-16T10:33:38.332Z

source checked

automated source review · 2026-09-16

Audit details

Task-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced.

Field: attributes.profile.facts.0.value

Source artifact SHA-256: 54fe4db6f35c03d0d4f3ef4da720eb26a832199372c56d0956609ff07af750ee

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

Inspected artifact

Splits
An 80:20 training/test partition is followed by five-fold cross-validation within training data.
Individual claims
2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model

Original source ↗

Methods §§2.1, 2.4; Results §§3.1–3.2; cached text lines 11–14, 35–36, 43–48

Version: journal full text in PMC
Retrieved: 2026-09-16T10:33:38.332Z

source checked

automated source review · 2026-09-16

Audit details

Task-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced.

Field: attributes.profile.facts.1.value

Source artifact SHA-256: 54fe4db6f35c03d0d4f3ef4da720eb26a832199372c56d0956609ff07af750ee

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

Inspected artifact

Adaptation
Supervised site classifier; comparator servers and retrained models have distinct training provenance.
Individual claims
2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model

Original source ↗

Methods §§2.1, 2.4; Results §§3.1–3.2; cached text lines 11–14, 35–36, 43–48

Version: journal full text in PMC
Retrieved: 2026-09-16T10:33:38.332Z

source checked

automated source review · 2026-09-16

Audit details

Task-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced.

Field: attributes.profile.facts.10.value

Source artifact SHA-256: 54fe4db6f35c03d0d4f3ef4da720eb26a832199372c56d0956609ff07af750ee

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

Inspected artifact

Metrics
Accuracy, F1, precision, recall, AUROC, AUPR and MCC; cross-validation results are averaged across folds.
Individual claims
2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model

Original source ↗

Methods §§2.1, 2.4; Results §§3.1–3.2; cached text lines 11–14, 35–36, 43–48

Version: journal full text in PMC
Retrieved: 2026-09-16T10:33:38.332Z

source checked

automated source review · 2026-09-16

Audit details

Task-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced.

Field: attributes.profile.facts.2.value

Source artifact SHA-256: 54fe4db6f35c03d0d4f3ef4da720eb26a832199372c56d0956609ff07af750ee

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

Inspected artifact

Baselines
GloVe/word2vec neural baselines; NmRF, H2Opred and Meta-2OM web servers; BERT2OME retrained on the benchmark.
Individual claims
2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model

Original source ↗

Methods §§2.1, 2.4; Results §§3.1–3.2; cached text lines 11–14, 35–36, 43–48

Version: journal full text in PMC
Retrieved: 2026-09-16T10:33:38.332Z

source checked

automated source review · 2026-09-16

Audit details

Task-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced.

Field: attributes.profile.facts.3.value

Source artifact SHA-256: 54fe4db6f35c03d0d4f3ef4da720eb26a832199372c56d0956609ff07af750ee

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

Inspected artifact

Leakage controls
The checked dataset/split passages specify sample partitioning but do not specify a gene-, donor- or overlapping-window exclusion rule.
Individual claims
2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model

Original source ↗

Methods §§2.1, 2.4; Results §§3.1–3.2; cached text lines 11–14, 35–36, 43–48

Version: journal full text in PMC
Retrieved: 2026-09-16T10:33:38.332Z

unreported

automated source review · 2026-09-16

Audit details

Task-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced.

Field: attributes.profile.facts.4.value

Source artifact SHA-256: 54fe4db6f35c03d0d4f3ef4da720eb26a832199372c56d0956609ff07af750ee

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
2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model

Original source ↗

Methods §§2.1, 2.4; Results §§3.1–3.2; cached text lines 11–14, 35–36, 43–48

Version: journal full text in PMC
Retrieved: 2026-09-16T10:33:38.332Z

unreported

automated source review · 2026-09-16

Audit details

Task-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced.

Field: attributes.profile.facts.5.value

Source artifact SHA-256: 54fe4db6f35c03d0d4f3ef4da720eb26a832199372c56d0956609ff07af750ee

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-82fc7843f07324.

Related records

Suggest a correction