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.

Sources

2OMe-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 metric rows

At a glance

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
Property	Description and evidence
Datasets	RMBase v3.0 and multiple experimentally annotated RNA modification datasets supply positive and negative examples. Sources 2OMe-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
Splits	An 80:20 training/test partition is followed by five-fold cross-validation within training data. Sources 2OMe-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
Metrics	Accuracy, F1, precision, recall, AUROC, AUPR and MCC; cross-validation results are averaged across folds. Sources 2OMe-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
Baselines	GloVe/word2vec neural baselines; NmRF, H2Opred and Meta-2OM web servers; BERT2OME retrained on the benchmark. Sources 2OMe-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 controls	The checked dataset/split passages specify sample partitioning but do not specify a gene-, donor- or overlapping-window exclusion rule. · Not reported in inspected sources Sources 2OMe-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
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. · Not reported in inspected sources Sources 2OMe-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 type	Paper-specific computational evaluation protocol. Sources 2OMe-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
Organisms	Human. Sources 2OMe-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
Assays	RNA modification-site annotations from RMBase and experimental datasets. Sources 2OMe-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 inputs	RNA sequence windows around candidate modification sites. Sources 2OMe-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
Adaptation	Supervised site classifier; comparator servers and retrained models have distinct training provenance. Sources 2OMe-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

How it works

How it worksComputational evaluation flow

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

Sources

2OMe-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 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.

Sources

2OMe-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.

Protocols

These source-backed links do not make different protocols or scores interchangeable.

Published comparisons

Explore the results reported under one evaluation protocol. Each figure keeps its source, dataset and metric together; it is not a ranking across studies.

Comparison and metric

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

ACC (fraction) · Higher values are better for this metric.

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.

Evaluation protocol · human RNA 2OMe sites

GloVe + MLP · Configuration · Author-reported evaluation0.795
GloVe + TextCNN + MLP · Configuration · Author-reported evaluation0.746
GloVe + Transformer + MLP · Configuration · Author-reported evaluation0.742
Word2vec + MLP · Configuration · Author-reported evaluation0.813
Word2vec + TextCNN + MLP · Configuration · Author-reported evaluation0.764
Word2Vec + Transformer + MLP · Configuration · Author-reported evaluation0.749
2OMe-LM · Configuration · Author-reported evaluation 0.846

Source order is preserved. Plotted marks show point estimates; uncertainty, where reported, is retained in the printed values and table. Differences do not establish statistical significance.

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

Values, uncertainty and evidence

ACC: original source values
Tested entity	Printed value	Uncertainty	Evidence
GloVe + MLP · Configuration	0.795 fraction	Not reported	Author-reported evaluation · source checked2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Table 1. (btaf417-T1), row 2 GloVe + MLP, column 2: Human RNA 2OMe sites, five-fold cross-validation ACC
GloVe + TextCNN + MLP · Configuration	0.746 fraction	Not reported	Author-reported evaluation · source checked2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Table 1. (btaf417-T1), row 3 GloVe + TextCNN + MLP, column 2: Human RNA 2OMe sites, five-fold cross-validation ACC
GloVe + Transformer + MLP · Configuration	0.742 fraction	Not reported	Author-reported evaluation · source checked2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Table 1. (btaf417-T1), row 4 GloVe + Transformer + MLP, column 2: Human RNA 2OMe sites, five-fold cross-validation ACC
Word2vec + MLP · Configuration	0.813 fraction	Not reported	Author-reported evaluation · source checked2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Table 1. (btaf417-T1), row 5 Word2vec + MLP, column 2: Human RNA 2OMe sites, five-fold cross-validation ACC
Word2vec + TextCNN + MLP · Configuration	0.764 fraction	Not reported	Author-reported evaluation · source checked2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Table 1. (btaf417-T1), row 6 Word2vec + TextCNN + MLP, column 2: Human RNA 2OMe sites, five-fold cross-validation ACC
Word2Vec + Transformer + MLP · Configuration	0.749 fraction	Not reported	Author-reported evaluation · source checked2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Table 1. (btaf417-T1), row 7 Word2Vec + Transformer + MLP, column 2: Human RNA 2OMe sites, five-fold cross-validation ACC
2OMe-LM · Configuration	0.846 fraction	Not reported	Author-reported evaluation · source checked2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Table 1. (btaf417-T1), row 8 2OMe-LM, column 2: Human RNA 2OMe sites, five-fold cross-validation ACC

Scope and limitations

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.

Source transcription and grouping reviewed by automated source review on 2026-09-17. These experiments were not independently reproduced by rewire.

Tested entities and results

Release 2026-09-17-d277315f7d76 · 12 evaluations · 84 metric rows. Different protocols are not a single leaderboard.

Evaluation setupMetricEvidence origin

Results grouped by the exact reported evaluation
Metric and finding	Coverage and uncertainty	Evidence
2OMe-LM: human RNA 2-prime-O-methylation site prediction Configuration: 2OMe-LMProtocol: Human RNA 2OMe sites, five-fold cross-validation (human RNA 2-prime-O-methylation site prediction)Dataset: human RNA 2OMe sites 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. Author-reported evaluation · Evaluation metadata: needs review
0.919 AUC Unit: fraction · Direction: higher	Uncertainty: not reported in legacy extract Scored: Not reported · Eligible: Not reported	source checked2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Table 1, 2OMe-LM row, AUC column Source checking is not independent reproduction.
0.929 AUPR Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checked2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Table 1. (btaf417-T1), row 8 2OMe-LM, column 7: Human RNA 2OMe sites, five-fold cross-validation AUPR Source checking is not independent reproduction.
0.873 Precision Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checked2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Table 1. (btaf417-T1), row 8 2OMe-LM, column 4: Human RNA 2OMe sites, five-fold cross-validation Precision Source checking is not independent reproduction.
0.846 ACC Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checked2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Table 1. (btaf417-T1), row 8 2OMe-LM, column 2: Human RNA 2OMe sites, five-fold cross-validation ACC Source checking is not independent reproduction.
GloVe + TextCNN + MLP: Human RNA 2OMe sites, five-fold cross-validation Configuration: GloVe + TextCNN + MLPProtocol: Human RNA 2OMe sites, five-fold cross-validation (human RNA 2-prime-O-methylation site prediction)Dataset: human RNA 2OMe sites 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. Author-reported evaluation · Evaluation metadata: needs review
0.502 MCC Unit: unitless · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checked2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Table 1. (btaf417-T1), row 3 GloVe + TextCNN + MLP, column 8: Human RNA 2OMe sites, five-fold cross-validation MCC Source checking is not independent reproduction.
0.805 Precision Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checked2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Table 1. (btaf417-T1), row 3 GloVe + TextCNN + MLP, column 4: Human RNA 2OMe sites, five-fold cross-validation Precision Source checking is not independent reproduction.
0.842 AUC Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checked2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Table 1. (btaf417-T1), row 3 GloVe + TextCNN + MLP, column 6: Human RNA 2OMe sites, five-fold cross-validation AUC Source checking is not independent reproduction.
BERT2OME: Human RNA 2OMe sites, independent test set Configuration: BERT2OMEProtocol: Human RNA 2OMe sites, independent test set (human RNA 2-prime-O-methylation site prediction)Dataset: Human RNA 2OMe sites, independent test set 41-nt centred RNA windows; balanced 8,037 positive and 8,037 negative samples after 80% identity filtering, then 8:2 train/test division. Held-out independent test set. Independent external evaluation · Evaluation metadata: needs review
0.795 ACC Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checked2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Table 2. (btaf417-T2), row 3 BERT2OME, column 2: Human RNA 2OMe sites, independent test set ACC Source checking is not independent reproduction.
GloVe + Transformer + MLP: Human RNA 2OMe sites, five-fold cross-validation Configuration: GloVe + Transformer + MLPProtocol: Human RNA 2OMe sites, five-fold cross-validation (human RNA 2-prime-O-methylation site prediction)Dataset: human RNA 2OMe sites 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. Author-reported evaluation · Evaluation metadata: needs review
0.832 AUC Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checked2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Table 1. (btaf417-T1), row 4 GloVe + Transformer + MLP, column 6: Human RNA 2OMe sites, five-fold cross-validation AUC Source checking is not independent reproduction.
0.490 MCC Unit: unitless · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checked2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Table 1. (btaf417-T1), row 4 GloVe + Transformer + MLP, column 8: Human RNA 2OMe sites, five-fold cross-validation MCC Source checking is not independent reproduction.
0.720 F1-score Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checked2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Table 1. (btaf417-T1), row 4 GloVe + Transformer + MLP, column 3: Human RNA 2OMe sites, five-fold cross-validation F1-score Source checking is not independent reproduction.
2OMe-LM: Human RNA 2OMe sites, independent test set Configuration: 2OMe-LMProtocol: Human RNA 2OMe sites, independent test set (human RNA 2-prime-O-methylation site prediction)Dataset: Human RNA 2OMe sites, independent test set 41-nt centred RNA windows; balanced 8,037 positive and 8,037 negative samples after 80% identity filtering, then 8:2 train/test division. Held-out independent test set. Author-reported evaluation · Evaluation metadata: needs review
0.963 AUPR Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checked2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Table 2. (btaf417-T2), row 6 2OMe-LM, column 7: Human RNA 2OMe sites, independent test set AUPR Source checking is not independent reproduction.
0.898 ACC Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checked2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Table 2. (btaf417-T2), row 6 2OMe-LM, column 2: Human RNA 2OMe sites, independent test set ACC Source checking is not independent reproduction.
Word2vec + TextCNN + MLP: Human RNA 2OMe sites, five-fold cross-validation Configuration: Word2vec + TextCNN + MLPProtocol: Human RNA 2OMe sites, five-fold cross-validation (human RNA 2-prime-O-methylation site prediction)Dataset: human RNA 2OMe sites 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. Author-reported evaluation · Evaluation metadata: needs review
0.852 AUPR Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checked2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Table 1. (btaf417-T1), row 6 Word2vec + TextCNN + MLP, column 7: Human RNA 2OMe sites, five-fold cross-validation AUPR Source checking is not independent reproduction.
0.764 ACC Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checked2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Table 1. (btaf417-T1), row 6 Word2vec + TextCNN + MLP, column 2: Human RNA 2OMe sites, five-fold cross-validation ACC Source checking is not independent reproduction.
0.772 Precision Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checked2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Table 1. (btaf417-T1), row 6 Word2vec + TextCNN + MLP, column 4: Human RNA 2OMe sites, five-fold cross-validation Precision Source checking is not independent reproduction.
0.761 F1-score Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checked2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Table 1. (btaf417-T1), row 6 Word2vec + TextCNN + MLP, column 3: Human RNA 2OMe sites, five-fold cross-validation F1-score Source checking is not independent reproduction.
H2Opred: Human RNA 2OMe sites, independent test set Configuration: H2OpredProtocol: Human RNA 2OMe sites, independent test set (human RNA 2-prime-O-methylation site prediction)Dataset: Human RNA 2OMe sites, independent test set 41-nt centred RNA windows; balanced 8,037 positive and 8,037 negative samples after 80% identity filtering, then 8:2 train/test division. Held-out independent test set. Independent external evaluation · Evaluation metadata: needs review
0.800 F1-score Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checked2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Table 2. (btaf417-T2), row 4 H2Opred, column 3: Human RNA 2OMe sites, independent test set F1-score Source checking is not independent reproduction.
Meta-2OM: Human RNA 2OMe sites, independent test set Configuration: Meta-2OMProtocol: Human RNA 2OMe sites, independent test set (human RNA 2-prime-O-methylation site prediction)Dataset: Human RNA 2OMe sites, independent test set 41-nt centred RNA windows; balanced 8,037 positive and 8,037 negative samples after 80% identity filtering, then 8:2 train/test division. Held-out independent test set. Independent external evaluation · Evaluation metadata: needs review
0.881 AUPR Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checked2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Table 2. (btaf417-T2), row 5 Meta-2OM, column 7: Human RNA 2OMe sites, independent test set AUPR Source checking is not independent reproduction.
0.891 Precision Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checked2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Table 2. (btaf417-T2), row 5 Meta-2OM, column 4: Human RNA 2OMe sites, independent test set Precision Source checking is not independent reproduction.
GloVe + MLP: Human RNA 2OMe sites, five-fold cross-validation Configuration: GloVe + MLPProtocol: Human RNA 2OMe sites, five-fold cross-validation (human RNA 2-prime-O-methylation site prediction)Dataset: human RNA 2OMe sites 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. Author-reported evaluation · Evaluation metadata: needs review
0.872 AUPR Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checked2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Table 1. (btaf417-T1), row 2 GloVe + MLP, column 7: Human RNA 2OMe sites, five-fold cross-validation AUPR Source checking is not independent reproduction.
0.843 Precision Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checked2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Table 1. (btaf417-T1), row 2 GloVe + MLP, column 4: Human RNA 2OMe sites, five-fold cross-validation Precision Source checking is not independent reproduction.
NmRF: Human RNA 2OMe sites, independent test set Configuration: NmRFProtocol: Human RNA 2OMe sites, independent test set (human RNA 2-prime-O-methylation site prediction)Dataset: Human RNA 2OMe sites, independent test set 41-nt centred RNA windows; balanced 8,037 positive and 8,037 negative samples after 80% identity filtering, then 8:2 train/test division. Held-out independent test set. Independent external evaluation · Evaluation metadata: needs review
0.624 F1-score Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checked2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Table 2. (btaf417-T2), row 2 NmRF, column 3: Human RNA 2OMe sites, independent test set F1-score Source checking is not independent reproduction.
0.586 AUC Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checked2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Table 2. (btaf417-T2), row 2 NmRF, column 6: Human RNA 2OMe sites, independent test set AUC Source checking is not independent reproduction.
Word2Vec + Transformer + MLP: Human RNA 2OMe sites, five-fold cross-validation Configuration: Word2Vec + Transformer + MLPProtocol: Human RNA 2OMe sites, five-fold cross-validation (human RNA 2-prime-O-methylation site prediction)Dataset: human RNA 2OMe sites 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. Author-reported evaluation · Evaluation metadata: needs review
0.749 ACC Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checked2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Table 1. (btaf417-T1), row 7 Word2Vec + Transformer + MLP, column 2: Human RNA 2OMe sites, five-fold cross-validation ACC Source checking is not 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.

Paper or primary resource	Version	Reference
2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model	journal full text in PMC	Read source

What is still missing

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

Strengths and limitations

Strengths and considerations

No source-reviewed explanatory claims are recorded here yet.

Limitations and conditions

Web-server comparisons and retrained comparators do not have identical training provenance; overlap with their training corpora has not been audited here.
Sources
2OMe-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

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

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 2026-09-17-d277315f7d76
Property and statement	Original source and location	Review 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

All evidence (CSV)All evidence (JSONL)How to read the evidence

Sources and history

Release 2026-09-17-d277315f7d76 · Record review: needs review

2 source records and release history

2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Original source · journal full text in PMC
2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Original source · journal full text in PMC

Download this release

Technical metadata and extraction receipts

Stable ID: reported-task-82fc7843f07324

areas: rna-transcriptomes
tasks: human RNA 2-prime-O-methylation site prediction
entity level: task
version: Not reported
task: human RNA 2-prime-O-methylation site prediction
scope note: Paper-specific evaluation task; protocol completeness requires further extraction.
comparison panels: id: 2ome-lm-2025-btaf417-t1-accuracy; title: Human RNA 2OMe sites, five-fold cross-validation · ACC; protocol id: paper-protocol-1e891689a18fea3b65; dataset id: reported-dataset-bd3d8e7d6cd196; metric: ACC; unit: fraction; direction: higher; result ids: paper-result-d7aa3ed3ecdcfb7659; paper-result-7eeb7cd00870d4b822; paper-result-975e1e3b3cef0095d6; paper-result-bd40af36b346c6babe; paper-result-212ef20ae0523df179; paper-result-40dcbc4ba963adc002; paper-result-4bf3c3f0eec618c5cf; source ids: 2ome-lm-2025; source locator: 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; context: 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.; caveats: 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.; review: method: automated_source_review; date: 2026-09-17; id: 2ome-lm-2025-btaf417-t1-F1; title: Human RNA 2OMe sites, five-fold cross-validation · F1-score; protocol id: paper-protocol-1e891689a18fea3b65; dataset id: reported-dataset-bd3d8e7d6cd196; metric: F1-score; unit: fraction; direction: higher; result ids: paper-result-7fa777341a7b054db1; paper-result-db5c42675cc3446cac; paper-result-3b51683bec36f2abaa; paper-result-5a1e3c197818f5eef1; paper-result-3b60f80651245fd9b6; paper-result-5a0302f7287f4744fe; paper-result-98d984a2c66d9da9cc; source ids: 2ome-lm-2025; source locator: Performance comparison of 2OMe-LM and deep learning baseline models using 5-fold CV. a; Table 1. (btaf417-T1), row 2 GloVe + MLP, column 3: Human RNA 2OMe sites, five-fold cross-validation F1-score; Table 1. (btaf417-T1), row 3 GloVe + TextCNN + MLP, column 3: Human RNA 2OMe sites, five-fold cross-validation F1-score; Table 1. (btaf417-T1), row 4 GloVe + Transformer + MLP, column 3: Human RNA 2OMe sites, five-fold cross-validation F1-score; Table 1. (btaf417-T1), row 5 Word2vec + MLP, column 3: Human RNA 2OMe sites, five-fold cross-validation F1-score; Table 1. (btaf417-T1), row 6 Word2vec + TextCNN + MLP, column 3: Human RNA 2OMe sites, five-fold cross-validation F1-score; Table 1. (btaf417-T1), row 7 Word2Vec + Transformer + MLP, column 3: Human RNA 2OMe sites, five-fold cross-validation F1-score; Table 1. (btaf417-T1), row 8 2OMe-LM, column 3: Human RNA 2OMe sites, five-fold cross-validation F1-score; context: 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.; caveats: 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.; review: method: automated_source_review; date: 2026-09-17; id: 2ome-lm-2025-btaf417-t1-precision; title: Human RNA 2OMe sites, five-fold cross-validation · Precision; protocol id: paper-protocol-1e891689a18fea3b65; dataset id: reported-dataset-bd3d8e7d6cd196; metric: Precision; unit: fraction; direction: higher; result ids: paper-result-3eeedfbb867730e5ae; paper-result-1acfee83326c80f579; paper-result-edd616527eedbbdd6e; paper-result-5b8226a4362a18dc2f; paper-result-3265bdf784a6414dad; paper-result-e4f14db506e688bbf3; paper-result-2fdf47de24865482a1; source ids: 2ome-lm-2025; source locator: Performance comparison of 2OMe-LM and deep learning baseline models using 5-fold CV. a; Table 1. (btaf417-T1), row 2 GloVe + MLP, column 4: Human RNA 2OMe sites, five-fold cross-validation Precision; Table 1. (btaf417-T1), row 3 GloVe + TextCNN + MLP, column 4: Human RNA 2OMe sites, five-fold cross-validation Precision; Table 1. (btaf417-T1), row 4 GloVe + Transformer + MLP, column 4: Human RNA 2OMe sites, five-fold cross-validation Precision; Table 1. (btaf417-T1), row 5 Word2vec + MLP, column 4: Human RNA 2OMe sites, five-fold cross-validation Precision; Table 1. (btaf417-T1), row 6 Word2vec + TextCNN + MLP, column 4: Human RNA 2OMe sites, five-fold cross-validation Precision; Table 1. (btaf417-T1), row 7 Word2Vec + Transformer + MLP, column 4: Human RNA 2OMe sites, five-fold cross-validation Precision; Table 1. (btaf417-T1), row 8 2OMe-LM, column 4: Human RNA 2OMe sites, five-fold cross-validation Precision; context: 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.; caveats: 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.; review: method: automated_source_review; date: 2026-09-17; id: 2ome-lm-2025-btaf417-t1-recall; title: Human RNA 2OMe sites, five-fold cross-validation · Recall; protocol id: paper-protocol-1e891689a18fea3b65; dataset id: reported-dataset-bd3d8e7d6cd196; metric: Recall; unit: fraction; direction: higher; result ids: paper-result-a63abaf273d6997c8f; paper-result-c3fa62647b4acefdab; paper-result-ff7373a626f7495c54; paper-result-dbd9c2c21ebea1c98f; paper-result-e56df473e582088515; paper-result-dca07f72da08e9b1aa; paper-result-671f931ffacbf39ee5; source ids: 2ome-lm-2025; source locator: Performance comparison of 2OMe-LM and deep learning baseline models using 5-fold CV. a; Table 1. (btaf417-T1), row 2 GloVe + MLP, column 5: Human RNA 2OMe sites, five-fold cross-validation Recall; Table 1. (btaf417-T1), row 3 GloVe + TextCNN + MLP, column 5: Human RNA 2OMe sites, five-fold cross-validation Recall; Table 1. (btaf417-T1), row 4 GloVe + Transformer + MLP, column 5: Human RNA 2OMe sites, five-fold cross-validation Recall; Table 1. (btaf417-T1), row 5 Word2vec + MLP, column 5: Human RNA 2OMe sites, five-fold cross-validation Recall; Table 1. (btaf417-T1), row 6 Word2vec + TextCNN + MLP, column 5: Human RNA 2OMe sites, five-fold cross-validation Recall; Table 1. (btaf417-T1), row 7 Word2Vec + Transformer + MLP, column 5: Human RNA 2OMe sites, five-fold cross-validation Recall; Table 1. (btaf417-T1), row 8 2OMe-LM, column 5: Human RNA 2OMe sites, five-fold cross-validation Recall; context: 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.; caveats: 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.; review: method: automated_source_review; date: 2026-09-17; id: 2ome-lm-2025-btaf417-t1-AUROC; title: Human RNA 2OMe sites, five-fold cross-validation · AUC; protocol id: paper-protocol-1e891689a18fea3b65; dataset id: reported-dataset-bd3d8e7d6cd196; metric: AUC; unit: fraction; direction: higher; result ids: paper-result-d2c72c9538f864b13d; paper-result-5046ce3e5b1283c839; paper-result-138834d6ec841f6c4d; paper-result-928adade90586a2477; paper-result-b3a1db1d2e30c1ab66; paper-result-9ce02fe7f446cb3868; b2-2ome-lm-2025; source ids: 2ome-lm-2025; source locator: Performance comparison of 2OMe-LM and deep learning baseline models using 5-fold CV. a; Table 1. (btaf417-T1), row 2 GloVe + MLP, column 6: Human RNA 2OMe sites, five-fold cross-validation AUC; Table 1. (btaf417-T1), row 3 GloVe + TextCNN + MLP, column 6: Human RNA 2OMe sites, five-fold cross-validation AUC; Table 1. (btaf417-T1), row 4 GloVe + Transformer + MLP, column 6: Human RNA 2OMe sites, five-fold cross-validation AUC; Table 1. (btaf417-T1), row 5 Word2vec + MLP, column 6: Human RNA 2OMe sites, five-fold cross-validation AUC; Table 1. (btaf417-T1), row 6 Word2vec + TextCNN + MLP, column 6: Human RNA 2OMe sites, five-fold cross-validation AUC; Table 1. (btaf417-T1), row 7 Word2Vec + Transformer + MLP, column 6: Human RNA 2OMe sites, five-fold cross-validation AUC; Table 1. (btaf417-T1), row 8 2OMe-LM, column 6: Human RNA 2OMe sites, five-fold cross-validation AUC; context: 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.; caveats: 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.; review: method: automated_source_review; date: 2026-09-17; id: 2ome-lm-2025-btaf417-t1-AUPRC; title: Human RNA 2OMe sites, five-fold cross-validation · AUPR; protocol id: paper-protocol-1e891689a18fea3b65; dataset id: reported-dataset-bd3d8e7d6cd196; metric: AUPR; unit: fraction; direction: higher; result ids: paper-result-256879a6ad6287f562; paper-result-cca7eb69b40055db2f; paper-result-a14ee136864e50bd74; paper-result-da3bae3411f4589cf5; paper-result-17e76530dee5b1fe4f; paper-result-84c2a332b94869bbbe; paper-result-18ce292cd466151112; source ids: 2ome-lm-2025; source locator: Performance comparison of 2OMe-LM and deep learning baseline models using 5-fold CV. a; Table 1. (btaf417-T1), row 2 GloVe + MLP, column 7: Human RNA 2OMe sites, five-fold cross-validation AUPR; Table 1. (btaf417-T1), row 3 GloVe + TextCNN + MLP, column 7: Human RNA 2OMe sites, five-fold cross-validation AUPR; Table 1. (btaf417-T1), row 4 GloVe + Transformer + MLP, column 7: Human RNA 2OMe sites, five-fold cross-validation AUPR; Table 1. (btaf417-T1), row 5 Word2vec + MLP, column 7: Human RNA 2OMe sites, five-fold cross-validation AUPR; Table 1. (btaf417-T1), row 6 Word2vec + TextCNN + MLP, column 7: Human RNA 2OMe sites, five-fold cross-validation AUPR; Table 1. (btaf417-T1), row 7 Word2Vec + Transformer + MLP, column 7: Human RNA 2OMe sites, five-fold cross-validation AUPR; Table 1. (btaf417-T1), row 8 2OMe-LM, column 7: Human RNA 2OMe sites, five-fold cross-validation AUPR; context: 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.; caveats: 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.; review: method: automated_source_review; date: 2026-09-17; id: 2ome-lm-2025-btaf417-t1-MCC; title: Human RNA 2OMe sites, five-fold cross-validation · MCC; protocol id: paper-protocol-1e891689a18fea3b65; dataset id: reported-dataset-bd3d8e7d6cd196; metric: MCC; unit: unitless; direction: higher; result ids: paper-result-9f3d430c64f27de03d; paper-result-038d30f130b6a4c64b; paper-result-2ca6b64f9aa1a9748e; paper-result-e408a58902cb9dc5bf; paper-result-93ccc046cae95aea0c; paper-result-fe6771186123a657fd; paper-result-71c551bcf9091644da; source ids: 2ome-lm-2025; source locator: Performance comparison of 2OMe-LM and deep learning baseline models using 5-fold CV. a; Table 1. (btaf417-T1), row 2 GloVe + MLP, column 8: Human RNA 2OMe sites, five-fold cross-validation MCC; Table 1. (btaf417-T1), row 3 GloVe + TextCNN + MLP, column 8: Human RNA 2OMe sites, five-fold cross-validation MCC; Table 1. (btaf417-T1), row 4 GloVe + Transformer + MLP, column 8: Human RNA 2OMe sites, five-fold cross-validation MCC; Table 1. (btaf417-T1), row 5 Word2vec + MLP, column 8: Human RNA 2OMe sites, five-fold cross-validation MCC; Table 1. (btaf417-T1), row 6 Word2vec + TextCNN + MLP, column 8: Human RNA 2OMe sites, five-fold cross-validation MCC; Table 1. (btaf417-T1), row 7 Word2Vec + Transformer + MLP, column 8: Human RNA 2OMe sites, five-fold cross-validation MCC; Table 1. (btaf417-T1), row 8 2OMe-LM, column 8: Human RNA 2OMe sites, five-fold cross-validation MCC; context: 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.; caveats: 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.; review: method: automated_source_review; date: 2026-09-17; id: 2ome-lm-2025-btaf417-t2-accuracy; title: Human RNA 2OMe sites, independent test set · ACC; protocol id: paper-protocol-d933438afda70a21ef; dataset id: paper-dataset-64b51e2f952f2c1c09; metric: ACC; unit: fraction; direction: higher; result ids: paper-result-6cd0c965571a51b666; paper-result-0a3793081d7daa05a3; paper-result-90076f457aae558dd0; paper-result-6f26b2a32012628065; paper-result-172c48ff6795f50b97; source ids: 2ome-lm-2025; source locator: Performance comparison of 2OMe-LM with existing predictors on the independent test set. a; Table 2. (btaf417-T2), row 2 NmRF, column 2: Human RNA 2OMe sites, independent test set ACC; Table 2. (btaf417-T2), row 3 BERT2OME, column 2: Human RNA 2OMe sites, independent test set ACC; Table 2. (btaf417-T2), row 4 H2Opred, column 2: Human RNA 2OMe sites, independent test set ACC; Table 2. (btaf417-T2), row 5 Meta-2OM, column 2: Human RNA 2OMe sites, independent test set ACC; Table 2. (btaf417-T2), row 6 2OMe-LM, column 2: Human RNA 2OMe sites, independent test set ACC; context: 41-nt centred RNA windows; balanced 8,037 positive and 8,037 negative samples after 80% identity filtering, then 8:2 train/test division. Held-out independent test set.; caveats: 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.; review: method: automated_source_review; date: 2026-09-17; id: 2ome-lm-2025-btaf417-t2-F1; title: Human RNA 2OMe sites, independent test set · F1-score; protocol id: paper-protocol-d933438afda70a21ef; dataset id: paper-dataset-64b51e2f952f2c1c09; metric: F1-score; unit: fraction; direction: higher; result ids: paper-result-2901879d63427fece0; paper-result-703d9f2e0a92c08138; paper-result-1f1eb13ac1d3b0659c; paper-result-d219017e57658f8194; paper-result-a6ed9c1d07e0a8e3ac; source ids: 2ome-lm-2025; source locator: Performance comparison of 2OMe-LM with existing predictors on the independent test set. a; Table 2. (btaf417-T2), row 2 NmRF, column 3: Human RNA 2OMe sites, independent test set F1-score; Table 2. (btaf417-T2), row 3 BERT2OME, column 3: Human RNA 2OMe sites, independent test set F1-score; Table 2. (btaf417-T2), row 4 H2Opred, column 3: Human RNA 2OMe sites, independent test set F1-score; Table 2. (btaf417-T2), row 5 Meta-2OM, column 3: Human RNA 2OMe sites, independent test set F1-score; Table 2. (btaf417-T2), row 6 2OMe-LM, column 3: Human RNA 2OMe sites, independent test set F1-score; context: 41-nt centred RNA windows; balanced 8,037 positive and 8,037 negative samples after 80% identity filtering, then 8:2 train/test division. Held-out independent test set.; caveats: 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.; review: method: automated_source_review; date: 2026-09-17; id: 2ome-lm-2025-btaf417-t2-precision; title: Human RNA 2OMe sites, independent test set · Precision; protocol id: paper-protocol-d933438afda70a21ef; dataset id: paper-dataset-64b51e2f952f2c1c09; metric: Precision; unit: fraction; direction: higher; result ids: paper-result-657a6c49b38ef8252b; paper-result-6489236abf51572541; paper-result-a070ec6c349b5e96ef; paper-result-2d7677257f873b4e29; paper-result-b90e8cd12cecf6951f; source ids: 2ome-lm-2025; source locator: Performance comparison of 2OMe-LM with existing predictors on the independent test set. a; Table 2. (btaf417-T2), row 2 NmRF, column 4: Human RNA 2OMe sites, independent test set Precision; Table 2. (btaf417-T2), row 3 BERT2OME, column 4: Human RNA 2OMe sites, independent test set Precision; Table 2. (btaf417-T2), row 4 H2Opred, column 4: Human RNA 2OMe sites, independent test set Precision; Table 2. (btaf417-T2), row 5 Meta-2OM, column 4: Human RNA 2OMe sites, independent test set Precision; Table 2. (btaf417-T2), row 6 2OMe-LM, column 4: Human RNA 2OMe sites, independent test set Precision; context: 41-nt centred RNA windows; balanced 8,037 positive and 8,037 negative samples after 80% identity filtering, then 8:2 train/test division. Held-out independent test set.; caveats: 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.; review: method: automated_source_review; date: 2026-09-17; id: 2ome-lm-2025-btaf417-t2-recall; title: Human RNA 2OMe sites, independent test set · Recall; protocol id: paper-protocol-d933438afda70a21ef; dataset id: paper-dataset-64b51e2f952f2c1c09; metric: Recall; unit: fraction; direction: higher; result ids: paper-result-eb25b223c10be4f330; paper-result-c8c5c199a2b0059317; paper-result-fab2a73ce6d700ff87; paper-result-7c85e27954addc7e14; paper-result-9980f6cb88d2219b02; source ids: 2ome-lm-2025; source locator: Performance comparison of 2OMe-LM with existing predictors on the independent test set. a; Table 2. (btaf417-T2), row 2 NmRF, column 5: Human RNA 2OMe sites, independent test set Recall; Table 2. (btaf417-T2), row 3 BERT2OME, column 5: Human RNA 2OMe sites, independent test set Recall; Table 2. (btaf417-T2), row 4 H2Opred, column 5: Human RNA 2OMe sites, independent test set Recall; Table 2. (btaf417-T2), row 5 Meta-2OM, column 5: Human RNA 2OMe sites, independent test set Recall; Table 2. (btaf417-T2), row 6 2OMe-LM, column 5: Human RNA 2OMe sites, independent test set Recall; context: 41-nt centred RNA windows; balanced 8,037 positive and 8,037 negative samples after 80% identity filtering, then 8:2 train/test division. Held-out independent test set.; caveats: 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.; review: method: automated_source_review; date: 2026-09-17; id: 2ome-lm-2025-btaf417-t2-AUROC; title: Human RNA 2OMe sites, independent test set · AUC; protocol id: paper-protocol-d933438afda70a21ef; dataset id: paper-dataset-64b51e2f952f2c1c09; metric: AUC; unit: fraction; direction: higher; result ids: paper-result-48c539e46e8e0de49c; paper-result-c5e158015fb2c59552; paper-result-da8a9134bd3530143b; paper-result-ce07a0b8b72a4068f5; paper-result-76e7297a1974a4704a; source ids: 2ome-lm-2025; source locator: Performance comparison of 2OMe-LM with existing predictors on the independent test set. a; Table 2. (btaf417-T2), row 2 NmRF, column 6: Human RNA 2OMe sites, independent test set AUC; Table 2. (btaf417-T2), row 3 BERT2OME, column 6: Human RNA 2OMe sites, independent test set AUC; Table 2. (btaf417-T2), row 4 H2Opred, column 6: Human RNA 2OMe sites, independent test set AUC; Table 2. (btaf417-T2), row 5 Meta-2OM, column 6: Human RNA 2OMe sites, independent test set AUC; Table 2. (btaf417-T2), row 6 2OMe-LM, column 6: Human RNA 2OMe sites, independent test set AUC; context: 41-nt centred RNA windows; balanced 8,037 positive and 8,037 negative samples after 80% identity filtering, then 8:2 train/test division. Held-out independent test set.; caveats: 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.; review: method: automated_source_review; date: 2026-09-17; id: 2ome-lm-2025-btaf417-t2-AUPRC; title: Human RNA 2OMe sites, independent test set · AUPR; protocol id: paper-protocol-d933438afda70a21ef; dataset id: paper-dataset-64b51e2f952f2c1c09; metric: AUPR; unit: fraction; direction: higher; result ids: paper-result-cf762cdb6f3083c1e5; paper-result-ea74464791a87509df; paper-result-79788c7d80922dad49; paper-result-209a40abae677db031; paper-result-13e1c3729d85f66b41; source ids: 2ome-lm-2025; source locator: Performance comparison of 2OMe-LM with existing predictors on the independent test set. a; Table 2. (btaf417-T2), row 2 NmRF, column 7: Human RNA 2OMe sites, independent test set AUPR; Table 2. (btaf417-T2), row 3 BERT2OME, column 7: Human RNA 2OMe sites, independent test set AUPR; Table 2. (btaf417-T2), row 4 H2Opred, column 7: Human RNA 2OMe sites, independent test set AUPR; Table 2. (btaf417-T2), row 5 Meta-2OM, column 7: Human RNA 2OMe sites, independent test set AUPR; Table 2. (btaf417-T2), row 6 2OMe-LM, column 7: Human RNA 2OMe sites, independent test set AUPR; context: 41-nt centred RNA windows; balanced 8,037 positive and 8,037 negative samples after 80% identity filtering, then 8:2 train/test division. Held-out independent test set.; caveats: 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.; review: method: automated_source_review; date: 2026-09-17; id: 2ome-lm-2025-btaf417-t2-MCC; title: Human RNA 2OMe sites, independent test set · MCC; protocol id: paper-protocol-d933438afda70a21ef; dataset id: paper-dataset-64b51e2f952f2c1c09; metric: MCC; unit: unitless; direction: higher; result ids: paper-result-acad7ffaf81174cddb; paper-result-d947e45a8a87762a5f; paper-result-abe41dfecafe879c49; paper-result-85be9319f746a0dd77; paper-result-e68cc241f300063bca; source ids: 2ome-lm-2025; source locator: Performance comparison of 2OMe-LM with existing predictors on the independent test set. a; Table 2. (btaf417-T2), row 2 NmRF, column 8: Human RNA 2OMe sites, independent test set MCC; Table 2. (btaf417-T2), row 3 BERT2OME, column 8: Human RNA 2OMe sites, independent test set MCC; Table 2. (btaf417-T2), row 4 H2Opred, column 8: Human RNA 2OMe sites, independent test set MCC; Table 2. (btaf417-T2), row 5 Meta-2OM, column 8: Human RNA 2OMe sites, independent test set MCC; Table 2. (btaf417-T2), row 6 2OMe-LM, column 8: Human RNA 2OMe sites, independent test set MCC; context: 41-nt centred RNA windows; balanced 8,037 positive and 8,037 negative samples after 80% identity filtering, then 8:2 train/test division. Held-out independent test set.; caveats: 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.; review: method: automated_source_review; date: 2026-09-17
benchmark research: review date: 2026-09-17; status: complete_tables_extracted; primary sources: evidence-expansion-2ome-lm-2025-54fe4db6; inspected locators: Table 1.; XML table btaf417-T1; Table 2.; XML table btaf417-T2; searched queries: 2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model 10.1093/bioinformatics/btaf417; gaps: 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.; claim scope: 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 missing metadata: protocol version: not_reported_in_legacy_extract
metadata review scope: historical_missing_metadata preserves the original discovery state. Current descriptive evidence and missingness are recorded in profile.facts; numerical-result review is separate.
legacy kinds: benchmark
entity classification: review date: 2026-09-17; rationale: This source-scoped record identifies the biological prediction task and holds its paper context. Preserve the existing task identity; exact split, model adaptation and scoring remain in linked evaluations or separate protocol records.; source ids: 2ome-lm-2025; source locator: Methods §§2.1, 2.4; Results §§3.1–3.2; cached text lines 11–14, 35–36, 43–48; ambiguities: A paper- or suite-specific task may constrain some inputs or metrics; that alone does not make it interchangeable with a complete versioned protocol. No protocol equivalence is inferred.; Some legacy profile Entity type facts use the generic phrase computational evaluation protocol. That boilerplate is not sufficient to establish a single fixed protocol identity or to merge this task with another protocol record.

Related records

dataset: human RNA 2OMe sites
evaluates task: Human RNA 2OMe sites, five-fold cross-validation (human RNA 2-prime-O-methylation site prediction)
evaluates task: Human RNA 2OMe sites, independent test set (human RNA 2-prime-O-methylation site prediction)

Suggest a correction