Model type
Recurrent neural network; this record is the paper-specific evaluated configuration.
Configuration
2OMe-LM
2OMe-LM predicts whether the central nucleotide of an RNA window carries a 2′-O-methylation modification.
Sources
2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · 3 Results/3.4 Motif analysis (paragraph 2); 2 Materials and methods/2.2 Model architecture/2.2.2 Word2vec embedding (paragraph 2)How it worksEvaluated procedure (conceptual)
Conceptual input–method–output guide. Check the procedure text and linked evaluation for fitted components, additional inputs and exact settings.
Sources
2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · 2 Materials and methods/2.2 Model architecture (paragraph 1); 2 Materials and methods/2.2 Model architecture/2.2.3 Feature fusion and prediction (paragraph 3)At a glance
Biological inputs
RNA sequence windows centred on candidate modification sites
Sources
2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · 3 Results/3.4 Motif analysis (paragraph 2); 4 Conclusion (paragraph 1)Outputs
Probability that the central site is 2′-O-methylated
Sources
2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · 2 Materials and methods/2.2 Model architecture/2.2.3 Feature fusion and prediction (paragraph 3); 3 Results/3.5 Case study (paragraph 1)limited source coverage · Automated source review, 2026-09-16. All specifications and missing details
Evaluations and results
Release 2026-09-17-d277315f7d76 · 1 evaluation · 7 metric rows. Different protocols are not a single leaderboard.
| 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. |
|
0.811
Recall 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 5: Human RNA 2OMe sites, five-fold cross-validation Recall Source checking is not independent reproduction. |
|
0.695
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 8 2OMe-LM, column 8: Human RNA 2OMe sites, five-fold cross-validation MCC Source checking is not independent reproduction. |
|
0.841
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 8 2OMe-LM, column 3: Human RNA 2OMe sites, five-fold cross-validation F1-score Source checking is not independent reproduction. |
How it works
How the evaluated method works
SpliceBERT embeddings pass through a dimensionality-reduction layer. A second branch encodes k-mers with word2vec and a bidirectional LSTM. Fused features enter an attention block and three fully connected layers for site classification.
Sources
2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · 2 Materials and methods/2.2 Model architecture (paragraph 1); 2 Materials and methods/2.2 Model architecture/2.2.3 Feature fusion and prediction (paragraph 3)What was evaluated
The linked evaluation record identifies 2OMe-LM: human RNA 2-prime-O-methylation site prediction. Its dataset, split, adaptation and evidence origin remain attached to the reported results.
Sources
2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · The named evaluation’s methods and comparison table; exact preserved evaluation IDs: evaluation-b2-2ome-lm-2025Strengths and limitations
Strengths and considerations
- Combines pretrained RNA representations with a separately learned k-mer branch and provides attention-based motif analysis.
Sources
2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Abstract (paragraph 1); 3 Results/3.4 Motif analysis (paragraph 1)
Limitations and conditions
- The reported human-RNA classification task and sampling scheme do not establish performance on every RNA species or modification type.
Sources
2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · 3 Results/3.6 Cross-nucleotide evaluation (paragraph 1); 3 Results/3.4 Motif analysis (paragraph 2)
Profile review details
Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction.
Stable record: reported-model-7f5b8234967c54Specifications
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.
| Property | Description and evidence |
|---|---|
| Model type | Recurrent neural network; this record is the paper-specific evaluated configuration.Sources2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · 2 Materials and methods/2.2 Model architecture (paragraph 1); 2 Materials and methods/2.2 Model architecture/2.2.3 Feature fusion and prediction (paragraph 3) |
| Architecture / procedure | SpliceBERT embeddings pass through a dimensionality-reduction layer. A second branch encodes k-mers with word2vec and a bidirectional LSTM. Fused features enter an attention block and three fully connected layers for site classification.Sources2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · 2 Materials and methods/2.2 Model architecture (paragraph 1); 2 Materials and methods/2.2 Model architecture/2.2.3 Feature fusion and prediction (paragraph 3) |
| Biological inputs | RNA sequence windows centred on candidate modification sitesSources2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · 3 Results/3.4 Motif analysis (paragraph 2); 4 Conclusion (paragraph 1) |
| Outputs | Probability that the central site is 2′-O-methylatedSources2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · 2 Materials and methods/2.2 Model architecture/2.2.3 Feature fusion and prediction (paragraph 3); 3 Results/3.5 Case study (paragraph 1) |
| Parameters | An aggregate parameter total for this exact evaluated configuration is not established by the inspected sources. · Not reported in inspected sourcesSources (2)2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model; CSUBioGroup/2OMe-LM README.md · 2 Materials and methods/2.1 Datasets; 2 Materials and methods/2.2 Model architecture; 2 Materials and methods/2.2 Model architecture/2.2.1 Pretrained RNA language model; 2 Materials and methods/2.2 Model architecture/2.2.2 Word2vec embedding; 2 Materials and methods/2.2 Model architecture/2.2.3 Feature fusion and prediction; 2 Materials and methods/2.3 Deep learning baseline models; 2 Materials and methods/2.4 Evaluation metrics; 2 Materials and methods/2.5 Implementation details; inspected for aggregate parameter count (component sizes are not added without an exact configuration); README.md at pinned repository revision |
| Known versions / configuration | 2OMe-LM is the comparison-table label; that label does not specify an immutable weight revision. · Not reported in inspected sourcesSources2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · Model identification in the comparison table and corresponding Methods; immutable checkpoint revision is not supplied by the table label. |
| Training data / fitting | 8,037 positive and 8,037 negative examples, with an 80:20 training/test partition; SpliceBERT provides separately pretrained sequence features.Sources2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · 2 Materials and methods/2.1 Datasets (paragraph 2); 2 Materials and methods/2.1 Datasets (paragraph 1) |
| Context limits | SpliceBERT supports up to 1,024 nucleotides; that backbone limit is not an independently verified limit of the complete predictor.Sources2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model · 3 Results/3.3 Effectiveness of pre-trained RNA language model (paragraph 1); Table btaf417-T2 (paragraph 1) |
| Access | Official study implementation and usage documentation: https://github.com/CSUBioGroup/2OMe-LM/blob/2e22439723777b5bacdce72cdcd7cfbde9e88cd1/README.md. This pinned documentation revision is not automatically the evaluated weight revision.SourcesCSUBioGroup/2OMe-LM README.md · README.md; installation, model download and usage instructions |
| Code licence | No explicit code licence was established from the paper’s availability statement and inspected repository-root documentation. · Not reported in inspected sourcesSourcesCSUBioGroup/2OMe-LM README.md · README.md and repository-root licence-file search |
| Weights licence | The inspected model-access documentation does not explicitly identify terms for this exact evaluated checkpoint or fitted head; repository code terms are shown separately. · Not reported in inspected sourcesSourcesCSUBioGroup/2OMe-LM README.md · README.md; checkpoint/access documentation and licence scope |
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.
20 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Diagram caption Conceptual input–method–output guide. Check the procedure text and linked evaluation for fitted components, additional inputs and exact settings. Individual claims | 2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model 2 Materials and methods/2.2 Model architecture (paragraph 1); 2 Materials and methods/2.2 Model architecture/2.2.3 Feature fusion and prediction (paragraph 3) Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Diagram steps ["RNA sequence windows centred on candidate modification sites","2OMe-LM","Probability that the central site is 2′-O-methylated"] Individual claims | 2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model 2 Materials and methods/2.2 Model architecture (paragraph 1); 2 Materials and methods/2.2 Model architecture/2.2.3 Feature fusion and prediction (paragraph 3) Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Diagram title Evaluated procedure (conceptual) Individual claims | 2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model 2 Materials and methods/2.2 Model architecture (paragraph 1); 2 Materials and methods/2.2 Model architecture/2.2.3 Feature fusion and prediction (paragraph 3) Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Model type Recurrent neural network; this record is the paper-specific evaluated configuration. Individual claims | 2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model 2 Materials and methods/2.2 Model architecture (paragraph 1); 2 Materials and methods/2.2 Model architecture/2.2.3 Feature fusion and prediction (paragraph 3) Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Architecture / procedure SpliceBERT embeddings pass through a dimensionality-reduction layer. A second branch encodes k-mers with word2vec and a bidirectional LSTM. Fused features enter an attention block and three fully connected layers for site classification. Individual claims | 2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model 2 Materials and methods/2.2 Model architecture (paragraph 1); 2 Materials and methods/2.2 Model architecture/2.2.3 Feature fusion and prediction (paragraph 3) Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Weights licence The inspected model-access documentation does not explicitly identify terms for this exact evaluated checkpoint or fitted head; repository code terms are shown separately. Individual claims | CSUBioGroup/2OMe-LM README.md README.md; checkpoint/access documentation and licence scope Version: 2e22439723777b5bacdce72cdcd7cfbde9e88cd1 | unreported automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Biological inputs RNA sequence windows centred on candidate modification sites Individual claims | 2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model 3 Results/3.4 Motif analysis (paragraph 2); 4 Conclusion (paragraph 1) Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Outputs Probability that the central site is 2′-O-methylated Individual claims | 2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model 2 Materials and methods/2.2 Model architecture/2.2.3 Feature fusion and prediction (paragraph 3); 3 Results/3.5 Case study (paragraph 1) Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Parameters An aggregate parameter total for this exact evaluated configuration is not established by the inspected sources. Individual claims | 2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model 2 Materials and methods/2.1 Datasets; 2 Materials and methods/2.2 Model architecture; 2 Materials and methods/2.2 Model architecture/2.2.1 Pretrained RNA language model; 2 Materials and methods/2.2 Model architecture/2.2.2 Word2vec embedding; 2 Materials and methods/2.2 Model architecture/2.2.3 Feature fusion and prediction; 2 Materials and methods/2.3 Deep learning baseline models; 2 Materials and methods/2.4 Evaluation metrics; 2 Materials and methods/2.5 Implementation details; inspected for aggregate parameter count (component sizes are not added without an exact configuration); README.md at pinned repository revision Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: journal full text in PMC | unreported automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Parameters An aggregate parameter total for this exact evaluated configuration is not established by the inspected sources. Individual claims | CSUBioGroup/2OMe-LM README.md 2 Materials and methods/2.1 Datasets; 2 Materials and methods/2.2 Model architecture; 2 Materials and methods/2.2 Model architecture/2.2.1 Pretrained RNA language model; 2 Materials and methods/2.2 Model architecture/2.2.2 Word2vec embedding; 2 Materials and methods/2.2 Model architecture/2.2.3 Feature fusion and prediction; 2 Materials and methods/2.3 Deep learning baseline models; 2 Materials and methods/2.4 Evaluation metrics; 2 Materials and methods/2.5 Implementation details; inspected for aggregate parameter count (component sizes are not added without an exact configuration); README.md at pinned repository revision Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 2e22439723777b5bacdce72cdcd7cfbde9e88cd1 | unreported automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
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
- CSUBioGroup/2OMe-LM README.md · Original source · 2e22439723777b5bacdce72cdcd7cfbde9e88cd1
Technical metadata and extraction receipts
Stable ID: reported-model-7f5b8234967c54
- areas
- rna-transcriptomes
- entity level
- method
- version
- not stated in table
- reported name
- 2OMe-LM
- historical missing metadata
- checkpoint revision: not_reported_in_legacy_extract; training data: not_reported_in_legacy_extract; licence: 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
- model
- entity classification
- review date: 2026-09-17; rationale: This source-scoped entry preserves the method/configuration actually named in an evaluation. It is neither a global family identity nor proof of an immutable checkpoint; the linked evaluation retains adaptation, fitting and scoring details.; source ids: 2ome-lm-2025; source locator: 2 Materials and methods/2.2 Model architecture (paragraph 1); 2 Materials and methods/2.2 Model architecture/2.2.3 Feature fusion and prediction (paragraph 3) | 3 Results/3.4 Motif analysis (paragraph 2); 2 Materials and methods/2.2 Model architecture/2.2.2 Word2vec embedding (paragraph 2); ambiguities: Configuration means the source-labelled evaluated identity. It does not establish missing checkpoint hashes, default settings or equivalence to same-named records in other papers.