Model type
Masked-token RNA transformer encoder
Model
RNA-FM
RNA-FM learns contextual representations of RNA nucleotides for downstream RNA analyses.
Sources (2)
ml4bio/RNA-FM: README.md; ml4bio/RNA-FM: fm/pretrained.py · README.md: Quick Start, embedding examples and RNA foundation model comparison table67 evaluations · 67 results5 configurations with further results2 open disagreements between studies involve this model
How it worksRNA-FM workflow
Conceptual summary of the documented data flow; optional inputs and configured downstream stages must be reported for a reproducible evaluation.
Sources (2)
ml4bio/RNA-FM: README.md; ml4bio/RNA-FM: fm/pretrained.py · README.md: Quick Start, embedding examples and RNA foundation model comparison tableOverview
Inputs
RNA sequences tokenized at nucleotide resolution.
Outputs
Contextual token embeddings for a specified downstream RNA task.
Access
Official project documentation and implementation: https://github.com/ml4bio/RNA-FM
Sources (2)
ml4bio/RNA-FM: README.md; ml4bio/RNA-FM: fm/pretrained.py · README.md: Quick Start, embedding examples and RNA foundation model comparison tablelimited source coverage · Automated source review, 2026-09-23. All specifications and missing details
Evaluations and results
67 evaluations · 67 results. Different protocols are not a single leaderboard.
Sorted by Spearman (higher is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.
| Tested configuration | Protocol and dataset | Spearman | AUROC | AUPRC | R² | MCC | NDCG (cutoff not stated) | Accuracy | F1 (base pairs; binary F1 over all position pairs pooled across the test set; threshold 0.5) | Mean columnwise RMSE | Precision at l | Splice top k accuracy | Pearson |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| RNA-FMEvaluation | BEACON CRI-On: CRISPR on-target efficiency prediction, DeepCRISPR (BEACON split) | 31.62(1.16) (best in column) | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | BEACON CRI-Off: CRISPR off-target effect prediction, DeepCRISPR (BEACON split) | 2.49(1.56) | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | NABench SELEX-RCV: Overall fitness prediction on NABench SELEX assays, Random cross validation Spearman ρ, NABench SELEX assays (NABench split) | 0.685 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | NABench SELEX-FS: Overall fitness prediction on NABench SELEX assays, Few-shot Spearman ρ, NABench SELEX assays (NABench split) | 0.617 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | NABench RCV-CORR-MRNA: Fitness prediction on mRNA assays, supervised, random cross validation, NABench mRNA assays (NABench split) | 0.597 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | NABench RCV-CORR-TRNA: Fitness prediction on tRNA assays, supervised, random cross validation, NABench tRNA assays (NABench split) | 0.587 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | NABench RCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, random cross validation, NABench promoter assays (NABench split) | 0.582 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | NABench RCV-CORR-RIBOZYME: Fitness prediction on ribozyme assays, supervised, random cross validation, NABench ribozyme assays (NABench split) | 0.556 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | NABench DMS-RCV: Overall fitness prediction on NABench deep mutational scanning assays, Random cross validation Spearman ρ, NABench deep mutational scanning assays (NABench split) | 0.544 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | NABench RCV-CORR-APTAMER: Fitness prediction on aptamer assays, supervised, random cross validation, NABench aptamer assays (NABench split) | 0.53 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | NABench ZS-CORR-TRNA: Fitness prediction on tRNA assays, zero-shot, NABench tRNA assays (NABench split) | 0.357 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | NABench CCV-CORR-TRNA: Fitness prediction on tRNA assays, supervised, contiguous cross validation, NABench tRNA assays (NABench split) | 0.345 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | NABench FS-CORR-MRNA: Fitness prediction on mRNA assays, few-shot, NABench mRNA assays (NABench split) | 0.318 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | NABench CCV-CORR-MRNA: Fitness prediction on mRNA assays, supervised, contiguous cross validation, NABench mRNA assays (NABench split) | 0.259 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | NABench ZS-CORR-MRNA: Fitness prediction on mRNA assays, zero-shot, NABench mRNA assays (NABench split) | 0.257 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | NABench RCV-CORR-ENHANCER: Fitness prediction on enhancer assays, supervised, random cross validation, NABench enhancer assays (NABench split) | 0.256 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | NABench FS-CORR-APTAMER: Fitness prediction on aptamer assays, few-shot, NABench aptamer assays (NABench split) | 0.248 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | NABench CCV-CORR-RIBOZYME: Fitness prediction on ribozyme assays, supervised, contiguous cross validation, NABench ribozyme assays (NABench split) | 0.242 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | NABench DMS-CCV: Overall fitness prediction on NABench deep mutational scanning assays, Contiguous cross validation Spearman ρ, NABench deep mutational scanning assays (NABench split) | 0.233 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | NABench FS-CORR-TRNA: Fitness prediction on tRNA assays, few-shot, NABench tRNA assays (NABench split) | 0.232 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | NABench DMS-FS: Overall fitness prediction on NABench deep mutational scanning assays, Few-shot Spearman ρ, NABench deep mutational scanning assays (NABench split) | 0.183 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | NABench ZS-CORR-APTAMER: Fitness prediction on aptamer assays, zero-shot, NABench aptamer assays (NABench split) | 0.167 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | NABench FS-CORR-RIBOZYME: Fitness prediction on ribozyme assays, few-shot, NABench ribozyme assays (NABench split) | 0.164 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | NABench FS-CORR-PROMOTER: Fitness prediction on promoter assays, few-shot, NABench promoter assays (NABench split) | 0.159 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | NABench DMS-ZS-CORR: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot Spearman ρ, NABench deep mutational scanning assays (NABench split) | 0.148 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | NABench CCV-CORR-APTAMER: Fitness prediction on aptamer assays, supervised, contiguous cross validation, NABench aptamer assays (NABench split) | 0.115 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | NABench ZS-CORR-RIBOZYME: Fitness prediction on ribozyme assays, zero-shot, NABench ribozyme assays (NABench split) | 0.103 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | NABench ZS-CORR-PROMOTER: Fitness prediction on promoter assays, zero-shot, NABench promoter assays (NABench split) | 0.098 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | NABench CCV-CORR-ENHANCER: Fitness prediction on enhancer assays, supervised, contiguous cross validation, NABench enhancer assays (NABench split) | 0.095 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | NABench SELEX-ZS-CORR: Overall fitness prediction on NABench SELEX assays, Zero-shot Spearman ρ, NABench SELEX assays (NABench split) | 0.085 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | NABench CCV-CORR-PROMOTER: Fitness prediction on promoter assays, supervised, contiguous cross validation, NABench promoter assays (NABench split) | 0.035 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | NABench ZS-CORR-ENHANCER: Fitness prediction on enhancer assays, zero-shot, NABench enhancer assays (NABench split) | 0.011 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | NABench FS-CORR-ENHANCER: Fitness prediction on enhancer assays, few-shot, NABench enhancer assays (NABench split) | 0.009 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | BEACON APA: Alternative polyadenylation isoform prediction, APARENT (BEACON split) | Not reported | Not reported | Not reported | 70.32(0.97) | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | BEACON CMP: Contact map prediction, RNAcontact (BEACON split) | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | 47.56(6.73)% | Not reported | Not reported |
| RNA-FMEvaluation | BEACON DMP: Distance map prediction, RNAcontact (BEACON split) | Not reported | Not reported | Not reported | 51.45(0.51) | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | BEACON Modif: RNA modification site prediction, MultiRM (BEACON split) | Not reported | 94.98(0.042) (best in column) | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | BEACON MRL: Mean ribosome loading prediction, Optimus (BEACON split) | Not reported | Not reported | Not reported | 79.47(0.47) (best in column) | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | BEACON ncRNA: Non-coding RNA family classification, Noorul's ncRNA set (BEACON split) | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | 96.81(0.061)% | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | BEACON PRS: Programmable RNA switch prediction, Angenent-Mari's switch set (BEACON split) | Not reported | Not reported | Not reported | 55.98(0.09) | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | BEACON SPL: Splice site prediction, SpliceAI (BEACON split) | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | 34.84(0.87)% | Not reported |
| RNA-FMEvaluation | BEACON SSI: Structure score imputation, StructureImpute (BEACON split) | Not reported | Not reported | Not reported | 42.36(0.24) | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | BEACON SSP: Secondary structure prediction, bpRNA-1m (BEACON split) | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | 68.50(0.54)% | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | BEACON VDP: Vaccine degradation prediction, OpenVaccine (BEACON split) | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | 0.347(0.003) | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | Mean ribosome load from MPRA, mRNABench MRL-MPRA | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | 0.49 |
| RNA-FMEvaluation | mRNABench ECLIP: eCLIP binding site prediction, mRNABench eCLIP (mRNABench split) | Not reported | Not reported | 35% | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | mRNABench GO: Gene Ontology term prediction, mRNABench GO (mRNABench split) | Not reported | Not reported | 32.2% | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | mRNABench HL: mRNA half life, mRNABench HL (mRNABench split) | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | 0.47 |
| RNA-FMEvaluation | mRNABench MRL-HL-PAIR: Paired mean ribosome load and half life, mRNABench MRL-HL-Pair (mRNABench split) | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | 0.49 |
| RNA-FMEvaluation | mRNABench MRL-MPRA: Mean ribosome load on an MPRA library, mRNABench MRL MPRA (mRNABench split) | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | 0.49 |
| RNA-FMEvaluation | mRNABench MRL: Mean ribosome load, mRNABench MRL (mRNABench split) | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | 0.29 |
| RNA-FMEvaluation | mRNABench MRNA-LOC-LR: mRNA localisation, long range, mRNABench mRNA Loc-LR (mRNABench split) | Not reported | Not reported | 74.3% (best in column) | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | mRNABench MRNA-LOC-SR: mRNA localisation, short range, mRNABench mRNA Loc-SR (mRNABench split) | Not reported | Not reported | 67% | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | mRNABench PROT-LOC: Protein localisation, mRNABench Prot Loc (mRNABench split) | Not reported | Not reported | 32.2% | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | mRNABench VEP: Variant effect prediction, mRNABench VEP (mRNABench split) | Not reported | Not reported | 25.7% | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | NABench DMS-ZS-AUC: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot AUC, NABench deep mutational scanning assays (NABench split) | Not reported | 0.541 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | NABench DMS-ZS-MCC: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot MCC, NABench deep mutational scanning assays (NABench split) | Not reported | Not reported | Not reported | Not reported | 0.068 (best in column) | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | NABench DMS-ZS-NDCG: Overall fitness prediction on NABench deep mutational scanning assays, Zero-shot NDCG, NABench deep mutational scanning assays (NABench split) | Not reported | Not reported | Not reported | Not reported | Not reported | 0.38 (best in column) | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | NABench SELEX-ZS-AUC: Overall fitness prediction on NABench SELEX assays, Zero-shot AUC, NABench SELEX assays (NABench split) | Not reported | 0.55 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | NABench SELEX-ZS-MCC: Overall fitness prediction on NABench SELEX assays, Zero-shot MCC, NABench SELEX assays (NABench split) | Not reported | Not reported | Not reported | Not reported | 0.05 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | NABench SELEX-ZS-NDCG: Overall fitness prediction on NABench SELEX assays, Zero-shot NDCG, NABench SELEX assays (NABench split) | Not reported | Not reported | Not reported | Not reported | Not reported | 0.194 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | NABench ZS-AUC-APTAMER: Fitness prediction on aptamer assays, zero-shot, NABench aptamer assays (NABench split) | Not reported | 0.578 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | NABench ZS-AUC-ENHANCER: Fitness prediction on enhancer assays, zero-shot, NABench enhancer assays (NABench split) | Not reported | 0.529 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | NABench ZS-AUC-MRNA: Fitness prediction on mRNA assays, zero-shot, NABench mRNA assays (NABench split) | Not reported | 0.638 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | NABench ZS-AUC-PROMOTER: Fitness prediction on promoter assays, zero-shot, NABench promoter assays (NABench split) | Not reported | 0.555 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | NABench ZS-AUC-RIBOZYME: Fitness prediction on ribozyme assays, zero-shot, NABench ribozyme assays (NABench split) | Not reported | 0.559 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| RNA-FMEvaluation | NABench ZS-AUC-TRNA: Fitness prediction on tRNA assays, zero-shot, NABench tRNA assays (NABench split) | Not reported | 0.682 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
All 67 result rows with coverage, uncertainty and sources
Filter evaluations
Applied filters: All linked evaluations
| Tested configuration | Protocol and dataset | Finding | Evidence and details |
|---|---|---|---|
| Configuration: RNA-FM | Task: BEACON APA: Alternative polyadenylation isoform prediction Dataset subset: APARENT (BEACON split) | 70.32(0.97) R² unitless · higher Uncertainty: SD 0.97 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRNA-FM on BEACON APA: Alternative polyadenylation isoform prediction BEACON harness, fixed downstream head per task. Train/validation/test 145,463/33,170/49,755; dataset APARENT. Aggregation: Not reported BEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(RNA-FM),column(APA) |
| Configuration: RNA-FM | Task: BEACON CMP: Contact map prediction Dataset subset: RNAcontact (BEACON split) | 47.56(6.73)% Precision at l percent · higher Uncertainty: SD 6.73 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRNA-FM on BEACON CMP: Contact map prediction BEACON harness, fixed downstream head per task. Train/validation/test 188/23/80; dataset RNAcontact. Aggregation: Not reported BEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(RNA-FM),column(CMP) |
| Configuration: RNA-FM | Task: BEACON CRI-Off: CRISPR off-target effect prediction Dataset subset: DeepCRISPR (BEACON split) | 2.49(1.56) Spearman unitless · higher Uncertainty: SD 1.56 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRNA-FM on BEACON CRI-Off: CRISPR off-target effect prediction BEACON harness, fixed downstream head per task. Train/validation/test 14,223/2,032/4,064; dataset DeepCRISPR. Aggregation: Not reported BEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(RNA-FM),column(CRI-Off) |
| Configuration: RNA-FM | Task: BEACON CRI-On: CRISPR on-target efficiency prediction Dataset subset: DeepCRISPR (BEACON split) | 31.62(1.16) Spearman unitless · higher Uncertainty: SD 1.16 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRNA-FM on BEACON CRI-On: CRISPR on-target efficiency prediction BEACON harness, fixed downstream head per task. Train/validation/test 1,453/207/416; dataset DeepCRISPR. Aggregation: Not reported BEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(RNA-FM),column(CRI-On) |
| Configuration: RNA-FM | Task: BEACON DMP: Distance map prediction Dataset subset: RNAcontact (BEACON split) | 51.45(0.51) R² unitless · higher Uncertainty: SD 0.51 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRNA-FM on BEACON DMP: Distance map prediction BEACON harness, fixed downstream head per task. Train/validation/test 188/23/80; dataset RNAcontact. Aggregation: Not reported BEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(RNA-FM),column(DMP) |
| Configuration: RNA-FM | Task: BEACON Modif: RNA modification site prediction Dataset subset: MultiRM (BEACON split) | 94.98(0.042) AUROC unitless · higher Uncertainty: SD 0.042 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRNA-FM on BEACON Modif: RNA modification site prediction BEACON harness, fixed downstream head per task. Train/validation/test 304,661/3,599/1,200; dataset MultiRM. Aggregation: Not reported BEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(RNA-FM),column(Modif) |
| Configuration: RNA-FM | Task: BEACON MRL: Mean ribosome loading prediction Dataset subset: Optimus (BEACON split) | 79.47(0.47) R² unitless · higher Uncertainty: SD 0.47 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRNA-FM on BEACON MRL: Mean ribosome loading prediction BEACON harness, fixed downstream head per task. Train/validation/test 76,319/7,600/7,600; dataset Optimus. Aggregation: Not reported BEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(RNA-FM),column(MRL) |
| Configuration: RNA-FM | Task: BEACON ncRNA: Non-coding RNA family classification Dataset subset: Noorul's ncRNA set (BEACON split) | 96.81(0.061)% Accuracy percent · higher Uncertainty: SD 0.061 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRNA-FM on BEACON ncRNA: Non-coding RNA family classification BEACON harness, fixed downstream head per task. Train/validation/test 5,679/650/2,400; dataset Noorul's ncRNA set. Aggregation: Not reported BEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(RNA-FM),column(ncRNA) |
| Configuration: RNA-FM | Task: BEACON PRS: Programmable RNA switch prediction Dataset subset: Angenent-Mari's switch set (BEACON split) | 55.98(0.09) R² unitless · higher Uncertainty: SD 0.09 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRNA-FM on BEACON PRS: Programmable RNA switch prediction BEACON harness, fixed downstream head per task. Train/validation/test 73,227/9,153/9,154; dataset Angenent-Mari's switch set. Aggregation: Not reported BEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(RNA-FM),column(PRS) |
| Configuration: RNA-FM | Task: BEACON SPL: Splice site prediction Dataset subset: SpliceAI (BEACON split) | 34.84(0.87)% Splice top k accuracy percent · higher Uncertainty: SD 0.87 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRNA-FM on BEACON SPL: Splice site prediction BEACON harness, fixed downstream head per task. Train/validation/test 144,628/18,078/16,505; dataset SpliceAI. Aggregation: Not reported BEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(RNA-FM),column(SPL) |
| Configuration: RNA-FM | Task: BEACON SSI: Structure score imputation Dataset subset: StructureImpute (BEACON split) | 42.36(0.24) R² unitless · higher Uncertainty: SD 0.24 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRNA-FM on BEACON SSI: Structure score imputation BEACON harness, fixed downstream head per task. Train/validation/test 14,049/1,756/3,095; dataset StructureImpute. Aggregation: Not reported BEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(RNA-FM),column(SSI) |
| Configuration: RNA-FM | Task: BEACON SSP: Secondary structure prediction Dataset subset: bpRNA-1m (BEACON split) | 68.50(0.54)% F1 (base pairs; binary F1 over all position pairs pooled across the test set; threshold 0.5) percent · higher Uncertainty: SD 0.54 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRNA-FM on BEACON SSP: Secondary structure prediction BEACON harness, fixed downstream head per task. Train/validation/test 10,814/1,300/1,305; dataset bpRNA-1m. Aggregation: Not reported BEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(RNA-FM),column(SSP) |
| Configuration: RNA-FM | Task: BEACON VDP: Vaccine degradation prediction Dataset subset: OpenVaccine (BEACON split) | 0.347(0.003) Mean columnwise RMSE unit-unreported · lower Uncertainty: SD 0.003 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRNA-FM on BEACON VDP: Vaccine degradation prediction BEACON harness, fixed downstream head per task. Train/validation/test 2,155/245/629; dataset OpenVaccine. Aggregation: Not reported BEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(RNA-FM),column(VDP) |
| Configuration: RNA-FM | Task: Mean ribosome load from MPRA Dataset: mRNABench MRL-MPRA | 0.49 Pearson unitless · unknown Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceRNA-FM: Mean ribosome load from MPRA Linear probe; mean across ten random seeds. Aggregation: Not reported mRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, RNA-FM row, MRL MPRA column |
| Configuration: RNA-FM | Task: mRNABench ECLIP: eCLIP binding site prediction Dataset subset: mRNABench eCLIP (mRNABench split) | 35% AUPRC percent · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRNA-FM on mRNABench ECLIP: eCLIP binding site prediction A linear probe over frozen embeddings, scored as the mean over ten random seeds. Aggregation: Not reported mRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(RNA-FM), column(eCLIP) |
| Configuration: RNA-FM | Task: mRNABench GO: Gene Ontology term prediction Dataset subset: mRNABench GO (mRNABench split) | 32.2% AUPRC percent · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRNA-FM on mRNABench GO: Gene Ontology term prediction A linear probe over frozen embeddings, scored as the mean over ten random seeds. Aggregation: Not reported mRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(RNA-FM), column(GO) |
| Configuration: RNA-FM | Task: mRNABench HL: mRNA half life Dataset subset: mRNABench HL (mRNABench split) | 0.47 Pearson unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRNA-FM on mRNABench HL: mRNA half life A linear probe over frozen embeddings, scored as the mean over ten random seeds. Aggregation: Not reported mRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(RNA-FM), column(HL) |
| Configuration: RNA-FM | Task: mRNABench MRL-HL-PAIR: Paired mean ribosome load and half life Dataset subset: mRNABench MRL-HL-Pair (mRNABench split) | 0.49 Pearson unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRNA-FM on mRNABench MRL-HL-PAIR: Paired mean ribosome load and half life A linear probe over frozen embeddings, scored as the mean over ten random seeds. Aggregation: Not reported mRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(RNA-FM), column(MRL-HL-Pair) |
| Configuration: RNA-FM | Task: mRNABench MRL-MPRA: Mean ribosome load on an MPRA library Dataset subset: mRNABench MRL MPRA (mRNABench split) | 0.49 Pearson unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRNA-FM on mRNABench MRL-MPRA: Mean ribosome load on an MPRA library A linear probe over frozen embeddings, scored as the mean over ten random seeds. Aggregation: Not reported mRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(RNA-FM), column(MRL MPRA) |
| Configuration: RNA-FM | Task: mRNABench MRL: Mean ribosome load Dataset subset: mRNABench MRL (mRNABench split) | 0.29 Pearson unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRNA-FM on mRNABench MRL: Mean ribosome load A linear probe over frozen embeddings, scored as the mean over ten random seeds. Aggregation: Not reported mRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(RNA-FM), column(MRL) |
| Configuration: RNA-FM | Task: mRNABench MRNA-LOC-LR: mRNA localisation, long range Dataset subset: mRNABench mRNA Loc-LR (mRNABench split) | 74.3% AUPRC percent · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRNA-FM on mRNABench MRNA-LOC-LR: mRNA localisation, long range A linear probe over frozen embeddings, scored as the mean over ten random seeds. Aggregation: Not reported mRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(RNA-FM), column(mRNA Loc-LR) |
| Configuration: RNA-FM | Task: mRNABench MRNA-LOC-SR: mRNA localisation, short range Dataset subset: mRNABench mRNA Loc-SR (mRNABench split) | 67% AUPRC percent · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRNA-FM on mRNABench MRNA-LOC-SR: mRNA localisation, short range A linear probe over frozen embeddings, scored as the mean over ten random seeds. Aggregation: Not reported mRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(RNA-FM), column(mRNA Loc-SR) |
| Configuration: RNA-FM | Task: mRNABench PROT-LOC: Protein localisation Dataset subset: mRNABench Prot Loc (mRNABench split) | 32.2% AUPRC percent · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRNA-FM on mRNABench PROT-LOC: Protein localisation A linear probe over frozen embeddings, scored as the mean over ten random seeds. Aggregation: Not reported mRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(RNA-FM), column(Prot Loc) |
| Configuration: RNA-FM | Task: mRNABench VEP: Variant effect prediction Dataset subset: mRNABench VEP (mRNABench split) | 25.7% AUPRC percent · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRNA-FM on mRNABench VEP: Variant effect prediction A linear probe over frozen embeddings, scored as the mean over ten random seeds. Aggregation: Not reported mRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, row(RNA-FM), column(VEP) |
| Configuration: RNA-FM | Task: NABench CCV-CORR-APTAMER: Fitness prediction on aptamer assays, supervised, contiguous cross validation Dataset subset: NABench aptamer assays (NABench split) | 0.115 Spearman unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceScored supervised, contiguous cross validation across the NABench aptamer assays. Aggregation: Not reported NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction · Table 11, row(RNA-FM), column(aptamer) |
Source checking is not independent reproduction. Release 2026-11-02-a7f03c9e55a5.
Further results on linked records
5 linked records have results that are not included above, because no reviewed claim yet ties the link to this model. Each record keeps its own settings and evaluations, and its scores are on its own page.
- RNA-FM (Evo 2 paper variant effect evaluations) Configuration · configuration of this model · 26 evaluations · 52 results
- RNAFM fine-tuned with an appended convolutional layer (You et al. 2026) Configuration · configuration of this model · 6 evaluations · 15 results
- RNA-FM (ViroBench classification) Configuration · configuration of this model · 12 evaluations · 12 results
- RNA-FM (RNAGym fitness leaderboard v0.1.1) Configuration · configuration of this model · 4 evaluations · 4 results
- RNA-FM (zero-shot, Wang et al. 2026) Configuration · configuration of this model · 36 evaluations · 36 results
Related configurations, pipelines and services
These configurations, services and pipelines use this model within their own configurations. Their results, where available, are not assigned to the underlying model.
- rna-fm Pipeline · 8 results
Use this model
How it works, versions and access
Versions and evaluated configurations
How it works
How it works
RNA-FM converts an RNA sequence into one token per nucleotide. Twelve transformer encoder blocks use self-attention to produce a 640-dimensional representation at each position. During pretraining, the model learns to recover masked nucleotides from their surrounding sequence. The resulting representations can be supplied to a separately specified downstream model; they are not, by themselves, a structure or functional prediction.
Sources
RNA-FM original methods, arXiv v5 · arXiv:2204.00300v5, Methods: ncRNA data collection and preprocessing and RNA foundation model training details (p.22)Versions and reproducibility
The nucleotide-based rna_fm_t12 and codon-based mrna_fm_t12 interfaces are distinct. The original RNA-FM paper sets a training input-length limit of 1,024 and describes a usable limit of 1,022 nucleotides. That limit should not be assigned to mRNA-FM without checking its separate configuration.
Sources (3)
ml4bio/RNA-FM: README.md; ml4bio/RNA-FM: fm/pretrained.py; RNA-FM original methods, arXiv v5 · Official README: Quick Start and RNA-FM/mRNA-FM examples; arXiv:2204.00300v5, Methods: training input length and SARS-CoV-2 genome embedding extraction (pp.22–23)Strengths, limitations and unresolved questions
Strengths and limitations
Strengths and considerations
- The repository exposes embedding extraction and examples for downstream RNA analyses.
Sources (2)
ml4bio/RNA-FM: README.md; ml4bio/RNA-FM: fm/pretrained.py · README.md: Quick Start, embedding examples and RNA foundation model comparison table
Limitations and conditions
- Base-level RNA-FM and codon-level mRNA-FM are not interchangeable. The task head and tokenization must be specified in each evaluation.
Sources (2)
ml4bio/RNA-FM: README.md; ml4bio/RNA-FM: fm/pretrained.py · README.md: Quick Start, embedding examples and RNA foundation model comparison table
Profile review details
Follow-up review of Checkpoint identification, Training cutoff, Weights licence. Source locations and before/after decisions are recorded in the 23 September profile-evidence audit. Other explanatory content retains its earlier source scope. No human scientific review or independent reproduction is implied.
Stable record: discovery-model-rna-fmSpecifications
Inputs, training, access and other details
Explanatory profile: limited source coverage · Automated source review, 2026-09-23. Review applies to the cited claims; unresolved fields are listed below. Numerical results retain their own review status.
| Property | Description and evidence |
|---|---|
| Model type | Masked-token RNA transformer encoderSources (2)ml4bio/RNA-FM: README.md; ml4bio/RNA-FM: fm/pretrained.py · README.md: Quick Start, embedding examples and RNA foundation model comparison table |
| Architecture | 12-layer masked-token transformer encoder with hidden width 640 and 20 attention heads; nucleotide tokens produce contextual representations.SourcesRNA-FM original methods, arXiv v5 · arXiv:2204.00300v5, Methods: ncRNA data collection and preprocessing and RNA foundation model training details (p.22) |
| Inputs | RNA sequences tokenized at nucleotide resolution.Sources (2)ml4bio/RNA-FM: README.md; ml4bio/RNA-FM: fm/pretrained.py · README.md: Quick Start, embedding examples and RNA foundation model comparison table |
| Outputs | Contextual token embeddings for a specified downstream RNA task.Sources (2)ml4bio/RNA-FM: README.md; ml4bio/RNA-FM: fm/pretrained.py · README.md: Quick Start, embedding examples and RNA foundation model comparison table |
| Parameters | 99M, as printed in the official Foundation Models table.Sources (2)ml4bio/RNA-FM: README.md; ml4bio/RNA-FM: fm/pretrained.py · README.md: Quick Start, embedding examples and RNA foundation model comparison table |
| Known versions | rna_fm_t12 and mrna_fm_t12 are separate pretrained interfaces.Sources (2)ml4bio/RNA-FM: README.md; ml4bio/RNA-FM: fm/pretrained.py · README.md: Quick Start, embedding examples and RNA foundation model comparison table |
| Training data | 23.7 million non-coding RNA sequences collected from RNAcentral. The authors replace T with U and remove identical sequences using CD-HIT-EST at 100% identity, naming the resulting corpus RNAcentral100.SourcesRNA-FM original methods, arXiv v5 · arXiv:2204.00300v5, Methods: ncRNA data collection and preprocessing and RNA foundation model training details (p.22) |
| Training cutoff | The original Methods describe RNAcentral100 preprocessing but do not establish a dated RNAcentral release. RNAcentral100 is a processed-corpus label, not a release number. · Not reported in inspected sourcesSourcesRNA-FM original methods, arXiv v5 · arXiv2204.00300v5, Methods: Large-scale pre-training dataset, p22 |
| Context limits | The original paper sets a training input-length limit of 1,024 and describes a usable input limit of 1,022 nucleotides. These are the original RNA-FM settings, not a validated limit for later codon-based mRNA-FM checkpoints.SourcesRNA-FM original methods, arXiv v5 · arXiv:2204.00300v5, Methods: RNA foundation model training details (pp.22–23) and RNA-FM application input-limit statement (p.23) |
| Weights licence | The official model-comparison table labels RNA-FM MIT, while the README footer explicitly refers to source code. Separate checkpoint-distribution terms remain unverified; the linked weight repository could not be retrieved during this review. · Not reported in inspected sourcesSources (3)ml4bio/RNA-FM: README.md; ml4bio/RNA-FM: LICENSE; rnafm loader: primary artifact · README: Related RNA Language Models, RNA-FM row; License footer; LICENSE. Linked https://huggingface.co/ml4bio/RNA-FM returned HTTP401 during the review. |
| Access | Official project documentation and implementation: https://github.com/ml4bio/RNA-FMSources (2)ml4bio/RNA-FM: README.md; ml4bio/RNA-FM: fm/pretrained.py · README.md: Quick Start, embedding examples and RNA foundation model comparison table |
| Code licence | MITSourcesml4bio/RNA-FM: LICENSE · LICENSE: licence text |
| Checkpoint identification | The official rna_fm_t12 loader downloads RNA-FM_pretrained.pth from the authors’ server. The inspected loader does not pin a checkpoint revision or publish a digest; a code commit alone cannot identify the bytes used by a published evaluation. · Not reported in inspected sourcesSourcesrnafm loader: primary artifact · load_fm_model_and_alphabet_hub: rna_fm_t12 branch, lines155–162 |
Applicable tests and references
Applicability is distinct from a completed evaluation.
- BEACON · Proposed association
Evidence
Source checking verifies the cited claim or transcription. It does not establish independent reproduction.
Evidence table
Inspect claims, sources and review details
Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.
One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.
37 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Diagram caption Conceptual summary of the documented data flow; optional inputs and configured downstream stages must be reported for a reproducible evaluation. Individual claims | ml4bio/RNA-FM: fm/pretrained.py README.md: Quick Start, embedding examples and RNA foundation model comparison table Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 348951516e0963d22bbb33b3c9fc18c89081d38e | source checked automated source review · 2026-09-23 Audit detailsFollow-up review of Checkpoint identification, Training cutoff, Weights licence. Source locations and before/after decisions are recorded in the 23 September profile-evidence audit. Other explanatory content retains its earlier source scope. No human scientific review or independent reproduction is implied. Field: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
| Diagram caption Conceptual summary of the documented data flow; optional inputs and configured downstream stages must be reported for a reproducible evaluation. Individual claims | ml4bio/RNA-FM: README.md README.md: Quick Start, embedding examples and RNA foundation model comparison table Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 348951516e0963d22bbb33b3c9fc18c89081d38e | source checked automated source review · 2026-09-23 Audit detailsFollow-up review of Checkpoint identification, Training cutoff, Weights licence. Source locations and before/after decisions are recorded in the 23 September profile-evidence audit. Other explanatory content retains its earlier source scope. No human scientific review or independent reproduction is implied. Field: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
Diagram steps
| ml4bio/RNA-FM: fm/pretrained.py README.md: Quick Start, embedding examples and RNA foundation model comparison table Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 348951516e0963d22bbb33b3c9fc18c89081d38e | source checked automated source review · 2026-09-23 Audit detailsFollow-up review of Checkpoint identification, Training cutoff, Weights licence. Source locations and before/after decisions are recorded in the 23 September profile-evidence audit. Other explanatory content retains its earlier source scope. No human scientific review or independent reproduction is implied. Field: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
Diagram steps
| ml4bio/RNA-FM: README.md README.md: Quick Start, embedding examples and RNA foundation model comparison table Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 348951516e0963d22bbb33b3c9fc18c89081d38e | source checked automated source review · 2026-09-23 Audit detailsFollow-up review of Checkpoint identification, Training cutoff, Weights licence. Source locations and before/after decisions are recorded in the 23 September profile-evidence audit. Other explanatory content retains its earlier source scope. No human scientific review or independent reproduction is implied. Field: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
| Diagram title RNA-FM workflow Individual claims | ml4bio/RNA-FM: fm/pretrained.py README.md: Quick Start, embedding examples and RNA foundation model comparison table Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 348951516e0963d22bbb33b3c9fc18c89081d38e | source checked automated source review · 2026-09-23 Audit detailsFollow-up review of Checkpoint identification, Training cutoff, Weights licence. Source locations and before/after decisions are recorded in the 23 September profile-evidence audit. Other explanatory content retains its earlier source scope. No human scientific review or independent reproduction is implied. Field: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
| Diagram title RNA-FM workflow Individual claims | ml4bio/RNA-FM: README.md README.md: Quick Start, embedding examples and RNA foundation model comparison table Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 348951516e0963d22bbb33b3c9fc18c89081d38e | source checked automated source review · 2026-09-23 Audit detailsFollow-up review of Checkpoint identification, Training cutoff, Weights licence. Source locations and before/after decisions are recorded in the 23 September profile-evidence audit. Other explanatory content retains its earlier source scope. No human scientific review or independent reproduction is implied. Field: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
| Model type Masked-token RNA transformer encoder Individual claims | ml4bio/RNA-FM: fm/pretrained.py README.md: Quick Start, embedding examples and RNA foundation model comparison table Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 348951516e0963d22bbb33b3c9fc18c89081d38e | source checked automated source review · 2026-09-23 Audit detailsFollow-up review of Checkpoint identification, Training cutoff, Weights licence. Source locations and before/after decisions are recorded in the 23 September profile-evidence audit. Other explanatory content retains its earlier source scope. No human scientific review or independent reproduction is implied. Field: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
| Model type Masked-token RNA transformer encoder Individual claims | ml4bio/RNA-FM: README.md README.md: Quick Start, embedding examples and RNA foundation model comparison table Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 348951516e0963d22bbb33b3c9fc18c89081d38e | source checked automated source review · 2026-09-23 Audit detailsFollow-up review of Checkpoint identification, Training cutoff, Weights licence. Source locations and before/after decisions are recorded in the 23 September profile-evidence audit. Other explanatory content retains its earlier source scope. No human scientific review or independent reproduction is implied. Field: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
| Architecture 12-layer masked-token transformer encoder with hidden width 640 and 20 attention heads; nucleotide tokens produce contextual representations. Individual claims | RNA-FM original methods, arXiv v5 arXiv:2204.00300v5, Methods: ncRNA data collection and preprocessing and RNA foundation model training details (p.22) Version: 2204.00300v5 | source checked automated source review · 2026-09-23 Audit detailsFollow-up review of Checkpoint identification, Training cutoff, Weights licence. Source locations and before/after decisions are recorded in the 23 September profile-evidence audit. Other explanatory content retains its earlier source scope. No human scientific review or independent reproduction is implied. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record Format: original_pdf |
| Access Official project documentation and implementation: https://github.com/ml4bio/RNA-FM Individual claims | ml4bio/RNA-FM: fm/pretrained.py README.md: Quick Start, embedding examples and RNA foundation model comparison table Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 348951516e0963d22bbb33b3c9fc18c89081d38e | source checked automated source review · 2026-09-23 Audit detailsFollow-up review of Checkpoint identification, Training cutoff, Weights licence. Source locations and before/after decisions are recorded in the 23 September profile-evidence audit. Other explanatory content retains its earlier source scope. No human scientific review or independent reproduction is implied. Field: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
Sources and history
Release 2026-11-02-a7f03c9e55a5 · Record review: discovered
6 source records and release history
- ml4bio/RNA-FM official source · Original source · 348951516e0963d22bbb33b3c9fc18c89081d38e
- RNA-FM original methods, arXiv v5 · Original source · 2204.00300v5
- ml4bio/RNA-FM: README.md · Original source · 348951516e0963d22bbb33b3c9fc18c89081d38e
- ml4bio/RNA-FM: fm/pretrained.py · Original source · 348951516e0963d22bbb33b3c9fc18c89081d38e
- ml4bio/RNA-FM: LICENSE · Original source · 348951516e0963d22bbb33b3c9fc18c89081d38e
- rnafm loader: primary artifact · Original source · 348951516e0963d22bbb33b3c9fc18c89081d38e
Technical metadata and extraction receipts
Stable ID: discovery-model-rna-fm
- areas
- rna-transcriptomes
- access
- official_source_linked
- candidate benchmark ids
- discovery-benchmark-beacon
- entity level
- family
- reported name
- RNA-FM
- entity classification
- review date: 2026-09-17; rationale: The cited profile describes a named learned biological predictor or representation model/family. Preserve this identity separately from task-specific fitting, individual checkpoints, pipelines and hosted access.; source ids: evidence-final-model-rna-fm-paper; evidence-official-fd8e332abdf04a75195b; evidence-official-e17e3864c464d981afc7; source locator: arXiv:2204.00300v5, Methods: ncRNA data collection and preprocessing and RNA foundation model training details (p.22) | README.md: Quick Start, embedding examples and RNA foundation model comparison table; ambiguities: None recorded
- missing metadata
- version: reason: unextracted
Related records
- applicable to: BEACON
- family: RNA-FM
- variant of: mRNA-FM
- family: RNA-FM
- alias of: RNA-FM
- configuration of: RNA-FM (Evo 2 paper variant effect evaluations)
- configuration of: RNAFM fine-tuned with an appended convolutional layer (You et al. 2026)
- configuration of: RNA-FM (ViroBench classification)
- configuration of: RNA-FM (RNAGym fitness leaderboard v0.1.1)
- configuration of: RNA-FM (zero-shot, Wang et al. 2026)
- family: RNA-FM
- uses model: rna-fm
- family: RNA-FM
- family: RNA-FM