| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RiNALMo (giga) (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot secondary structure, TS test set (70 PDB structures), attention, F1 score (mean over structures) | F1 (attention; mean over structures) | 0.414±0.255 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RiNALMo (giga) (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot secondary structure, TS test set (70 PDB structures), attention, F1 score (median over structures) | F1 (attention; median over structures) | 0.404 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RiNALMo (giga) (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot secondary structure, TS test set (70 PDB structures), attention, MCC (mean over structures) | MCC (attention; mean over structures) | 0.423±0.257 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RiNALMo (giga) (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot secondary structure, TS test set (70 PDB structures), attention, MCC (median over structures) | MCC (attention; median over structures) | 0.416 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RiNALMo (giga) (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot secondary structure, TS-Hard test set (15 PDB structures), attention, F1 score (mean over structures) | F1 (attention; mean over structures) | 0.365±0.214 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RiNALMo (giga) (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot secondary structure, TS-Hard test set (15 PDB structures), attention, F1 score (median over structures) | F1 (attention; median over structures) | 0.337 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RiNALMo (giga) (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot secondary structure, TS-Hard test set (15 PDB structures), attention, MCC (mean over structures) | MCC (attention; mean over structures) | 0.375±0.222 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RiNALMo (giga) (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot secondary structure, TS-Hard test set (15 PDB structures), attention, MCC (median over structures) | MCC (attention; median over structures) | 0.347 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RiNALMo (giga) (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), FFT embedding, 1 − OR (mean over repeated random samplings of sequence pairs) | One minus overlap ratio (FFT embedding; mean over random samplings of sequence pairs) | 0.790±0.001 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RiNALMo (giga) (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), FFT embedding, AUC (mean over repeated random samplings of sequence pairs) | AUROC (FFT embedding; mean over random samplings of sequence pairs) | 0.896±0.001 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RiNALMo (giga) (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), FFT embedding, F1 (mean over repeated random samplings of sequence pairs) | F1 (FFT embedding; mean over random samplings of sequence pairs) | 0.824±0.001 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RiNALMo (giga) (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), FFT embedding, MCC (mean over repeated random samplings of sequence pairs) | MCC (FFT embedding; mean over random samplings of sequence pairs) | 0.657±0.001 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RiNALMo (giga) (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, AUC (mean over repeated random samplings of sequence pairs) | AUROC (FFT embedding; mean over random samplings of sequence pairs) | 0.705±0.001 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RiNALMo (giga) (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), CLS embedding, 1 − OR (mean over repeated random samplings of sequence pairs) | One minus overlap ratio (CLS embedding; mean over random samplings of sequence pairs) | 0.803±0.001 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RiNALMo (giga) (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), CLS embedding, AUC (mean over repeated random samplings of sequence pairs) | AUROC (CLS embedding; mean over random samplings of sequence pairs) | 0.901±0.000 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RiNALMo (giga) (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), CLS embedding, F1 (mean over repeated random samplings of sequence pairs) | F1 (CLS embedding; mean over random samplings of sequence pairs) | 0.836±0.000 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RiNALMo (giga) (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), CLS embedding, MCC (mean over repeated random samplings of sequence pairs) | MCC (CLS embedding; mean over random samplings of sequence pairs) | 0.667±0.001 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RiNALMo (giga) (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), CLS embedding, AUC (mean over repeated random samplings of sequence pairs) | AUROC (CLS embedding; mean over random samplings of sequence pairs) | 0.721±0.001 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RiNALMo (mega) (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), WT-LLR, AUC (mean over assays) | AUROC (WT-LLR; mean over assays) | 0.588±0.073 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RiNALMo (mega) (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), WT-LLR, AUC (median over assays) | AUROC (WT-LLR; median over assays) | 0.556 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RiNALMo (mega) (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), WT-LLR, MCC (mean over assays) | MCC (WT-LLR; mean over assays) | 0.141±0.108 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RiNALMo (mega) (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), WT-LLR, MCC (median over assays) | MCC (WT-LLR; median over assays) | 0.104 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RiNALMo (mega) (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), WT-LLR, SR (mean over assays) | Absolute spearman correlation (WT-LLR; mean over assays) | 0.178±0.152 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RiNALMo (mega) (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), WT-LLR, SR (median over assays) | Absolute spearman correlation (WT-LLR; median over assays) | 0.114 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RiNALMo (mega) (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, AUC (mean over assays) | AUROC (PLL-D; mean over assays) | 0.584±0.073 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RiNALMo (mega) (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, AUC (median over assays) | AUROC (PLL-D; median over assays) | 0.571 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RiNALMo (mega) (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, MCC (mean over assays) | MCC (PLL-D; mean over assays) | 0.125±0.108 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RiNALMo (mega) (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, MCC (median over assays) | MCC (PLL-D; median over assays) | 0.101 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RiNALMo (mega) (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, SR (mean over assays) | Absolute spearman correlation (PLL-D; mean over assays) | 0.168±0.149 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RiNALMo (mega) (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, SR (median over assays) | Absolute spearman correlation (PLL-D; median over assays) | 0.135 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RiNALMo (mega) (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, F1 (mean over repeated random samplings of sequence pairs) | F1 (FFT embedding; mean over random samplings of sequence pairs) | 0.672±0.001 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RiNALMo (micro) (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, 1 − OR (mean over repeated random samplings of sequence pairs) | One minus overlap ratio (FFT embedding; mean over random samplings of sequence pairs) | 0.621±0.001 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RiNALMo (micro) (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, AUC (mean over repeated random samplings of sequence pairs) | AUROC (FFT embedding; mean over random samplings of sequence pairs) | 0.705±0.001 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RiNALMo (micro) (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, F1 (mean over repeated random samplings of sequence pairs) | F1 (FFT embedding; mean over random samplings of sequence pairs) | 0.672±0.002 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RiNALMo (micro) (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, MCC (mean over repeated random samplings of sequence pairs) | MCC (FFT embedding; mean over random samplings of sequence pairs) | 0.435±0.002 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RiNALMo (micro) (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), CLS embedding, 1 − OR (mean over repeated random samplings of sequence pairs) | One minus overlap ratio (CLS embedding; mean over random samplings of sequence pairs) | 0.659±0.001 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RiNALMo (micro) (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), CLS embedding, F1 (mean over repeated random samplings of sequence pairs) | F1 (CLS embedding; mean over random samplings of sequence pairs) | 0.684±0.002 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RNAErnie (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), WT-LLR, AUC (mean over assays) | AUROC (WT-LLR; mean over assays) | 0.581±0.071 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RNAErnie (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), WT-LLR, AUC (median over assays) | AUROC (WT-LLR; median over assays) | 0.568 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RNAErnie (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), WT-LLR, MCC (mean over assays) | MCC (WT-LLR; mean over assays) | 0.125±0.105 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RNAErnie (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), WT-LLR, MCC (median over assays) | MCC (WT-LLR; median over assays) | 0.099 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RNAErnie (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), WT-LLR, SR (mean over assays) | Absolute spearman correlation (WT-LLR; mean over assays) | 0.162±0.148 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RNAErnie (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), WT-LLR, SR (median over assays) | Absolute spearman correlation (WT-LLR; median over assays) | 0.133 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RNAErnie (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, AUC (mean over assays) | AUROC (PLL-D; mean over assays) | 0.551±0.045 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RNAErnie (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, AUC (median over assays) | AUROC (PLL-D; median over assays) | 0.541 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RNAErnie (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, MCC (mean over assays) | MCC (PLL-D; mean over assays) | 0.076±0.069 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RNAErnie (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, MCC (median over assays) | MCC (PLL-D; median over assays) | 0.051 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RNAErnie (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, SR (mean over assays) | Absolute spearman correlation (PLL-D; mean over assays) | 0.100±0.092 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RNAErnie (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot fitness, RNAGym ncRNA DMS assays (31 assays), PLL-D, SR (median over assays) | Absolute spearman correlation (PLL-D; median over assays) | 0.081 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RNAErnie (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot secondary structure, TS test set (70 PDB structures), attention, F1 score (mean over structures) | F1 (attention; mean over structures) | 0.288±0.223 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RNAErnie (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot secondary structure, TS test set (70 PDB structures), attention, F1 score (median over structures) | F1 (attention; median over structures) | 0.238 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RNAErnie (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot secondary structure, TS test set (70 PDB structures), attention, MCC (mean over structures) | MCC (attention; mean over structures) | 0.290±0.221 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RNAErnie (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot secondary structure, TS test set (70 PDB structures), attention, MCC (median over structures) | MCC (attention; median over structures) | 0.236 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RNAErnie (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot secondary structure, TS-Hard test set (15 PDB structures), attention, F1 score (mean over structures) | F1 (attention; mean over structures) | 0.240±0.152 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RNAErnie (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot secondary structure, TS-Hard test set (15 PDB structures), attention, F1 score (median over structures) | F1 (attention; median over structures) | 0.231 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RNAErnie (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot secondary structure, TS-Hard test set (15 PDB structures), attention, MCC (mean over structures) | MCC (attention; mean over structures) | 0.243±0.152 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RNAErnie (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot secondary structure, TS-Hard test set (15 PDB structures), attention, MCC (median over structures) | MCC (attention; median over structures) | 0.237 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RNAErnie (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), FFT embedding, 1 − OR (mean over repeated random samplings of sequence pairs) | One minus overlap ratio (FFT embedding; mean over random samplings of sequence pairs) | 0.709±0.000 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RNAErnie (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), FFT embedding, AUC (mean over repeated random samplings of sequence pairs) | AUROC (FFT embedding; mean over random samplings of sequence pairs) | 0.854±0.001 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RNAErnie (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), FFT embedding, F1 (mean over repeated random samplings of sequence pairs) | F1 (FFT embedding; mean over random samplings of sequence pairs) | 0.775±0.001 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RNAErnie (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), FFT embedding, MCC (mean over repeated random samplings of sequence pairs) | MCC (FFT embedding; mean over random samplings of sequence pairs) | 0.532±0.001 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RNAErnie (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, 1 − OR (mean over repeated random samplings of sequence pairs) | One minus overlap ratio (FFT embedding; mean over random samplings of sequence pairs) | 0.572±0.002 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RNAErnie (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, AUC (mean over repeated random samplings of sequence pairs) | AUROC (FFT embedding; mean over random samplings of sequence pairs) | 0.765±0.001 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RNAErnie (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, F1 (mean over repeated random samplings of sequence pairs) | F1 (FFT embedding; mean over random samplings of sequence pairs) | 0.713±0.001 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RNAErnie (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, MCC (mean over repeated random samplings of sequence pairs) | MCC (FFT embedding; mean over random samplings of sequence pairs) | 0.367±0.011 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RNAErnie (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), CLS embedding, 1 − OR (mean over repeated random samplings of sequence pairs) | One minus overlap ratio (CLS embedding; mean over random samplings of sequence pairs) | 0.751±0.001 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RNAErnie (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), CLS embedding, AUC (mean over repeated random samplings of sequence pairs) | AUROC (CLS embedding; mean over random samplings of sequence pairs) | 0.880±0.000 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RNAErnie (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), CLS embedding, F1 (mean over repeated random samplings of sequence pairs) | F1 (CLS embedding; mean over random samplings of sequence pairs) | 0.801±0.001 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RNAErnie (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot family classification, RfamSample (561 Rfam families), CLS embedding, MCC (mean over repeated random samplings of sequence pairs) | MCC (CLS embedding; mean over random samplings of sequence pairs) | 0.594±0.002 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RNAErnie (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), CLS embedding, 1 − OR (mean over repeated random samplings of sequence pairs) | One minus overlap ratio (CLS embedding; mean over random samplings of sequence pairs) | 0.612±0.000 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RNAErnie (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), CLS embedding, AUC (mean over repeated random samplings of sequence pairs) | AUROC (CLS embedding; mean over random samplings of sequence pairs) | 0.784±0.001 |
|---|
| Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning | RNAErnie (zero-shot, Wang et al. 2026) | Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), CLS embedding, F1 (mean over repeated random samplings of sequence pairs) | F1 (CLS embedding; mean over random samplings of sequence pairs) | 0.728±0.001 |
|---|