Protocol

Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, F1 (mean over repeated random samplings of sequence pairs)

Zero-shot: cosine similarity of FFT-reduced last-hidden-state embeddings; F1 reported as mean over repeated random samplings of sequence pairs (Supplementary Table 7).

37 evaluations · 37 results

Overview

An explanatory profile has not yet been reviewed for this record.

Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.

37 recorded evaluations, 37 metric rows. A comparison chart has not yet been validated for these results. The table retains the individual findings and their sources.

View coverage and remaining gaps across all benchmarks

Results

Results are available, but no reviewed comparison panel is linked in this release.

All evaluations

37 evaluations · 37 results. Different protocols are not a single leaderboard.

Protocol: Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, F1 (mean over repeated random samplings of sequence pairs) · Dataset: ArchiveII-Nr (1273 RNAs) (Wang et al. 2026)

Sorted by F1 (FFT embedding; mean over random samplings of sequence pairs) (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	F1 (FFT embedding; mean over random samplings of sequence pairs)
ProtRNA (zero-shot, Wang et al. 2026)Evaluation	0.809±0.001 (best in column)
RNA-FM (zero-shot, Wang et al. 2026)Evaluation	0.789±0.001
AIDO.RNA (650M) (zero-shot, Wang et al. 2026)Evaluation	0.782±0.001
AIDO.RNA (1.6B) (zero-shot, Wang et al. 2026)Evaluation	0.767±0.001
Uni-RNA (L8) (zero-shot, Wang et al. 2026)Evaluation	0.751±0.001
Uni-RNA (L16) (zero-shot, Wang et al. 2026)Evaluation	0.750±0.001
Uni-RNA (L12) (zero-shot, Wang et al. 2026)Evaluation	0.747±0.001
BiRNA-BERT (NUC) (zero-shot, Wang et al. 2026)Evaluation	0.735±0.001
LAMAR (2k) (zero-shot, Wang et al. 2026)Evaluation	0.724±0.001
ERNIE-RNA (zero-shot, Wang et al. 2026)Evaluation	0.721±0.002
MP-RNA (zero-shot, Wang et al. 2026)Evaluation	0.719±0.001
RNABERT (zero-shot, Wang et al. 2026)Evaluation	0.719±0.001
LAMAR (4k) (zero-shot, Wang et al. 2026)Evaluation	0.715±0.001
RNAErnie (zero-shot, Wang et al. 2026)Evaluation	0.713±0.001
SpliceBERT (zero-shot, Wang et al. 2026)Evaluation	0.712±0.000
RNA-km (zero-shot, Wang et al. 2026)Evaluation	0.701±0.001
DGRNA (zero-shot, Wang et al. 2026)Evaluation	0.698±0.001
BiRNA-BERT (BPE) (zero-shot, Wang et al. 2026)Evaluation	0.685±0.000
LucaOne (D17.6M) (zero-shot, Wang et al. 2026)Evaluation	0.677±0.000
NT (zero-shot, Wang et al. 2026)Evaluation	0.672±0.001
RiNALMo (mega) (zero-shot, Wang et al. 2026)Evaluation	0.672±0.001
RiNALMo (micro) (zero-shot, Wang et al. 2026)Evaluation	0.672±0.002
UTR_LM (zero-shot, Wang et al. 2026)Evaluation	0.669±0.000
DNABERT-2 (zero-shot, Wang et al. 2026)Evaluation	0.668±0.000
3UTRBERT (K3) (zero-shot, Wang et al. 2026)Evaluation	0.667±0.000
3UTRBERT (K4) (zero-shot, Wang et al. 2026)Evaluation	0.667±0.000
3UTRBERT (K6) (zero-shot, Wang et al. 2026)Evaluation	0.667±0.000
DNABERT (k=3) (zero-shot, Wang et al. 2026)Evaluation	0.667±0.000
LucaOne (D36.0M) (zero-shot, Wang et al. 2026)Evaluation	0.667±0.000
PlantRNA-FM (zero-shot, Wang et al. 2026)Evaluation	0.667±0.000
RFamLlama (Base) (zero-shot, Wang et al. 2026)Evaluation	0.667±0.000
RFamLlama (Large) (zero-shot, Wang et al. 2026)Evaluation	0.667±0.000
RiNALMo (giga) (zero-shot, Wang et al. 2026)Evaluation	0.667±0.000
LucaOne (G36.8M) (zero-shot, Wang et al. 2026)Evaluation	0.666±0.001
3UTRBERT (K5) (zero-shot, Wang et al. 2026)Evaluation	0.657±0.000
GenerRNA (zero-shot, Wang et al. 2026)Evaluation	0.657±0.001
DNABERT (k=6) (zero-shot, Wang et al. 2026)Evaluation	0.654±0.001

All 37 result rows with coverage, uncertainty and sources

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configuration	Protocol and dataset	Finding	Evidence and details
Configuration: 3UTRBERT (K3) (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, F1 (mean over repeated random samplings of sequence pairs) Dataset: ArchiveII-Nr (1273 RNAs) (Wang et al. 2026)	0.667±0.000 F1 (FFT embedding; mean over random samplings of sequence pairs) unitless · higher Uncertainty: SD 0.000 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source 3UTRBERT (K3) zero-shot RNA type classification on ArchiveII-Nr (1273 RNAs) (FFT embedding, F1, sampled-mean) lit-rna-20261011-rnalm-zeroshot-protocol-t7-f1-sampled-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 7, row '3UTRBERT (K3)', column 'F1'
Configuration: 3UTRBERT (K4) (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, F1 (mean over repeated random samplings of sequence pairs) Dataset: ArchiveII-Nr (1273 RNAs) (Wang et al. 2026)	0.667±0.000 F1 (FFT embedding; mean over random samplings of sequence pairs) unitless · higher Uncertainty: SD 0.000 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source 3UTRBERT (K4) zero-shot RNA type classification on ArchiveII-Nr (1273 RNAs) (FFT embedding, F1, sampled-mean) lit-rna-20261011-rnalm-zeroshot-protocol-t7-f1-sampled-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 7, row '3UTRBERT (K4)', column 'F1'
Configuration: 3UTRBERT (K5) (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, F1 (mean over repeated random samplings of sequence pairs) Dataset: ArchiveII-Nr (1273 RNAs) (Wang et al. 2026)	0.657±0.000 F1 (FFT embedding; mean over random samplings of sequence pairs) unitless · higher Uncertainty: SD 0.000 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source 3UTRBERT (K5) zero-shot RNA type classification on ArchiveII-Nr (1273 RNAs) (FFT embedding, F1, sampled-mean) lit-rna-20261011-rnalm-zeroshot-protocol-t7-f1-sampled-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 7, row '3UTRBERT (K5)', column 'F1'
Configuration: 3UTRBERT (K6) (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, F1 (mean over repeated random samplings of sequence pairs) Dataset: ArchiveII-Nr (1273 RNAs) (Wang et al. 2026)	0.667±0.000 F1 (FFT embedding; mean over random samplings of sequence pairs) unitless · higher Uncertainty: SD 0.000 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source 3UTRBERT (K6) zero-shot RNA type classification on ArchiveII-Nr (1273 RNAs) (FFT embedding, F1, sampled-mean) lit-rna-20261011-rnalm-zeroshot-protocol-t7-f1-sampled-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 7, row '3UTRBERT (K6)', column 'F1'
Configuration: AIDO.RNA (1.6B) (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, F1 (mean over repeated random samplings of sequence pairs) Dataset: ArchiveII-Nr (1273 RNAs) (Wang et al. 2026)	0.767±0.001 F1 (FFT embedding; mean over random samplings of sequence pairs) unitless · higher Uncertainty: SD 0.001 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source AIDO.RNA (1.6B) zero-shot RNA type classification on ArchiveII-Nr (1273 RNAs) (FFT embedding, F1, sampled-mean) lit-rna-20261011-rnalm-zeroshot-protocol-t7-f1-sampled-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 7, row 'AIDO.RNA (1.6B)', column 'F1'
Configuration: AIDO.RNA (650M) (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, F1 (mean over repeated random samplings of sequence pairs) Dataset: ArchiveII-Nr (1273 RNAs) (Wang et al. 2026)	0.782±0.001 F1 (FFT embedding; mean over random samplings of sequence pairs) unitless · higher Uncertainty: SD 0.001 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source AIDO.RNA (650M) zero-shot RNA type classification on ArchiveII-Nr (1273 RNAs) (FFT embedding, F1, sampled-mean) lit-rna-20261011-rnalm-zeroshot-protocol-t7-f1-sampled-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 7, row 'AIDO.RNA (650M)', column 'F1'
Configuration: BiRNA-BERT (BPE) (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, F1 (mean over repeated random samplings of sequence pairs) Dataset: ArchiveII-Nr (1273 RNAs) (Wang et al. 2026)	0.685±0.000 F1 (FFT embedding; mean over random samplings of sequence pairs) unitless · higher Uncertainty: SD 0.000 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source BiRNA-BERT (BPE) zero-shot RNA type classification on ArchiveII-Nr (1273 RNAs) (FFT embedding, F1, sampled-mean) lit-rna-20261011-rnalm-zeroshot-protocol-t7-f1-sampled-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 7, row 'BiRNA-BERT (BPE)', column 'F1'
Configuration: BiRNA-BERT (NUC) (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, F1 (mean over repeated random samplings of sequence pairs) Dataset: ArchiveII-Nr (1273 RNAs) (Wang et al. 2026)	0.735±0.001 F1 (FFT embedding; mean over random samplings of sequence pairs) unitless · higher Uncertainty: SD 0.001 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source BiRNA-BERT (NUC) zero-shot RNA type classification on ArchiveII-Nr (1273 RNAs) (FFT embedding, F1, sampled-mean) lit-rna-20261011-rnalm-zeroshot-protocol-t7-f1-sampled-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 7, row 'BiRNA-BERT (NUC)', column 'F1'
Configuration: DGRNA (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, F1 (mean over repeated random samplings of sequence pairs) Dataset: ArchiveII-Nr (1273 RNAs) (Wang et al. 2026)	0.698±0.001 F1 (FFT embedding; mean over random samplings of sequence pairs) unitless · higher Uncertainty: SD 0.001 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DGRNA zero-shot RNA type classification on ArchiveII-Nr (1273 RNAs) (FFT embedding, F1, sampled-mean) lit-rna-20261011-rnalm-zeroshot-protocol-t7-f1-sampled-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 7, row 'DGRNA', column 'F1'
Configuration: DNABERT-2 (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, F1 (mean over repeated random samplings of sequence pairs) Dataset: ArchiveII-Nr (1273 RNAs) (Wang et al. 2026)	0.668±0.000 F1 (FFT embedding; mean over random samplings of sequence pairs) unitless · higher Uncertainty: SD 0.000 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DNABERT-2 zero-shot RNA type classification on ArchiveII-Nr (1273 RNAs) (FFT embedding, F1, sampled-mean) lit-rna-20261011-rnalm-zeroshot-protocol-t7-f1-sampled-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 7, row 'DNABERT-2', column 'F1'
Configuration: DNABERT (k=3) (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, F1 (mean over repeated random samplings of sequence pairs) Dataset: ArchiveII-Nr (1273 RNAs) (Wang et al. 2026)	0.667±0.000 F1 (FFT embedding; mean over random samplings of sequence pairs) unitless · higher Uncertainty: SD 0.000 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DNABERT (k=3) zero-shot RNA type classification on ArchiveII-Nr (1273 RNAs) (FFT embedding, F1, sampled-mean) lit-rna-20261011-rnalm-zeroshot-protocol-t7-f1-sampled-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 7, row 'DNABERT (k=3)', column 'F1'
Configuration: DNABERT (k=6) (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, F1 (mean over repeated random samplings of sequence pairs) Dataset: ArchiveII-Nr (1273 RNAs) (Wang et al. 2026)	0.654±0.001 F1 (FFT embedding; mean over random samplings of sequence pairs) unitless · higher Uncertainty: SD 0.001 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DNABERT (k=6) zero-shot RNA type classification on ArchiveII-Nr (1273 RNAs) (FFT embedding, F1, sampled-mean) lit-rna-20261011-rnalm-zeroshot-protocol-t7-f1-sampled-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 7, row 'DNABERT (k=6)', column 'F1'
Configuration: ERNIE-RNA (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, F1 (mean over repeated random samplings of sequence pairs) Dataset: ArchiveII-Nr (1273 RNAs) (Wang et al. 2026)	0.721±0.002 F1 (FFT embedding; mean over random samplings of sequence pairs) unitless · higher Uncertainty: SD 0.002 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source ERNIE-RNA zero-shot RNA type classification on ArchiveII-Nr (1273 RNAs) (FFT embedding, F1, sampled-mean) lit-rna-20261011-rnalm-zeroshot-protocol-t7-f1-sampled-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 7, row 'ERNIE-RNA', column 'F1'
Configuration: GenerRNA (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, F1 (mean over repeated random samplings of sequence pairs) Dataset: ArchiveII-Nr (1273 RNAs) (Wang et al. 2026)	0.657±0.001 F1 (FFT embedding; mean over random samplings of sequence pairs) unitless · higher Uncertainty: SD 0.001 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source GenerRNA zero-shot RNA type classification on ArchiveII-Nr (1273 RNAs) (FFT embedding, F1, sampled-mean) lit-rna-20261011-rnalm-zeroshot-protocol-t7-f1-sampled-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 7, row 'GenerRNA', column 'F1'
Configuration: LAMAR (2k) (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, F1 (mean over repeated random samplings of sequence pairs) Dataset: ArchiveII-Nr (1273 RNAs) (Wang et al. 2026)	0.724±0.001 F1 (FFT embedding; mean over random samplings of sequence pairs) unitless · higher Uncertainty: SD 0.001 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source LAMAR (2k) zero-shot RNA type classification on ArchiveII-Nr (1273 RNAs) (FFT embedding, F1, sampled-mean) lit-rna-20261011-rnalm-zeroshot-protocol-t7-f1-sampled-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 7, row 'LAMAR (2k)', column 'F1'
Configuration: LAMAR (4k) (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, F1 (mean over repeated random samplings of sequence pairs) Dataset: ArchiveII-Nr (1273 RNAs) (Wang et al. 2026)	0.715±0.001 F1 (FFT embedding; mean over random samplings of sequence pairs) unitless · higher Uncertainty: SD 0.001 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source LAMAR (4k) zero-shot RNA type classification on ArchiveII-Nr (1273 RNAs) (FFT embedding, F1, sampled-mean) lit-rna-20261011-rnalm-zeroshot-protocol-t7-f1-sampled-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 7, row 'LAMAR (4k)', column 'F1'
Configuration: LucaOne (D17.6M) (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, F1 (mean over repeated random samplings of sequence pairs) Dataset: ArchiveII-Nr (1273 RNAs) (Wang et al. 2026)	0.677±0.000 F1 (FFT embedding; mean over random samplings of sequence pairs) unitless · higher Uncertainty: SD 0.000 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source LucaOne (D17.6M) zero-shot RNA type classification on ArchiveII-Nr (1273 RNAs) (FFT embedding, F1, sampled-mean) lit-rna-20261011-rnalm-zeroshot-protocol-t7-f1-sampled-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 7, row 'LucaOne (D17.6M)', column 'F1'
Configuration: LucaOne (D36.0M) (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, F1 (mean over repeated random samplings of sequence pairs) Dataset: ArchiveII-Nr (1273 RNAs) (Wang et al. 2026)	0.667±0.000 F1 (FFT embedding; mean over random samplings of sequence pairs) unitless · higher Uncertainty: SD 0.000 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source LucaOne (D36.0M) zero-shot RNA type classification on ArchiveII-Nr (1273 RNAs) (FFT embedding, F1, sampled-mean) lit-rna-20261011-rnalm-zeroshot-protocol-t7-f1-sampled-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 7, row 'LucaOne (D36.0M)', column 'F1'
Configuration: LucaOne (G36.8M) (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, F1 (mean over repeated random samplings of sequence pairs) Dataset: ArchiveII-Nr (1273 RNAs) (Wang et al. 2026)	0.666±0.001 F1 (FFT embedding; mean over random samplings of sequence pairs) unitless · higher Uncertainty: SD 0.001 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source LucaOne (G36.8M) zero-shot RNA type classification on ArchiveII-Nr (1273 RNAs) (FFT embedding, F1, sampled-mean) lit-rna-20261011-rnalm-zeroshot-protocol-t7-f1-sampled-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 7, row 'LucaOne (G36.8M)', column 'F1'
Configuration: MP-RNA (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, F1 (mean over repeated random samplings of sequence pairs) Dataset: ArchiveII-Nr (1273 RNAs) (Wang et al. 2026)	0.719±0.001 F1 (FFT embedding; mean over random samplings of sequence pairs) unitless · higher Uncertainty: SD 0.001 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source MP-RNA zero-shot RNA type classification on ArchiveII-Nr (1273 RNAs) (FFT embedding, F1, sampled-mean) lit-rna-20261011-rnalm-zeroshot-protocol-t7-f1-sampled-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 7, row 'MP-RNA', column 'F1'
Configuration: NT (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, F1 (mean over repeated random samplings of sequence pairs) Dataset: ArchiveII-Nr (1273 RNAs) (Wang et al. 2026)	0.672±0.001 F1 (FFT embedding; mean over random samplings of sequence pairs) unitless · higher Uncertainty: SD 0.001 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NT zero-shot RNA type classification on ArchiveII-Nr (1273 RNAs) (FFT embedding, F1, sampled-mean) lit-rna-20261011-rnalm-zeroshot-protocol-t7-f1-sampled-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 7, row 'NT', column 'F1'
Configuration: PlantRNA-FM (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, F1 (mean over repeated random samplings of sequence pairs) Dataset: ArchiveII-Nr (1273 RNAs) (Wang et al. 2026)	0.667±0.000 F1 (FFT embedding; mean over random samplings of sequence pairs) unitless · higher Uncertainty: SD 0.000 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source PlantRNA-FM zero-shot RNA type classification on ArchiveII-Nr (1273 RNAs) (FFT embedding, F1, sampled-mean) lit-rna-20261011-rnalm-zeroshot-protocol-t7-f1-sampled-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 7, row 'PlantRNA-FM', column 'F1'
Configuration: ProtRNA (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, F1 (mean over repeated random samplings of sequence pairs) Dataset: ArchiveII-Nr (1273 RNAs) (Wang et al. 2026)	0.809±0.001 F1 (FFT embedding; mean over random samplings of sequence pairs) unitless · higher Uncertainty: SD 0.001 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source ProtRNA zero-shot RNA type classification on ArchiveII-Nr (1273 RNAs) (FFT embedding, F1, sampled-mean) lit-rna-20261011-rnalm-zeroshot-protocol-t7-f1-sampled-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 7, row 'ProtRNA', column 'F1'
Configuration: RFamLlama (Base) (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, F1 (mean over repeated random samplings of sequence pairs) Dataset: ArchiveII-Nr (1273 RNAs) (Wang et al. 2026)	0.667±0.000 F1 (FFT embedding; mean over random samplings of sequence pairs) unitless · higher Uncertainty: SD 0.000 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source RFamLlama (Base) zero-shot RNA type classification on ArchiveII-Nr (1273 RNAs) (FFT embedding, F1, sampled-mean) lit-rna-20261011-rnalm-zeroshot-protocol-t7-f1-sampled-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 7, row 'RFamLlama (Base)', column 'F1'
Configuration: RFamLlama (Large) (zero-shot, Wang et al. 2026)	Protocol: Wang et al. 2026 zero-shot RNA type classification, ArchiveII-Nr (1273 RNAs), FFT embedding, F1 (mean over repeated random samplings of sequence pairs) Dataset: ArchiveII-Nr (1273 RNAs) (Wang et al. 2026)	0.667±0.000 F1 (FFT embedding; mean over random samplings of sequence pairs) unitless · higher Uncertainty: SD 0.000 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source RFamLlama (Large) zero-shot RNA type classification on ArchiveII-Nr (1273 RNAs) (FFT embedding, F1, sampled-mean) lit-rna-20261011-rnalm-zeroshot-protocol-t7-f1-sampled-mean Aggregation: Not reported Zero-shot benchmarking of RNA language models: Supplementary Information; Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Supplementary Table 7, row 'RFamLlama (Large)', column 'F1'

Source checking is not independent reproduction. Release 2026-10-22-1b7cf027e4f6.

Methods and evaluation design

Procedure, tasks and evaluated configurations

Recorded evaluations

Each evaluation records what was tested and under which conditions.

Explore all linked results

Baseline coverage

Reference methods help show what a model adds beyond simple controls. We track a null control and a conventional method for each protocol.

0 of 2 active baseline roles have published Rewire measurements in this release. Measurements on a selected protocol do not establish coverage of an entire suite.

No execution recipe linked to this protocol. Recipe availability does not establish a completed evaluation.

External evaluations: 37

Literature evidence is not a Rewire measurement. Executed but unpublished runs and private review status are not included.

Null control

Proposed control: requires review

Protocol-valid seeded random ranking; no fitting on assay labels

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

Conventional reference

Proposed control: requires review

Established label-free reference with explicitly permitted sequence/MSA inputs

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

Protocol coverage CSV (gzip) · Model evaluation matrix (gzip) · Source table (gzip) · Release and checksums (gzip)

Coverage is derived from release 2026-10-22-1b7cf027e4f6. Source citations describe the original records; they do not validate an unreviewed baseline proposal. No results have been generated by this audit.

Run instructions

No runnable recipe has been reviewed for this protocol. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.

Strengths, limitations and unresolved questions

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.

0 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-10-22-1b7cf027e4f6
Property and statement	Original source and location	Review and provenance

No evidence rows match these filters. Choose another scope or clear the search.

How to read the evidence

Sources and history

Release 2026-10-22-1b7cf027e4f6 · Record review: source checked

2 source records and release history

Zero-shot benchmarking of RNA language models: Supplementary Information · Original source · bbag098_supplymentary_information_20260209.docx from the Europe PMC supplementary files archive for PMC12963973
Zero-shot benchmarking of RNA language models in structural, functional, and evolutionary learning · Original source · Briefings in Bioinformatics 2026, bbag098 (issue date 2026-03-01); PMC12963973 full-text XML

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: lit-rna-20261011-rnalm-zeroshot-protocol-t7-f1-sampled-mean

areas: rna-transcriptomes
contexts: research
protocol: Zero-shot: cosine similarity of FFT-reduced last-hidden-state embeddings. Metric F1, mean over repeated random samplings of sequence pairs.
version: Wang et al. 2026
metric: f1-score
metric direction: higher
unit: unitless
metric qualifier: FFT embedding; mean over repeated random samplings of sequence pairs
source locator: Supplementary Table 7 caption and column 'F1'; main text Methods
limitations: Zero-shot only; no fine-tuning or task head.; Classification metrics are computed on cosine similarities of sampled homologous versus non-homologous pairs; the threshold used for F1 and MCC is not stated.; Many rows print F1 0.667 with MCC near 0, which is what a classifier that labels every pair homologous scores when the two classes are equal in size; the source does not describe the decision threshold for F1 and MCC.

Related records

Suggest a correction