CNN
Supervised architecture trained from scratch per task by the BEACON authors.
Overview
Supervised architecture trained from scratch per task by the BEACON authors.
Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.
Evaluations and results
Release 2026-09-17-1a18ca2c038a · 13 evaluations · 13 metric rows. Different protocols are not a single leaderboard. Where several source tables report the same metric, the published comparisons above offer a pooled view that names what it does not hold constant.
| Metric and finding | Coverage and uncertainty | Evidence |
|---|---|---|
| CNN on BEACON APA: Alternative polyadenylation isoform prediction Method: CNNTask: BEACON APA: Alternative polyadenylation isoform predictionDataset subset: APARENT (BEACON split) BEACON harness, fixed downstream head per task. Train/validation/test 145,463/33,170/49,755; dataset APARENT. Author-reported evaluation · Evaluation metadata: source checked | ||
| 50.93(0.17)% r2 Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 0.17 Scored: Not reported · Eligible: Not reported | source checkedBEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(CNN),column(APA) Source checking is not independent reproduction. |
| CNN on BEACON CMP: Contact map prediction BEACON harness, fixed downstream head per task. Train/validation/test 188/23/80; dataset RNAcontact. Author-reported evaluation · Evaluation metadata: source checked | ||
| 43.89(5.53)% precision_at_l Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 5.53 Scored: Not reported · Eligible: Not reported | source checkedBEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(CNN),column(CMP) Source checking is not independent reproduction. |
| CNN on BEACON CRI-Off: CRISPR off-target effect prediction Method: CNNTask: BEACON CRI-Off: CRISPR off-target effect predictionDataset subset: DeepCRISPR (BEACON split) BEACON harness, fixed downstream head per task. Train/validation/test 14,223/2,032/4,064; dataset DeepCRISPR. Author-reported evaluation · Evaluation metadata: source checked | ||
| 11.40(0.10)% spearman_corr Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 0.10 Scored: Not reported · Eligible: Not reported | source checkedBEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(CNN),column(CRI-Off) Source checking is not independent reproduction. |
| CNN on BEACON CRI-On: CRISPR on-target efficiency prediction Method: CNNTask: BEACON CRI-On: CRISPR on-target efficiency predictionDataset subset: DeepCRISPR (BEACON split) BEACON harness, fixed downstream head per task. Train/validation/test 1,453/207/416; dataset DeepCRISPR. Author-reported evaluation · Evaluation metadata: source checked | ||
| 29.69(2.52)% spearman_corr Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 2.52 Scored: Not reported · Eligible: Not reported | source checkedBEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(CNN),column(CRI-On) Source checking is not independent reproduction. |
| CNN on BEACON DMP: Distance map prediction BEACON harness, fixed downstream head per task. Train/validation/test 188/23/80; dataset RNAcontact. Author-reported evaluation · Evaluation metadata: source checked | ||
| 27.76(5.00)% r2 Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 5.00 Scored: Not reported · Eligible: Not reported | source checkedBEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(CNN),column(DMP) Source checking is not independent reproduction. |
| CNN on BEACON Modif: RNA modification site prediction Method: CNNTask: BEACON Modif: RNA modification site predictionDataset subset: MultiRM (BEACON split) BEACON harness, fixed downstream head per task. Train/validation/test 304,661/3,599/1,200; dataset MultiRM. Author-reported evaluation · Evaluation metadata: source checked | ||
| 70.87(0.40)% auc Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 0.40 Scored: Not reported · Eligible: Not reported | source checkedBEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(CNN),column(Modif) Source checking is not independent reproduction. |
| CNN 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. Author-reported evaluation · Evaluation metadata: source checked | ||
| 74.13(0.58)% r2 Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 0.58 Scored: Not reported · Eligible: Not reported | source checkedBEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(CNN),column(MRL) Source checking is not independent reproduction. |
| CNN on BEACON ncRNA: Non-coding RNA family classification Method: CNNTask: BEACON ncRNA: Non-coding RNA family classificationDataset subset: Noorul's ncRNA set (BEACON split) BEACON harness, fixed downstream head per task. Train/validation/test 5,679/650/2,400; dataset Noorul's ncRNA set. Author-reported evaluation · Evaluation metadata: source checked | ||
| 88.62(0.71)% accuracy Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 0.71 Scored: Not reported · Eligible: Not reported | source checkedBEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(CNN),column(ncRNA) Source checking is not independent reproduction. |
| CNN on BEACON PRS: Programmable RNA switch prediction Method: CNNTask: BEACON PRS: Programmable RNA switch predictionDataset subset: Angenent-Mari's switch set (BEACON split) BEACON harness, fixed downstream head per task. Train/validation/test 73,227/9,153/9,154; dataset Angenent-Mari's switch set. Author-reported evaluation · Evaluation metadata: source checked | ||
| 45.40(0.66)% r2 Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 0.66 Scored: Not reported · Eligible: Not reported | source checkedBEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(CNN),column(PRS) Source checking is not independent reproduction. |
| CNN on BEACON SPL: Splice site prediction BEACON harness, fixed downstream head per task. Train/validation/test 144,628/18,078/16,505; dataset SpliceAI. Author-reported evaluation · Evaluation metadata: source checked | ||
| 8.43(0.38)% top_k_accuracy Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 0.38 Scored: Not reported · Eligible: Not reported | source checkedBEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(CNN),column(SPL) Source checking is not independent reproduction. |
| CNN on BEACON SSI: Structure score imputation Method: CNNTask: BEACON SSI: Structure score imputationDataset subset: StructureImpute (BEACON split) BEACON harness, fixed downstream head per task. Train/validation/test 14,049/1,756/3,095; dataset StructureImpute. Author-reported evaluation · Evaluation metadata: source checked | ||
| 34.36(0.12)% r2 Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 0.12 Scored: Not reported · Eligible: Not reported | source checkedBEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(CNN),column(SSI) Source checking is not independent reproduction. |
| CNN 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. Author-reported evaluation · Evaluation metadata: source checked | ||
| 49.95(0.82)% f1 Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 0.82 Scored: Not reported · Eligible: Not reported | source checkedBEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(CNN),column(SSP) Source checking is not independent reproduction. |
| CNN on BEACON VDP: Vaccine degradation prediction Method: CNNTask: BEACON VDP: Vaccine degradation predictionDataset subset: OpenVaccine (BEACON split) BEACON harness, fixed downstream head per task. Train/validation/test 2,155/245/629; dataset OpenVaccine. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.361(0.003) mcrmse Unit: error · Direction: lower | Uncertainty: type: standard deviation; value: 0.003 Scored: Not reported · Eligible: Not reported | source checkedBEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(CNN),column(VDP) Source checking is not 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
| Property and statement | Original source and location | Review and provenance |
|---|
No evidence rows match these filters. Choose another scope or clear the search.
Sources and history
Release 2026-09-17-1a18ca2c038a · Record review: source checked
1 source records and release history
- BEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Original source · v2, 12 December 2024
Technical metadata and extraction receipts
Stable ID: beacon-model-cnn
- areas
- rna-transcriptomes
- family
- naive
- source locator
- Table3,p.8,row(CNN)
- missing metadata
- checkpoint revision: unreported; parameters: unextracted
Related records
- model: CNN on BEACON APA: Alternative polyadenylation isoform prediction
- model: CNN on BEACON CMP: Contact map prediction
- model: CNN on BEACON CRI-Off: CRISPR off-target effect prediction
- model: CNN on BEACON CRI-On: CRISPR on-target efficiency prediction
- model: CNN on BEACON DMP: Distance map prediction
- model: CNN on BEACON Modif: RNA modification site prediction
- model: CNN on BEACON MRL: Mean ribosome loading prediction
- model: CNN on BEACON ncRNA: Non-coding RNA family classification
- model: CNN on BEACON PRS: Programmable RNA switch prediction
- model: CNN on BEACON SPL: Splice site prediction
- model: CNN on BEACON SSI: Structure score imputation
- model: CNN on BEACON SSP: Secondary structure prediction
- model: CNN on BEACON VDP: Vaccine degradation prediction