Fair splits flip the leaderboard: CHANRG reveals limited generalization in RNA secondary-structure prediction
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910066413666304 |
|---|---|
| author | Chen, Zhiyuan Deng, Zhenfeng Deng, Pan Liao, Yue Su, Xiu Ye, Peng Liu, Xihui |
| author_facet | Chen, Zhiyuan Deng, Zhenfeng Deng, Pan Liao, Yue Su, Xiu Ye, Peng Liu, Xihui |
| contents | Accurate prediction of RNA secondary structure underpins transcriptome annotation, mechanistic analysis of non-coding RNAs, and RNA therapeutic design. Recent gains from deep learning and RNA foundation models are difficult to interpret because current benchmarks may overestimate generalization across RNA families. We present the Comprehensive Hierarchical Annotation of Non-coding RNA Groups (CHANRG), a benchmark of 170{,}083 structurally non-redundant RNAs curated from more than 10 million sequences in Rfam~15.0 using structure-aware deduplication, genome-aware split design and multiscale structural evaluation. Across 29 predictors, foundation-model methods achieved the highest held-out accuracy but lost most of that advantage out of distribution, whereas structured decoders and direct neural predictors remained markedly more robust. This gap persisted after controlling for sequence length and reflected both loss of structural coverage and incorrect higher-order wiring. Together, CHANRG and a padding-free, symmetry-aware evaluation stack provide a stricter and batch-invariant framework for developing RNA structure predictors with demonstrable out-of-distribution robustness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_22330 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Fair splits flip the leaderboard: CHANRG reveals limited generalization in RNA secondary-structure prediction Chen, Zhiyuan Deng, Zhenfeng Deng, Pan Liao, Yue Su, Xiu Ye, Peng Liu, Xihui Biomolecules Machine Learning Accurate prediction of RNA secondary structure underpins transcriptome annotation, mechanistic analysis of non-coding RNAs, and RNA therapeutic design. Recent gains from deep learning and RNA foundation models are difficult to interpret because current benchmarks may overestimate generalization across RNA families. We present the Comprehensive Hierarchical Annotation of Non-coding RNA Groups (CHANRG), a benchmark of 170{,}083 structurally non-redundant RNAs curated from more than 10 million sequences in Rfam~15.0 using structure-aware deduplication, genome-aware split design and multiscale structural evaluation. Across 29 predictors, foundation-model methods achieved the highest held-out accuracy but lost most of that advantage out of distribution, whereas structured decoders and direct neural predictors remained markedly more robust. This gap persisted after controlling for sequence length and reflected both loss of structural coverage and incorrect higher-order wiring. Together, CHANRG and a padding-free, symmetry-aware evaluation stack provide a stricter and batch-invariant framework for developing RNA structure predictors with demonstrable out-of-distribution robustness. |
| title | Fair splits flip the leaderboard: CHANRG reveals limited generalization in RNA secondary-structure prediction |
| topic | Biomolecules Machine Learning |
| url | https://arxiv.org/abs/2603.22330 |