公平分割颠覆排行榜：CHANRG模型在RNA二级结构预测中显现泛化能力局限

摘要

RNA二级结构的精确预测是转录组注释、非编码RNA机制分析和RNA治疗设计的基石。基于深度学习与RNA基础模型的最新成果难以阐释，因为现有基准测试可能高估了跨RNA家族的泛化能力。我们推出全面层级化非编码RNA群组注释库（CHANRG），该基准集通过结构感知去重、基因组感知分割设计和多尺度结构评估，从Rfam 15.0数据库的1000多万条序列中筛选出170,083个结构非冗余RNA。在对29种预测工具的测试中，基础模型方法在保留集上达到最高精度，但在分布外数据中丧失大部分优势；而结构化解码器和直接神经预测器则保持显著更强的鲁棒性。这种差距在控制序列长度后依然存在，既反映了结构覆盖度的损失，也体现了高阶结构连接的错误识别。CHANRG基准集与免填充、对称感知的评估框架共同为开发具有可验证分布外鲁棒性的RNA结构预测工具提供了更严格且批次无关的评估体系。

English

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.

公平分割颠覆排行榜：CHANRG模型在RNA二级结构预测中显现泛化能力局限

Fair splits flip the leaderboard: CHANRG reveals limited generalization in RNA secondary-structure prediction

摘要

Support