序列信息引导的RNA三维结构几何评估
Sequence-Informed Geometric Evaluation of RNA 3D Structures
浏览论文内容
中文总结 AI 辅助
提出SIRGE,一种利用预训练RNA语言模型核苷酸嵌入条件化结构表示的几何评估器,在Kendall-τ对齐、Top-1选择和Top-3排序上优于现有方法,证明序列信息补充几何推理。
中文摘要 AI 辅助
计算RNA结构流程为同一序列生成许多候选构象。因此,可靠的评估不仅需要识别合理的几何结构,还需要确定该几何结构是否与序列兼容。我们提出了SIRGE,一种序列信息引导的几何评估器,它将结构表示条件化于来自预训练RNA语言模型的核苷酸嵌入之上。早期结果表明,SIRGE在Kendall-τ对齐、Top-1选择和Top-3排序方面优于已建立的评估器。受控比较进一步表明,序列条件化纠正了原本匹配的几何模型所犯的错误,并改善了目标级别的排序结构。这些发现提供了初步证据,表明预训练的序列表示提供了补充几何推理的排序信息。
英文摘要
Computational RNA structure pipelines generate many candidate conformations for the same sequence. Reliable evaluation therefore requires more than recognising plausible geometry, it requires determining whether that geometry is compatible with the sequence. We introduce SIRGE, a sequence-informed geometric evaluator that conditions structural representations on nucleotide embeddings from a pretrained RNA language model. Early results show that SIRGE outperforms established evaluators in Kendall--$τ$ alignment, Top-1 selection, and Top-3 ranking. Controlled comparisons further show that sequence conditioning corrects errors made by an otherwise matched geometric model and improves target-level rank structure. These findings provide initial evidence that pretrained sequence representations supply ranking information that complements geometric reasoning.
发表机构
- Aalborg University(奥尔堡大学)
- Imperial College London(帝国理工学院)
- Bioinformatics Institute (BII), A*STAR(新加坡科技研究局生物信息学研究所)
- Genome Institute of Singapore (GIS), A*STAR(新加坡科技研究局新加坡基因组研究所)
- Statens Serum Institut(丹麦国家血清研究所)
- University of Copenhagen(哥本哈根大学)
机构由 AI 辅助整理,请以论文原文为准。