Knowledge of RNA three-dimensional (3D) structures is critical to understanding the important biological functions of RNAs. Although various structure prediction models have been developed, the high-accuracy predictions of RNA 3D structures are still limited to the RNAs with short lengths or with simple topology. In this work, we proposed a new model, namely FebRNA, for building RNA 3D structures through fragment assembly based on coarse-grained (CG) fragment ensembles. Specifically, FebRNA is composed of four processes: establishing the library of different types of non-redundant CG fragment ensembles regardless of the sequences, building CG 3D structure ensemble through fragment assembly, identifying top-scored CG structures through a specific CG scoring function, and rebuilding the all-atom structures from the top-scored CG ones. Extensive examination against different types of RNA structures indicates that FebRNA consistently gives the reliable predictions on RNA 3D structures, including pseudoknots, three-way junctions, four-way and five-way junctions, and RNAs in the RNA-Puzzles. FebRNA is available on the Web site: https://github.com/Tan-group/FebRNA.

了解 RNA 三维 (3D) 结构对于理解 RNA 的重要生物学功能至关重要。尽管已经开发了各种结构预测模型，但RNA 3D结构的高精度预测仍然仅限于长度较短或拓扑简单的RNA。在这项工作中，我们提出了一种新模型，即 FebRNA，用于通过基于粗粒度 (CG) 片段集合的片段组装来构建 RNA 3D 结构。具体来说，FebRNA由四个过程组成：建立不同类型的非冗余CG片段集成库，无论序列如何，通过片段组装构建CG 3D结构集成，通过特定的CG评分函数识别得分最高的CG结构，以及从得分最高的 CG 结构中重建全原子结构。对不同类型 RNA 结构的广泛检查表明，FebRNA 始终能够对 RNA 3D 结构做出可靠的预测，包括假结、三向连接、四向和五向连接以及 RNA 谜题中的 RNA。FebRNA 可在网站上获取：https://github.com/Tan-group/FebRNA。