Predicting RNA three-dimensional structures from sequence could accelerate understanding of the growing number of RNA molecules being discovered across biology. Rosetta's Fragment Assembly of RNA with Full-Atom Refinement (FARFAR) has shown promise in community-wide blind RNA-Puzzle trials, but lack of a systematic and automated benchmark has left unclear what limits FARFAR performance. Here, we benchmark FARFAR2, an algorithm integrating RNA-Puzzle-inspired innovations with updated fragment libraries and helix modeling. In 16 of 21 RNA-Puzzles revisited without experimental data or expert intervention, FARFAR2 recovers native-like structures more accurate than models submitted during the RNA-Puzzles trials. Remaining bottlenecks include conformational sampling for >80-nucleotide problems and scoring function limitations more generally. Supporting these conclusions, preregistered blind models for adenovirus VA-I RNA and five riboswitch complexes predicted native-like folds with 3- to 14 Å root-mean-square deviation accuracies. We present a FARFAR2 webserver and three large model archives (FARFAR2-Classics, FARFAR2-Motifs, and FARFAR2-Puzzles) to guide future applications and advances.

从序列预测 RNA 三维结构可以加速对生物学中发现的越来越多的 RNA 分子的理解。Rosetta 的全原子精炼 RNA 片段组装 (FARFAR) 在社区范围的盲 RNA-Puzzle 试验中显示出了前景，但缺乏系统和自动化的基准使得人们不清楚是什么限制了 FARFAR 的性能。在这里，我们对 FARFAR2 进行了基准测试，这是一种将 RNA-Puzzle 启发的创新与更新的片段库和螺旋建模相结合的算法。在没有实验数据或专家干预的情况下重新审视的 21 个 RNA-Puzzles 中的 16 个中，FARFAR2 恢复了比 RNA-Puzzles 试验期间提交的模型更准确的类天然结构。剩下的瓶颈包括 >80 个核苷酸问题的构象采样和更普遍的评分函数限制。支持这些结论的是，预先注册的腺病毒 VA-I RNA 和五种核糖开关复合物的盲模型以 3 至 14 Å 均方根偏差精度预测了类似天然的折叠。我们提供 FARFAR2 网络服务器和三个大型模型档案（FARFAR2-Classics、FARFAR2-Motifs 和 FARFAR2-Puzzles）来指导未来的应用和进步。