Accurate Classification of RNA Structures Using Topological Fingerprints

While RNAs are well known to possess complex structures, functionally similar RNAs often have little sequence similarity. While the exact size and spacing of base-paired regions vary, functionally similar RNAs have pronounced similarity in the arrangement, or topology, of base-paired stems. Furthermore, predicted RNA structures often lack pseudoknots (a crucial aspect of biological activity), and are only partially correct, or incomplete. A topological approach addresses all of these difficulties. In this work we describe each RNA structure as a graph that can be converted to a topological spectrum (RNA fingerprint). The set of subgraphs in an RNA structure, its RNA fingerprint, can be compared with the fingerprints of other RNA structures to identify and correctly classify functionally related RNAs. Topologically similar RNAs can be identified even when a large fraction, up to 30%, of the stems are omitted, indicating that highly accurate structures are not necessary. We investigate the performance of the RNA fingerprint approach on a set of eight highly curated RNA families, with diverse sizes and functions, containing pseudoknots, and with little sequence similarity–an especially difficult test set. In spite of the difficult test set, the RNA fingerprint approach is very successful (ROC AUC > 0.95). Due to the inclusion of pseudoknots, the RNA fingerprint approach both covers a wider range of possible structures than methods based only on secondary structure, and its tolerance for incomplete structures suggests that it can be applied even to predicted structures. Source code is freely available at https://github.rcac.purdue.edu/mgribsko/XIOS_RNA_fingerprint.尽管核糖核酸（RNA）具有复杂结构已是学界共识，但功能相似的RNA往往序列相似度极低。尽管碱基配对区域的精确尺寸与间距存在差异，但功能相似的RNA在碱基配对茎区的排布方式（即拓扑结构）上具有显著的相似性。此外，预测得到的RNA结构往往缺少假结（pseudoknot）——这是生物活性的关键特征之一，且这些结构往往仅部分正确，甚至存在缺失。拓扑学方法则可解决上述所有难题。本研究将每个RNA结构建模为可转换为拓扑谱（RNA指纹）的图结构。RNA结构中的子图集合即为其RNA指纹，通过将其与其他RNA结构的指纹进行比对，即可识别并准确分类功能相关的RNA。即便多达30%的茎区被省略，仍可识别出拓扑结构相似的RNA，这表明无需使用精度极高的RNA结构即可完成分类。本研究在8个经过精心整理的RNA家族数据集上验证了RNA指纹方法的性能，这些家族涵盖了不同的尺寸与功能，均包含假结且序列相似度极低——这是一组极具挑战性的测试集。即便面对如此具有挑战性的测试集，RNA指纹方法仍取得了极佳的表现（受试者工作特征曲线下面积（Receiver Operating Characteristic Area Under the Curve，ROC AUC）> 0.95）。由于纳入了假结特征，RNA指纹方法相比仅基于二级结构的方法，可覆盖更广泛的潜在RNA结构；同时其对不完整结构的兼容性，意味着该方法甚至可应用于预测得到的RNA结构。本研究的源代码可在https://github.rcac.purdue.edu/mgribsko/XIOS_RNA_fingerprint免费获取。