Prediction of hydrogen and carbon chemical shifts from RNA using database mining and support vector regression.
Prediction of hydrogen and carbon chemical shifts from RNA using database mining and support vector regression.
复制标题
DOI：
10.1007/s10858-015-9961-4
复制
发表时间：
2015-09
影响因子：
2.7
通讯作者：
Johnson BA
中科院分区：
文献类型：
--
作者：
Brown JD;Summers MF;Johnson BA
生物磁共振数据库（BMRB）包含超过200种RNA和含RNA复合物的NMR化学位移沉积。我们分析了1H NMR和13 C化学位移报告的非交换质子的187这些RNA。开发了下载BMRB数据集和相应PDB结构文件的软件，然后基于计算的二级结构生成残基特异性属性。属性表示存在于五个相邻残基的每个连续延伸中的性质，并且包括诸如核苷酸类型、碱基对存在和类型以及四环类型的变量。然后使用中心核苷酸的属性和1H和13 C NMR化学位移作为输入，使用支持向量回归训练预测模型。然后，这些模型可以用于预测新序列的偏移。新的软件工具，可作为独立的脚本或集成到NMR可视化和分析程序NMRViewJ，应有助于NMR分配和/或验证RNA 1H和13 C化学位移。此外，我们的研究结果使得能够使用已发表的NMR化学位移和高分辨率X射线结构数据作为指导来重新校准环电流位移模型。
The Biological Magnetic Resonance Data Bank (BMRB) contains NMR chemical shift depositions for over 200 RNAs and RNA-containing complexes. We have analyzed the 1H NMR and 13C chemical shifts reported for non-exchangeable protons of 187 of these RNAs. Software was developed that downloads BMRB datasets and corresponding PDB structure files, and then generates residue-specific attributes based on the calculated secondary structure. Attributes represent properties present in each sequential stretch of five adjacent residues and include variables such as nucleotide type, base-pair presence and type, and tetraloop types. Attributes and 1H and 13C NMR chemical shifts of the central nucleotide are then used as input to train a predictive model using support vector regression. These models can then be used to predict shifts for new sequences. The new software tools, available as stand-alone scripts or integrated into the NMR visualization and analysis program NMRViewJ, should facilitate NMR assignment and/or validation of RNA 1H and 13C chemical shifts. In addition, our findings enabled the recalibration a ring-current shift model using published NMR chemical shifts and high-resolution X-ray structural data as guides.