RNAprecis: Prediction of full-detail RNA conformation from the experimentally best-observed sparse parameters

We address the problem of predicting high-detail RNA structure geometry from the information available in low-detail experimental maps. Here, low-detail refers to resolutions ≈ 2.5-3.5Å, where the location of the phosphate groups and the glycosidic bonds can be determined from experimental maps but all other backbone atom positions cannot. In contrast, higher-resolution maps allow high-detail determinations of all backbone atomic positions. To this end, we first create a gold standard dataset of highly curated, experimentally supported RNA suites. Second, we develop and employ a modified version of the previously devised algorithm MINT-AGE to learn clusters that are in high correspondence with the gold standard’s conformational classes of suites based on 3D RNA structure. Since some of the gold standard classes are of very small size, a new modified version of MINT-AGE is able to also identify very small clusters. Third, we create a new conformer prediction algorithm, RNAprecis, which assigns low-detail structures to newly designed 3D shape coordinates. Our improvements include: (i) learned classes augmented to cover also very low sample sizes and (ii) replacing distances from clusters by Bayesian posterior probabilities. On test data containing suites modeled as conformational outliers, RNAprecis shows good results suggesting that our learning method generalizes well. In particular, we show that the modified MINT-AGE clustering can more finely delineate between previously unseen suite conformer separations. For example, the 0a conformer has been separated into two clusters seen in different structural contexts. Such new distinctions can have implications for biochemical interpretation of RNA structure.Author summary: This article addresses the problem that RNA molecular structures inferred from measurement and stored in molecular structure data bases frequently contain errors on the atomic scale, leading to chemically impossible molecule shapes. We provide a method to identify valid RNA structure elements from chemically viable structures and use a statistical comparison on a coarse grained scale to indicate correct atom placement. On a data set of faulty structures with known corrections, we achieve a high rate of matching corrections, showing the power of our method.