LinearFold: Linear-Time Prediction of RNA Secondary Structures

Abstract

Predicting the secondary structure of an RNA sequence with speed and accuracy is useful in many applications such as drug design. The state-of-the-art predictors have a fundamental limitation: they have a run time that scales cubically with the length of the input sequence, which is slow for longer RNAs and limits the use of secondary structure prediction in genome-wide applications. To address this bottleneck, we designed the first linear-time algorithm for this problem. which can be used with both thermodynamic and machine-learned scoring functions. Our algorithm, like previous work, is based on dynamic programming (DP), but with two crucial differences: (a) we incrementally process the sequence in a left-to-right rather than in a bottom-up fashion, and (b) because of this incremental processing, we can further employ beam search pruning to ensure linear run time in practice (with the cost of exact search). Even though our search is approximate, surprisingly, it results in even higher overall accuracy on a diverse database of sequences with known structures. More interestingly, it leads to significantly more accurate predictions on the longest sequence families in that database (16S and 23S Ribosomal RNAs), as well as improved accuracies for long-range base pairs (500+ nucleotides apart).