- TL;DR: A DL model for RNA secondary structure prediction, which uses an unrolled algorithm in the architecture to enforce constraints.
- Abstract: In this paper, we propose an end-to-end deep learning model, called E2Efold, for RNA secondary structure prediction which can effectively take into account the inherent constraints in the problem. The key idea of E2Efold is to directly predict the RNA base-pairing matrix, and use an unrolled constrained programming algorithm as a building block in the architecture to enforce constraints. With comprehensive experiments on benchmark datasets, we demonstrate the superior performance of E2Efold: it predicts significantly better structures compared to previous SOTA (29.7% improvement in some cases in F1 scores and even larger improvement for pseudoknotted structures) and runs as efficient as the fastest algorithms in terms of inference time.
- Keywords: RNA secondary structure prediction, learning algorithm, deep architecture design, computational biology