RNA Secondary Structure Prediction By Learning Unrolled Algorithms

TL;DR

E2Efold is a deep learning model that predicts RNA secondary structures by directly modeling base-pairing matrices and using unrolled algorithms to enforce biological constraints, achieving state-of-the-art accuracy and efficiency.

Contribution

The paper introduces E2Efold, a novel end-to-end deep learning approach that incorporates unrolled algorithms for constrained prediction of RNA structures.

Findings

E2Efold outperforms previous methods, especially for pseudoknotted structures.

It achieves superior accuracy while maintaining fast inference times.

Demonstrates effectiveness on benchmark datasets.

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 algorithm for constrained programming as the template for deep architectures 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 (especially for pseudoknotted structures), while being as efficient as the fastest algorithms in terms of inference time.