# RNA Secondary Structure Prediction By Learning Unrolled Algorithms

arXiv: https://arxiv.org/abs/2002.05810 · HTML: https://mlsanity.com/paper/2002.05810/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Feb 2020.

## Built on by (most cited first, 24 of 24)

- [Learning to Optimize: A Primer and A Benchmark](https://mlsanity.com/paper/2103.12828/) (2021)
- [Learning Long-Term Reward Redistribution via Randomized Return Decomposition](https://mlsanity.com/paper/2111.13485/) (2021)
- [Accurate RNA 3D structure prediction using a language model-based deep learning approach](https://mlsanity.com/paper/2207.01586/) (2022)
- [Symbolic Learning to Optimize: Towards Interpretability and Scalability](https://mlsanity.com/paper/2203.06578/) (2022)
- [RDesign: Hierarchical Data-efficient Representation Learning for Tertiary Structure-based RNA Design](https://mlsanity.com/paper/2301.10774/) (2023)
- [Beyond Sequence: Impact of Geometric Context for RNA Property Prediction](https://mlsanity.com/paper/2410.11933/) (2024)
- [Probabilistic Transformer: Modelling Ambiguities and Distributions for RNA Folding and Molecule Design](https://mlsanity.com/paper/2205.13927/) (2022)
- [BEACON: Benchmark for Comprehensive RNA Tasks and Language Models](https://mlsanity.com/paper/2406.10391/) (2024)
- [Protein-RNA interaction prediction with deep learning: Structure matters](https://mlsanity.com/paper/2107.12243/) (2021)
- [uGLAD: Sparse graph recovery by optimizing deep unrolled networks](https://mlsanity.com/paper/2205.11610/) (2022)
- [Two-Stage Learning For the Flexible Job Shop Scheduling Problem](https://mlsanity.com/paper/2301.09703/) (2023)
- [Scalable Deep Learning for RNA Secondary Structure Prediction](https://mlsanity.com/paper/2307.10073/) (2023)
- [ModelPred: A Framework for Predicting Trained Model from Training Data](https://mlsanity.com/paper/2111.12545/) (2021)
- [Compact Optimality Verification for Optimization Proxies](https://mlsanity.com/paper/2405.21023/) (2024)
- [Probability estimation and structured output prediction for learning preferences in last mile delivery](https://mlsanity.com/paper/2201.10269/) (2022)
- [Deciphering RNA Secondary Structure Prediction: A Probabilistic K-Rook Matching Perspective](https://mlsanity.com/paper/2212.14041/) (2022)
- [RNACG: A Universal RNA Sequence Conditional Generation model based on Flow-Matching](https://mlsanity.com/paper/2407.19838/) (2024)
- [Neural representation and generation for RNA secondary structures](https://mlsanity.com/paper/2102.00925/) (2021)
- [Learned Interpretable Residual Extragradient ISTA for Sparse Coding](https://mlsanity.com/paper/2106.11970/) (2021)
- [CLMB: deep contrastive learning for robust metagenomic binning](https://mlsanity.com/paper/2111.09656/) (2021)
- [Knowledge Propagation over Conditional Independence Graphs](https://mlsanity.com/paper/2308.05857/) (2023)
- [Kirigami: large convolutional kernels improve deep learning-based RNA secondary structure prediction](https://mlsanity.com/paper/2406.02381/) (2024)
- [Predicting Distance matrix with large language models](https://mlsanity.com/paper/2409.16333/) (2024)
- [OmniGenBench: Automating Large-scale in-silico Benchmarking for Genomic Foundation Models](https://mlsanity.com/paper/2410.01784/) (2024)

## Abstract (arXiv)

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.