PriFold: Biological Priors Improve RNA Secondary Structure Predictions

• DOI: 10.1609/aaai.v39i1.32080
• Publication Date: 2025-04-11T09:31:22Z
• Authors: Chenchen Yang; Hao Wu; Tao Shen; Kai Zou; Siqi Sun

Predicting RNA secondary structures is crucial for understanding function, designing RNA-based therapeutics, and studying molecular interactions within cells. Existing deep-learning-based methods structure prediction have mainly focused on local structural properties, often overlooking the global characteristics evolutionary features of sequences. Guided by biological priors, we propose PriFold, incorporating two key innovations: 1) improving attention mechanism with pairing probabilities to utilize characteristics, 2) implementing data augmentation based covariation leverage information. Our structured enhanced pretraining finetuning strategy significantly optimizes model performance. Extensive experiments demonstrate that PriFold achieves state-of-the-art (SOTA) results in benchmark datasets such as bpRNA, RNAStrAlign ArchiveII. These not only validate our approach but also highlight potential integrating information, into tasks, opening new avenues research biology bioinformatics.