PrimeNet: rational design of Prime editing pegRNAs by deep learning.

Abstract

The rapid development of gene editing technology has revolutionized life science research and biotechnology applications. Prime editing, a precise gene editing tool, has shown promise in various applications, including disease research and therapeutic interventions. However, its suboptimal editing efficiency for extensive fragments and lack of predictive models have hindered its widespread adoption. Existing models exhibit low prediction accuracy and limitations, such as neglecting epigenetic factors that impact gene editing effects. To address these challenges, we developed PrimeNet, a novel prediction model that integrates significant epigenetic factors, including chromatin accessibility and DNA methylation. By incorporating data from multiple cell lines and introducing multiscale convolution and attention mechanisms, PrimeNet enhances the accuracy of predictions and generalization performance. Our results show that PrimeNet achieves a Spearman correlation coefficient of 0.94 and 0.82 on two datasets originated from HEK293T and K562 cell lines, respectively, outperforming existing models. This novel model has the potential to guide experimental design, enhance the success rate of gene editing, and reduce unnecessary experimental costs, thereby advancing the application of gene editing technology in genetic disease treatment and related fields.