DTMP-prime: A deep learning model for predicting prime editing success and guide RNA activity

DTMP-Prime predicts prime editing efficiency with improved accuracy compared to existing models.

• A deep transformer-based model was developed to predict the activity of prime editing guide RNA (PegRNA).
• The model enhances the design of PegRNA and ngRNA by analyzing a broad range of prime editing data.
• Features of PegRNAs and target DNA sequences were effectively extracted, boosting the model's predictive capabilities.
• Improvements in precision and generalizability were achieved through the integration of a multi-head attention framework.
• Evaluation metrics, including Pearson and Spearman correlation coefficients, indicate that DTMP-Prime outperforms other models in predicting prime editing outcomes.

Simplified