Deep learning-based model that can predict the prime editing efficiency for all possible pegRNAs for a given target sequence.
Published Paper
Download Model
GitHub Repository (legacy)
The links marked legacy point to the original published source code. For the model as this web server runs it, use the Download Model link above.
Python Package
DeepPrime is a deep-learning-based prime editing efficiency prediction tool developed in the Laboratory of Genome Editing, Yonsei University.
It greatly expands upon the previous state-of-the-art pegRNA activity prediction model, DeepPE, which was limited to a specific set of edit type and length combinations.
DeepPrime was trained using 259K pegRNAs with:
Primer binding site (PBS) lengths: 1 to 17bp
Reverse transcription template (RTT) lengths: 1 to 50bp
Edit positions: +1 to +30
Editing lengths: 1 to 3nt
A prime editing efficiency prediction model trained on data from HEK293T or K562 cell lines (Mathis et al., Nature Biotechnology, 2024). This model may be useful for cross-validating long edit types.
Access: Web tool / GitHub
COSMIC. COSMIC is a product of Genome Research Limited (Wellcome Sanger Institute). It is free for academic and non-commercial use; commercial use requires a COSMIC licence. Lookups here resolve a single user-typed identifier — no COSMIC data is listed, browsable or served in bulk.
epegRNA. The engineered pegRNA (epegRNA) 3' motifs (tevopreQ1, tevo2.0 and the related v2 motifs) are the subject of a Broad Institute patent application; commercial users may need a licence to use them.
If you have any questions, bug reports, or suggestions, please do not hesitate to contact us through the Support page.
© Laboratory of Genome Editing (Yonsei University)