bioRxiv : the preprint server for biologyFeb 27, 2026

Using explainable machine learning to predict prime editing results accurately

CRISPR Gene Editing Weekly Brief ↗PubMed ↗DOI ↗

Updated Jun 27, 2026

Abstract

Essence

OptiPrime improved prediction and design of prime editing outcomes across several prospective therapeutic settings.

Evidence

A mechanistic machine learning study evaluated PE efficiency prediction, PE3 and twinPE outcomes, MMR-related determinants, and applications in primary human and mouse cells plus an in vivo mouse brain correction experiment.

Caveat

The abstract reports platform performance and selected prospective demonstrations, but broad therapeutic effectiveness and safety are not established.

Simplified

Although prime editing (PE) can effect virtually any specified local change to genomic DNA in living systems, its efficient application currently requires extensive optimization of prime editing guide RNA (pegRNA) sequences. We present OptiPrime, a machine learning model of PE efficiency based on our current understanding of the mechanism of prime editing. OptiPrime achieves state-of-the-art accuracy on PE efficiency prediction and also enables prediction of nicking guide RNA (PE3) and dual pegRNA (twinPE) outcomes. We validated that OptiPrime has learned the determinants of mammalian mismatch repair (MMR), and is therefore well suited for nominating MMR-evasive silent edits that improve PE efficiency. We demonstrate the utility of OptiPrime in a variety of prospective therapeutic contexts, including in primary human and mouse cells. Finally, we show how OptiPrime can be used to achieve highly streamlined and efficientcorrection of a pathogenic mutation in the brain of a mouse model of-associated neurological disorder. in vivo KIF1A