Home
 /
Papers
 /
Biochemistry
 /
Mechanistic machine learning enables interpretable and generalizable prediction of prime editing outcomes
Preprint
Open access
Top 1% · Validated by QED

Mechanistic machine learning enables interpretable and generalizable prediction of prime editing outcomes

Alvin Hsu, Peter J. Chen, Angus H. Li +24 more
February 2026
 ·
bioRxiv
 ·
DOI 
10.64898/2026.02.20.706353
99
%
QED Score
QED Impressions

By modeling prime editing as discrete biochemical steps rather than a black box, OptiPrime replaces laborious pegRNA optimization with principled prediction—unlocking efficient therapeutic correction in primary cells and live mouse brain without iterative experimentation.

Run full QED analysis
Read paper
Save

QED claims analysis

Summary

OptiPrime, a mechanistic machine learning model that incorporates the biological mechanism of prime editing through differential equations governing pseudo-rates of individual biochemical steps, achieves superior prediction accuracy compared to existing models and enables rapid optimization of therapeutic prime editing strategies, including achieving >40% in vivo correction efficiency in mouse brain with streamlined pegRNA design requiring only 15 candidates rather than hundreds typically needed.

See full analysis
Main Claim 1 –

High-throughput screens reveal structural and cellular MMR determinants

Main Claim 2 –

OptiPrime mechanistic ML predicts prime editing and MMR effects

Supporting evidence

  • OptiPrime pseudo-rates enable PE3 prediction via transfer learning
  • OptiPrime pseudo-rates predict twinPE via mechanism rewiring
Main Claim 3 –

OptiPrime accurately predicts prime editing across diverse contexts

Main Claim 4 –

OptiPrime speeds therapeutic prime editing strategy development

Supporting evidence

  • OptiPrime enables efficient correction in primary human cells
  • OptiPrime silent edits boost prime editing in primary T cells
  • OptiPrime twinPE predictions improve eePASSIGE gene integration efficiency
  • OptiPrime achieves high editing using only 15 pegRNAs
  • OptiPrime-optimized prime editing exceeds 40% in mouse brain
  • OptiPrime outperforms existing models across therapeutic targets

Abstract

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 efficient in vivo correction of a pathogenic mutation in the brain of a mouse model of KIF1A-associated neurological disorder.

Related papers

How the QED Score works

QED Score is an AI-based quality metric for life science research. It rates each paper on two dimensions: originality (is the finding new and important?) and validity (does the evidence support the claims?). Author names and affiliations are removed before scoring. Each manuscript is broken down into its claims and the experiments behind them, and specialized AI agents then examine those claims for statistical rigor, consistency across figures, and contradictions with the existing literature. A verification layer re-checks every issue they flag. Scores are percentile ranks against all papers in the corpus. In a blinded study of papers where QED Score and journal rank disagreed, domain experts sided with QED Score in 75% of cases.
Read the methodology

Free access for academic researchers

Create your free QED account to validate your research, strengthen grant proposals, and uncover scientific insights.
We've sent you an access link.
Please check your inbox.

Didn't get your email? Check your spam folder or reach out to info@qedscience.com

Oops! Something went wrong while submitting the form.
Looking for QED for pharma, biotech or life science organizations?