Easy-Prime: a machine learning\u2013based prime editor design tool

Yichao Li,Yong Cheng,Shengdar Q Tsai,Jingjing Chen

doi:10.1186/s13059-021-02458-0

Yichao Li, Yong Cheng + Show 2 more

Open Access

https://doi.org/10.1186/s13059-021-02458-0

Copy DOI

Abstract

Prime editing is a revolutionary genome-editing technology that can make a wide range of precise edits in DNA. However, designing highly efficient prime editors (PEs) remains challenging. We develop Easy-Prime, a machine learning–based program trained with multiple published data sources. Easy-Prime captures both known and novel features, such as RNA folding structure, and optimizes feature combinations to improve editing efficiency. We provide optimized PE design for installation of 89.5% of 152,351 GWAS variants. Easy-Prime is available both as a command line tool and an interactive PE design server at: http://easy-prime.cc/.

Highlights

Genome-editing technologies have revolutionized genetic studies ranging from those involving traditional interventions to precise manipulations of DNA sequences, offering both simplicity and robust outcomes [1]
For PE2 model, we used the 46,614 PE2 data generated by high-throughput integration system [17] and 199 endogenous editing sites measured by 597 amplicon sequencing [8]
Even though Easy-Prime and the previously published DeepPE [17] are trained with different algorithms and different feature combinations, both programs demonstrate the importance of spCas9 activity and primer binding site (PBS) GC content

Summary

Introduction

Genome-editing technologies have revolutionized genetic studies ranging from those involving traditional interventions to precise manipulations of DNA sequences, offering both simplicity and robust outcomes [1]. Among different genome-editing technologies, the clustered regularly interspaced short palindromic repeats (CRISPR)– based systems [2,3,4] are the most widely used ones. Different CRISPR-based systems have their own strengths and weaknesses. Standard CRISPR-Cas approaches tend to introduce imprecise edits with indels varying in size from a single nucleotide to hundreds of nucleotides through nonhomologous end joining (NHEJ) [4]. Base editors can generate transition point mutations with high efficiency and accuracy without introducing double-strand breaks [5,6,7]. Base editors are not suitable for generating other types of point mutations or for insertions and deletions

Methods

Results

Conclusion