BEguider:一个单碱基编辑器sgRNA设计与编辑效率预测工具

单碱基编辑器是实用且高效的基因编辑工具，其编辑效率与单向导RNA(single guide RNA, sgRNA)序列的设计密切相关。目前单碱基编辑器sgRNA序列的设计缺少特定的法则，主要依靠经验和大量尝试完成。本研究基于卷积神经网络，开发了一个单碱基编辑器sgRNA序列设计工具BEguider。BEguider利用TensorFlow 2深度学习框架建立编辑效率预测模型，能够在人基因组范围内针对NGG PAM序列依赖的单碱基编辑器ABE7.10-NGG和BE4-NGG批量设计sgRNA序列，预测编辑效率。此外，通过整合Cas-OFFinder, BEguider能够提供对sgRNA脱靶情况的评估。利用BEguider设计sgRNA序列，有助于研究人员提高实验效率，节约实验成本。

BEguider: A base editor for sgRNA design and editing efficiency prediction

Base editors are practical and efficient gene editing tools, whose editing efficiencies often depend on the design of single guide RNA(sgRNA) sequences. At present, the design of sgRNA libraries lacks of specific rules and mainly relies on experience and attempts. On the basis of the convolutional neural network, BEguider was developed for sgRNAs design of base editors. BEguider used the deep learning framework TensorFlow 2 to build editing efficiency prediction models, which could design sgRNA sequences and predict editing probabilities for NGG PAM-dependent base editor variants ABE7.10-NGG and BE4-NGG within the scope of the human genome. Besides, Beguider could evaluate potential off-target sites of sgRNAs by integrating Cas-OFFinder. Using BEguider to design sgRNA sequences will facilitate future application of base editors and save experimental cost.