Institute of Informatics and Telecommunications, NCSR Demokritos, Patr. Gregoriou E & 27 Neapoleos Str, 15341 Athens, Greece.
School of Informatics, Aristotle University of Thessaloniki, 54124 Thessaloniki, Greece.
Nucleic Acids Res. 2022 Jul 5;50(W1):W191-W198. doi: 10.1093/nar/gkac466.
The development of the CRISPR-Cas9 technology has provided a simple yet powerful system for genome editing. Current gRNA design tools serve as an important platform for the efficient application of the CRISPR systems. However, most of the existing tools are black-box models that suffer from limitations, such as variable performance and unclear mechanism of decision making. Here, we introduce CRISPRedict, an interpretable gRNA efficiency prediction model for CRISPR-Cas9 gene editing. Its strength lies in the fact that it can accurately predict efficient guide RNAs-with equivalent performance to state-of-the-art tools-while being a simple linear model. Implemented as a user-friendly web server, CRISPRedict offers (i) quick and accurate predictions across various experimental conditions (e.g. U6/T7 transcription); (ii) regression and classification models for scoring gRNAs and (iii) multiple visualizations to explain the obtained results. Given its performance, interpretability, and versatility, we expect that it will assist researchers in the gRNA design process and facilitate genome editing research. CRISPRedict is available for use at http://www.crispredict.org/.
CRISPR-Cas9 技术的发展为基因组编辑提供了一个简单而强大的系统。当前的 gRNA 设计工具是高效应用 CRISPR 系统的重要平台。然而,大多数现有的工具都是黑盒模型,存在性能不稳定和决策机制不明确等局限性。在这里,我们介绍了 CRISPRedict,这是一个用于 CRISPR-Cas9 基因编辑的可解释的 gRNA 效率预测模型。它的优势在于能够准确预测高效的指导 RNA,其性能与最先进的工具相当,但它是一个简单的线性模型。作为一个用户友好的网络服务器实现,CRISPRedict 提供了(i)在各种实验条件下(例如 U6/T7 转录)快速准确的预测;(ii)用于评分 gRNA 的回归和分类模型;以及(iii)多种可视化方式来解释获得的结果。鉴于其性能、可解释性和多功能性,我们预计它将帮助研究人员进行 gRNA 设计,并促进基因组编辑研究。CRISPRedict 可在 http://www.crispredict.org/ 使用。