GNL-Scorer: a generalized model for predicting CRISPR on-target activity by machine learning and featurization

• 作者: Jun Wang Xi Xiang Lars Bolund Xiuqing Zhang Lixin Cheng Yonglun Luo
• 来源期刊: 分子细胞生物学报（英文版）
• 年，卷（期）: 2020,（11）
• 所属期刊栏目: Application Note
• 页码范围: 909-911
• 页数: 3页
• 语种: 英文
• DOI: 10.1093/jmcb/mjz116

摘要

CRISPR/Cas9 is an adaptive immunity system in bacteria and most archaea (Koonin and Makarova, 2009;Horvath and Barrangou, 2010).The CRISPR/Cas9 gene editing system is comprised of two key components, a small guide RNA (gRNA) and a Cas9 endonuclease (Deltcheva et al., 2011;Jineket al., 2012).The gRNA is a chimeric RNA molecule of tracrRNA and crRNA (Ran et al., 2013) which guides the Cas9 protein to the target site in the genome.Therefore,selecting a target site with high ontarget activity and low off-target effect is crucial for gene editing.Previously, we have discovered that the gene editing activity of CRISPR-Cas9 in mammalian cells was affected by several factors, such as the secondary structure andchromatin accessibility of the guide sequences (Jensen et al., 2017).Strikingly, previous results from us and other research groups consistently revealed that the CRISPR gRNA activities are highly variable.Thus, several in silico gRNA design web tools and algorithms have been developed to facilitate CRISPR design and applications.