期刊名称：Proceedings of the National Academy of Sciences
印刷版ISSN：0027-8424
电子版ISSN：1091-6490
出版年度：2019
卷号：116
期号：18
页码：8693-8698
DOI：10.1073/pnas.1820523116
出版社：The National Academy of Sciences of the United States of America
摘要：While CRISPR/Cas9 is a powerful tool in genome engineering, the on-target activity and off-target effects of the system widely vary because of the differences in guide RNA (gRNA) sequences and genomic environments. Traditional approaches rely on separate models and parameters to treat on- and off-target cleavage activities. Here, we demonstrate that a free-energy scheme dominates the Cas9 editing efficacy and delineate a method that simultaneously considers on-target activities and off-target effects. While data-driven machine-learning approaches learn rules to model particular datasets, they may not be as transferrable to new systems or capable of producing new mechanistic insights as principled physical approaches. By integrating the energetics of R-loop formation under Cas9 binding, the effect of the protospacer adjacent motif sequence, and the folding stability of the whole single guide RNA, we devised a unified, physical model that can apply to any cleavage-activity dataset. This unified framework improves predictions for both on-target activities and off-target efficiencies of spCas9 and may be readily transferred to other systems with different guide RNAs or Cas9 ortholog proteins.
