Design of prime-editing guide RNAs with deep transfer learning

作者全名："Liu, Feng; Huang, Shuhong; Hu, Jiongsong; Chen, Xiaozhou; Song, Ziguo; Dong, Junguo; Liu, Yao; Huang, Xingxu; Wang, Shengqi; Wang, Xiaolong; Shu, Wenjie"

作者地址："[Liu, Feng] Chongqing Med Univ, Coll Med Informat, Chongqing, Peoples R China; [Huang, Shuhong; Song, Ziguo; Liu, Yao; Wang, Xiaolong] Northwest A&F Univ, Coll Anim Sci & Technol, Int Joint Agr Res Ctr Anim Biobreeding, Minist Agr & Rural Affairs,Key Lab Anim Genet Bree, Yangling, Peoples R China; [Hu, Jiongsong; Dong, Junguo; Wang, Shengqi; Shu, Wenjie] Bioinformat Ctr AMMS, Beijing, Peoples R China; [Chen, Xiaozhou] Yunnan Minzu Univ, Sch Math & Comp Sci, Kunming, Peoples R China; [Huang, Xingxu] Zhejiang Univ, Affiliated Hosp 1, Sch Med, Zhejiang Prov Key Lab Pancreat Dis, Hangzhou, Peoples R China; [Huang, Xingxu] Zhejiang Univ, Inst Translat Med, Sch Med, Hangzhou, Peoples R China"

通信作者："Wang, XL (通讯作者)，Northwest A&F Univ, Coll Anim Sci & Technol, Int Joint Agr Res Ctr Anim Biobreeding, Minist Agr & Rural Affairs,Key Lab Anim Genet Bree, Yangling, Peoples R China.; Wang, SQ; Shu, WJ (通讯作者)，Bioinformat Ctr AMMS, Beijing, Peoples R China."

来源：NATURE MACHINE INTELLIGENCE

ESI学科分类：　

WOS号：WOS:001091265700003

JCR分区：Q1

影响因子：18.8

年份：2023

卷号：　

期号：　

开始页：　

结束页：　

文献类型：Article; Early Access

关键词：　

摘要："Prime editors (PEs) are promising genome-editing tools, but effective optimization of prime-editing guide RNA (pegRNA) design remains a challenge owing to the lack of accurate and broadly applicable approaches. Here we develop Optimized Prime Editing Design (OPED), an interpretable nucleotide language model that leverages transfer learning to improve its accuracy and generalizability for the efficiency prediction and design optimization of pegRNAs. Comprehensive validations on various published datasets demonstrate its broad applicability in efficiency prediction across diverse scenarios. Notably, pegRNAs with high OPED scores consistently show significantly increased editing efficiencies. Furthermore, the versatility and efficacy of OPED in design optimization are confirmed by efficiently installing various ClinVar pathogenic variants using optimized pegRNAs in the PE2, PE3/PE3b and ePE editing systems. OPED consistently outperforms existing state-of-the-art approaches. We construct the OPEDVar database of optimized designs from over two billion candidates for all pathogenic variants and provide a user-friendly web application of OPED for any desired edit. Prime editors are innovative genome-editing tools, but selecting guide RNAs with high efficiency remains challenging and requires costly experimental efforts. Liu and colleagues develop a method to design prime-editing guide RNAs based on transfer learning for in silico prediction of editing efficacy."

基金机构："This work was supported in part by the National Key Research and Development Project of China (2021YFC2302400 to W.S.), the National Natural Science Foundation of China (31901064, 81830101 and 32272848 to F.L., S.W. and X.W., respectively), the General Pro [2021YFC2302400]; National Key Research and Development Project of China [31901064, 81830101, 32272848]; National Natural Science Foundation of China [CSTB2022NSCQ-MSX1059]; General Project of Chongqing Natural Science Foundation of China [ZHYXQNRC202103]; Intelligent Medicine Research Project of Chongqing Medical University [2022GD-TSLD-46]; Shaanxi Double-chain Fusion Key Project"

基金资助正文："This work was supported in part by the National Key Research and Development Project of China (2021YFC2302400 to W.S.), the National Natural Science Foundation of China (31901064, 81830101 and 32272848 to F.L., S.W. and X.W., respectively), the General Project of Chongqing Natural Science Foundation of China (CSTB2022NSCQ-MSX1059 to F.L.), the Intelligent Medicine Research Project of Chongqing Medical University (ZHYXQNRC202103 to F.L.) and the Shaanxi Double-chain Fusion Key Project (2022GD-TSLD-46 to X.W.). The computational platform of OPED was supported by Y. Zhu in the Bioinformatics Platform of China National Center for Protein Sciences (Beijing), in conjunction with Supercomputing Center of Chongqing Medical University."