Aarhus University Seal / Aarhus Universitets segl

Enhancing CRISPR-Cas9 gRNA efficiency prediction by data integration and deep learning

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaperJournal articleResearchpeer-review

  • Xi Xiang, Lars Bolund Institute of Regenerative Medicine, BGI-Qingdao, BGI-Shenzhen, Qingdao, 266000, China., Univ Chinese Acad Sci, University of Chinese Academy of Sciences, CAS, Chinese Academy of Sciences, BGI-Shenzhen, 518083 Shenzhen, China; China National GeneBank-Shenzhen, BGI-Shenzhen, 518083 Shenzhen, China.
  • ,
  • Giulia I Corsi, University of Copenhagen
  • ,
  • Christian Anthon, University of Copenhagen
  • ,
  • Kunli Qu, Lars Bolund Institute of Regenerative Medicine, BGI-Qingdao, China., University of Copenhagen
  • ,
  • Xiaoguang Pan, Lars Bolund Institute of Regenerative Medicine, BGI-Qingdao, China.
  • ,
  • Xue Liang, Lars Bolund Institute of Regenerative Medicine, BGI-Qingdao, China., University of Copenhagen
  • ,
  • Peng Han, Lars Bolund Institute of Regenerative Medicine, BGI-Qingdao, China., University of Copenhagen
  • ,
  • Zhanying Dong, Lars Bolund Institute of Regenerative Medicine, BGI-Qingdao, China.
  • ,
  • Lijun Liu, Lars Bolund Institute of Regenerative Medicine, BGI-Qingdao, China.
  • ,
  • Jiayan Zhong, BGI-Shenzhen, Shenzhen, China.
  • ,
  • Tao Ma, BGI-Shenzhen, Shenzhen, China.
  • ,
  • Jinbao Wang, BGI-Shenzhen, Shenzhen, China.
  • ,
  • Xiuqing Zhang, BGI-Shenzhen, Shenzhen, China.
  • ,
  • Hui Jiang, BGI-Shenzhen, Shenzhen, China.
  • ,
  • Fengping Xu, Lars Bolund Institute of Regenerative Medicine, BGI-Qingdao, China., BGI-Shenzhen, Shenzhen, China.
  • ,
  • Xin Liu, BGI-Shenzhen, Shenzhen, China.
  • ,
  • Xun Xu, BGI-Shenzhen, Shenzhen, China.
  • ,
  • Jian Wang, BGI-Shenzhen, Shenzhen, China.
  • ,
  • Huanming Yang, BGI-Shenzhen, Shenzhen, China.
  • ,
  • Lars Bolund
  • George M Church, Harvard Medical School, Boston
  • ,
  • Lin Lin
  • Jan Gorodkin, University of Copenhagen
  • ,
  • Yonglun Luo

The design of CRISPR gRNAs requires accurate on-target efficiency predictions, which demand high-quality gRNA activity data and efficient modeling. To advance, we here report on the generation of on-target gRNA activity data for 10,592 SpCas9 gRNAs. Integrating these with complementary published data, we train a deep learning model, CRISPRon, on 23,902 gRNAs. Compared to existing tools, CRISPRon exhibits significantly higher prediction performances on four test datasets not overlapping with training data used for the development of these tools. Furthermore, we present an interactive gRNA design webserver based on the CRISPRon standalone software, both available via https://rth.dk/resources/crispr/ . CRISPRon advances CRISPR applications by providing more accurate gRNA efficiency predictions than the existing tools.

Original languageEnglish
Article number3238
JournalNature Communications
Volume12
ISSN2041-1723
DOIs
Publication statusPublished - May 2021

See relations at Aarhus University Citationformats

ID: 217471758