TY - JOUR
T1 - Modeling CRISPR-Cas13d on-target and off-target effects using machine learning approaches
AU - Cheng, Xiaolong
AU - Li, Zexu
AU - Shan, Ruocheng
AU - Li, Zihan
AU - Wang, Shengnan
AU - Zhao, Wenchang
AU - Zhang, Han
AU - Chao, Lumen
AU - Peng, Jian
AU - Fei, Teng
AU - Li, Wei
N1 - Funding Information:
We would like to thank all members of the Li and Fei lab for the valuable discussion of the results. This work was supported by the startup fund from the Center of Genetic Medicine Research and Gilbert Family NF1 Institute at the Children’s National Medical Center (X.C. and W.L.), the National Institute of Health research grant R01 HG010753 (W.L.), the National Natural Science Foundation of China 31871344 and 32071441 (T.F.), the Fundamental Research Funds for the Central Universities N182005005 and N2020001 (T.F.), the 111 Project B16009 (T.F.), and LiaoNing Revitalization Talents Program XLYC1807212 (T.F.), the Key Laboratory of Bioresource Research and Development of Liaoning Province (2022JH13/10200026) (T.F.).
Publisher Copyright:
© 2023, The Author(s).
PY - 2023/12
Y1 - 2023/12
N2 - A major challenge in the application of the CRISPR-Cas13d system is to accurately predict its guide-dependent on-target and off-target effect. Here, we perform CRISPR-Cas13d proliferation screens and design a deep learning model, named DeepCas13, to predict the on-target activity from guide sequences and secondary structures. DeepCas13 outperforms existing methods to predict the efficiency of guides targeting both protein-coding and non-coding RNAs. Guides targeting non-essential genes display off-target viability effects, which are closely related to their on-target efficiencies. Choosing proper negative control guides during normalization mitigates the associated false positives in proliferation screens. We apply DeepCas13 to the guides targeting lncRNAs, and identify lncRNAs that affect cell viability and proliferation in multiple cell lines. The higher prediction accuracy of DeepCas13 over existing methods is extensively confirmed via a secondary CRISPR-Cas13d screen and quantitative RT-PCR experiments. DeepCas13 is freely accessible via http://deepcas13.weililab.org.
AB - A major challenge in the application of the CRISPR-Cas13d system is to accurately predict its guide-dependent on-target and off-target effect. Here, we perform CRISPR-Cas13d proliferation screens and design a deep learning model, named DeepCas13, to predict the on-target activity from guide sequences and secondary structures. DeepCas13 outperforms existing methods to predict the efficiency of guides targeting both protein-coding and non-coding RNAs. Guides targeting non-essential genes display off-target viability effects, which are closely related to their on-target efficiencies. Choosing proper negative control guides during normalization mitigates the associated false positives in proliferation screens. We apply DeepCas13 to the guides targeting lncRNAs, and identify lncRNAs that affect cell viability and proliferation in multiple cell lines. The higher prediction accuracy of DeepCas13 over existing methods is extensively confirmed via a secondary CRISPR-Cas13d screen and quantitative RT-PCR experiments. DeepCas13 is freely accessible via http://deepcas13.weililab.org.
UR - http://www.scopus.com/inward/record.url?scp=85147894529&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85147894529&partnerID=8YFLogxK
U2 - 10.1038/s41467-023-36316-3
DO - 10.1038/s41467-023-36316-3
M3 - Article
C2 - 36765063
AN - SCOPUS:85147894529
SN - 2041-1723
VL - 14
JO - Nature communications
JF - Nature communications
IS - 1
M1 - 752
ER -