DeepCRISPR: optimized CRISPR guide RNA design by deep learning

Guohui Chuai; Hanhui Ma; Jifang Yan; Ming Chen; Nanfang Hong; Dongyu Xue; Chi Zhou; Chenyu Zhu; Ke Chen; Bin Duan; Feng Gu; Sheng Qu; Deshuang Huang; Jia Wei; Qi Liu

doi:10.1186/s13059-018-1459-4

DeepCRISPR: optimized CRISPR guide RNA design by deep learning

Genome Biol. 2018 Jun 26;19(1):80. doi: 10.1186/s13059-018-1459-4.

Authors

Guohui Chuai^{1

2}, Hanhui Ma³, Jifang Yan^{1

2}, Ming Chen⁴, Nanfang Hong^{1

2}, Dongyu Xue^{1

2}, Chi Zhou^{1

2}, Chenyu Zhu^{1

2}, Ke Chen^{1

2}, Bin Duan^{1

2}, Feng Gu⁵, Sheng Qu^{1

2}, Deshuang Huang⁶, Jia Wei⁷, Qi Liu^{8

9}

Affiliations

¹ Department of Endocrinology & Metabolism, Shanghai Tenth People's Hospital, Tongji University, Shanghai, 20009, China.
² Bioinformatics Department, School of Life Sciences and Technology, Tongji University, Shanghai, 20009, China.
³ School of Life Science and Technology, ShanghaiTech University, Shanghai, China.
⁴ R&D Information, Innovation Center China, AstraZeneca, 199 Liangjing Road, Shanghai, 201203, China.
⁵ State Key Laboratory Cultivation Base and Key Laboratory of Vision Science, Ministry of Health and Zhejiang Provincial Key Laboratory of Ophthalmology and Optometry, School of Ophthalmology and Optometry, Eye Hospital, Wenzhou Medical University, Wenzhou, Zhejiang, 325027, China.
⁶ Machine Learning & Systems Biology Lab, School of Electronics and Information Engineering, Tongji University, Shanghai, 201804, China. dshuang@tongji.edu.cn.
⁷ R&D Information, Innovation Center China, AstraZeneca, 199 Liangjing Road, Shanghai, 201203, China. Jenny.Wei@astrazeneca.com.
⁸ Department of Endocrinology & Metabolism, Shanghai Tenth People's Hospital, Tongji University, Shanghai, 20009, China. qiliu@tongji.edu.cn.
⁹ Bioinformatics Department, School of Life Sciences and Technology, Tongji University, Shanghai, 20009, China. qiliu@tongji.edu.cn.

Abstract

A major challenge for effective application of CRISPR systems is to accurately predict the single guide RNA (sgRNA) on-target knockout efficacy and off-target profile, which would facilitate the optimized design of sgRNAs with high sensitivity and specificity. Here we present DeepCRISPR, a comprehensive computational platform to unify sgRNA on-target and off-target site prediction into one framework with deep learning, surpassing available state-of-the-art in silico tools. In addition, DeepCRISPR fully automates the identification of sequence and epigenetic features that may affect sgRNA knockout efficacy in a data-driven manner. DeepCRISPR is available at http://www.deepcrispr.net/ .

Keywords: CRISPR system; Deep learning; Gene knockout; Off-targets; On-targets.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

CRISPR-Cas Systems / genetics*
Cell Line
Cell Line, Tumor
Clustered Regularly Interspaced Short Palindromic Repeats / genetics*
Computational Biology / methods
Computer Simulation
HCT116 Cells
HEK293 Cells
HL-60 Cells
HeLa Cells
Humans
Machine Learning
RNA Editing / genetics
RNA, Guide, CRISPR-Cas Systems / genetics*

Substances

RNA, Guide, CRISPR-Cas Systems