A systematic evaluation of nucleotide properties for CRISPR sgRNA design

BMC Bioinformatics

Research Article

Pei Fen Kuan¹  Kaiqiao Li¹  Shuyao He¹  Scott Powers²  Xiaoyu Zhao²  Bo Huang³ 

[1] Department of Applied Mathematics and Statistics, Stony Brook University, 100 Nicolls Road, 11794, Stony Brook, USA;Department of Pathology, Stony Brook University, 100 Nicolls Road, 11794, Stony Brook, USA;Oncology Business Unit, Pfizer Inc., 558 Eastern Point Rd, 06340, Groton, USA;

关键词: CRISPR;    Machine learning;    Predictive modeling;    Thermodynamics;   

DOI  :  10.1186/s12859-017-1697-6

 received in 2017-03-20, accepted in 2017-05-18,  发布年份 2017

来源: Springer

【 摘 要 】

BackgroundCRISPR is a versatile gene editing tool which has revolutionized genetic research in the past few years. Optimizing sgRNA design to improve the efficiency of target/DNA cleavage is critical to ensure the success of CRISPR screens.ResultsBy borrowing knowledge from oligonucleotide design and nucleosome occupancy models, we systematically evaluated candidate features computed from a number of nucleic acid, thermodynamic and secondary structure models on real CRISPR datasets. Our results showed that taking into account position-dependent dinucleotide features improved the design of effective sgRNAs with area under the receiver operating characteristic curve (AUC) >0.8, and the inclusion of additional features offered marginal improvement (∼2% increase in AUC).ConclusionUsing a machine-learning approach, we proposed an accurate prediction model for sgRNA design efficiency. An R package predictSGRNA implementing the predictive model is available at http://www.ams.sunysb.edu/~pfkuan/softwares.html#predictsgrna.

【 授权许可】

CC BY   
© The Author(s) 2017

【 图 表 】

40517_2023_273_Article_IEq6.gif

40517_2023_273_Article_IEq4.gif

Fig. 1

Fig. 2

Fig. 3