DeepCRISPR: optimized CRISPR guide RNA design by deep learning

被引：269

作者：

Chuai, Guohui ^{[1
,2
]}

Ma, Hanhui ^{[5
]}

Yan, Jifang ^{[1
,2
]}

Chen, Ming ^{[4
]}

Hong, Nanfang ^{[1
,2
]}

Xue, Dongyu ^{[1
,2
]}

Zhou, Chi ^{[1
,2
]}

Zhu, Chenyu ^{[1
,2
]}

Chen, Ke ^{[1
,2
]}

Duan, Bin ^{[1
,2
]}

Gu, Feng ^{[6
,7
,8
]}

Qu, Sheng ^{[1
,2
]}

Huang, Deshuang ^{[3
]}

Wei, Jia ^{[4
]}

Liu, Qi ^{[1
,2
]}

机构：

[1] Tongji Univ, Dept Endocrinol & Metab, Shanghai Peoples Hosp 10, Shanghai 20009, Peoples R China

[2] Tongji Univ, Sch Life Sci & Technol, Bioinformat Dept, Shanghai 20009, Peoples R China

[3] Tongji Univ, Sch Elect & Informat Engn, Machine Learning & Syst Biol Lab, Shanghai 201804, Peoples R China

[4] AstraZeneca, Innovat Ctr China, R&D Informat, 199 Liangjing Rd, Shanghai 201203, Peoples R China

[5] ShanghaiTech Univ, Sch Life Sci & Technol, Shanghai, Peoples R China

[6] Wenzhou Med Univ, State Key Lab Cultivat Base, Eye Hosp, Wenzhou 325027, Zhejiang, Peoples R China

[7] Wenzhou Med Univ, Key Lab Vis Sci, Minist Hlth, Eye Hosp, Wenzhou 325027, Zhejiang, Peoples R China

[8] Wenzhou Med Univ, Zhejiang Prov Key Lab Ophthalmol & Optometry, Sch Ophthalmol & Optometry, Eye Hosp, Wenzhou 325027, Zhejiang, Peoples R China

来源：

GENOME BIOLOGY | 2018年 / 19卷

基金：

中国国家自然科学基金;

关键词：

CRISPR system; Gene knockout; Deep learning; On-targets; Off-targets; OFF-TARGET CLEAVAGE; GENOME; SEQ; DNA; SPECIFICITIES; PREDICTION; NUCLEASES; SELECTION; SGRNAS;

D O I：

10.1186/s13059-018-1459-4

中图分类号：

Q81 [生物工程学（生物技术）]; Q93 [微生物学];

学科分类号：

071005 ; 0836 ; 090102 ; 100705 ;

摘要：

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.deeperispr.net/.

引用

页数：18

共 55 条

[1] Aach J, 2014, bioRxiv
[2] A machine learning approach for predicting CRISPR-Cas9 cleavage efficiencies and patterns underlying its mechanism of action
Abadi, Shiran
Yan, Winston X.
Amar, David
Mayrose, Itay
[J]. PLOS COMPUTATIONAL BIOLOGY, 2017, 13 (10)
[3] Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning
Alipanahi, Babak
Delong, Andrew
Weirauch, Matthew T.
Frey, Brendan J.
[J]. NATURE BIOTECHNOLOGY, 2015, 33 (08) : 831 - +
[4] Badaro G, 2013, INT WIREL COMMUN, P349, DOI 10.1109/IWCMC.2013.6583584
[5] Cas-OFFinder: a fast and versatile algorithm that searches for potential off-target sites of Cas9 RNA-guided endonucleases
Bae, Sangsu
Park, Jeongbin
Kim, Jin-Soo
[J]. BIOINFORMATICS, 2014, 30 (10) : 1473 - 1475
[6] Representation Learning: A Review and New Perspectives
Bengio, Yoshua
Courville, Aaron
Vincent, Pascal
[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2013, 35 (08) : 1798 - 1828
[7] The use of the area under the roc curve in the evaluation of machine learning algorithms
Bradley, AP
[J]. PATTERN RECOGNITION, 1997, 30 (07) : 1145 - 1159
[8] sgRNA Scorer 2.0: A Species-Independent Model To Predict CRISPR/Cas9 Activity
Chari, Raj
Yeo, Nan Cher
Chavez, Alejandro
Church, George M.
[J]. ACS SYNTHETIC BIOLOGY, 2017, 6 (05): : 902 - 904
[9] Chari R, 2015, NAT METHODS, V12, P823, DOI [10.1038/NMETH.3473, 10.1038/nmeth.3473]
[10] Analysis of off-target effects of CRISPR/Cas-derived RNA-guided endonucleases and nickases
Cho, Seung Woo
Kim, Sojung
Kim, Yongsub
Kweon, Jiyeon
Kim, Heon Seok
Bae, Sangsu
Kim, Jin-Soo
[J]. GENOME RESEARCH, 2014, 24 (01) : 132 - 141

← 1 2 3 4 5 6 →