深度学习在作物基因编辑技术的应用与研究进展

doi:10.19788/j.issn.2096-6369.000120

Abstract

Abstract:

In recent years, gene editing technology has developed rapidly and has become a core tool for basic gene function research and biological breeding. And with the growth of computers and big data driving the application of deep learning in gene editing, deep learning technology is playing an increasingly significant role in optimizing the gene editing process, especially in enhancing the efficiency of crop improvement. This article reviews the research progress of deep learning in gene editing optimization, focusing on the application of deep learning in gene editing efficiency and specificity enhancement. In addition, the article delves into the technical challenges facing the deep integration of deep learning and gene editing, and looks forward to its future development prospects. By combining advanced gene editing technology with deep learning, the progress of crop breeding will be further accelerated in the future.

Key words: deep learning, language models, gene editing

ZHAO XiaoYan, ZHOU HuanBin, ZHOU GuoMin, ZHANG JianHua. Application of Deep Learning in Crop Gene Editing Technology and Research Progress[J].Journal of Agricultural Big Data, 2026, 8(1): 24-35.

Figures/Tables 8

Fig. 1

Fig. 2

Fig. 3

Table 1

Table 2

Table 3

Fig. 4

Fig. 5

References 58

[1]	赖郑诗雨, 黄赞唐, 孙洁婷, 等. CRISPR/Cas基因组编辑技术及其在农作物品种改良中的应用. 科学通报, 2022, 67: 1923-1937.
	LAI Z S Y, HUANG Z T, SUN J T, et al. The recent progress of CRISPR/Cas genome editing technology and its application in crop improvement. Chinese Science Bulletion, 2022, 67: 1923-1937.
[2]	LI J, WU P, CAO Z, et al. Machine learning-based prediction models to guide the selection of Cas9 variants for efficient gene editing. Cell Reports, 2024, 43(2): 113765. doi: 10.1016/j.celrep.2024.113765
[3]	CHEN K, WANG Y, ZHANG R, et al. CRISPR/Cas genome editing and precision plant breeding in agriculture. Annual Review of Plant Biology, 2019, 70: 667-697. doi: 10.1146/annurev-arplant-050718-100049 pmid: 30835493
[4]	ZHANG B. CRISPR/Cas9: A robust genome-editing tool withversatile functions and endless application. International Journal of Molecular Sciences, 2020, 21: 5111. doi: 10.3390/ijms21145111
[5]	WATERMAN D P, HABER J E, SMOLKA M B. Checkpoint responses to DNA double-strand breaks. Annual Review of Biochemistry, 2020, 89:103-133. doi: 10.1146/annurev-biochem-011520-104722 pmid: 32176524
[6]	MORTON J, DAVIS M W, JORGENSEN E M, et al. Induction and repair of zinc-finger nuclease-targeted double-strand breaks in Caenorhabditis elegans somatic cells. Proceedings of the National Academy of Sciences of the United States of America, 2006, 103(44):16370-16375.
[7]	CARROLL D. Genome engineering with zinc-finger nucleases. Genetics, 2011, 188:773-778. doi: 10.1534/genetics.111.131433 pmid: 21828278
[8]	JOUNG J K, SANDER J D. TALENs: A widely applicable technology for targeted genome editing. Nature Reviews of Molecular Cell Biology, 2013, 14: 49-55. doi: 10.1038/nrm3486
[9]	RICHTER C, CHANG J T, FINERAN P C. Function and regulation of clustered regularly interspaced short palindromic repeats(CRISPR) / CRISPR associated (Cas) systems. Viruses, 2012, 4: 2291-2311. doi: 10.3390/v4102291
[10]	ESVELT K M, MALI P, BRAFF J L, et al. Orthogonal Cas9 proteins for RNA-guided gene regulation and editing. Nature Methods, 2013, 10: 1116-1121. doi: 10.1038/nmeth.2681 pmid: 24076762
[11]	ZHANG X, CHENG J, LIN Y, et al. Editing homologous copies of an essential gene affords crop resistance against two cosmopolitan necrotrophic pathogens. Plant Biotechnology Journal, 2021, 19(11): 2349-2361. doi: 10.1111/pbi.13667 pmid: 34265153
[12]	ZHANG J, ZHOU Z, BAI J, et al. Disruption of MIR396e and MIR396f improves rice yield under nitrogen-deficient conditions. National Science Review, 2019, 7: 102-112. doi: 10.1093/nsr/nwz142
[13]	KOMOR A C, KIM Y B, PACKER M S, et al. Programmable editing of a target base in genomic DNA without double-stranded DNA cleavage. Nature, 2016, 533: 420-424. doi: 10.1038/nature17946
[14]	DOM L, RAGURAM A, NEWBY G A, et al. Evaluation and minimization of Cas9-independent off-target DNA editing by cytosine base editors. Nature Biotechnology, 2020, 38:620-628. doi: 10.1038/s41587-020-0414-6 pmid: 32042165
[15]	ZHAO D, LI J, LI S, et al. Glycosylase base editors enable C-to-a and C-to-G base changes. Nature Biotechnology, 2021, 39: 35-40. doi: 10.1038/s41587-020-0592-2
[16]	CHEN P J, LIU D R. Prime editing for precise and highly versatile genome manipulation. Nature Reviews Genetics, 2022, 24:161-177. doi: 10.1038/s41576-022-00541-1 pmid: 36344749
[17]	SHAH M A, JIARUI K, RUOFU T, et al. CRISPR/Cas 9 mediated knockout of the OsbHLH024 transcription factor improves salt stress resistance in rice (Oryza sativa L.). Plants, 2022, 11(9):1184-1184. doi: 10.3390/plants11091184
[18]	LI S, ZHANG Y, LIU Y, et al. The E3 ligase TaGW2 mediates transcription factor TaARR12 degradation to promote drought resistance in wheat. The Plant cell, 2024, 36(3):605-625. doi: 10.1093/plcell/koad307
[19]	LIU L, GALLAGHER J, AREVALO E D, et al. Enhancing grain-yield-related traits by CRISPR-Cas9 promoter editing of maize CLE genes. Nature plants, 2021, 7(3): 287-294. doi: 10.1038/s41477-021-00858-5 pmid: 33619356
[20]	WANG Y X, LIU X Q, ZHENG X X, et al. Creation of aromatic maize by CRISPR/Cas. Journal of Integrative Plant Biology, 2021, 63(9):1664-1670. doi: 10.1111/jipb.13105
[21]	LI H L, WANG L B, DAI Y Z, et al. Synergetic interaction between neighbouring platinum monomers in CO₂ hydrogenation. Nature Nanotechnology, 2018, 13(5):411-417. doi: 10.1038/s41565-018-0089-z
[22]	LIU T F, JI J, CHENG Y Y, et al. CRISPR/Cas9-mediated editing of GmTAP1 confers enhanced resistance to Phytophthora sojae in soybean. Journal of Integrative Plant Biology, 2023, 65(7):1609-1612. doi: 10.1111/jipb.v65.7
[23]	CHAO C W, CUI Y, LIN Y, et al. Identification of salt tolerance- associated presence-absence variations in the OsMADS56 gene through the integration of DEGs dataset and eQTL analysis. The New Phytologist, 2024, 243(3):833-838. doi: 10.1111/nph.v243.3
[24]	WANG L, NIE R, YU Z, et al. An interpretable deep-learning architecture of capsule networks for identifying cell-type gene expression programs from single-cell RNA-sequencing data. Nature Machine Intelligence, 2020, 2(11):693-703. doi: 10.1038/s42256-020-00244-4
[25]	GUO J, ZENG L, CHEN H, et al. CRISPR/Cas9-Mediated targeted mutagenesis of BnaCOL9 advances the flowering time of Brassica napus L. International Journal of Molecular Sciences, 2022, 23(23): 14944-14944. doi: 10.3390/ijms232314944
[26]	王远立, 啜国晖, 闫继芳, 等. 计算机辅助 CRISPR 向导 RNA 设计. 生物工程学报, 2017, 33(10): 1744-1756.
	WANG Y L, CHUAI G H, YAN J F, et al. In silico CRISPR-based sgRNA design. Chinese Journal of Biotechnology, 2017, 33(10): 1744-1756.
[27]	JINEK M, CHYLINSKI K, FONFARA I, et al. A programmable Dual-RNA-Guided DNA endonuclease in adaptive bacterial immunity. Science, 2012, 337(6096):816-821. doi: 10.1126/science.1225829 pmid: 22745249
[28]	MEJÍA-GUERRA M K, BUCKLER E S. A k-mer grammar analysis to uncover maize regulatory architecture. BMC Plant Biology, 2019, 19(1):1-17. doi: 10.1186/s12870-018-1600-2
[29]	FENG Z Y, ZHANG B T, DING W, et al. Efficient genome editing in plants using a CRISPR/Cas system. Cell Research, 2013, 23: 1229-1232. doi: 10.1038/cr.2013.114 pmid: 23958582
[30]	ZHANG H, YAN J F, LU Z K, et al. Deep sampling of gRNA in the human genome and deep-learning-informed prediction of gRNA activities. Cell Discovery, 2023, 9(1):48-48. doi: 10.1038/s41421-023-00549-9 pmid: 37193681
[31]	WANG D Q, ZHANG C D, WANG B, et al. Optimized CRISPR guide RNA design for two high-fidelity Cas 9 variants by deep learning. Nature Communications, 2019, 10(1):4284. doi: 10.1038/s41467-019-12281-8
[32]	CHUAI G, MA H, YAN J, et al. DeepCRISPR: optimized CRISPR guide RNA design by deep learning. Genome Biology, 2018, 19(1): 1-18. doi: 10.1186/s13059-017-1381-1
[33]	LIN J C, Zhang Z L, ZHANG S, et al. CRISPR-net: a recurrent convolutional network quantifies off-target with activities CRISPR mismatches and indels. Advanced Science, 2020, 7(13): 1903562. doi: 10.1002/advs.v7.13
[34]	JASPER Z, FRÉDERIC G, MIJUNG K, et al. SpliceRover: interpretable convolutional neural networks for improved splice site prediction. Bioinformatics, 2018, 34(24):4180-4188. doi: 10.1093/bioinformatics/bty497 pmid: 29931149
[35]	SCHOONENBERG V A C, COLE M A, YAO Q M, et al. CRISPRO: identification of functional protein coding sequences based on genome editing dense mutagenesis. Genome Biology, 2018, 19(1):169. doi: 10.1186/s13059-018-1563-5 pmid: 30340514
[36]	KWON H K, GOOSANG Y, JINMAN P, et al. Predicting the efficiency of prime editing guide RNAs in human cells. Nature Biotechnology, 2020, 39(2):198-206. doi: 10.1038/s41587-020-0677-y
[37]	KIM H K, KIM Y, LEE S, et al. SpCas9 activity prediction by DeepSpCas9, a deep learning-based model with high generalization performance. Science Advances, 2019, 5(11): eaax9249. doi: 10.1126/sciadv.aax9249
[38]	CHEN Q C, CHUAI G, ZHANG H H, et al. Genome-wide CRISPR off-target prediction and optimization using RNA-DNA interaction fingerprints. Nature Communications, 2023, 14(1):7521-7521. doi: 10.1038/s41467-023-42695-4 pmid: 37980345
[39]	康里奇, 谈攀, 洪亮. 人工智能时代下的酶工程. 合成生物学, 2023, 4(3): 524-534. doi: 10.12211/2096-8280.2023-009
	KANG L Q, TAN P, HONG L. Enzyme engineering in the age of artificial intelligence. Synthetic Biology Journal, 2023, 4(3): 524-534. doi: 10.12211/2096-8280.2023-009
[40]	THEAN D G L, CHU H Y, FONG J H C, et al. Machine learning-coupled combinatorial mutagenesis enables resource-efficient engineering of CRISPR-Cas9 genome editor activities. Nature Communications, 2022, 13(1): 2219. doi: 10.1038/s41467-022-29874-5 pmid: 35468907
[41]	KIM N, KIM H K, LEE S, et al. Prediction of the sequence-specific cleavage activity of Cas9 variants. Nature Biotechnol, 2020, 38: 1328-1336. doi: 10.1038/s41587-020-0537-9
[42]	CONCORDET J P, HAEUSSLER M. CRISPOR: Intuitive guide selection for CRIsPR/Cas9 genome editing experiments and screens. Nucleic Acids Research, 2018, 46 (W1):W242-W2 45.
[43]	NAYFACH S, BHATNAGAR A, NOVICHKOV A, et al. Engineer- ing of CRISPR-Cas PAM recognition using deep learning of vast evolutionary data. BioRxiv: the preprint server for biology, 2025.
[44]	JIANG F, LI M, DONG J, et al. A general temperature-guided language model to design proteins of enhanced stability and activity. Science Advances, 2024, 29;10(48).
[45]	SINGH R, LANCHANTIN J, ROBINS G, et al. DeepChroene: deep- learning for predicting gene expressionfromhistone podifications. Bioinformatics, 2016. 32(17): i639-i648.
[46]	YIN Q, WU M, LIU Q, et al. DeepHiatone: a deep leaming approach topredictinghistone modications. BMC Geomics, 2019, 20: 11-23.
[47]	HOFFMAN G E, BENDL J, GIRDHAR K, et al. Functional interpretation of genetic variants using deep learning predicts impact on chromatin accessibility and histone modification. Nucleic Acids Research, 2019, 47 (20): 10597-10611. doi: 10.1093/nar/gkz808 pmid: 31544924
[48]	PARK H M, WON J, PARK Y, et al. CRISPR-Cas-Docker: web-based in silico docking and machine learning-based classification of crRNAs with Cas proteins. BMC Bioinformatics, 2023, 24(1): 167. doi: 10.1186/s12859-023-05296-y
[49]	NETHERY M A, KORVINK M, MAKAROVA K S, et al. CRISPRclassify: repeat-based classification of CRISPR loci. The CRISPR Journal, 2021, 4(4): 558-574. doi: 10.1089/crispr.2021.0021
[50]	YANG S S, HUANG J, HE B F. CASPredict: a web service for identifying Cas proteins. PeerJ, 2021, 9: e11887.
[51]	ZHANG T J, JIA Y R, LI H F, et al. CRISPRCasStack: a stacking strategy-based ensemble learning identification of framework for accurate Cas proteins. Briefings in Bioinformatics, 2022, 23(5): bbac335.
[52]	ALKHNBASHI O S, MITROFANOV A, BONIDIA R, et al. CRISPRloci: comprehensive and accurate annotation of CRISPR-Cas systems. Nucleic Acids Research, 2021, 49(W1): W125-W130. doi: 10.1093/nar/gkab456
[53]	NAHYE K, SUNGCHUL C, SUNGJAE K, et al. Deep learning models to predict the editing efficiencies and outcomes of diverse base editors. Nature Biotechnology, 2023, 42(3):484-497. doi: 10.1038/s41587-023-01792-x pmid: 37188916
[54]	YUAN T, WU L, LI S, et al. Deep learning models incorporating endogenous factors beyond DNA sequences improve the prediction accuracy of base editing outcomes. Cell Discovery, 2024, 10(1):20-20. doi: 10.1038/s41421-023-00624-1 pmid: 38378648
[55]	ALEX H, FLORENCE D, SEBASTIEN B, et al. Generating functional protein variants with variational autoencoders. Plos Computational Biology, 2021, 17(2):e1008736-e1008736. doi: 10.1371/journal.pcbi.1008736
[56]	DAWID G, SIMON M, IRENE R G, et al. LATE-a novel sensitive cell-based assay for the study of CRISPR/Cas9-related long-term adverse treatment effects. Molecular Therapy - Methods & Clinical Development, 2021, 22 249-262.
[57]	TAN Y Y, CHU A H Y, BAO S Y, et al. Rationally engineered Staphylococcus aureus Cas9 nucleases with high genome-wide specificity. Proceedings of the National Academy of Sciences of the United States of America, 2019, 116(42):20969-20976.
[58]	TIEU V, SOTILLO E, BJELAJAC R J, et al. A versatile CRISPR- Cas13d platform for multiplexed transcriptomic regulation and metabolic engineering in primary human T cells. Cell, 2024, 187(5): 1278-1295.e20. doi: 10.1016/j.cell.2024.01.035

名称 Tool name	链接 Accession link	主要功能 Main Functions	年份 Year	引用 References
GPP Web Portal	https://portals.broadinstitute.org/gpp/public/analysis-tools/sgrna-design	结合深度学习预测sgRNA切割效率及脱靶效应，支持CRISPRko/i/a设计	2023	/
DeepHF	http://www.deephf.com/	基于LSTM预测sgRNA在人类细胞中的编辑效率	2019	[31]
DeepCRISPR	http://www.deepcrispr.net/	结合CNN预测sgRNA活性与脱靶效应	2018	[32]
CRISPR-Net	https://codeocean.com/ capsule/9553651/tree/v1	基于CNN和注意力机制优化sgRNA效率预测	2020	[33]
SpliceRover	http://bioit2.irc.ugent.be/splicerover/	专为CRISPR剪接调控设计的sgRNA优化工具	2018	[34]
CRISPRO	http://gitlab.com/bauerlab/crispro	结合gRNA结构预测sgRNA结合效率	2020	[35]
DeepPE	https://www.crisprbehive.design/ Source code: https://github.com/	预测不同gRNA序列的编辑效率	2020	[36]
DeepSpCas9	http://deepcrispr.info/DeepSpCas9/	预测不同gRNA的活性	2019	[37]

名称 Tool name	链接 Accession link	主要功能 Main Functions	年份 Year	引用 References
Protein2PAM	https://protein2pam.profluent.bio/login	基于45,000+ CRISPR-Cas进化数据集训练，预测并定制Cas蛋白的PAM识别能力，突破靶向范围限制	2025	[43]
PRO-PRIME	https://github.com/ai4protein/Pro-Prime	引入物种温度标签的语言模型，预测单点突变对蛋白稳定性与活性的影响，在LbCas12a等5种蛋白中实现>30%阳性突变率	2024	[44]
AlphaFold2	https://colab.research.google.com/github/sokrypton/ColabFold/blob/main/AlphaFold2.ipynb	蛋白质结构预测或RNA结构预测	2018	/
DeepChrome	https:// www.deepchrome.org	基于 CNN 的组蛋白修饰数据预测基因表达水平	2020	[45]
DeepHistone	https://github.com/QijinYin/DeepHistone	基于CNN的序列和DNase测序准确预测组蛋白修饰位点	2021	[46]
DeepFIGV	https://deepfigv.mssm.edu/index.html	基于CNN预测对染色质可及性和组蛋白修饰的影响	2020	[47]

名称 Tool name	可标注单位 Annotatable units	链接 Accession link	年份 Year	引用 References
CRISPRcasIdentifier	Cas gene	https://github.com/BackofenLab/CRISPRcasIdentifier	2020	[49]
CASPredict	Cas gene	http://i.uestc.edu.cn/caspredict/cgi-bin/CASPredict.pl	2021	[50]
CRISPRcasStack	Cas gene	https://bioinfor.nefu.edu.cn/CRISPRCasStack/	2022	[51]
CRISPR-Cas-Docker	Cas gene	https://www.crisprcasdocker.org	2020	/
CRISPRloci	Cas gene (based on CRISPRcasIdentifier)	https://rna.informatik.uni-freiburg.de/CRISPRloci/	2021	[52]

Application of Deep Learning in Crop Gene Editing Technology and Research Progress

RichHTML

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 8

References 58

Related Articles 10

Metrics

Comments

Recommended 0

[1]	YE DuanNan, LI GenTian. A Small Object Detection Model Based on Improved YOLO [J]. Journal of Agricultural Big Data, 2025, 7(2): 173-182.
[2]	LIU Hong, DOU JingWen, WANG Yue, LIAO Yong, LIU XiaoLei, LI XinYun, ZHAO ShuHong, FU YuHua. A Multi-Omics Dataset for Functional Gene Mining in Animals [J]. Journal of Agricultural Big Data, 2025, 7(1): 96-106.
[3]	NIU BoWen, FENG QuanLong, ZHANG Yu, GAO BingBo, SUKHBAATAR Chinzorig, FENG AiPing, YANG JianYu. A 10-m Fractional Vegetation Cover Monthly Dataset of the Kherlen River Basin in 2022 [J]. Journal of Agricultural Big Data, 2025, 7(1): 59-68.
[4]	LI JiaLe, ZHANG JianHua, WANG Jian, ZHOU GuoMin. Metrological Analysis of Data-driven Deep Learning Methods for Agriculture [J]. Journal of Agricultural Big Data, 2024, 6(3): 400-411.
[5]	DU JiaKuan, LI YanFei, SUN SiWen, LIU JiDong, JIANG TengDa. Pan-spatiotemporal Feature Rice Deep Learning Extraction Based on Multi-source Data Fusion [J]. Journal of Agricultural Big Data, 2024, 6(1): 56-67.
[6]	MAO KeBiao, YUAN ZiJin, SHI JianCheng, WU ShengLi, HU DeYong, CHE Jin, DONG LiXin. Theory and Engineering Technology Implementation of Artificial Intelligence Retrieval Paradigm for Parameters of Remote Sensing Based on Big Data [J]. Journal of Agricultural Big Data, 2023, 5(4): 1-12.
[7]	ZHAO HongXin, SHAO MingYue, PAN Pan, WANG ZhiAo, MU Qiang, HE ZiKang, ZHANG JianHua. A Training Dataset for Deep Neural Network Model Recognition of Common Cotton Diseases [J]. Journal of Agricultural Big Data, 2023, 5(4): 47-55.
[8]	Lingxu Zhang,Rui Han,Wenming Li,Yinxue Shi,Chi Liu. A Survey of Big Data Deep Learning Systems and a Typical Agricultural Application [J]. Journal of Agricultural Big Data, 2019, 1(2): 88-104.
[9]	Lei Wu,Xiaohe Liang,Jisiguleng Wu,Rui Wang. Method and Agricultural Empirical Study of Query Reformulation Based on Word Embedding [J]. Journal of Agricultural Big Data, 2019, 1(2): 114-120.
[10]	Li Xianjiang, Chen Youqi, Zou Jinqiu, Shi Shuqin, Guo Tao, Cai Weimin, Chen Hao. Application of Convolutional Neural Networks in High-Resolution Image Classification [J]. Journal of Agricultural Big Data, 2019, 1(1): 67-77.