TABLE 1.
Overview of Recent Studies Using Deep Learning in CRISPR-Cas system.
| Research Topics | Brief description | Studies |
|---|---|---|
| Prediction of gRNA Activities | Uses deep learning methods to predict the efficiency or on- and off activities of guide RNAs (gRNAs) in the CRISPR/Cas system | Ameen et al. (2021), Shrawgi and Sisodia (2019), Dimauro et al. (2019), Xie et al. (2023), Xue et al. (2019), Wan and Jiang (2023), Zhang et al. (2020b), Li et al. (2022a), Xiang et al. (2021), Kirillov et al. (2022), Elkayam and Orenstein (2022), Niu et al. (2021b), Luo et al. (2019), Zhang et al. (2021a), Yang et al. (2023), Zhang et al. (2020c), Liu et al. (2020), Zhang and Jiang (2022), Vinodkumar et al. (2021), Zhang et al. (2020a), Vora et al. (2023), Lin et al. (2020), Charlier et al. (2021), Lin et al. (2022), Niu et al. (2021a), Jost et al. (2020), Xiao et al. (2021), Wang and Zhang (2019) |
| Prediction of CRISPR-Cas Editing Outcomes | Deep learning models to predict diverse outcomes of CRISPR-Cas editing, including mutational outcomes and cleavage efficiency | Li et al. (2021), Liu et al. (2022), Wang et al. (2021), Li et al. (2022b), Li et al. (2022c), Naert et al. (2020), Naert et al. (2021), Marquart et al. (2021), Zhang et al. (2021b) |
| Design of High-Activity gRNAs | Uses deep learning to design highly active gRNAs for CRISPR-mediated gene editing or epigenome editing | Baisya et al. (2022), Wang et al. (2019), Feng et al. (2021), Kim et al. (2020a) |
| Automated System Implementation | Using deep learning to automate specific processes in the application of CRISPR-Cas system | Cordero-Maldonado et al. (2019), Allen et al. (2022), Patino et al. (2021), Kanfer et al. (2021) |
| Nucleic Acid Detection | Utilizing CRISPR and deep learning for detection of nucleic acids related to specific diseases | Xie et al. (2022), Kang et al. (2022), Ding et al. (2023) |
| Anti-CRISPR Protein Identification | Utilizing deep learning to identify anti-CRISPR proteins | Wandera et al. (2022), Upmeier zu Belzen et al. (2019), Park et al. (2022) |
| Cas9 Variant Activity Prediction | Developing deep learning models to predict the activity and specificity of different Cas9 variants | Kim et al. (2020b) |
| Transcription Factor Binding Predictions | Using deep learning to predict transcription factor binding interactions | Avsec et al. (2021) |
| Analysis of Public Opinion | Employing deep learning to analyze public opinions about the CRISPR-Cas9 system | Muller et al. (2020) |