Hybrid Deep Learning Framework for Predicting CRISPR-Cas9 Off-Target Activities Using Experimentally Validated Mismatch and Indel Datasets
DOI:
https://doi.org/10.63282/3117-5481/AIJCST-V7I2P114Keywords:
CRISPR-Cas9, Off-Target Prediction, Deep Learning (DL), Lightweight Model, HyperparameterAbstract
The CRISPR-Cas9 system has been discovered as a potential biological gene-editing method. However, there is still a considerable chance of unintended consequences. Models for off-target prediction have been developed recently thanks to advances in deep learning, although these models often fall short of fully using sequence pair information. The challenge of "off-target," however, hampers the swift development of gene editing technologies. In this paper. This study presents a successful work on classification with ML and DL models, considering a structured dataset and utilizing multiple performance measures. The proposed models Logistic Regression (LR) and Recurrent Neural Network (RNN) were compared with the several baseline models: ANN, Naïve Bayes (NB) and SVM. The data was preprocessed for reliable training and testing by data cleaning and encoding, normalization and balanced splitting. The experimental findings show that the suggested models work better than the current techniques: LR achieves an accuracy of 97%, and RNN achieves the best accuracy of 97.32%, precision of 98%, recall of 97.2%, and F1 score of 97.9%. The outcomes show that the models proposed here have the potential to improve classification and overall prediction performance.
References
[1] F. A. Ran, P. D. Hsu, J. Wright, V. Agarwala, D. A. Scott, and F. Zhang, “Genome engineering using the CRISPR-Cas9 system,” Nat. Protoc., vol. 8, no. 11, pp. 2281–2308, Nov. 2013, doi: 10.1038/nprot.2013.143.
[2] Y. Mei, Y. Wang, H. Chen, Z. S. Sun, and X.-D. Ju, “Recent Progress in CRISPR/Cas9 Technology,” J. Genet. Genomics, vol. 43, no. 2, pp. 63–75, Feb. 2016, doi: 10.1016/j.jgg.2016.01.001.
[3] T. Zhan, N. Rindtorff, J. Betge, M. P. Ebert, and M. Boutros, “CRISPR/Cas9 for cancer research and therapy,” Semin. Cancer Biol., vol. 55, pp. 106–119, Apr. 2019, doi: 10.1016/j.semcancer.2018.04.001.
[4] F. Jiang and J. A. Doudna, “CRISPR–Cas9 Structures and Mechanisms,” Annu. Rev. Biophys., vol. 46, no. 1, pp. 505–529, May 2017, doi: 10.1146/annurev-biophys-062215-010822.
[5] H. Wang, M. La Russa, and L. S. Qi, “CRISPR/Cas9 in Genome Editing and Beyond,” Annu. Rev. Biochem., vol. 85, no. 1, pp. 227–264, Jun. 2016, doi: 10.1146/annurev-biochem-060815-014607.
[6] S.-C. Liu et al., “Target residence of Cas9-sgRNA influences DNA double-strand break repair pathway choices in CRISPR/Cas9 genome editing,” Genome Biol., vol. 23, no. 1, p. 165, Dec. 2022, doi: 10.1186/s13059-022-02736-5.
[7] A. Samach et al., “CRISPR/Cas9-induced DNA breaks trigger crossover, chromosomal loss, and chromothripsis-like rearrangements,” Plant Cell, vol. 35, no. 11, pp. 3957–3972, Oct. 2023, doi: 10.1093/plcell/koad209.
[8] G. Zhang, Y. Luo, X. Dai, and Z. Dai, “Benchmarking deep learning methods for predicting CRISPR/Cas9 sgRNA on- and off-target activities,” Brief. Bioinform., vol. 24, no. 6, Sep. 2023, doi: 10.1093/bib/bbad333.
[9] F. Özden and P. Minary, “Learning to quantify uncertainty in off-target activity for CRISPR guide RNAs,” Nucleic Acids Res., vol. 52, no. 18, pp. e87–e87, Oct. 2024, doi: 10.1093/nar/gkae759.
[10] P. D. Hsu et al., “DNA targeting specificity of RNA-guided Cas9 nucleases,” Nat. Biotechnol., vol. 31, no. 9, pp. 827–832, Sep. 2013, doi: 10.1038/nbt.2647.
[11] M. Stemmer, T. Thumberger, M. del Sol Keyer, J. Wittbrodt, and J. L. Mateo, “CCTop: An Intuitive, Flexible and Reliable CRISPR/Cas9 Target Prediction Tool,” PLoS One, vol. 10, no. 4, p. e0124633, Apr. 2015, doi: 10.1371/journal.pone.0124633.
[12] G. Zhang, Y. Luo, H. Xie, and Z. Dai, “Crispr-SGRU: Prediction of CRISPR/Cas9 Off-Target Activities with Mismatches and Indels Using Stacked BiGRU,” Int. J. Mol. Sci., vol. 25, no. 20, p. 10945, Oct. 2024, doi: 10.3390/ijms252010945.
[13] Y. Yang, J. Li, Q. Zou, Y. Ruan, and H. Feng, “Prediction of CRISPR-Cas9 off-target activities with mismatches and indels based on hybrid neural network,” Comput. Struct. Biotechnol. J., vol. 21, pp. 5039–5048, 2023, doi: 10.1016/j.csbj.2023.10.018.
[14] A. Imani, J. Valiant, and A. A. Santoso Gunawan, “Deep Learning-based Approach on sgRNA off-target Prediction in CRISPR/Cas9,” in 2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE), IEEE, Feb. 2023, pp. 440–444. doi: 10.1109/ICCoSITE57641.2023.10127682.
[15] K. Sanyour and W. Kim, “Machine Learning Algorithms in Gene Editing,” in 2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), IEEE, Dec. 2022, pp. 799–802. doi: 10.1109/BIBM55620.2022.9995135.
[16] W. Xiang, D. Chen, Y. Cui, and S. Peng, “H-VAE: A Hybrid Variational AutoEncoder with Data Augmentation in Predicting CRISPR/Cas9 Off-target,” in 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), IEEE, Dec. 2021, pp. 550–555. doi: 10.1109/BIBM52615.2021.9669570.
[17] R. Niu, J. Peng, Z. Zhang, and X. Shang, “R-CRISPR: A Deep Learning Network to Predict Off-Target Activities with Mismatch, Insertion and Deletion in CRISPR-Cas9 System,” Genes (Basel)., vol. 12, no. 12, p. 1878, Nov. 2021, doi: 10.3390/genes12121878.
[18] Q. Liu, X. Cheng, G. Liu, B. Li, and X. Liu, “Deep learning improves the ability of sgRNA off-target propensity prediction,” BMC Bioinformatics, vol. 21, no. 1, p. 51, Dec. 2020, doi: 10.1186/s12859-020-3395-z.
[19] A. Bhardwaj, P. Tomar, and V. Nain, “Machine Learning-Driven Prediction of CRISPR-Cas9 Off-Target Effects and Mechanistic Insights,” Eurobiotech J., vol. 8, no. 4, pp. 213–229, 2024, doi: 10.2478/ebtj-2024-0020.
[20] J. Charlier, R. Nadon, and V. Makarenkov, “Accurate deep learning off-target prediction with novel sgRNA-DNA sequence encoding in CRISPR-Cas9 gene editing,” Bioinformatics, vol. 37, no. 16, pp. 2299–2307, 2021, doi: 10.1093/bioinformatics/btab112.
[21] J. Das, S. Kumar, D. C. Mishra, K. K. Chaturvedi, R. K. Paul, and A. Kairi, “Machine learning in the estimation of CRISPR-Cas9 cleavage sites for plant system,” Front. Genet., vol. 13, no. January, pp. 1–13, Jan. 2023, doi: 10.3389/fgene.2022.1085332.
