Predicting CRISPR-Cas9 off-target effects in human primary cells using bidirectional LSTM with BERT embedding

Orhan Sari; Ziying Liu; Youlian Pan; Xiaojian Shao

doi:10.1093/bioadv/vbae184

Predicting CRISPR-Cas9 off-target effects in human primary cells using bidirectional LSTM with BERT embedding

Bioinform Adv. 2024 Dec 30;5(1):vbae184. doi: 10.1093/bioadv/vbae184. eCollection 2025.

Authors

Orhan Sari¹, Ziying Liu², Youlian Pan², Xiaojian Shao^{2

3}

Affiliations

¹ Department of Mining and Materials Engineering, McGill University, Montreal, QC, H3A 2B1, Canada.
² Digital Technologies Research Center, National Research Council Canada, Ottawa, ON, K1A 0R6, Canada.
³ Department of Biochemistry, Microbiology and Immunology, Ottawa Institute of Systems Biology, University of Ottawa, Ottawa, ON, K1H 8M5, Canada.

Abstract

Motivation: Clustered Regularly Interspaced Short Palindromic Repeats (CRISPR)-Cas9 system is a ground-breaking genome editing tool, which has revolutionized cell and gene therapies. One of the essential components involved in this system that ensures its success is the design of an optimal single-guide RNA (sgRNA) with high on-target cleavage efficiency and low off-target effects. This is challenging as many conditions need to be considered, and empirically testing every design is time-consuming and costly. In silico prediction using machine learning models provides high-performance alternatives.

Results: We present CrisprBERT, a deep learning model incorporating a Bidirectional Encoder Representations from Transformers (BERT) architecture to provide a high-dimensional embedding for paired sgRNA and DNA sequences and Bidirectional Long Short-term Memory networks for learning, to predict the off-target effects of sgRNAs utilizing only the sgRNAs and their paired DNA sequences. We proposed doublet stack encoding to capture the local energy configuration of the Cas9 binding and applied the BERT model to learn the contextual embedding of the doublet pairs. Our results showed that the new model achieved better performance than state-of-the-art deep learning models regarding single split and leave-one-sgRNA-out cross-validations as well as independent testing.

Availability and implementation: The CrisprBERT is available at GitHub: https://github.com/OSsari/CrisprBERT.