CRISMER: A transformer-based Interpretable Deep Learning Approach for Genome-wide CRISPR Cas-9 Off-Target Prediction and Optimization

CRISPR-Cas9 gene editing holds transformative promise for genetic therapies, but is hindered by off-target effects that undermine its precision and safety. To address this, we developed CRISMER, a hybrid deep-learning architecture that uses multi-branch convolutional neural networks to extract k-mer features and transformer blocks to capture long-range dependencies. This hybrid approach enhances the prediction and optimization of single-guide RNA (sgRNA) designs. CRISMER was trained on Change-seq and Site-seq datasets, using a sparse one-hot encoding scheme, and evaluated on independent datasets including Circle-seq, Guide-seq, Surro-seq, and TTISS. CRISMER outperformed existing tools, achieving an F1 score of 0.7092 and a PR-AUC of 0.8006 on the CRISPR-DIPOff dataset. It also excelled in measuring sgRNA specificity and optimizing designs for genes, such as PCSK9 and BCL11A, yielding sgRNAs with reduced off-target activity. For example, a G-to-C mutation at position 12 in the sgRNA for PCSK9 and at position 11 for BCL11A led to significant improvements in off-target profiles. Interpretability analysis via integrated gradients confirmed the model's focus on critical PAM-proximal regions and mismatch patterns. These results demonstrate that CRISMER significantly improves the accuracy and safety of CRISPR-Cas9, advancing its reliability for therapeutic applications.