College of Engineering, Shantou University, Shantou 515063, China.
School of Cyber Science and Technology, Sun Yat-sen University, Shenzhen 518107, China.
Int J Mol Sci. 2024 Oct 11;25(20):10928. doi: 10.3390/ijms252010928.
CRISPR/Cas9 has been applied to edit the genome of various organisms, but our understanding of editing outcomes at specific sites after Cas9-mediated DNA cleavage is still limited. Several deep learning-based methods have been proposed for repair outcome prediction; however, there is still room for improvement in terms of performance regarding frameshifts and model interpretability. Here, we present DeepIndel, an end-to-end multi-label regression model for predicting repair outcomes based on the BERT-base module. We demonstrate that our model outperforms existing methods in terms of accuracy and generalizability across various metrics. Furthermore, we utilized Deep SHAP to visualize the importance of nucleotides at various positions for DNA sequence and found that mononucleotides and trinucleotides in DNA sequences surrounding the cut site play a significant role in repair outcome prediction.
CRISPR/Cas9 已被应用于编辑各种生物体的基因组，但我们对 Cas9 介导的 DNA 切割后特定位点的编辑结果的理解仍然有限。已经提出了几种基于深度学习的方法来进行修复结果预测；然而，在涉及移码和模型可解释性方面，性能仍有改进的空间。在这里，我们提出了 DeepIndel，这是一种基于 BERT-base 模块的用于基于预测修复结果的端到端多标签回归模型。我们证明，我们的模型在准确性和跨各种指标的泛化能力方面优于现有方法。此外，我们利用 Deep SHAP 来可视化 DNA 序列中各个位置的核苷酸的重要性，发现切割位点周围的 DNA 序列中的单核苷酸和三核苷酸在修复结果预测中起着重要作用。
