基于多尺度卷积神经网络的CRISPR/Cas9脱靶预测方法

Prediction of CRISPR/Cas9 off-target activity using multi-scale convolutional neural network

摘要:

规律成簇的间隔短回文重复序列/CRISPR相关蛋白9 (clustered regularly interspaced palindromic repeats/CRISPR-associated protein 9, CRISPR/Cas9)是新一代基因编辑技术，该技术依靠单向导RNA识别特定基因位点，并引导Cas9核酸酶对特定位点进行编辑。然而，该技术存在脱靶效应限制了其发展。近年来，运用深度学习辅助CRISPR/Cas9脱靶预测研究是一个新兴的思路，有助于研究者实现更高效安全的基因编辑和基因治疗。而现有的深度学习模型对脱靶预测的准确性仍有提高空间。为此，本文基于多尺度卷积神经网络提出CnnCRISPR模型预测CRISPR/Cas9的脱靶情况。首先，将向导RNA和DNA序列分别进行独热编码，再将两个二值矩阵按位进行或运算。其次，将编码后的序列输入基于Inception模块的网络进行训练和验证分析。最后，输出向导RNA和DNA序列对的脱靶情况。在公开数据集上的实验结果表明，CnnCRISPR模型的性能优于现有的深度学习脱靶预测模型，为脱靶问题的研究提供了有效且可行的方法。

Abstract:

Clustered regularly interspaced short palindromic repeat/CRISPR-associated protein 9 (CRISPR/Cas9) is a new generation of gene editing technology, which relies on single guide RNA to identify specific gene sites and guide Cas9 nuclease to edit specific location in the genome. However, the off-target effect of this technology hampers its development. In recent years, several deep learning models have been developed for predicting the CRISPR/Cas9 off-target activity, which contributes to more efficient and safe gene editing and gene therapy. However, the prediction accuracy remains to be improved. In this paper, we proposed a multi-scale convolutional neural network-based method, designated as CnnCRISPR, for CRISPR/Cas9 off-target prediction. First, we used one-hot encoding method to encode the sgRNA-DNA sequence pair, followed by a bitwise or operation on the two binary matrices. Second, the encoded sequence was fed into the Inception-based network for training and evaluating. Third, the well-trained model was applied to evaluate the off-target situation of the sgRNA-DNA sequence pair. Experiments on public datasets showed CnnCRISPR outperforms existing deep learning-based methods, which provides an effective and feasible method for addressing the off-target problems.