R-CRISPR: A Deep Learning Network to Predict Off-Target Activities with Mismatch, Insertion and Deletion in CRISPR-Cas9 System

Abstract

The Clustered Regularly Interspaced Short Palindromic Repeats (CRISPR)—associated protein 9 (Cas9) system is a groundbreaking gene-editing tool, which has been widely adopted in biomedical research. However, the guide RNAs in CRISPR-Cas9 system may induce unwanted off-target activities and further affect the practical application of the technique. Most existing in silico prediction methods that focused on off-target activities possess limited predictive precision and remain to be improved. Hence, it is necessary to propose a new in silico prediction method to address this problem. In this work, a deep learning framework named R-CRISPR is presented, which devises an encoding scheme to encode gRNA-target sequences into binary matrices, a convolutional neural network as feature extractor, and a recurrent neural network to predict off-target activities with mismatch, insertion, or deletion. It is demonstrated that R-CRISPR surpasses six mainstream prediction methods with a significant improvement on mismatch-only datasets verified by GUIDE-seq. Compared with the state-of-art prediction methods, R-CRISPR also achieves competitive performance on datasets with mismatch, insertion, and deletion. Furthermore, experiments show that data concatenate could influence the quality of training data, and investigate the optimal combination of datasets.

Using traditional machine learning and deep learning methods for on- and off-target prediction in CRISPR/Cas9: a review

“…Informative features such as epigenetic features, microhomology properties, or RNA fold score can be further exploited to increase the models accuracy. Convolutional layers of CNN and LRCN deep learning networks are able to discover useful features from sequences directly and independently, avoiding eventual biases introduced by hand-crafted features [ 74 , 84 , 132 ]. The use of the SHAP [ 135 ] (SHapley Additive exPlanations—this algorithm gives an explanation to the model’s behavior, connecting optimal credit allocation with local explanations using the classic Shapley values from game theory), Tree SHAP [ 131 ] (this algorithm calculates SHAP values for tree-based models), and Deep SHAP [ 135 ] algorithms (this is a high-speed approximation algorithm for SHAP values) is highly recommended to assess how each feature impacts the selected model.…”

“…al. [ 132 ] proposed the R-CRISPR deep learning model that encodes sgRNA target sequences into a binary matrix and then uses a CNN model as a feature extractor. Precisely, the authors applied a Rep-VGG inference time body composed of a stack of 3 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} }{}$\times $\end{document} 3 convolutions and ReLUs [ 133 ] in the convolutional layers to extract relevant features.…”

Efficient deletion of microRNAs using CRISPR/Cas9 with dual guide RNAs

“…However, before conducting such high-throughput assays, it is essential to evaluate the off-target effects of designed gRNAs. Employing advanced algorithms to select gRNAs with minimal off-target consequences ( Concordet and Haeussler, 2018 ; Dhanjal et al, 2020 ; Trivedi et al, 2020 ; Dhanjal et al, 2020 ; Niu et al, 2021 ; Z.-R; Zhang and Jiang, 2022 ) is essential for maintaining the specificity of the CRISPR/Cas9 system. Additionally, the application of Cas9 variants known for reduced off-target activity, such as enhanced S. pyogenes Cas9 (eSpCas9) ( Slaymaker et al, 2016 ) and high-fidelity SpCas9-HF1 (P. H. Smith et al, 2016 ), could significantly enhance the precision of CRISPR/Cas9-mediated miRNA editing.…”

gRNA Design: How its Evolution Impacted on CRISPR/Cas9 Systems Refinement

“…A high similarity between the gRNA sequence and non-targeting sequences leads to an elevated percentage of these off-target bindings. These off-target effects can be classified depending on the distinct occurrences: Manghwar, Zhang, and Niu [37][38][39] presents three types of off-target effects, regarding "bulges" and simple mismatches; on the other hand, Borrelli et al [40] present two types, which are much more general and simpler than those from [37][38][39]. Any CRISPR experiment can have off-target bindings and all their adverse and undesired effects.…”