New Encoding Model Based on gRNA-DNA Pairs to Predict off-target Effects of Genome Editing with CRISPR/Cas۹

CRISPR/Cas۹ is a new genome-editing technology used in biomedical applications. To make genome editing with CRISPR far more precise and practical, we must concentrate on predicting CRISPR off-target effects and try to decrease them. Although numerous computational models have been developed to predict off-target activities, the existing methods suffer from low precision for gene editing at the clinical level. In addition, the inputs of most of these algorithms are gRNA sequences in on-hot vector encoding form. However, recent research illustrated that both gRNA and DNA strongly impact on the prediction precision of off-target activity. To address these problems, we propose a novel encoding scheme of gRNA-DNA sequences, and deploy it in two deep neural network-based architectures, including Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), to predict off-target e↵ects. The comparison of off-target prediction results based on our proposed gRNA-DNA encoding scheme with state-of-the-art on two popular geneediting datasets, CRISPOR and GUIDE-seq, reveals the superiority of our approach based on the area under the Receiver Operating Characteristic (AUROC) curve criteria which is the promising value of up to ۹۸%.

کلیدواژه ها:

CRISPR/Cas ، gRNA Design ، Off-target ، Encoding ، Machine learning