A Hybrid Deep Learning-based Model for Off-target Prediction in CRISPR System

The CRISPR system, as a gene editing method, has revolutionized the field of biology,provided that the exact target sites (on-targets), for gene editing are determined accurately, to avoidunintended side effects that could potentially harm cellular function. To address this issue,computational methods have been developed to accurately predict off-target locations. In this research,a hybrid deep learning model incorporating two neural networks, BiLSTM and CNN, has been proposedfor identifying off-target sites in the CRISPR system. Due to the length and complexity of DNAsequences, a specialized encoding method is suggested for feeding information into the model. Utilizingk-mer sequence embeddings of various sizes using DNAtoVec, and calculating sequence mismatchesat both nucleotide and K-mer levels, this model is capable of identifying specific patterns and featuresin sequences. Furthermore, the use of data augmentation and under sampling techniques has provideda balanced dataset to address the issue of data imbalance in this research. The evaluation results indicatethat the proposed model surpasses the baseline models, achieving accuracy and F۱-Measure metrics forpredicting off-target sites that exceed ۰.۹۸.

کلیدواژه ها:

CRISPR ، off-target positions ، Increased Data ، Deep Learning