Off-target predictions in CRISPR-Cas9 gene editing using deep learning.

Area of Science:

• Genomics
• Bioinformatics
• Molecular Biology

Background:

• CRISPR-Cas9 gene editing requires accurate prediction of off-target mutations for safety and efficacy.
• Existing prediction methods based on sequence mismatches have limitations in scalability and precision for clinical applications.

Purpose of the Study:

• To develop and evaluate deep neural network algorithms for predicting CRISPR-Cas9 off-target mutations.
• To compare the performance of deep learning models against existing methods and traditional machine learning approaches.

Main Methods:

• Implementation of two deep neural network models: deep convolutional neural network (CNN) and deep feedforward neural network (FFNN).
• Training and testing on the CRISPOR dataset and additional evaluation using the GUIDE-seq dataset.
• Comparison of AUC values with state-of-the-art methods (CFD, MIT, CROP-IT, CCTop) and traditional ML models.

Main Results:

• Deep CNN achieved the highest performance with an average AUC of 97.2% on the CRISPOR dataset.
• Deep FFNN demonstrated competitive performance with an average AUC of 97.0% under similar conditions.
• Both deep learning models showed superior performance compared to existing prediction methods and traditional machine learning models.

Conclusions:

• Deep neural networks, particularly CNNs, offer a significant advancement in predicting CRISPR-Cas9 off-target mutations.
• The developed algorithms provide enhanced precision necessary for safe and effective clinical gene editing.
• The study provides open-source code and datasets for further research and development.