Artificial Intelligence for Predictive Modeling in CRISPR/Cas9 Gene Editing: a Survey of Methods and Design...

Area of Science:

• Genomics
• Bioinformatics
• Computational Biology

Background:

• CRISPR-Cas systems and their variants have revolutionized genome editing.
• Artificial intelligence (AI) and machine learning (ML) are increasingly integrated into biological research.

Purpose of the Study:

• To provide an integrative survey of computational developments in AI-mediated genome editing.
• To evaluate AI/ML methodologies, data strategies, and applications in various biomedical fields.
• To address challenges in model interpretability, ethics, and clinical translation.

Main Methods:

• Review and synthesis of predictive algorithms and deep learning frameworks for genome editing.
• Analysis of data-centric strategies and sequence-encoding representations.
• Evaluation of AI/ML applications in oncology, neurology, rare diseases, and precision medicine.

Main Results:

• AI/ML significantly enhances specificity, throughput, and predictive capacity in genome editing.
• Identified key areas for improvement including dataset biases and model interpretability.
• Developed a taxonomy for AI-mediated genome editing approaches.

Conclusions:

• AI holds substantial potential to advance secure, effective, and accessible genome engineering.
• Further research is needed to overcome current constraints for clinical translation.
• AI integration promises to refine therapeutic design and accelerate biomedical research.