An overview of CRISPR-artificial intelligence theranostics: Current and emerging applications

Area of Science:

• Biotechnology and Biomedical Engineering
• Genomics and Molecular Biology
• Artificial Intelligence in Healthcare

Background:

• CRISPR-based diagnostics offer sensitive detection of biomarkers for precision medicine.
• Traditional CRISPR diagnostics have limitations in multiplexing, off-target effects, and delivery.
• CRISPR-based theranostics aim to combine disease detection with targeted therapy.

Purpose of the Study:

• To review the evolution of CRISPR-AI theranostic systems.
• To explore current and emerging point-of-care diagnostic test (POCT) applications.
• To highlight challenges in translating CRISPR-AI theranostics into clinical practice.

Main Methods:

• Integration of artificial intelligence (AI) for intelligent guide RNA (gRNA) design and biosensor output interpretation.
• Development of advanced biosensors using CRISPR with nanomaterials, fluorescence, and electrochemical sensing.
• Utilizing machine learning tools (e.g., DeepCRISPR, Azimuth 2.0) for specificity and personalized genome editing.

Main Results:

• AI significantly enhances CRISPR platforms, improving specificity and reducing off-target events.
• Advanced biosensors detect a wide range of disease biomarkers, enabling diagnostics and gene therapy.
• CRISPR-AI facilitates accurate, low-cost testing in various settings, including point-of-care and resource-limited environments.

Conclusions:

• The integration of AI and CRISPR accelerates biomarker discovery and the development of adaptive therapeutic platforms.
• CRISPR-AI POCTs are crucial for early screening of high-mortality diseases.
• CRISPR-based diagnostics offer rapid, programmable, and portable alternatives to traditional nucleic acid tests, with ongoing challenges in clinical translation.