AI-driven cellular immunotherapy: transforming CAR-T engineering and translation.

Area of Science:

• Oncology
• Immunotherapy
• Bioengineering

Background:

• Chimeric antigen receptor T (CAR-T) cell therapy shows promise in blood cancers but faces hurdles in solid tumors.
• Challenges include target specificity, antigen expression variability, unpredictable outcomes, and complex manufacturing.

Purpose of the Study:

• To review how artificial intelligence (AI) is transforming CAR-T cell therapy engineering.
• To explore AI applications across the CAR-T development pipeline, from discovery to manufacturing.

Main Methods:

• Review of AI approaches (machine learning, deep learning, generative models) in CAR-T engineering.
• Analysis of AI's role in antigen discovery, CAR design, functional prediction, and manufacturing optimization.

Main Results:

• AI facilitates data-driven identification of tumor-specific targets using multi-omics and clinical data.
• AI aids in designing antigen-recognition modules and programming CAR architectures.
• AI improves prediction of CAR-T performance, efficacy, and clinical outcomes.
• AI streamlines manufacturing, quality control, and process optimization through advanced analytics.

Conclusions:

• AI is shifting CAR-T engineering from empirical methods to programmable, predictive, and autonomous frameworks.
• These AI-driven advances promise to accelerate the development of safer and more effective CAR-T immunotherapies.